1612 results about "Domain knowledge" patented technology

The invention provides an intelligent data labeling method and system based on multi-modal fusion and large model verification, belongs to the field of artificial intelligence and data processing, and innovatively fuses multi-modal information such as an OCR recognition result, a layout structure, original image visual features and deep semantic analysis of a large language model (LLM). And a precise automatic labeling result credibility evaluation mechanism is constructed. According to the method, various errors in automatic labeling can be accurately recognized and adaptively corrected, and the errors comprise conventional error correction based on hard coding rules and complex semantic error correction driven by LLM. Meanwhile, the system can continuously optimize the data labeling capability of the system through an efficient man-machine cooperation and closed-loop feedback learning mechanism, and automatically precipitate domain knowledge assets. The invention aims to solve the problems of recognition accuracy bottleneck, heavy manual proofreading burden, lack of intelligent judgment and error correction, knowledge accumulation lag and the like in traditional document data labeling, so that the efficiency, accuracy and automation level of document data labeling are remarkably improved.

The invention discloses a method for converting a natural language into a low code based on multi-modal reinforcement learning, which comprises the following steps of: performing word segmentation, embedding and multi-layer feature extraction on a natural language instruction input by a user, combining a self-attention mechanism and a graph attention mechanism, extracting and optimizing an original semantic feature vector, and automatically identifying a business field; semantic relationship triples in the domain knowledge graph are fused, and a multi-modal semantic alignment and context enhancement strategy is adopted, so that the accuracy and stability of semantic representation are remarkably improved; when semantic drift or ambiguity is detected, a multi-candidate correction mechanism is triggered to obtain a better analysis result, and the robustness of semantic understanding is enhanced; and finally, mapping an analysis result into an instruction which can be identified by a low-code platform, automatically generating a code structure, continuously optimizing a semantic model and a knowledge graph based on user feedback, realizing adaptive learning, and improving the conversion efficiency and quality from a natural language to codes.

The invention relates to an unmanned aerial vehicle fault traceability analysis method and device, equipment and a storage medium. The method comprises the steps of defining entity types and relationship types among entities based on a predefined fault ontology model to construct a mode layer of an unmanned aerial vehicle fault knowledge graph; based on the mode layer, extracting a fault triple from the multi-source operation data of the unmanned aerial vehicle by using a mixed extraction model, and constructing a fault knowledge graph containing instance data; endowing a dynamic weight probability representing confidence to a relation edge in the fault knowledge graph, and generating a probabilistic fault knowledge graph; and mapping to-be-analyzed fault information to the probabilistic fault knowledge graph, performing traceability analysis by using a hybrid inference engine, and outputting a fault reason and a transmission path. According to the method, structured deep fusion of domain knowledge and data value is realized, and the traceability conclusion is improved from qualitative judgment to quantitative decision support with confidence measurement.

The invention provides a multi-modal information fusion feeding decision-making system and method for chicken breeding behavior recognition, and the method comprises the steps: collecting a multi-source heterogeneous data set, and extracting a primary fusion feature vector; constructing a triple knowledge graph; mining implicit association rules of the ingestion frequency and the body temperature; performing secondary fusion on the primary fusion feature vector and an implicit association rule to generate an intermediate decision feature; and generating a feeding decision instruction through the pre-training decision model and the expert rule base. According to the method, the knowledge graph is constructed, GNN reasoning is utilized, and a manual preset rule static mode is replaced; performing secondary feature fusion, generating intermediate decision features by combining primary fusion features and implicit rules, and then combining a pre-training model and an expert rule base, ensuring decision real-time performance, integrating domain knowledge, outputting accurate adjustment parameters, realizing full-link intelligence, improving the accuracy and adaptability of breeding chicken feeding decisions, and improving the accuracy and adaptability of chicken feeding decisions. Therefore, dynamic requirements of complex breeding scenes are met, and chicken flock health and breeding efficiency improvement are promoted.

The invention provides a highway intelligent operation and maintenance question-answering system based on a large language model, and belongs to the technical field of natural language processing. The system takes a large language model as a core reasoning engine and combines a domain knowledge base and an RAG technology to realize accurate question and answer of highway operation and maintenance; the method comprises the following steps: based on original knowledge data cutting, generating a title through a large language model, and customizing a knowledge base; receiving query, analyzing an intention by using a large language model, and matching to generate a function; the query is rewritten by using a large language model, dense and sparse vector query is generated, and a double-layer retrieval mechanism is formed; a two-step recall mode is utilized, coarse-grained recall is firstly carried out, then a recall result is subjected to fine-grained optimization through a screening mechanism, and a reasoning text is generated; and finally, inputting the query and reasoning text into the large language model, and generating an optimal answer through single-round and multi-round questions and answers. According to the method, the professionality and reliability of answers are enhanced, and the technical problem that answers are incomplete and inaccurate in an existing question and answer system is solved.

A system and method for extending mobile-optimized multi-stage language model processing with federated persistent cognitive architecture. The system processes prompts through a first large language model to generate “thoughts,” which are cached and processed with the original prompt through a smaller language model. Building upon the three-tier thought caching, the system implements a federated multi-tier hierarchy with local device, domain-specific branch, and global collective caches. A federated cognitive orchestrator coordinates operations across multiple domain-specialized instances, managing thought routing, state synchronization, and cross-domain knowledge sharing while maintaining domain boundaries. During user inactivity, autonomous reasoning continues in cloud environments, generating insights from existing thoughts and interaction history. The system performs memory consolidation, thought cache optimization, and cross-domain pattern recognition without consuming mobile device resources, while maintaining privacy boundaries. This persistent cognitive architecture functions as an evolving reasoning partner rather than merely a responsive tool.

The invention relates to the technical field of artificial intelligence application, and discloses an information technology auxiliary consultation system based on artificial intelligence. The system comprises a data acquisition module, a knowledge graph construction module, an intention analysis module, a decision engine module, a strategy optimization module and a feedback correction module. The data acquisition module acquires multi-dimensional data such as a semantic type, an intention label and a historical interaction record of a user consultation request in real time; the knowledge graph construction module dynamically generates a hierarchically associated domain knowledge graph according to the domain database; and the intention analysis module completes user intention classification and analysis through a multi-level attention mechanism. The decision engine module combines the analysis result and the knowledge graph to generate candidate strategies, and the strategy optimization module screens out target strategies meeting real-time response requirements through an adaptive weighting algorithm. The feedback correction module utilizes user interaction data to update system parameters, improves service precision, and is suitable for various information technology consultation scenes.

The invention relates to a test case generation method and system based on multi-agent efficient collaboration, belongs to the technical field of software testing, and solves the problems of incomplete scene coverage, logic disorder and the like when a single large model processes a complex task. The method comprises the following steps: constructing a multi-modal professional field knowledge base; the task planning agent module generates a test case generation task based on a project development document and a software source code file of a to-be-tested project and distributes the test case generation task to the test demand analysis agent module; based on the test case generation task, extracting a test demand point related to the tested software configuration item, describing the test demand point, and labeling a corresponding tracking relationship between a test demand point ID and a code snippet or a function in the software source code file to construct a test demand-code snippet / function set; and generating a test case and a test description document based on the test demand-code snippet / function set and the multi-modal professional domain knowledge base. And the ability of generating the test case of the large model is enhanced through organic and efficient cooperation of multiple agents.

The invention discloses a method based on a large language model and ATTamp; the invention discloses a CK framework penetration test automation method and device, and the method comprises the steps: firstly carrying out the structural analysis of multi-source input information and tool output, and guaranteeing that key fields are not discarded; then combining a retrieval enhancement generation technology and a network security knowledge base to provide domain knowledge support for the large language model, so as to generate a model with ATTamp; a penetration test task tree marked by CK tactics, technologies and sub-technologies; on the basis, an optimal tool is automatically selected through a tool resource library and a multi-dimensional screening mechanism, an execution instruction is generated, and finally an execution result is returned to the input analysis module to form a self-adaptive optimization test closed loop. According to the method, semantic fidelity compression and standardization processing of long information can be realized aiming at the problems of large output format difference, more information redundancy and the like of different penetration testing tools, and efficient, explainable and auditory technical support can be provided for automatic penetration testing in a complex network environment.

The invention discloses an intelligent question bank retrieval and recommendation system based on an artificial intelligence knowledge graph, and relates to the technical field of artificial intelligence education. Comprising a knowledge graph construction module which is used for processing original education data and constructing a neighborhood knowledge graph comprising a hard preposition relation and a soft incidence relation; the user knowledge state graph construction module is used for constructing a user personal knowledge state graph isomorphic to the domain knowledge graph, and dynamically calculating a mastery index of each knowledge node through a deep knowledge tracking model based on user historical answer data; according to the method, by constructing the domain knowledge graph containing the hard preposition relation and the soft incidence relation, discrete knowledge points are organized into the structured network conforming to the cognitive law, so that the system can understand and follow the internal logic between knowledge, and a learning path which is clear in organization, efficient and coherent is generated.

The invention relates to a man-machine interaction dialogue method, system and device based on a natural language and a medium. The method comprises the steps that firstly, multi-modal interaction data is acquired and preprocessed, and segmented words and syntax are analyzed through a natural language processing technology to construct intention feature vectors; combining the intention feature vector with a historical dialogue record, and using a pre-trained language model to generate context semantic elements containing a semantic relationship; if the context semantic elements are matched with the preset scene feature library information, predicting a user intention change trend by adopting a reinforcement learning model to obtain an intention prediction result; and finally, evaluating user intention change based on an intention prediction result, extracting associated domain knowledge by utilizing a knowledge graph if significant change occurs, and inputting the associated domain knowledge into a dialogue generation model to obtain a natural language reply sequence. According to the method, the understanding precision of the user intention is improved, the dynamic prediction of the intention change is realized, the relativity and coherence of reply are guaranteed, and a more efficient processing path is provided for natural language man-machine interaction.

The invention discloses a multi-modal data fusion and intelligent analysis platform and method for an unmanned aerial vehicle inspection system for a wind power plant. The platform comprises a multi-modal data acquisition module, a feature extraction and standardization module, a multi-modal information fusion module, a joint learning and optimization module, a domain knowledge injection module and an intelligent decision and application module. The system processes multi-source heterogeneous data through an integrated learning and deep learning fusion strategy, projects features to a shared semantic space by using joint training and comparative learning to enhance the anomaly discrimination ability, and performs verification and semantic enhancement on a supervised retrieval result in combination with a knowledge base in the wind power field. And finally, outputting a high-reliability diagnosis report and a maintenance suggestion. According to the invention, accurate identification and positioning of the fan fault are realized, and the inspection efficiency and the system decision reliability are significantly improved.

The invention discloses an AI (artificial intelligence) agent construction system based on hybrid retrieval and father-child segmentation, which comprises the following steps of: dividing a subclass knowledge base according to domain knowledge, performing father-child segmentation processing, and constructing a hierarchical semantic network; vectorization embedding and deep semantic reconstruction are carried out on the user question text; retrieving the reconstructed problem by adopting a mixed retrieval algorithm combining sparse retrieval and dense retrieval, and forming a high-score sub-segment set according to a comprehensive score obtained by dynamic weight distribution; mapping the sub-segments to the parent segment through a hierarchical backtracking algorithm, aggregating brother nodes to form an extended candidate set, and generating an associated sub-segment set after duplicate removal and re-retrieval; and finally inputting a large language model to generate a complete answer. According to the method, the problems of context segmentation, low retrieval accuracy and complicated knowledge base maintenance of traditional document segments are solved, the answer coverage and accuracy of an intelligent question-answering system are remarkably improved, and the method is suitable for knowledge question-answering scenes in the complicated technical fields such as intelligent network connection automobiles and the like.

The computer fault diagnosis method based on the causal reasoning and mapping knowledge domain hybrid architecture comprises the steps of obtaining and processing multi-source heterogeneous data of an embedded computer, constructing a system mapping knowledge domain integrating the multi-source data of the embedded computer, and forming a knowledge base containing components, functions, fault phenomena and association relationships thereof; the method is characterized in that a causal reasoning engine is designed, domain knowledge constraints are utilized, a real cross-level fault propagation causal chain is mined from atlas association, and root causes are verified through anti-fact reasoning. And the engine dynamically feeds back the mined causal knowledge to the atlas, so that the causal knowledge is continuously optimized. According to the hybrid architecture, accurate and rapid tracing with causal explanation from a fault phenomenon to a root cause is realized, and the diagnosis capability in high-reliability fields such as aerospace and industrial control is remarkably improved.

The invention discloses an intelligent policy question-answering method and system based on retrieval enhancement generation and a medium. The method comprises the following steps: constructing a universal knowledge base and a plurality of mutually independent domain knowledge bases; in response to user input, the following steps are executed: performing routing analysis on the user input through a first large language model to generate a structured routing decision; retrieving the general knowledge base to obtain related general knowledge text segments and vectorization expressions thereof; according to the routing decision, a domain knowledge base corresponding to the at least one policy domain identifier is retrieved in parallel, and related policy text fragments corresponding to the at least one domain knowledge base and vectorization expressions of the related policy text fragments are obtained; obtaining an initial answer set based on retrieval results of the general knowledge base and the domain knowledge base; and performing intelligent fusion processing on the initial answer set through a second large language model, and generating and outputting response content. According to the method, the problem of knowledge updating lag is effectively solved, and the accuracy, timeliness and cross-domain specialty of policy questions and answers are improved.

The invention relates to the technical field of automatic driving, and discloses an automatic driving track prediction method based on a vision-language model, near-end strategy optimization and a diffusion model. VLM-DM is proposed, which is the first framework for guiding initial noise priori generation in trajectory prediction based on a diffusion model by using a vision-language model. In order to close up modal gaps, a vision-language model auxiliary prior generator is introduced, and the vision-language model auxiliary prior generator is a module trained through reinforcement learning and can generate noise vectors with semantic meaning under scalar feedback guidance provided by a vision-language model. In order to overcome the limitation of a general vision-language model in application in a specific field, a retrieval enhanced vision-language model is designed, and the model continuously accumulates field knowledge related to a track by retrieving a historical scene and continuously optimizes the evaluation ability through joint training.

The invention relates to the technical field of software testing, and discloses an automatic test script generation method and system, a storage medium and electronic device.The method comprises the steps that test case information and tested environment information are received, and structured case representation is generated; enhancing the structured use case representation based on a preset knowledge base; generating a plurality of positioning candidates for the target control in the testing step, and establishing a priority relationship among the positioning candidates; generating an executable automatic test script; running the script, and when execution failure is detected, automatically adjusting a positioning strategy, a waiting strategy or a business process based on a failure type, and executing again; and feeding back the successfully executed script information to the knowledge base, and updating the content and priority of the knowledge base. Through organic combination of knowledge base enhancement, multi-candidate positioning and a self-healing mechanism, the technical problems that an existing automatic test script is high in maintenance cost, poor in stability and lack of domain knowledge are solved.

The invention relates to the technical field of text verification, in particular to an intelligent text verification method based on a hybrid model knowledge graph, which comprises the following steps of: analyzing a document, separating a text from a visual object, and generating semantics and visual vectors by using a bidirectional encoder and a hybrid visual model; performing form normalization verification by constructing a self-adaptive template matrix; judging the semantic homology of the image-text content by using a cross-modal gating arbiter; the text is converted into a semantic fact triple mapped to a unified space-time coordinate system, and logic irregularity is detected in a domain knowledge graph based on ontology constraint; and finally, summarizing all results to generate a structured verification report. According to the method, cross-modal semantic understanding and knowledge graph reasoning are effectively fused, full-dimension intelligent verification of content forms, image-text semantics and deep space-time causal logic is achieved, and the depth and accuracy of large-scale digital content verification are remarkably improved.

The invention relates to the technical field of natural language processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a document interpretation and report generation method, device, equipment and medium, which comprises the following steps: receiving an original document set to generate a structured document object, executing optical character recognition on an image content set to generate a recognition text set, the recognition text set and the text content set are combined into a unified text sequence, element item extraction is executed based on the interpretation template parameter set to generate an interpretation element set, a retrieval enhancement context is retrieved and generated from the domain knowledge base, and the unified text sequence, the interpretation template parameter set and the retrieval enhancement context are input into a language model to generate an interpretation result. And generating report content based on the historical report template set. According to the method, automatic closed loop of document interpretation and report generation is realized through multi-modal unified processing and semantic enhanced reasoning, the efficiency is improved, and the manual dependence and compliance risk are reduced.

The invention relates to the field of document processing, and particularly provides a document format processing method, system, terminal and medium based on a large language model.The method comprises the steps that a generation instruction containing a target document type and a source material are received, and original text content is generated through the large language model integrating domain knowledge; obtaining a matched structured format template, and analyzing the style rule into a format instruction set; identifying logic elements and hierarchical relationships thereof in the original text based on a natural language processing technology; performing association mapping on the format instruction and the logic element, and performing automatic style rendering by calling a document object model interface to generate an intermediate document with a standard format; and finally, outputting after quality verification. According to the method, an automatic process of content generation and intelligent formatting is constructed, and the document writing efficiency and normalization are improved.

The invention relates to the technical field of artificial intelligence, in particular to a large language model compliance reasoning method and system based on domain knowledge graph constraint, and the method comprises the steps: collecting domain literature corpora, extracting an entity relationship triple, labeling a timestamp interval and confidence, and constructing a domain knowledge basic data layer; organizing the state change of the same entity at different time points into a directed evolution link, forming a knowledge evolution tracking graph, and generating a time sequence perception type domain knowledge graph; constructing a semantic alignment detection mechanism, and detecting a semantic drift region; selecting a current effective graph knowledge fragment according to a detection result, and embedding time sequence constraint into a model context through a dynamic knowledge injection channel to realize real-time knowledge calibration in a reasoning process; and establishing a compliance reasoning verification process, comparing the reasoning result with the time sequence constraint rules one by one, marking and correcting, and outputting a compliance conclusion conforming to the current specification.

The invention discloses a small sample self-learning accurate identification method based on distillation knowledge migration. The method comprises the following steps: S1, extracting deep semantic features of a source domain and shallow features of a small number of samples of a target domain, and calculating a mapping matrix; s2, calculating an entropy difference distillation excitation function based on the initial alignment features; s3, executing domain knowledge distillation and generating staged distillation representation; s4, constructing a composite fitness function and initializing a parameter population; s5, performing iterative optimization by adopting a variable step size dynamic feedback compression strategy; s6, loading the optimal parameters and performing coupling alignment with the historical distillation representation; and S7, performing combined fine adjustment on the distillation weight and the model parameters through self-learning feedback. According to the method, through adaptive knowledge distillation and dynamic optimization feedback closed loop, high-precision and adaptive identification under extremely few labeled samples is realized, the generalization ability of the model is remarkably improved, and overfitting is effectively inhibited.

The invention relates to a field information analysis method and system based on RAG and a knowledge graph, and belongs to the technical field of artificial intelligence, and the system comprises a multi-source heterogeneous data collection module which is used for collecting field-related original data; the intelligent document processing engine is used for carrying out cleaning and structured processing on the data and extracting entities, relationships and events; the multi-source knowledge graph construction and management module is used for constructing and fusing multi-sub-field knowledge graphs to form a unified knowledge graph; the RAG retrieval enhancement generation dynamic fusion sequencing module is used for receiving user query, performing multi-channel information retrieval by querying a text vector index and a knowledge graph, performing fusion resequencing on a result, and generating an analysis result by utilizing a large language model; and the agent workflow engine is used for decomposing query into subtasks and scheduling professional agents to cooperatively complete analysis and report generation. Deep semantic understanding, intelligent retrieval and automatic analysis of domain information are realized, and the accuracy and efficiency of information processing are improved.

The invention provides a vertical field data construction method based on a large model, which belongs to the technical field of data processing and artificial intelligence, and comprises the following steps: converting a vertical field source document into an intermediate format text, and segmenting the intermediate format text into a plurality of text blocks; inputting the text blocks into a pre-trained generative language model, guiding the pre-trained generative language model according to pre-designed cue words to generate a plurality of candidate questions according to the content of the text blocks, and performing preliminary screening and fine screening on each candidate question to obtain a question set; pre-defining a mode of a knowledge graph according to field characteristics of the vertical field, processing all text blocks based on an information extraction model, and constructing a field knowledge graph; and performing local context retrieval on each final question in the question set based on the text block of the question source, performing global knowledge retrieval based on the domain knowledge graph, and generating a final answer and a final thinking chain. The method is suitable for different vertical fields, the data quality can be effectively improved, and the problem generation accuracy is guaranteed.

A scalable expert foundry system enables creation, management, and coordination of multiple specialized expert domains, each developing autonomous cognitive capabilities through geometric manifold formation while maintaining hierarchical oversight and cross-domain knowledge transfer. The system utilizes a Persistent Cognitive Machine architecture with hierarchical supervisory networks that provide multi-layered coordination, conflict resolution, and quality management across distributed expert domains. Cross-domain coordinators orchestrate communication and knowledge sharing between domains through geometric abstraction and manifold projection techniques that preserve semantic integrity while enabling beneficial knowledge propagation. Executive manifold supervisors implement second-order control architectures managing meta-cognitive capabilities and system-wide reasoning strategies. The system supports enterprise deployment across multiple geographic regions with distributed computing resources. Expert domains achieve operational readiness through statistical observables monitoring including cache hit rates, distance distribution shifts, and trajectory coherence measurements that validate manifold maturity. The architecture enables scalable expert-level performance across diverse knowledge domains while maintaining coordination effectiveness and quality standards.

The invention discloses a new energy consumption multi-objective decision reasoning method and system based on a knowledge graph. The method comprises the following steps: completing data acquisition and preprocessing; extracting the relationship between the core entities and the entities to generate a structured triple, and further constructing an energy field knowledge graph; designing a loss function by taking economy and stability as optimization targets, training a GNN integrated with power grid topology perception in combination with historical scheduling data, and completing model construction; entity change and relation update in the new data are identified through an incremental learning method, and the energy field knowledge graph is automatically supplemented or corrected; according to a current scheduling demand, extracting a corresponding associated sub-graph from the updated knowledge graph, inputting the trained GNN model, and outputting a scheduling decision scheme; and accessing the scheduling decision scheme output by the GNN to a power grid digital twinborn simulation platform to complete analogue simulation and feedback regulation. And efficient and safe consumption of new energy in a dynamic environment is ensured.

The invention provides an intelligent automobile test case automatic generation and evaluation system, device and product, and relates to the technical field of intelligent automobile test.According to the system, domain knowledge support is provided through a test knowledge base, and a demand understanding module is combined with a fine-tuning large model to deeply analyze demands; function points are extracted, and hidden scenes such as sensor faults and multi-system cooperation are identified; the test case generation module is based on a special prompt template and few-sample learning, a complete case containing elements such as purposes, steps and data is generated by fusing a vehicle model configuration library, and the specialty and the performability are ensured; and the evaluation module realizes objective quality evaluation through multi-dimensional quantitative scoring of demand coverage rate, scene integrity, risk coverage degree, normalization and the like. All the modules cooperate to realize intelligent generation and system evaluation of test cases, and the automation level, coverage range and reliability of intelligent automobile testing are improved.

The invention discloses an aviation airborne software test case intelligent generation and closed-loop optimization method, which comprises the following steps of: knowledge graph construction: analyzing a DO-178C standard document and a related field document, extracting entities and relationships defined in the DO-178C standard document and the related field document, and constructing a field knowledge graph fused with DO-178C standard knowledge; initial test case generation: based on the domain knowledge graph, combining a static analysis result of the source code of the tested airborne software, and utilizing a large language model to drive and generate an initial test case set; and closed-loop iterative optimization: executing the test case, evaluating whether the structural coverage rate reaches the standard or not, automatically identifying uncovered codes when the structural coverage rate does not reach the standard, generating a supplementary test case for iterative optimization, and outputting a final test case set until a coverage rate target corresponding to the software security level is met. According to the method, the test quality and efficiency of the aviation airborne software can be improved.

The invention discloses an electric power AI security detection model optimization method and system fusing attribution quantification and adversarial correction. The optimization method comprises the following steps: step 1, carrying out structured semantic representation on heterogeneous security alarms of an electric power network; 2, performing model decision logic analysis based on hybrid attribution quantization; step 3, automatically diagnosing decision prejudice based on domain knowledge masks; step 4, constructing an adversarial sample generated based on an anti-fact text; and 5, performing closed-loop fine adjustment and optimization on the attribution regularization model. According to the method, the interpretable ability of large model decision analysis, the root cause positioning ability of misinformation and the autonomous repair optimization ability are improved, the transparency and credibility of model decision are improved, the model misinformation caused by environmental influence is reduced, and the efficiency of model autonomous correction is improved.

The invention belongs to the technical field of aero-engine maintenance, and discloses an aero-engine intelligent fault diagnosis and maintenance system based on a domain knowledge graph and a large language model. The system comprises four core modules, wherein a data processing module adopts an AemCasRel model to extract a fault entity and relation triple from maintenance data; the knowledge graph management module stores the triple into a Neo4j database, constructs a structured knowledge graph and provides a management interface; the knowledge visualization module realizes visual display and interactive retrieval of the atlas based on D3. Js; the intelligent question and answer module depends on LangChain and a stellar fire big model and combines a multi-hop path reasoning technology to generate an interpretable diagnosis report. According to the system, the whole process integration of fault knowledge from extraction and management to intelligent diagnosis is realized, the precision, efficiency and intelligent level of maintenance diagnosis are remarkably improved, and the system has a wide application prospect in the fields of aviation, aerospace, machinery and the like.