57 results about "Implicit knowledge" patented technology

The invention relates to the technical field of intelligent manufacturing, in particular to a milling process intelligent decision-making method based on multi-agent collaboration, which comprises the following steps of: constructing a milling process planning-oriented multi-modal knowledge base, receiving and analyzing a milling processing demand input by a user based on a central large language model agent, and establishing a multi-modal knowledge base; decomposing a process planning task into associated sub-tasks based on knowledge in the multi-modal knowledge base, and distributing the associated sub-tasks to corresponding professional agents; and obtaining related knowledge based on a retrieval enhancement generation technology, and executing the subtask. Through the LLM-driven multi-agent collaborative system and the RAG technology, autonomous dynamic optimization of the process scheme is realized to improve the intelligence level, a distributed architecture is adopted to enhance the flexibility to adapt to frequent changes, a multi-modal knowledge base is constructed to capture and reuse expert implicit knowledge to ensure the consistency of the scheme, and the method has the advantages of being high in practicability and high in practicability. And multi-dimensional knowledge is integrated and deeply applied to cope with complex process requirements, so that the defects in the prior art are effectively overcome.

The invention discloses a field large model geological survey report generation method based on a knowledge graph, and the method comprises the following steps: S1, building an engineering survey field data set through multi-source heterogeneous data collection and structured preprocessing, and the engineering survey field data set comprises five text dimension tags divided according to engineering survey specifications; s2, constructing an engineering investigation knowledge graph; and S2A, knowledge extraction, wherein a bidirectional encoder presentation layer-bidirectional long short-term memory network-conditional random field joint extraction model is adopted. According to the method, a bidirectional encoder presentation layer-bidirectional long short-term memory network-conditional random field joint extraction model is improved on knowledge modeling to perform high-precision entity-relation joint extraction, a geological knowledge map with consistent semantics and clear structure is constructed based on RDF, rule reasoning and graph neural network reasoning mechanisms are fused, and the method has the advantages of high-precision entity-relation joint extraction and high-precision entity-relation joint extraction. Deep mining and complementation of explicit and implicit knowledge are realized, and the ability of the prior art in knowledge expression granularity and reasoning breadth is improved.

The invention provides a transformer area line loss intelligent algorithm decision-making method based on a knowledge graph and a large model agent, semantic retrieval in the algorithm calling process is supported, dominant and implicit knowledge such as expert experience, technical standards and historical cases is coded in a unified mode, a mapping relation is established between algorithm nodes and process nodes in the knowledge graph, and the algorithm is optimized. An integrated reasoning path is formed, so that the intelligent agent can automatically combine and call an algorithm according to a task target, a large model is embedded into a transformer area line loss analysis process, and a hierarchical structure of'task analysis intelligent agent-algorithm decision intelligent agent-result analysis intelligent agent 'is formed; the task analysis agent is responsible for converting a problem input by a user into a structured task; the algorithm decision agent is responsible for algorithm selection and adaptive parameter adjustment; the result analysis agent is responsible for report generation and decision recommendation based on the knowledge base; according to the method, organized association can be carried out on scattered algorithm tools, expert experience and business rules, and a unified transformer area line loss agent tool integration framework is constructed.

The invention discloses an agent interaction method and system for enhancing specific industry knowledge, and belongs to the technical field of artificial intelligence. According to the method, multi-modal original data of a target industry is collected and preprocessed, dominant entities and relationships are extracted based on an industry ontology to generate a triple, and implicit knowledge is fused to construct an iterative mixed knowledge graph; converting a user query into a vector, retrieving a Top-K candidate knowledge vector, and then performing interpretable scoring in combination with a query vector, a candidate vector and a triple to obtain an enhanced feature; and dynamically determining an expert sub-network set, and fusing reasoning results of the experts to generate a final answer. The system comprises a knowledge graph and a feature enhancement and reasoning module, and dynamic updating and accurate reasoning of knowledge are achieved. According to the method, the industry knowledge coverage degree, the reasoning accuracy and the interpretability are improved, the illusion problem of a large language model is relieved, and the method is suitable for intelligent interaction services in the professional fields of medical treatment, finance and the like.

The invention relates to the technical field of intelligent water conservancy, and discloses and provides a hydraulic structure large language model fine tuning and graph retrieval enhanced generation method based on knowledge distillation, and the method specifically comprises the steps: obtaining a hydraulic structure instruction fine tuning data set in combination with a knowledge distillation method; performing supervised training on the large language model by using a low-rank decomposition technology to obtain a hydraulic structure large language model; identifying a question intention of a user by using a hydraulic structure large language model, and converting a question statement into a knowledge graph query language; and enhancing the professional and credibility of water conservancy generated by the answer of the large model of the hydraulic structure by using a knowledge graph retrieval result. According to the method, the hydraulic structure knowledge is embedded into the large language model, the large language model customized for the hydraulic structure field is obtained, and the explicit knowledge stored in the water conservancy knowledge graph and the implicit knowledge of the large language model are effectively combined, so that the answer is more accurate and traceable, and an effective technical means is provided for intelligent water conservancy construction.

The invention belongs to the technical field of computer aided process design (CAPP), and particularly relates to a body-based shaft part fixture scheme automatic generation method. The method specifically comprises the following steps: (1) constructing a shaft part clamp scheme generation body; (2) establishing a shaft part clamp scheme to generate an SWRL inference rule; (3) extracting relevant feature constraint information of the part; (4) constructing and generating an instantiated ontology model; and (5) combining a Drools inference engine with an SWRL rule, and carrying out inference selection and adjustment on a shaft part fixture scheme. Constructing an ontology reasoning knowledge framework by utilizing ontology pair shaft part clamp scheme domain knowledge, and reasoning implicit knowledge according to dominant domain knowledge; and reasoning an optimal clamp scheme according to the feature constraint condition of the geometric product in combination with a semantic network rule language rule base. According to the method, a consistent knowledge description framework generated by the shaft part clamp scheme can be provided, so that a computer can automatically select a proper clamp scheme and the like according to various constraints of geometric product parts, and a quick and effective method is provided for intelligent selection of the shaft part clamp scheme.

The invention relates to the technical field of machine learning, in particular to a knowledge distillation method and system based on view alignment. The invention aims to solve the main limitations in the traditional distillation technology, including the problems of excessive confidence of a teacher model, confirmation deviation and the like. The invention provides a novel knowledge distillation framework based on logarithmic probability, which is called KDVA; specifically, z-score standardization is applied to the logarithmic probability of a model for smooth output, so that transmission of more teacher implicit knowledge is promoted. In addition, a same-view-angle and cross-view-angle alignment mechanism is introduced into the KDVA, and comparison information of weak and strong image transformation is utilized to enlighten a student model to obtain more knowledge. In addition, the student model is supervised by using the real label of the sample, so that the student model can obtain more information about each sample target category. According to the method, when different network architectures are applied to different data sets, high effectiveness and stability are shown.

The invention discloses a knowledge base construction method and system based on urban planning implicit knowledge deduction, relates to the technical field of urban planning, and aims to solve the problems that an existing planning knowledge base is insufficient in implicit knowledge mining, poor in scene adaptability and lack of dynamic optimization capability. The method comprises the steps of obtaining multi-source data and performing standardization processing to obtain an enhanced data pool; optimizing the large language model to extract explicit and implicit planning knowledge; constructing a planning knowledge association network with association strength; building an initial knowledge base containing classification, retrieval and implicit knowledge deduction units; generating an adaptability evaluation result through a multi-scene test; constructing a knowledge evolution rule based on an evaluation result and completing knowledge base iterative reconstruction; and establishing a real-time spatial data dynamic triggering mechanism to realize continuous optimization of the knowledge base. According to the method, accurate association and deduction of explicit and implicit knowledge are realized, the scene adaptability and dynamic updating capability of the knowledge base are improved, scientific and efficient knowledge support is provided for urban planning decision making, and the method is suitable for various planning scenes.

The invention relates to the technical field of artificial intelligence, provides a decision generation method, device and equipment based on knowledge distillation and a medium, is applied to financial and medical health care service scenes, can extract multi-modal features in target input data, and realizes extraction and preliminary integration of multi-modal effective features. Knowledge distillation is carried out on the multi-modal initial features, more implicit knowledge is learned for the multi-modal initial features, and the quality and expression ability of the features are improved; the hierarchical knowledge graph is constructed according to the multi-modal knowledge enhancement features, so that the multi-modal knowledge can be subjected to structured representation from different hierarchies, and a clear and organized knowledge basis is provided for subsequent reasoning and decision making; the hierarchical reasoning decision is carried out according to the multi-modal knowledge enhancement features and the hierarchical knowledge graph, analysis and decision making can be carried out on multi-modal information from different granularities, the processing capacity and decision making accuracy of complex tasks are improved, and effective reasoning from local features to global decision making is achieved.

The invention provides a circuit design optimization method based on knowledge rule induction and implicit knowledge mining. The method comprises the following steps: 1) classifying and sorting design rules; 2) extraction and modeling of dominant design rules; 3) mining and structured expression of the implicit design rule; 4) constructing and optimizing a knowledge document; 5) establishing and applying a design rule base; and 6) reasoning and verifying the key links in the electrical design process. According to the method, explicit knowledge such as electrical design specifications and periodical papers is systematically summarized, and implicit knowledge such as design experience and skills is extracted in combination with a data mining and knowledge reasoning technology, so that systematic management of key knowledge information in the electrical design process is realized, the intelligent level of an electrical design software platform can be effectively improved, and the design efficiency is improved. The knowledge sharing and multiplexing capability in the design process is enhanced, so that the cable wiring scheme is optimized, and the reliability of the design result in the aspects of safety, economy, scheme consistency and the like is improved.

The application discloses a kind of self-adapting intelligent teaching content recommendation system, it is related to intelligent teaching technical field, including data acquisition analysis module: collection student in the learning process multiple types of data, including student's learning behavior data, physiological signal, environmental data and learning achievement cognitive feedback data, after acquisition, multiple types of data are preprocessed with noise reduction, standardization and analysis feature extraction, generate multimodal data;The application is analyzed by constructing knowledge point, error type, three-dimensional knowledge graph of thinking path and time sequence convolution network TCN, not only can identify dominant knowledge defects, but also can diagnose implicit knowledge leaks, so that students can accurately know their own knowledge system leaks, targeted to check and fill the gap and strengthen training;By extracting learning interest information from multimodal data, an explicit and implicit multidimensional interest model is established, and the teaching content is filtered in combination with the knowledge gap diagnosis result.

The invention discloses a ship lockage rolling pre-planning automation system, and belongs to the technical field of intelligent transportation and waterway transportation. According to the system, firstly, a digital twin navigation environment synchronized with a physical world in real time is constructed; in the environment, an initial scheduling strategy is generated through forward reinforcement learning training, the system allows a scheduling expert to intervene a pre-plan generated by the initial strategy, and operation of the pre-plan is collected to form an expert demonstration track; and then, analyzing the track based on reverse reinforcement learning, reversely reasoning the implicit decision preference of the expert and quantifying the implicit decision preference into an expert reward function, and finally, fusing the expert reward function with the initial reward function. The ship lockage scheduling method solves the technical problems that an existing scheduling system depends on a solidified rule, cannot learn expert implicit knowledge and is poor in adaptability, and the intelligent level, efficiency and safety of ship lockage scheduling in a complex dynamic environment are remarkably improved by constructing a closed-loop learning framework of man-machine co-evolution.

This invention relates to artificial intelligence and big data processing technologies, aiming to provide a method for constructing multimodal intelligent knowledge cards and self-organizing links by topic. The method includes: collecting data from multiple sources, preprocessing it to extract multimodal information, and constructing several standard structured data objects as knowledge cards; encapsulating the data in a unified format to build a knowledge card database; constructing multidimensional hybrid embedding vectors based on the attributes of the data in the knowledge card database using different knowledge cards; establishing a multimodal semantic adaptive topology network under spatiotemporal constraints to achieve self-organizing links by topic; storing the knowledge cards as nodes in a backend knowledge graph and establishing connections with the frontend display / interactive interface. This invention can be used for intelligent processing of data extraction, structured encapsulation, and dynamic association. Through vector space alignment, it can discover implicit knowledge and potential connections, achieving dynamic evolution and adaptability.

The invention discloses a pre-training language model post-interpretation method and system based on framework knowledge detection, and particularly belongs to the field of artificial intelligence and natural language processing. Comprising a framework-based semantic analysis module, a framework-based knowledge graph construction module and an interpretable knowledge detection module. The method is a post-interpretation mechanism based on a framework semantic linguistics cognitive mechanism, and the core of the method is to evaluate and interpret internal parameter concepts of a pre-training language model which cannot be understood by human beings by using framework cognitive concepts which can be understood by the human beings. By introducing a framework, framework elements and framework relationship concepts, a framework knowledge graph capable of representing implicit knowledge behind a text is realized based on a given text. And then a knowledge detection module is combined to generate multiple types of detection problems, and understanding and reasoning of the model on text back implicit knowledge are evaluated. According to the method, the limitation of the model in the aspects of knowledge representation and reasoning can be effectively identified, and support is provided for model optimization and research of a credible artificial intelligence model.

The invention relates to a multi-agent video multi-round question and answer method based on implicit knowledge enhancement, and the method comprises the steps: merging the video features of a real agent and the features of a virtual agent, and generating an extended agent feature set; constructing a multi-agent video question and answer model; training a multi-agent video question and answer model based on the extended agent feature set to obtain a trained multi-agent video question and answer model; and inputting the video features of the plurality of real agents and the to-be-processed question text features into the trained multi-agent video question and answer model to obtain a final video question and answer result. According to the method and the device, support features of historical rounds are expressed as virtual agent features, and unified modeling is carried out on the virtual agent features and real agent features of the current round, so that efficient multiplexing of context information in multi-round questions and answers is realized. The method has remarkable advantages in question and answer accuracy, calculation efficiency and communication overhead, and a new solution is provided for multi-round multi-modal question and answer tasks.

The present application relates to the technical field of multi-modal dialogue, and especially relates to a knowledge extraction and mining method for a smart home multi-modal dialogue system, which comprises the following steps: S1. smart home multi-modal dialogue system input data acquisition; S2. multi-modal explicit knowledge graph construction; S3. multi-modal explicit knowledge representation learning; S4. multi-modal explicit knowledge reasoning and relationship completion; and S5. multi-modal implicit knowledge mining and representation learning. The present application extracts and aligns knowledge from massive unstructured texts, pictures and videos, constructs a multi-modal knowledge graph, performs representation learning on the graph based on semantic meta paths, extracts rich subgraph information through graph convolution operation to complete knowledge reasoning, and further completes the missing relationships. In addition, based on a large-scale pre-training model, a pre-training task for mining implicit knowledge is designed to guide the model to learn implicit knowledge such as emotion, which can improve the logical reasoning ability of the dialogue system.

The application provides a threat intelligence analysis method and system based on a knowledge graph. Since the embedding layer processing of entity extraction is improved on the basis of existing threat intelligence analysis, the entity category and boundary can be accurately labeled, and the hidden state is obtained by improving the LSTM layer. Then, the mapping relationship of the related entity is predicted by introducing the label transition probability algorithm, so that the deficiency that the existing knowledge graph cannot obtain implicit knowledge when performing semantic retrieval is overcome, and semantic retrieval and reasoning analysis based on the knowledge graph are realized.

The application relates to a disease prediction method and device based on implicit knowledge enhancement, equipment and a medium. The method comprises the following steps: calculating a patient comprehensive representation according to historical medical records and static information representation, and training a backbone network by using the patient comprehensive representation; obtaining a patient representation matrix by using the backbone network, and screening K similar patient representations with the highest similarity to a target patient by using cosine similarity; constructing a medical time sequence heterogeneous graph according to a disease type and a relationship type, encoding the medical time sequence heterogeneous graph by using a heterogeneous graph encoding algorithm to obtain a medical time sequence heterogeneous graph representation; constructing a disease comprehensive representation by using the patient comprehensive representation, the similar patient representation and the medical time sequence heterogeneous graph representation, training a disease prediction model according to the disease comprehensive representation, and outputting a disease prediction result by using the trained disease prediction model. The application enhances patient modeling by using the collective wisdom of similar patients and the potential complex relationship between diseases, and improves the accuracy of disease prediction.

The invention discloses an air and space big data intelligent data management system and method based on four-database collaboration and knowledge generation. A core layer adopts a temporary storage database, a controlled database, a product database and a knowledge database to form a four-database architecture; and the service layer adopts a data governance engine, a productization engine, a knowledge generation engine and an intelligent enabling engine. The system combines a data governance engine and a productization engine to carry out collaborative linkage to carry out data governance. Depositing knowledge assets into a knowledge base by relying on a knowledge generation engine; performing intelligent enabling application of each link of the data governance process by means of an intelligent enabling engine; and an intelligent enabling application effect is fed back, and knowledge assets in the knowledge base are optimized. According to the intelligent closed-loop data governance system, data governance implicit knowledge is converted into dominant knowledge and reused, the self-adaptability and the intelligent level of the data governance process are improved through knowledge reverse enabling, and then an intelligent closed-loop data governance system capable of self-learning, self-optimizing and continuously adapting to service requirements is formed.

The invention relates to the field of computer technology and artificial intelligence technology, and discloses an authorized purchase-oriented risk management and control system and method, and the system comprises a knowledge base construction module which is used for collecting multi-source heterogeneous data related to authorized purchase, and constructing a knowledge base; the intelligent template module is configured to generate a service quantity list and a technical parameter template based on the knowledge base, and perform real-time semantic risk identification and early warning when a user inputs a purchase demand text; and the risk assessment and price limit module is configured to receive a to-be-approved authorized purchase demand, analyze the authorized purchase demand based on the knowledge base and the semantic risk identification result, and output a comprehensive risk index and a dynamic maximum price limit. Various scattered and heterogeneous data generated in a purchase whole chain are processed and precipitated into a structured dynamic knowledge base, and implicit knowledge originally stored in personal experience or scattered documents is converted into enterprise-level, computable and inheritable dominant knowledge assets.

The invention discloses a gray measurement expert knowledge generalization model construction method, which comprises the following steps of: constructing a dual-task deep learning model sharing an encoder by synchronously acquiring quantitative scores and visual focus data of experts, so that the dual-task deep learning model learns and predicts expert scores and regions of interest at the same time; the method comprises the following steps of: establishing a deep model, migrating implicit knowledge of the deep model to an interpretable shallow model by utilizing knowledge distillation, extracting dominant and readable discrimination rules, and finally establishing a man-machine collaborative closed loop: submitting highly uncertain samples of the rules and the model to an expert for auditing and correcting, and utilizing feedback iteration to finely adjust the model to realize continuous optimization of performance and interpretability. According to the method, recessive and intuitive knowledge and dominant knowledge of experts are effectively fused, the generalization performance, robustness and interpretability of the model are remarkably improved, and a solid technical support is provided for high-precision and high-reliability automatic gray scale measurement and calculation.

The present application belongs to the technical field of education data mining, and discloses a test question implicit knowledge attribute association mining method and system based on attribute exploration and a related test question pushing method and system, which comprises the following steps: constructing a formal background of a student's error question set; preprocessing a student's question answer record source data, and then filtering out the student's error answer information in combination with a knowledge attribute set contained in the labeled question; exploring the current formal background by using an attribute exploration knowledge attribute mining algorithm to obtain a knowledge attribute implication association set and a non-redundant test question set through any student error answer information; calculating the similarity between test questions by using concept lattice similarity analysis, finding questions containing similar knowledge points to the practice wrong questions, and selecting a number of related test questions meeting a threshold to push. The present application solves the drawbacks caused by the missing attributes in the students' fuzzy judgment in the traditional analysis mode, and can provide targeted test question recommendations for students.

This invention relates to the field of intelligent customer service, specifically disclosing a method and system for constructing a customer service knowledge base based on a knowledge graph. The method includes: identifying implicit needs by analyzing the spatiotemporal correlation between user actions and customer service dialogues, generating enhanced knowledge units that integrate explicit and implicit knowledge; constructing a knowledge graph, achieving adaptive optimization of the knowledge graph through real-time monitoring of relationship strength changes, forming a dynamic knowledge graph; capturing the user's current contextual information, matching it with the dynamic knowledge graph to generate contextualized knowledge subgraphs, and using multi-path reasoning to generate personalized response content; the system includes modules for implementing the above steps. This invention effectively solves the shortcomings of traditional customer service knowledge bases in implicit knowledge mining, dynamic updating, and deep contextual awareness, achieving improvements in knowledge acquisition from partial to comprehensive, knowledge base from static to dynamic, and responses from general to personalized, significantly enhancing the cognitive depth and service quality of intelligent customer service systems.

The invention relates to an image-text test question knowledge point labeling method and system based on a quaternion hypergraph, belongs to the technical field of intelligent education, and aims to solve the problem of low knowledge point labeling accuracy caused by neglect of implicit knowledge features and insufficient multi-stage interaction between modals in the prior art. According to the technical scheme, the method comprises the steps of obtaining explicit and implicit four-dimensional features of two modes of text and vision of an image-text test question; a cross-modal interaction analysis module is constructed, a text hypergraph and a visual hypergraph are constructed based on explicit and implicit feature similarity, and then a unified quaternion hypergraph fusion multi-modal feature is constructed; a modal independence loss function is introduced to keep mutual independence of each modal; proposing a knowledge consistency loss function to optimize cross-modal knowledge consistency; and updating features and optimizing network parameters through a modal complementation module to complete knowledge point labeling. According to the method, high-order association of explicit and implicit features can be effectively mined, and cross-modal semantic alignment precision and knowledge point labeling accuracy are improved.

The present disclosure relates to a training method of a recommendation model, a pushing method and device of a resource object, and an electronic device, including: obtaining a first resource recommendation model to be trained, and taking the first resource recommendation model as a student network to be trained; then obtaining a second resource recommendation model pre-trained, and taking the second resource recommendation model as a teacher network; then training the student network to be trained based on the teacher network, so as to migrate at least part of the implicit knowledge of the teacher network to the student network in the training process, and after the student network is trained, determining the first resource recommendation model corresponding to the student network as a coarse ranking model of a resource recommendation platform, and determining the second resource recommendation model corresponding to the teacher network as a fine ranking model of the resource recommendation platform. The above scheme can ensure the consistency between the estimated feedback data output by the coarse ranking model and the fine ranking model, and further improve the accuracy of the target resource object pushed to the user account.

The application provides a self-adaptive procedure generation method based on case-based reasoning and transfer learning, and the application constructs an excellent case knowledge base, structures and makes implicit knowledge, i.e., successful experience of experts verified in history, explicit, and innovatively combines the case-based reasoning and the transfer learning thought, so that the system can not only find the most similar historical case, but also intelligently and self-adaptively correct the scheme in a "transfer" mode according to the difference between the new task and the historical case, thereby automatically generating the engineering procedure which is highly customized, close to the actual situation and has the "design thought" annotation. The application solves the technical problems of low efficiency and poor consistency of the traditional method, and the technical problems of rigidity and lack of learning evolution ability of the existing software system.

The application relates to the technical field of dialogue processing, and discloses a dialogue method, system, device and medium with enhanced knowledge base retrieval, wherein the method comprises the following steps: in response to a dialogue context input by a user, performing attribute selection and entity selection on entities in an external knowledge base to obtain a target entity set; configuring corresponding implicit knowledge labels for entities in the target entity set to obtain an implicit knowledge enhanced entity set; wherein the implicit knowledge labels represent labels for distinguishing similar entities in the target entity set; configuring corresponding display knowledge texts for entities in the implicit knowledge enhanced entity set to obtain an explicit knowledge enhanced entity set; wherein the display knowledge texts represent descriptive texts of the entities in the implicit knowledge enhanced entity set; and generating a target response based on the explicit knowledge enhanced entity set and the dialogue context. The technical scheme provided by the application can improve the quality and accuracy of generated replies.

The invention provides a traffic logistics-oriented large model knowledge base construction method and system, and the method comprises the steps: carrying out the semantic relation mining based on a standard term set in the traffic logistics field, generating a structured term graph, constructing a template knowledge probe set, inputting a pre-training large language model, and carrying out the directional activation detection operation, thereby obtaining an implicit knowledge neuron cluster, the method comprises the following steps of: carrying out space-time correlation analysis on an activation response mode of the neural network, extracting distribution characteristics of neuron activation intensity and a dependency relationship among the characteristics, mapping an implicit knowledge neuron cluster into a semantic traffic logistics field knowledge unit, carrying out hierarchical organization and semantic linking according to a logic correlation degree and a functional attribute classification result, and carrying out hierarchical classification on the neural network. Generating a traffic logistics field structured knowledge network; and calling a standard traffic logistics business problem set to perform knowledge utility verification, and dynamically optimizing and adjusting knowledge units and association relationships to obtain a large model knowledge base, thereby providing high-quality knowledge support for intelligent application in the field of traffic logistics.

The invention provides a document analysis method in the building field, and relates to the technical field of document intelligent processing, and the method comprises the following steps: document preprocessing and media persistence: carrying out format unification and automatic numbering static processing on an original document, uploading an extracted multi-modal resource to an object storage to generate a URL (Uniform Resource Locator), and backfilling; structural analysis is carried out, a DOM tree is constructed, a chapter nesting relation is precisely restored through a stack algorithm, and non-title content merging and full-path serial number generation are achieved; performing knowledge representation and storage, performing dissimilatory abstract extraction on chapters by utilizing a large language model, calling an embedded model to generate semantic vectors, and constructing a mixed retrieval index containing text and vector fields; and retrieval and application: executing mixed retrieval based on keyword and semantic similarity, and recalling a high-quality chapter template. According to the method, standardized precipitation and intelligent reuse of hidden knowledge in the building field are realized, and the scheme compiling efficiency is remarkably improved.

The invention discloses a learning plan updating method and device based on an AI agent, and relates to the technical field of education, and the method comprises the steps: responding to the obtained learning behavior data of a student for question learning based on a learning plan in a learning accompanying system, and determining the question information and note information of a student for learning a target question based on the learning behavior data; determining an implicit knowledge point set in knowledge point sets corresponding to the question information and the note information based on a first knowledge point set marked for the target question; determining a target implicit knowledge point set corresponding to the learning plan from the implicit knowledge point set according to a first repair relationship and correlation information in the implicit knowledge point set and in the first knowledge point set; and updating the target implicit knowledge point set in a knowledge point learning grid corresponding to the learning plan to update the learning plan into a target learning plan including the target implicit knowledge point set. According to the invention, the learning efficiency and the systematicness of knowledge construction can be improved.