1035 results about "Semantic enhancement" patented technology

The invention discloses a cross-modal information fusion and retrieval method and system driven by semantic comprehension, and the method comprises the steps: obtaining text, image and audio original data, and extracting an initial feature set of each modal through a deep neural network; dynamically distributing each modal weight coefficient based on an attention mechanism, and performing weighted fusion on the initial feature set to obtain cross-modal fusion feature representation; through a cross-modal semantic association analysis model, high-dimensional semantic association features are extracted from the fusion feature representation, and semantic enhancement feature vectors are generated; constructing a cross-modal semantic graph network based on the vector, complementing missing modal features, and generating an optimized multi-modal feature set; and inputting the optimized feature set and the query sample into a contrast learning model, calculating a semantic similarity score, and generating a cross-modal retrieval result sorting list according to the score.

The invention relates to the technical field of intelligent operation and maintenance monitoring and self-adaptive rule engines, in particular to a monitoring strategy system and method based on a rule base. The method comprises the following steps: constructing a unified state vector model through multi-source heterogeneous data collection, enhancing state representation in combination with context semantics, and verifying the validity of the state representation; a dynamic rule cutting mechanism is adopted, a graph structure is constructed based on semantic redundancy and conflict relations between rules, and an optimal non-redundant rule subset is screened in combination with a greedy cutting algorithm; generating a strategy graph through rule semantic fusion, aggregating semantics by using a graph neural network, constructing a directed acyclic graph to solve action conflicts, and generating a safe and efficient response sequence; a cross-scene migration mechanism is introduced, and source scene strategy semantics are projected to a target scene through a mapping matrix, so that lightweight migration and self-evolution of a knowledge base are realized. According to the method, the dynamic adaptability of the rule base is improved, the redundancy execution risk is reduced, and multi-scene seamless migration is supported.

The invention discloses a Transform-CNN medical image segmentation method and system based on multi-scale fusion semantic enhancement, and relates to the technical field of image segmentation, and the method comprises the steps: collecting medical image data, and constructing a medical image data set; constructing a medical image segmentation network model; training the medical image segmentation network model through the medical image data set; and inputting real-time acquired data into the trained medical image segmentation network model to obtain a medical image segmentation result. According to the invention, double encoders, LGDA modules and the like are adopted to capture multi-scale global features of kidney tumors and enhance representation, and the LGDA module is used for adapting to size and form changes of the kidney tumors; the MLCF module is used for supplementing information of the main encoder; the PSE module captures multi-scale global semantic information and integrates local context information, local features are fused through the SAM module, and kidney tumor positioning in an endoscope image is achieved.

The invention relates to the technical field of knowledge graph retrieval, in particular to a genuine medicinal material intelligent retrieval method and system based on a graph. The method comprises the following steps: performing semantic granularity analysis on a retrieval request input by a user, constructing a multi-level semantic edge and generating a hierarchical semantic graph structure; semantic enhancement is carried out on the map relation through semantic annotation, and a multi-condition intention is extracted in combination with dimensions such as regions, drug properties and channel tropism; further, the system executes multi-hop path combination, a structured semantic path conforming to the composite intention is mined, edge nodes in the path are inferred and complemented, and a genuine medicinal material retrieval result with a closed structure and complete semantics is generated. Compared with a traditional keyword matching and static field retrieval mode, the method has higher semantic perception ability and reasoning intelligence, and the accuracy and adaptability of the system in processing fuzzy, composite and path-incomplete retrieval scenes are remarkably improved.

The invention relates to the technical field of agricultural meteorological prediction, in particular to an agricultural meteorological disaster time sequence prediction system and method based on multi-modal data fusion, and the method comprises the steps: collecting and preprocessing agricultural meteorological disaster related data, constructing a dynamic semantic association graph, carrying out the multi-layer feature abstraction processing, and generating a semantic enhancement feature vector; the dual-branch prediction network processes time sequence dependence and local mode features, multi-granularity attention processing identifies key feature information, multi-scale feature fusion extracts different time scale feature information, and cascade fusion is carried out; the multi-target optimization module carries out model training based on the comprehensive feature representation and optimizes a plurality of targets; the multi-time scale prediction output module generates short-term accurate prediction, medium-term trend prediction and long-term risk assessment results, and provides prediction confidence, error range and risk level information; a dynamic semantic association graph and a multi-layer feature mapping mechanism are constructed, and deep fusion of multi-modal data on the semantic level is achieved.

The invention discloses a rule base dynamic construction method and device based on a large language model and a medium, and relates to the field of rule base construction.The method comprises the steps that on the basis of a preset layered template structure, meta-knowledge injection is conducted through a field knowledge graph corresponding to standard data, and dynamic cue words are generated; outputting a corresponding semantic triple through the large language model, and performing semantic enhancement on the semantic triple; performing symbolization processing and vectorization processing to obtain a rule vector, and generating a corresponding specified rule; and locally and dynamically updating the rule subset in the rule base through data updating of an external specified knowledge base, and dynamically updating the rule weight of the specified rule determined through the confidence coefficient. Through deep collaboration of the large language model and the symbol system, a logic verification layer is introduced through local dynamic updating to carry out formalized constraint on a large language model generation result, and the rule logic completeness is ensured while the generation capability is reserved.

The invention relates to the technical field of telecommunication, in particular to a switch automatic configuration method and system and a medium. The method comprises the following steps: obtaining switch resource configuration data, and carrying out semantic enhancement topological graph modeling to obtain a network environment digital twinborn model; performing configuration instruction analysis based on the network environment digital twin model and a preset configuration management database to obtain an intention configuration semantic set; performing multi-manufacturer semantic mapping arrangement based on the configuration strategy path of the intention configuration semantic set to obtain a native configuration command set; performing identity path integrity auditing on each configuration command in the native configuration command set to obtain a signature command set passing verification; uploading the verified signature command set to a switch management platform to execute the command; and acquiring real-time behavior state data of the switch, and performing semantic deviation calculation to obtain a configuration result report. According to the invention, the effectiveness and adaptability of switch configuration can be improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as agent autonomous decision making, financial science and technology and medical health, and discloses a multi-modal hierarchical feature fusion and decision making method, device, equipment and medium, and the method comprises the steps: obtaining vision, language and motion data, and carrying out the hierarchical feature extraction to generate a multi-modal initial feature set; feature importance is analyzed, screening and dimension reduction are carried out, and screened multi-modal features are obtained; performing semantic enhancement on the screened multi-modal features to generate multi-modal semantic enhancement features; executing cross-modal attention fusion on the multi-modal semantic enhancement features to obtain cross-modal fusion features; and inputting the cross-modal fusion features into a semantic reasoning network to generate a decision result. According to the method, through multi-level screening dimension reduction, semantic enhancement and cross-modal attention fusion, the model can accurately utilize key feature relationships among multi-modal data, redundant interference is reduced, and semantic reasoning accuracy and decision-making efficiency are improved.

The invention provides a semantic enhancement and dynamic completion method and system for a power market data graph. The method comprises the following steps: acquiring target entity information and external data of a power market data graph by responding to a data query instruction; converting external data into structured semantic tags, then traversing the topological structure, establishing a mapping relationship between the tags and entity attributes, and combining query instruction influence logic to calculate topological integrity indexes and mark missing entities or correlate to form a missing tag set; establishing attribute mapping based on a target entity and external data, generating a semantic vector fusing cross-domain features, and projecting the semantic vector to a topological space according to a missing mark set to form cross-domain feature topological nodes and connections; embedding a missing position to reconstruct a topological structure, and checking logic connectivity; the dynamic conduction chain is analyzed, and a feedback interface containing the semantic relation and the completion structure is generated to respond to query. According to the method, conduction logic closed-loop verification of the missing elements in the power market data graph is realized.

The invention provides a question and answer system construction method and system based on a large language model, and the method comprises the steps: obtaining multi-modal data, constructing a question and answer knowledge base and a knowledge graph, and carrying out the dynamic updating of the question and answer knowledge base; obtaining a query text, and respectively carrying out vectorization processing on the query text and the multi-modal data to generate a corresponding query semantic vector and a multi-modal vector; an entity in the query text is extracted by using the recognition model, a triple associated with the entity is extracted from the knowledge graph, the query text and the triple are spliced and vectorized, and a query semantic enhancement vector is generated; according to the method, through a dynamic knowledge base incremental updating mechanism, a context-aware hybrid retrieval strategy, a cross-modal semantic enhancement technology and a user feedback-driven continuous optimization method, real-time processing requirements of various modal data such as texts, images and voices can be effectively met, and accurate semantic understanding and answer generation of complex queries are achieved.

The invention provides a text sentiment analysis method based on dynamic semantic segmentation and feature perception, and belongs to the field of natural language processing. Inputting the semantic vector sequence into a knowledge retrieval and dynamic graph construction model for multi-path context enhancement through the knowledge retrieval and dynamic graph construction model to obtain semantic features, semantic knowledge and graph structure information; the semantic vector sequence is subjected to multi-path context enhancement, the complex relation between different parts in the text can be comprehensively considered, and more comprehensive and deep semantic features and knowledge can be mined. Unified representation of semantic features is combined with heterogeneous graph features, an antagonism training strategy is adopted to train a knowledge retrieval and dynamic graph construction model, an improved ATOSS + module is introduced to carry out hierarchical attention fusion, and multi-granularity semantic enhancement features are obtained; therefore, emotion clues and semantic association hidden in the text can be captured, and the accuracy and integrity of semantic understanding of the text are improved.

The invention discloses a retrieval generation method and system based on multi-agent collaboration, a terminal and a medium, and relates to the field of artificial intelligence. Performing semantic analysis on the input word embedding converted by the natural language query instruction through a query analysis agent, and determining a semantic intention vector; performing reinforcement learning and meta learning on the semantic intention vector through a strategy construction agent, and determining a retrieval strategy; performing semantic enhancement on the semantic intention vector according to knowledge graph node embedding to obtain a semantic enhancement vector; determining a data channel according to the semantic enhancement vector, a retrieval strategy and a real-time system load, and calling the data channel for retrieval to obtain candidate documents; and generating a target answer according to each candidate document based on an adaptive reflection feedback mechanism in combination with an auto-encoder and a generative adversarial network. The problems that the prior art depends on a fixed retrieval strategy, has limitation when facing complex query, multi-round interaction and cross-modal data fusion, is easily interfered by noise and is not accurate enough in semantic matching are effectively solved.

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 field of knowledge graph completion, provides a knowledge graph completion method based on multi-modal visual angle perception and a deep neural network, and aims to solve the problems of weak multi-modal information expression ability, rough fusion mode and insufficient structural reasoning ability in the prior art. According to the method, structure information, text description and visual image information of an entity in a knowledge graph are obtained, structure, text and image modal input is constructed respectively, and a graph neural network, a pre-training language model and a visual encoder are adopted for feature coding; weighted fusion and semantic enhancement of multi-modal features are realized through a visual angle fusion mechanism and hierarchical attention processing; cross-modal contrast learning is introduced to improve modal consistency; and carrying out triple reasoning by using a uniform Transform encoder, and verifying a completion result by scores. According to the method, multi-modal semantics are effectively integrated, the entity representation capability and the triple prediction accuracy are improved, the model robustness is enhanced, and the method is suitable for application scenes such as intelligent question answering and recommendation systems and has remarkable practical value and popularization prospects.

The invention discloses an AI-based conference record data searching method and system, and the method comprises the steps: carrying out the feature extraction and alignment through a multi-mode fusion neural network according to the voice, text, image and video data collected in a conference process, and obtaining a semantic representation vector; according to the semantic representation vector, combining context information of the conference scene, and utilizing a pre-trained context perception model to perform semantic enhancement processing to generate an enhanced semantic vector with context association; according to the enhanced semantic vector, combining with an external knowledge base, and utilizing a dynamic knowledge graph construction algorithm to generate a knowledge graph related to the conference theme in real time; and according to the knowledge graph, intelligent retrieval and recommendation of conference record data are carried out by using a graph neural network. By utilizing the embodiment of the invention, the intelligent retrieval efficiency and accuracy of the conference record can be improved.

The invention discloses a semantic enhancement auxiliary inquiry system and method based on a medical knowledge graph, and the system comprises a patient information receiving module, a theoretical knowledge graph storage library, an evidence-based knowledge graph storage library, a double-track diagnosis path construction module, a medical knowledge conflict judgment module, and a semantic enhancement report generation module. The double-track diagnosis path construction module inquires the received patient information in a theoretical knowledge graph storage library and an evidence-based knowledge graph storage library which are independent from each other in parallel, and a theoretical diagnosis path and an evidence-based diagnosis path are generated respectively; the medical knowledge conflict judgment module dynamically compares the two paths in real-time interaction, and performs priority judgment according to a preset medical judgment rule; finally, the semantic enhancement report generation module presents the two paths and the conflict judgment result to the user at the same time. Transparency and interpretability of the whole interrogation process are assisted, and reliable semantic enhancement decision support is provided for doctors when the doctors face complex medical knowledge conflicts.

The invention provides a semantic enhancement adaptive partitioning method and system for natural resource large model questions and answers, and aims to solve the problems of difficulty in term boundary recognition, damage to semantic integrity and the like. According to the method, three core technologies including theme perception coarse-grained paragraph division, self-adaptive sliding window theme hierarchy division and embedded perception context self-adaptive text segmentation are fused. The system firstly analyzes a natural resource long text structure, identifies titles and theme levels and aligns associated contents; paragraphs are extracted according to a theme perception strategy and are subdivided into sentence sets according to grammar rules; an improved sliding window mechanism is adopted to divide sentences into window sentence block groups. The method is characterized in that a dynamic aggregation threshold mechanism is introduced, the semantic association degree between adjacent sentence blocks is calculated through an embedded perception context semantic segmentation technology, whether the sentence blocks are combined or not is judged by combining a similarity distribution change trend and a dynamic adjustment threshold, self-adaptive delimitation of semantic boundaries is achieved, and text blocks which are clear in structure and coherent in semantics are generated.

The invention relates to the technical field of intelligent decision making, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a multi-modal data-based event analysis method, which comprises the following steps of: obtaining attribute data, monitoring data, environment data and biological characteristic data of a user, and performing standardization processing on the attribute data, the monitoring data, the environment data and the biological characteristic data; combining semantic analysis and structured fusion of the text records to form a unified input data set; and performing multi-modal fusion modeling on the unified input data set by using an intelligent decision model, generating a potential event analysis result of an individual state, generating a visual report containing potential event levels, main influence factors and intervention suggestions based on the result, and finally sending the report to a user terminal. According to the method, the multi-source structured data and the multi-source unstructured data are integrated, and the intelligent decision-making model is introduced to realize feature level fusion and semantic enhancement modeling, so that the accuracy and timeliness of individual state analysis are effectively improved, and the personalized expression of an analysis result is enhanced.

The invention relates to the technical field of multi-modal data processing and semantic retrieval, in particular to a multi-modal heterogeneous knowledge fusion construction and semantic enhancement retrieval system based on a large model, which comprises a data acquisition module, a semantic analysis module, a knowledge fusion module and a retrieval optimization module. Multi-modal data such as texts, images and audios are uniformly expressed and deeply analyzed by introducing a large model technology, a knowledge graph is dynamically constructed, a structure is optimized in combination with a user query intention, and meanwhile accurate sorting and screening are achieved through a semantic enhancement algorithm. According to the method, the semantic comprehension capability and the intelligent level of the system can be improved, the real-time and diversified scene requirements are met, and the accuracy and the adaptability of a retrieval result are remarkably enhanced.

The invention provides a multi-modal data dynamic fusion method and system based on distributed edge cloud collaboration, and relates to the technical field of data processing, and the method comprises the steps: building a domain knowledge graph, carrying out generative adversarial completion, carrying out cross-modal semantic alignment based on an attention mechanism, carrying out knowledge reasoning, dynamically adjusting a sampling strategy, and cooperatively scheduling a sensor. According to the method, through semantic enhancement and dynamic sampling strategy optimization, the accuracy and the real-time performance of multi-modal data fusion are improved, the system resource consumption is reduced, and efficient data processing under edge-cloud collaboration is realized.

The invention relates to the technical field of space planning, and discloses a territorial space planning multi-source data fusion processing method and system, and the method comprises the steps: carrying out the format analysis and semantic annotation of multi-source territorial space data, and obtaining the standard territorial space data of territorial planning; performing hierarchical feature extraction on the standard territorial spatial data to obtain spatial features and attribute features of territorial planning; performing adaptive feature fusion on the spatial features and the attribute features to obtain a multi-semantic fusion feature map of territorial planning; constructing a spatial constraint rule base of territorial planning based on a use control rule and an ecological protection red line of territorial planning; based on a spatial constraint rule base, resolving conflict pattern spots in the multi-semantic fusion feature map, and performing semantic enhancement on the resolved multi-semantic fusion feature map to obtain an optimized fusion result; performing visual rendering on an optimization fusion result to obtain an auxiliary decision graph; according to the invention, the efficiency of data fusion processing in territorial space can be improved.

The invention relates to the technical field of semantic processing, in particular to a context-aware SQL (structured query language) generation method based on table field semantic enhancement, which comprises the following steps of: acquiring financial management and investment combination data of a user and mode information of a background database, constructing a mixed semantic index database, receiving natural language query input by the user, and generating a query result. Performing intention judgment on the query by utilizing the lightweight intention classification model, and if the intention is judged to be matched, calling a parameterized SQL template bound with the query intention and filling parameters to generate a final SQL query; if it is judged that the query intention is an exploration type intention, executing a two-stage SQL generation process, including generating an SQL skeleton according to the query intention, performing target type field recall based on the SQL skeleton, and filling the recalled field into the SQL skeleton to generate a final SQL query; and monitoring the execution performance of the final SQL query, and updating the query popularity metadata and the calculation cost metadata. According to the method, the SQL generation efficiency is improved through intelligent shunting and self-optimization.

The invention provides a fault inference analysis method and system based on a large language model, and the method comprises the steps: firstly obtaining a multi-source operation and maintenance data set of a to-be-diagnosed system, including a structured performance index, a semi-structured service log and unstructured text description data, carrying out the semantic enhancement of the multi-source operation and maintenance data set, and carrying out the semantic enhancement of the multi-source operation and maintenance data set; obtaining a semantic data unit containing entity, relation and attribute semantic tags, constructing a semantic association network based on the semantic data unit, calling a pre-trained large language model to carry out root cause reasoning analysis on the network, generating a candidate root cause set sorted according to confidence, and carrying out root cause reasoning analysis on the candidate root cause set; and finally, according to the candidate root cause set, generating an operation and maintenance decision instruction containing an entity operation sequence and a priority sequence, and sending the instruction to a system management terminal to trigger an automatic repair process. Therefore, the operation and maintenance efficiency and reliability of the system can be improved.

The invention discloses an analysis method and device for screening a target customer group, equipment and a medium, and relates to the technical field of customer data analysis. The method comprises the following steps: constructing registered user behavior data into a triple graph structure comprising user nodes, behavior nodes and entity nodes, and injecting domain knowledge for semantic enhancement; 24 hours are divided into periodic time periods, time period embedding vectors are generated, and Transform modeling cross-time behavior dependence is sensed through the time periods. According to the method, a triple graph structure is constructed, domain knowledge is injected, periodic time period modeling and multi-modal feature fusion are combined, behavior semantic association and time sequence dependence are deeply mined, and the effect of capturing hidden demands of a user is achieved; customer layering is optimized through local multi-source data cross validation, four-level division is defined, reinforcement learning and dynamic threshold decision are associated, and the effect of improving layering precision is achieved.

The invention provides a legacy system-oriented large-model-driven API document automatic generation system, belongs to the crossing field of artificial intelligence and software development, and provides a multi-modal data fusion and closed-loop verification mechanism aiming at the defects of a traditional API document generation method in the aspects of semantic comprehension, dynamic context capture and multi-technology stack adaptation. A code static feature and a dynamic track during operation are analyzed through a multi-source data acquisition module, and an interface semantic feature is extracted in combination with a field self-adaptive large model of a semantic enhancement analysis module; deducing an implicit service rule by fusing static / dynamic characteristics through a graph neural network, and generating a standardized document conforming to an OpenAPI specification through a parameterized template generative adversarial network (PT-GAN); and finally, performing three-level verification and closed-loop optimization through a sandbox environment. The method supports a heterogeneous system of 16 programming languages such as Java / C + + / Python, interface version changes can be automatically recognized, document patches are generated, the problems of missing and outdated system documents and low maintenance efficiency are solved, and maintainability and integration efficiency of enterprise-level systems are remarkably improved.

The invention discloses a multi-mode fusion product document and source code association retrieval method based on a knowledge graph, and relates to the technical field of software engineering and artificial intelligence. The method comprises the steps that source codes are preprocessed, and code structure information and business semantics are mapped in combination with a predefined business term dictionary; performing controlled induction on a code file and a product document by utilizing a large model, extracting business terms, logic intentions and a subject relationship, fusing with original codes, and establishing a vector retrieval index system; further analyzing a code structure by using an abstract syntax tree, and extracting an entity and a calling relationship; semantic enhancement and relation normalization are performed in combination with the large model, entities and relations are stored in a graph database, and a knowledge graph is formed; and performing parallel processing on user query based on a full-text retrieval index, a vector retrieval index system and a knowledge graph, and finally generating a product concept. According to the method, the retrieval speed, the semantic depth and the logical reasoning ability can be considered at the same time, and the retrieval accuracy is improved.

Mechanisms are provided for automatically generating semantical enhanced metadata for a structured data structure. Multi-task machine learning training is performed, based on data comprising separate sets of training data samples for each of a plurality of semantic metadata enhancement tasks, of a base artificial intelligence (AI) computer model to thereby generate a fine-tuned AI computer model trained to specifically generate semantically enhanced metadata for structured data structures. A prompt is received that specifies a structure of an input structured data structure and requests a semantic metadata enhancement task from the plurality of semantic metadata enhancement tasks. The fine-tuned AI computer model processes the prompt to generate semantically enhanced metadata for the structure of the input structured data structure and provide it to a downstream computing system for performing a downstream computing operation based on the semantically enhanced metadata.

The invention discloses a government affair data automatic classification and grading method, and relates to the technical field of data management and information processing. According to the method, data of different sources and formats are converted into structured formats by adopting a regular expression and a pattern matching technology, and the consistency and accuracy of the data are improved by means of a machine learning algorithm, data quality detection, anomaly correction and the like; by constructing a government domain ontology and a knowledge graph and combining a natural language processing technology, semantic classification is effectively carried out on government affair data, overlapping and uncertainty between categories are solved, robustness and accuracy of classification decision are further improved through an integrated learning algorithm, high efficiency and reliability of classification are ensured, and the method is suitable for large-scale popularization and application. By establishing a data grading dynamic adjustment and update mechanism and combining real-time data monitoring, sensitivity evaluation and automatic adjustment of access control rules, the flexibility and security of data management are ensured.

The invention discloses a fine-grained zero-sample medical image classification method based on cross-modal feature alignment, and the method comprises the steps: 1, carrying out the partitioning of a full-section pathological image, and extracting the features of a local image block; 2, a cross-modal alignment module is used for designing a local window attention mechanism to enhance space interaction between image blocks; the semantic enhancement module is used for constructing a pathology prompt template based on a large language model to generate fine-grained category description, and expanding the distance between categories in a semantic space; and 4, performing weighted fusion on the image block features through coordinate sensing, and generating final slice-level classification prediction. According to the invention, through multi-scale space interaction of the cross-modal image block alignment module and semantic enhancement of the semantic refinement module based on the visual language model, the classification precision of the fine-grained medical image is significantly improved, and the limitation of the existing method on feature alignment and semantic differentiation is effectively solved; and an efficient solution is provided for zero-sample medical image classification.

According to the method and device for generating the SQL statement based on the natural language, the equipment and the storage medium provided by the invention, the query instruction input by the user is received, and the query instruction is the natural language; performing semantic analysis on the query instruction; performing semantic vector coding on the query instruction, and performing similarity retrieval in a preset vector database to obtain semantic enhancement information related to the query instruction; filling a preset structured prompt template with the semantic analysis result and the semantic enhancement information to obtain prompt input information; and inputting the prompt input information into a large language model to generate an SQL statement. According to the method, semantic analysis and vector coding are performed on the natural language instruction of the user, and semantic enhancement is performed in combination with the preset vector database, so that the generation process has context semantic support, and the integrating degree of the generation result and the intention of the user is effectively improved.