1812 results about "Semantic vector" patented technology

The invention discloses a multi-modal semantic and physical law driven remote sensing image generation method, belongs to the technical field of computer vision and remote sensing image generation, and aims to solve the problems of insufficient cross-modal semantic alignment, low reliability of a generation result and insufficient physical mechanism fusion. The four-stage method comprises the following steps: firstly, rejecting low-quality samples from original data and unifying a spatial scale; then, extracting a multi-modal semantic vector by adopting a BLIP model and a CLIP model, and introducing a remote sensing physical rule to carry out vector optimization; then position coding and physical constraint conditions are embedded in the submerged space, and multi-source information joint modeling is achieved through a cross-modal encoder; and finally, by taking text description, physical priori knowledge and diffusion time steps as joint conditions, performing de-noising reasoning based on a Transform architecture, and completing back diffusion reconstruction by means of a trans-attention mechanism. According to the method, physical rationality and semantic consistency are improved, and a more reliable technical normal form is provided for remote sensing image generation in the fields of disaster monitoring, military simulation and the like.

The invention discloses a multi-modal knowledge-based automotive body innovative design system, which comprises a multi-modal data fusion module, a multi-modal data fusion module, a multi-modal data fusion module, a multi-modal data fusion module and a multi-modal data fusion module, wherein the multi-modal data fusion module is used for receiving text data, picture data, a three-dimensional CAD (Computer Aided Design) model file and an engineering symbol expression from an automotive body design process and is used for carrying out feature extraction and semantic alignment on input data of four modals; generating a unified semantic vector representation; the cross-modal knowledge mining and graph construction module is used for extracting multi-level entities and relationships from the unified semantic vector and constructing a dynamically weighted multi-modal knowledge graph; the large-model-driven multi-hop collaborative reasoning module is used for analyzing the multi-modal design requirement of a user, carrying out multi-hop reasoning on a knowledge graph, and outputting design parameter recommendation and an interpretable reasoning chain. The method aims at breaking through the limitation of an existing design system in the aspects of multi-modal processing and shallow semantic understanding, and deep fusion and intelligent application of multi-source heterogeneous design data are achieved.

The invention discloses an AI-based large-model-driven contract review and regulation interpretation method and system, and the method comprises the steps: S1, collecting a regulation and institute document, and carrying out the text extraction and semantic disassembly, and obtaining term information; s2, based on a LawCheckLM + BERT-CRF named entity recognition model, performing entity recognition and classification labeling on clause information, and storing recognized key information fields into a knowledge base; s3, encoding each piece of clause information into a semantic vector through an embedded model, and storing the semantic vector into a knowledge base; and S4, performing text extraction and semantic disassembly on the uploaded contract document to obtain clause information, repeating the steps S2-S3, retrieving similar semantic vectors of laws and regulations or institutional documents similar to the contract from the knowledge base as references, if the similar semantic vectors are not retrieved, taking Top-N laws and regulations or institutional documents with similar semantics as outputs, and marking the Top-N laws and regulations or institutional documents as required to be examined. The problems that an existing management system is difficult to adapt to regulation changes, complex contract review and cross-scene deployment are achieved, and the overall iteration period is long are solved.

The invention discloses a listed company operation risk early warning method based on multi-source auditing and text semantic fusion, and relates to the technical field of auditing, and the method comprises the steps: S1, crawling and converging multi-source heterogeneous data of listed company financial newspapers, auditing suggestions, supervision announcements, inquiry letters, news public opinions and market transactions; according to the method, unstructured texts are subjected to cleaning, blocking and semantic vectorization processing, each text segment is embedded into a high-dimensional semantic space, a vector index is established, a bottom-layer knowledge base of an RAG framework is formed, in the stage, it is ensured that the data structure is uniform, the source is traceable, standardized input is provided for subsequent semantic retrieval and modeling, and the reliability of the system is improved. S2, a query expression is constructed based on a target company, a time window and a risk topic, dense semantic retrieval and sparse BM25 retrieval methods are comprehensively used, a time decay and source credibility weighting mechanism is introduced, and the problems that a traditional method is single in data dimension and information is split are solved.

The invention provides an industrial injury auxiliary identification method and system based on dual-channel retrieval enhancement generation, and relates to the technical field of artificial intelligence and industrial injury auxiliary identification, and the method comprises the steps: obtaining multi-modal data of a wounded movement video, a medical image and a case text; fusing the semantic vectors of the image, the text and the video into a unified semantic representation vector; inputting the semantic representation vector into a dual-channel retrieval enhancement generation model, and after inputting the semantic representation vector into the dual-channel retrieval enhancement generation model, respectively entering a law and regulation structured knowledge graph retrieval path and a historical case semantic retrieval path; extracting the final representation of each node in the regulation knowledge graph through the regulation structured knowledge graph retrieval path, and performing regulation node path extension to obtain a regulation graph matching basis chain; the historical case semantic retrieval path calculates historical related cases through semantic similarity to obtain case core summary information. According to the invention, the auxiliary evaluation efficiency is improved, and the interpretability of the result is enhanced.

The embodiment of the invention relates to the field of artificial intelligence, and provides a model context protocol injection attack protection method and device based on dynamic semantic analysis, computer equipment and a storage medium, and the method comprises the steps: obtaining request data corresponding to a call request initiated by a user through a model context protocol, carrying out the preprocessing of the request data, obtaining the preprocessed request data; performing semantic vectorization on request text and context historical information in the request data through a lightweight bidirectional encoder representation model to output an initial risk score; correcting the initial risk score according to context historical information carried in a model context protocol to obtain a corrected final risk score; and performing hierarchical defense decision according to the final risk score, and determining risk grading information corresponding to each piece of request data so as to execute a protection action corresponding to each piece of risk grading information. By adopting the method, the accuracy of identifying the protocol injection attack can be improved.

The invention discloses a large-model knowledge retrieval method based on knowledge graph enhancement, which comprises the following steps: S1, collecting multi-source data, constructing an original knowledge triple set, and generating a knowledge graph; s2, inputting natural language query data, executing semantic analysis and intention recognition, and forming a query semantic vector and a structured query template; s3, performing combined convolution operation on the target entity node and the relation vector through an improved combined graph convolution network CompGCN to generate a candidate knowledge list and distribute confidence; s4, calculating the similarity between the query vector and the knowledge vector by utilizing a semantic embedding mechanism and DistilBERT acceleration to obtain a first retrieval result set and a credibility score; s5, fusing the two types of retrieval results to obtain a knowledge result set; and S6, generating an answer text according to the fused knowledge result set, and outputting a reasoning path, entity reference and a relation link. According to the method, the accuracy, the response speed and the knowledge reasoning transparency of complex query processing are improved.

The invention relates to a military training-oriented dynamic multi-modal knowledge graph retrieval method, which comprises the following steps of: acquiring a multi-source data set to generate a unified original event stream; based on the original event flow, preliminarily constructing a knowledge graph by adopting a Bayesian prior-based tetrad model, locally embedding and updating through a military training event incremental graph neural network, and dynamically re-estimating the confidence of nodes and edges through a Bayesian evidence propagation algorithm; a pre-training language model in the military field is adopted for analysis and semantic coding, a query semantic vector is generated, a retrieval module is constructed, and a retrieval result is output based on the knowledge graph; and constructing a military retrieval strategy optimization network based on a reinforcement learning framework, dynamically adjusting a retrieval strategy, writing back user feedback data, and optimizing node embedding and retrieval strategy parameters. According to the method, multi-source heterogeneous data can be integrated, a dynamic credible graph is constructed, retrieval accuracy, timeliness and self-adaption are improved, and military training decisions are supported.

The invention relates to the technical field of electrical digital data processing, and discloses a source code security vulnerability semantic detection method based on a large language model, which comprises the following steps: analyzing a source code to be detected to extract execution path constraint features, and constructing an orthogonal feature base vector sequence through orthogonalization feature extraction; inputting the source code to be tested into the large language model to obtain an initial semantic tensor; orthogonal projection is carried out on the initial semantic tensor to a code security constraint subspace constructed by an orthogonal feature basis vector sequence, weighted aggregation is carried out in combination with attention weight distribution information entropy, and a refined semantic vector is generated; according to the hidden logic offset vulnerability recognition method, business semantic noise is eliminated by utilizing a logic subspace projection mechanism, the association between a detection conclusion and code execution logic is established, and the precision of recognizing hidden logic offset vulnerabilities is improved.

The invention provides a knowledge base and business system collaboration method under an AI platform, and belongs to the technical field of AI platform digital data processing.The method includes the steps that triple semantic analysis is conducted on query by constructing a multi-level semantic vector representation module, a parallel data retrieval engine is started, vector retrieval, graph reasoning and real-time data pulling are executed at the same time, and the query efficiency is improved; establishing a dynamic confidence evaluation mechanism to evaluate the quality of the data source, executing a weight distribution algorithm based on reinforcement learning, dynamically calculating the weight of the data source according to a query type by adopting a graph convolutional network intelligent routing decision model, and implementing multi-source data fusion and consistency verification to solve data conflicts through a weighted voting mechanism. An intelligent result sorting and filtering system is established, a multi-dimensional evaluation strategy is adopted to output high-quality answers, a continuous learning and feedback optimization loop is constructed, system performance is continuously optimized through active learning and a graph shortest path algorithm, and the technical problem that knowledge base data and a service system cannot effectively and uniformly make decisions is solved.

The invention relates to the technical field of artificial intelligence, in particular to a self-organizing knowledge base construction method, system and device based on a multi-agent system and a storage medium, and the method comprises the steps: S1, monitoring a dialogue information flow, calculating the self-reply confidence coefficient of an agent, and if the self-reply confidence coefficient exceeds a preset dynamic threshold value, judging that a potential knowledge value exists and triggering an extraction request; s2, in response to the request, performing semantic coding on a dialogue fragment, extracting knowledge elements, and generating a structured knowledge unit by utilizing graph neural network modeling and relation calibration; s3, through a pre-training semantic coding model, mapping the multi-dimensional semantic coding model into a multi-dimensional semantic vector; s4, carrying out hierarchical clustering comparison and combination, and if a threshold value is exceeded, establishing a new classification and adjusting a knowledge base index; and S5, knowledge fingerprints are generated and compared, and fusion updating is carried out based on the reputation scoring model when semantics conflict or redundancy occurs. According to the method, unstructured dialogue high-precision knowledge extraction is realized, so that the knowledge base structure is dynamically self-organized according to semantics, multi-source knowledge is coordinated, and the knowledge management automation level and quality are improved.

The invention discloses a large model retrieval enhancement generation method and system, and the method comprises the steps: obtaining the comprehensive document data of a power grid field, carrying out the partitioning processing of the comprehensive document data, and obtaining the partitioned text data; performing deep analysis on the block text data to generate a thinking chain enhanced text; encoding the thinking chain enhanced text based on a hierarchical weighted encoding method to generate a thinking chain enhanced semantic vector; inputting the block text data into a pre-trained large language model to obtain a generated task perception representation vector; splicing the thinking chain enhanced semantic vector and the generated task perception representation vector to obtain a fusion vector, and constructing a vector database in the power grid field based on the fusion vector; responding to the text retrieval signal, obtaining question text data of the target user, analyzing the question text data to obtain a question fusion vector, comparing the question fusion vector with a vector database, and obtaining retrieval data of the question text data based on a comparison result.

The invention discloses an automatic software function testing and evaluating method based on a multi-modal large model, and particularly relates to the field of non-embedded software function testing and evaluating, which comprises the following steps: collecting software texts, images and structured data, generating corresponding feature vectors, aligning through a cross-modal comparison algorithm, and constructing a multi-modal testing and evaluating data set; deep features of all modes are extracted through a mode exclusive encoder, and a unified multi-mode function vector is output based on information entropy dynamic weighted fusion; constructing triple training data, and optimizing the multi-modal large model by combining a joint loss function with an enhanced training strategy; and finally, deploying the model at a cloud end and an edge node, carrying out real-time triggering test by docking a CI / CD process, and realizing functional integrity verification, interactive compliance detection and accurate defect positioning through semantic vector comparison, graph isomorphism rate calculation and cross-modal attention backtracking. According to the scheme, the test comprehensiveness and precision are improved, and the rapid iteration requirement of software is met.

The invention provides a full-text retrieval method and system fusing various types of documents, and relates to the technical field of information retrieval, and the method comprises the following steps: obtaining document representation through document content extraction and structure recognition, generating a cross-modal semantic vector by using word embedding and nonlinear transformation, constructing a hierarchical index and a cross-document association graph, and obtaining a full-text retrieval result; the basic correlation score is calculated after the query request is received, and the comprehensive score of the candidate content segments is calculated based on the association graph to determine the optimal retrieval result, so that unified representation and retrieval of heterogeneous documents are realized, the cross-document retrieval precision and relevance are improved, and the processing capability of a retrieval system on complex queries is enhanced.

The invention provides an intelligent question and answer method based on a preset multi-dimensional knowledge base and a large language model, and the method comprises the steps: receiving a natural language query, converting the natural language query into a query semantic vector, and recognizing a corresponding intention type and a first confidence coefficient; if the first confidence coefficient is higher than an intention threshold value and the highest similarity between the query semantic vector and a standard question semantic vector in a preset multi-dimensional knowledge base is higher than a matching threshold value, returning a standard answer; otherwise, retrieving a generated context based on the query semantic vector, fusing the user query and the generated context, inputting the fused user query and generated context into a large language model to generate a preliminary answer, checking fact consistency of the preliminary answer and a standard answer in the generated context to generate a credibility score, and obtaining a target answer when the credibility score exceeds a credibility threshold; and dynamically optimizing the system based on feedback data of the user to the target answer. The intelligent customer service system with controllability, flexibility and self-optimization capability is realized, and the semantic understanding depth and response accuracy of the system are improved.

The invention discloses an unmanned aerial vehicle multi-task collaborative planning method based on a large language model, and particularly relates to the technical field of path planning. Obtaining a task natural language description and extracting a task semantic vector; constructing a task semantic association graph and performing clustering to form a task cluster; collecting unmanned aerial vehicle state information to generate a state vector; calculating a task-unmanned aerial vehicle matching score based on a large language model, and constructing an initial task allocation matrix; introducing feasibility constraints and generating a feasible task allocation scheme through an optimization algorithm; combining an A * algorithm and a large language model to generate an initial path, and performing iterative optimization on the path through a semantic constraint loss function; in the task execution process, if task or communication changes are detected, task allocation and paths are dynamically reconstructed; the method has the technical advantages of strong semantic understanding, high planning robustness and excellent path adaptability, and is suitable for multi-unmanned aerial vehicle cooperative task execution in a complex dynamic environment.

The invention relates to the technical field of data analysis, and discloses a multi-modal time sequence anomaly analysis method, device, equipment and medium, and the method comprises the steps: collecting visual data, audio data and process text data, carrying out the preprocessing and standardization processing of different types of data, constructing a multi-modal data set with aligned timestamps, and storing the multi-modal data set in a database; the method comprises the following steps: extracting a time-frequency dynamic feature and a semantic vector feature, extracting a map structure feature, a time-frequency dynamic feature and a semantic vector feature, fusing the features by using a cross-modal attention mechanism to generate a fused feature vector, finally performing analysis processing based on the fused feature vector, and outputting an analysis result. According to the method, the multi-modal data set with consistent time is constructed, the structural features of various modals are extracted, and the cross-modal attention mechanism is introduced to realize deep fusion of the feature level, so that the problems of single information utilization and weak feature relevance of the existing detection means are solved, and the comprehensiveness of defect detection and the accuracy of fault diagnosis are improved.

The invention discloses an enterprise knowledge base retrieval and intelligent answering method and system based on a large language model. The method comprises the following steps: performing clause-level segmentation on an enterprise knowledge base document, associating document metadata to form structured knowledge entries, and establishing a keyword reverse index and a semantic vector index for the structured knowledge entries; analyzing the natural language query of the user, and performing multi-strategy expansion to generate an enhanced query expression and a query semantic vector; performing dual-channel mixed retrieval, performing duplicate removal, version filtering and weighted fusion sorting on a result, and generating a final candidate knowledge item list; and based on the candidate list and a predefined instruction, calling a large language model to generate a structured answer with complete traceability information. The method is compatible with an existing retrieval framework, precise understanding, knowledge point-level positioning, cross-document content integration and version consistency control of natural language problems are achieved, and the retrieval accuracy, answer availability and service intelligence level of an enterprise knowledge base are remarkably improved.

The invention relates to the technical field of artificial intelligence in the education industry, in particular to an intelligent composition quality evaluation method and system based on a large language model, and the method comprises the steps: carrying out the text normalization and semantic unit segmentation of a composition, extracting a semantic vector through a first large language model in combination with a context enhancement strategy, and positioning a semantic fracture risk position; recognizing composition core elements through a second large language model, and mapping the composition core elements back to the semantic unit sequence; constructing a demonstration logic diagram, extracting a core demonstration path and abstracting the core demonstration path into a logic role topological graph; in combination with a pre-constructed writing specification knowledge graph, comparing structural compliance, connection strength and an expected support relationship, identifying and demonstrating logic defects, and generating a global deduction item list; semantic clustering is carried out on illegal items to form an error label set, comprehensive weight is calculated in combination with historical data of students, and core weak items are positioned; according to the application, the logic analysis depth of intelligent evaluation of the argument is remarkably improved, and the pertinence and practicability of teaching feedback are improved.

The invention discloses a fusion semantic vector space mapping-based translation ambiguity term accurate matching method, which comprises the following steps of: S1, obtaining source language ambiguity terms, context texts and a target language candidate translation list, and extracting domain tags and term matching features to form a multi-modal data set; s2, using improved XLM-R model coding to generate term-level, sentence-level and translation-level semantic vectors; s3, training a dynamic mapping matrix based on a bilingual parallel corpus, and aligning source side vectors to a shared semantic space; s4, fusing the source-side basic vector and the multi-dimensional features through a double-channel attention fusion network, and generating source-side and translation-side comprehensive semantic vectors; s5, introducing term-context attention weight to correct cosine similarity; and S6, outputting an optimal translation through normalized sorting and part-of-speech secondary judgment. According to the method, multi-field ambiguous term accurate matching is realized, the term translation precision and efficiency in professional fields are improved, and the requirements of high reliability of term translation in the fields of medicine, machinery, computers and the like are met.

The invention provides a code quality adaptive evaluation and optimization method, system and device and a medium, and belongs to the technical field of computers. The method comprises the following steps: performing redundant information cleaning and standardization processing on an original code; selecting an adaptive parser to convert the processed code into an abstract syntax tree, and optimizing the abstract syntax tree; performing embedding processing on each node of the abstract syntax tree by using a pre-trained deep learning model to generate a node semantic vector, and performing aggregation, feature extraction and vector normalization operation to obtain a semantic vector representing code semantic features; extracting a dependency relationship from the abstract syntax tree to construct a program dependency graph, extracting node features by using a neural network model, and generating a dependency relationship analysis result; based on the semantic vector and the dependency analysis result, identifying a code potential problem by using an optimization algorithm and generating an optimization suggestion; codes are automatically modified according to optimization suggestions, the optimization effect is re-evaluated, and related models and algorithms are iteratively optimized according to feedback information.

The invention belongs to the technical field of semantic understanding systems, and particularly relates to a semantic understanding system based on a large language model.The semantic understanding system is characterized in that firstly, a data preprocessing module is used for conducting cleaning, denoising and cross-modal conversion on input multi-modal data such as texts and images, and standardized data is generated; a semantic feature extraction module extracts general semantic features by using a pre-training model, adapts to field requirements through dynamic learning rate fine adjustment, and outputs scenarized semantic vectors; then, a dynamic semantic-knowledge bidirectional fusion module adjusts token weight according to a dynamic semantic weight algorithm, realizes real-time alignment of semantics and a knowledge graph by means of a knowledge entity association strength algorithm, and a knowledge enhancement fusion module further optimizes knowledge weight and dynamically updates association; then, the semantic reasoning module performs multi-round reasoning based on fusion information, and evaluates the result reliability in combination with a confidence coefficient algorithm; and finally, the output and optimization module generates a structured result, and iteratively optimizes parameters of each module according to feedback data to complete a semantic understanding processing flow.

The invention discloses a knowledge graph question-answer interaction method and system based on artificial intelligence, and the method comprises the steps: receiving a natural language question input by a user, carrying out the hierarchical analysis of entity words and intention words in the question through a dynamic weight distribution mechanism, and generating an enhanced semantic vector containing entity association strength and intention probability distribution; traversing the knowledge graph based on the enhanced semantic vector, and constructing a hierarchical query sub-graph comprising a core entity, an associated entity and an implicit relationship; performing reasoning calculation on the hierarchical query subgraph by adopting a multi-path collaborative reasoning algorithm to generate a candidate answer set; and performing semantic consistency verification and redundancy elimination on the candidate answer set, generating an adaptive answer and an association explanation path in combination with historical interaction preference of the user, and synchronously feeding back a newly discovered entity association relationship to the knowledge graph for incremental updating to form a question and answer interaction closed loop. By utilizing the embodiment of the invention, the accuracy and interpretability of questions and answers can be improved, and the user interaction experience and the information acquisition efficiency are improved.

The invention discloses a method and a system for generating an SQL (Structured Query Language) query based on a natural language question. The method comprises the following steps: converting mode information of a target database and the natural language question into semantic vector representation; based on the semantic vector representation, a simplified database mode set related to SQL query is screened out through an attention mechanism; based on the natural language problem, the simplified database mode set and preset database constraint information, generating an SQL structural skeleton, and filling specific elements of the SQL structural skeleton to form a preliminary SQL query; and performing dynamic correction and verification on the initial SQL query by utilizing a large language model, and outputting a final SQL query. According to the method, association mining between user query and a database mode is effectively enhanced by utilizing a context-aware cross-encoder mechanism, and an implicit corresponding relation between a natural language problem and a database table / column can be more accurately identified and utilized.

The invention discloses a business-adaptive RAG knowledge base rapid question and answer implementation method, relates to the technical field of natural language processing and knowledge base retrieval, and realizes deep fusion and accurate context extraction of fragmented and structured business knowledge by constructing a business enhanced knowledge base and executing multi-stage dynamic retrieval. When an original business document is subjected to intelligent structured analysis and segmentation, a link business entity is identified, rich business attribute metadata is marked, in the process, an unstructured text is converted into an enhanced knowledge fragment carrying clear business semantics, a semantic vector is generated through an embedded model, and on the basis, the semantic vector is subjected to semantic segmentation; according to the method, rapid preliminary screening based on keywords and metadata, fine arrangement based on semantic vectors and association expansion based on a business knowledge graph are sequentially executed, the progressive retrieval strategy ensures that retrieval results are highly related to business contexts, and the accuracy of generated answers is improved.

The invention relates to the technical field of data analysis, and discloses a data analysis method and device based on multi-modal data fusion, equipment and a medium, and the method comprises the steps: collecting visual data, audio data and process text data, carrying out the preprocessing and standardization processing of different types of data, constructing a multi-modal data set with aligned timestamps, and storing the multi-modal data set in a database; the method comprises the following steps: extracting a time-frequency dynamic feature and a semantic vector feature, extracting a map structure feature, a time-frequency dynamic feature and a semantic vector feature, fusing the features by using a cross-modal attention mechanism to generate a fused feature vector, finally performing analysis processing based on the fused feature vector, and outputting an analysis result. According to the method, the multi-modal data set with consistent time is constructed, the structural features of various modals are extracted, and the cross-modal attention mechanism is introduced to realize deep fusion of the feature level, so that the problems of single information utilization and weak feature relevance of the existing detection means are solved, and the comprehensiveness of defect detection and the accuracy of fault diagnosis are improved.

The invention discloses a question answering method and device based on retrieval enhancement generation, a medium and equipment, and relates to the technical field of computers. According to the method, related candidate sub-graphs are matched in an existing structured knowledge graph according to the query problem of a user, and the candidate sub-graphs are further judged to be insufficient to deal with the query problem through logical reasoning; according to the method, sparse keyword vectors of query questions based on surface vocabularies and dense question vectors based on context deep dependency are further extracted; matching the query question with a sparse semantic vector of each text block of the unstructured text based on surface vocabularies and a dense semantic vector of each text block based on context deep dependency, which are acquired in advance, so as to determine the text block related to the query question from the unstructured text; the candidate sub-graphs are further converted into graph structures to supplement the candidate sub-graphs, answers corresponding to the query questions are generated based on the graph structures, and the performance of questions and answers in multi-hop reasoning and information integration retrieval recall is improved.

The invention discloses a multi-mode federated learning method and system, computer equipment and a readable storage medium, and belongs to the technical field of federated learning. The multi-modal federated learning method comprises the following steps: on each client node, mapping local data of various modals into a plurality of vectors in a unified semantic space, determining an incidence matrix of the data of the various modals, and fusing the plurality of vectors according to the incidence matrix to obtain a local semantic vector; training a local model by using the local semantic vector to obtain local model parameters, and uploading the local model parameters to a server; on the server, identifying the difference degree between the data distribution condition of each client node and the global data distribution condition, and determining the node weight vector of each client node; and performing weighted aggregation on the corresponding local model parameters by using the node weight vector of each client node to generate global model parameters for next federated learning. Therefore, the performance of the training model can be improved.

The invention belongs to the technical field of robot control, and provides a robot self-adaptive task planning and action adjusting method and system, and the method comprises the steps: responding to a task instruction, and calibrating the motion parameters of a mechanical arm of a robot; acquiring a state vector according to a set frequency, determining whether visual abnormality or motion abnormality exists or not according to a continuous change condition of the state vector, and generating an abnormality mark if the visual abnormality or motion abnormality exists; performing action correction in response to the abnormal mark or the task failure mark, performing cross-modal fusion on the current state vector and the semantic vector of the task instruction, generating a candidate action sequence based on the fused feature and task target, and considering the compatibility of the candidate action and the current environment, the residual step number of the action queue and the task failure mark. An optimal action is screened out, and then an action adjusting instruction is generated; and continuously obtaining the state vector and the action correction process until the robot completes the task instruction. The environment adaptability and the execution success rate of the robot in a complex scene can be improved.

The invention relates to the technical field of OA examination and approval, in particular to a multi-modal file intelligent examination and approval method and system based on a large language model, and the method comprises the steps: configuring exclusive examination and approval templates for different examination and approval roles, and generating a role exclusive intelligent examination model; the method comprises the following steps: receiving a to-be-approved multi-modal file, analyzing file content, and outputting structured JSON (JavaScript Object Notation) data; inputting the structured JSON data and a configured approval template into a corresponding intelligent review model, performing step-by-step reasoning through a thinking chain prompt strategy, and outputting a structured review intermediate result; encoding the review intermediate result into a semantic vector, and retrieving Top-K similar historical approval cases from a knowledge base module based on a vector database to generate a reference suggestion set; fusing the review intermediate result with the reference suggestion set to generate a review result; based on the review result and the feedback of the approver, the standardized approval opinions are generated, and the accuracy and consistency of review are improved.