Data management system for administrative affair management platform

Abstract

The invention relates to the field of data management, in particular to a data management system for an administrative affair management platform, and the system comprises an image evaluation module which is used for detecting the character freedom degree and character writing density of each target processing image so as to determine the image state of each target processing image; the image analysis module is used for acquiring an analysis image combination and determining a corresponding analysis strategy according to an image state; the first analysis module is used for determining to-be-matched characters according to the character combination richness and determining reference matching character elements of the corresponding analysis image combination according to the element reference degree; the second analysis module is used for determining keyword group information and keyword groups of the analysis image combination according to the phrase use frequency and the phrase related parameters, and determining effective keyword groups according to the reference validity; and the image storage module is used for determining a storage strategy of the corresponding matched reference image according to the analysis completion condition, and the validity of the stored matched reference image is improved.

Description

Technical Field

[0001] The present invention relates to the field of data management, and in particular to a data management system for an administrative affairs management platform. Background Art

[0002] In the process of administrative affairs management, there are a large number of handwritten materials. In order to prevent the existence of forged materials, it is necessary to compare the new materials with the past materials. However, due to the large differences in the writing characteristics of different people, it is easy to affect the recognition process. Therefore, the handwritten material images of different people are stored separately to improve the efficiency of subsequent text comparison. However, when the same person faces different writing restrictions, his or her writing characteristics will change to a certain extent. Therefore, how to analyze and store the existing writing material images based on different writing restrictions to ensure the validity of the stored handwritten material images is a problem that needs to be urgently solved by technical personnel in this field.

[0003] Chinese patent publication number CN115471849A discloses a handwritten Chinese character image evaluation method and system, firstly obtains a handwritten Chinese character image and a template Chinese character image, performs denoising and binarization processing, and obtains a preprocessed image; then performs stroke type determination processing, compares the stroke type of the obtained handwritten Chinese character image with the stroke type of the template Chinese character image, obtains the similarity value of the handwritten Chinese character image, and is used to evaluate the handwritten Chinese character image. Chinese patent publication number CN111612429A discloses an auxiliary approval method and auxiliary approval system applied to administrative approval, belonging to the field of administrative approval system, the method is to assist in the verification and approval of the application form and application materials submitted through the administrative approval user interface and the shared data and shared materials obtained from the third-party government service sharing platform through the data interface. The auxiliary approval system includes an approval configuration module, a user auxiliary module, a verification module, an approval module, and an authenticity verification module. The above technical solution has the following problems: it fails to determine the stored handwriting material image according to the writing features of the existing handwriting material image under different writing restrictions, resulting in low validity of the stored handwriting material image, and further resulting in low efficiency of subsequent character matching. Summary of the invention

[0004] To this end, the present invention provides a data management system for an administrative affairs management platform, which is used to overcome the problem in the prior art that the stored handwriting material image cannot be determined according to the writing characteristics of the existing handwriting material image under different writing restriction conditions, resulting in low validity of the stored handwriting material image, and further resulting in low efficiency of subsequent character matching.

[0005] To achieve the above-mentioned purpose, the present invention provides a data management system for an administrative affairs management platform, comprising:

[0006] An image evaluation module, used to detect the character freedom degree and character writing density of each target processed image, so as to determine the image state of each target processed image;

[0007] An image analysis module connected to the image evaluation module to obtain an analysis image combination and respond to the image state of the analysis condition to determine a corresponding analysis strategy;

[0008] A first analysis module, which is connected to the image analysis module, is used to determine the characters to be matched according to the character combination richness, and to determine the reference matching character elements of the analyzed image combination according to the element reference degree;

[0009] A second analysis module, connected to the image analysis module, is used to determine the keyword group information and keyword group of the analysis image combination according to the frequency of use of the phrase and the phrase-related parameters, and to determine the effective keyword group according to the reference validity;

[0010] An image storage module is connected to the first analysis module and the second analysis module, and is used to respond to different analysis completion conditions and determine a storage strategy for matching reference images corresponding to each analysis image combination.

[0011] Further, the image evaluation module responds to the character freedom and character writing density of the evaluation conditions to determine the image state of each target processed image;

[0012] Processing images for a single target,

[0013] The image evaluation module responds to the evaluation condition that the character freedom degree is greater than the preset character freedom degree and the character writing density is less than or equal to the preset character writing density, then determines that the target processed image is in the first preset image state;

[0014] The image evaluation module responds to an evaluation condition that the character freedom degree is less than or equal to the preset character freedom degree or the character writing density is greater than the preset character writing density, and then determines that the target processed image is in the second preset image state.

[0015] Further, the image analysis module responds to the combination division condition and divides each target processing image to obtain an analysis image combination;

[0016] All target processed images in any analysis image combination are in the same image state, and the writing ratio difference value of each analysis image combination is less than the preset writing ratio difference value;

[0017] The combination division condition is that each target processed image has completed the determination of the image state.

[0018] Further, the image analysis module responds to the image state of the analysis condition to determine a corresponding analysis strategy;

[0019] For a single analysis image combination,

[0020] The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the first preset image state, then it is determined that the first analysis module extracts characters to be matched for each target processed image in the analysis image combination according to the character richness;

[0021] The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the second preset image state, and then the second analysis module is determined to determine the keyword group of the analysis image combination.

[0022] Furthermore, the first analysis module responds to the first analysis condition, performs character combination richness detection on the characters contained in each target processed image in the analysis image combination, and records the characters whose character combination richness is greater than the preset character combination richness as characters to be matched;

[0023] The first analysis condition is that the image analysis module determines that the first analysis module extracts characters to be matched for each target processed image in an analysis image combination according to character richness.

[0024] Furthermore, the first analysis module performs element reference degree detection of each category of character elements for any analysis image combination that has completed extraction of the to-be-matched character;

[0025] The reference matching character element of the corresponding analysis image combination is determined according to the element reference degree, and the character element whose element reference degree is greater than the preset element reference degree is recorded as the reference matching character element of the analysis image combination.

[0026] Further, the second analysis module determines the key word group information of the analysis image combination according to the phrase usage frequency and phrase related parameters in response to the second analysis condition;

[0027] The character combination corresponding to each keyword group information in the target processing image is recorded as a keyword group;

[0028] The second analysis condition is that the image analysis module determines the keyword group of the second analysis module to analyze the image combination.

[0029] Furthermore, the second analysis module responds to the key analysis condition and detects the position distribution characteristics of each keyword group corresponding to any keyword group information of the analysis image combination;

[0030] The keyword groups with the same position distribution characteristics and corresponding keyword group information are classified as a reference matching combination, and the reference validity of each reference matching combination is determined according to the number of similar writing characteristics between the keyword groups in each reference matching combination;

[0031] Record the keyword group included in the reference matching combination whose reference validity is greater than the preset reference validity as a valid keyword group;

[0032] The key analysis condition is to extract the keyword group by analyzing the image combination.

[0033] Further, the image storage module responds to the first analysis completion condition, determines the matching reference degree of each target processed image according to the number of reference matching character elements contained in each target processed image, and determines the matching reference image according to the matching reference degree of each target processed image;

[0034] The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state and writing ratio reference value;

[0035] The first analysis completion condition is that each analysis image combination in the first preset image state completes the determination of the reference matching character element.

[0036] Further, the image storage module responds to the second analysis completion condition, determines the matching reference degree of each target processed image according to the number of valid keyword groups included, and determines the matching reference image of the analysis image combination according to the matching reference degree of each target processed image;

[0037] The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state, writing ratio reference value and position distribution characteristics of the included effective keyword group;

[0038] The second analysis completion condition is that all analysis image combinations in the second preset image state have completed the determination of valid keyword groups.

[0039] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical scheme of the present invention, the image state of each target processed image is determined according to the character degrees of freedom and character writing density of the target processed images historically submitted by the same applicant, and the analysis image combination is determined based on the image state and the writing ratio difference value, and the corresponding analysis strategy is determined in response to different image states to obtain reference matching character elements or valid keyword groups with reference value in different analysis image combinations, and thereby determine the stored matching reference image. The present invention improves the effectiveness of the stored matching reference image.

[0040] Furthermore, the present invention determines the image state of each target processing image based on the character degrees of freedom and the character writing density, so as to divide the target processing image in advance to avoid the influence of different writing restrictions on the character writing characteristics, and further divides it based on the writing proportion difference value to improve the accuracy of the subsequent analysis results of each analysis image combination.

[0041] Furthermore, the image analysis module in the present invention responds to different image states to determine the analysis strategy for each analysis image combination, so that the analysis process is more in line with the actual situation of the target processing image in the analysis image combination. For the analysis combination image in the first preset image state, since the target processing images in this type of analysis combination image have fewer writing restrictions, the characters to be matched are determined based on the richness of the character combination to determine the character elements with higher reference value, thereby improving the effectiveness of the stored matching reference image.

[0042] Furthermore, in the present invention, for the analysis combined image in the second preset image, keyword phrase information is determined based on the frequency of phrase use and phrase-related parameters. The target processing image of such analysis combined image often has differences between the same characters or character elements due to greater writing restrictions. Therefore, the frequently used keyword phrase information is analyzed to determine the similarities between keyword phrases with the same position distribution characteristics, so as to determine keyword phrase information with higher reference value, thereby improving the effectiveness of the stored matching reference image. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A module connection diagram of a data management system for an administrative affairs management platform of the present invention;

[0044] Figure 2 A flowchart of the image evaluation module of the present invention responding to the character freedom degree and character writing density of the evaluation conditions to determine the image state of each target processed image;

[0045] Figure 3 A flowchart of an image analysis module of the present invention responding to an image state of an analysis condition to determine a corresponding analysis strategy;

[0046] Figure 4 The present invention is a flowchart of an image storage module that determines a storage strategy for matching reference images corresponding to each analysis image combination in response to different analysis completion conditions. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0050] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] See also Figures 1 to 4 As shown, the present invention provides a data management system for an administrative affairs management platform, comprising:

[0052] An image evaluation module, used to detect the character freedom degree and character writing density of each target processed image, so as to determine the image state of each target processed image;

[0053] An image analysis module connected to the image evaluation module to obtain an analysis image combination and respond to the image state of the analysis condition to determine a corresponding analysis strategy;

[0054] A first analysis module, which is connected to the image analysis module, is used to determine the characters to be matched according to the character combination richness, and to determine the reference matching character elements of the analyzed image combination according to the element reference degree;

[0055] A second analysis module, connected to the image analysis module, is used to determine the keyword group information and keyword group of the analysis image combination according to the frequency of use of the phrase and the phrase-related parameters, and to determine the effective keyword group according to the reference validity;

[0056] An image storage module is connected to the first analysis module and the second analysis module, and is used to respond to different analysis completion conditions and determine a storage strategy for matching reference images corresponding to each analysis image combination.

[0057] Among them, the present invention is applied to the handwriting recognition learning of the administrative affairs management platform to improve the learning effect of the handwriting of each person in the administrative affairs management platform, to improve the accuracy of handwriting recognition, and thus avoid the problem of low effectiveness of the handwriting material images stored in the prior art. The target processing images in the present invention are all handwriting material images uploaded by each applicant in the past. The applicant is a person who needs to use the administrative affairs management platform to complete event approval and has uploaded handwriting material images. The handwriting material image is an image taken by the applicant for the handwriting material. Each target processing image corresponds to an applicant and has completed character recognition. When analyzing the target processing image in the present invention, each target processing image only corresponds to the same applicant;

[0058] The present invention applies several historical processing records, and any one of the historical processing records records the character degrees of freedom, character writing density, writing ratio difference value, character combination richness, element reference degree, key coefficient, feature parameter difference value, reference validity and matching reference degree of each target processing image in the optimization and storage process of an applicant's target processing image at least once, and each historical monitoring record corresponds to a qualified mark, which records whether the processing efficiency of the subsequent character matching process based on the stored target processing image meets user requirements.

[0059] Specifically, the image evaluation module responds to the character freedom and character writing density of the evaluation conditions to determine the image state of each target processed image;

[0060] Processing images for a single target,

[0061] The image evaluation module responds to the evaluation condition that the character freedom degree is greater than the preset character freedom degree and the character writing density is less than or equal to the preset character writing density, then determines that the target processed image is in the first preset image state;

[0062] The image evaluation module responds to an evaluation condition that the character freedom degree is less than or equal to the preset character freedom degree or the character writing density is greater than the preset character writing density, and then determines that the target processed image is in the second preset image state.

[0063] Among them, a scan is performed on any target processing image to obtain the proportion of the restricted area in the target processing image and the spacing distance of the restricted line segments, and character blocks are divided for each character in the target processing image, each character block is a rectangular area and only has one complete character, the restricted line segment is a horizontal line segment printed on the surface of the paper photographed by the target processing image, the character degree of freedom is determined according to the proportion of the restricted area in the target processing image and the reference restricted distance, character degree of freedom = 1 / (restricted area proportion + reference restricted distance), the target processing image is divided into a number of processing sub-images with the same area, the processing sub-image with the restricted line segment is recorded as the restricted area, the restricted area proportion = the number of restricted areas of the target processing image / the number of processing sub-images of the target processing image, the reference restricted distance is the average value of the shortest distance between two adjacent and parallel restricted line segments, the character writing density is the number of character blocks contained in each processing sub-image at the same scaling ratio, and the long side and the short side of the paper area contained in each target processing image at the same scaling ratio are the same;

[0064] The values ​​of the preset character degrees of freedom and the preset character writing density can be determined by the user according to the actual working scenario. For example, the user can set them according to the historical processing records. The higher the user's requirements for the processing efficiency of the character matching process, the greater the value of the preset character degrees of freedom, and the smaller the value of the preset character writing density. A method for determining the value of the preset character degrees of freedom is provided, and the historical processing records of the characters to be matched of the target processing image extracted according to the character richness are recorded as evaluation reference records, and the minimum value of the character degrees of freedom of each target processing image in the evaluation reference records that meet the user's requirements for the processing efficiency of the character matching process is recorded as the preset character degrees of freedom. A method for determining the value of the preset character writing density is provided, and the maximum value of the character writing density of each target processing image in the evaluation reference records that meet the user's requirements for the processing efficiency of the character matching process is recorded as the preset character writing density.

[0065] Specifically, the image analysis module responds to the combination division condition and divides each target processing image to obtain an analysis image combination;

[0066] All target processed images in any analysis image combination are in the same image state, and the writing ratio difference value of each analysis image combination is less than the preset writing ratio difference value;

[0067] The combination division condition is that each target processed image has completed the determination of the image state.

[0068] Among them, the character writing ratio reference value of each target processing image is detected. For a single target processing image, several character blocks are randomly selected, and the average value of the character writing ratio of each character block is recorded as the character writing ratio reference value of the target processing image. For a single character block, its character writing ratio = the area of ​​the character block / the area of ​​the target processing image. The writing ratio of any analysis image combination is n is the number of target processing images contained in the analysis image combination, Di is the character number writing ratio reference value of the i-th target processing image in the analysis image combination, D0 is the average value of the character writing ratio reference values ​​of each target processing image in the analysis image combination, and the value of the preset writing ratio difference value can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical processing records. The higher the user's requirement for the processing efficiency of the character matching process, the smaller the value of the preset writing ratio difference value. A method for determining the preset writing ratio difference value is provided, and the average value of the writing ratio difference values ​​of each analysis image combination in the historical processing records that meet the user's requirement for the processing efficiency of the character matching process is recorded as the preset writing ratio difference value.

[0069] Specifically, the image analysis module responds to the image state of the analysis condition to determine the corresponding analysis strategy;

[0070] For a single analysis image combination,

[0071] The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the first preset image state, then it is determined that the first analysis module extracts characters to be matched for each target processed image in the analysis image combination according to the character richness;

[0072] The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the second preset image state, and then the second analysis module is determined to determine the keyword group of the analysis image combination.

[0073] Specifically, the first analysis module responds to the first analysis condition, performs character combination richness detection on the characters contained in each target processed image in the analysis image combination, and records the characters whose character combination richness is greater than the preset character combination richness as characters to be matched;

[0074] The first analysis condition is that the image analysis module determines that the first analysis module extracts characters to be matched for each target processed image in an analysis image combination according to character richness.

[0075] Among them, for any character, the richness of the character combination is the number of categories of character elements included in the standard character image corresponding to the character. In the present invention, each character is provided with a corresponding standard character image, that is, the printed image corresponding to each character. The categories of character elements include but are not limited to: 冫, 氵, 彳, and 忄. The user can set according to the actual usage scenario for the categories of character elements. The value of the preset richness of the character combination can be determined by the user according to the actual working scenario. For example, the user can set according to the historical processing records. The higher the user's requirement for the processing efficiency of the character matching process, the larger the value of the preset richness of the character combination. A method for obtaining the value of the preset richness of the character combination is provided. The average value of the richness of the character combination of each character in the historical processing records that meet the user's requirement for the processing efficiency of the character matching process is recorded as the preset richness of the character combination.

[0076] Specifically, the first analysis module performs an element reference degree detection on various categories of character elements for any analysis image combination that has completed the extraction of the character to be matched.

[0077] According to the element reference degree, the reference matching character elements of the corresponding analysis image combination are determined. The character elements with an element reference degree greater than the preset element reference degree are recorded as the reference matching character elements of the analysis image combination.

[0078] Among them, for any analysis image combination that has completed the extraction of the character to be matched, the element reference degree of the character elements of each category is determined according to the element usage efficiency and the reference element similarity of the character elements of each category included in the character to be matched. For a single category of character elements, the element reference degree = ln(element usage efficiency × reference element similarity). The element usage efficiency is the number of relevant matching characters in the analysis image combination. The relevant matching characters are the characters to be matched with the character elements of this category. Reference Aj is the feature difference value of the j-th writing feature parameter, Bj is the influence coefficient corresponding to the j-th writing feature parameter, and m is the number of writing features for determining the reference element similarity. For a single writing feature parameter, the feature difference value is the sum of the absolute values of the differences between the feature parameters of each relevant matching character and the feature average parameter. The feature average parameter is the average value of the feature parameters of each relevant matching character.

[0079] The user can provide a writing feature parameter for determining the similarity of the reference element and its corresponding influence coefficient according to the actual usage scenario. The writing feature parameters used are the turning point offset angle and the element length. The position where the writing direction changes during the writing process of the character element is recorded as the turning point. Two rays are drawn along the writing directions before and after the turning point with the turning point as the endpoint. The angle between the two rays is the turning point offset angle. The element length is the distance between the two points with the longest straight-line distance in the character element. The influence coefficient corresponding to the turning point offset angle is 0.5, and the influence coefficient corresponding to the element length is 0.5.

[0080] The value of the preset element reference degree can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical processing records. The higher the user's requirement for the processing efficiency of the character matching process, the larger the value of the preset element reference degree. A method for determining the value of the preset element reference degree is provided, and the minimum value of the element reference degree of each reference matching character element in the historical processing records that meets the user's requirement for the processing efficiency of the character matching process is recorded as the preset element reference degree.

[0081] Specifically, the second analysis module determines the key word group information of the analysis image combination according to the phrase usage frequency and phrase related parameters in response to the second analysis condition;

[0082] The character combination corresponding to each keyword group information in the target processing image is recorded as a keyword group;

[0083] The second analysis condition is that the image analysis module determines the keyword group of the second analysis module to analyze the image combination.

[0084] Among them, there are several phrase information in the present invention, and any one of the phrase information is composed of several identical or different characters, and the characters constituting the phrase information are recorded as the character combination of the phrase information. The key coefficient of each phrase information is determined according to the phrase usage frequency and the phrase related parameters. For a single phrase information, the key coefficient is the sum of the phrase usage frequency and the phrase related parameters. The phrase usage frequency is the average number of times the character combination corresponding to the phrase information exists in each target processing image of the analysis image combination, and the phrase related parameters are the average number of times the character combination corresponding to the phrase information exists in each target processing image of the applicant corresponding to the target processing image. Mean, record the phrase information whose key coefficient is greater than the preset key coefficient as key phrase information, the value of the preset key coefficient can be determined by the user according to the actual working scenario, for example, the user can set it according to the historical processing records, the higher the user's requirement for the processing efficiency of the character matching process, the larger the value of the preset key coefficient, and provide a method for setting the value of the preset key coefficient, record the minimum value of the key coefficient of the key phrase information in the historical processing records that meets the user's requirement for the processing efficiency of the character matching process as the preset key coefficient, for the applicant corresponding to the target processing image currently being analyzed, the related applicants are other applicants with the same position as the applicant.

[0085] Specifically, the second analysis module responds to the key analysis condition and detects the position distribution characteristics of each keyword group corresponding to any keyword group information of the analysis image combination;

[0086] The keyword groups with the same position distribution characteristics and corresponding keyword group information are classified as a reference matching combination, and the reference validity of each reference matching combination is determined according to the number of similar writing characteristics between the keyword groups in each reference matching combination;

[0087] Record the keyword group included in the reference matching combination whose reference validity is greater than the preset reference validity as a valid keyword group;

[0088] The key analysis condition is to extract the keyword group by analyzing the image combination.

[0089] Among them, the position distribution characteristics of the corresponding keyword group are determined according to the spacing distance between the edge character block in each keyword group and the writing restriction edge, the edge character block is a character block with only one adjacent character block in a keyword group, and the set of each connected restriction area in a target processing image is recorded as the writing restriction area. For an edge character block, the shortest distance between the two sides of the edge character block perpendicular to the restriction line segment and the two vertical edge lines of the writing restriction area to which it belongs is determined respectively, and the minimum value of each determined shortest distance is recorded as the spacing distance between the edge character block and the writing restriction edge;

[0090] If the spacing distance between the edge character block and the writing restriction edge in a keyword group is less than or equal to the preset spacing distance, the position distribution feature of the keyword group is determined to be edge distribution; if the spacing distance between the edge character block and the writing restriction edge in a keyword group is greater than the preset spacing distance, the position distribution feature of the keyword group is determined to be center distribution. The value of the preset spacing distance can be determined by the user according to the actual working scene. A value of the preset spacing distance is provided, and 10% of the horizontal length of the writing restriction area is recorded as the preset spacing distance;

[0091] There are several writing features in the present invention, and any writing feature corresponds to a related character element and a corresponding writing feature parameter. The writing feature parameters in the present invention include but are not limited to: the intersection angle of the character elements, the width of the character block, and the inclination angle of the character elements. For a single writing feature, the keyword group containing its corresponding related character element is recorded as a related phrase. If the feature parameter difference values ​​of each writing feature parameter corresponding to the writing feature in each related phrase in a reference matching combination are all less than the preset feature parameter difference value, then the writing feature is determined to be a similar writing feature. For any writing feature parameter of the writing feature, the feature parameter difference value is the writing feature parameter difference value of each related phrase in the reference matching combination. The sum of the absolute values ​​of the differences between the number and the average writing feature parameter, the average writing feature parameter is the average value of the writing feature parameters of each related phrase, the value of the preset feature parameter difference value of each writing feature parameter can be determined by the user according to the actual working scenario, for example, the user can set it according to the historical processing record, the higher the user's requirements for the processing efficiency of the character matching process, the smaller the value of the preset feature parameter difference value, and a method for determining the preset feature parameter difference value is provided, and the maximum value of the feature parameter difference value of each writing feature parameter of similar writing features in the historical processing record that meets the user's requirements for the processing efficiency of the character matching process is recorded as the preset feature parameter difference value of the corresponding writing feature parameter;

[0092] For a single reference matching combination, the reference validity is positively correlated with the number of similar writing features of the reference matching combination. The value of the preset reference validity can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical processing records. The higher the user's requirements for the processing efficiency of the character matching process, the larger the value of the preset reference validity. A method for setting the value of the preset reference validity is provided, and the minimum value of the reference validity of the reference matching combination corresponding to the keyword group in the historical processing records that meets the user's requirements for the processing efficiency of the character matching process is recorded as the preset reference validity.

[0093] Specifically, the image storage module responds to the first analysis completion condition, determines the matching reference degree of each target processing image according to the number of reference matching character elements contained in each target processing image, and determines the matching reference image of the corresponding analysis image combination according to the matching reference degree of each target processing image;

[0094] The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state and writing ratio reference value;

[0095] The first analysis completion condition is that each analysis image combination in the first preset image state completes the determination of the reference matching character element.

[0096] Specifically, the image storage module responds to the second analysis completion condition, determines the matching reference degree of each target processed image according to the number of valid keyword groups included, and determines the matching reference image of the analysis image combination according to the matching reference degree of each target processed image;

[0097] The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state, writing ratio reference value and position distribution characteristics of the included effective keyword group;

[0098] The second analysis completion condition is that all analysis image combinations in the second preset image state have completed the determination of valid keyword groups.

[0099] Among them, under the first analysis completion condition, for a single analysis image combination, the matching reference degree is positively correlated with the number of reference matching character elements contained in the target processing image. Under the second analysis completion condition, for a single analysis image combination, the matching reference degree is positively correlated with the number of valid keyword groups contained in the target processing image. The target processing image with a matching reference degree greater than a preset matching reference degree is recorded as a matching reference image. The value of the preset matching reference degree can be determined by the user according to the actual working scenario. For example, the user can set it according to the historical processing records. The higher the user's requirements for the processing efficiency of the character matching process, the greater the value of the preset reference matching degree. The average value of the matching reference degrees of each target processing image in the historical processing records that meet the user's requirements for the processing efficiency of the character matching process is recorded as the preset matching reference degree.

[0100] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data management system for an administrative affairs management platform, characterized in that: include: An image evaluation module, used to detect the character freedom degree and character writing density of each target processed image, so as to determine the image state of each target processed image; An image analysis module connected to the image evaluation module to obtain an analysis image combination and respond to the image state of the analysis condition to determine a corresponding analysis strategy; A first analysis module, which is connected to the image analysis module, is used to determine the characters to be matched according to the character combination richness, and to determine the reference matching character elements of the analyzed image combination according to the element reference degree; A second analysis module, connected to the image analysis module, is used to determine the keyword group information and keyword group of the analysis image combination according to the frequency of use of the phrase and the phrase-related parameters, and to determine the effective keyword group according to the reference validity; An image storage module is connected to the first analysis module and the second analysis module, and is used to respond to different analysis completion conditions and determine a storage strategy for matching reference images corresponding to each analysis image combination.

2. The data management system for the administrative affairs management platform according to claim 1 is characterized in that: The image evaluation module responds to the character freedom and character writing density of the evaluation conditions to determine the image state of each target processed image; Processing images for a single target, The image evaluation module responds to the evaluation condition that the character freedom degree is greater than the preset character freedom degree and the character writing density is less than or equal to the preset character writing density, then determines that the target processed image is in the first preset image state; The image evaluation module responds to an evaluation condition that the character freedom degree is less than or equal to the preset character freedom degree or the character writing density is greater than the preset character writing density, and then determines that the target processed image is in the second preset image state.

3. The data management system for the administrative affairs management platform according to claim 2 is characterized in that: The image analysis module responds to the combination division condition and divides each target processing image to obtain an analysis image combination; All target processed images in any analysis image combination are in the same image state, and the writing ratio difference value of each analysis image combination is less than the preset writing ratio difference value; The combined division condition is that each target processed image has completed the determination of the image state.

4. The data management system for the administrative affairs management platform according to claim 3 is characterized in that: The image analysis module responds to the image status of the analysis condition to determine the corresponding analysis strategy; For a single analysis image combination, The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the first preset image state, then it is determined that the first analysis module extracts characters to be matched for each target processed image in the analysis image combination according to the character richness; The analysis condition responded by the image analysis module is that each target processed image in the analysis image combination is in the second preset image state, and then the second analysis module is determined to determine the keyword group of the analysis image combination.

5. The data management system for the administrative affairs management platform according to claim 4 is characterized in that: The first analysis module responds to the first analysis condition, performs character combination richness detection on the characters contained in each target processed image in the analysis image combination, and records the characters whose character combination richness is greater than the preset character combination richness as characters to be matched; The first analysis condition is that the image analysis module determines that the first analysis module extracts characters to be matched for each target processed image in an analysis image combination according to character richness.

6. The data management system for the administrative affairs management platform according to claim 5 is characterized in that: The first analysis module performs element reference degree detection of each category of character elements for any analysis image combination that has completed extraction of characters to be matched; The reference matching character element of the corresponding analysis image combination is determined according to the element reference degree, and the character element whose element reference degree is greater than the preset element reference degree is recorded as the reference matching character element of the analysis image combination.

7. The data management system for the administrative affairs management platform according to claim 6 is characterized in that: The second analysis module determines the key word group information of the analysis image combination according to the phrase usage frequency and phrase related parameters in response to the second analysis condition; The character combination corresponding to each keyword group information in the target processing image is recorded as a keyword group; The second analysis condition is that the image analysis module determines the keyword group of the second analysis module to analyze the image combination.

8. The data management system for the administrative affairs management platform according to claim 7, characterized in that: The second analysis module responds to the key analysis condition and detects the position distribution characteristics of each keyword group corresponding to any keyword group information of the analysis image combination; The keyword groups with the same position distribution characteristics and corresponding keyword group information are classified as a reference matching combination, and the reference validity of each reference matching combination is determined according to the number of similar writing characteristics between the keyword groups in each reference matching combination; Record the keyword group included in the reference matching combination whose reference validity is greater than the preset reference validity as a valid keyword group; The key analysis condition is to extract the keyword group by analyzing the image combination.

9. The data management system for the administrative affairs management platform according to claim 8, characterized in that: The image storage module responds to the first analysis completion condition, determines the matching reference degree of each target processed image according to the number of reference matching character elements contained in each target processed image, and determines the matching reference image according to the matching reference degree of each target processed image; The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state and writing ratio reference value; The first analysis completion condition is that each analysis image combination in the first preset image state completes the determination of the reference matching character element.

10. The data management system for the administrative affairs management platform according to claim 9, characterized in that: The image storage module responds to the second analysis completion condition, determines the matching reference degree of each target processed image according to the number of valid keyword groups included, and determines the matching reference image of the analysis image combination according to the matching reference degree of each target processed image; The image storage module stores the matching reference image of each analysis image combination in coordination with its corresponding image state, writing ratio reference value and position distribution characteristics of the included effective keyword group; The second analysis completion condition is that all analysis image combinations in the second preset image state have completed the determination of valid keyword groups.

Images