Archive management system, method and equipment for intelligent miniature archive room

Abstract

The invention discloses an archive management system, method and device for an intelligent miniature archive room, and the system comprises a storage positioning unit which is used for recognizing the content of an archive to be stored through OCR, and calculating the similarity between the archive to be stored and a plurality of target clustering centers, so as to determine the storage position of the archive; the archive encoding unit is used for constructing a multi-dimensional code of a target archive according to archive attribute information including an archive type, a storage position, a security level and a date number; the archive retrieval unit is used for calculating the similarity between retrieval keywords and the content of all archives and outputting information of one or more to-be-selected archives based on the user permission and the multi-dimensional codes of the archives; and the archive recommendation unit is used for recommending associated archives of the selected archives by adopting an improved collaborative filtering algorithm. Through the scheme of the invention, the problems of an existing system in the aspects of intelligence, space utilization, usability, safety and the like can be effectively solved.

Description

Technical Field

[0001] The present application relates to the field of archive management, and in particular to an archive management system, method and equipment for an intelligent micro archive room. Background Art

[0002] Archives management system has become an indispensable and important tool in modern organizations, playing a key role in information management, historical record preservation and decision support. The main function of archives management system is to systematically collect, organize, store and retrieve various documents, records and data to ensure the integrity, security and accessibility of information. With the rapid development of information technology, traditional paper archives management has gradually shifted to digitalization and intelligence, which not only improves work efficiency, but also greatly enhances the ability to share and utilize information. The importance of archives management system is reflected in many aspects: it can effectively protect important historical documents and data, provide a reliable basis for organizational decision-making, and is also an important tool to ensure organizational compliance and transparency. Existing archives management system technologies mainly include digital storage, metadata management, full-text retrieval, and permission control. The working principle of these technologies is to digitize files, add descriptive information (metadata), establish an index system, and set access rights, so as to achieve efficient management and rapid retrieval of archives. However, existing technologies still face some problems, such as low efficiency in processing massive data, insufficient intelligence, difficulty in system integration, and insufficient security and privacy protection.

[0003] At present, in order to solve the above problems, the industry has developed some improvement methods. For example, distributed storage and cloud computing technologies are used to improve data processing capabilities, artificial intelligence algorithms are introduced to enhance the intelligence of retrieval and classification, and blockchain technology is used to strengthen data security and traceability. However, these methods still have some obvious defects. First, most existing solutions still require a lot of manual intervention and cannot achieve true intelligent and automated management. Secondly, these systems are often large-scale, require complex hardware facilities and professional technical support, and are not suitable for small organizations or space-constrained scenarios. Furthermore, the existing systems are still insufficient in data integration and cross-platform compatibility, and it is difficult to meet the growing needs of information sharing and collaboration. Finally, although some systems have introduced advanced security technologies, there are still potential security risks in the face of increasingly complex network threats.

[0004] Therefore, there is an urgent need for a technical solution that can effectively solve the problems of the existing system in terms of intelligence, space utilization, ease of use and safety. Summary of the invention

[0005] In order to solve the deficiencies of the prior art, the embodiments of the present application provide an archive management system, method and device for an intelligent micro-archive room. The present application solves the technical problems that the prior art cannot effectively solve in terms of intelligence, space utilization, ease of use and security.

[0006] The embodiment of the present application provides an archive management system for an intelligent micro-archive room, comprising: a storage positioning unit, an archive coding unit, an archive retrieval unit, an archive recommendation unit and an encryption unit; wherein the storage positioning unit is used to identify the content of the archive to be stored through OCR, and calculate the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive; the archive coding unit is used to construct a multi-dimensional code of the target archive according to archive attribute information including archive type, storage location, security level and date number; the archive retrieval unit is used to calculate the similarity between the retrieval keyword and the content of all archives, and output the information of one or more archives to be selected based on user authority and the multi-dimensional code of the archive; the archive recommendation unit is used to recommend the associated archives of the selected archive by adopting an improved collaborative filtering algorithm; the encryption unit is used to encrypt data including the archive content recognized by OCR and the archive multi-dimensional code, so as to store it in an offline database.

[0007] In a possible implementation, the content of the archive to be stored is identified by OCR, and the similarity between the archive to be stored and multiple target cluster centers is calculated to determine the storage location of the archive, including: preprocessing the image containing the archive content to be stored, and detecting the text area and the image area respectively to obtain the structural text content of the archive; clustering the vectors of the structural text content of all archives based on an adaptive threshold and a dynamic merging strategy to determine the optimal number of clusters; constructing an archive relationship graph based on the primary clustering, and optimizing the nodes using a graph neural network; performing secondary clustering on the optimized node representation through a density-based initial center selection strategy and an adaptive cluster number adjustment mechanism to obtain multiple target cluster centers; including:

[0008]

[0009] Among them, C * represents the final optimal cluster center set, C represents the current cluster center set, z i represents the optimized node representation, c j represents the jth cluster center, A j represents the set of nodes belonging to the jth cluster, k represents the number of clusters, ρ(z i ) represents node z i The density function, σ represents the scale parameter of the density function, C initRepresents the initial cluster center set; calculates the similarity between the archive to be stored and multiple target cluster centers to select the cluster with the highest similarity to determine the storage location.

[0010] In a possible implementation, the content similarity between the search keyword and all archives is calculated, and the information of one or more archives to be selected is output based on user permissions and the multi-dimensional encoding of the archives, including: using a natural language processing model to identify the intent and extract entities of the search keyword; based on the identified intent and entities, the search query is expanded through a knowledge graph and word embedding; a multi-level index structure including an inverted index, a B+ tree index and / or a local sensitive hash index is constructed; the comprehensive similarity with all archives is calculated based on text content similarity, attribute similarity and time correlation; an access control policy is defined based on user permissions and the security level of the archive, and the search results are screened to output the information of one or more archives to be selected.

[0011] In a possible implementation, an improved collaborative filtering algorithm is used to recommend related archives of a selected archive, including: constructing an interaction matrix and performing matrix decomposition to introduce multiple target parameters to optimize the interaction matrix; and generating a personalized archive recommendation list based on the optimized interaction matrix.

[0012] In a possible implementation, data including archive content recognized by OCR and archive multi-dimensional encoding are encrypted for storage in an offline database, including: dividing the archive content into multiple fixed-size blocks, using an improved AES-256 algorithm to independently encrypt each block, and inserting padding data of random length between each block; using a dynamic key generation mechanism to generate keys, and distributing keys through an identity-based encryption scheme; and performing access control encryption and homomorphic encryption on data reading based on a preset scheme.

[0013] In a possible implementation, the comprehensive similarity with all archives is calculated based on text content similarity, attribute similarity and time correlation, including:

[0014] Among them, Similarity(d,q) represents the comprehensive similarity between document d and query q, α, β, and γ represent adjustable weight parameters used to balance the importance of the three components, and IDF(q i ) represents the query word q i The inverse document frequency, tf(q i ,d) represents the query word q iThe term frequency in document d, k, b represent the parameters of the BM25+ algorithm, |d| represents the length of document d, avgdl represents the average document length, δ represents the additional parameters in the BM25+ algorithm, HammingDistance() represents the calculation of the Hamming distance between two encodings, Encoding() represents the conversion of a document or query into a multidimensional encoding, MaxDistance represents the maximum possible distance between two encodings, λ represents the time decay factor, current\_time represents the current time, and document\_time represents the creation or last modification time of the document.

[0015] In a possible implementation, an interaction matrix is ​​constructed and matrix decomposition is performed to introduce multiple target parameters to optimize the interaction matrix, including: Among them, R ij represents the predicted interaction matrix strength of user i to profile j, μ represents the global average interaction strength, and b i represents the bias term of user i, b j represents the bias term of file j, p i represents the latent vector of user i, q j represents the latent vector of file j, T ij represents the time decay factor, γ represents the weight coefficient of content similarity, S ij represents the content similarity between archive i and archive j, δ represents the weight coefficient of context feature, c represents the context feature vector, w j represents the context weight vector of profile j.

[0016] In a possible implementation, it also includes a remote supervision unit; wherein the remote supervision unit is used to provide the superior archive room with the real-time operating status, environmental parameters and / or personnel operation information of the subordinate archive room, and remotely approve the corresponding operations of the subordinate archive room.

[0017] The embodiment of the present application also provides an archive management method for an intelligent micro-archive room, including: identifying the content of the archive to be stored through OCR, and calculating the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive; constructing a multi-dimensional code of the target archive based on archive attribute information including archive type, storage location, security level and date number; calculating the similarity between the search keyword and the content of all archives, and outputting information of one or more archives to be selected based on user permissions and the multi-dimensional code of the archive; using an improved collaborative filtering algorithm to recommend associated archives of the selected archive; encrypting data including the archive content recognized by OCR and the archive multi-dimensional code for storage in an offline database.

[0018] An embodiment of the present application also provides an archive management device for an intelligent micro archive room, comprising: a processor, a memory, and a system bus; wherein the processor and the memory are connected via the system bus; the memory is used to store one or more programs, and the one or more programs include instructions, which, when executed by the processor, enable the processor to execute the method described in the above embodiment.

[0019] In the archive management system, method and equipment of an intelligent micro-archive room provided above, the embodiment of the present application can realize automatic classification, labeling and intelligent retrieval of archives through deep integration of artificial intelligence and machine learning technologies, greatly improving the automation and efficiency of the system; by introducing advanced data compression and storage technologies, efficient storage and rapid access to massive data can be achieved within a limited physical space; by adopting multi-level encryption and access control mechanisms, the absolute security of archives can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application 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 some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A schematic block diagram of an archive management system for an intelligent micro archive room provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of an archive retrieval method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0024] Those skilled in the art will appreciate that the terms "first", "second" and the like in the embodiments of the present application are only used to distinguish different steps, devices or modules, etc., and do not represent any specific technical meaning, nor do they represent the necessary logical order between them. It should also be understood that in the embodiments of the present application, "multiple" may refer to two or more, and "at least one" may refer to one, two or more. It should also be understood that for any component, data or structure mentioned in the embodiments of the present application, in the absence of explicit limitation or contrary revelation given in the context, it can generally be understood as one or more. In addition, the term "and / or" in the present application is only a kind of association relationship describing the associated objects, indicating that there can be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present application generally indicates that the associated objects before and after are an "or" relationship. It should also be understood that the description of each embodiment in the present application emphasizes the differences between the embodiments, and the same or similar parts can refer to each other. For the sake of brevity, they will not be repeated one by one.

[0025] At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use. The techniques, methods and devices known to ordinary technicians in the relevant fields may not be discussed in detail, but where appropriate, the techniques, methods and devices should be considered as part of the specification. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] Figure 1A schematic block diagram of an archive management system for an intelligent micro-archive room provided in an embodiment of the present application. It should be understood that the system shown in the figure is exemplary and not restrictive. This means that the system architecture involved is not limited to a specific form or design, but is presented as an example. In other words, the architecture shown in the figure can be regarded as a way of expression to clearly describe related concepts and relationships, and does not exclude other forms of architecture. Therefore, when interpreting the architecture in the picture, it should be understood that the model is flexible and diverse, and its purpose is to provide an exemplary description rather than a restrictive provision on a specific form. The embodiment of the present application includes a storage positioning unit 101, an archive encoding unit 102, an archive retrieval unit 103, an archive recommendation unit 104 and an encryption unit 105.

[0028] The storage location unit 101 is used to identify the content of the archive to be stored through OCR, and calculate the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive.

[0029] First, the image containing the archive content to be stored is preprocessed, and the text area and the image area are detected respectively to obtain the structural text content of the archive. It should be noted that the multimodal fusion OCR recognition algorithm that can be used in this application. By combining the three modal information of image, text and voice, and further realizing end-to-end recognition through a deep learning model. The input archive image is preprocessed, including denoising, correction and enhancement. Adaptive Gaussian filter is used to remove noise, and then the tilt correction algorithm based on Hough transform is used for image correction. Then, the contrast limited adaptive histogram equalization (CLAHE) method is applied to enhance the image quality.

[0030] The preprocessed image is input into an improved YOLOv5 model for text region detection. The backbone network of the YOLOv5 model adopts CSPDarknet53, and the spatial pyramid pooling (SPP) module is introduced to enhance the feature extraction capability. The detected text region is then cropped and input into the recognition model. The recognition model can adopt a bidirectional LSTM-Transformer architecture. First, CNN is used to extract image features, and then a bidirectional LSTM network is input to capture contextual information. The output of LSTM is then passed through the Transformer encoder with a multi-head attention mechanism, and finally the recognition result is obtained through CTC decoding. At the same time, the system can also integrate a speech recognition module to recognize voice annotations in archives. The final OCR recognition content is obtained by weighted fusion of the recognition results of the three modalities. The fusion weight is dynamically adjusted through a reinforcement learning algorithm to adapt to different types of archives.

[0031] Next, the vectors of the structured text content of all archives are clustered based on the adaptive threshold and dynamic merging strategy to determine the optimal number of clusters. The archive content obtained by OCR recognition is preprocessed, including word segmentation, stop word removal and stem extraction. The text is then converted into a vector representation using the Word2Vec model. The archives are preliminarily clustered using an improved hierarchical clustering algorithm. In one embodiment, it may include:

[0032]

[0033] Among them, C * represents a clustering result, k represents the number of clusters, C i represents the i-th cluster, x represents a data point in the cluster, μ i represents the center point of the i-th cluster, var(C i ) represents the variance of the ith cluster, β represents the parameter that controls the rate of change of the adaptive weight, θ represents the variance threshold, and Euclidean(x,μ i ) represents the Euclidean distance, DTW(x,μ i ) represents the dynamic time warping distance, n represents the total number of data points, γ represents the regularization strength parameter, and k * represents the optimal number of clusters determined by the elbow rule, Merge(C i ,C j ) represents the merged cluster C i and C j Operation, diam(C i ) represents cluster C i The diameter of , δ represents the merging threshold. The algorithm introduces adaptive threshold and dynamic merging strategy, which can automatically determine the optimal number of clusters.

[0034] Based on the primary clustering, the archive relationship graph is constructed, and the graph neural network is used to optimize the nodes. Based on the preliminary clustering, the archive relationship graph is constructed, each archive is a node in the graph, and the edge weights between nodes are determined by the similarity of archive content. Then the graph neural network (GNN) is applied for further feature learning and clustering optimization. The GNN model adopts the GraphSAGE architecture, which includes attention mechanism and skip connection.

[0035] Secondly, based on the node representation learned by GNN, the improved K-Means++ algorithm is used to obtain the final clustering result. The improvements include secondary clustering of the optimized node representation through the density-based initial center selection strategy and the adaptive cluster number adjustment mechanism to obtain multiple target cluster centers; these include:

[0036]

[0037] Among them, C * represents the final optimal cluster center set, C represents the current cluster center set, z i represents the optimized node representation, c j represents the jth cluster center, A j represents the set of nodes belonging to the jth cluster, k represents the number of clusters, ρ(z i ) represents node z i The density function, σ represents the scale parameter of the density function, C init represents the initial cluster center set;

[0038] After obtaining the clustering results, calculate the similarity between the archive to be stored and multiple target cluster centers to select the cluster with the highest similarity to determine the storage location. Similarity calculation can use a weighted combination of cosine similarity and edit distance: Similarity(doc,cluster)=α·cos(doc,cluster\_center)+(1-α)·(1-normalized\_edit\_distance(doc,cluster\_center)), where α is an adjustable weight parameter.

[0039] The archive encoding unit 102 is used to construct a multi-dimensional code of the target archive based on the archive attribute information including the archive type, storage location, security level and date number. Specifically, the archive type is encoded using the improved Huffman code to obtain the type code; the location is layered based on the clustering result obtained by the storage positioning unit to obtain the location code; the information entropy of the archive content is calculated and mapped to the corresponding security level to obtain the security level code; the date is encoded using the improved Gray code to obtain the date code; the type code, location code, security level code and date code are combined, and the combined code is compressed based on the context to obtain the multi-dimensional code.

[0040] In one implementation scenario, based on the storage location information obtained by the storage location unit and combined with other attributes of the archive, an innovative multi-dimensional coding scheme is constructed. The scheme adopts a hierarchical coding structure, which includes the following levels:

[0041] Type encoding: Use improved Huffman coding to encode file types. First, count the frequency of occurrence of each type, and then build a Huffman tree. Different from traditional Huffman coding, this solution introduces a dynamic adjustment mechanism that can automatically update the coding according to the newly added file types.

[0042] Storage location coding: Based on the clustering results obtained by the storage location unit, a hierarchical location coding scheme is designed. First, the clusters are numbered, and then each cluster is further subdivided. The coding structure is: [cluster number][sub-region number][specific location].

[0043] Security level coding: Adopt an entropy-based coding scheme. First, calculate the entropy of the archive content, and then map the entropy value to different security levels. The code length is proportional to the security level. Archives with high security levels have longer codes to increase security.

[0044] Date number encoding: Use improved Gray code to encode the date. Compared with traditional binary code, Gray code has only one bit difference between adjacent dates, which is convenient for date range query.

[0045] Finally, the above-mentioned layers of coding are combined into the final multi-dimensional coding. In order to improve the compression rate of the coding, a context-based compression algorithm can be used. This algorithm uses the correlation between archive attributes and reduces redundant information through a predictive model:

[0046] Final\_encoding=Compress(Concatenate(E type ,E location ,E security ,E date )); Context-based compression algorithm: Compress(x)=x-Predict(x|context).

[0047] The archive retrieval unit 103 is used to calculate the content similarity between the search keyword and all archives, and output the information of one or more archives to be selected based on the user authority and the multi-dimensional encoding of the archive. This includes: using a natural language processing model to identify the intent and extract entities of the search keyword; based on the identified intent and entity, expanding the search query through knowledge graph and word embedding; constructing a multi-level index structure including an inverted index, a B+ tree index and / or a local sensitive hash index; calculating the comprehensive similarity with all archives based on text content similarity, attribute similarity and time correlation; defining an access control strategy based on user authority and the security level of the archive, and screening the search results to output the information of one or more archives to be selected (such as Figure 2 The specific method will be shown in Figure 2 (see the instructions for more information).

[0048] The profile recommendation unit 104 is used to recommend the associated profiles of the selected profile using an improved collaborative filtering algorithm. In one embodiment, it includes: constructing an interaction matrix and performing matrix decomposition to introduce multiple target parameters to optimize the interaction matrix; including: Among them, R ij represents the predicted interaction matrix strength of user i to profile j, μ represents the global average interaction strength, and b i represents the bias term of user i, b j represents the bias term of file j, p i represents the latent vector of user i, q j represents the latent vector of file j, T ij represents the time decay factor, γ represents the weight coefficient of content similarity, S ij represents the content similarity between archive i and archive j, δ represents the weight coefficient of context feature, c represents the context feature vector, w j represents the context weight vector of profile j. Then a personalized profile recommendation list is generated based on the optimized interaction matrix.

[0049] Specifically, this unit proposes a multi-factor dynamic collaborative filtering algorithm that combines content analysis, user behavior, and time factors to achieve personalized profile recommendations. First, we construct a user-profile interaction matrix R, where R ij Represents the interaction intensity of user i on profile j. The interaction intensity considers multiple factors: R ij =w1·View\_count+w2·Download\_count+w3·Edit\_time+w4·Cite\_count, where w1,w2,w3,w4 are weight parameters, which are dynamically adjusted by machine learning algorithms. An improved matrix decomposition algorithm is used to introduce user and archive bias items: Where μ is the global average, b i and b j are the bias items for users and profiles respectively, p i and q j is the latent vector of the user and the profile. The objective function can be set as: The above objective function is optimized using stochastic gradient descent (SGD).

[0050] Next, we introduce a time decay factor to give more weight to recent interactions: T ij =exp(-β·(current\_time-interaction\_time)), integrating the time factor into the matrix decomposition model: Based on the content features of the archives, the similarity matrix S between the archives is calculated. A hybrid representation of TF-IDF and Word2Vec is used:

[0051] Doc\_vector=α·TF-IDF(doc)+(1-α)·Word2Vec(doc);

[0052] S ij =cosine\_similarity(Doc\_vector i ,Doc\_vector j ),

[0053] Incorporating content similarity into the recommendation model:

[0054] Secondly, context awareness is performed to consider the user's current context, such as work tasks, time, etc. Context feature vector c is constructed and the model is expanded: where w j is the context weight vector of file j.

[0055] Multi-task learning can be used during training to optimize multiple objectives simultaneously, including rating prediction, profile classification, and label prediction. Construct a multi-task loss function: L = λ1·L rating +λ2·L classification +λ3·L tagging , where L rating is the mean square error of the rating prediction, L classification is the cross entropy loss for archive classification, L tagging F1 score for label predictions.

[0056] You can also use incremental learning algorithms to update model parameters in real time. When there is new interaction data, the stochastic gradient descent method is used to update the parameters: Where η is the learning rate, which is adaptively adjusted by the Adam optimizer.

[0057] Based on the above model, a personalized profile recommendation list is generated for each user. A strategy that balances diversity and novelty is adopted: score(i,j)=α·R ij +β·diversity(j)+γ·novelty(j), where diversity(j) measures the difference between profile j and the recommended profiles, and novelty(j) measures the novelty of profile j.

[0058] In addition, recommendation explanations can be generated to help users understand the reasons for the recommendation. In one embodiment, an explanation generation model based on an attention mechanism is used:

[0059] explanation=Attention(user\_embedding, item\_embedding, context).

[0060] The encryption unit 105 is used to encrypt data including the archive content recognized by OCR and the archive multi-dimensional code, so as to store them in the offline database.

[0061] First, the archive content is divided into multiple fixed-size blocks, and each block is encrypted independently using the improved AES-256 algorithm, and random-length padding data is inserted between each block. A dynamic key generation mechanism is used to generate keys, and key distribution is performed through an identity-based encryption scheme. The key is generated by the following formula: K = H (user\_id∥timestamp∥random\_seed), where H is a secure hash function and || represents string concatenation. Random-length padding data is inserted between each block to increase the randomness of the ciphertext. The padding length L can be determined by the following formula: L = (block\_index·17+timestamp)modmax\_padding\_length.

[0062] Secondly, access control encryption and homomorphic encryption are performed on data reading based on the preset scheme. For access control encryption, the access policy can be embedded into the ciphertext using the attribute-based encryption (ABE) scheme. Define a set of attribute sets A and specify the access structure T during encryption. Only users who meet T can decrypt:

[0063] CT = ABE.Encrypt(PK,M,T);

[0064]

[0065] For homomorphic encryption, in order to support data analysis in an encrypted state, a partial homomorphic encryption scheme can be introduced. The improved Paillier encryption algorithm is used to support additive homomorphism and limited number of multiplication homomorphism:

[0066] E(m1+m2)=E(m1)·E(m2);

[0067] E(k·m)=E(m) k .

[0068] Through the above-mentioned multi-level and multi-dimensional encryption scheme, this system can achieve all-round protection of archival data, ensuring the confidentiality, integrity and availability of the data.

[0069] In addition, the embodiment of the present application may further include configuring a remote monitoring unit 106; wherein the remote monitoring unit 106 is used to provide the upper-level archive room with the real-time operating status, environmental parameters and / or personnel operation information of the lower-level archive room, and remotely approve the corresponding operation of the lower-level archive room. This unit may be configured according to the relevant level.

[0070] Specifically, the remote supervision function aims to achieve effective supervision and management of subordinate units (such as township archives) by superior units (such as district archives bureaus). Through network connection, this function enables superior units to grasp the operation status and archives management of subordinate archives in real time and make necessary interventions and guidance.

[0071] For real-time monitoring of the operating status, environmental parameters and personnel operations of subordinate archives. Real-time video monitoring can be carried out through the camera installed in the archive room, and environmental sensors can be deployed to monitor parameters such as temperature, humidity, and light, and record the operation log of the archive management system. Time series analysis models can also be used to detect abnormal situations. For example, the autoregressive moving average model (ARMA) is used to predict the normal value of the relevant parameters. If the difference between the actual observed value and the predicted value exceeds the preset threshold, an alarm is triggered. In one embodiment, the district archives bureau discovered that the temperature of the archives room in Township A was abnormally high through the monitoring system. The system automatically triggered an alarm, and the district archives bureau immediately notified Township A to conduct an inspection, promptly discover and repair the air conditioning failure, and avoid possible damage to the archives.

[0072] Furthermore, remote approval is performed for important operations of subordinate archives. The types of operations that require remote approval can be set, such as confidential archive access, large-scale archive destruction, etc. The superior administrator receives the approval request through the system and conducts remote review, and the approval results are fed back to the subordinate archives in real time.

[0073] The approval process model may include, but is not limited to, using a finite state machine (FSM) to control the approval process:

[0074] Status set S = {pending submission, pending approval, under preliminary review, under review, under final review, approved, rejected, withdrawn, expired};

[0075] Input set I = {submit application, withdraw application, pass preliminary review, reject preliminary review, pass re-review, reject re-review, pass final review, reject final review, timeout};

[0076] The conversion function δ(s,i) can be defined as follows:

[0077] δ(pending submission, application submitted) = pending approval;

[0078] δ(pending approval, application withdrawn) = withdrawn;

[0079] δ(pending approval, passed the preliminary review) = under review;

[0080] δ(pending approval, rejected in the first instance) = rejected;

[0081] δ(under review, passed review) = under final review;

[0082] δ(under review, review rejected) = rejected;

[0083] δ(under final review, passed in final review) = passed;

[0084] δ(under final review, rejected in final review) = rejected;

[0085] δ(any status, timeout) = expired.

[0086] Combined with the above model, the approval process can be configured to allow multiple approvers to review at the same time, and only when all approvers pass can the next stage be entered. Choose different approval paths according to the application content. Define different roles (such as applicants, approvers, administrators) and their operating permissions. Text comments and uploaded attachments can be added for each approval step. Set up automatic reminders and reminders to automatically send reminders for applications that are about to time out. Introduce a delegated approval mechanism, and the approver can temporarily delegate authority to others. Add approval history records to record the operator, time, opinions and other information of each step. You can also set the approval rollback function to allow the application to be returned to a previous step for re-approval. At the same time, introduce approval templates and preset commonly used approval process templates to facilitate quick creation. For example, Township C applies to destroy a batch of expired archives. The District Archives Bureau can review the destruction list through remote approval and supervise the destruction process through video surveillance to ensure compliance.

[0087] Through the remote supervision function, the supervision efficiency can be improved, 24 / 7 all-weather supervision can be achieved, and the timeliness and coverage of supervision can be greatly improved. Furthermore, the supervision cost can be reduced, the frequency of on-site inspections can be reduced, and manpower and travel costs can be saved. Furthermore, standardized management can be promoted, and the standardization and normalization of archive management can be promoted through a unified remote supervision platform. It can also strengthen emergency response capabilities, achieve rapid response and coordinated disposal, and improve the ability to respond to emergencies. Optimize resource allocation, based on data analysis, to achieve more accurate resource allocation and management decisions. Improve personnel quality, and continuously improve the business capabilities of grassroots archive management personnel through remote guidance.

[0088] Figure 2 This is a flowchart of a file retrieval method provided in an embodiment of the present application. This unit adopts a multi-stage retrieval algorithm, combined with semantic understanding, similarity calculation and authority control, to achieve efficient and accurate file retrieval. Figure 2As shown, at step S201, a natural language processing model is used to perform intent recognition and entity extraction on search keywords.

[0089] First, the semantic understanding of the search keywords entered by the user is performed. The improved BERT model is used for intent recognition and entity extraction. The improvements include but are not limited to the introduction of domain-specific pre-training tasks and multi-task learning frameworks.

[0090] At step S202, based on the identified intent and entity, the retrieved query is expanded through the knowledge graph and word embedding. Specifically, a hybrid method of knowledge graph and word embedding is used to expand synonyms, hyponyms and hyponyms. The knowledge graph is built using Neo4j and contains professional knowledge in the archives field. Word embedding uses the FastText model, which can handle unregistered words. The mathematical expression of query expansion is as follows:

[0091] Q expanded =Q original ∪KG expand (Q original )∪WE expand (Q original ),

[0092] Among them, Q expanded Represents the expanded query set, including the original query terms and the related terms obtained through expansion. original Represents the original query word set entered by the user, KG expand (Q original ) represents query expansion based on knowledge graph. We use Neo4j to build archive domain knowledge graph and find out synonyms, hypernyms, hyponyms and other related words through graph relationships. expand (Q original ) represents query expansion based on word embedding, which uses the FastText model for word embedding to find words that are close to the original query words in the vector space. ∪ represents a set union operation, which merges the original query words with the words obtained by the two expansion methods.

[0093] The above formula describes the process of query expansion, which is to merge the original query with the related words expanded based on the knowledge graph and word embedding methods to form the final expanded query set.

[0094] At step S203, a multi-level index structure including an inverted index, a B+ tree index and / or a local sensitive hash index is constructed. In one embodiment:

[0095] Inverted index: used to quickly locate archives containing query terms.

[0096] B+ tree index: built based on the multi-dimensional encoding of archives, supporting range queries.

[0097] LSH index: used for approximate nearest neighbor search and accelerates similarity calculation.

[0098] The retrieval process adopts a layer-by-layer filtering strategy. First, the candidate set is filtered out using the inverted index, then the encoding range is filtered using the B+ tree index, and finally the similarity is calculated using the LSH index.

[0099] At step S204, the comprehensive similarity with all archives is calculated based on the text content similarity, attribute similarity and time correlation. In one embodiment, it includes:

[0100]

[0101] Among them, Similarity(d,q) represents the comprehensive similarity between document d and query q, α, β, and γ represent adjustable weight parameters used to balance the importance of the three components, and IDF(q i ) represents the query word q i The inverse document frequency, tf(q i ,d) represents the query word q i The term frequency in document d, k, b represent the parameters of the BM25+ algorithm, |d| represents the length of document d, avgdl represents the average document length, δ represents the additional parameters in the BM25+ algorithm, HammingDistance() represents the calculation of the Hamming distance between two encodings, Encoding() represents the conversion of a document or query into a multidimensional encoding, MaxDistance represents the maximum possible distance between two encodings, λ represents the time decay factor, current\_time represents the current time, and document\_time represents the creation or last modification time of the document.

[0102] Specifically, the similarity calculation method integrating multiple features in the embodiment of the present application takes into account text content similarity, attribute similarity and time correlation.

[0103] The text similarity adopts the improved BM25 algorithm:

[0104]

[0105] Attribute similarity is calculated based on the multidimensional encoding of the archive:

[0106]

[0107] Time relevance considers the timeliness of the archive:

[0108] Time\_relevance(d)=exp(-λ·(current\_time-document\_time)),

[0109] The final similarity is the weighted sum of the three:

[0110] Similarity(d,q)=

[0111] α·BM25 + (d,q)+β·Sim attr (d,q)+γ·Time\_relevance(d),

[0112] Among them, α, β, and γ are adjustable weight parameters.

[0113] At step S205, an access control policy is defined based on user authority and the security level of the archive, and the search results are screened to output information of one or more archives to be selected. Specifically, the access control policy is defined using the attribute-based access control (ABAC) model, combined with the advantages of role-based access control (RBAC):

[0114] Policy(user,document)=

[0115] f(user\_attributes,document\_attributes,environment\_attributes), where f is the decision function, which comprehensively considers user attributes, document attributes and environment attributes. Then the Learning to Rank method is used to sort the search results. The LambdaMART algorithm is used to train the sorting model, and the features include similarity scores, document attributes, user historical behaviors, etc. Finally, the final search results are filtered and displayed based on the sorting results and user permissions.

[0116] The intelligent micro-archive room archive management system disclosed in the above content of this application is expected to effectively solve the problems of existing systems in terms of intelligence, space utilization, ease of use and security. It will provide a highly intelligent, safe, reliable and easy-to-use archive management solution for small organizations and space-constrained scenarios, bringing significant progress in the field of archive management. This system can not only meet current needs, but also lay a solid foundation for future information management and knowledge sharing, and promote the entire industry to develop in a smarter and more efficient direction.

[0117] Furthermore, an embodiment of the present application also provides an archive management device for an intelligent micro archive room, comprising: a processor, a memory, and a system bus; the processor and the memory are connected via the system bus; the memory is used to store one or more programs, and the one or more programs include instructions, which, when executed by the processor, enable the processor to execute any of the above methods.

[0118] Furthermore, an embodiment of the present application also provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the above methods.

[0119] It can be known from the description of the above implementation mode that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0120] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0121] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0122] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent micro-archive room file management system, characterized in that: include: storage positioning unit, file encoding unit, file retrieval unit, file recommendation unit and encryption unit; wherein, The storage positioning unit is used to identify the content of the archive to be stored through OCR, and calculate the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive; The archive encoding unit is used to construct a multi-dimensional code of the target archive according to the archive attribute information including archive type, storage location, security level and date number; The archive retrieval unit is used to calculate the similarity between the retrieval keyword and the content of all archives, and output the information of one or more archives to be selected based on the user authority and the multi-dimensional code of the archive; The file recommendation unit is used to recommend related files of the selected file by using an improved collaborative filtering algorithm; The encryption unit is used to encrypt data including the archive content recognized by OCR and the archive multi-dimensional encoding, so as to store them in an offline database.

2. The file management system according to claim 1, characterized in that: in, Identify the content of the archive to be stored through OCR, and calculate the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive, including: Preprocessing the image containing the archive content to be stored, and detecting the text area and the image area respectively, so as to obtain the structural text content of the archive; Cluster the vectors of the structured text content of all archives based on adaptive thresholds and dynamic merging strategies to determine the optimal number of clusters; Construct an archive relationship graph based on primary clustering and use graph neural network to optimize nodes; The optimized node representation is clustered again through the density-based initial center selection strategy and the adaptive cluster quantity adjustment mechanism to obtain multiple target cluster centers; including: Among them, C * represents the final optimal cluster center set, C represents the current cluster center set, z i represents the optimized node representation, c j represents the jth cluster center, A j represents the set of nodes belonging to the jth cluster, k represents the number of clusters, ρ(z i ) represents node z i The density function, σ represents the scale parameter of the density function, C init represents the initial cluster center set; Calculate the similarity between the archive to be stored and multiple target cluster centers to select the cluster with the highest similarity to determine the storage location.

3. The file management system according to claim 1, characterized in that: in, Calculate the similarity between the search keyword and the content of all archives, and output the information of one or more archives to be selected based on user permissions and the multi-dimensional coding of the archives, including: Use natural language processing models to identify the intent and extract entities of search keywords; Based on the identified intents and entities, the retrieved queries are expanded through knowledge graphs and word embeddings; Construct a multi-level index structure including inverted index, B+ tree index and / or locality sensitive hash index; Calculate the comprehensive similarity with all archives based on text content similarity, attribute similarity and time correlation; The access control policy is defined based on the user's authority and the security level of the archive, and the search results are filtered to output the information of one or more archives to be selected.

4. The file management system according to claim 1, characterized in that: in, An improved collaborative filtering algorithm is used to recommend related files of the selected files, including: constructing an interaction matrix and performing matrix decomposition to introduce multiple objective parameters to optimize the interaction matrix; Generate a personalized profile recommendation list based on the optimized interaction matrix.

5. The file management system according to claim 1, characterized in that: in, Encrypt the data including the OCR-recognized archive content and the archive multi-dimensional encoding to store in the offline database, including: Divide the archive content into multiple fixed-size blocks, encrypt each block independently using the modified AES-256 algorithm, and insert padding data of random length between each block; A dynamic key generation mechanism is used to generate keys, and key distribution is performed through an identity-based encryption scheme; Access control encryption and homomorphic encryption are performed on data reading based on preset schemes.

6. The file management system according to claim 3, characterized in that: in, The comprehensive similarity with all archives is calculated based on text content similarity, attribute similarity and time correlation, including: Among them, Similarity(d,q) represents the comprehensive similarity between document d and query q, α, β, and γ represent adjustable weight parameters used to balance the importance of the three components, and IDF(q i ) represents the query word q i The inverse document frequency, tf(q i ,d) represents the query word q i The term frequency in document d, k, b represent the parameters of the BM25+ algorithm, |d| represents the length of document d, avgdl represents the average document length, δ represents the additional parameters in the BM25+ algorithm, HammingDistance() represents the calculation of the Hamming distance between two encodings, Encoding() represents the conversion of a document or query into a multidimensional encoding, MaxDistance represents the maximum possible distance between two encodings, λ represents the time decay factor, current\_time represents the current time, and document\_time represents the creation or last modification time of the document.

7. The file management system according to claim 4, characterized in that: in, An interaction matrix is ​​constructed and matrix decomposition is performed to introduce multiple objective parameters to optimize the interaction matrix, including: Among them, R ij represents the predicted interaction matrix strength of user i to profile j, μ represents the global average interaction strength, and b i represents the bias term of user i, b j represents the bias term of file j, p i represents the latent vector of user i, q j represents the latent vector of file j, T ij represents the time decay factor, γ represents the weight coefficient of content similarity, S ij represents the content similarity between archive i and archive j, δ represents the weight coefficient of context feature, c represents the context feature vector, w j represents the context weight vector of profile j.

8. The file management system according to claim 1, characterized in that: It also includes a remote monitoring unit; wherein the remote monitoring unit is used to provide the superior archive room with the real-time operating status, environmental parameters and / or personnel operation information of the subordinate archive room, and remotely approve the corresponding operations of the subordinate archive room.

9. A method for managing archives in an intelligent micro-archive room, characterized in that: include: Identify the content of the archive to be stored through OCR, and calculate the similarity between the archive to be stored and multiple target cluster centers to determine the storage location of the archive; Constructing a multi-dimensional code of a target archive based on archive attribute information including archive type, storage location, security level and date number; Calculate the similarity between the search keyword and the content of all archives, and output the information of one or more archives to be selected based on the user's authority and the multi-dimensional coding of the archives; An improved collaborative filtering algorithm is used to recommend related files of the selected files; The data including the archive content recognized by OCR and the archive multi-dimensional coding are encrypted and stored in the offline database.

10. An intelligent micro-archive room file management device, characterized in that: include: A processor, a memory, and a system bus; wherein the processor and the memory are connected via the system bus; The memory is used to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor is caused to perform the method of claim 9.

Images