Electronic archive filing management system based on artificial intelligence
By utilizing artificial intelligence-based electronic archive management systems and employing natural language processing and deep learning technologies, automatic classification and intelligent retrieval of electronic archives have been achieved. This has solved the problem of low efficiency in traditional management methods and improved the efficiency and accuracy of archive management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANDONG YILU TECH CO LTD
- Filing Date
- 2026-03-09
- Publication Date
- 2026-06-05
AI Technical Summary
Traditional electronic record management methods are time-consuming, labor-intensive, inefficient, and inaccurate, and are easily affected by human factors, making it difficult to meet the needs of modern record management for high efficiency, accuracy, and security.
An AI-based electronic records archiving management system is adopted, which utilizes natural language processing, machine learning, and deep learning technologies to achieve automatic classification and intelligent retrieval of electronic records. Through classification analysis and retrieval analysis modules, accurate classification and efficient organization are carried out. Combined with intelligent retrieval and content analysis functions, the efficiency and accuracy of records management are improved.
It significantly improves the efficiency and accuracy of electronic records management, reduces manual operation steps, avoids errors and information omissions caused by human factors, and realizes efficient management of massive archives and in-depth mining of information value.
Smart Images
Figure CN122153143A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of electronic records management technology, specifically an artificial intelligence-based electronic records archiving and management system. Background Technology
[0002] With the rapid development of information technology, electronic archives, as an important product of the information age, have experienced explosive growth in quantity. Traditional electronic archive management methods mainly rely on manual operations, including the classification, organization, storage, and retrieval of archives. These tasks are not only time-consuming and labor-intensive but also easily affected by human factors, leading to problems such as low management efficiency, insufficient accuracy, and security risks. Especially when faced with massive amounts of electronic archives, manual management methods are inadequate and fail to meet the demands of modern archive management for efficiency, accuracy, and security.
[0003] At the same time, the rapid development of artificial intelligence technology has brought new opportunities to electronic records management. Natural language processing, machine learning, deep learning, image recognition, and other AI technologies have demonstrated powerful capabilities in data processing, pattern recognition, and intelligent decision-making. Applying these technologies to electronic records management can achieve functions such as automatic classification, intelligent retrieval, content analysis, and security assurance, thereby significantly improving the efficiency, accuracy, and security of records management.
[0004] Based on this, in order to achieve intelligent management of electronic archives, the present invention provides an electronic archive archiving and management system based on artificial intelligence. Summary of the Invention
[0005] To address the problems of the aforementioned solutions, this invention provides an artificial intelligence-based electronic archive management system.
[0006] The objective of this invention can be achieved through the following technical solutions: An AI-based electronic records archiving and management system, including a platform and a user terminal; Furthermore, the platform establishes communication connections with each user terminal.
[0007] The platform includes a classification analysis module and a retrieval analysis module; The classification analysis module is used to perform classification analysis, identify various potential classification methods, perform keyword simulation classification based on various potential classification methods, obtain various classification feature items, set and update the corresponding classification word recognition method based on each classification feature item, and configure the classification word recognition method in the archiving module on the user end.
[0008] Furthermore, keyword simulation classification is performed based on various potential classification methods, including: Identify the classification items corresponding to each potential classification method, remove duplicates from each identified classification item, and mark the remaining items as classification feature items.
[0009] Furthermore, keyword simulation classification is performed based on various potential classification methods, including: Identify the classification items corresponding to each potential classification method, and remove duplicates from each identified classification item; perform effect conflict analysis on each deduplicated classification item to obtain the effect conflict results between each classification item. The results of identifying conflicting effects are the corresponding categories. The category with higher priority is retained, the other category is removed, and the remaining categories are marked as classification features.
[0010] Furthermore, after eliminating classification items based on the results of conflicting effects, each classification item is simulated and verified based on the pre-acquired classification materials. When the verification is successful, each classification item is marked as a classification feature item.
[0011] The retrieval analysis module is used to perform retrieval analysis, obtain the user's search term recognition method, and configure the search term recognition method in the archiving module on the user's end.
[0012] The user terminal includes an archiving module, an archive repository, an archive management module, and a retrieval module; The archiving module is used to archive electronic archives, identify electronic archives that need to be archived in real time, identify electronic archives according to preset classification word recognition methods and search word recognition methods, obtain the classification word set and search word set of the electronic archives, mark the classification word set and search word set on the electronic archives, and store the electronic archives in the archive database.
[0013] Furthermore, the preset classification term recognition method and search term recognition method are evaluated in real time to obtain the update evaluation results corresponding to the classification term recognition method and search term recognition method respectively. The update evaluation results include those that need to be updated and those that do not need to be updated. When the updated evaluation result indicates that an update is needed, the classification term set or search term set of the corresponding electronic archives in the archive database is adjusted using the corresponding classification term recognition method or search term recognition method; No adjustments will be made if the updated assessment result indicates that no update is needed.
[0014] Furthermore, the classification term set or search term set of the corresponding electronic archives in the archive database is adjusted by using the corresponding classification term recognition method or search term recognition method, while retaining the original classification term set or search term set.
[0015] Furthermore, the classification term set or search term set of the corresponding electronic archives in the archive database is adjusted by using the corresponding classification term recognition method or search term recognition method, and the original classification term set or search term set is not retained.
[0016] Furthermore, the preset classification term recognition method and search term recognition method are updated and evaluated in real time, including: The system acquires real-time updated data for preset classification word recognition methods and search word recognition methods, establishes an update evaluation model, and the expression for the update evaluation model is: ; In the formula: s is the input data, representing the updated data of the corresponding classification word recognition method or search word recognition method; the output data is the updated evaluation value GP(s), which is 1 or 0; By updating the model, the updated data of the classification word recognition method and the search word recognition method are analyzed in real time to obtain the corresponding update evaluation results.
[0017] The archive is used to store electronic records.
[0018] The document management module is used for document management, real-time acquisition of users' document classification requirements, analysis of document classification requirements, acquisition of document classification rules, and classification and management of electronic documents in the archive according to the document classification rules.
[0019] The search module is used by users to search for files, obtain search results, and display the search results to users.
[0020] Artificial intelligence-based electronic record archiving and management methods include: The platform sets and updates the category word recognition method and search word recognition method in real time, and configures the category word recognition method and search word recognition method on the user's end. Electronic archives are identified using classification term recognition and search term recognition methods to obtain classification term sets and search term sets for electronic archives. The classification term sets and search term sets are then marked on the electronic archives, and the electronic archives are stored in the archive database. The system acquires users' document classification requirements in real time, analyzes these requirements to obtain document classification rules, and then classifies and manages electronic archives in the archive database according to these rules. The system acquires the user's search data, performs searches based on the search terms of the search data and the various electronic archives in the database, obtains the search results, and displays the search results to the user.
[0021] Compared with the prior art, the beneficial effects of the present invention are: By integrating cutting-edge artificial intelligence technologies such as natural language processing, machine learning, deep learning, and image recognition, the system can automatically complete the accurate classification and efficient organization of electronic archives, significantly reducing manual operations and improving management efficiency. It effectively overcomes the drawbacks of traditional manual management methods, which are time-consuming, labor-intensive, and inefficient when dealing with massive amounts of archives. At the same time, with the help of intelligent retrieval and content analysis functions, the system can quickly locate the required archives and deeply mine the value of archive information, greatly improving the accuracy of archive retrieval and the fullness of information utilization, and avoiding retrieval errors and information omissions caused by human factors. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0023] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation
[0024] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0025] like Figure 1 As shown, the AI-based electronic records archiving management system includes a platform and a user terminal. The platform establishes communication connections with each user terminal.
[0026] The platform is used to provide services to various users, including a classification analysis module and a retrieval analysis module; The classification analysis module is used to perform classification analysis, identify the classification methods of various electronic files that each user may use, mark them as potential classification methods, perform keyword simulation classification based on each potential classification method, obtain various classification feature items for classification, which are used to represent various classification feature words that need to be extracted from electronic files, such as file type, time, size, content type and other related classification feature items. The module sets and updates the corresponding classification word recognition method based on each classification feature item, that is, it is used to realize the recognition method of identifying the corresponding features of each classification feature item from electronic files; the classification word recognition method is configured in the archiving module on the user end.
[0027] In one embodiment, keyword simulation classification is performed based on various potential classification methods, including: Identify the classification items corresponding to each potential classification method, remove duplicates from each identified classification item, and mark the remaining items as classification feature items.
[0028] In one embodiment, keyword simulation classification is performed based on various potential classification methods, including: Identify the category items corresponding to each potential classification method, that is, what data the potential classification method is based on, such as source, time, file type, name, content classification, etc.; and remove duplicates from each identified category item. Perform effect conflict analysis on each category item, that is, if the classification effect is the same in actual classification, such as having category items A and B, both of which classify a certain category, the classification effect is the same and they can be substituted, which is considered to be an effect conflict, and obtain the effect conflict results between each category item; The identification results of conflicting effects are the corresponding categories. The category with higher priority is retained, and the other category is removed. For example, if B has all the category effects of A, then A can be replaced by B. However, if B cannot be replaced by A, then B has a higher priority than A. If B can also be replaced by A, the priority is evaluated based on identification efficiency, cost, etc. If neither A nor B can be replaced, then there is no conflict. That is, classification simulation can be performed by checking whether they can be replaced to determine whether each category can be replaced, thereby obtaining the results of conflicting effects. The following classification materials are used for simulation.
[0029] The remaining classification items are labeled as classification features.
[0030] In one embodiment, conflict analysis of effects is performed on each category item, and intelligent analysis can also be performed by building intelligent models based on machine learning, deep learning algorithms, etc.
[0031] In one embodiment, based on the above embodiments, each classification item is verified; Obtain the user's category materials, which are various representative electronic documents that the user will classify and manage in the future. Alternatively, a batch of historical electronic documents that have undergone security processing such as dehiding can be packaged as category materials. The materials are classified according to each category item. The simulation shows whether the classification can be qualified under various possible user classification requirements. If the classification can be qualified, the verification is passed and each category item is marked as a classification feature item. If the classification cannot be qualified, the verification is failed and the category items are adjusted. That is, according to the reason for the failure, the corresponding category items are added and removed until the verification is passed.
[0032] In one embodiment, the classification word recognition method is updated, that is, it is determined in real time whether to update according to the determination process of the classification feature items. If it is updated, the classification word recognition method is updated according to the updated classification feature items.
[0033] The retrieval analysis module is used to perform retrieval analysis, obtain the user's search term recognition method, and configure the search term recognition method in the archiving module on the user's end.
[0034] This involves determining which keywords from electronic documents can be extracted for rapid retrieval based on the retrieval requirements of various existing retrieval methods, so that subsequent retrieval does not require recognizing the content of electronic documents; setting up based on existing methods, for example, simulating various retrieval technologies to determine each retrieval data item, setting the search term recognition method according to each retrieval data item, or directly setting the search term recognition method manually.
[0035] The user terminal includes an archiving module, an archive repository, an archive management module, and a retrieval module; The archiving module is used to archive electronic archives, identify electronic archives that need to be archived in real time, identify electronic archives according to preset classification term recognition methods and search term recognition methods, obtain the corresponding electronic archive classification term set and search term set, mark the classification term set and search term set on the electronic archive, and store the electronic archive in the archive database.
[0036] In one embodiment, the preset classification word recognition method and search word recognition method are evaluated in real time to obtain the update evaluation results corresponding to the classification word recognition method and search word recognition method respectively. The update evaluation results include those that need to be updated and those that do not need to be updated. When the updated evaluation result indicates that an update is required, the classification term set or search term set of the electronic archives stored in the archives that have been identified using the corresponding classification term recognition method or search term recognition method will be adjusted, that is, re-identified according to the current classification term recognition method or search term recognition method. No adjustments will be made if the updated assessment result indicates that no update is needed.
[0037] In one embodiment, the preset classification term recognition method and search term recognition method are evaluated in real time. First, it is determined whether the preset classification term recognition method and search term recognition method need to be updated. If they are not updated, the update evaluation result is that no update is needed. If they are updated, it is determined whether the classification term set and search term set for recognizing electronic files are different based on the updated classification term recognition method and search term recognition method. If they are different, the update evaluation result is that an update is needed. If they are not different, the update evaluation result is that no update is needed.
[0038] Based on the above methods, evaluation can be conducted using various existing technologies, such as building intelligent models based on machine learning and deep learning algorithms for intelligent evaluation. Evaluation can also be conducted using the following methods: Real-time acquisition of updated data for preset category word recognition and search term recognition methods refers to the relevant data used to update these methods. An update evaluation model is then established, and its expression is as follows: ; In the formula: s is the input data, representing the updated data of the corresponding classification word recognition method or search word recognition method; s is abnormal data, indicating that the corresponding updated data will cause the recognition results of the classification word recognition method or search word recognition method to be different, and is considered abnormal compared with the original situation; the output data is the update evaluation value GP(s), and the update evaluation value is 1 or 0; the corresponding training set is labeled using historical update data for training; By updating the model, the updated data of the classification word recognition method and the search word recognition method are analyzed in real time to obtain the corresponding update evaluation results.
[0039] In one embodiment, the classification term set or search term set of the corresponding electronic archives in the archive database can be adjusted by the corresponding classification term recognition method or search term recognition method. Words that differ from the original classification term set or search term set can also be removed, depending on the user's needs.
[0040] The archive is used to store electronic records.
[0041] The document management module is used for document management, acquiring users' document classification requirements in real time. Users can dynamically adjust classification rules based on their needs, describing these requirements via text, voice, etc. The module then determines the document classification rules based on these requirements, specifying which categories to group together. This is done using natural language processing, machine learning, and deep learning. For example, a classification analysis model is built based on machine learning and deep learning, and the platform provides a corresponding training set for training. The training set includes input and output data: the input data is the document classification requirements, and the output data is the document classification rules. The successfully trained classification analysis model is then used for analysis, and the electronic documents in the archive are classified and managed according to the document classification rules.
[0042] The retrieval module is used by users to search for archives. It performs searches based on the user's search terms and the search term sets of each electronic archive, obtains search results, and displays the search results to the user.
[0043] Artificial intelligence-based electronic record archiving and management methods include: The platform sets and updates the category word recognition method and search word recognition method in real time, and configures the category word recognition method and search word recognition method on the user's end. Electronic archives are identified using classification term recognition and search term recognition methods to obtain classification term sets and search term sets for electronic archives. The classification term sets and search term sets are then marked on the electronic archives, and the electronic archives are stored in the archive database. The system acquires users' document classification requirements in real time, analyzes these requirements to obtain document classification rules, and then classifies and manages electronic archives in the archive database according to these rules. The system acquires the user's search data, performs searches based on the search terms of the search data and the various electronic archives in the database, obtains the search results, and displays the search results to the user.
[0044] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.
[0045] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.
Claims
1. An AI-based electronic records archiving management system, characterized in that, Including both the platform side and the user side; The platform includes a classification analysis module and a retrieval analysis module; the user terminal includes an archiving module, an archive database, an archive management module, and a retrieval module. The classification analysis module is used to perform classification analysis, identify various potential classification methods, perform keyword simulation classification based on various potential classification methods, obtain various classification feature items, set and update the corresponding classification word recognition method based on each classification feature item, and configure the classification word recognition method in the archiving module on the user end. The retrieval analysis module is used to perform retrieval analysis, obtain the user's retrieval term recognition method, and configure the retrieval term recognition method in the archiving module on the user's end; The archiving module is used to archive electronic archives, identify electronic archives that need to be archived in real time, identify electronic archives according to preset classification word recognition methods and search word recognition methods, obtain the classification word set and search word set of the electronic archives, mark the classification word set and search word set on the electronic archives, and store the electronic archives in the archive database. The archive is used to store electronic records; The document management module is used for document management, real-time acquisition of users' document classification requirements, analysis of document classification requirements, acquisition of document classification rules, and classification and management of electronic documents in the archive according to the document classification rules; The search module is used by users to search for files, obtain search results, and display the search results to users.
2. The AI-based electronic archive management system according to claim 1, characterized in that, The platform establishes communication connections with each user terminal.
3. The AI-based electronic archive management system according to claim 1, characterized in that, Keyword simulation classification is performed based on various potential classification methods, including: Identify the classification items corresponding to each potential classification method, remove duplicates from each identified classification item, and mark the remaining items as classification feature items.
4. The AI-based electronic archive management system according to claim 3, characterized in that, Keyword simulation classification is performed based on various potential classification methods, including: Identify the classification items corresponding to each potential classification method, and remove duplicates from each identified classification item; perform effect conflict analysis on each deduplicated classification item to obtain the effect conflict results between each classification item. The results of identifying conflicting effects are the corresponding categories. The category with higher priority is retained, the other category is removed, and the remaining categories are marked as classification features.
5. The AI-based electronic archive management system according to claim 4, characterized in that, After eliminating category items based on conflicting results, each category item is simulated and verified using pre-acquired category materials. When the verification is successful, each category item is marked as a category feature item.
6. The artificial intelligence-based electronic archive management system according to claim 1, characterized in that, The preset classification term recognition method and search term recognition method are evaluated in real time to obtain the update evaluation results corresponding to the classification term recognition method and search term recognition method respectively. The update evaluation results include whether an update is needed and whether an update is not needed. When the updated evaluation result indicates that an update is needed, the classification term set or search term set of the corresponding electronic archives in the archive database is adjusted using the corresponding classification term recognition method or search term recognition method; No adjustments will be made if the updated assessment result indicates that no update is needed.
7. The AI-based electronic archive management system according to claim 6, characterized in that, The classification term set or search term set of the corresponding electronic archives in the archive database is adjusted by using the corresponding classification term recognition method or search term recognition method, while retaining the original classification term set or search term set.
8. The AI-based electronic archive management system according to claim 6, characterized in that, The classification term set or search term set of the corresponding electronic archives in the archive database is adjusted by using the corresponding classification term recognition method or search term recognition method, and the original classification term set or search term set is not retained.
9. The artificial intelligence-based electronic archive management system according to claim 6, characterized in that, The preset classification term recognition method and search term recognition method are updated and evaluated in real time, including: The system acquires real-time updated data for preset classification word recognition methods and search word recognition methods, establishes an update evaluation model, and the expression for the update evaluation model is: ； In the formula: s is the input data, representing the updated data of the corresponding classification word recognition method or search word recognition method; the output data is the updated evaluation value GP(s), which is 1 or 0; By updating the model, the updated data of the classification word recognition method and the search word recognition method are analyzed in real time to obtain the corresponding update evaluation results.
10. An electronic records archiving and management method based on artificial intelligence, characterized in that: The method, applied to an AI-based electronic records archiving management system as described in any one of claims 1 to 9, comprises: The platform sets and updates the category word recognition method and search word recognition method in real time, and configures the category word recognition method and search word recognition method on the user's end. Electronic archives are identified using classification term recognition and search term recognition methods to obtain classification term sets and search term sets for electronic archives. The classification term sets and search term sets are then marked on the electronic archives, and the electronic archives are stored in the archive database. The system acquires users' document classification requirements in real time, analyzes these requirements to obtain document classification rules, and then classifies and manages electronic archives in the archive database according to these rules. The system acquires the user's search data, performs searches based on the search terms of the search data and the various electronic archives in the database, obtains the search results, and displays the search results to the user.