151 results about "Knowledge structure" patented technology

The invention discloses a declarative knowledge construction method and device for semantic and situational knowledge collaborative modeling, computer equipment and a readable storage medium, and relates to the field of data processing.The method comprises the steps that firstly, a multi-modal document is analyzed, a chapter abstract is extracted, and structured content is obtained; entities, events and multi-modal knowledge points are extracted from the structured content, and cross-modal fusion is carried out on the entities, the events and the multi-modal knowledge points; carrying out anaphora resolution based on the fused knowledge points, and constructing a double atlas containing a knowledge atlas, a affair atlas and a four-dimensional relation triple; clustering the double maps to obtain a theme community, and performing association mapping on the community, the triple and the entity event, the chapter abstract and the multi-modal knowledge point to form association knowledge; vectorizing the associated knowledge and establishing a vector knowledge index; and carrying out compression ratio and accuracy evaluation on the knowledge through an evaluation system, and feeding back and optimizing the whole knowledge construction process. According to the method, multi-modal knowledge deep fusion and semantic scene collaborative modeling are realized, and the knowledge structuring degree and the application reliability are improved.

The invention discloses a large-model-driven automatic knowledge graph construction method based on a confidence feedback mechanism, and aims to improve the structural accuracy and semantic consistency in a structured triple generation process, and perform structural constraint guidance by using a few-sample prompt mechanism and a cross validation mechanism of a heterogeneous large model. And the control capability of the large language model on the triple format is enhanced, so that format offset and semantic redundancy in the generation process are reduced. And meanwhile, a multi-dimensional confidence evaluation system is constructed, model consensus judgment, semantic rationality analysis and knowledge consistency verification are fused, and refined quantification and screening of triple quality are realized. According to the method, a confidence backtracking feedback strategy is introduced, a generation-verification-optimization closed-loop process is constructed, the expression and correction capability of the system on a complex knowledge structure is enhanced, the dependence on an external API is effectively reduced, the consumption of computing resources is reduced, and the operation efficiency of the system and the feasibility of engineering deployment are remarkably improved.

The invention relates to the field of semiconductors, in particular to an answer generation method and device based on a semiconductor knowledge base and a medium. The method comprises the steps of performing data association on structured knowledge according to a semiconductor domain knowledge structure to construct a class of knowledge bases; performing data recombination on the unstructured knowledge according to the layout so as to construct a second-class knowledge base; a query question is received, retrieval is executed in the first-class knowledge base and the second-class knowledge base based on a preset retrieval model, and a plurality of related knowledge fragments are obtained; determining a first fusion weight between the knowledge fragments of the same knowledge type based on the relevancy between each knowledge fragment and the query question and the update time of each knowledge fragment; determining an optimal knowledge type according to the group feature information, and determining a second fusion weight between different knowledge types according to the optimal knowledge type; and based on the first fusion weight and the second fusion weight, obtaining a reference answer according to the plurality of knowledge fragments. And the requirements of the semiconductor field on information comprehensiveness and answer accuracy are considered.

The invention relates to the technical field of online education, and discloses an online course learning management method based on a knowledge graph. The method comprises the following steps: acquiring multi-modal learning behavior data of a learner, and extracting a deep learning state vector reflecting knowledge understanding depth, learning input degree and cognitive confusion through semantic fusion; and dynamically calculating and updating the logical relationship strength among the knowledge points in the course knowledge graph by using the vector, so that the knowledge structure can adaptively evolve along with the actual cognitive state of the learning group. And generating a real-time personalized learning path based on the updated knowledge graph and the current state vector of the learner. Meanwhile, according to cognitive confusion features in the state vector, intervention measures such as pushing of remedial resources, adjusting of content sequence or starting of self-adaptive testing are triggered in real time. According to the method, the dynamic optimization of the knowledge graph and the accurate and immediate response of learning intervention are realized, and the adaptability and management efficiency of online learning are improved.

The invention provides a knowledge structured extraction method based on a multi-modal large model, and relates to the technical field of data processing. Comprising the steps of determining to-be-extracted attribute information according to a data extraction requirement, and generating a structured data model according to the to-be-extracted attribute information; according to the structured data model and a preset extraction strategy, performing data extraction on a to-be-processed original multi-modal file to obtain a plurality of extraction results; merging the plurality of extraction results to obtain a merged extraction result; and verifying the combined extraction result to obtain a target extraction result. According to the method, in knowledge extraction through a multi-modal large model, through an extraction strategy of combining multi-round extraction with staged extraction, the data volume of one-time extraction of the model can be reduced, data extraction omission is avoided, meanwhile, staged extraction enables the model to be gradually progressive from coarse to fine and from global understanding to field-level fine extraction, context loss is avoided, and the knowledge extraction efficiency is improved. And the precision of the extraction result is improved.

System and method for using knowledge fabric based on knowledge ontology, designed for deep language understanding and mechanistic causal reasoning, and meta-knowledge repository for auditable question answering. The method includes receiving an input text from a user, building a knowledge graph that represents real world facts and associations in the form of contextually tagged and weighted knowledge propositions, in multiple knowledge domains. The knowledge graph in combination with causal path knowledge and metadata describing digital sources containing answers constitutes the knowledge fabric. The method includes resolving ambiguity and determining actual intent of the user for the input text, from a plurality of interpretations of intent for sentences using the knowledge graph in conjunction with logical inference to achieve deep natural language understanding. The method includes finding / delivering response to the input request as to why / how unknown factors resulted in known outcome, or what outcomes are likely given known causal factors.

The invention relates to the technical field of education science and technology recommendation systems oriented to personalized learning path optimization, and particularly discloses an education science and technology recommendation system oriented to personalized learning path optimization. The method aims at solving the problems that an existing recommendation system is difficult to dynamically perceive a cognitive state, knowledge structure semantics and dependency relationships are ignored, and the recommendation precision is low due to data sparsity. The system comprises a multi-source data acquisition and fusion module, a dynamic cognitive state evaluation module, a knowledge graph construction and semantic enhancement module, a path generation and optimization decision module and a self-adaptive execution and feedback adjustment module. Through multi-source data fusion, real-time cognitive state quantification, knowledge graph semantic modeling, multi-target optimization path generation and closed-loop feedback adjustment, accurate recommendation of personalized learning paths is realized, and the continuity, rationality and educational effectiveness of the paths are effectively improved.

The invention provides a cloud-edge collaborative heterogeneous graph neural network vehicle re-identification method, and relates to the technical field of intelligent traffic. The method comprises the following steps: constructing a knowledge structure through a multi-modal heterogeneous graph; extracting a multi-modal semantic relationship through a heterogeneous graph neural network to construct a cloud teacher model; in the method, a dynamic knowledge distillation mechanism driven by feature clustering is introduced to carry out knowledge fine-grained migration to generate a lightweight student model. Experiments are verified on VeRi-776, CityFlow-ReID and a self-built traffic data set, and results show that under the conditions that model parameters are compressed by 63% and a video memory is reduced by 64%, the total precision loss of a student model does not exceed 5%, and the reasoning speed reaches 213FPS. Compared with an existing traditional baseline method, the HGKDF has significant statistical advantages in RMSE and MAE indexes, is superior in training duration and video memory overhead, and is suitable for constructing the deployment of an integrated traffic large model system oriented to city-level intelligent interactive decision and safety monitoring.

The invention relates to the technical field of artificial intelligence and data fusion, in particular to a knowledge graph-based multi-modal data fusion computing system, which comprises a multi-modal data source interface module, a preprocessing module, a fusion alignment module, a knowledge graph module and a reasoning module, different modal features are mapped to a unified semantic space based on a Riemannian manifold theory, cross-modal information interaction is realized through a geometric perception attention mechanism on manifold, and uncertainty is quantified based on manifold entropy. The knowledge graph module provides semantic constraint to guide a fusion process and receives a fusion result to update a knowledge structure, the reasoning module combines fusion features and uncertainty evaluation to perform reliability sorting and interpretation information generation, the system improves the accuracy, reliability and interpretability of multi-modal data fusion, the fusion accuracy is improved by 15%-20%, and the system is suitable for popularization and application. And the cross-modal semantic alignment error rate is reduced by more than 30%.

The invention relates to the technical field of knowledge tracking, and discloses a graph enhanced double-memory collaborative knowledge tracking model based on an ACT-R cognitive architecture. Comprising a static knowledge structure coding module based on hypergraph projection, a batch-level dynamic learning track construction and coding module, a cross-graph gating fusion mechanism, a sequence modeling module and an expert hybrid prediction module. According to the method, long-term stable structured semantic association between concepts in declarative memory is modeled through a static knowledge structure diagram, a dynamic learning trajectory diagram based on batch reconstruction is designed to accurately capture an evolution rule of a behavior sequence in programmed memory, and on the basis, a cross-diagram gating fusion mechanism and a hybrid expert mechanism are introduced, so that the evolution rule of the behavior sequence in the programmed memory is accurately captured. And self-adaptive fusion and multi-path decision of double-graph features are realized.

The invention provides an engineering carbon emission factor dynamic calculation and traceability analysis method and system, and belongs to the field of engineering construction. The method comprises the following steps: acquiring multi-source heterogeneous data of the whole engineering construction process, and preprocessing the multi-source heterogeneous data to form a data set supporting knowledge modeling and computational analysis; constructing a semantic knowledge structure in the field of carbon emission factors in the whole engineering construction process by utilizing a knowledge graph technology; carrying out dynamic calculation on the carbon emission factor and correcting the weight; and carrying out visual analysis on a dynamic calculation result and a correction result to complete dynamic calculation and traceability analysis on the engineering carbon emission factor. According to the method, the defects in a carbon emission accounting system in the existing engineering construction field are overcome.

The invention provides a clinical decision knowledge graph construction method and system, and the method comprises the steps: extracting standardized entities corresponding to diseases, symptoms and diagnosis and treatment elements from medical knowledge data; constructing a clinical concept knowledge graph for representing a medical concept logic relationship and a causal relationship according to the semantic association relationship and the causal dependency relationship among the standardized entities; a diagnosis event, an examination event and a treatment event related to the patient are extracted, link evidences among the events are determined based on the event chain relation among the events, and a clinical event knowledge graph used for representing the disease course evolution process of the patient is constructed according to all the link evidences; and performing knowledge element fusion based on an entity association relationship between the clinical concept knowledge graph and the clinical event knowledge graph, and generating a target knowledge graph for clinical decision analysis. By adopting the scheme of the invention, the cross-map fusion of the static medical concept knowledge and the dynamic disease course event chain relationship can be realized, and the clinical decision knowledge structure with the reasoning ability can be constructed.

The invention relates to the technical field of intelligent education, in particular to a personalized learning path generation method and system driven by a dynamic knowledge graph. The method comprises the steps of collecting and processing multi-modal learning behavior data of a learner to construct and update a dynamic knowledge graph reflecting a knowledge mastering state and knowledge point association in real time; a double-engine diagnosis mechanism combining large model deep reasoning and knowledge graph real-time verification is adopted, and cognitive weak points and knowledge structure defects of learners are accurately recognized; and on the basis of a diagnosis result, a personalized learning path adaptively matched with the cognitive state of the learner is generated through multi-agent collaborative decision, and closed-loop optimization is performed on a knowledge graph and a path planning strategy according to real-time feedback of a path execution effect. According to the invention, the defects of the traditional adaptive learning system in the aspects of diagnosis accuracy, individuation degree and dynamic adaptability are effectively overcome, and accurate, efficient and continuously optimized individualized learning experience can be provided for students. According to the method, through deep fusion of double-engine diagnosis and the dynamic knowledge graph, the accuracy and reliability of cognitive state diagnosis are remarkably improved, and the illusion problem of a large model in the STEM field is solved; through a multi-agent collaborative decision-making mechanism, high personalization and dynamic adaptability of a learning path are realized; finally, a teaching closed loop with a self-optimization capability is formed, and the intelligent level and the teaching efficiency of the self-adaptive learning system are essentially improved.

Provided is a method and system (108) for building and leveraging a knowledge fabric (110) in a Software Development Lifecycle (SDLC). A plurality of SDLC artifacts are received from a plurality of heterogeneous data sources (102). The plurality of SDLC artifacts are then correlated to build an end-to-end correlation and are clustered to generate an SDLC knowledge fabric (110). This includes extracting semantic and contextual data from the plurality of SDLC artifacts using Natural Language Processing (NLP) and deep text analytics and transforming the extracted semantic and contextual data to knowledge graphs. One or more actionable items (112) are then derived using the SDLC knowledge fabric (110) and the one or more actionable items (112) are used to improve overall process efficiency and accelerate software delivery in the SDLC.

The invention relates to the technical field of deep learning, in particular to an intelligent prospecting model construction method based on a knowledge graph and data deep learning, which comprises the following steps: collecting multi-source geological data to perform time decomposition and spatial stratified sampling to extract features, calculating an attachment weight through semantic coding to construct a geological knowledge structure, and constructing a geological prospecting model; the method comprises the steps of extracting spatial-temporal features in a convolution mode, combining with semantic deviation degree weighted fusion to generate a hierarchical feature coupling result, carrying out aggregation analysis on spatial-temporal correlation to extract consistent components, judging a metallogenic response relation through conditional probability reasoning, fitting a model, calculating deviation, adjusting weights, analyzing semantic consistency, and carrying out classification and aggregation to generate an intelligent prospecting optimization result. The feature precision is improved through time decomposition and spatial stratified sampling of multi-source geological data, data association is enhanced through semantic coding, time-space consistency is enhanced through convolution extraction and semantic fusion, multi-scale features are balanced through hierarchical coupling, the ore-forming relation judgment accuracy is improved through probabilistic reasoning, and the result precision and stability are remarkably improved.

The invention discloses a document processing method and a related device, and relates to the technical field of data processing. Comprising the following steps: analyzing an original document to obtain a text sequence corresponding to the original document; processing the text sequence through a large language model to generate a directory list corresponding to the text sequence; segmenting the text sequence to obtain a plurality of text blocks; based on the plurality of text blocks, a preset fusion rule and a large language model, determining a plurality of target semantic text segments and titles, starting point positions and ending point positions of the target semantic text segments; constructing a hierarchical knowledge structure based on the target list, the plurality of target semantic text segments, and titles, starting point positions and ending point positions of the target semantic text segments; the hierarchical knowledge structure has the characteristics of structuralization, traceability and semantic coherence, and the knowledge retrieval accuracy and efficiency can be improved by storing the hierarchical knowledge structure into a knowledge base.

A hierarchical personalized federal learning method based on cross-client prototype clustering relates to the field of artificial intelligence and distributed machine learning, and comprises the following steps: a client maps a local sample to a semantic prototype space for information compression, and generates a category prototype matrix; the server receives the prototype matrix uploaded by each client, dynamically clusters and aggregates the prototype matrix, constructs a multi-level knowledge structure including a cluster-level expert model and a global semantic prototype, and maintains the global semantic prototype through index moving average; the client receives the cluster-level expert model, the global model parameters and the global semantic prototype from the server, and carries out a new round of local training on the basis; the client integrates local data and multi-level knowledge issued by the server to optimize three types of loss updating models; through loop iteration, the local model of the client gradually realizes personalized adaptation and global alignment. According to the method, the communication efficiency, the privacy protection safety, the model convergence speed and the generalization ability are improved.

The invention belongs to the technical field of emotion recognition, and particularly discloses a big language model enhanced dialogue causal emotion implication method and system, and the method comprises the steps: extracting common knowledge corresponding to the identity of a speaker of each dialogue, and carrying out the coding and aggregation of the speech-level feature representation and the common knowledge through a graph structure, generating a first utterance feature representation with enhanced common knowledge; inputting the utterance-level feature representation into a multi-head self-attention module with relative position perception, and generating a second utterance feature representation with an enhanced dialogue structure; and splicing the utterance-level feature representation and the knowledge structure interaction feature to obtain a final utterance complementarity feature representation, and inputting the utterance complementarity feature representation into a multi-layer perceptron to obtain a prediction result of the emotion causal relationship. According to the method and the device, the emotion causal relationship prediction performance of the model in a complex dialogue scene can be improved, and the emotion causal relationship prediction accuracy is improved.

The invention provides a multi-modal large model combined question analysis and explanation generation method and system, and relates to the technical field of multi-modal learning, and the method comprises the steps: carrying out the standardization processing of a multi-modal input question, and obtaining the standardized question data; separating structured question information to perform deep feature extraction, driving three-level knowledge structure linkage matching of the question solving thought library, and generating a plurality of initial question solving paths; performing knowledge blind area coverage screening, and positioning a target problem solving path; recursive knowledge point reinforcement is carried out, and a non-blind area credible problem solving chain is generated; step-by-step analysis logic derivation is carried out, and a target analysis logic framework is output; and performing cross-modal directional rendering according to real-time explanation modal selection, and delivering and outputting a multi-modal analysis explanation stream. The technical problems that in the prior art, deep understanding of personalized requirements and knowledge mastering levels of users is lacked, customized answers cannot be provided for the users, and the learning effect of the users and tool practicability are affected are solved.

A knowledge-creation assistance device (100) comprises: a knowledge-structuring unit (111) that, on the basis of a measurement analysis result of a sample outputted from an analysis device, generates pre-complementary structured knowledge that is configured to include one or more items pertaining to measurement; a missing-knowledge estimation unit (113) that adds an item to the pre-complementary structured knowledge to generate post-complementary structured knowledge; and a knowledge-editing unit (114) that receives an editing instruction for the post-complementary structured knowledge and generates confirmed structured knowledge. The missing-knowledge estimation unit (113) adds the item to the pre-complementary structured knowledge by using an estimation model that is a machine learning model in which an item included in the pre-complementary structured knowledge is used as an explanatory variable, and an item included in the confirmed structured knowledge is used as an objective variable.

The application relates to a knowledge-driven multi-agent cooperative reactor scheme demonstration system and a design method, medium and equipment thereof, the system comprising: a knowledge internalization unit for converting unstructured and semi-structured documents into a dynamic knowledge source which can be queried and utilized by a model in real time; a knowledge structuring unit for extracting core entities, relationships and attributes from the knowledge source and constructing a professional knowledge graph of a reactor design field; and a knowledge application unit for constructing intelligent agents and a collaborative working mechanism of multi-professional intelligent agents based on the knowledge source and the knowledge graph, and constructing an intelligent question and answer interface. Through automatic knowledge management and intelligent agent collaborative work, the application significantly reduces the time and effort of manual intervention and improves the efficiency of reactor scheme demonstration.

The invention discloses a text question-answer pair data set generation method and device, a medium and electronic equipment, and relates to the field of natural language processing. The method comprises the steps of performing hierarchical standardization analysis on a to-be-processed text, and determining a chapter logic hierarchical structure; extracting candidate knowledge points based on the chapter logic hierarchical structure, and reversely aggregating the semantic context by taking the candidate knowledge points as a core to generate a structured tetrad; positioning each structured tetrad in the to-be-processed text to obtain a text position corresponding to the structured tetrad; based on the similarity between the knowledge points in different structured tetrads, aggregating the structured tetrads meeting the similarity requirement and the corresponding text positions, and generating an index table corresponding to the knowledge points; and based on the index table, generating a question and answer pair data set corresponding to the to-be-processed text. Through an index table for associating knowledge points dispersed in different hierarchical units, the defect that a traditional method is limited to context and cannot reflect the whole knowledge structure is overcome.

The application discloses a knowledge graph-based event clue multi-dimensional knowledge base construction method and system, which comprises the following steps: collecting and preprocessing multi-source event clues, constructing a standardized knowledge graph, and generating a multi-dimensional knowledge base; performing graph layering based on improved K-core decomposition, identifying high-cohesion event groups, forming K-core subgraphs and boundary structures; setting walk parameters of subgraphs with different K values, formulating in-and-out community walk strategies, and updating knowledge structures; performing multi-round layering walks, generating event node path sequences covering in-and-out community structures; aggregating walk sequence features, generating clue vectors, completing clustering, reasoning and completion, and optimizing the knowledge base; triggering graph layering and walks when new clues are added, and periodically or real-timely updating the multi-dimensional knowledge base structure. The application realizes the structured expression and efficient aggregation of multi-source event clues by introducing K-core decomposition and layering random walk methods, and constructs a multi-dimensional knowledge base which can dynamically evolve to support intelligent analysis and reasoning of complex events.

The invention relates to the field of semiconductors, in particular to an answer generation method and device based on a semiconductor knowledge base and a medium. The method comprises the steps of performing data association on structured knowledge according to a semiconductor domain knowledge structure to construct a class of knowledge bases; performing data recombination on the unstructured knowledge according to the layout so as to construct a second-class knowledge base; a query question is received, retrieval is executed in the first-class knowledge base and the second-class knowledge base based on a preset retrieval model, and a plurality of related knowledge fragments are obtained; determining a first fusion weight between the knowledge fragments of the same knowledge type based on the relevancy between each knowledge fragment and the query question and the update time of each knowledge fragment; determining an optimal knowledge type according to the group feature information, and determining a second fusion weight between different knowledge types according to the optimal knowledge type; and based on the first fusion weight and the second fusion weight, obtaining a reference answer according to the plurality of knowledge fragments. And the requirements of the semiconductor field on information comprehensiveness and answer accuracy are considered.

The application relates to the technical field of data governance and artificial intelligence, in particular to a modeling and retrieval enhancement method and system for multi-source data and field knowledge fusion. The method comprises the following steps: acquiring multi-source heterogeneous metadata and power grid field standardized documents, and performing metadata extraction, cleaning treatment and knowledge structuring to form a standardized data set; based on a power grid field ontology model, the standardized data set is instantiated, mapped and associated to build a knowledge fusion model; the semantic analysis of a user natural language query is performed, business entities and constraint conditions are extracted, and mixed retrieval is performed to obtain candidate data assets; the knowledge fusion model is used for associated expansion and blood relationship tracing, the results are confidence evaluated and structured, retrieval enhancement results are generated and output. The application realizes semantic analysis of a user natural language query, mixed retrieval and associated expansion, thereby improving the accuracy, correlation and result reliability of power grid data retrieval.

The application provides an engineering carbon emission factor dynamic calculation and traceability analysis method and system, and belongs to the field of engineering construction. The method comprises the following steps: acquiring multi-source heterogeneous data of the whole process of engineering construction, and pre-processing the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis; constructing a semantic knowledge structure of the carbon emission factor field of the whole process of engineering construction by using knowledge graph technology; dynamically calculating the carbon emission factor and correcting the weight; and visualizing the dynamic calculation result and the correction result to complete the dynamic calculation and traceability analysis of the engineering carbon emission factor. The application solves the deficiencies existing in the current carbon emission accounting system in the field of engineering construction.

The invention discloses a grouting construction intelligent control system and method based on double-liquid slurry, and the method comprises the steps: obtaining multi-source state data formed in a grouting construction process, and obtaining a fluid state formed in a double-liquid conveying process; inputting the multi-source state data and the fluid state into a construction knowledge structure; identifying a field dependency relationship between the multi-source state data and the fluid state, and establishing a dynamic coupling relationship graph for reflecting construction process logic; and performing hierarchical deconstruction on the construction knowledge structure according to the dynamic coupling relation graph, extracting a step identifier corresponding to the current construction stage, and generating a control sequence matched with the step identifier. Through dynamic modeling and self-adaptive control, the whole-process intelligent management of the double-slurry grouting process is realized, and the construction precision, stability and real-time response capability are remarkably improved.

The embodiment of the invention discloses an agent knowledge structure determination method and device, equipment, a medium and a product. The method comprises the steps that scene data and task data of a target agent in a current operation task scene are acquired; inputting the scene data and the task data into an agent knowledge structure recommendation model to obtain at least one recommendation knowledge structure corresponding to the target agent; the recommended knowledge structure is a knowledge structure defined in a preset knowledge structure library; determining a scoring result corresponding to the recommended knowledge structure by using a preset scoring algorithm; and according to the scoring result, determining a target knowledge structure adopted by the target agent in the current operation task scene from the recommended knowledge structure. According to the technical scheme, the skills of the intelligent agent are accurately improved, and the ability of the intelligent agent to adapt to different industries and scenes is improved.

The invention discloses an implementation method and system for AI and Agent agents to carry out autonomous team-forming social contact, and relates to the technical field of AI and Agent agents, and the implementation method comprises the steps: generating a cognitive state vector with a variable time sequence based on a knowledge structure, a reasoning mode and decision preference of the agents, and forming a multi-dimensional semantic representation representing individual cognitive characteristics; calculating cognitive similarity among the agents according to the cognitive state vectors, and when the cognitive similarity exceeds a preset threshold value and the average resonance intensity of the group reaches a critical condition, triggering the multiple agents to spontaneously aggregate into a temporary cooperative community without central control; in the temporary collaboration community, the social identity of each agent is determined based on the trust strength, the communication influence and the task contribution degree among the members, the social identity comprises at least one of a leader, a coordinator, an innovator or an executor, and identity state transition is modeled through a Markov decision process.

The invention relates to the technical field of natural language processing, and discloses a synonym retrieval optimization method in RAG, which comprises the following steps of: S1, constructing a semantic topological graph of which nodes have topological entropy weights; s2, based on a semantic topological graph; s3, calculating topological coupling scores of the candidate synonyms in the semantic topological graph; s4, performing retrieval based on the extended query; s5, judging the cohesion of the answers by evaluating the aggregation topological entropy of the answers of the draft in the semantic topological graph; and S6, using the final context after iterative optimization. According to the method, the knowledge structure is accurately modeled by adopting a semantic topological graph construction technology with topological entropy weights on the nodes, and the semantic relationship between the knowledge can be clearly reflected. Compared with the prior art, the method has the advantages that the defect that a traditional knowledge representation method cannot effectively capture subtle semantic relations is overcome, and richer background information is provided for semantic understanding.