A data processing method and system based on archive information

Abstract

The invention relates to the technical field of archive data processing, and discloses a data processing method and system based on archive information, the system comprising an archive file filing address judgment module, an archive file filing address feedback module, and an archive file filing address correction and filing execution module; by accurately retrieving archive file filing address parameters; using screenshot software to open and capture interface images of each layer of filing space layer by layer, scientifically constructing archive file filing addresses and corresponding archive file filing space image parameters, realizing accurate digital image fusion of archive file filing space addresses and address spaces; visually pushing archive file filing addresses and corresponding archive file filing space images to an archive management terminal through a display screen.

Description

Technical Field

[0001] The present invention relates to the technical field of archive data processing, and in particular to a data processing method and system based on archive information. Background Art

[0002] Archives, a Chinese word, means various forms of original records with preservation value directly formed by people in various social activities. Original record is its essential attribute; archives in ancient my country have different names in different dynasties. In the Shang Dynasty, it was called "book", in the Zhou Dynasty, it was called "book", in the Qin and Han Dynasties, it was called "documents", "copyright", "case", "case file", "book", "book", "archive", "archive", "book", "archive" after the Han and Wei Dynasties, and "archive" was used more after the Qing Dynasty. Now it is uniformly called "archives"; among them, electronic archives are the most widely used; electronic archives are electronic files with voucher, inquiry and preservation value and archived. Electronic files are various information records in digital format formed, handled, transmitted and stored by electronic devices such as computers in the process of performing their statutory duties or handling affairs by state agencies, social organizations or individuals. Electronic files are composed of content, structure and background. Electronic archives refer to a collection of general electronic image files stored by devices such as computer disks, corresponding to paper archives, and interrelated, usually in the form of case files. The existing electronic archive information archiving process cannot realize intelligent judgment of the archive file archiving address, nor can it provide accurate feedback on the archive file archiving address processing results; it is even more impossible to correct the archive file archiving address and archive the archive files based on the management personnel calibration information, which reduces the efficiency and accuracy of archive information archiving.

[0003] The Chinese invention patent application with publication number CN116974989A discloses a method for processing archive data with diversified data sources, which includes a paper archive processing module, a business system archive processing module and a raw data archive processing module; for the acquired multi-source data, a directory keyword check is used to reorganize the data to form a key, the key overlap is monitored, the keys exceeding the threshold are screened, and the corresponding overlapping archive data are screened and deleted, so as to realize the organization, storage and key setting of multi-source archives; the reliability and security of the data are ensured, however, the above technical scheme cannot accurately judge and correct the archiving address for the collected archive data with diversified sources, which reduces the efficiency of archiving archive data. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In order to solve the problem that the existing electronic archive information archiving process is unable to realize intelligent judgment of the archive file archiving address, and cannot accurately feedback the archive file archiving address processing results; it is even more unable to perform archive file archiving address correction and archive file archiving operations based on the calibration information of the management personnel, the above-mentioned intelligent judgment of the archive file archiving address, standardized visual feedback of the archiving address, accurate correction of the archive file archiving address data, autonomous execution of archive file archiving operations, and the purpose of improving the efficiency and accuracy of archive information management are realized.

[0006] (II) Technical solution

[0007] The present invention is implemented by the following technical solution: a data processing method based on archive information, the method comprising the following steps:

[0008] S1. Collecting characteristic data of archive file contents;

[0009] S2, collecting archive file filing space image data and performing filing space classification folder recognition processing on filing space folder image data to generate filing space classification folder recognition result data;

[0010] S3. When the recognition result is existence, search for the internal file information of the archive space classification folder and generate the file content feature data of the archive space classification folder, perform archive file archiving target folder analysis and processing based on the archive file content feature data and the archive space classification folder file content feature data, and generate archive file archiving object folder data;

[0011] S4, looping and executing step S2 based on the archive space generated by the archive object folder data until the recognition result is that it does not exist, and then terminating the loop operation instruction;

[0012] S5. When the recognition result is that the file does not exist, the archive file archiving address is searched according to the archive file archiving object folder data, the archive file archiving address data is generated, and the interface image of each layer of archiving space is opened layer by layer to capture, and the archive file archiving address and image data are constructed and pushed to the archive management end;

[0013] S6, collecting the archive file filing address calibration data and performing archive file filing address correction processing on the archive file filing address data to generate archive file filing address correction data;

[0014] S7, performing the archive file archiving operation according to the archive file archiving address correction data.

[0015] Preferably, the steps of collecting the characteristic data of the archive file content are as follows:

[0016] S11. Use office software to open the archive file, collect the internal text information of the archive file, and generate archive file content feature data P, wherein the office software includes any one of OfficeSuite, SumatraPDF, and WPSOffice.

[0017] Preferably, the steps of collecting the archive file filing space image data and performing filing space classification folder recognition processing with the filing space folder image data to generate the filing space classification folder recognition result data are as follows:

[0018] S21, using screenshot software to collect an interface image of the initial filing space of the electronic archive management platform and generate archive file filing space image data A, wherein the screenshot software includes any one of Screenshot King, QQ Screenshot, and ShareX;

[0019] S22. Establishing an archive space folder image data set where a' m Represents the image data of the mth archive space folder, Indicates the maximum value of the number of archive space folder image data, wherein the archive space folder image data indicates the folder image data of archive files classified and archived in the archive space of the electronic archive management platform;

[0020] S23, using a breadth-first search algorithm to compare the archive file filing space image data A with the filing space folder image data set A'. m Perform image feature recognition of archive space classification folders, and generate archive space classification folder recognition result data A based on the image feature recognition results of archive space classification folders jieguo ;

[0021] When A and a' m The successful recognition of the image feature of the classified folder in the archive space indicates that there are classified and archived folders in the archive space of the electronic archive management platform, and the archive space classified folder recognition result data A is output. jieguo for existence;

[0022] When A and a' m If the image features of the classified folders in the archive space are not successfully identified, it means that there are no classified folders in the archive space of the electronic archive management platform, and the archive space classified folder identification result data A is output. jieguo Does not exist.

[0023] Preferably, when the recognition result is existence, the internal file information of the archive space classification folder is searched out and the file content feature data of the archive space classification folder is generated, and the archive file archiving target folder analysis and processing are performed based on the archive file content feature data and the archive space classification folder file content feature data, and the operation steps of generating the archive file archiving object folder data are as follows:

[0024] S31, when the archive space classification folder identification result data A jieguo When it exists, the BERT language model is used to retrieve the archive files in the archive space classification folder one by one and open and collect the internal text information of the archive files with office software to establish the archive space classification folder file content feature data set B = (b1,…,bn,…,b θ ), n = 1, 2, 3, ..., θ; where bn represents the collection of the file content feature data of the archive space classification folder corresponding to the nth classification folder, and θ represents the maximum number of archive space classification folder types;

[0025] S32, compare the archive file content feature data P with the archive space classification folder file content feature data set B. n Perform archive file content feature matching to search for the archive space classification folder file content feature data b that best matches the archive file content feature data P n , perform a search to find the b that best matches P n The execution steps are as follows:

[0026] S321, initialization, updating the maximum number of iterations T of the algorithm, and searching the location of the pelican population using text features;

[0027] S322, exploration stage, text feature search pelican determines the location of prey, that is, searches for archive space classification folder file content feature data set B in the search space that matches the archive file content feature data P. n The position of the prey is then moved to the determined position area, and the text feature search pelican approaching prey strategy is modeled. The text feature search pelican scans the search space of the archive space classification folder file content feature data set B, thereby increasing the exploration range of the text feature search pelican in different position areas in the search space of the archive space classification folder file content feature data set B; the position of the prey is randomly generated in the search space of the archive space classification folder file content feature data set B, that is, the archive space classification folder file content feature data b that matches the archive file content feature data P nIn the archive space classification folder file content feature data set B search space is randomly generated, text feature search pelican approach prey strategy formula is as follows: Among them, M i,j The position of the i-th text feature search pelican in the j-th dimension, that is, the position of the i-th text feature search pelican in the archive space classification folder file content feature data set B search space with a spatial dimension of θ, α represents a random integer for position adjustment, rand represents a random number in the range of [0,1], M' i,j is the position of the i-th text feature search pelican in the j-dimension after the exploration phase update, that is, the position of the i-th text feature search pelican in the archive space classification folder file content feature data set B with a spatial dimension of θ after the exploration phase update, J j is the position of the prey in the jth dimension, that is, the archive space classification folder file content feature data b that matches the archive file content feature data P n The position in the search space of the file content feature data set B in the archive space classification folder, Δ y is the objective function value of the prey, Δ i Search the objective function value of Pelican for the i-th text feature;

[0028] S323, in the development stage, the text feature search pelican performs hunting behavior; that is, searches for all archive space classification folder file content feature data b that match the archive file content feature data P in the archive space classification folder file content feature data set B search space n , the hunting behavior process of the text feature search pelican is modeled so that the algorithm converges to a better position in the hunting area. The algorithm operation process must check the position near the text feature search pelican position so that the algorithm hunts to a better position. The calculation formula for the text feature search pelican hunting behavior is as follows:

[0029] Where G' i ' ,j It represents the position of the ith text feature search pelican in the jth dimension after the development phase update, that is, the position of the ith text feature search pelican in the search space of the archive space classification folder file content feature data set B with dimension θ after the development phase update; Π is a random integer of 0 or 2; t is the current iteration number; T is the maximum iteration number;

[0030] S324, when the algorithm meets the maximum number of iterations, output the archive space classification folder file content feature data b that best matches the archive file content feature data P n ;

[0031] S33, based on the file content feature data b of the archive space classification folder output in step S324n Corresponding to the filing space classification folder type number identification generates archive file filing object folder data C n .

[0032] Preferably, the archiving space generated based on the archiving object folder data of the archive file executes step S2 cyclically until the recognition result is that it does not exist, and the operation steps of terminating the loop operation instruction are as follows:

[0033] S41, according to the archive file filing object folder data C n The corresponding archive folder is opened and a new archive file is generated. The archive space repeats the steps S21, S22 and S23 until the archive space classification folder recognition result data A is obtained. jieguo If it does not exist, the loop operation instruction ends.

[0034] Preferably, when the recognition result is that the file does not exist, the archive file archiving address is searched according to the archive file archiving object folder data, the archive file archiving address data is generated, and the interface image of each layer of archiving space is opened layer by layer to capture, and the archive file archiving address and image data are constructed and pushed to the archive management end. The operation steps are as follows:

[0035] S51, when the archive space classification folder identification result data A jieguo If it does not exist, a breadth-first search algorithm is used to search and obtain the archive file filing object folder data C n The storage address in the electronic archive management platform generates the archive file filing address data set D = (d1, ..., d o1 );where d1 represents the archive file filing address data of the first layer of the electronic archive management platform, d o1 Indicates the archival address data of the archive file at the o1 level of the electronic archive management platform;

[0036] S52, according to d1 to d in the archive file filing address data set D, o1 The filing space interface of the electronic archive management platform corresponding to each archive file filing address is opened in order layer by layer, and the interface image of each layer of the filing space and the file addresses d1 to d in the archive file filing address data set D are captured in order using the screenshot software. o1 Combine the address data to construct the archive file address and image data set E = (e1,…,e o1 ), where e1 represents the archive file filing address and image data after the archive file filing address data d1 and the matching archive space interface image are combined, e o1 Indicates the archive file filing address data d o1The archival file filing address and image data after data combination with the matching archiving space interface image;

[0037] S53: The archive file address and image data set E from e1 to e o1 The files are pushed to the archive management end in an orderly manner through the display screen.

[0038] Preferably, the collected archive file filing address calibration data and the archive file filing address data are subjected to archive file filing address correction processing to generate archive file filing address correction data in the following steps:

[0039] S61, using a voice recognition device, the online archive manager obtains storage address data that needs to be calibrated in the archive address of the archive file and generates archive address calibration data G;

[0040] S62: Compare the archive file filing address calibration data G with the archive file filing address characters in d1 to d2 of the archive file filing address data set D. o1 Perform archival file filing address recognition to correct the archival file filing address data in the archival file filing address data set D, and generate an archival file filing address correction data set D'=(d'1, ..., d' o2 ), where d'1 represents the archive address correction data of the archive file at the first level of the electronic archive management platform, d' o2 It represents the archive file filing address modification data of the archive file at the o2th layer of the electronic archive management platform, and the modification includes replacement and deletion.

[0041] Preferably, the operation steps of performing the archive file archiving operation according to the archive file archiving address correction data are as follows:

[0042] S71, modifying d'1 to d' in the data set D' according to the archive file filing address o2 Search and open the archive space where the archive file archiving address is located and execute the archive file archiving job.

[0043] A data processing system based on archival information, used to implement the data processing method based on archival information, the system comprises an archival file filing address judgment module, an archival file filing address feedback module, an archival file filing address correction and filing execution module;

[0044] The archive file filing address judgment module includes an archive file content parameter acquisition unit, an archive file filing space image acquisition unit, an archive space folder image storage unit, an archive space classification folder identification unit, an archive space classification folder content information search unit, an archive file filing object folder analysis unit, and an archive space classification folder identification circulation unit;

[0045] The archive file content parameter acquisition unit acquires archive file content feature data through office software; the archive file filing space image acquisition unit acquires archive file filing space image data through screenshot software; the archive space folder image storage unit is used to store archive space folder image data; the archive space classification folder recognition unit performs archive space classification folder recognition processing on the archive file filing space image data and the archive space folder image data to generate archive space classification folder recognition result data; the archive space classification folder content information search unit is used to search out the internal file information of the archive space classification folder and generate archive space classification folder file content feature data; the archive file filing object folder analysis unit performs archive file filing target folder analysis processing based on the archive file content feature data and the archive space classification folder file content feature data to generate archive file filing object folder data; the archive space classification folder recognition loop unit loops and executes the steps of acquiring archive file filing space image data and generating archive space classification folder recognition result data based on the archive space generated by the archive file filing object folder data until the recognition result is non-existent, and the loop operation instruction is terminated;

[0046] The archive file filing address feedback module includes an archive file filing address generation unit, an archive file filing address interface image capture unit, and an archive file filing address push unit;

[0047] The archive file filing address generating unit searches for the archive file filing address according to the archive file filing object folder data to generate the archive file filing address data; the archive file filing address interface image capturing unit opens and captures the interface image of each layer of filing space layer by layer according to the archive file filing address data to construct the archive file filing address and image data; the archive file filing address pushing unit pushes the archive file filing address and image data to the archive management terminal;

[0048] The archive file filing address correction and filing execution module includes an archive file filing address calibration information collection unit, an archive file filing address correction unit, and an archive file filing operation execution unit;

[0049] The archive file filing address calibration information collection unit collects archive file filing address calibration data through a voice recognition device; the archive file filing address correction unit performs archive file filing address correction processing on the archive file filing address calibration data and the archive file filing address data to generate archive file filing address correction data; the archive file filing job execution unit executes the archive file filing job according to the archive file filing address correction data.

[0050] (III) Beneficial effects

[0051] The present invention provides a data processing method and system based on archival information, which has the following beneficial effects:

[0052] 1. Accurately collect archive file text parameters and archive file filing space image parameters through office software and screenshot software to provide data support for intelligent archiving of archive files; use archive file filing space image parameters and scientifically pre-stored archive space folder image parameters to identify archive space classification folders, and accurately search whether there are multiple classification archive spaces in the archive file filing space; accurately search for file content feature parameters of archive files stored in multiple classification archive spaces and perform text character analysis with archive file content feature data to accurately determine the archive file filing target folder object; accurately identify the final filing target folder of the archive file, realize intelligent retrieval of archive file filing folders, and improve the efficiency of archiving archive files.

[0053] 2. Accurately retrieve the archival file filing address parameters; use screenshot software to open and capture the interface images of each layer of the archival space layer by layer, scientifically construct the archival file filing address and the corresponding archival file filing space image parameters, and realize the accurate digital image fusion of the archival file filing space address and the address space; push the archival file filing address and the corresponding archival file filing space image to the archive management end through the display screen visualization.

[0054] 3. By using voice recognition equipment to accurately collect the archival file filing address calibration parameters, and at the same time using the archival file filing address calibration data and the archival file filing address data for archival file filing address correction processing, the archival file filing address parameters are accurately corrected, thereby improving the accuracy of archival file filing address analysis; based on the archival file filing address correction parameters, the archival file filing operation is independently realized, thereby improving the quality and efficiency of archival file filing operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of a module of a data processing system based on archival information provided by the present invention;

[0056] Figure 2The present invention provides a flowchart of a data processing method based on archival information. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The embodiments of the data processing method and system based on archival information are as follows:

[0059] Embodiment 1:

[0060] See also Figure 1 - Figure 2 , a data processing method based on archival information, the method comprising the following steps:

[0061] S1. Collecting characteristic data of archive file contents;

[0062] S2, collecting archive file filing space image data and performing filing space classification folder recognition processing on filing space folder image data to generate filing space classification folder recognition result data;

[0063] S3. When the recognition result is existence, search for the internal file information of the archive space classification folder and generate the file content feature data of the archive space classification folder, perform archive file archiving target folder analysis and processing based on the archive file content feature data and the archive space classification folder file content feature data, and generate archive file archiving object folder data;

[0064] S4, looping and executing step S2 based on the archive space generated by the archive object folder data until the recognition result is that it does not exist, and then terminating the loop operation instruction;

[0065] S5. When the recognition result is that the file does not exist, the archive file filing address is searched according to the archive file filing object folder data, the archive file filing address data is generated, and the interface image of each layer of the filing space is opened layer by layer to capture, and the archive file filing address and image data are constructed and pushed to the archive management end;

[0066] S6, collecting the archive file filing address calibration data and the archive file filing address data, performing archive file filing address correction processing, and generating archive file filing address correction data;

[0067] S7. Modify the data according to the archive address and execute the archive operation.

[0068] For further information, see Figure 1 - Figure 2 ,The steps for collecting the content feature data of archive files are as follows:

[0069] S11. Use office software to open the archive file, collect the internal text information of the archive file and generate archive file content feature data P. The office software includes any one of OfficeSuite, SumatraPDF, and WPSOffice.

[0070] The steps for collecting archive file filing space image data and performing filing space classification folder recognition processing with filing space folder image data to generate filing space classification folder recognition result data are as follows:

[0071] S21, using screenshot software to capture an interface image of the initial filing space of the electronic archive management platform and generate archive file filing space image data A, the screenshot software including any one of Screenshot King, QQ Screenshot, and ShareX;

[0072] S22. Establishing an archive space folder image data set where a' m Represents the image data of the mth archive space folder, Indicates the maximum value of the number of archive space folder image data, and the archive space folder image data indicates the folder image data of archive files classified and archived in the archive space of the electronic archive management platform;

[0073] S23, using a breadth-first search algorithm to search the archive file filing space image data A and the filing space folder image data a' in the filing space folder image data set A'. m Perform image feature recognition of archive space classification folders, and generate archive space classification folder recognition result data A based on the image feature recognition results of archive space classification folders jieguo ;

[0074] When A and a' m The successful recognition of the image feature of the classified folder in the archive space indicates that there are classified and archived folders in the archive space of the electronic archive management platform, and the archive space classified folder recognition result data A is output. jieguo for existence;

[0075] When A and a' m If the image features of the classified folders in the archive space are not successfully identified, it means that there are no classified folders in the archive space of the electronic archive management platform, and the archive space classified folder identification result data A is output. jieguo Does not exist.

[0076] When the recognition result is existence, the internal file information of the archive space classification folder is searched out and the file content feature data of the archive space classification folder is generated. The archive file archiving target folder is analyzed and processed according to the archive file content feature data and the archive space classification folder file content feature data. The operation steps for generating the archive file archiving object folder data are as follows:

[0077] S31, when the archive space classification folder recognition result data A jieguo When it exists, the BERT language model is used to retrieve the archive files in the archive space classification folder one by one and open and collect the internal text information of the archive files with office software to establish the archive space classification folder file content feature data set B = (b1,…,b n ,…,b θ ), n=1,2,3,…,θ; where b n Indicates collecting the file content feature data of the archive space classification folder corresponding to the nth classification folder, θ the maximum number of archive space classification folder types;

[0078] S32, compare the archive file content feature data P with the archive space classification folder file content feature data set B. n Perform archival file content feature matching to search for the archival space classification folder file content feature data b that best matches the archival file content feature data P n , perform a search to find the b that best matches P n The execution steps are as follows:

[0079] S321, initialization, updating the maximum number of iterations T of the algorithm, and searching the location of the pelican population using text features;

[0080] S322, exploration stage, text feature search pelican determines the location of prey, that is, searches for archive space classification folder file content feature data set B in the search space that matches the archive file content feature data P. n The position of the prey is then moved to the determined position area, and the text feature search pelican approaching prey strategy is modeled. The text feature search pelican scans the search space of the archive space classification folder file content feature data set B, thereby increasing the exploration range of the text feature search pelican in different position areas in the search space of the archive space classification folder file content feature data set B; the position of the prey is randomly generated in the search space of the archive space classification folder file content feature data set B, that is, the archive space classification folder file content feature data b that matches the archive file content feature data P nIn the archive space classification folder file content feature data set B search space is randomly generated, text feature search pelican approach prey strategy formula is as follows: Among them, M i,j The position of the i-th text feature search pelican in the j-th dimension, that is, the position of the i-th text feature search pelican in the archive space classification folder file content feature data set B search space with a spatial dimension of θ, α represents a random integer for position adjustment, rand represents a random number in the range of [0,1], M' i,j is the position of the i-th text feature search pelican in the j-dimension after the exploration phase update, that is, the position of the i-th text feature search pelican in the archive space classification folder file content feature data set B with a spatial dimension of θ after the exploration phase update, J j is the position of the prey in the jth dimension, that is, the archive space classification folder file content feature data b that matches the archive file content feature data P n The position in the search space of the file content feature data set B in the archive space classification folder, Δ y is the objective function value of the prey, Δ i Search the objective function value of Pelican for the i-th text feature;

[0081] S323, in the development stage, the text feature search pelican performs hunting behavior; that is, searches for all archive space classification folder file content feature data b that match the archive file content feature data P in the archive space classification folder file content feature data set B search space n , the hunting behavior process of the text feature search pelican is modeled so that the algorithm converges to a better position in the hunting area. The algorithm operation process must check the position near the text feature search pelican position so that the algorithm hunts to a better position. The calculation formula for the text feature search pelican hunting behavior is as follows:

[0082] Where G' i ' ,j It represents the position of the ith text feature search pelican in the jth dimension after the development phase update, that is, the position of the ith text feature search pelican in the search space of the archive space classification folder file content feature data set B with dimension θ after the development phase update; Π is a random integer of 0 or 2; t is the current iteration number; T is the maximum iteration number;

[0083] S324, when the algorithm meets the maximum number of iterations, output the archive space classification folder file content feature data b that best matches the archive file content feature data P n ;

[0084] S33, based on the file content feature data b of the archive space classification folder output in step S324n Corresponding to the filing space classification folder type number identification generates archive file filing object folder data C n .

[0085] The archive space generated based on the archive object folder data executes step S2 in a loop until the recognition result is that it does not exist, and the operation steps of the loop operation instruction are as follows:

[0086] S41, according to the archive file file object folder data C n The corresponding archive folder is opened and a new archive file is generated. Steps S21, S22, and S23 are repeatedly executed in the archive space until the archive space classification folder recognition result data A is obtained. jieguo If it does not exist, the loop operation instruction ends.

[0087] Through the cooperation of the archive file content parameter acquisition unit and the archive file filing space image acquisition unit, office software and screenshot software are used to accurately collect archive file text parameters and archive file filing space image parameters, providing data support for intelligent archiving of archive files; the archive space classification folder recognition unit uses the archive file filing space image parameters and the scientifically pre-stored archive space folder image parameters to perform archive space classification folder recognition, and accurately searches out whether there are multiple classified archiving spaces in the archive file filing space; the archive space classification folder content information search unit and the archive file filing object folder analysis unit cooperate with each other to accurately search out the file content feature parameters of archive files stored in multiple classified archiving spaces and perform text character analysis with the archive file content feature data to accurately determine the archive file filing target folder object; the archive space classification folder recognition circulation unit realizes the accurate recognition of the final filing target folder of the archive file, realizes the intelligent retrieval of the archive file filing folder, and improves the archiving efficiency of the archive file.

[0088] For further information, see Figure 1 - Figure 2 When the recognition result is that it does not exist, the archive file archiving address is searched according to the archive file archiving object folder data, the archive file archiving address data is generated, and the interface image of each layer of archiving space is opened layer by layer to capture, and the archive file archiving address and image data are constructed and pushed to the archive management end. The operation steps are as follows:

[0089] S51, when the archive space classification folder recognition result data A jieguo If it does not exist, a breadth-first search algorithm is used to search and obtain the archive file object folder data C n The storage address in the electronic archive management platform generates the archive file filing address data set D = (d1, ..., d o1);where d1 represents the archive file filing address data of the first layer of the electronic archive management platform, d o1 Indicates the archival address data of the archive file at the o1 level of the electronic archive management platform;

[0090] S52, according to the archive file filing address data set D from d1 to d o1 The archiving space interface of the electronic archive management platform corresponding to each archival file archiving address is opened in order layer by layer, and the interface images of each layer of archiving space and the archival file archiving address data set D are captured in order by using the screenshot software. o1 Combine the address data to construct the archive file address and image data set E = (e1,…,e o1 ), where e1 represents the archive file filing address and image data after the archive file filing address data d1 and the matching archive space interface image are combined, e o1 Indicates the archive file filing address data d o1 The archival file filing address and image data after data combination with the matching archiving space interface image;

[0091] S53, archiving the archive file address and image data set E from e1 to e o1 The files are pushed to the archive management end in an orderly manner through the display screen.

[0092] The archive file filing address generation unit can be used to accurately retrieve the archive file filing address parameters; the archive file filing address interface image capture unit uses screenshot software to open and capture the interface image of each layer of the filing space layer by layer, and scientifically construct the archive file filing address and the corresponding archive file filing space image parameters to achieve accurate digital image fusion of the archive file filing space address and the address space; the archive file filing address push unit pushes the archive file filing address and the corresponding archive file filing space image to the archive management end through a display screen visualization.

[0093] For further information, see Figure 1 - Figure 2 , collect the archive file filing address calibration data and the archive file filing address data to perform archive file filing address correction processing, and the operating steps for generating archive file filing address correction data are as follows:

[0094] S61, using a voice recognition device, the online archive manager obtains storage address data that needs to be calibrated in the archive address of the archive file and generates archive address calibration data G;

[0095] S62, the archive file filing address calibration data G is compared with the archive file filing address data set D in d1 to d o1Perform archival file filing address recognition and modify the archival file filing address data in the archival file filing address data set D to generate the archival file filing address modification data set D'=(d'1, ..., d' o2 ), where d'1 represents the archive address correction data of the archive file at the first level of the electronic archive management platform, d' o2 Indicates the modification data of the archive file's archiving address at the o2th layer of the electronic archive management platform. Modification includes replacement and deletion.

[0096] The steps to perform the archive file archiving operation according to the archive file archiving address correction data are as follows:

[0097] S71, modify d'1 to d' in the data set D' according to the archive file filing address o2 Search and open the archive space where the archive file archiving address is located and execute the archive file archiving job.

[0098] Through the cooperation between the archive file filing address calibration information collection unit and the archive file filing address correction unit, the voice recognition equipment is used to accurately collect the archive file filing address calibration parameters, and the archive file filing address calibration data and the archive file filing address data are simultaneously processed for archive file filing address correction, so as to accurately correct the archive file filing address parameters and improve the accuracy of archive file filing address analysis; the archive file filing operation execution unit independently realizes the archive file filing operation according to the archive file filing address correction parameters, thereby improving the quality and efficiency of archive file filing operation management.

[0099] Embodiment 2:

[0100] See also Figure 1 - Figure 2 , a data processing system based on archival information, used to implement a data processing method based on archival information, the system includes an archival file filing address judgment module, an archival file filing address feedback module, an archival file filing address correction and filing execution module;

[0101] The archive file filing address judgment module includes an archive file content parameter acquisition unit, an archive file filing space image acquisition unit, an archive space folder image storage unit, an archive space classification folder recognition unit, an archive space classification folder content information search unit, an archive file filing object folder analysis unit, and an archive space classification folder recognition circulation unit;

[0102] An archive file content parameter acquisition unit, which acquires archive file content feature data through office software; an archive file filing space image acquisition unit, which acquires archive file filing space image data through screenshot software; an archive space folder image storage unit, which is used to store archive space folder image data; an archive space classification folder recognition unit, which performs archive space classification folder recognition processing on archive file filing space image data and archive space folder image data, and generates archive space classification folder recognition result data; an archive space classification folder content information search unit, which is used to search out the internal file information of the archive space classification folder and generate archive space classification folder file content feature data; an archive file filing object folder analysis unit, which performs archive file filing target folder analysis processing based on the archive file content feature data and the archive space classification folder file content feature data, and generates archive file filing object folder data; an archive space classification folder recognition loop unit, which loops and executes the steps of acquiring archive file filing space image data and generating archive space classification folder recognition result data based on the archive space generated by the archive file filing object folder data until the recognition result is non-existent, and ends the loop operation instruction;

[0103] The archive file filing address feedback module includes an archive file filing address generation unit, an archive file filing address interface image capture unit, and an archive file filing address push unit;

[0104] The archive file filing address generating unit searches for the archive file filing address according to the archive file filing object folder data and generates the archive file filing address data; the archive file filing address interface image capturing unit opens and captures the interface image of each layer of filing space layer by layer according to the archive file filing address data and constructs the archive file filing address and image data; the archive file filing address pushing unit pushes the archive file filing address and image data to the archive management terminal;

[0105] The archive file filing address correction and filing execution module includes an archive file filing address calibration information collection unit, an archive file filing address correction unit, and an archive file filing operation execution unit;

[0106] The archive file filing address calibration information collection unit collects the archive file filing address calibration data through the voice recognition device; the archive file filing address correction unit performs archive file filing address correction processing on the archive file filing address calibration data and the archive file filing address data to generate the archive file filing address correction data; the archive file filing job execution unit executes the archive file filing job according to the archive file filing address correction data.

[0107] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data processing method based on archival information, characterized in that: The method comprises the following steps: S1, collecting archive file content feature data, said S1 comprises the following steps: S11, using office software to open the archive file and collect the internal text information of the archive file and generate the archive file content feature data P; S2, collecting archive file filing space image data and performing filing space classification folder recognition processing on filing space folder image data to generate filing space classification folder recognition result data, said S2 includes the following steps: S21, capturing the interface image of the initial filing space of the electronic archive management platform through a screenshot software and generating archive file filing space image data A; S22. Establishing an archive space folder image data set where a' m Represents the image data of the mth archive space folder, Indicates the maximum value of the number of archive space folder image data, wherein the archive space folder image data indicates the folder image data of archive files classified and archived in the archive space of the electronic archive management platform; S23, the archive file filing space image data A and the filing space folder image data a' in the filing space folder image data set A' are combined. m Perform image feature recognition of archive space classification folders, and generate archive space classification folder recognition result data A based on the image feature recognition results of archive space classification folders jieguo ; When A and a' m The successful recognition of the image feature of the classified folder in the archive space indicates that there are classified and archived folders in the archive space of the electronic archive management platform, and the archive space classified folder recognition result data A is output. jieguo for existence; When A and a' m If the image features of the classified folders in the archive space are not successfully identified, it means that there are no classified folders in the archive space of the electronic archive management platform, and the archive space classified folder identification result data A is output. jieguo for not existing; S3. When the recognition result is existence, search for the internal file information of the archive space classification folder and generate the file content feature data of the archive space classification folder, perform archive file archiving target folder analysis and processing based on the archive file content feature data and the archive space classification folder file content feature data, and generate archive file archiving object folder data; S4, looping and executing step S2 based on the archive space generated by the archive object folder data until the recognition result is that it does not exist, and then terminating the loop operation instruction; S5. When the recognition result is that the file does not exist, the archive file archiving address is searched according to the archive file archiving object folder data, the archive file archiving address data is generated, and the interface image of each layer of archiving space is opened layer by layer to capture, and the archive file archiving address and image data are constructed and pushed to the archive management end; S6, collecting the archive file filing address calibration data and performing archive file filing address correction processing on the archive file filing address data to generate archive file filing address correction data; S7, performing the archive file archiving operation according to the archive file archiving address correction data.

2. A data processing method based on archival information according to claim 1, characterized in that: The S3 comprises the following steps: S31, when the archive space classification folder identification result data A jieguo When it exists, the BERT language model is used to retrieve the archive files in the archive space classification folder one by one and open and collect the internal text information of the archive files with office software to establish the archive space classification folder file content feature data set B = (b1,…,b n ,…,b θ ), n=1,2,3,…,θ; where b n Indicates collecting the file content feature data of the archive space classification folder corresponding to the nth classification folder, θ the maximum number of archive space classification folder types; S32, compare the archive file content feature data P with the archive space classification folder file content feature data set B. n Perform archive file content feature matching to search for the archive space classification folder file content feature data b that best matches the archive file content feature data P n , perform a search to find the b that best matches P n The execution steps are as follows: S321, initialization, updating the maximum number of iterations T of the algorithm, and searching the location of the pelican population using text features; S322, exploration stage, text feature search pelican determines the location of prey, that is, searches for archive space classification folder file content feature data set B in the search space that matches the archive file content feature data P. n The position of the prey is then moved to the determined position area, and the text feature search pelican approaching prey strategy is modeled. The text feature search pelican scans the search space of the archive space classification folder file content feature data set B, thereby increasing the exploration range of the text feature search pelican in different position areas in the search space of the archive space classification folder file content feature data set B; the position of the prey is randomly generated in the search space of the archive space classification folder file content feature data set B, that is, the archive space classification folder file content feature data b that matches the archive file content feature data P n The file content feature data set B in the archive space classification folder is randomly generated in the search space; S323, in the development stage, the text feature search pelican performs hunting behavior; that is, searches for all archive space classification folder file content feature data b that match the archive file content feature data P in the archive space classification folder file content feature data set B search space n , the hunting behavior process of the text feature search pelican is modeled so that the algorithm converges to a better position in the hunting area. The algorithm operation process must check the position near the text feature search pelican position so that the algorithm hunts to a better position; S324, when the algorithm meets the maximum number of iterations, output the archive space classification folder file content feature data b that best matches the archive file content feature data P n ; S33, based on the file content feature data b of the archive space classification folder output in step S324 n Corresponding to the archive space classification folder type number identification generates archive file archive object folder data C n .

3. A data processing method based on archival information according to claim 2, characterized in that: The S4 comprises the following steps: S41, according to the archive file filing object folder data C n The corresponding archive folder is opened and a new archive file is generated. The archive space repeats the steps S21, S22 and S23 until the archive space classification folder recognition result data A is obtained. jieguo If it does not exist, the loop operation instruction ends.

4. A data processing method based on archival information according to claim 3, characterized in that: The S5 comprises the following steps: S51, when the archive space classification folder identification result data A jieguo If it does not exist, a breadth-first search algorithm is used to search and obtain the archive file filing object folder data C n The storage address in the electronic archive management platform generates the archive file filing address data set D = (d1, ..., d o1 );where d1 represents the archive file filing address data of the first layer of the electronic archive management platform, d o1 Indicates the archival address data of the archive file at the o1 level of the electronic archive management platform; S52, according to d1 to d in the archive file filing address data set D, o1 The filing space interface of the electronic archive management platform corresponding to each archive file filing address is opened in order layer by layer, and the interface image of each layer of the filing space and the file addresses d1 to d in the archive file filing address data set D are captured in order using the screenshot software. o1 Combine the address data to construct the archive file address and image data set E = (e1,…,e o1 ), where e1 represents the archive file filing address and image data after the archive file filing address data d1 and the matching archive space interface image are combined, e o1 Indicates the archive file filing address data d o1 The archival file filing address and image data after data combination with the matching archiving space interface image; S53: The archive file address and image data set E from e1 to e o1 The files are pushed to the archive management end in an orderly manner through the display screen.

5. A data processing method based on archival information according to claim 4, characterized in that: The S6 comprises the following steps: S61, using a voice recognition device, the online archive manager obtains storage address data that needs to be calibrated in the archive address of the archive file and generates archive address calibration data G; S62: Compare the archive file filing address calibration data G with the archive file filing address characters in d1 to d2 of the archive file filing address data set D. o1 Perform archival file filing address recognition to correct the archival file filing address data in the archival file filing address data set D, and generate an archival file filing address correction data set D'=(d'1, ..., d' o2 ), where d'1 represents the archive address correction data of the archive file at the first level of the electronic archive management platform, d' o2 It represents the archive file filing address modification data of the archive file at the o2th layer of the electronic archive management platform, and the modification includes replacement and deletion.

6. A data processing method based on archival information according to claim 5, characterized in that: The S7 comprises the following steps: S71, modifying d'1 to d' in the data set D' according to the archive file filing address o2 Search and open the archive space where the archive file archiving address is located and execute the archive file archiving job.

7. A data processing system based on archival information, used to implement a data processing method based on archival information according to any one of claims 1 to 6, characterized in that: The system comprises an archive file filing address judgment module, an archive file filing address feedback module, and an archive file filing address correction and filing execution module.

Images