An intelligent government service method and terminal based on OCR recognition technology

Abstract

The present application relates to the field of electronic government technology, and in particular to an intelligent government service method and terminal based on OCR recognition technology. The method comprises: obtaining a document image data set, performing degradation recognition processing on each document image in the document image data set, and determining the degradation area information; based on the degradation area information, analyzing the document image data set, and determining the document content multidimensional information set; obtaining government process information, and based on the government process information, performing logical association analysis on the document content multidimensional information set, and determining the association analysis results; based on the association analysis results, performing markup error correction on the document content multidimensional information set, and determining and outputting a document processing report. The present application improves the comprehensive processing capability of the electronic processing process of government documents based on OCR technology for documents in the government service field with high input complexity and strong business logic coupling, and reduces the frequency of intervention of relevant staff in the government service process.

Description

Technical Field

[0001] The present application relates to the field of e-government technology, and in particular to an intelligent government service method and terminal based on OCR recognition technology. Background Art

[0002] With the comprehensive and in-depth development of information technology, the pace of digital transformation of government services is accelerating. OCR (Optical Character Recognition) technology has been widely used in the digitization of paper documents in government services, effectively improving the processing efficiency of government affairs and promoting the informatization development of government services.

[0003] However, when existing OCR technology is applied to government service systems, it can usually only realize the conversion between images and text. It lacks the comprehensive processing capabilities for documents in the government service field with high input complexity and strong business logic coupling. As a result, the government service process still requires frequent intervention from relevant staff, and its auxiliary role in the efficient processing of government services is very limited. Summary of the Invention

[0004] This application provides an intelligent government service method and terminal based on OCR recognition technology to solve the above technical problems.

[0005] In the first aspect, the present application provides an intelligent government service method based on OCR recognition technology, the method comprising: obtaining a document image data set, performing degradation recognition processing on each document image in the document image data set, and determining the degradation area information; based on the degradation area information, analyzing the document image data set, and determining a multidimensional information set of document content; obtaining government process information, and based on the government process information, performing logical association analysis on the multidimensional information set of document content, and determining the association analysis result; based on the association analysis result, performing marked error correction on the multidimensional information set of document content, and determining and outputting a document processing report.

[0006] Through this solution, the degraded areas in the document image are identified and processed to obtain the degraded area information. On this basis, the document content multidimensional information set containing each document element and the corresponding complementary content is analyzed and obtained. Combined with the government process information, the document content multidimensional information set is logically associated with the analysis. According to the obtained analysis results, the document content multidimensional information set is marked and corrected, and the corresponding document processing report is provided to the corresponding government service personnel for their rapid approval and modification. This improves the comprehensive processing capability of the electronic processing process of government documents based on OCR technology for documents in the government service field with high input complexity and strong business logic coupling, reduces the frequency of intervention of relevant staff in the government service process, improves the efficiency of government services, and promotes the digitalization of government services.

[0007] Optionally, the degradation recognition processing is performed on each document image in the document image data set to determine the degradation area information, including: analyzing the document image data set to extract several feature degradation areas of each document image; based on the image convolutional neural network model, extracting several image feature vectors corresponding to the feature degradation areas, and performing feature degradation type probability distribution analysis on each image feature vector to determine the degradation distribution probability of each feature degradation area under each feature degradation type; the feature degradation types include creases, fading, stains and missing; based on a preset degradation classification minimization loss function, according to the degradation distribution probability of each feature degradation area under each feature degradation type, the feature degradation type corresponding to each feature degradation area is determined; according to each feature degradation area and its corresponding feature degradation type, the degradation area information is constructed.

[0008] Through this solution, the multi-scale feature fusion analysis process is utilized to accurately analyze the feature degradation types corresponding to different feature degradation areas, effectively solve the confusion problem of similar degradation features, and significantly improve the accuracy of degradation type identification in complex degradation scenarios. It provides scientific data basis for subsequent targeted completion analysis of fuzzy document content under different feature degradation types, and reduces the risk of error propagation in the subsequent document completion process.

[0009] Optionally, the preset degradation classification minimization loss function is specifically the following formula:

[0010] ;

[0011] in, is the cross entropy loss, is the degenerate type index, is the total number of degenerate types, For the The historical frequency of occurrence of degradation types, For the A vector of preset type labels for the degenerate types, For the The degradation distribution probability of each degradation type.

[0012] Through this scheme, based on mathematical analysis methods, a preset degradation classification minimization loss function is constructed, and the difference between the degradation distribution probability of the current degradation area under different degradation types analyzed by the image convolutional neural network model and the distribution probability of the document's historical degradation characteristics is measured. The cross-entropy loss minimization optimization process is used to improve the accuracy of the degradation distribution probability, thereby improving the accuracy of the degradation type analysis process to which the degradation area belongs.

[0013] Optionally, the document image data set is analyzed based on the degraded area information to determine a multidimensional information set of document content, including: analyzing the document image data set, identifying and determining the document layout structure area, the text area and the additional mark area in each document image in the document image data set, and extracting the document content in each document area; based on the degraded area information, determining a number of cross-fuzzy areas and their corresponding document areas according to the intersection area between the feature degraded area and the document layout structure area / the text area / the additional mark area; based on the feature degradation type and the document area to which the cross-fuzzy area belongs, performing inference completion analysis on the cross-fuzzy area according to the document content corresponding to the document area, and determining the corresponding information to be completed in each cross-fuzzy area; constructing the document content multidimensional information set according to the document content in each document area and the information to be completed in each cross-fuzzy area.

[0014] Through this solution, the document layout structure area, text area and additional markup area in the document are accurately divided, laying the foundation for the completion analysis process and improving the document area sensitivity of the completion analysis process. By targeting the document areas to which different feature degradation types and cross-fuzzy areas belong, and according to the document content corresponding to the document areas, targeted reasoning completion analysis strategies are adopted for different cross-fuzzy areas to obtain the information to be completed corresponding to each cross-fuzzy area, thereby improving the regional matching degree and accuracy of the information to be completed.

[0015] Optionally, the document area to which the feature degradation type and the cross-fuzzy area belong is subjected to an inferential completion analysis based on the document content corresponding to the document area to determine the information to be completed corresponding to each cross-fuzzy area, including: if the document area is the document layout structure area, extracting the overall layout structure outline of the document based on the document content corresponding to the document layout structure area; searching a preset document template database based on the overall layout structure outline of the document to determine whether there is a corresponding document template; if the document template exists, taking the differentiated contour edge between the overall layout structure outline of the document and the corresponding document template as the information to be completed; if the document template does not exist, based on the graph neural network, performing a line continuity completion analysis on the overall layout structure outline of the document based on the feature degradation type to determine the completion structure lines of the cross-fuzzy area, and taking the completion structure lines as the information to be completed.

[0016] Through this solution, the overall layout structure outline of the document corresponding to the document layout structure area is extracted, and this is used as the retrieval basis to search the preset document template database. If the document template exists, the differentiated outline edge between the overall layout structure outline of the document and the corresponding document template is used as the information to be completed, reducing the occupation of computing resources. If the document template does not exist, the overall layout structure outline of the document is subjected to line continuity completion analysis according to the feature degradation type, and the corresponding completed structure lines are used as the information to be completed, thereby improving the matching degree between the completed content and the non-standard document, and improving the flexibility and accuracy of the layout structure completion analysis process.

[0017] Optionally, the document area to which the feature degradation type and the cross-fuzzy area belong is subjected to an inferential completion analysis based on the document content corresponding to the document area to determine the information to be completed corresponding to each cross-fuzzy area, including: if the document area to which the feature degradation type and the cross-fuzzy area are applied, edge feature analysis is performed on the text information in the text area according to an image edge detection algorithm to determine printed information and handwritten information; based on an image edge detection algorithm, the handwritten information is analyzed to determine a handwriting feature set; based on a preset feature point descriptor, the handwriting feature set is analyzed to determine a handwriting feature vector; based on the handwriting feature vector, a handwriting analogy analysis is performed on the handwriting information to determine handwritten text semantic information; based on the handwriting feature vector, a contextual semantic continuity analysis is performed on the printed information and the handwritten text semantic information to determine semantic continuity guarantee completion information, and the semantic continuity guarantee completion information is used as the information to be completed.

[0018] Through this solution, the printed information and handwritten information in the text area are separated, and the semantic information of the handwritten text is determined by analyzing and extracting the note features of the handwritten text. Based on natural language analysis technology, contextual semantic continuity analysis is performed on the printed information and the handwritten text semantic information to determine the semantic continuity guarantee completion information, and the semantic continuity guarantee completion information is used as the information to be completed, avoiding the propagation of errors caused by the mixed processing of handwritten and printed text, and improving the adaptability of the completion analysis process to diverse documents.

[0019] Optionally, the document area to which the cross-fuzzy area belongs based on the feature degradation type and the cross-fuzzy area is subjected to an inferential completion analysis according to the document content corresponding to the cross-fuzzy area, and the corresponding information to be completed in each cross-fuzzy area is determined, including: if the document area is the additional mark area, dividing and extracting the background semi-transparent watermark content and the foreground dark seal content according to the document content corresponding to the additional mark area; analyzing the background semi-transparent watermark content, extracting the watermark unit content, and determining the unit to which the document belongs; analyzing the foreground dark seal content, and determining the document approval unit; sending the document verification information to the corresponding unit according to the document unit and the document approval unit, and receiving the verification feedback information and the target seal image provided by the corresponding unit; if the verification feedback information is that the verification is correct, then taking the difference contour between the watermark unit content and the cross-fuzzy area as the information to be completed, and at the same time taking the difference contour between the target seal image and the foreground dark seal content as the information to be completed.

[0020] Through this solution, the watermark content and seal content in the additional mark area are separated to clarify the unit to which the current document belongs and the approval unit, and document verification information is sent to the corresponding unit. After determining that the verification feedback information is correct, the difference outline between the watermark unit content and the cross-fuzzy area is used as the information to be completed. At the same time, the difference outline between the target seal image and the foreground dark seal content is used as the information to be completed. While avoiding document tampering and forgery, accurate analysis of the watermark and seal content completion information is achieved.

[0021] Optionally, the government affairs process information includes a government affairs process directed graph, a government affairs rule logical expression set, government affairs timeliness information and a government affairs responsibility matrix. Based on the government affairs process information, a logical association analysis is performed on the multidimensional information set of the document content to determine the association analysis result, including: based on the multidimensional information set of the document content, according to the information to be completed in each cross-fuzzy area, the document content in each document area is completed to determine the completed document content; based on the natural language analysis algorithm, the completed document content is analyzed to determine the document government affairs process, document government affairs rules, document government affairs timeliness information and document government affairs responsibility Subject; according to the government affairs process directed graph, perform a topological matching evaluation on the document government affairs process to determine the topological matching degree of the process node; according to the government affairs rule logical expression set, perform rule compliance verification on the document government affairs rule to determine the rule matching degree; according to the government affairs timeliness information, perform timeliness verification on the document government affairs timeliness information to determine the timing matching degree; according to the government affairs responsibility matrix, perform a cosine similarity evaluation on the document government affairs responsible subject to determine the responsibility matching degree; according to the process node topological matching degree, the rule matching degree, the timing matching degree and the responsibility matching degree, construct the association analysis result.

[0022] Through this solution, based on government process information, starting from the four dimensions of process, rules, timeliness and responsibility, a logical correlation analysis is performed on the multidimensional information set of document content. Through the four quantitative indicators of process node topology matching, rule matching, timing matching and responsibility matching, the matching degree between the multidimensional information set of document content and the corresponding government process information in different dimensions is mapped respectively. This is used as the correlation analysis result to improve the scientificity and comprehensiveness of the logical correlation analysis process.

[0023] Optionally, based on the association analysis results, the multidimensional information set of the document content is marked and corrected, including: comparing the process node topology matching degree, the rule matching degree, the timing matching degree and the responsibility matching degree in the association analysis results with the corresponding matching degree ranges respectively; if there is a situation where the process node topology matching degree / the rule matching degree / the timing matching degree / the responsibility matching degree is not within the corresponding matching degree range, extracting the corresponding abnormal matching degree; based on the color-differentiated document annotation strategy and the government process information, according to the abnormality type corresponding to the abnormal matching degree, the local content of the document corresponding to the abnormal matching degree is highlighted, and the corresponding adjustment suggestions are determined.

[0024] Through this solution, accurate positioning and efficient correction of errors in government documents are achieved through matching comparison and visual annotation. The color differentiation strategy reduces the complexity of manual review, and the highlighted annotations directly point to the problem areas. Combined with targeted adjustment suggestions, the standardization and efficiency of government processing procedures are significantly improved. At the same time, through automated anomaly detection and prompts, compliance risks caused by omissions or misjudgments are reduced, ensuring that the document content is highly consistent with government process requirements.

[0025] In the second aspect, the present application provides an intelligent government service terminal based on OCR recognition technology, and the terminal includes: a degradation analysis module, which is used to obtain a document image data set, perform degradation recognition processing on each document image in the document image data set, and determine the degradation area information; a document analysis module, which is used to analyze the document image data set based on the degradation area information, and determine the document content multidimensional information set; an association analysis module, which is used to obtain government process information, perform logical association analysis on the document content multidimensional information set based on the government process information, and determine the association analysis result; a document marking module, which is used to perform marked error correction on the document content multidimensional information set according to the association analysis result, and determine and output a document processing report. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0027] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0028] Figure 2 A flowchart of an intelligent government service method based on OCR recognition technology provided in one embodiment of the present application;

[0029] Figure 3 A schematic diagram of the structure of an intelligent government service terminal based on OCR recognition technology provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0032] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0033] Based on this, the present application provides an intelligent government service method and terminal based on OCR recognition technology. The degraded area in the document image is identified and processed to obtain the degraded area information. On this basis, a document content multidimensional information set containing each document element and the corresponding complementary content is analyzed and obtained. In combination with the government process information, a logical correlation analysis is performed on the document content multidimensional information set. According to the obtained visit analysis results, the document content multidimensional information set is marked and corrected, and the corresponding document processing report is provided to the corresponding government service personnel for their rapid approval and modification. This improves the comprehensive processing capability of the electronic processing process of government documents based on OCR technology for documents in the government service field with high input complexity and strong business logic coupling, reduces the frequency of intervention of relevant staff in the government service process, improves the efficiency of government services, and promotes the digitalization of government services.

[0034] Figure 1 This is a schematic diagram of an application scenario provided by this application. The method provided by this application is applied in the process of electronic government documents. Highly complex government service documents with strong business logic coupling are input for comprehensive processing, improving government service efficiency and reducing the involvement of relevant staff.

[0035] Specifically, the method of the present application is applied to any server that communicates with a document scanning device, obtains and analyzes a document image data set through the server, identifies and processes the degraded area in the document image, and obtains the degraded area information. On this basis, a multidimensional information set of the document content containing each document element and the corresponding complementary content is analyzed and obtained. Combined with the government process information, a logical association analysis is performed on the multidimensional information set of the document content. Based on the obtained visit analysis results, the multidimensional information set of the document content is marked and corrected, and the corresponding document processing report is provided to the corresponding government service personnel for their rapid approval and modification, thereby improving the comprehensive processing capability of the electronic processing process of government documents based on OCR technology for documents in the government service field with high input complexity and strong business logic coupling, reducing the frequency of intervention of relevant staff in the government service process, improving the efficiency of government services, and promoting the digitalization of government services.

[0036] For specific implementation methods, please refer to the following embodiments.

[0037] Figure 2 This is a flowchart of an intelligent government service method based on OCR recognition technology provided in one embodiment of this application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0038] S201: Acquire a document image dataset, perform degradation recognition processing on each document image in the document image dataset, and determine degradation area information.

[0039] Document image datasets can be collections of images corresponding to various document files involved in government service processing. Document image datasets can be acquired using document scanning devices. Degradation recognition processing can identify degraded features in documents that may obscure local document information, such as creases and stains. Degraded region information can be information about regions within a document affected by these degraded features.

[0040] Specifically, in the process of government affairs processing, paper documents are affected by factors such as storage time and the owner's storage method, and the clarity of their document content is highly uncertain. In addition, in the process of government affairs processing, affected by historical problems, the document digitization process often needs to face a large number of old paper documents, such as archival files. When existing OCR technology processes old documents in the process of government affairs, since the content of government documents involves complex and numerous document elements, such as form structure, seals, watermarks, etc., and old documents are affected by storage conditions and time, their document content has different degrees of degradation. Existing OCR technology is difficult to ensure the accuracy and completeness of the content of old documents in the process of document digitization. Through mathematical analysis, degradation recognition processing is performed on different document images, and the areas affected by degradation and their corresponding degradation types in different documents are determined, providing a scientific data basis for subsequent analysis and completion of document content in the degraded area.

[0041] S202: Analyze the document image data set based on the degraded region information to determine a document content multidimensional information set.

[0042] The document content multidimensional information set may be an information set containing different types of document components, such as document structure, printed parts, handwritten parts, etc.

[0043] Specifically, government documents are composed of a large number of different types of document elements. Different document elements require different document content completion methods after being affected by degenerate areas. For example, after the document structure is affected by the degenerate area, since the document structure is mainly composed of different continuous wireframes and does not involve specific text content, the completion of the document structure is mainly achieved by the completion analysis of the continuity of the structural lines. If the document body content is affected by the degenerate area, it is necessary to use natural language analysis technology, combined with the contextual information around the degenerate area, to infer the text information in the degenerate area to achieve the completion of the text content. Therefore, based on the degenerate area information, the document content in different document images in the document image dataset is structurally divided to determine the different dimensional document elements affected by the degenerate area in the document and the corresponding completion information of the document elements, thereby forming a multi-dimensional information set of document content as a targeted basis in the document completion analysis process.

[0044] S203: Obtain government affairs process information, perform logical association analysis on the document content multi-dimensional information set based on the government affairs process information, and determine the association analysis result.

[0045] The government affairs process information may be information used to characterize the relationship between nodes in the current government affairs process.

[0046] Logical association analysis can be an analysis process of whether there is a logical conflict between the document content in the current document content multidimensional information set and the government process based on the corresponding government process.

[0047] The association analysis result may be information including different types of logical conflict analysis results.

[0048] Specifically, after the analysis and completion of the old document content, although it can ensure that the document content is smooth in terms of textual semantics, it does not mean that the completed document content is logically completely matched with the corresponding government process. For example, the registration certificate is very old and there is no corresponding electronic file. After scanning with existing OCR technology, some fields are blurred. After completion through the above steps, the accuracy of some basic general information can be guaranteed, but some approval process descriptions and approval agency responsibilities involved in the completed document may have logical conflicts with the government process corresponding to the document, and there will be conflicts in the document's responsible parties. Therefore, after completing the document, it is necessary to refer to the corresponding government process and conduct a logical correlation analysis on the multi-dimensional information set of the document content to avoid logical conflicts in government processes.

[0049] S204: Based on the association analysis results, markup error correction is performed on the document content multidimensional information set, and a document processing report is determined and output.

[0050] Marking-based error correction can be the process of marking portions of a multidimensional document content information set that contain logical conflicts in government processes and providing correction suggestions. A document processing report can be a report containing a series of corresponding changes in the document content during the current government document processing process.

[0051] Specifically, through the results of correlation analysis, the logical conflict parts of the government process in the completed document content are located, and according to the corresponding government process information, the logical conflict parts are marked, and corresponding error correction suggestions are given. Through data visualization technology, the corresponding document processing report is constructed and provided to the corresponding government service personnel for their quick approval and modification.

[0052] Through this solution, the degraded areas in the document image are identified and processed to obtain the degraded area information. On this basis, the document content multidimensional information set containing each document element and the corresponding complementary content is analyzed and obtained. Combined with the government process information, the document content multidimensional information set is logically associated with the analysis. According to the obtained analysis results, the document content multidimensional information set is marked and corrected, and the corresponding document processing report is provided to the corresponding government service personnel for their rapid approval and modification. This improves the comprehensive processing capability of the electronic processing process of government documents based on OCR technology for documents in the government service field with high input complexity and strong business logic coupling, reduces the frequency of intervention of relevant staff in the government service process, improves the efficiency of government services, and promotes the digitalization of government services.

[0053] In some embodiments, a document image data set is analyzed to extract several feature degradation regions of each document image; based on an image convolutional neural network model, image feature vectors corresponding to the several feature degradation regions are extracted, and a feature degradation type probability distribution analysis is performed on each image feature vector to determine the degradation distribution probability of each feature degradation region under each feature degradation type; feature degradation types include creases, fading, stains, and missing; based on a preset degradation classification minimization loss function, the feature degradation type corresponding to each feature degradation region is determined according to the degradation distribution probability of each feature degradation region under each feature degradation type; and degradation region information is constructed based on each feature degradation region and its corresponding feature degradation type.

[0054] A feature degradation region may be a local area in a document image where visual quality degrades, specifically a set of continuous pixels with abnormal pixel values, broken textures, or missing content. The feature degradation region can be divided into regions of the document image using an image segmentation algorithm (such as a threshold segmentation method based on edge detection), and the region with poor visual quality can be screened out as a feature degradation region.

[0055] The image convolutional neural network model can be a feature extraction network modified from the ResNet-34 architecture. Its input layer receives image patches of degraded regions normalized to corresponding pixels (e.g., 224×224 pixels). After extracting spatial features through several convolutional modules (e.g., five convolutional modules), a global average pooling layer outputs an image feature vector of a specified dimension (e.g., 1024 dimensions). This image feature vector can be used to represent the comprehensive image features within the feature-degraded region.

[0056] The feature degradation type probability distribution analysis may be a process of analyzing the probability corresponding to each degradation type of the current feature degradation region. The degradation distribution probability may be a probability distribution value of the current feature degradation region under each degradation type.

[0057] The preset degradation classification minimization loss function may be a mathematical function used to measure the difference between an assessment of the feature degradation type within the degradation region by the image convolutional neural network model and the actual situation. The feature degradation type may be a degradation cause that causes blurring of document data within the current feature degradation region.

[0058] Specifically, in the process of digitizing paper documents, especially for old documents, due to differences in document preservation status, there is a common phenomenon of mixed existence of multiple degradation types in the image. The traditional single threshold detection method is difficult to accurately distinguish similar degradation features such as creases and stains, fading and missing. The image convolutional neural network model is used to quantitatively analyze the probability distribution value of each image feature vector under different degradation types. Combined with the preset degradation classification minimization loss function, the difference between the evaluation result and the actual situation is minimized, thereby determining the feature degradation type corresponding to each feature degradation area, and fusing multi-scale features to enhance the ability to distinguish the feature degradation type corresponding to the feature degradation area, providing scientific data basis for the subsequent targeted completion analysis of fuzzy document content under different feature degradation types.

[0059] Through this solution, the multi-scale feature fusion analysis process is utilized to accurately analyze the feature degradation types corresponding to different feature degradation areas, effectively solve the confusion problem of similar degradation features, and significantly improve the accuracy of degradation type identification in complex degradation scenarios. It provides scientific data basis for subsequent targeted completion analysis of fuzzy document content under different feature degradation types, and reduces the risk of error propagation in the subsequent document completion process.

[0060] In some embodiments, a degradation classification minimization loss function is preset, specifically the following formula (1):

[0061] ;

[0062] in, is the cross entropy loss, is the degenerate type index, is the total number of degenerate types, For the The historical frequency of occurrence of degradation types, For the A vector of preset type labels for the degenerate types, For the The degradation distribution probability of each degradation type.

[0063] Cross entropy loss can be a quantitative value used to characterize the difference between the model's predicted probability distribution and the true distribution.

[0064] The historical occurrence frequency can be the frequency of various degradation phenomena calculated based on statistics from a government document database. The historical occurrence frequency of various degradation types in government documents generally follows the following pattern: fade > crease > stain > loss. The preset type label vector can be a vector representing the degradation type. The preset type label vector can be represented using one-hot encoding, such as [1, 0, 0, 0] for crease and [0, 1, 0, 0] for fade.

[0065] Specifically, the difference between the degradation distribution probability of the current degradation area under different degradation types obtained by the image convolutional neural network model and the distribution probability of the document's historical degradation characteristics is measured by formula (1). By introducing the historical occurrence frequency of each type as its influence weight and combining it with the degradation characteristics of government documents, the influence weight of the high-frequency type is reduced, and the model's attention to the low-frequency degradation type is enhanced. The cross-entropy loss minimization optimization process is used to improve the accuracy of the degradation distribution probability, thereby improving the accuracy of the degradation type analysis process to which the degradation area belongs.

[0066] Through this scheme, based on mathematical analysis methods, a preset degradation classification minimization loss function is constructed, and the difference between the degradation distribution probability of the current degradation area under different degradation types analyzed by the image convolutional neural network model and the distribution probability of the document's historical degradation characteristics is measured. The cross-entropy loss minimization optimization process is used to improve the accuracy of the degradation distribution probability, thereby improving the accuracy of the degradation type analysis process to which the degradation area belongs.

[0067] In some embodiments, a document image data set is analyzed, the document layout structure area, the main text area and the additional mark area in each document image in the document image data set are identified and determined, and the document content in each document area is extracted; based on the degraded area information, a number of cross-fuzzy areas and their corresponding document areas are determined according to the intersection area between the feature degraded area and the document layout structure area / main text area / additional mark area; based on the feature degradation type and the document area to which the cross-fuzzy area belongs, according to the document content corresponding to the document area, an inference-based completion analysis is performed on the cross-fuzzy area to determine the corresponding information to be completed in each cross-fuzzy area; based on the document content in each document area and the information to be completed in each cross-fuzzy area, a multidimensional information set of document content is constructed.

[0068] The document layout structure area can be the framework area used to define the overall layout of a document, such as headers, footers, table borders, column dividers, and other structural document elements. The body area can be the continuous area within a document that carries the core text information and can include printed or handwritten text. The additional markup area can be special identification areas within a document that have legal effect, such as company watermarks, approval stamps, and signature areas.

[0069] Document content can be the document element content corresponding to different document regions. The intersection region can be the overlap between the distribution of different document regions and the feature degradation region. The document region can be the document region where each intersection region is located. Inferential completion analysis can be the process of reconstructing degraded content through multimodal information fusion based on document context semantics, structural features, and degradation type.

[0070] The information to be completed may be document information that needs to be completed in the intersection area.

[0071] Specifically, existing OCR-based document completion technologies lack document region sensitivity, making it difficult to perform targeted completion processing on the layout area, text area, and markup area in government documents, resulting in low completion accuracy. This solution is based on the Mask R-CNN model with ResNet-101 as the backbone network. It outputs instance segmentation masks of document images, demarcates the corresponding document layout structure area, and uses the connected domain analysis method to detect text lines in non-layout areas and demarcate the corresponding text area. Furthermore, based on color space analysis algorithms (such as HSV channels) and shape matching algorithms, the corresponding additional markup areas are demarcated. The overlapping areas between feature degradation areas and the corresponding document layout structure areas / text areas / additional markup areas are regarded as cross-fuzzy areas. Based on the feature degradation type and the document area to which the cross-fuzzy areas belong, and according to the document content corresponding to the document area, targeted reasoning-time completion analysis strategies are adopted for different cross-fuzzy areas. The information to be completed corresponding to each cross-fuzzy area is obtained, and the document content in each document area and the information to be completed in each cross-fuzzy area are then integrated to construct a multi-dimensional information set of document content.

[0072] Through this solution, the document layout structure area, text area and additional markup area in the document are accurately divided, laying the foundation for the completion analysis process and improving the document area sensitivity of the completion analysis process. By targeting the document areas to which different feature degradation types and cross-fuzzy areas belong, and according to the document content corresponding to the document areas, targeted reasoning completion analysis strategies are adopted for different cross-fuzzy areas to obtain the information to be completed corresponding to each cross-fuzzy area, thereby improving the regional matching degree and accuracy of the information to be completed.

[0073] In some embodiments, if the document area is a document layout structure area, the overall layout structure outline of the document is extracted based on the document content corresponding to the document layout structure area; based on the overall layout structure outline of the document, a preset document template database is retrieved to determine whether a corresponding document template exists; if a document template exists, the differentiated outline edge between the overall layout structure outline of the document and the corresponding document template is used as information to be completed; if a document template does not exist, based on a graph neural network, according to the feature degradation type, a line continuity completion analysis is performed on the overall layout structure outline of the document, and the completed structural lines of the cross-fuzzy area are determined, and the completed structural lines are used as information to be completed.

[0074] The overall document layout structure outline may be an outline of lines constituting the document layout structure.

[0075] The preset document template database may be a preset database for storing various government document templates.

[0076] The corresponding document template may be a document template from a preset document template database that has the same overall layout structure outline as the current document. The differentiated outline edge may be the difference between the overall layout structure outline of the document and the structure outline in the corresponding document template, i.e., the missing portion of the layout structure in the current document. The line continuity completion analysis may be a document completion analysis process aimed at ensuring the continuity of the layout structure lines.

[0077] Specifically, in the process of completing the analysis of the document layout structure, since the document layout structure is usually composed of different types of continuous wireframes and does not involve specific deep meanings, the main focus is on the analysis of the document layout structure contour. Through image analysis algorithms such as edge detection algorithms, the geometric features of the document layout structure area (such as table borders, paragraph boundaries, and title bar edges) are identified, and the overall document layout structure contour containing lines, rectangular frames, and text block positions is extracted. The overall document layout structure contour is matched with various document templates in the preset document template database for similarity. The similarity matching process can be based on the coordinate distribution and topological relationship of contour key points (such as corner points and intersection points). Calculate the structural similarity score. If there is a template whose matching score exceeds the preset threshold, it is determined that the corresponding document template exists, otherwise it is determined that it does not exist. If a corresponding template exists, the overall layout structure outline of the document is superimposed and compared with the standardized outline of the corresponding template, and the differences between the two in edge direction, line length and connection point position are extracted to generate differentiated contour edges as the information to be completed. If there is no corresponding template, a graph structure with layout structure lines as nodes and line connection relationships as edges is constructed. The pre-trained graph neural network model (such as GCN, GAT) is used to analyze the topological dependency between nodes, predict the direction and connection method of missing lines, and generate completed structure lines as the information to be completed.

[0078] Through this solution, the overall layout structure outline of the document corresponding to the document layout structure area is extracted, and this is used as the retrieval basis to search the preset document template database. If the document template exists, the differentiated outline edge between the overall layout structure outline of the document and the corresponding document template is used as the information to be completed, reducing the occupation of computing resources. If the document template does not exist, the overall layout structure outline of the document is subjected to line continuity completion analysis according to the feature degradation type, and the corresponding completed structure lines are used as the information to be completed, thereby improving the matching degree between the completed content and the non-standard document, and improving the flexibility and accuracy of the layout structure completion analysis process.

[0079] In some embodiments, if the document area is a text area, edge feature analysis is performed on the text information in the text area based on an image edge detection algorithm to determine the printed information and handwritten information; based on the image edge detection algorithm, the handwritten information is analyzed to determine a handwriting feature set; based on a preset feature point descriptor, the handwriting feature set is analyzed to determine a handwriting feature vector; based on the handwriting feature vector, a handwriting analogy analysis is performed on the handwriting information to determine the semantic information of the handwritten text; based on a natural language analysis algorithm, contextual semantic continuity analysis is performed on the printed information and the handwritten text semantic information to determine semantic continuity guarantee completion information, and the semantic continuity guarantee completion information is used as the information to be completed.

[0080] Printed text can be standardized text generated by a printing device within a document, with regular font shapes and spacing. Handwritten text can be handwritten text within a document, with font shapes and handwriting varying from person to person. A handwriting feature set can be unique handwriting attributes extracted from handwriting, such as stroke characteristics, connective strokes, and tilt angles.

[0081] The preset feature point descriptor can be a quantitative model used to quantitatively describe key local features of handwriting. The preset feature point descriptor can adopt the SIFT descriptor (Scale-Invariant Feature Transform). The handwriting feature vector can be a numerical vector obtained by transforming the note features using the preset feature point descriptor. The handwritten text semantic information can be the handwritten text content and its semantic meaning restored based on handwriting analysis. Contextual semantic continuity analysis can be a document content completion process that ensures that the completed content maintains consistency with the original text in terms of grammar, logic, and themes. Semantic continuity ensures that the completed information can be completed content obtained through contextual reasoning and consistent with the original text's semantics.

[0082] Specifically, printed and handwritten characters often coexist in government documents. The processing logic of printed and handwritten characters is significantly different. Printed characters have fixed fonts and can be directly recognized by OCR; while handwritten characters require personalized handwriting analysis. If they are not distinguished, completion errors will occur (such as misapplying printed character rules to handwritten characters). Handwritten character completion depends on individual handwriting features and uses image edge detection algorithms, such as the Canny edge detection algorithm, to evaluate the regularity of the text contour in the text area. If the contour regularity is higher than the threshold (such as curvature variance < 0.1, spacing standard deviation < 5 pixels), it is marked as printed. If the contour is irregular (such as curvature variance ≥ 0.1), it is marked as The handwriting is recorded as handwriting, and its connected domain is extracted. The following features are extracted from each handwriting connected domain: the stroke inclination angle is detected through Hough transform to extract the stroke direction feature, the writing force is inferred based on the change of stroke width to extract the pen pressure feature, and the topological relationship between the connection points of the strokes is analyzed to extract the connection feature. The above features are encoded into a handwriting feature vector of a specified dimension (such as 128 dimensions) using the preset SIFT feature point descriptor. Based on the handwriting feature vector, the handwriting information in the document body area is converted into handwriting recognition to determine the text information corresponding to the handwriting. The text information is then contextually semantically parsed using a natural language analysis model, such as the BERT model (Bidirectional Encoder Representations from Transformers, based on transformers), to determine the semantic information of the handwriting text. The natural language analysis model is further used to perform contextual semantic continuity analysis on the printed information and the handwritten text semantic information to detect semantic logical faults in the text. Based on the contextual semantic information of the location of the semantic logical fault and combined with the domain dictionary, semantic continuity guarantee completion information is generated as the information to be completed.

[0083] Through this solution, the printed information and handwritten information in the text area are separated, and the semantic information of the handwritten text is determined by analyzing and extracting the note features of the handwritten text. Based on natural language analysis technology, contextual semantic continuity analysis is performed on the printed information and the handwritten text semantic information to determine the semantic continuity guarantee completion information, and the semantic continuity guarantee completion information is used as the information to be completed, avoiding the propagation of errors caused by the mixed processing of handwritten and printed text, and improving the adaptability of the completion analysis process to diverse documents.

[0084] In some embodiments, if the document area is an additional mark area, the background semi-transparent watermark content and the foreground dark seal content are divided and extracted according to the document content corresponding to the additional mark area; the background semi-transparent watermark content is analyzed, and the watermark unit content is extracted to determine the unit to which the document belongs; the foreground dark seal content is analyzed to determine the document approval unit; according to the document unit and the document approval unit, the document verification information is sent to the corresponding unit, and the verification feedback information and the target seal image provided by the corresponding unit are received; if the verification feedback information is that the verification is correct, the difference outline between the watermark unit content and the cross-fuzzy area is used as the information to be completed, and the difference outline between the target seal image and the foreground dark seal content is used as the information to be completed.

[0085] The background semi-transparent watermark content can be a low-transparency logo image superimposed on the bottom layer of the document, usually associated with the organization to which the document belongs. The foreground dark seal content can be a dark seal or signature covering the surface of the document, used to identify the approval organization or responsible person.

[0086] The watermark unit content can be the smallest unit of content that constitutes a document watermark. The document affiliation can be the organization to which the current document belongs, which can be determined through watermark content analysis. The document approval unit can be the organization that reviews and confirms the document content, identified through the seal content. Verification feedback information can be the watermark and seal verification results (such as "verified correct" or "verified abnormal") provided by the corresponding unit. The target seal image can be a standard seal image provided by the corresponding unit, used as a reference image information for seal completion.

[0087] The difference contour may be a shape difference contour between the cross-blurred area and the standard watermark / seal image.

[0088] Specifically, government documents usually contain non-text marking elements such as watermarks and seals, which are used to prove the legality and authority of the document and prevent the document content from being tampered with or forged. In the process of analyzing and completing document elements such as watermarks and seals as document markers, due to the different transparency and color depth of watermarks and seals, they need to be processed separately for accurate completion. Semi-transparent watermarks are easily affected by background interference, and dark seals require high-precision contour extraction. In addition, since watermarks and seals are used as document security identifiers, they cannot be completed directly, otherwise it is easy to cause document forgery loopholes. It is necessary to pass the verification of the unit to which the watermark or seal belongs before the mark completion in the electronic process can be carried out. The background and foreground of the document image are separated by image segmentation algorithms (such as the threshold method based on the HSV color space), the low-saturation background area is identified, and the low-saturation background area is binarized. Through OCR Identify and extract the corresponding repeated text as the background semi-transparent watermark content, and extract the watermark unit content from it, and at the same time identify the foreground high contrast area, use the edge tracking algorithm (such as Suzuki contour detection) to close the contour, and extract the foreground dark seal content. According to the watermark unit content and the foreground dark seal content, respectively retrieve the corresponding institutional units, package the corresponding document content as document verification information and send it to the corresponding structural unit, and receive the verification feedback information provided by the corresponding institutional unit. If the verification feedback information is a verification exception, the current document will be marked as a verification exception document and submitted for manual review. If the verification feedback information is that the verification is correct, then through the image edge detection algorithm, the difference contour between the watermark unit content and the cross-fuzzy area is used as the information to be completed, and the difference contour between the target seal image and the foreground dark seal content is also used as the information to be completed.

[0089] Through this solution, the watermark content and seal content in the additional mark area are separated to clarify the unit to which the current document belongs and the approval unit, and document verification information is sent to the corresponding unit. After determining that the verification feedback information is correct, the difference outline between the watermark unit content and the cross-fuzzy area is used as the information to be completed. At the same time, the difference outline between the target seal image and the foreground dark seal content is used as the information to be completed. While avoiding document tampering and forgery, accurate analysis of the watermark and seal content completion information is achieved.

[0090] In some embodiments, based on the multidimensional information set of the document content, the document content in each document area is completed according to the information to be completed in each cross-fuzzy area to determine the document content after completion; based on the natural language analysis algorithm, the completed document content is analyzed to determine the document government process, document government rules, document government timeliness information and document government responsibility subject; according to the government process directed graph, the document government process is topologically matched and evaluated to determine the topological matching degree of the process node; according to the government rule logical expression set, the document government rules are rule-compliantly verified to determine the rule matching degree; according to the government timeliness information, the document government timeliness information is time-validated to determine the timing matching degree; according to the government responsibility matrix, the document government responsibility subject is evaluated by cosine similarity to determine the responsibility matching degree; according to the process node topology matching degree, rule matching degree, timing matching degree and responsibility matching degree, the association analysis result is constructed.

[0091] Government process information includes a directed graph of government processes, a set of logical expressions for government rules, government timeliness information, and a government responsibility matrix. A directed graph of government processes can be a topological diagram describing the nodes and their execution order in a government process. Nodes represent approval steps, and directed edges represent the direction of the process. A set of logical expressions for government rules can be a set of rules connected by logical operators (AND / OR / NOT) that constrain government processing rules. Government timeliness information can be the time limits for each step in a government process. A government responsibility matrix can be a matrix that records the correspondence between each process node and the responsible entity, used to clarify the ownership of government processing rights and responsibilities. The completed document content can be the complete document information obtained by completing intersecting fuzzy regions within the document based on the information to be completed. Topological matching evaluation can be the process of evaluating the degree of match between the completed document process and the corresponding government process. This topological matching evaluation can be implemented using a directed graph topology matching algorithm. The process node topological matching degree can be a quantitative indicator of the structural similarity between the document's government process and the directed graph of government processes.

[0092] Rule compliance verification can be an evaluation process used to verify whether the content of a document complies with the rules specified in the government affairs process. Rule compliance verification converts the logical expression of the document's government affairs rules into conjunctive normal form (CNF) and performs a subset inclusion comparison with the set of government affairs rule logical expressions.

[0093] The rule matching degree can be a compliance score between the document government rules and the government rule logical expression.

[0094] Time validity verification can be an evaluation process for evaluating whether the time information in the current completed document complies with the time validity stipulated in the government affairs process. Time validity verification can be achieved by comparing the timestamp information in the document with the time range corresponding to the time validity stipulated in the government affairs process.

[0095] The temporal matching degree can be a time consistency score between the government affairs timeliness information of the document and the government affairs timeliness information.

[0096] Cosine similarity evaluation can be a process of evaluating the matching degree of responsibility division based on the vector cosine similarity between the responsibility information in the current document and the government process responsibility matrix.

[0097] The responsibility matching degree can be the correlation score between the government responsibility subject in the document and the responsible person in the government responsibility matrix.

[0098] Specifically, in the process of conducting logical association analysis on the multidimensional information set of document content based on government process information, the degree of match between the completed document content and the corresponding government process is mainly evaluated from four dimensions: process, rules, timeliness and responsibility; government processes have strict sequence requirements, and process deviations may lead to process violations; rule deviations between government processes and documents will lead to document approval failure; timeliness mismatch will cause contradictions and deviations in the document processing process; deviations in the responsible subjects will lead to unclear responsibility division; through topological matching evaluation, the topological matching degree of the process node is determined to reflect the degree of match between the process in the current document and the corresponding government process; through rule compliance verification, the rule matching degree is determined to reflect whether the current document content meets the government process rule requirements; through timeliness verification, the timing matching degree is determined to reflect whether the timestamp information in the document meets the timeliness regulations in the government process; cosine similarity evaluation is performed between the government responsibility matrix and the responsible subject division information in the document to reflect whether the responsibility division conflicts; based on the process node topological matching degree, rule matching degree, timeliness matching degree and responsibility matching degree, the association analysis results are comprehensively constructed from four dimensions.

[0099] Through this solution, based on government process information, starting from the four dimensions of process, rules, timeliness and responsibility, a logical correlation analysis is performed on the multidimensional information set of document content. Through the four quantitative indicators of process node topology matching, rule matching, timing matching and responsibility matching, the matching degree between the multidimensional information set of document content and the corresponding government process information in different dimensions is mapped respectively. This is used as the correlation analysis result to improve the scientificity and comprehensiveness of the logical correlation analysis process.

[0100] In some embodiments, the process node topology matching, rule matching, timing matching and responsibility matching in the association analysis results are compared with the corresponding matching ranges respectively; if there is a situation where the process node topology matching / rule matching / timing matching / responsibility matching is not within the corresponding matching range, the corresponding abnormal matching is extracted; based on the color-differentiated document annotation strategy and government process information, according to the abnormality type corresponding to the abnormal matching, the local content of the document corresponding to the abnormal matching is highlighted, and the corresponding adjustment suggestions are determined.

[0101] The color-differentiated document annotation strategy may be an annotation strategy that uses different colors to mark different types of content anomalies in a document.

[0102] Adjustment suggestions can be corresponding adjustment suggestions for abnormal content in documents based on government process information.

[0103] Specifically, government documents must strictly follow the preset processes, rules, time limits and responsibility requirements. By comparing the relationship between different matching degrees and the corresponding range thresholds, the different content deviations in the document can be clarified to avoid subjective judgment errors. The process node topology matching degree, rule matching degree, timing matching degree and responsibility matching degree obtained by the analysis of the above embodiments are compared with the corresponding ranges respectively. If a certain matching degree exceeds the threshold range, it will be marked as an abnormal matching degree and its type (such as "process abnormality") is recorded. Predefined colors are selected according to the abnormality type: process abnormality (red), rule abnormality (blue), time limit abnormality (yellow), responsibility abnormality (purple), and the local content corresponding to the abnormal matching degree is located in the document (such as the missing node paragraph in the flowchart). The area is selected with the corresponding color to mark the abnormal content, and further, according to different types of abnormalities, the correct reference information in the government process information is extracted as the corresponding adjustment suggestion.

[0104] Through this solution, accurate positioning and efficient correction of errors in government documents are achieved through matching comparison and visual annotation. The color differentiation strategy reduces the complexity of manual review, and the highlighted annotations directly point to the problem areas. Combined with targeted adjustment suggestions, the standardization and efficiency of government processing procedures are significantly improved. At the same time, through automated anomaly detection and prompts, compliance risks caused by omissions or misjudgments are reduced, ensuring that the document content is highly consistent with government process requirements.

[0105] Figure 3 A schematic diagram of the structure of an intelligent government service terminal based on OCR recognition technology provided in one embodiment of the present application is shown as follows: Figure 3 As shown, an intelligent government service terminal 300 based on OCR recognition technology in this embodiment includes: a degradation analysis module 301, a document analysis module 302, a correlation analysis module 303 and a document marking module 304.

[0106] The degradation analysis module 301 is used to obtain a document image data set, perform degradation identification processing on each document image in the document image data set, and determine the degradation area information; the document analysis module 302 is used to analyze the document image data set based on the degradation area information, and determine the document content multidimensional information set; the association analysis module 303 is used to obtain government process information, perform logical association analysis on the document content multidimensional information set based on the government process information, and determine the association analysis result; the document marking module 304 is used to perform marked error correction on the document content multidimensional information set based on the association analysis result, and determine and output a document processing report.

[0107] Optionally, the degradation analysis module 301 is specifically used to: analyze the document image data set to extract several feature degradation areas of each document image; based on the image convolutional neural network model, extract the image feature vectors corresponding to the several feature degradation areas, and perform feature degradation type probability distribution analysis on each image feature vector to determine the degradation distribution probability of each feature degradation area under each feature degradation type; the feature degradation types include creases, fades, stains and missing; based on a preset degradation classification minimization loss function, determine the feature degradation type corresponding to each feature degradation area according to the degradation distribution probability of each feature degradation area under each feature degradation type; construct the degradation area information according to each feature degradation area and its corresponding feature degradation type.

[0108] Optionally, the preset degradation classification minimization loss function in the degradation analysis module 301 is specifically the following formula:

[0109] ;

[0110] in, is the cross entropy loss, is the degenerate type index, is the total number of degenerate types, For the The historical frequency of occurrence of degradation types, For the A vector of preset type labels for the degenerate types, For the The degradation distribution probability of each degradation type.

[0111] Optionally, the document analysis module 302 is specifically used to: analyze the document image data set, identify and determine the document layout structure area, text area and additional mark area in each document image in the document image data set, and extract the document content in each document area; based on the degraded area information, determine a number of cross-fuzzy areas and their corresponding document areas according to the intersection area between the feature degraded area and the document layout structure area / the text area / the additional mark area; based on the feature degradation type and the document area to which the cross-fuzzy area belongs, perform inference completion analysis on the cross-fuzzy area according to the document content corresponding to the document area, and determine the corresponding information to be completed in each cross-fuzzy area; construct the document content multidimensional information set according to the document content in each document area and the information to be completed in each cross-fuzzy area.

[0112] Optionally, the document analysis module 302 performs an inferential completion analysis on the cross-fuzzy area based on the feature degradation type and the document area to which the cross-fuzzy area belongs, according to the document content corresponding to the document area, and determines the corresponding information to be completed in each cross-fuzzy area, specifically for: if the document area to which the document belongs is the document layout structure area, extracting the overall layout structure outline of the document according to the document content corresponding to the document layout structure area; searching a preset document template database based on the overall layout structure outline of the document to determine whether there is a corresponding document template; if the document template exists, taking the differentiated contour edge between the overall layout structure outline of the document and the corresponding document template as the information to be completed; if the document template does not exist, based on the graph neural network, performing a line continuity completion analysis on the overall layout structure outline of the document according to the feature degradation type, determining the completion structure lines of the cross-fuzzy area, and taking the completion structure lines as the information to be completed.

[0113] Optionally, the document analysis module 302 performs an inferential completion analysis on the cross-fuzzy area based on the feature degradation type and the document area to which the cross-fuzzy area belongs, according to the document content corresponding to the document area, and determines the information to be completed corresponding to each cross-fuzzy area, specifically for: if the document area to which the cross-fuzzy area belongs is the text area, performing edge feature analysis on the text information in the text area according to the image edge detection algorithm to determine the printed information and handwritten information; analyzing the handwritten information based on the image edge detection algorithm to determine the handwriting feature set; analyzing the handwriting feature set based on the preset feature point descriptor to determine the handwriting feature vector; performing handwriting analogy analysis on the handwriting information based on the handwriting feature vector to determine the semantic information of the handwritten text; performing contextual semantic continuity analysis on the printed information and the handwritten text semantic information based on the natural language analysis algorithm to determine the semantic continuity guaranteed completion information, and using the semantic continuity guaranteed completion information as the information to be completed.

[0114] Optionally, the document analysis module 302 performs an inferential completion analysis on the cross-fuzzy area based on the feature degradation type and the document area to which the cross-fuzzy area belongs, according to the document content corresponding to the document area, and determines the information to be completed corresponding to each cross-fuzzy area, specifically for: if the document area to which the cross-fuzzy area belongs is the additional mark area, according to the document content corresponding to the additional mark area, divide and extract the background semi-transparent watermark content and the foreground dark seal content; analyze the background semi-transparent watermark content, extract the watermark unit content, and thereby determine the unit to which the document belongs; analyze the foreground dark seal content, and determine the document approval unit; according to the document unit to which the document belongs and the document approval unit, send the document verification information to the corresponding unit, and receive the verification feedback information and the target seal image provided by the corresponding unit; if the verification feedback information is that the verification is correct, then use the difference contour between the watermark unit content and the cross-fuzzy area as the information to be completed, and at the same time use the difference contour between the target seal image and the foreground dark seal content as the information to be completed.

[0115] Optionally, the association analysis module 303 is specifically used to: based on the multidimensional information set of the document content, according to the information to be completed in each cross-fuzzy area, complete the document content in each document area to determine the completed document content; based on the natural language analysis algorithm, analyze the completed document content to determine the document government affairs process, document government affairs rules, document government affairs timeliness information and document government affairs responsible party; according to the government affairs process directed graph, perform a topological matching evaluation on the document government affairs process to determine the topological matching degree of the process node; according to the government affairs rule logical expression set, perform rule compliance verification on the document government affairs rules to determine the rule matching degree; according to the government affairs timeliness information, perform timeliness verification on the document government affairs timeliness information to determine the timing matching degree; according to the government affairs responsibility matrix, perform a cosine similarity evaluation on the document government affairs responsible party to determine the responsibility matching degree; according to the process node topological matching degree, the rule matching degree, the timing matching degree and the responsibility matching degree, construct the association analysis result.

[0116] Optionally, the document marking module 304 is specifically used to: compare the process node topology matching degree, the rule matching degree, the timing matching degree and the responsibility matching degree in the association analysis result with the corresponding matching degree ranges respectively; if the process node topology matching degree / the rule matching degree / the timing matching degree / the responsibility matching degree is not within the corresponding matching degree range, extract the corresponding abnormal matching degree; based on the color-differentiated document annotation strategy and the government process information, according to the abnormality type corresponding to the abnormal matching degree, highlight the local content of the document corresponding to the abnormal matching degree, and determine the corresponding adjustment suggestions.

[0117] The terminal of this embodiment can be used to execute the method of any of the above embodiments. The implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. An intelligent government service method based on OCR recognition technology, characterized in that: include: Acquire a document image data set, perform degradation recognition processing on each document image in the document image data set, and determine degradation area information; Analyzing the document image data set based on the degraded region information to determine a document content multidimensional information set; Acquiring government affairs process information, and performing a logical correlation analysis on the multi-dimensional information set of the document content based on the government affairs process information to determine a correlation analysis result; Based on the association analysis results, performing markup error correction on the document content multidimensional information set, and determining and outputting a document processing report; The step of analyzing the document image dataset based on the degraded region information to determine a document content multidimensional information set includes: Analyzing the document image data set, identifying and determining a document layout structure region, a text region, and an additional markup region within each document image in the document image data set, and extracting document content within each document region; Based on the degenerate region information, determining a plurality of intersecting fuzzy regions and their corresponding document regions according to the intersecting regions between the characteristic degenerate region and the document layout structure region / the text region / the additional mark region; Based on the feature degradation type and the document area to which the cross-fuzzy area belongs, and according to the document content corresponding to the document area, performing an inference completion analysis on the cross-fuzzy area to determine the information to be completed corresponding to each cross-fuzzy area; constructing the document content multidimensional information set according to the document content in each document area and the information to be completed in each cross-fuzzy area; The information to be completed corresponding to the document layout structure area is: the differential outline edge between the overall document layout structure outline and the corresponding document template; The information to be completed corresponding to the text area is: the completion information guaranteed by the semantic continuity between the printed information and the handwritten text semantic information; The information to be completed in the additional mark area is: the difference outline between the watermark unit content and the cross-fuzzy area, and the difference outline between the target seal image and the foreground dark seal content.

2. The method according to claim 1, characterized in that The performing degradation identification processing on each document image in the document image data set to determine degradation area information includes: Analyzing the document image dataset to extract several characteristic degradation regions of each document image; Based on the image convolutional neural network model, extracting image feature vectors corresponding to several feature degradation regions, and performing feature degradation type probability distribution analysis on each of the image feature vectors to determine the degradation distribution probability of each feature degradation region under each feature degradation type; The types of feature degradation include creases, fades, stains, and loss; Based on a preset degradation classification minimization loss function, determining the feature degradation type corresponding to each feature degradation region according to the degradation distribution probability of each feature degradation region under each feature degradation type; The degradation region information is constructed according to each of the feature degradation regions and the corresponding feature degradation type.

3. The method according to claim 2, characterized in that The preset degradation classification minimizes the loss function, specifically the following formula: ； in, is the cross entropy loss, is the degenerate type index, is the total number of degenerate types, For the The historical frequency of occurrence of degradation types, For the A vector of preset type labels for the degenerate types, For the The degradation distribution probability of each degradation type.

4. The method according to claim 1, wherein The method of performing an inference-based completion analysis on the cross-fuzzy regions based on the feature degradation type and the document regions to which the cross-fuzzy regions belong, according to the document content corresponding to the cross-fuzzy regions, and determining the information to be completed corresponding to each cross-fuzzy region, includes: If the document region is the document layout structure region, extracting the overall document layout structure outline according to the document content corresponding to the document layout structure region; According to the overall layout structure outline of the document, searching a preset document template database to determine whether there is a corresponding document template; If the document template exists, the differential outline edge between the overall layout structure outline of the document and the corresponding document template is used as the information to be completed; If the document template does not exist, based on the graph neural network and according to the feature degradation type, the line continuity completion analysis of the overall layout structure outline of the document is performed to determine the completed structural lines of the cross-fuzzy area, and the completed structural lines are used as the information to be completed.

5. The method according to claim 1, wherein The method of performing an inference-based completion analysis on the cross-fuzzy regions based on the feature degradation type and the document regions to which the cross-fuzzy regions belong, according to the document content corresponding to the cross-fuzzy regions, and determining the information to be completed corresponding to each cross-fuzzy region, includes: If the document area is the text area, performing edge feature analysis on the text information in the text area according to an image edge detection algorithm to determine the printed information and handwritten information; Analyzing the handwriting information based on an image edge detection algorithm to determine a handwriting feature set; Analyzing the handwriting feature set according to a preset feature point descriptor to determine a handwriting feature vector; performing handwriting analogy analysis on the handwriting information according to the handwriting feature vector to determine semantic information of the handwriting text; Based on a natural language analysis algorithm, contextual semantic continuity analysis is performed on the printed information and the handwritten text semantic information to determine the semantic continuity guarantee supplement information, and the semantic continuity guarantee supplement information is used as the information to be supplemented.

6. The method according to claim 1, characterized in that The method of performing an inference-based completion analysis on the cross-fuzzy regions based on the feature degradation type and the document regions to which the cross-fuzzy regions belong, according to the document content corresponding to the cross-fuzzy regions, and determining the information to be completed corresponding to each cross-fuzzy region, includes: If the document area is the additional mark area, dividing and extracting the background semi-transparent watermark content and the foreground dark seal content according to the document content corresponding to the additional mark area; Analyzing the background semi-transparent watermark content and extracting the watermark unit content to determine the unit to which the document belongs; Analyze the content of the foreground dark seal to determine the document approval unit; According to the unit to which the document belongs and the document approval unit, the document verification information is sent to the corresponding unit, and the verification feedback information and the target seal image provided by the corresponding unit are received; If the verification feedback information indicates that the verification is correct, the difference contour between the watermark unit content and the cross fuzzy area is used as the information to be completed, and the difference contour between the target seal image and the foreground dark seal content is used as the information to be completed.

7. The method according to claim 5, characterized in that The government affairs process information includes a government affairs process directed graph, a government affairs rule logical expression set, government affairs timeliness information, and a government affairs responsibility matrix. Based on the government affairs process information, performing a logical association analysis on the document content multidimensional information set to determine the association analysis result includes: Based on the document content multidimensional information set, the document content in each document area is completed according to the information to be completed in each cross-fuzzy area to determine the completed document content; Analyze the completed document content based on a natural language analysis algorithm to determine the document government affairs process, document government affairs rules, document government affairs timeliness information, and document government affairs responsible parties; Performing a topological matching evaluation on the documented government affairs process according to the government affairs process directed graph to determine the topological matching degree of the process nodes; According to the set of logical expressions of the government affairs rules, the rule compliance of the document government affairs rules is verified to determine the rule matching degree; According to the government affairs timeliness information, the timeliness verification of the government affairs timeliness information of the document is performed to determine the time sequence matching degree; Based on the government responsibility matrix, a cosine similarity evaluation is performed on the government responsibility subjects of the document to determine the responsibility matching degree; The association analysis result is constructed according to the process node topology matching degree, the rule matching degree, the timing matching degree and the responsibility matching degree.

8. The method according to claim 7, characterized in that The step of performing markup error correction on the document content multidimensional information set according to the association analysis result includes: Comparing the process node topology matching degree, the rule matching degree, the timing matching degree, and the responsibility matching degree in the association analysis result with corresponding matching degree ranges respectively; If the process node topology matching degree / the rule matching degree / the timing matching degree / the responsibility matching degree is not within the corresponding matching degree range, the corresponding abnormal matching degree is extracted; Based on the color-differentiated document annotation strategy and the government process information, according to the exception type corresponding to the exception matching degree, the local content of the document corresponding to the exception matching degree is highlighted, and corresponding adjustment suggestions are determined.

9. An intelligent government service terminal based on OCR recognition technology, characterized in that: Applicable to executing the method according to any one of claims 1 to 8, comprising: a degradation analysis module, configured to obtain a document image data set, perform degradation identification processing on each document image in the document image data set, and determine degradation region information; A document analysis module, configured to analyze the document image dataset based on the degraded region information to determine a document content multidimensional information set; A correlation analysis module is used to obtain government affairs process information, perform logical correlation analysis on the multi-dimensional information set of the document content based on the government affairs process information, and determine the correlation analysis result; The document marking module is used to perform marking-type error correction on the multi-dimensional information set of the document content according to the association analysis result, and determine and output a document processing report.

Images