Digital processing method, system and equipment for paper archives based on artificial intelligence

Abstract

The present invention relates to a method, system and device for digital processing of paper archives based on artificial intelligence. The method comprises: scanning paper documents to be processed by a scanner to obtain a picture electronic document set; scanning and monitoring the picture electronic document set based on an artificial intelligence visual recognition picture feature model to obtain an electronic document set to be processed; processing the electronic document set to be processed by a logic algorithm to obtain a target electronic document set; based on an artificial intelligence visual recognition tag data model, performing piece-by-piece processing on the target electronic document set to obtain a plurality of target folders; packaging the target electronic file in each of the target folders into a formatted electronic file of a target format; based on an artificial intelligence directory extraction model, extracting data from each of the formatted electronic files and outputting an electronic directory to realize digital processing of the paper documents to be processed, thereby effectively improving the efficiency of digitization of paper archives.

Description

Technical Field

[0001] The present invention belongs to the technical field of archive digitization, and specifically relates to a method, system and equipment for digital processing of paper archives based on artificial intelligence. Background Art

[0002] Archives management is very important for any industry. With the continuous development of the times, paper archives are gradually being eliminated. Electronic archives are gradually replacing paper archives due to their convenience, easy storage and easy query. The previous paper archives need to be digitized to ensure the timeliness of the archives. At present, most of the digitization of paper archives is done manually, which is relatively inefficient and consumes a lot of manpower costs.

[0003] Therefore, how to improve the digital processing of paper archives has become a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0004] In order to at least solve the above-mentioned problems existing in the prior art, the present invention provides a method, system and device for digital processing of paper archives based on artificial intelligence.

[0005] The technical solution provided by the present invention is as follows:

[0006] On the one hand, a method for digital processing of paper archives based on artificial intelligence, comprising:

[0007] Scan the paper documents to be processed by a scanner to obtain an electronic file set of images;

[0008] Based on an artificial intelligence visual recognition image feature model, the electronic file set of the image is scanned and monitored to obtain the electronic file set to be processed;

[0009] Processing the electronic file set to be processed by a logical algorithm to obtain a target electronic file set;

[0010] Based on the artificial intelligence visual recognition tag data model, the target electronic file set is processed into pieces to obtain a plurality of target folders, each of which includes the same target electronic file;

[0011] Packing the target electronic files in each of the target folders into a formatted electronic file in a target format;

[0012] Based on the artificial intelligence directory extraction model, data is extracted from each electronic file in the format, and an electronic directory is output to realize digital processing of the paper files to be processed.

[0013] Optionally, before scanning the paper document to be processed by a scanner to obtain the electronic image file set, the method further includes:

[0014] Classifying and arranging a first preset number of electronic image files according to different feature classifications, and producing a second preset number of feature training samples, wherein the features include black edge features, folding features, fading features, blank features, tilt features, and inversion features;

[0015] The second preset number of feature training samples are trained based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition picture feature model. The artificial intelligence visual recognition picture feature model is also used to identify different types of errors and repair the error features through corresponding program algorithms according to different error features.

[0016] Optionally, the electronic image file set is obtained by sequentially scanning paper documents;

[0017] Before scanning the paper document to be processed by a scanner to obtain the electronic image file set, the method further includes:

[0018] Classifying and arranging a third preset number of electronic image files according to different label categories, and producing a fourth preset number of label training samples, wherein the labels include a home page label, a middle page label, and a last page label;

[0019] The fourth preset number of label training samples are trained based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition label data model.

[0020] Optionally, the target electronic file set is processed into pieces based on the artificial intelligence visual recognition tag data model to obtain multiple target folders, including:

[0021] Based on the artificial intelligence visual recognition tag data model, the target electronic file set is searched on the first page and the last page;

[0022] According to the results of the first page search and the last page search, multiple target folders are established according to preset rules.

[0023] Optionally, after establishing multiple target folders according to preset rules, the method further includes:

[0024] Reading text content of each image of the target electronic file in each of the target folders by optical character recognition;

[0025] The text content of each image is analyzed through artificial intelligence semantic recognition, and whether the target electronic files in the target folder are the same file is verified.

[0026] Optionally, after constructing the artificial intelligence visual recognition label data model, the method further includes:

[0027] Using an artificial intelligence visual recognition label data model, batch-process the electronic image files carrying the home page label and place them into a specific sample folder;

[0028] Model annotation is performed on the electronic image files carrying the home page label in the specific sample folder according to the requirement rules to obtain a fifth preset number of annotation samples, wherein the requirement rules include a case number rule, a filing unit rule, a directory name rule, a document number rule, a responsible person rule, a file number rule, a page number rule, a year rule, and a date rule;

[0029] The fifth preset number of labeled samples are trained based on an artificial intelligence structured algorithm to obtain an artificial intelligence catalog extraction model.

[0030] Optionally, after obtaining the artificial intelligence catalog extraction model as described above, the method further includes:

[0031] Performing additional annotation processing on the unannotated electronic image files in the specific sample folder to obtain verification annotation samples;

[0032] The verification and annotation samples are verified and trained based on an artificial intelligence structured algorithm to obtain a verification model as the artificial intelligence catalog extraction model.

[0033] Optionally, the output electronic catalogue includes:

[0034] Output electronic catalogs in different formats according to preset filing rules or file management software rules.

[0035] In another aspect, a paper archive digital processing system includes:

[0036] A scanning module is used to scan the paper documents to be processed through a scanner to obtain an electronic file set of images;

[0037] A processing module is used to scan and monitor the electronic file set of the image based on an artificial intelligence visual recognition image feature model to obtain the electronic file set to be processed; and to process the electronic file set to be processed through a logical algorithm to obtain a target electronic file set;

[0038] A subdivision module, for performing subdivision processing on the target electronic file set based on an artificial intelligence visual recognition tag data model to obtain a plurality of target folders, each of which includes the same target electronic file;

[0039] The digital generation module is used to package the target electronic files in each of the target folders into electronic files in a target format; based on an artificial intelligence directory extraction model, data is extracted from each electronic file in the target format, and an electronic directory is output to realize digital processing of the paper files to be processed.

[0040] In another aspect, a digital processing device for paper archives includes: a processor, and a memory connected to the processor;

[0041] The memory is used to store a computer program, and the computer program is used to at least execute any one of the above-mentioned methods for digital processing of paper archives based on artificial intelligence;

[0042] The processor is used to call and execute the computer program in the memory.

[0043] The beneficial effects of the present invention are:

[0044] The present invention provides an artificial intelligence-based digital processing method, system and equipment for paper archives, the method comprising: scanning paper documents to be processed by a scanner to obtain a picture electronic file set; based on an artificial intelligence visual recognition picture feature model, scanning and monitoring the picture electronic file set to obtain a set of electronic files to be processed; processing the set of electronic files to be processed by a logical algorithm to obtain a target electronic file set; based on an artificial intelligence visual recognition label data model, segmenting the target electronic file set to obtain multiple target folders, each of which includes the same target electronic file; packaging the target electronic files in each of the target folders into a formatted electronic file in a target format; based on an artificial intelligence directory extraction model, extracting data from each of the formatted electronic files, and outputting an electronic directory to realize digital processing of the paper documents to be processed, all processes after the scanning is completed are completed by machine automation, and only a small number of personnel are required to monitor, which saves a lot of labor costs while effectively improving the efficiency of paper archive digitization. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a flow chart of a method for digital processing of paper archives based on artificial intelligence provided by an embodiment of the present invention;

[0047] Figure 2 This is a structural schematic diagram of a digital processing system for paper archives based on artificial intelligence provided by an embodiment of the present invention;

[0048] Figure 3 The present invention is a schematic diagram of a structure of a digital processing device for paper archives based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0050] Figure 1 The present invention provides a flowchart of a method for digitalizing paper archives based on artificial intelligence.

[0051] like Figure 1 As shown, this embodiment provides a method for digital processing of paper archives based on artificial intelligence, comprising the following steps:

[0052] S11. Scan the paper document to be processed by a scanner to obtain an electronic file set of images.

[0053] A file that needs to be scanned and digitized is defined as a paper file to be processed. In this embodiment, a paper file is used as an example for explanation. However, in actual application, it is not limited to paper file files, and other paper files can also be used. As long as the paper files need to be digitized, they can be called paper files to be processed. Since the paper files to be processed are scanned one by one, the scan results obtained are all the electronic files of the pictures, which can be called a set of electronic files of pictures.

[0054] S12. Based on the artificial intelligence visual recognition image feature model, the electronic file set of the image is scanned and monitored to obtain the electronic file set that needs to be processed.

[0055] S13. Process the electronic file set to be processed by means of a logic algorithm to obtain a target electronic file set.

[0056] Specifically, before scanning the paper documents to be processed by a scanner to obtain the image electronic file set, it also includes: classifying and arranging the first preset number of image electronic files according to different feature classifications, and preparing a second preset number of feature training samples, the features include black edge features, folding features, fade features, blank features, tilt features and inverted features, etc.; training the second preset number of feature training samples based on an artificial intelligence visual recognition algorithm to build an artificial intelligence visual recognition image feature model, which is also used to identify different types of errors, and repair the error features through corresponding program algorithms according to different error features. By training on different image features, an image feature model is obtained, and then, it can be identified according to the image feature model, and the image electronic file set is scanned and monitored. For the image electronic file set that meets the model features, artificial intelligence visual recognition is performed to detect which ones need to be processed, and the files that need to be processed and meet the model features are processed through corresponding logic and algorithms to obtain the target electronic file set, and the target electronic file set achieves the effect of a normal electronic file.

[0057] S14. Based on the artificial intelligence visual recognition label data model, the target electronic file set is divided into pieces to obtain multiple target folders, each of which includes the same target electronic file.

[0058] Specifically, when scanning paper archive files, the scanning order is the order in which the original paper files are placed in the archive box, so as to ensure that the order of the obtained electronic image files is the relevant order of the original paper files. Before scanning the paper files to be processed by the scanner to obtain the electronic image file set, it also includes: classifying and arranging the third preset number of electronic image files according to different label classifications, and preparing a fourth preset number of label training samples, the labels include the first page label, the middle page label and the last page label; training the fourth preset number of label training samples based on the artificial intelligence visual recognition algorithm, and constructing an artificial intelligence visual recognition label data model.

[0059] Specifically, based on the artificial intelligence visual recognition label data model, the target electronic file set is divided into pieces to obtain multiple target folders, including: based on the artificial intelligence visual recognition label data model, the target electronic file set is searched on the first page and the last page; the main function of the artificial intelligence visual recognition label data model is to label the image electronic files to ensure that it can be distinguished whether the location of each image is the first page, the last page or the middle page, and then according to the results of the first page search and the last page search, multiple target folders are established according to preset rules, that is, multiple images of the same file are placed in the same folder according to the preset rules, so that each folder contains the same file, and the quality and effect of the electronic files can also be guaranteed.

[0060] After establishing multiple target folders according to preset rules, it also includes: reading the text content of each image of the target electronic file in each target folder through optical character recognition; analyzing the text content of each image through artificial intelligence semantic recognition, and verifying whether the target electronic files in the target folder are the same file. The image files in the same folder are semantically recognized through artificial intelligence semantic recognition function, and the correlation between each image is determined through voice analysis, and finally it is determined whether the files in the folder are the same file, so as to realize repeated verification of the files and ensure the correctness of the files.

[0061] S15. Pack the target electronic files in each target folder into a target format electronic file.

[0062] The above steps complete the segmentation of the electronic file set, that is, it is divided into multiple different folders, each folder contains the same archive electronic file, and for the folders that have been segmented, they are automatically packaged into electronic files of the target format according to the order of the image electronic files in the folders, for example, they can be packaged into PDF files.

[0063] S16. Based on the artificial intelligence catalog extraction model, data is extracted from each format of electronic files and an electronic catalog is output to realize digital processing of paper files to be processed.

[0064] Specifically, after constructing the artificial intelligence visual recognition label data model, it also includes: batch processing the electronic image files with the home page label through the artificial intelligence visual recognition label data model and placing them in a specific sample folder; model annotating the electronic image files with the home page label in the specific sample folder according to the required rules to obtain the fifth preset number of annotated samples, the required rules include the archive number rule, the filing unit rule, the directory name rule, the document number rule, the responsible person rule, the item number rule, the page number rule, the year rule and the date rule; training the fifth preset number of annotated samples based on the artificial intelligence structured algorithm to obtain the artificial intelligence directory extraction model. After obtaining the artificial intelligence directory extraction model, it also includes: adding annotating processing to the unannotated electronic image files in the specific sample folder to obtain the verification annotated samples; verifying and training the verification annotated samples based on the artificial intelligence structured algorithm to obtain the verification model as the artificial intelligence directory extraction model.

[0065] After obtaining the artificial intelligence catalog extraction model, data is extracted from each electronic file format based on the artificial intelligence catalog extraction model and stored in the database. Since each file has a catalog name, responsible person, filing unit, date and other related attributes, data is extracted for the attribute to obtain a pre-selected catalog, and then the pre-selected catalog is processed again, and according to the preset filing rules or archive management software rules, electronic catalogs suitable for different formats are output, including Excel format, XML format, etc.

[0066] The present embodiment provides an artificial intelligence-based digital processing method for paper archives, comprising: scanning paper documents to be processed by a scanner to obtain a picture electronic file set; based on an artificial intelligence visual recognition picture feature model, scanning and monitoring the picture electronic file set to obtain a set of electronic files to be processed; processing the set of electronic files to be processed by a logical algorithm to obtain a target electronic file set; based on an artificial intelligence visual recognition tag data model, segmenting the target electronic file set to obtain a plurality of target folders, each of which includes the same target electronic file; packaging the target electronic files in each of the target folders into a formatted electronic file in a target format; based on an artificial intelligence directory extraction model, extracting data from each of the formatted electronic files and outputting an electronic directory to realize digital processing of the paper documents to be processed. All processes after the scanning are completed are completed by machine automation, and only a small number of personnel are required to monitor. While greatly saving labor costs, it also effectively improves the efficiency of paper archive digitization. From the beginning of processing, the entire process is automatically completed by the machine in batches and steps. One person can be responsible for monitoring multiple links at the same time, which greatly saves labor costs and has the characteristics of low cost, high efficiency, short time consumption, high precision and reuse. By combining computer technology, artificial intelligence, program algorithms, etc., the whole process of archive digitization work has been comprehensively integrated and improved, and different solutions can be output for different industries, so that modeling can be used multiple times once.

[0067] Based on the same general inventive concept, the present application also protects a digital processing system for paper archives based on artificial intelligence.

[0068] Figure 2 The present invention is a schematic diagram of a digital processing system for paper archives based on artificial intelligence.

[0069] like Figure 2 As shown, this embodiment provides a digital processing system for paper archives based on artificial intelligence, including:

[0070] The scanning module 10 is used to scan the paper documents to be processed through a scanner to obtain an electronic file set of images;

[0071] The processing module 20 is used to scan and monitor the electronic file set of the image based on the artificial intelligence visual recognition image feature model to obtain the electronic file set to be processed; the electronic file set to be processed is processed through a logical algorithm to obtain a target electronic file set;

[0072] A division module 30 is used to divide the target electronic file set into pieces based on an artificial intelligence visual recognition tag data model to obtain a plurality of target folders, each of which includes the same target electronic file;

[0073] The digital generation module 40 is used to package the target electronic files in each target folder into formatted electronic files in the target format; based on the artificial intelligence directory extraction model, data is extracted from each formatted electronic file, and an electronic directory is output to realize digital processing of the paper files to be processed.

[0074] The present embodiment provides an artificial intelligence-based paper archive digital processing system, comprising: scanning the paper documents to be processed by a scanner to obtain a picture electronic file set; based on an artificial intelligence visual recognition picture feature model, scanning and monitoring the picture electronic file set to obtain a set of electronic files to be processed; processing the set of electronic files to be processed by a logical algorithm to obtain a target electronic file set; based on an artificial intelligence visual recognition tag data model, segmenting the target electronic file set to obtain a plurality of target folders, each of which includes the same target electronic file; packaging the target electronic files in each of the target folders into a formatted electronic file in a target format; based on an artificial intelligence directory extraction model, extracting data from each of the formatted electronic files and outputting an electronic directory to realize digital processing of the paper documents to be processed. All processes after the scanning are completed are completed by machine automation, and only a small number of personnel are required to monitor. While greatly saving labor costs, it also effectively improves the efficiency of paper archive digitization. From the beginning of processing, the entire process is automatically completed by the machine in batches and steps. One person can be responsible for monitoring multiple links at the same time, which greatly saves labor costs and has the characteristics of low cost, high efficiency, short time consumption, high precision and reuse. By combining computer technology, artificial intelligence, program algorithms, etc., the whole process of archive digitization work has been comprehensively integrated and improved, and different solutions can be output for different industries, so that modeling can be used multiple times once.

[0075] The embodiments of the device part have been introduced and explained in detail in the corresponding method embodiments. Therefore, no specific explanation will be given in the corresponding device part, and they can be understood by reference to each other.

[0076] Based on the same general inventive concept, the present application also protects a digital processing device for paper archives based on artificial intelligence.

[0077] Figure 3 The present invention is a schematic diagram of a structure of a digital processing device for paper archives based on artificial intelligence provided by an embodiment of the present invention.

[0078] like Figure 3 As shown, the present embodiment provides a digital processing device for paper archives based on artificial intelligence, comprising: a processor, and a memory connected to the processor;

[0079] The memory is used to store a computer program, and the computer program is used to at least execute the digital processing method of paper archives based on artificial intelligence in any of the above embodiments;

[0080] The processor is used to call and execute the computer program in the memory.

[0081] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0082] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0083] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0084] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0085] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0087] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0088] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0090] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for digital processing of paper archives based on artificial intelligence, characterized in that: include: Classifying and arranging a first preset number of electronic image files according to different feature classifications, and producing a second preset number of feature training samples, wherein the features include black edge features, folding features, fading features, blank features, tilt features, and inversion features; The second preset number of feature training samples are trained based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition picture feature model; the artificial intelligence visual recognition picture feature model is also used to identify different types of errors, and repair the error features through corresponding program algorithms according to different error features; Classifying and arranging a third preset number of electronic image files according to different label categories, and producing a fourth preset number of label training samples, wherein the labels include a home page label, a middle page label, and a last page label; Training the fourth preset number of label training samples based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition label data model; Using an artificial intelligence visual recognition label data model, batch-process the electronic image files carrying the home page label and place them into a specific sample folder; Model annotation is performed on the electronic image files carrying the home page label in the specific sample folder according to the requirement rules to obtain a fifth preset number of annotation samples, wherein the requirement rules include a case number rule, a filing unit rule, a directory name rule, a document number rule, a responsible person rule, a file number rule, a page number rule, a year rule, and a date rule; Training the fifth preset number of labeled samples based on an artificial intelligence structured algorithm to obtain an artificial intelligence catalog extraction model; Scanning the paper documents to be processed by a scanner to obtain an electronic picture file set; the electronic picture file set is obtained by sequentially scanning the paper documents; Based on an artificial intelligence visual recognition image feature model, the electronic file set of the image is scanned and monitored to obtain the electronic file set to be processed; Processing the electronic file set to be processed by a logical algorithm to obtain a target electronic file set; Based on the artificial intelligence visual recognition tag data model, the target electronic file set is processed into pieces to obtain a plurality of target folders, each of which includes the same target electronic file; Packing the target electronic files in each of the target folders into a formatted electronic file in a target format; Based on the artificial intelligence directory extraction model, data is extracted from each electronic file in the format, and an electronic directory is output to realize digital processing of the paper files to be processed.

2. The method for digital processing of paper archives based on artificial intelligence according to claim 1 is characterized in that: The target electronic file set is processed into pieces based on the artificial intelligence visual recognition tag data model to obtain multiple target folders, including: Based on the artificial intelligence visual recognition tag data model, the target electronic file set is searched on the first page and the last page; According to the results of the first page search and the last page search, multiple target folders are established according to preset rules.

3. The method for digital processing of paper archives based on artificial intelligence according to claim 2 is characterized in that: After the multiple target folders are established according to the preset rules, the method further includes: Reading text content of each image of the target electronic file in each of the target folders by optical character recognition; The text content of each image is analyzed through artificial intelligence semantic recognition, and whether the target electronic files in the target folder are the same file is verified.

4. The method for digital processing of paper archives based on artificial intelligence according to claim 1 is characterized in that: After obtaining the artificial intelligence directory extraction model, the method further includes: Performing additional annotation processing on the unannotated electronic image files in the specific sample folder to obtain verification annotation samples; The verification and annotation samples are verified and trained based on an artificial intelligence structured algorithm to obtain a verification model as the artificial intelligence catalog extraction model.

5. The method for digital processing of paper archives based on artificial intelligence according to claim 1 is characterized in that: The output electronic catalogue includes: Output electronic catalogs in different formats according to preset filing rules or file management software rules.

6. A paper archive digital processing system, characterized in that: include: A scanning module, used to scan the paper documents to be processed by a scanner to obtain a picture electronic file set; and also used to classify and sort a first preset number of picture electronic files according to different feature classifications before scanning the paper documents to be processed by a scanner to obtain the picture electronic file set, and to prepare a second preset number of feature training samples, wherein the features include black edge features, folding features, fade features, blank features, tilt features, and inverted features; The second preset number of feature training samples are trained based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition picture feature model; the artificial intelligence visual recognition picture feature model is also used to identify different types of errors, and repair the error features through corresponding program algorithms according to different error features; Classifying and arranging a third preset number of electronic image files according to different label categories, and producing a fourth preset number of label training samples, wherein the labels include a home page label, a middle page label, and a last page label; Training the fourth preset number of label training samples based on an artificial intelligence visual recognition algorithm to construct an artificial intelligence visual recognition label data model; Using an artificial intelligence visual recognition label data model, batch-process the electronic image files carrying the home page label and place them into a specific sample folder; Model annotation is performed on the electronic image files carrying the home page label in the specific sample folder according to the requirement rules to obtain a fifth preset number of annotation samples, wherein the requirement rules include a case number rule, a filing unit rule, a directory name rule, a document number rule, a responsible person rule, a file number rule, a page number rule, a year rule, and a date rule; Training the fifth preset number of labeled samples based on an artificial intelligence structured algorithm to obtain an artificial intelligence catalog extraction model; A processing module is used to scan and monitor the electronic file set of the image based on an artificial intelligence visual recognition image feature model to obtain the electronic file set to be processed; and to process the electronic file set to be processed through a logical algorithm to obtain a target electronic file set; A subdivision module, for performing subdivision processing on the target electronic file set based on an artificial intelligence visual recognition tag data model to obtain a plurality of target folders, each of which includes the same target electronic file; A digital generation module, used for packaging the target electronic files in each of the target folders into a formatted electronic file in a target format; Based on the artificial intelligence directory extraction model, data is extracted from each electronic file in the format, and an electronic directory is output to realize digital processing of the paper files to be processed.

7. A digital processing device for paper archives, characterized in that: include: A processor, and a memory connected to the processor; The memory is used to store a computer program, and the computer program is used to at least execute the method for digital processing of paper archives based on artificial intelligence according to any one of claims 1 to 5; The processor is used to call and execute the computer program in the memory.

Images