693 results about "Semantic matching" patented technology

The invention discloses an automatic label labeling and classifying method and system oriented to unstructured system documents, and relates to the technical field of artificial intelligence. The method comprises the steps that semantic structure pre-analysis is conducted on an original system text, and a system semantic structure tree is constructed; establishing a system semantic enhancement vector space based on the semantic units and the logic relationship thereof; performing semantic deconstruction on the preset tag and extracting a feature vector; realizing cross-space semantic matching of the document and the tag through a system semantic attention mechanism; a confidence evaluation module is introduced to screen high-confidence labels from the three dimensions of structural integrity, coverage and logic consistency; and outputting a final label and a score through semantic conflict detection and resolution. According to the method, the problems that in the prior art, unstructured system text labeling accuracy is low and large-scale labeling samples are dependent on polysemy ambiguity, high context dependency, complex semantic structure and the like are solved, and labeling accuracy and robustness are remarkably improved.

The invention relates to the technical field of natural language processing, in particular to a context-based Prompt generative model optimization system, which comprises a context analysis module, a cue word generation module, a context optimization module, a semantic check module and a structure reconstruction module. According to the method, the context path and the semantic hierarchy information of the semantic unit are introduced, the fine degree of semantic matching degree recognition is improved, semantic guide deviation caused by statement template solidification is avoided, the cue words are recombined in combination with the semantic coherence weight and the logic dependency relationship, and the recognition accuracy is improved. The consistency and expression accuracy of the prompt content in the context are enhanced, the prompt word insertion sequence and connection mode are dynamically adjusted through a semantic conflict detection and structure rechecking mechanism, coherence and stability of a semantic structure and controllable generation of the prompt content are kept, semantic conflicts and expression chaos caused by static matching are effectively avoided in the generation process, and the generation efficiency is improved. And dynamic adaptation of prompt configuration and smooth optimization of language output are integrally realized.

The invention provides an mbse-based system full life cycle management method and system, and relates to the technical field of data synchronization, and the method comprises the steps: obtaining to-be-synchronized data of a source system, constructing a semantic graph structure, generating a mapping strategy based on implicit association between semantic matching learning systems, executing transactional data transmission, and constructing a time sequence traceability tree to track change propagation. And adaptive reconstruction is carried out when a constraint conflict is detected. According to the method, the problem of data synchronization among heterogeneous systems is solved, and the model consistency maintenance capability and the adaptive conflict processing efficiency are improved.

The invention relates to an information retrieval method and device for hierarchical planning reinforcement learning based on retrieval enhancement. The method comprises the following steps: acquiring a natural language query request of a user; calling a large language model of hierarchical planning reinforcement learning training based on retrieval enhancement to generate semantic keywords; the high-level strategy splits the natural language query request into a series of sub-query requests; the low-level strategy generates a retrieval query according to the context of the current sub-query request, and obtains a result verification condition from an external knowledge base through an RAG model; calling a search engine to execute multiple rounds of fine-grained information retrieval to obtain a plurality of candidate retrieval results; and performing deep semantic matching analysis on the candidate retrieval results and the result verification conditions by utilizing the post-trained large language model to calculate a matching degree score, and screening the candidate results according to the matching degree to obtain a final information retrieval result. Compared with the prior art, the method has the advantages that high-quality content retrieval and result display of complex query problems of users in various scenes can be realized.

The invention discloses a retrieval enhancement generation method and system based on hybrid retrieval and adaptive sorting, and relates to the technical field of artificial intelligence and natural language processing. Comprising the following steps: 1, analyzing a query language and providing multi-path retrieval: receiving a natural language query input by a user, and performing semantic analysis and structured processing; starting dense vector retrieval and sparse semantic retrieval in parallel, and respectively obtaining candidate document sets from the knowledge base; 2, candidate mixed result fusion is carried out, wherein duplicate removal and preliminary fusion are carried out on candidate documents obtained through dense retrieval and sparse retrieval, and a unified candidate document pool is formed; all the candidate documents are evaluated according to the query semantic matching degree, document authority and quality, context coherence and generation task type factors, sorting weights are dynamically generated based on all the factors, and a candidate document pool is resorted; and constructing a structured context prompt prompt, inputting the structured context prompt prompt into a pre-trained large model, and generating final response content.

The invention relates to the technical field of smart city services, and discloses a city service agent scheduling method and system based on intention recognition, and the method comprises the steps: collecting the multi-modal original request data of a city complex, and carrying out the preprocessing and feature extraction; identifying a multi-level intention, extracting an intention entity and a constraint condition, and evaluating an intention priority; constructing an intelligent agent capability model and a knowledge base, calculating a semantic matching degree between the intention and the intelligent agent, and generating an intelligent agent combination scheme according to a matching result; constructing a multi-objective optimization model and generating a scheduling scheme of a single intention and a composite intention; task issuing is carried out, execution abnormity is processed, fault-tolerant recovery is carried out, task completion quality is verified, and user feedback is collected; intention recognition optimization is carried out, scheduling strategy parameters are adjusted, and intelligent agent capability evaluation is updated; according to the method, the multi-dimensional intention of the user can be accurately understood, and multi-agent efficient collaboration and resource optimization configuration are realized.

The invention discloses an automatic test case generation method and system based on a large model, and the method comprises the steps: multi-modal data fusion: receiving a natural language demand, a UML design drawing, an API document, a historical defect log and system monitoring data, aligning text and image features through a CLIP model, analyzing the interface constraint through CodeBERT, and carrying out the multi-modal data fusion; feature fusion is realized by adopting a cross-modal attention mechanism; a dynamic test scene modeling step: constructing an environment simulator based on reinforcement learning, and simulating high-concurrency, distributed abnormal and other complex scenes; and a layered test case generation step: generating a function test case, a boundary test case and an increment test case through GPT-4, GAN and LSTM respectively, and introducing an entropy evaluation model to quantify the effectiveness of the cases. According to the method, the multi-modal data is brought into the test case generation process for the first time, the test case generation time is shortened by 80%, the complex scene coverage rate is increased to 95%, the semantic matching degree reaches 92%, and the intelligent level and efficiency of software testing are remarkably improved.

The invention discloses a heterogeneous document structured data extraction system and method based on multi-modal fusion, and the method comprises the following steps: S1, receiving a heterogeneous document, and carrying out the preprocessing; s2, extracting visual and semantic modal information based on the visual backbone network and an OCR module, and fusing spatial coordinates, text content and layout features; s3, receiving a dynamic target mode Schema, executing field-level semantic matching, and calculating semantic similarity; s4, performing consistency verification, verifying and filling the field values, and correcting the associated fields; s5, converting the format into a data file in a specified format, and reserving fields to be mapped with an original document semantic block; s6, automatically switching a cloud mode and a local mode according to a deployment environment; and S7, outputting the data file of the target field. According to the method, high-precision and low-delay structured data extraction of the heterogeneous format document can be realized, and the automatic processing efficiency and the data credibility are improved.

The invention relates to the technical field of prompt optimization engineering, in particular to an embedded clustering multi-path recall large model question and answer method, system and device and a medium, and the method comprises the following steps: preprocessing a multi-source text to generate an associated paragraph, and converting the associated paragraph into a semantic vector; executing clustering and adjusting a clustering center based on a matching strategy to form a vector library; receiving queries, converting the queries into semantic vectors and retrieving related units in parallel; the recall result is comprehensively evaluated on the basis of a credibility perception attention mechanism in combination with semantic matching and timeliness score, the semantic matching score is calculated by a local bge-ryanker-v2-m3 model, the timeliness score is quantized through a date difference attenuation function, and finally high-quality content is weighted and screened to be input into a large language model to generate question and answer output. And the result accuracy, timeliness and service adaptability are improved.

The invention relates to a query optimization method and device based on agent planning, electronic equipment and a medium. The method comprises the following steps: pre-retrieving a target tree structure index based on a user query request to obtain a pre-retrieval result set; generating a retrieval-reasoning double-stage directed acyclic graph task chain comprising a task type, a retrieval / reasoning target and a dependency relationship; executing each task according to a topological sequence, and obtaining a target text fragment through query rewriting and expansion; and performing multi-hop logical reasoning in combination with the task chain and the target text fragment, and outputting a final answer. Therefore, dynamic task planning of environment perception is carried out by constructing a retrieval-reasoning dual-stage directed acyclic graph task chain and combining a knowledge base tree structure index; the problems that when an existing retrieval enhancement generation system processes a multi-hop question and answer task, logic association understanding ability among retrieval fragments is insufficient, semantic matching precision is low, and a reasoning path is prone to deviation are solved, and the retrieval recall rate and the answer accuracy under a multi-hop question and answer scene are improved.

The invention discloses an intelligent decision data inquiry system and method based on a generative large model, and belongs to the technical field of artificial intelligence. Natural language inquiry input by a user is received, and an inquiry intention and a target field are extracted; extracting structured and unstructured cost data from the real estate project database, and constructing a candidate field set; performing semantic matching by utilizing the generative large model to generate an intention field mapping matrix; constructing a field dependency graph based on a mapping result, and extracting a minimum closed-loop field set; performing credibility evaluation on the fields, and constructing a weighted field set; generating a dynamic query template, outputting a natural language answer, and attaching a field tracing path; if the field is missing or the credibility is insufficient, automatically generating a reverse query until a credibility requirement is met; according to the method, automatic association and accurate question and answer between complex semantic query and heterogeneous cost data are realized, and the method has good interpretability, traceability and intelligent interaction capability.

The invention discloses a knowledge point extraction and question knowledge point matching method based on a large language model, and relates to the technical field of natural language processing. Firstly, a knowledge point extraction test set and a candidate baseline large model are constructed, an average recall score is calculated through matching, and an optimal baseline model is selected; a model adaptive to the teaching field is obtained through supervised fine tuning, then knowledge points are disassembled through the model, classification is carried out according to a Bloom learning model so as to clarify a teaching target, and finally the mastering degree of students is analyzed by associating questions with the knowledge points. According to the method, the course analysis efficiency can be improved, and full-automatic or manual intervention flexible analysis is realized; the accuracy and generalization ability of knowledge point extraction and matching are guaranteed, and subjective errors are reduced through semantic matching and evaluation schemes; teaching objectives are defined, and Bloom type labels are marked for knowledge points; a detailed question and knowledge point corresponding relation is constructed, the importance degree of each knowledge point is represented through a weight vector, and support is provided for student portrait and teaching progress analysis and the like.

The invention discloses an intelligent extraction method and equipment for structural data of a scanned copy and a medium, and relates to the cross technical field of computer vision and intelligent document processing. The method comprises the following steps: acquiring a to-be-processed scanned copy image, and performing joint feature extraction on the scanned copy image based on a preset multi-modal neural network model to generate intermediate feature representation; constructing an extensible structured index template library containing field rules, value domain constraints and cross-field verification logic; based on an attention mechanism, performing intelligent semantic matching and mapping on the intermediate feature representation and a target field in an extensible structured index template library to output preliminary structured data; based on a verification rule preset in an extensible structured index template library, executing automatic logic verification and conflict resolution on the preliminary structured data to generate standard structured data conforming to business specifications; and carrying out serialization output on the standard structured data according to a predetermined format.

The invention relates to the technical field of intelligent matching, and discloses a big language model dynamic position recommendation method and system based on dialogue contexts.The method comprises the steps that candidate skill label analysis is conducted on natural language input of candidates, a semantic analysis result is generated, and based on the semantic analysis result, a big language model dynamic position is recommended; dynamically updating the candidate portrait, carrying out semantic matching on candidate portrait data and standardized post information to obtain a post matching result, carrying out post similarity calculation on the post matching result, generating an initial post recommendation list, then carrying out recommendation logic adjustment, generating feedback processing data, and carrying out post similarity calculation on the initial post recommendation list. Dynamically optimizing the initial position recommendation list in combination with the semantic analysis result, candidate portrait data and feedback processing data, generating position dynamic recommendation results, reordering the position dynamic recommendation results, and outputting a final position recommendation list; according to the method, the accuracy of dynamic position recommendation of the large language model based on the dialogue context can be improved.

The invention relates to an object attitude estimation method based on scene-level semantic three-dimensional Gaussian spatter, which comprises the following steps of: firstly, constructing scene-level three-dimensional representation according to a multi-view image, and associating semantic embedding of three-dimensional Gaussian points of each target object; positioning a target mask area of a target object described by a language instruction according to the query image, and extracting each target three-dimensional Gaussian point subset through semantic matching and three-dimensional space clustering; secondly, an ICP registration method is guided through two-stage learning, and the initial 6D pose of the target object is obtained; and finally, performing cascade fine optimization by combining pose rendering and similarity comparison under disturbance to obtain a 6D pose of the target object in the target scene. According to the design scheme, target retrieval and instance extraction under open vocabularies are achieved through three-dimensional Gaussian reconstruction of semantic enhancement, and the attitude estimation precision under the conditions of shielding and low texture in a complex scene is effectively improved by combining language prompt and registration and rendering fine optimization guided by two-stage learning.

The invention relates to the technical field of medical knowledge retrieval, in particular to a traditional Chinese medicine acupuncture field knowledge retrieval method and system based on deep learning, and the method comprises the following steps: obtaining an acupoint sequence and combining with semantics to construct a vector fragment, extracting symptom-related acupoint analysis response to generate a path sequence, and extracting a root combination vector matrix; according to the method, the sequence information of the acupuncture points in the meridian path is extracted, the semantic description and the major content are combined to construct the structured expression, the path organization and recognition capability is enhanced, the curative effect level and the treatment cycle are fused to form the sequence, the response pertinence of the acupuncture points is improved, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. Through major treatment, direction and positioning root three-dimensional combination vectorization expression, semantic comparison and standardization are enhanced, keyword matching frequency and distribution density are combined, semantic association between input and knowledge is enhanced, and acupoint combinations are screened based on semantic matching and path continuity, so that the result is ensured to have relevance and practicability.

The invention discloses a semantic matching-based field name standard abbreviation mapping method and system, and particularly relates to the technical field of data governance, a source field set to be subjected to abbreviation and a standard field set in a standard field library are acquired, field names and field descriptions are normalized, and field text representation is generated; using the pre-training language model to generate a semantic vector and recalling a candidate mapping pair set; calculating character string similarity, synonym expansion matching score, data type consistency score and sample value pattern consistency score for the candidate mapping pairs; generating a neighbor confusion risk index based on semantic neighbor density, entity category distribution deviation, synonym expansion and context anti-verification, performing risk gating correction, and judging a score in combination with a difficult case; and applying table-level consistency constraints in the same service table or entity domain to carry out joint consistency solution to obtain a table-level optimal mapping scheme, generating confirmation confidence, and outputting an automatic confirmation or manual recheck mapping result.

The invention provides a data heterogeneous integration method under an AI platform, and belongs to the technical field of digital data processing.The data heterogeneous integration method comprises the steps that feature recognition is conducted on multi-source heterogeneous data through a data fingerprint technology, the data contribution rate is calculated, and an overall alignment index matrix and a partial alignment index matrix are constructed; a semantic alignment optimization model based on a Transform architecture is adopted to carry out deep semantic matching to construct a standardized data set, and a data AI training feedback model is combined with a sparse sampling function and a Gaussian kernel smoothing function to construct a simplified data set to carry out shallow training. And the performance of the complete model is rapidly evaluated by using a performance estimation function, a feedback signal is converted into a standardized feedback signal through a feedback signal generation function, an optimization process is monitored through an iterative index calculation function, and a closed-loop optimization process is formed, so that the technical problem that self-adaptive optimization integration is difficult to realize in a multi-source heterogeneous data integration process is solved.

The invention is suitable for the technical field of data processing, and provides a database query method, system and device based on a natural language and a medium. Based on the natural language text and the field library, calling a root matching strategy, a semantic matching strategy and a fuzzy matching strategy through a hierarchical collaboration mechanism to perform field mapping, and determining a target field; splicing the target fields to obtain an initial semantic query statement; loading and executing the plurality of modifiers in sequence through a service discovery mechanism to obtain a target semantic query statement; converting the target semantic query statement to obtain a target physical query statement; and executing the target physical query statement to obtain a target query result and returning the target query result to the query party. Through hierarchical cooperation of the root matching strategy, the semantic matching strategy and the fuzzy matching strategy, the expandability and adaptability of the matching strategy are improved, the field recognition accuracy is improved, the field matching range is expanded, and the matching efficiency is optimized.

The invention relates to a cross-architecture code automatic migration method, system and device based on a large language model agent and a medium. The method comprises the following steps: acquiring a source code, a construction script and an architecture related header file of a target project; based on a pre-constructed transplantation target system architecture knowledge base, analyzing system architecture differences in combination with construction scripts and positioning architecture related positions needing to be modified in source codes to obtain a preliminary modification scheme; constructing scripts through static analysis and carrying out abstract syntax tree analysis on source codes to obtain a global dependency directed graph; based on a transplantation target system architecture knowledge base, performing migration code semantic matching on the source code according to the preliminary modification scheme and the global dependency directed graph, and generating a semantic equivalent replacement code to obtain a patch list; and sequentially executing incremental compiling, function consistency testing and performance regression verification on the migration project copy after the patch list is applied to generate verification information and a verification result. By adopting the method, cross-architecture code automatic migration can be realized.

The invention provides an intention recognition response method and system based on forest farmer question and answer data, and the method comprises the steps: firstly obtaining an initial question and answer data set of forest farmer users, the initial question and answer data set comprises a plurality of question and answer interaction records, and then carrying out the semantic standardization processing of the initial question and answer data to obtain a structured question and answer data set; then semantic association features and interaction time sequence features are extracted from the structured question and answer data, the semantic association features reflect the semantic matching degree of user questions and system responses, the interaction time sequence features reflect the context dependency relationship of adjacent question and answer records, and dynamic intention mapping processing is conducted based on the semantic association features and the interaction time sequence features; and finally, according to the target intention recognition result, matching a preset response knowledge base, generating optimized response data, and sending the optimized response data to the forest farmer user terminal to update the response, so that the accuracy of forest farmer question and answer intention recognition and the accuracy of the response are improved.

The embodiment of the invention provides a pulmonary nodule automatic labeling method based on multi-modal semantic affinity iterative optimization, and belongs to the technical field of data processing, and the method specifically comprises the steps: obtaining a lung CT image and a text report; performing structured semantic analysis on the text report; performing visual feature extraction on the lung CT image; based on the key semantic information, performing semantic guidance processing on the depth visual feature representation to generate semantic enhanced visual guidance features; based on the semantic enhanced visual guidance features, calling a segmentation basic model, and generating a plurality of candidate segmentation masks by introducing an active variation mechanism; for each candidate segmentation mask, calculating a semantic matching degree score of the candidate segmentation mask; and comparing the semantic matching degree scores of all the candidate segmentation masks, and selecting the candidate segmentation mask with the highest score as a final pulmonary nodule labeling result to be output. Through the scheme of the invention, the labeling precision, adaptability and interpretability are improved.

The invention provides an intelligent question and answer semantic understanding and enhanced rewriting optimization method based on multiple rounds of dialogues, and relates to the technical field of artificial intelligence semantic understanding, and the method comprises the steps: obtaining a current query statement and a historical dialogue context, carrying out the time sequence analysis of the historical dialogue context, and constructing a dialogue context coding representation; and performing multi-level semantic disassembly on the query statement to identify dominant and implicit intentions, generating a semantic enhancement rewriting statement based on an intention hierarchical structure, and finally performing semantic matching and retrieval to output answers. The understanding accuracy of the real intention of the user in multiple rounds of dialogues can be effectively improved, and the interaction experience and the answering quality of the intelligent question answering system are improved.

The invention provides an electric power training knowledge graph construction method and device based on multi-source heterogeneous data, equipment and a storage medium, and relates to the technical field of knowledge graphs. The method comprises the following steps: acquiring and preprocessing multi-source heterogeneous post training data to obtain structured post description data and course description data; respectively extracting post feature vectors and course feature vectors; calculating the semantic similarity between the post feature vector and the course feature vector; comparing the semantic similarity with a preset matching threshold value, screening out candidate courses matched with the target post, and generating a triple; constructing and updating a post training knowledge graph based on the triple; and when a new post or course is added, generating a new triple to update the knowledge graph. Through unified processing of multi-source heterogeneous data, post-course semantic matching and dynamic triple updating, precision, structuring and real-time updating of post training content are realized, and training pertinence and management efficiency are improved.

The invention discloses an information recommendation method and device, a storage medium and electronic equipment, and relates to the technical field of recommendation systems.The method comprises the steps that in response to terminal interaction operation, input data is obtained; filling the input data into a first preset prompt word template according to a preset format to form first fusion data containing prompt guide information; inputting the first fusion data into a prediction model, and outputting an intention label and an associated extended keyword set through intention analysis and keyword extension processing; performing semantic matching and preference matching based on the intention tag, the extended keyword set and locally stored chat robot Chatt related data to obtain a candidate Chatt set; filling a second preset cue word template with the first fusion data and the candidate Chatpot set according to a preset format to form second fusion data containing an adaptive service scene; and inputting the second fusion data into the prediction model, and determining Chatpot recommendation information.

The invention discloses an anaphora disambiguation method and system based on big language model enhanced text and structured query language generation. The method comprises the following steps: receiving a natural language question of a user, and analyzing and generating structured table field information through mode information; identifying and rewriting fuzzy time expression in the problem; extracting ambiguous entities, and replacing the ambiguous entities with database standard values through semantic matching and fuzzy matching; synthesizing the information to generate a structured query language statement and executing the structured query language statement; and if the execution result is null, automatically triggering an anaphora disambiguation process, performing error correction and re-matching on field values in the statement through a dual matching mechanism, and generating and executing a corrected query statement. According to the method, the problems of fuzzy anaphora, indefinite time expression, low matching accuracy, resource waste and the like in a traditional SQL system are effectively solved through a strategy of combining pre-processing and post-processing, and the accuracy, robustness and execution efficiency of complex query are remarkably improved.

The invention discloses a method for generating an image description text based on a large model, which relates to the technical field of image processing, and comprises the following steps: an image preprocessing step: dividing a target level through semantic segmentation and extracting key visual information by adopting hybrid denoising and self-adaptive normalization; a feature extraction step: fusing the multi-scale visual features and the semantic features, and generating a high-dimensional fusion feature vector through cross-modal alignment; a large model initialization and adaptation step: loading the pre-training model and performing incremental fine tuning, and dynamically adjusting the Prompt template; a text generation step: generating candidate texts through logic constraint and beam search; and a text optimization adjustment step of outputting a final description text based on multi-dimensional evaluation and user preference iterative correction. According to the method, the semantic matching degree, logic coherence and common sense accuracy of image description are improved, multi-element scenes are adapted through dynamic adaptation and iterative optimization, and high-quality text description support is provided for high-precision and diversified scenes.

The present application discloses a method for determining a degree of matching prediction model and a related apparatus. For a target search scenario comprising two types of correlation tasks, hybrid training is performed on an initial model by using training samples from the two types of correlation tasks. In the hybrid training, model parameters are shared, and for the shared model parameters, weights are adjusted to distinguish different types of correlation tasks, so that the initial model can learn the shared model parameters so as to participate in prediction of a first type of correlation task using first weights and participate in prediction of a second type of correlation task using second weights. On this basis, in a finally obtained degree of matching prediction model, the shared model parameters have two sets of weights corresponding to the two types of correlation tasks, so as to be compatible with different requirements of semantic matching of different types of correlation tasks, so that a single model has a capability of covering the two types of correlation tasks. Accordingly, only one model needs to be deployed in the target search scenario, thereby improving the deployment efficiency of the model and reducing resource overhead.

The invention relates to the technical field of picture sharing, and discloses a picture sharing method and device based on an AI platform, electronic equipment and a storage medium, and the method comprises the steps: obtaining a generated data stream of a picture uploaded by a first user, converting the generated data stream into a structured JSON file, and enabling a built-in cross-platform compatible tag to support multi-terminal sharing; based on the second user creation preference portraits and the key features, non-key parameters are screened through an AI semantic matching model, an adaptive priority adjustable component is generated, and a difference thermodynamic diagram and a new picture are generated after user adjustment; the enhanced copyright metadata containing original author identification, content fingerprints and the like are embedded into the JSON parameter stream; and calculating a hierarchical hash value and carrying out block chain evidence storage during each parameter iteration, calculating contribution degree distribution earnings based on a multi-dimensional index, generating a corresponding NFT copyright certificate, and supporting on-chain reverse tracing. According to the method and the device, the problem of low efficiency in secondary creation parameter adjustment caused by lack of standardized structured packaging and dependency relationship labeling in parameter generation can be solved.

The invention particularly relates to a compliance review method based on a large model. The compliance review method based on the large model comprises the following steps: collecting and preprocessing a rule text and a regulation text to form standardized data supporting modeling; performing semantic vectorization representation on the text by using the large model, and extracting context semantic features; semantic association and logic constraints of compliance review are constructed based on the knowledge graph and the rule base; semantic matching is carried out on the regular text terms and the regulation terms, and compliance is judged; and outputting a compliance examination result, and generating an optimization suggestion and risk assessment report. The compliance review method based on the large model not only solves the problems of efficiency and accuracy of traditional system compliance review, but also constructs a set of sustainable, extensible and explainable intelligent review framework, and is of great significance for improving the compliance governance ability of enterprises.