Archives identification method and device based on semantic recognition of natural language processing technology

Abstract

The embodiment of the present application provides an archive identification method and device based on semantic recognition of natural language processing technology, which relates to the field of archive management technology. The method includes: performing preliminary metadata extraction and storage on the entered archives; performing semantic analysis on the archives to identify semantic elements in the archives, wherein the semantic elements include entities, relationships and events; setting identification rules, automatically identifying the archives according to the preset identification rules, and assigning identification tasks; setting a process model, and receiving real-time operations, automatically updating the status of the archives at the corresponding process nodes and displaying them; generating a detailed identification report and related statistical information based on the identification results, and storing all data of the entire archive processing process; and deeply understanding the semantic information of the archive content, so that the identification results are accurate and comprehensive, meeting the needs of modern archive management for efficient and accurate identification.

Description

Technical Field

[0001] The present application relates to the technical field of archive management, and in particular to an archive identification method and device based on semantic recognition of natural language processing technology. Background Art

[0002] Traditional archival appraisal faces numerous challenges, including low manual efficiency, high subjectivity, and difficulty in standardizing. While some archival management systems have emerged with the advancement of information technology, intelligent, automated, and highly accurate solutions for archival appraisal remain lacking. Existing archival appraisal systems often fail to deeply understand the semantic information within archival content, resulting in inaccurate and incomplete appraisal results, making them unable to meet the demands of modern archival management for efficient and accurate appraisal. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a method and device for archive identification based on semantic recognition of natural language processing technology, so as to solve the problem that current archive identification methods are often unable to deeply understand the semantic information of the archive content, resulting in inaccurate and incomplete identification results, and it is difficult to meet the needs of modern archive management for efficient and accurate identification.

[0004] In a first aspect, the present invention provides a method for file identification based on semantic recognition of natural language processing technology, including:

[0005] Extract and store preliminary metadata of the entered archives;

[0006] Perform semantic analysis on the archives to identify semantic elements in the archives, where semantic elements include entities, relationships, and events;

[0007] Set identification rules, automatically identify files according to the preset identification rules, and assign identification tasks;

[0008] Set up process models and receive real-time operations, automatically update the status of files at corresponding process nodes and display them;

[0009] Generate detailed identification reports and relevant statistical information based on the identification results, and store all data of the entire archive processing process.

[0010] In the above implementation process, preliminary metadata of the entered archives is extracted and stored; semantic analysis is performed on the archives to identify semantic elements in the archives, where semantic elements include entities, relationships and events; identification rules are set, and archives are automatically identified and assigned identification tasks according to the preset identification rules; a process model is set, and real-time operations are received to automatically update the status of the archives at the corresponding process nodes and display them; a detailed identification report and related statistical information are generated based on the identification results, and all data of the entire archive processing process are stored; an in-depth understanding of the semantic information of the archive content is achieved, so that the identification results are accurate and comprehensive, meeting the needs of modern archive management for efficient and accurate identification.

[0011] Furthermore, the preliminary metadata extraction and storage of the input archives includes:

[0012] Enter files, including paper files and electronic document files;

[0013] Convert the entered files into a unified format;

[0014] The entered archives are initially metadata extracted and stored in the database, where the metadata includes the archive type, creation time and source.

[0015] In the above implementation process, the input archival data will be converted into a unified format and metadata will be extracted to facilitate subsequent processing.

[0016] Furthermore, the semantic analysis of the archive is performed to identify semantic elements in the archive, wherein the semantic elements include entities, relationships and events, including:

[0017] Construct a dictionary containing various entity types and process the archive to match words in the archive text with the dictionary and match the words with the corresponding type of entity;

[0018] Determine the location and grammatical structure of the entity according to the grammatical rules of the language;

[0019] Extracting features for entity recognition from text, wherein the features include: features of the word itself, context features of the word, and part-of-speech features;

[0020] Using the labeled entity training data, a supervised learning model is used to train the entity recognition model. The trained entity recognition model is used to predict entities and types for the newly input archive text.

[0021] Using dependency parsing tools, we construct a syntactic tree for each sentence to show the dependency relationships between words. Based on the dependency types and paths in the syntactic tree, we formulate rules to extract the relationships between entities.

[0022] By training the relation recognition model on texts labeled with semantic roles, the relation recognition model learns to identify the semantic role played by each component in the sentence;

[0023] According to the results of semantic role labeling, establish semantic role-based relationships between entities;

[0024] Pre-build a knowledge graph, where the knowledge graph contains various entities and the relationship types between entities;

[0025] When processing archival text, the identified entities are matched with entities in the knowledge graph. Once the entities in the text are successfully matched with the entities in the knowledge graph, the relationships in the knowledge graph are used to infer the relationships between the entities in the text and to supplement the missing relationship information.

[0026] Determine the keywords used to trigger the event. If the keywords are detected in the archive text, it is preliminarily determined that an event exists.

[0027] According to different types of events, event templates are constructed, and the content surrounding the trigger words in the text is matched with the event templates to identify complete event information;

[0028] Using the theory of frame semantics, each event is mapped to a semantic frame with different slots. The semantic frame corresponding to the event is identified in the archival text and the information of each slot is filled.

[0029] Use a pre-trained word vector model to convert words in the text into vector representations, where the word vectors include the semantic information of the words and represent the semantic relationship between words through vector operations;

[0030] A set network model is used to model the context of the text to capture the order information and contextual dependencies of words in the sentence;

[0031] Analyze the text's chapter structure and complete event recognition.

[0032] In the above implementation process, it is possible to identify semantic elements such as entities, relationships, events, etc. in the text, and understand the overall semantics and context of the text, which is conducive to subsequent archival identification.

[0033] Furthermore, the setting of identification rules, automatically identifying files according to the preset identification rules, and assigning identification tasks include:

[0034] Set up rules for assigning identification tasks;

[0035] When evaluating a new file text, the relevant information of the file is automatically read, and according to the evaluation task assignment rules, qualified personnel are searched in the evaluation personnel database to assign the evaluation task;

[0036] Collect competency data of appraisers and establish a competency model for each appraiser. The competency data includes the quality and efficiency of past appraisal tasks, professional skills, and experience level.

[0037] When a new appraisal task is received, the characteristics of the task are matched with the ability model of the appraiser, a machine learning algorithm is used to calculate the matching score between the task and each appraiser, and the appraiser is selected based on the score.

[0038] In the above implementation process, the rules cover multiple aspects such as the importance, timeliness, and integrity of archives. At the same time, the rule base is extensible and maintainable.

[0039] Furthermore, the process model is set up, and real-time operations are received to automatically update the status of the archive at the corresponding process node and display it, including:

[0040] Predefine the process model of archive appraisal, which includes the specific operations and requirements of each stage and sets different states for each process node;

[0041] After receiving real-time operations on the file, the status of the file at the corresponding process node is automatically updated;

[0042] The real-time status of the archive identification process is displayed through a graphical interface;

[0043] Based on business experience and process requirements, abnormal situation rules are set, and various data in the archive identification process are monitored in real time. When situations that meet the abnormal rules are found, the early warning mechanism is automatically triggered.

[0044] In the above implementation process, during the identification process, the progress of each stage is monitored in real time to ensure that the identification work proceeds smoothly according to the process; at the same time, it facilitates communication and information sharing between identification personnel to improve identification efficiency and accuracy.

[0045] Furthermore, after setting the process model, receiving real-time operations, and automatically updating the status of the archive at the corresponding process node and displaying it, the process further includes:

[0046] When receiving real-time operations on archives, automatically record the timestamp of the operations;

[0047] Based on timestamp data, calculate the residence time of each file at each process node and the overall identification progress, and display the progress information through dashboards or reports;

[0048] Among them, there is a relationship and dependency between multiple tasks in the archive identification process;

[0049] When the status of a task changes, the progress and status of related dependent tasks are automatically updated based on the task association relationship.

[0050] During the above implementation process, the progress of each stage is monitored in real time to ensure that the appraisal work proceeds smoothly according to the process.

[0051] Furthermore, a detailed identification report and relevant statistical information are generated based on the identification results, and all data of the entire archive processing process are stored, including:

[0052] Obtain basic data of archives;

[0053] Determine the final conclusion based on the appraisal results and comprehensive judgment of each stage of the appraisal process, and write the conclusion into the report;

[0054] Query the rules related to the file identification process from the identification rule library;

[0055] If natural language processing technology is used for semantic analysis during the identification process, the results of the semantic analysis shall be included in the basis for identification;

[0056] Propose corresponding treatment measures based on the appraisal conclusions;

[0057] Query all the files that have been authenticated from the database, classify and count them by file type, and present the statistical results in the form of tables or charts;

[0058] Search the database for files that have been appraised, classify and count them according to the appraisal conclusions, and display the statistical results in the form of a pie chart;

[0059] Stores all data from the entire archive processing process, including original archive data, metadata, NLP semantic analysis results, identification rules, identification process records, and identification results.

[0060] In the above implementation process, detailed appraisal reports and related statistical information are generated based on the appraisal results to provide data support for archive management decisions; efficient data storage and retrieval technologies are used to ensure the security, integrity and fast access performance of the data.

[0061] In a second aspect, an embodiment of the present application provides a file identification device for semantic recognition based on natural language processing technology, comprising:

[0062] The pre-entry module is used to extract and store preliminary metadata of the entered archives;

[0063] A semantic analysis module is used to perform semantic analysis on archives and identify semantic elements in the archives, where semantic elements include entities, relations, and events;

[0064] The identification processing module is used to set identification rules, automatically identify files according to the preset identification rules, and assign identification tasks;

[0065] The process processing module is used to set the process model, receive real-time operations, automatically update the status of the file at the corresponding process node and display it;

[0066] The result generation module is used to generate a detailed identification report and related statistical information based on the identification results, and store all data of the entire archive processing process.

[0067] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0068] A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the archive identification method based on semantic recognition of natural language processing technology as described above.

[0069] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a server, the archive identification method for semantic recognition based on natural language processing technology as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0071] Figure 1 A flowchart of a method for file identification based on semantic recognition using natural language processing technology provided in an embodiment of the present application;

[0072] Figure 2 This is a structural diagram of a file identification device based on semantic recognition of natural language processing technology provided in an embodiment of the present application;

[0073] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0075] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0076] NLP (Natural Language Processing) technology, namely natural language processing technology, is an important direction in the fields of computer science and artificial intelligence.

[0077] Please see Figure 1 , Figure 1 This is a flow chart of a method for file identification based on semantic recognition using natural language processing technology provided in an embodiment of the present application. The method for file identification based on semantic recognition using natural language processing technology includes:

[0078] 100. Extract and store preliminary metadata of the entered archives.

[0079] It should be noted that the archive identification system based on semantic recognition of natural language processing technology includes an archive entry module, an NLP semantic analysis module, an identification rule base module, an identification process management module, a result output module and a database module.

[0080] 110. Enter files, including paper files and electronic document files.

[0081] It is understandable that paper files need to be scanned into electronic format before being entered, and electronic document files can be directly imported into the file entry module.

[0082] 120. Convert the entered files into a unified format.

[0083] Optionally, a unified format can be established for all archives. This can be determined based on the type of archive (e.g., text, photos, audio, video, etc.) and the specific needs of the organization. For example, for text archives, formats such as layout files, OFD, DOCX, XML, and PDF can be selected because these formats have high compatibility and readability.

[0084] 130. Perform preliminary metadata extraction on the entered archives and store them in the database, where the metadata includes the archive type, creation time and source.

[0085] 200. Perform semantic analysis on the archives to identify semantic elements in the archives, where the semantic elements include entities, relationships and events.

[0086] It should be noted that the NLP semantic analysis module is one of the core modules of the system, using advanced NLP technology to conduct in-depth semantic analysis of archival content. It can identify semantic elements such as entities, relationships, and events in the text, and understand the overall semantics and context of the text. For example, for a contract file, this module can accurately identify key information such as the contracting parties, the subject matter of the contract, the signing date, and the content of the terms, and analyze the logical relationships and potential risks between the terms. In addition, this module also has a sentiment analysis function, which can determine the emotional tendencies expressed in the archival text, which is of great significance for archival appraisals involving subjective evaluations or opinions.

[0087] 211. Construct a dictionary containing various entity types and process the archives to match the words in the archive text with the dictionary and match the words with the corresponding type of entity.

[0088] Specifically, a dictionary containing various entity types (such as names of people, places, organizations, and products) is constructed. When processing document text, the words in the text are matched against the dictionary. When a match occurs, it is identified as an entity of the corresponding type. For example, for contract documents, a dictionary containing common company names is used. When these company names appear in the text, they are identified as one of the two parties in the contract.

[0089] 212. Determine the location and grammatical structure of the entity based on the grammatical rules of the language.

[0090] Specifically, based on the grammatical rules of the language, we determine the possible locations and grammatical structures of entities. For example, in Chinese, a noun phrase in the subject position is more likely to be an entity. By analyzing the grammatical structure of a sentence, we can find noun phrases that match the characteristics of an entity. For example, in the sentence "Party A (XX Company) agrees to purchase Party B's products," grammatical analysis can determine that "XX Company" is an entity.

[0091] 213. Extract features for entity recognition from text, where the features include: features of the word itself, context features of the word, and part-of-speech features.

[0092] Specifically, features used for entity recognition are extracted from text, such as word characteristics (such as capitalization and the presence of numbers), word context (such as the preceding and following words), and part-of-speech features. For example, when recognizing a person's name, surnames and given names often have specific word usage patterns, and identity-related words (such as "Mr." and "Ms.") may appear around the name.

[0093] 214. Use the training data with labeled entities and adopt the supervised learning model to train the entity recognition model. According to the trained entity recognition model, predict the entity and type of the newly input file text.

[0094] Specifically, using training data with labeled entities (e.g., entities such as the contracting parties and the subject matter of the contract in the contract text), supervised learning models (such as hidden Markov models, conditional random fields (CRFs), and BiLSTM-CRFs in deep learning) are trained. The trained model can then predict entities and their types based on features in new text. For example, in a new contract text, the model can accurately identify the names of the contracting parties based on previously learned features and patterns.

[0095] 215. Using dependency syntactic analysis tools, a syntactic tree is constructed for the sentence to show the dependency relationship between words. Based on the dependency relationship type and path in the syntactic tree, rules are formulated to extract the relationship between entities.

[0096] Specifically, dependency parsing tools are used to construct a syntactic tree for sentences, showing the dependency relationships between words. For example, in the sentence "Party A sells products to Party B," dependency parsing reveals that "Party A" is the subject of the action "selling," and "Party B" is the object of the action. This subject-action-object relationship helps identify relationships between entities.

[0097] Furthermore, rules are developed based on the dependency types and paths in the syntactic tree to extract relationships between entities. For example, if a dependency path such as "nsubj (subject) - verb - dobj (direct object)" exists, and both the subject and object are entities, then an action relationship can be extracted between the two entities. In the above example, this is the relationship between "Party A - Seller - Party B."

[0098] 221. By training the relation recognition model on texts labeled with semantic roles, the relation recognition model learns to identify the semantic role played by each component in the sentence.

[0099] Specifically, by training on a large amount of text labeled with semantic roles (such as agent, patient, time, and location), the model learns to identify the semantic role played by each component in a sentence. For example, in the sentence "Party A signed a contract with Party B at the company's headquarters on January 1, 2023," the model can identify "Party A" as the agent of the "signing" event, "Party B" as the patient, "January 1, 2023" as the time, and "company headquarters" as the location.

[0100] 222. Based on the results of semantic role labeling, establish semantic role-based relationships between entities.

[0101] Specifically, based on the results of semantic role labeling, semantic role-based relationships between entities are established. For example, in a contract signing scenario, the agent-patient relationship between the two parties in the "signing" event is identified, as well as the relationship between the time and place of the event and the contracting parties.

[0102] 223. Pre-build a knowledge graph, where the knowledge graph contains various entities and the relationship types between entities.

[0103] Specifically, an existing knowledge graph is pre-built or referenced. The knowledge graph contains various entities and the types of relationships between entities (such as partnerships between companies, family relationships between people, etc.). When processing archival text, the identified entities are matched with the entities in the knowledge graph.

[0104] 224. When processing archival text, the identified entities are matched with the entities in the knowledge graph. Once the entities in the text are successfully matched with the entities in the knowledge graph, the relationships in the knowledge graph are used to infer the relationships between the entities in the text and to supplement the missing relationship information.

[0105] For example, in a business cooperation file, if two company entities are identified, their specific relationship in the cooperation scenario described in the file text can be inferred through the cooperation relationship information about the two companies in the knowledge graph.

[0106] 231. Determine the keywords used to trigger the event. If the keywords are detected in the file text, it is preliminarily determined that an event exists.

[0107] Specifically, we identify keywords that can trigger events, such as verbs that indicate actions (e.g., "buy," "sell," and "sign") and words that indicate changes in status (e.g., "change," "terminate"). Once these trigger words are detected in the text, we can preliminarily determine the presence of an event. For example, in a contract file, the trigger word "sign a contract" indicates a contract signing event.

[0108] 232. Construct event templates based on different types of events, match the content surrounding the trigger words in the text with the event templates, and identify complete event information.

[0109] Specifically, event templates are constructed based on different types of events (such as contract signing events and product delivery events). These templates include elements such as the entity roles involved in the event (e.g., the contracting parties in a contract signing event), the conditions for the event (e.g., the fulfillment of contract terms), and the event's outcome (e.g., the contract becoming effective). The content surrounding the trigger words in the text is matched against the event template to identify the complete event information. For example, for a contract signing event template, if the text contains the names of the contracting parties, the signing date, and content related to the contract becoming effective, it will successfully match and identify a complete contract signing event.

[0110] 233. Using the theory of frame semantics, each event is mapped to a semantic frame with different slots. The semantic frame corresponding to the event is identified in the archival text and the information of each slot is filled.

[0111] Specifically, using frame semantics theory, each event corresponds to a semantic frame, which has different slots (such as the event's participants, time, location, and method). The semantic frame corresponding to the event is identified in the text and the information in each slot is filled in. For example, for a meeting event frame, slot information such as the meeting participants (through entity recognition), the meeting time (through time information extraction), and the meeting location (through location entity recognition) is identified, thus fully identifying the meeting event.

[0112] 234. Use a pre-trained word vector model to convert words in the text into vector representations, where the word vector includes the semantic information of the words and the semantic relationship between words is represented through vector operations.

[0113] Specifically, pre-trained word vector models (such as Word2Vec and BERT) are used to convert words in a text into vector representations. These word vectors contain semantic information about the words and can represent semantic relationships between them through vector operations. For example, by calculating the similarity of word vectors, we can determine the semantic proximity between two words (such as "purchase" and "procurement"). Then, the vectors of all words in the text are combined to obtain a semantic representation of the text, which is used to understand the overall semantic meaning of the text.

[0114] 235. The context of the text is modeled using a set network model to capture the order information and contextual dependencies of words in a sentence.

[0115] Optionally, recurrent neural networks (RNNs) or their variants (such as LSTMs and GRUs), or the self-attention mechanism in the Transformer architecture, can be used to model the context of the text. These models can capture the order and contextual dependencies of words in a sentence, thereby better understanding the semantics of the text. For example, in a sentence, context modeling can help us understand the specific entity referred to by a pronoun or the precise meaning of a polysemous word in the current context.

[0116] 236. Analyze the text structure and complete event identification.

[0117] Specifically, analyze the text's structure, such as the relationships between paragraphs (general-specific, causal, parallel, etc.) and the cohesive devices between sentences (conjunctions, pronoun reference, etc.). By understanding the structure of the text, one can grasp the overall logic and context of the text. For example, in a contract, analyzing the relationship between clauses can help determine which clauses are principal and which are subsidiary, and whether there is a causal relationship between clauses (e.g., what consequences will result from violating a principal clause), thereby understanding the context and semantics of the entire contract text.

[0118] 300. Set identification rules, automatically identify files according to the preset identification rules, and assign identification tasks.

[0119] It's important to note that the authentication rule library module stores a rich set of archival authentication rules, developed by archival management experts based on the characteristics of different archival types and relevant laws, regulations, and industry standards. These rules cover aspects such as the archival's importance, timeliness, and integrity. For example, for controlled archival items, the rule library includes rules for sensitive keywords, control level determination criteria, and control period. For important archives, there are also rules for determining their impact on organizational decision-making, business operations, and other aspects. The rule library is scalable and maintainable, allowing administrators to add, modify, and delete rules based on actual circumstances.

[0120] 310. Set up rules for assigning appraisal tasks.

[0121] Optionally, a series of appraisal task allocation rules can be pre-set in the system. For example, tasks can be assigned to appraisers in different professional fields based on file type (such as document files, scientific and technological files, financial files, etc.); tasks can be assigned to those with less workload based on the principle of balancing the workload of appraisers; or tasks can be assigned to appraisers with corresponding authority and experience based on the importance and control level of the files.

[0122] 320. When a new file text is being appraised, the relevant information of the file is automatically read, and according to the appraisal task assignment rules, qualified personnel are searched in the appraisal personnel database to assign the appraisal task.

[0123] Optionally, when a new file requires appraisal, the system automatically reads the file's relevant information (such as type and importance). Based on pre-set rules, it searches the appraiser database for qualified individuals and automatically assigns the appraisal task to them. For example, if a scientific research and development file is identified as a scientific and technological file, the system will identify it as a scientific and technological file and assign it to an appraiser with expertise in the field.

[0124] 330. Collect the competency data of appraisers and establish a competency model for each appraiser. The competency data includes the completion quality and efficiency of past appraisal tasks, professional skills, and experience level.

[0125] Specifically, we collect data on the appraisers' professional skills, experience, and the quality and efficiency of their past appraisal tasks to build a competency model for each appraiser. For example, by analyzing information such as the types of files they have previously appraised, the accuracy of their appraisal results, and the time it takes to complete their appraisal tasks, we generate a competency vector for each appraiser, which contains competency indicators across different dimensions.

[0126] 340. Upon receiving a new appraisal task, the characteristics of the task are matched with the competence model of the appraiser, a machine learning algorithm is used to calculate the matching score between the task and each appraiser, and the appraiser is selected based on the score.

[0127] Specifically, upon receiving a new appraisal task, the system matches the task's characteristics (such as the file's professional field and complexity) with the appraiser's competency profile. Machine learning algorithms (such as collaborative filtering and content-based recommendation algorithms) can be used to calculate a matching score between the task and each appraiser. The appraiser with the highest score is assigned the task. For example, for a file involving complex financial data, the system will prioritize assigning it to an appraiser with a high financial competency score and a moderate workload.

[0128] 400. Set up a process model and receive real-time operations, automatically update the status of the file at the corresponding process node and display it.

[0129] It's important to note that the Appraisal Process Management module manages the entire archive appraisal process, including tasks, process monitoring, and progress tracking. Following the pre-defined appraisal process (e.g., initial review, re-review, and final review), this module assigns archives to appropriate appraisers or automatically triggers intelligent appraisal processes. During the appraisal process, it monitors progress at each stage in real time to ensure smooth and consistent execution. The module also provides a communication and collaboration platform, facilitating information sharing among appraisers and improving appraisal efficiency and accuracy.

[0130] 410. A process model for archive appraisal is predefined, wherein the process model includes specific operations and requirements for each stage and sets different states for each process node.

[0131] Optionally, a process model for archive appraisal can be pre-defined in the system, including various stages (such as preliminary review, re-review, final review, etc.) and the specific operations and requirements of each stage, and different statuses can be set for each process node, such as "pending", "processing", "completed", etc.

[0132] 420. After receiving the real-time operation on the file, the status of the file in the corresponding process node is automatically updated.

[0133] Optionally, upon receiving real-time actions on a file (such as starting a preliminary review, submitting a review opinion, etc.), the file's status at the corresponding process node will be automatically updated. For example, if the appraiser clicks the "Start preliminary review" button, the system will update the file's status at the preliminary review node to "Processing" and record the start time.

[0134] 430. The real-time status of the archive appraisal process is displayed through a graphical interface.

[0135] Optionally, the real-time status of the file appraisal process can be displayed to administrators and relevant personnel through graphical interfaces (such as flowcharts and progress bars). Administrators can intuitively see which stage each file is in, as well as the number of tasks and completion status at each stage. For example, in a flowchart, different colored nodes represent different statuses, allowing administrators to quickly identify which files are stuck in the preliminary review stage and which have entered the final review stage.

[0136] 440. Based on business experience and process requirements, set up abnormal situation rules and monitor the data in the archive identification process in real time. When a situation that meets the abnormal rules is found, the early warning mechanism will be automatically triggered.

[0137] Specifically, a series of exception rules are set based on business experience and process requirements. For example, if the processing time of a certain process node exceeds the preset deadline (for example, the initial review should be completed within 3 working days; if it exceeds this time, it will be considered an exception); or if the appraiser modifies the appraisal results multiple times at a certain stage, and the modifications are significant, etc.

[0138] Specifically, the system monitors all data in the file appraisal process in real time. When any abnormalities are detected, an early warning mechanism is automatically triggered. Warnings can be delivered through in-system notifications, email alerts, and text message reminders, notifying relevant personnel (such as administrators and the appraisal personnel at that stage) to promptly address the abnormalities. For example, if a file remains uncompleted after more than five working days in the review phase, the system will send an early warning email to the reviewer and administrator, reminding them to monitor the appraisal progress.

[0139] 450. When receiving a real-time operation on a file, automatically record the timestamp of the operation.

[0140] Specifically, when a real-time operation on a file is received (such as opening a file, submitting an appraisal opinion, passing an audit, etc.), the timestamp of the operation is automatically recorded. Optionally, these timestamps are accurate to the second to provide basic data for subsequent progress statistics.

[0141] 460. Based on the timestamp data, calculate the residence time of each file at each process node and the overall identification progress, and display the progress information in the form of a chart.

[0142] Specifically, based on timestamp data, the system calculates the time each file spends at each process node, along with overall appraisal progress (such as the percentage of completed stages compared to the total number of stages). This progress information is then presented to relevant personnel through dashboards and reports. For example, an administrator can view that a file has spent two days in the initial review stage and one day in the review stage since entering the appraisal process, with an overall progress of 60% (assuming there are five stages in total and three have been completed).

[0143] 470. Among them, there is a relationship and dependency between multiple tasks in the archive appraisal process.

[0144] Specifically, complex archival appraisal processes may involve multiple tasks with interconnected and interdependent relationships. For example, the review phase may require the initial reviewer to submit supplementary materials before it can begin; or the final review may require comprehensive consideration of the reviewer's opinions. The system defines the prerequisites and dependencies between these tasks.

[0145] 480. When the status of a task changes, the progress and status of related dependent tasks will be automatically updated based on the task association relationship.

[0146] Specifically, when the status of a task changes, the progress and status of related dependent tasks are automatically updated based on the task relationships. For example, if the initial reviewer submits supplementary materials, the system will automatically update the status of the review task from "Waiting for Materials" to "Ready to Start" and recalculate the estimated start time and overall progress of the review task. This allows relevant personnel to clearly understand the progress changes caused by the dependencies between tasks, allowing them to rationally arrange work and resources.

[0147] 500. Generate detailed appraisal reports and relevant statistical information based on the appraisal results, and store all data of the entire archive processing process.

[0148] It should be noted that the result output module generates a detailed report and related statistical information based on the appraisal results. The report includes basic archive information, the appraisal conclusion (such as whether to maintain, open, or control), the appraisal basis (specifically, the appraisal rules and semantic analysis results), and recommended treatment measures. Statistical information can be analyzed by archive type, appraisal conclusion, time, and other dimensions, providing data support for archive management decisions.

[0149] It should be noted that the identification database module stores all data generated during the operation of the system, including original archival data, metadata, NLP semantic analysis results, identification rules, identification process records, identification results, etc. The database uses efficient data storage and retrieval technology to ensure data security, integrity, and fast access performance.

[0150] 510. Obtain basic data of archives.

[0151] Specifically, we need to obtain basic data about the archive, such as the file number, file name, creation time, creator, department, file type (such as document files, scientific files, financial files, etc.). This information is usually stored in specific fields in the database and can be extracted through query statements.

[0152] For example, consider a scientific and technological file titled "XX Project R&D Report," with the file number "001-KJ01-XM005-ML001-AJ003," creation date May 1, 2023, creator name Zhang San, department name R&D, and file type name Scientific and Technological File. This information will serve as the beginning of the appraisal report, providing context for the subsequent content.

[0153] 520. Based on the appraisal results and comprehensive judgment at each stage of the appraisal process, the final appraisal conclusion shall be determined and written into the report.

[0154] Specifically, the final conclusion is determined based on the findings and comprehensive assessments at each stage of the appraisal process. Conclusions may include maintain, open, or control. For example, after preliminary, reexamination, and final review, a file whose control period has expired and whose content is no longer sensitive will be considered open; whereas a file containing important business information within its validity period will be considered controlled.

[0155] Specifically, the appraisal conclusion should be clearly written into the report, usually expressed in a concise and clear sentence, such as "After appraisal, the appraisal conclusion of the archive is: open."

[0156] 530. Query the rules related to the file identification process from the identification rule library.

[0157] Specifically, the rules related to the identification process of the archive are queried from the identification rule library. For example, for an archive, it may involve sensitive keyword matching rules, level judgment standard rules, etc., and the specific content of these rules and how to apply these rules in the identification of the archive are explained in detail. For example, during the identification process, by scanning the archive text for keywords, it was found that it contained sensitive keywords such as "XX core technical parameters". According to the level judgment standard, the archive belongs to the non-public archive within the level, and the period is 5 years from the date of creation. As of this identification, the period has expired, and after expert review, the content is no longer sensitive, so it is determined to be no longer controlled.

[0158] 540. If natural language processing technology is used for semantic analysis during the identification process, the results of the semantic analysis shall be included in the basis for identification.

[0159] Optionally, if natural language processing (NLP) technology is used for semantic analysis during the appraisal process, the results of this semantic analysis can also be incorporated into the appraisal basis. For example, if semantic analysis reveals that the description of a product's market share in the archives is consistent with public reports and contains no sensitive information, this result supports the final conclusion. This could be expressed as, "NLP semantic analysis shows that the description of market share in the archives is consistent with public information and contains no sensitive content, further supporting the appraisal conclusion."

[0160] 550. Based on the appraisal conclusion, put forward corresponding treatment measures.

[0161] Specifically, based on the appraisal conclusions, corresponding treatment measures are recommended. For example, for open archives, it is recommended to remove them from the controlled archives repository, manage and utilize them as ordinary archives, and update the archive status and related metadata in the system. For controlled archives, it is recommended to continue to store, approve borrowing, etc. in accordance with the management requirements of controlled archives, and conduct regular reviews. These treatment measures are written in detail in the report, such as "Since this archive is no longer controlled, it is recommended to transfer it from the controlled archives repository to the ordinary archives repository, update the archive status in the system to 'open', and indicate the opening date and related information in the archive catalog to facilitate subsequent management and utilization."

[0162] 560. Query all the files that have been appraised from the database, classify and count them according to the file type, and display the statistical results in the form of tables or charts.

[0163] Specifically, query all the files that have been appraised from the database and classify and count them by file type. For example, count the number and proportion of various types of files such as document files, scientific and technological files, and financial files. You can use SQL query statements, such as:

[0164] SELECT COUNT(*) AS count, type FROM archives WHERE status='completed' GROUP BY type, where archives is the archive table, status is the archive identification status field, and type is the archive type field.

[0165] Optionally, the statistical results can be displayed in the form of a table or chart, such as a bar chart, with the horizontal axis representing the file type and the vertical axis representing the number, to intuitively present the identification status of different types of files.

[0166] 570. Query the files that have been appraised from the database, classify and count them according to the appraisal conclusions, and display the statistical results in the form of a pie chart.

[0167] Specifically, query the database for files that have been appraised and categorize them according to the appraisal conclusion (maintain, open, controlled, etc.). For example, count the number of controlled files (X), the number of maintained files (Y), the number of open files (Z), etc. Use a similar SQL query statement, such as:

[0168] SELECT COUNT(*)AS count, conclusion FROM archives WHERE status='completed' GROUP BY conclusion.

[0169] Optionally, the statistical results can be displayed in the form of a pie chart, with each sector area representing a different identification conclusion and its proportion, so that managers can quickly understand the distribution of various identification conclusions.

[0170] For example, statistics can be collected by time dimensions such as year, month, and week. For example, to count the number of files that have been appraised each year, the query statement is as follows:

[0171] SELECT YEAR(completed_date) AS year, COUNT(*) AS count FROM archivesWHERE status='completed 'GROUP BY YEAR(completed_date), where completed_date is the time field when the archive appraisal was completed.

[0172] Optionally, the statistical results of the time dimension can be displayed in a line graph, with the horizontal axis being time (such as year) and the vertical axis being the number of archives. The trend of the line graph can be used to observe the changing trends of the appraisal work in different time periods, providing data support in the time dimension for archive management decisions, such as whether it is necessary to increase the number of appraisal personnel or optimize the appraisal process in certain time periods.

[0173] 580. Store all data of the entire archive processing process, including the original archive data, metadata, NLP semantic analysis results, identification rules, identification process records and identification results.

[0174] Therefore, the database adopts efficient data storage and retrieval technology to ensure the security, integrity and fast access performance of data.

[0175] For example, taking the appraisal of public documents and archives as an example, the scenario is: a city needs to appraise a large number of public documents and archives, including notices, announcements, reports, requests, etc., to determine whether they can be opened to the public and the scope and method of opening. The content of public documents and archives involves all aspects of work, such as policies and regulations, government activities, people's livelihood affairs, etc.

[0176] Specifically, the implementation process includes: file entry and preprocessing: enter the official document files into the file entry module by scanning paper documents or importing the official document data into the e-government system. The system automatically extracts the metadata of the official document, such as the official document number, issuing agency, issuing date, etc., and preprocesses the official document text, including removing irrelevant information such as red headers and official seals, and performing text cleaning and word segmentation operations.

[0177] NLP semantic analysis and feature extraction: The NLP semantic analysis module conducts in-depth analysis of official document texts, identifying semantic information such as policy themes, departments and institutions involved, relevant legal and regulatory references, and event descriptions. It extracts the document's subject terms, such as "urban construction," "environmental protection," and "social security," as well as keywords, such as specific policy measures, project names, and funding amounts. It also generates semantic vectors to represent the document's semantic features.

[0178] Rule-based authentication: The authentication process management module matches the semantic features and metadata of official documents with the rules in the authentication rule library according to the process and requirements of archival authentication. For example, for official documents involving sensitive information, if the document contains specific keywords or involves major decisions, important strategies, and meets the criteria for determining sensitive information in the authentication rules, the system will preliminarily determine that the document is a sensitive document and push it to the relevant departments for review. For some general notices and announcements, if the semantic analysis results show that their content does not involve sensitive information and complies with information disclosure regulations, the system can preliminarily determine that they are publicly available documents.

[0179] Intelligent appraisal and manual intervention: For some policy and regulatory documents, the system can automatically perform intelligent appraisal based on NLP semantic analysis results and the appraisal rule library, such as determining the timeliness and scope of application of the policy, and generate an appraisal conclusion. For some complex documents, such as those involving multi-department coordination, policy adjustments, or controversial documents, the system will trigger a manual intervention process. Appraisers can use the NLP semantic analysis tools provided by the system to conduct in-depth analysis of the semantic content and potential impact of the document, communicate and discuss with leaders and experts from relevant departments, and ultimately determine the appraisal conclusion of the document, including whether it can be made public, the scope of disclosure (such as full text disclosure, partial disclosure, etc.), and the time of disclosure.

[0180] Result Output and Feedback: The appraisal result output module generates a detailed official document appraisal report based on the appraisal conclusions. This report includes the document's basic information, the appraisal conclusion, the appraisal basis (specifically, the appraisal rules and semantic analysis results involved), and recommended handling measures (such as the document's storage and use requirements, and the channels and methods for publishing publicly available documents). The appraisal report is stored in the archive management system database and provided to relevant departments and leaders. The system also collects feedback and opinions from appraisers on the appraisal results, as well as public feedback after the actual disclosure. This information is used to continuously optimize the appraisal rule base and NLP semantic analysis model, improving the scientific nature and accuracy of official document and archive appraisals, and better serving information disclosure and government administration.

[0181] As described above, the embodiment of the present application performs preliminary metadata extraction and storage on the entered archives; performs semantic analysis on the archives to identify semantic elements in the archives, wherein the semantic elements include entities, relationships and events; sets identification rules, automatically identifies the archives according to the preset identification rules, and assigns identification tasks; sets a process model, and receives real-time operations, automatically updates the status of the archives at the corresponding process nodes and displays them; generates detailed identification reports and related statistical information based on the identification results, and stores all data of the entire archive processing process; deeply understands the semantic information of the archive content, so that the identification results are accurate and comprehensive, meeting the needs of modern archive management for efficient and accurate identification.

[0182] Specifically, the embodiment of the present application is based on the application of deep NLP semantic recognition technology: it innovatively integrates advanced NLP semantic recognition technology into the process of archival appraisal, and can accurately understand the semantic information of archival texts, breaking through the limitations of traditional archival appraisal that is based only on surface information and simple keyword matching. Through the comprehensive recognition of semantic elements such as entities, relationships, and events and the extraction of semantic features, it provides a richer and more accurate basis for archival appraisal, greatly improving the accuracy and reliability of the appraisal. For example, in the appraisal of a historical document archive, the system can not only identify the basic information such as people, places, and time in the document, but also understand the background, process, and impact of the historical events described in the document, so as to more accurately judge the historical value and importance of the document.

[0183] The embodiments of the present application achieve deep integration of technologies and break through traditional limitations: Limitations of traditional archive appraisal: Traditional archive appraisal methods are often limited to simple processing of archive surface information, such as preliminary classification and judgment based only on limited information such as the title and keywords of the archive. This method cannot deeply explore the intrinsic meaning and potential value of the archive content, and can easily lead to omissions and misjudgments of important information. For example, for some historical document archives, it may not be possible to accurately judge their importance and influence in a specific historical period just by the title, and simple keyword matching may not be able to fully reflect the true content and value of the archive due to unreasonable keyword selection and weight setting. Deep integration of NLP semantic recognition technology: The embodiments of the present application innovatively integrate advanced NLP semantic recognition technology into the archive appraisal process, achieving a comprehensive and in-depth understanding of the archive text. This technology can perform detailed grammatical analysis, semantic parsing and contextual understanding of the archive text, not just staying at the surface form of the text, but going deep into the semantic level of the text. For example, when processing a historical document archive, the system can accurately identify entity information such as names of people, places, and dates, which is also possible with traditional methods. However, it goes a step further and analyzes the relationships between these entities, such as kinship and affiliation between characters, the chronological order of events, and causal relationships. At the same time, the system can understand the context, process, and impact of historical events described in the text. For example, by analyzing the description of a historical event in a document, including the cause of the event, the various parties involved, the course of the event, and its impact on the social, political, and economic aspects of the time, it can more accurately assess the value and importance of the document in historical research. This deep integration makes archival appraisal no longer a simple information screening, but an intelligent analysis process based on a comprehensive and in-depth understanding of the archival content.

[0184] This embodiment of the present application involves comprehensive identification and feature extraction of semantic elements: comprehensive identification of entities, relationships, and events. It utilizes NLP technology to accurately identify entities in archival text, covering various entity types, such as names (including historical figures, modern figures, fictional characters, etc.), place names (cities, regions, specific locations, etc.), organization names (institutions, enterprises, social organizations, etc.), time (specific dates, time periods, historical periods, etc.), and item names. Taking a corporate archive as an example, the system can accurately identify entity information such as the company's name, address, principal, partners, product names, and production time. Based on entity identification, it further analyzes relationships between entities, such as the partnership between the company and its partners, and the correspondence between products and production time. It can also identify various events described in the archive, such as the company's founding, product development, and marketing events, and analyze the chronological order and causal relationships of these events. For example, by analyzing corporate archives, it can be discovered that the successful development of a certain product was due to the company's collaboration with a research institute, and that the product's launch led to an increase in the company's market share. The relationships and impacts between these events can be accurately captured and analyzed by the system. Rich semantic feature extraction: In addition to identifying entities, relationships, and events, the system can also extract rich semantic features, providing a multi-dimensional basis for archival appraisal. These semantic features include but are not limited to subject terms, keywords, and semantic vectors. Subject terms summarize the core content and subject areas of an archive. For example, the subject terms for a scientific archive might be "artificial intelligence," "machine learning," or "data mining." Keywords focus on highlighting key information points within the archive, such as specific technical terms, important parameters, and key events. Semantic vectors represent the semantic information of archival text in vector form, facilitating operations such as semantic similarity calculation and cluster analysis. By extracting these semantic features, the system can more accurately classify, compare, and evaluate archives. For example, when appraising a batch of scientific archives, subject terms and keywords can be used to quickly identify archives related to a specific research direction. Semantic vectors can then be used to calculate similarity between archives, identifying archives with similar research content or technical approaches. This provides researchers with more comprehensive and accurate reference materials, helps uncover potential value and relevant information within archives, and improves the accuracy and reliability of archive appraisals.

[0185] The specific manifestations of the improvement of the accuracy and reliability of identification by the embodiments of the present application are as follows: More accurate value judgment: Taking historical document archives as an example, traditional methods may classify them as general historical materials based only on the title of the document or some surface information, but through the in-depth analysis of the content of the document by NLP semantic recognition technology, the system can discover the important information and value hidden therein. For example, for a seemingly ordinary diary document, the system can accurately judge that the document has important reference value for studying the social life, interpersonal relationships and other aspects of the historical period by identifying the social customs, people's sufferings and details of the author's interactions with important historical figures at that time mentioned therein, combined with the semantic understanding and background analysis of this information, thereby avoiding the underestimation of value caused by the limitations of traditional identification methods. More comprehensive information consideration: When identifying archives, traditional methods may ignore other relevant factors because they only focus on some key information, thereby affecting the accuracy of the identification results. The NLP semantic recognition technology of the embodiments of the present application can comprehensively consider various information in the archives, including subtle expressions in the text, implicit logical relationships, etc. For example, when identifying a legal file, the system will not only focus on the basic facts of the case and the citation of legal provisions, but also understand factors such as the tone and emotional tendencies in the parties' statements and the logical coherence between different evidence through semantic analysis, so as to more comprehensively and accurately judge the nature of the case, the reliability of the evidence and the accuracy of the application of the law, providing a more reliable basis for the identification of legal files and reducing the risk of misjudgment due to incomplete information.

[0186] The embodiments of the present application are adaptable to complex and diverse file types: different types of files have different characteristics and identification requirements, and traditional methods are often difficult to adapt to this diversity. The NLP semantic recognition technology of the embodiments of the present application has strong versatility and adaptability, and can effectively handle various types of files, whether they are historical documents, scientific and technological reports, legal documents, corporate files or official documents. For example, for scientific and technological report files, the system can accurately understand the complex content such as professional terms, technical processes and experimental data, and conduct identification based on this information; for official document files, the system can identify the type of document, purpose of writing, policy content and scope of influence, etc., thereby providing an accurate basis for the classification, level determination and disclosure scope of official documents. This good adaptability to complex and diverse file types enables the embodiments of the present application to play an important role in different fields and scenarios, greatly improving the overall accuracy and reliability of file identification.

[0187] The embodiment of the present application integrates intelligent identification rules and NLP: the identification rule base is closely integrated with NLP semantic analysis, realizing the organic integration of rule-driven and semantic understanding. The identification rules are no longer isolated, static clauses, but are mutually related and mutually verified with the semantic content of the archives. The system can automatically match and apply the corresponding identification rules according to the results of NLP semantic analysis. At the same time, the identification personnel can also better understand and interpret the application of the identification rules through the results of semantic analysis, thereby improving the operability and adaptability of the identification rules. For example, for the identification of controlled archives, the system can identify keywords and their contextual context based on semantic analysis, accurately judge the controlled level and scope, and give reasonable identification conclusions based on the corresponding identification rules.

[0188] Specifically, the organic integration of rules and semantics: Limitations of traditional identification rules: In traditional archive identification, identification rules are usually a series of pre-set isolated and static clauses. These rules are often formulated based on experience and general standards and lack in-depth interaction with the specific content of the archives. For example, for the identification of controlled archives, traditional rules may simply list some keywords or stipulate that certain types of archives are controlled, but in actual applications, these rules are difficult to accurately cope with the diversity and complexity of archive content. Because relying solely on keyword matching may lead to misjudgments, for example, a keyword may have different meanings in different contexts, and traditional rules cannot take into account such contextual differences, resulting in inaccurate identification results. Innovative way of intelligent integration: The embodiment of the present application closely combines the identification rule library with NLP semantic analysis, breaking the isolation and static nature of traditional rules. Identification rules are no longer rigid clauses, but establish a dynamic association with the semantic content of the archives. The system uses NLP technology to conduct in-depth analysis of the archive text and understand the semantic information therein, including entities, relationships, events, and contextual context. Then, based on these semantic analysis results, the corresponding identification rules are automatically matched and applied. For example, in the identification of controlled archives, the system not only identifies sensitive keywords but also analyzes the context in which these keywords appear. If a keyword appears in a text describing a common workflow, and the context doesn't indicate controlled nature, the system might not simply classify the archive as controlled. However, if the keyword appears in the context of key content such as core technologies or strategic decisions, the system will incorporate relevant identification rules to accurately determine the level and scope of control. This organic integration of rules and semantics makes the identification process more intelligent and precise, better adapting to the changes and diversity of archive content.

[0189] The present embodiment automatically matches and applies rules: Efficient and accurate rule application: The system can automatically and quickly match the most appropriate identification rules based on the real-time results of NLP semantic analysis, greatly improving the efficiency and accuracy of identification work. Taking corporate archives as an example, when a new contract file enters the system, the NLP semantic analysis module quickly identifies key contract information, such as the parties to the contract, the contract subject, the contract amount, and the terms. The system then automatically searches the identification rule library for relevant rules based on this semantic information, such as rules for determining the significance of contract amounts reaching a certain value, or rules covering specific technologies or business areas. This automatic rule matching and application process requires no human intervention, avoiding omissions and errors that may occur when manually searching and judging rules, and ensuring the comprehensive and accurate application of identification rules. For example, for a contract involving a large financial transaction and containing sensitive technical information, the system can quickly identify these key elements and, based on the corresponding identification rules such as significance, accurately classify the contract as an important and controlled file, providing a reliable basis for subsequent management and processing. Dynamic adaptation to different archives: Due to the diverse content and characteristics of different archives, traditional static rules are difficult to meet diverse identification needs. The automatic matching and application rule mechanism of the embodiment of the present application has strong dynamic adaptability. Regardless of whether the archive is about historical events, scientific research, or commercial transactions, the system can extract its unique semantic features through NLP semantic analysis, and then flexibly match and apply identification rules based on these features. For example, for a historical document archive, the system may match relevant rules such as the importance assessment, authenticity judgment, and preservation value identification of historical materials based on semantic information such as the detailed description of historical events, the complexity of character relationships, and the source and age of the document; and for a scientific research report archive, the system will automatically apply identification rules on the innovation and scientificity of scientific research results based on the semantic content such as the research methods, experimental data, research results, and the association with existing scientific research results in the report. This dynamic adaptability enables the system to be widely used in various types of archive identification, improving the versatility and practicality of the system.

[0190] The embodiments of the present application enhance the operability and adaptability of identification rules: making it easier for identification personnel to understand and operate them: Traditional identification rules may be relatively abstract and difficult to understand for identification personnel, especially when faced with complex archives, making it difficult to accurately grasp the application conditions and scope of the rules. However, the embodiments of the present application provide identification personnel with more intuitive and clear operational guidance by combining identification rules with NLP semantic analysis results. By viewing the system's semantic analysis results of the archives, identification personnel can better understand the content and semantic characteristics of the archives, and then understand why certain identification rules are applied and how these rules are related to the archive content. For example, in the identification of controlled archives, identification personnel can see the keywords identified by the system and their contextual analysis, as well as how this information corresponds to the specific terms in the identification rules. This enables identification personnel to understand and implement identification rules more accurately, reduces identification differences caused by inconsistent understanding of the rules, and improves the quality and consistency of identification work. Improved adaptability of rules: As archive content and management requirements continue to change, identification rules also need to be continuously updated and adjusted. The intelligent fusion mechanism of the embodiments of the present application enables identification rules to better adapt to these changes. On the one hand, the system can automatically identify potential deficiencies or inapplicability in existing identification rules based on new semantic patterns and features revealed in the NLP semantic analysis results, providing a basis for rule optimization and updating. For example, if, while analyzing a large number of new scientific and technological archives, the system discovers that keywords and semantic relationships in certain emerging technology fields are not adequately considered in existing identification rules, it can prompt administrators to supplement and improve the relevant rules. On the other hand, when archive management policies, regulations, or business processes change, administrators can quickly verify and adjust the effectiveness and applicability of the new rules by updating the identification rule library and incorporating the results of NLP semantic analysis. For example, if new regulations on official document control are issued, administrators can convert the new regulations into identification rules and enter them into the system. Then, through semantic analysis and rule application testing on a sample of typical official documents, administrators can ensure that the new rules can be accurately applied to actual archive identification work. This improves the adaptability and timeliness of the identification rules, ensuring that the system maintains a high-efficiency and accurate identification state.

[0191] The collaborative mechanism between intelligent identification and manual identification in the embodiment of the present application: a working mode in which intelligent identification and manual identification cooperate and complement each other is established. Under the premise of ensuring the efficiency of identification, the high efficiency of artificial intelligence and the professional knowledge and experience of human experts are fully utilized. For simple archives with clear rules, the system can automatically complete the identification, which greatly improves work efficiency; for complex archives, manual identification personnel can use the NLP semantic analysis tools and intelligent identification results provided by the system to conduct more in-depth and accurate identification, ensuring the accuracy and authority of the identification results. This collaborative mechanism not only improves the overall efficiency of archive identification, but also ensures the quality of identification, and maximizes the advantages of man and machine.

[0192] Feedback optimization mechanism for identification results in the embodiment of the present application: It has a complete identification result feedback optimization mechanism, which can continuously optimize the identification rule base and NLP semantic analysis model based on the feedback from the identification personnel and the actual identification situation. Through the accumulation and analysis of a large number of identification cases, the system can automatically learn and adjust the weights, thresholds and parameters of the identification rules and the NLP model, so that it can better adapt to the identification needs of different types of archives, and realize the self-evolution and continuous improvement of the system. This mechanism enables the system to continuously improve the accuracy and intelligence level of identification as time goes by and the frequency of use increases, providing users with better quality archive identification services.

[0193] Specifically, the comprehensiveness and systematicness of the feedback optimization mechanism: The shortcomings of traditional systems: Traditional archive appraisal systems often lack an effective feedback mechanism. Once the appraisal rules and models are set, it is difficult to dynamically adjust and optimize them according to actual usage. This results in the system being unable to make adaptive changes in a timely manner when faced with new archive types, changing appraisal standards or continuously accumulated appraisal experience, thereby affecting the accuracy and effectiveness of the appraisal. For example, over time, the importance of certain archives may change, or the introduction of new laws and regulations may lead to adjustments to the appraisal standards of controlled archives, but traditional systems cannot automatically perceive these changes and make corresponding optimizations. They can only rely on manual updating of rules, which is not only inefficient but also prone to omissions and errors. The innovation of the embodiment of the present application: The embodiment of the present application has a complete appraisal result feedback optimization mechanism, covering multiple dimensions from feedback from appraisers to analysis of actual appraisal situations. As front-line users, the experience and judgment of appraisers are crucial to system optimization. The system can collect direct feedback from appraisers on the appraisal results, including approval, questioning and modification suggestions of the appraisal conclusions. The system also automatically records various data from the actual identification process, such as the distribution of identification results for different types of archives, the triggering frequency and effectiveness of identification rules, and the performance of the NLP semantic analysis model in different scenarios. By comprehensively analyzing this rich information, the system can fully understand its strengths and weaknesses in identification work, providing a solid data foundation and direction for subsequent optimization.

[0194] Automatic Learning and Adjustment Based on Data Accumulation: Automated learning is achieved by accumulating and analyzing a large number of identification cases and applying advanced machine learning algorithms to automatically learn and adjust the identification rule base and NLP semantic analysis model. Specifically, for the identification rule base, the system automatically adjusts the weights and thresholds of the identification rules based on the accuracy and reliability of different identification results, as well as feedback from appraisers. For example, in the identification of controlled archives, if a keyword is accurately identified as controlled in a specific context, the weight of the identification rule corresponding to that keyword will be increased accordingly. Conversely, if a rule frequently leads to false positives, the system will automatically reduce its weight or adjust the threshold to improve the rule's applicability. For the NLP semantic analysis model, the system automatically adjusts model parameters based on the semantic analysis results of the archive text, such as the accuracy of entity recognition, the completeness of relationship extraction, and the validity of the semantic vector. For example, if the system detects low entity recognition accuracy for a certain type of archive, it will automatically adjust model parameters related to that type of archive, such as the dimension of the word vector and the number of layers and nodes in the neural network, to improve the model's performance when processing that type of archive.

[0195] Advantages of Adapting to Different Archive Types: This automatic learning and adjustment mechanism, based on accumulated data, enables the system to quickly adapt to the authentication needs of various archive types. Whether it's historical documents, scientific reports, commercial contracts, or official documents, the system continuously refines its authentication capabilities as it processes and analyzes these archives. For example, for historical archives, as the system processes an increasing number of documents, it automatically learns the linguistic characteristics, common vocabulary, and expressions of different historical periods, enabling more accurate identification of entities, relationships, and events within the documents, providing a more precise basis for authentication. For scientific report archives, the system optimizes its NLP semantic analysis model based on accumulated information on professional terminology, technical processes, and research methods, further understanding the content and value of scientific reports. It then adjusts its authentication rules to ensure that the authentication of scientific and technological archives is consistent with their professional characteristics and practical value. This adaptive capability enables the system to maintain a high level of authentication accuracy and intelligence across a diverse range of archives, providing users with more personalized and precise archive authentication services.

[0196] Self-evolution and continuous improvement of the system in the embodiment of the present application: The process and effects of self-evolution: Over time and with increasing frequency of use, the embodiment of the present application is capable of continuous self-evolution and continuous improvement. In its initial stages, the system may operate based on a few general identification rules and NLP models. However, as a large number of identification cases accumulate and feedback information is continuously incorporated, the system will gradually develop a set of identification rule bases and NLP semantic analysis models optimized for specific user groups and file types. For example, a system specifically designed for enterprise archive management will continuously optimize itself over the long term based on the enterprise's business characteristics, archive content style, and internal identification standards and practices. For common enterprise contract archives, the system will more accurately identify key information and potential risks in contract terms, and its assessment of sensitive information will be more consistent with the enterprise's actual control requirements. For enterprise R&D project archives, the system will better understand the professional content in technical documents and accurately assess the project's innovation and importance. This self-evolution enables the system to deeply integrate with user needs and usage scenarios, providing increasingly high-quality archive identification services. The value enhancement brought by continuous improvement: The continuous improvement of the system is reflected not only in improved identification accuracy, but also in multiple aspects such as work efficiency and user experience. By optimizing identification rules and NLP models, the system can process archives more quickly, reduce the number of misjudgments and manual interventions, and thus improve overall work efficiency. At the same time, more accurate and intelligent identification results can also provide users with more valuable references, helping them better manage and utilize archival resources. For example, for archive managers, the system can more accurately screen out important and controlled archives, reducing their workload and improving the standardization and security of archive management; for scientific researchers or corporate decision makers, the system's precise identification and analysis of relevant archives can provide them with more comprehensive and accurate information support, helping them make more scientific decisions. This ability to continuously improve makes the system more vital and competitive, enabling it to always maintain a leading position in the ever-changing archive management environment and create greater value for users.

[0197] The above steps are not to be performed in a strict order as described in the numbers, but should be understood as an overall solution.

[0198] In the second aspect, based on the above embodiments, Figure 2 This is a schematic diagram of the structure of a file identification device based on semantic recognition of natural language processing technology provided in an embodiment of the present application. Figure 2 The archive identification device based on semantic recognition of natural language processing technology provided in this embodiment specifically includes: an input advance module 201, a semantic analysis module 202, an identification processing module 203, a process processing module 204 and a result generation module 205.

[0199] Among them, the advance entry module 201 is used to extract and store preliminary metadata of the entered archives; the semantic analysis module 202 is used to perform semantic analysis on the archives and identify the semantic elements in the archives, wherein the semantic elements include entities, relationships and events; the identification processing module 203 is used to set identification rules, automatically identify archives according to the preset identification rules, and assign identification tasks; the process processing module 204 is used to set the process model, and receive real-time operations, automatically update the status of the archives at the corresponding process nodes and display them; the result generation module 205 is used to generate a detailed identification report and related statistical information based on the identification results, and store all data of the entire archive processing process.

[0200] As described above, the embodiment of the present application performs preliminary metadata extraction and storage on the entered archives; performs semantic analysis on the archives to identify semantic elements in the archives, wherein the semantic elements include entities, relationships and events; sets identification rules, automatically identifies the archives according to the preset identification rules, and assigns identification tasks; sets a process model, and receives real-time operations, automatically updates the status of the archives at the corresponding process nodes and displays them; generates detailed identification reports and related statistical information based on the identification results, and stores all data of the entire archive processing process; deeply understands the semantic information of the archive content, so that the identification results are accurate and comprehensive, meeting the needs of modern archive management for efficient and accurate identification.

[0201] The archive identification device for semantic recognition based on natural language processing technology provided in the embodiment of the present application can be used to execute the archive identification method for semantic recognition based on natural language processing technology provided in the above embodiment, and has corresponding functions and beneficial effects.

[0202] On the third aspect, an embodiment of the present application further provides an electronic device that can integrate the archive identification device for semantic recognition based on natural language processing technology provided in an embodiment of the present application. Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 The electronic device includes: an input device 33, an output device 34, a memory 32, and one or more processors 31; the memory 32 is used to store one or more programs; when the one or more programs are executed by the one or more processors 31, the one or more processors 31 implement the archive identification method based on semantic recognition of natural language processing technology as provided in the above embodiment. The input device 33, the output device 34, the memory 32, and the processor 31 can be connected by a bus or other means. Figure 3 The bus connection is taken as an example.

[0203] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, that is, realizes the above-mentioned archive identification method of semantic recognition based on natural language processing technology.

[0204] The electronic device provided above can be used to execute the archive identification method based on semantic recognition of natural language processing technology provided in the above embodiment, and has corresponding functions and beneficial effects.

[0205] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the archive identification method based on semantic recognition based on natural language processing technology as described above, and can achieve the same beneficial effects.

[0206] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present application is not limited to the archive identification method based on semantic recognition of natural language processing technology as described above, and can also execute related operations in the archive identification method based on semantic recognition of natural language processing technology provided in any embodiment of the present application.

[0207] In a fifth aspect, the embodiments of the present application further provide a computer program product. The methods described in the various embodiments of the present application can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the various embodiments of the present application are executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model), or other programmable device.

[0208] The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0209] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0210] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0211] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0212] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0213] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0214] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A method for file identification based on semantic recognition of natural language processing technology, characterized in that: The method comprises: Extract and store preliminary metadata of the entered archives; Perform semantic analysis on the archives to identify semantic elements in the archives, where semantic elements include entities, relationships, and events; Set identification rules, automatically identify files according to the preset identification rules, and assign identification tasks; Set up process models and receive real-time operations, automatically update the status of files at corresponding process nodes and display them; Generate detailed appraisal reports and relevant statistical information based on the appraisal results, and store all data from the entire archive processing process; The semantic analysis of the archive to identify semantic elements in the archive includes: Build a dictionary containing various entity types and process the archives; Match the words in the archive text with the dictionary and match the words with entities of the corresponding type; Determine the location and grammatical structure of the entity according to the grammatical rules of the language; Extract features for entity recognition from the text, and predict entities and types for newly input archive text based on the trained entity recognition model; Use dependency parsing tools to build a syntactic tree that shows the dependency relationships between words in a sentence; Formulate rules to extract the relationships between entities based on the dependency types and paths in the syntax tree; Train a relation recognition model on text annotated with semantic roles; According to the results of semantic role labeling, establish semantic role-based relationships between entities; Pre-build a knowledge graph and use the relationships in the knowledge graph to infer the relationships between entities in the text; Determine the keywords used to trigger events, build event templates based on different types of events, and identify complete event information; Convert words in the text into vector representations, use a set network model to model the context of the text, analyze the text's chapter structure, and complete event recognition.

2. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: The preliminary metadata extraction and storage of the input archives includes: Enter files, including paper files and electronic document files; Convert the entered files into a unified format; The entered archives are initially metadata extracted and stored in the database, where the metadata includes the archive type, creation time and source.

3. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: The process of extracting features for entity recognition from text and predicting entities and types of newly input archive text based on the trained entity recognition model includes: Extracting features for entity recognition from text, wherein the features include: features of the word itself, context features of the word, and part-of-speech features; Using the labeled entity training data, a supervised learning model is used to train the entity recognition model. The trained entity recognition model is used to predict the entity and type of the newly input archive text. The training of the relationship recognition model on the text labeled with semantic roles includes: The relationship recognition model is trained on texts labeled with semantic roles, so that the relationship recognition model learns to identify the semantic role played by each component in the sentence; The pre-built knowledge graph uses the relationships in the knowledge graph to infer the relationships between entities in the text, including: Pre-build a knowledge graph, where the knowledge graph contains various entities and the relationship types between entities; When processing archival text, the identified entities are matched with entities in the knowledge graph. Once the entities in the text are successfully matched with the entities in the knowledge graph, the relationships in the knowledge graph are used to infer the relationships between the entities in the text and to supplement the missing relationship information. The keywords used to trigger the event are determined, and event templates are constructed based on different types of events to identify complete event information, including: Determine the keywords used to trigger the event. If the keywords are detected in the archive text, it is preliminarily determined that an event exists. According to different types of events, event templates are constructed, and the content surrounding the trigger words in the text is matched with the event templates to identify complete event information; Using the theory of frame semantics, each event is mapped to a semantic frame with different slots. The semantic frame corresponding to the event is identified in the archival text and the information of each slot is filled. The process of converting words in a text into vector representations, modeling the context of the text using a set network model, analyzing the text's chapter structure, and completing event recognition includes: Use a pre-trained word vector model to convert words in the text into vector representations, where the word vectors include the semantic information of the words and represent the semantic relationship between words through vector operations; A set network model is used to model the context of the text to capture the order information and contextual dependencies of words in the sentence; Analyze the text's chapter structure and complete event recognition.

4. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: The setting of identification rules, automatically identifying files according to the preset identification rules, and assigning identification tasks include: Set up rules for assigning identification tasks; When evaluating a new file text, the relevant information of the file is automatically read, and according to the evaluation task assignment rules, qualified personnel are searched in the evaluation personnel database to assign the evaluation task; Collect competency data of appraisers and establish a competency model for each appraiser. The competency data includes the quality and efficiency of past appraisal tasks, professional skills, and experience level. When a new appraisal task is received, the characteristics of the task are matched with the ability model of the appraiser, a machine learning algorithm is used to calculate the matching score between the task and each appraiser, and the appraiser is selected based on the score.

5. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: The process model is set up, and real-time operations are received, and the status of the archive at the corresponding process node is automatically updated and displayed, including: Predefine the process model of archive appraisal, which includes the specific operations and requirements of each stage and sets different states for each process node; After receiving real-time operations on the file, the status of the file at the corresponding process node is automatically updated; The real-time status of the archive identification process is displayed through a graphical interface; Based on business experience and process requirements, abnormal situation rules are set, and various data in the archive identification process are monitored in real time. When situations that meet the abnormal rules are found, the early warning mechanism is automatically triggered.

6. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: After setting the process model, receiving real-time operations, and automatically updating and displaying the status of the archive at the corresponding process node, the process also includes: When receiving real-time operations on archives, automatically record the timestamp of the operations; Based on timestamp data, calculate the residence time of each file at each process node and the overall identification progress, and display the progress information through dashboards or reports; Among them, there is a relationship and dependency between multiple tasks in the archive identification process; When the status of a task changes, the progress and status of related dependent tasks are automatically updated based on the task association relationship.

7. The archive identification method based on semantic recognition of natural language processing technology according to claim 1 is characterized in that: The above mentioned system generates a detailed identification report and relevant statistical information based on the identification results, and stores all data of the entire archive processing process, including: Obtain basic data of archives; Determine the final conclusion based on the appraisal results and comprehensive judgment of each stage of the appraisal process, and write the conclusion into the report; Query the rules related to the file identification process from the identification rule library; If natural language processing technology is used for semantic analysis during the identification process, the results of the semantic analysis shall be included in the basis for identification; Propose corresponding treatment measures based on the appraisal conclusions; Query all the files that have been authenticated from the database, classify and count them by file type, and present the statistical results in the form of tables or charts; Search the database for files that have been appraised, classify and count them according to the appraisal conclusions, and display the statistical results in the form of a pie chart; Stores all data from the entire archive processing process, including original archive data, metadata, NLP semantic analysis results, identification rules, identification process records, and identification results.

8. A file identification device based on semantic recognition of natural language processing technology, characterized in that: include: The pre-entry module is used to extract and store preliminary metadata of the entered archives; A semantic analysis module is used to perform semantic analysis on archives and identify semantic elements in the archives, where semantic elements include entities, relations, and events; The identification processing module is used to set identification rules, automatically identify files according to the preset identification rules, and assign identification tasks; The process processing module is used to set the process model, receive real-time operations, automatically update the status of the file at the corresponding process node and display it; The result generation module is used to generate a detailed appraisal report and related statistical information based on the appraisal results, and store all data of the entire archive processing process; The semantic analysis of the archive to identify semantic elements in the archive includes: Build a dictionary containing various entity types and process the archives; Match the words in the archive text with the dictionary and match the words with entities of the corresponding type; Determine the location and grammatical structure of the entity according to the grammatical rules of the language; Extract features for entity recognition from the text, and predict entities and types for newly input archive text based on the trained entity recognition model; Use dependency parsing tools to build a syntactic tree that shows the dependency relationships between words in a sentence; Formulate rules to extract the relationships between entities based on the dependency types and paths in the syntax tree; Train a relation recognition model on text annotated with semantic roles; According to the results of semantic role labeling, establish semantic role-based relationships between entities; Pre-build a knowledge graph and use the relationships in the knowledge graph to infer the relationships between entities in the text; Determine the keywords used to trigger events, build event templates based on different types of events, and identify complete event information; Convert words in the text into vector representations, use a set network model to model the context of the text, analyze the text's chapter structure, and complete event recognition.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method for archival identification based on semantic recognition of natural language processing technology as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a server, implements the archive identification method based on semantic recognition of natural language processing technology as described in any one of claims 1 to 7.

Images