511 results about "Semantic relevance" patented technology

The invention discloses a knowledge question-answering system based on a large language model. The method comprises the steps that a power operation and maintenance knowledge base module obtains data from a data source for preprocessing, constructs a power operation and maintenance field knowledge graph, converts text content into semantic vectors and integrates the semantic vectors to form a power operation and maintenance knowledge base; the problem understanding module is used for identifying and analyzing problems and converting the user problems into semantic vectors; the retrieval and reordering module is used for performing semantic retrieval in the electric power operation and maintenance knowledge base, recalling knowledge information related to question semantics, and ordering retrieval results based on semantic relevance, knowledge confidence and information importance; and the answer generation module is used for integrating the knowledge information and the user question into input of a large language model, generating prompt information, and generating an answer in a natural language form according to the prompt information by adopting the large language model based on data fine adjustment in the field of power operation and maintenance. According to the scheme, the deep learning technology is used for understanding semantics of user questions, and accurate retrieval is carried out in the knowledge base.

The embodiment of the invention discloses a retrieval generation method and device based on a large language model and a knowledge graph. The problems that retrieval semantic relevance is weak, and recalled data lacks global knowledge can be solved. The method comprises the following steps: performing vector analysis on a plurality of preset domain documents, and constructing a vector database; constructing a knowledge graph according to the entity description information and the relationship description information extracted from the plurality of field documents, and storing the knowledge graph into a graph database; performing feature extraction on a target question input by a user to obtain a multi-dimensional keyword corresponding to the target question; retrieving the multi-dimensional keywords through a preset search engine, a vector database and a graph database to obtain a target retrieval result; and determining target input information according to the target retrieval result, and inputting the target input information into the target language model to obtain target output response information.

The invention relates to the technical field of voice processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a voice intention recognition method, device and equipment and a medium, and the method comprises the steps: obtaining a to-be-processed voice signal, carrying out the voice activity detection processing of the voice signal, dividing the voice signal into a plurality of voice segments, analyzing semantic contents of the plurality of voice segments, determining semantic correlation information of each voice segment, analyzing sound source attributes of the plurality of voice segments, determining sound field type information of each voice segment, screening out a target voice segment from the plurality of voice segments according to the semantic correlation information and the sound field type information, and executing intention recognition processing based on the target voice segment to generate an intention recognition result. According to the invention, through a dual analysis mechanism of semantic correlation information and sound field type information, effective screening of voice segments is realized before voice recognition, non-target voice or interference segments are effectively prevented from being sent to an intention recognition model, and the accuracy of a recognition result is improved.

The invention relates to the technical field of power plant management and control, and discloses an intelligent power plant management and control system based on the Internet of Things, and the system comprises the steps: when a plurality of labels related to the same equipment or parameter exist in different subsystems, according to a similarity index between the labels and an equipment association relationship; on the basis of the detected conflict label group, combining equipment historical operation and maintenance data and an upstream and downstream parameter flow relationship, constructing a label semantic evolution graph, and performing reasoning analysis on label equipment through a fusion rule engine and a graph neural network; through mapping knowledge domain fusion and semantic embedding comparison, matching and clustering among conflict labels are completed based on structural similarity and semantic relevancy, and a label alignment rule is constructed; according to a label coordination result, designing a mapping rule of a data field; and performing inter-system synchronous verification on a result after structure conversion and label standardization processing, and writing a standardized label into a unified semantic database. The method has the advantage of improving data semantic consistency.

The invention discloses a retrieval method and device based on a knowledge graph, computer equipment and a storage medium. The method comprises the steps that the knowledge graph is acquired, a node relation vector is output through a preset relation learning module, nodes related to user query content are retrieved from the knowledge graph, and an external knowledge representation result is generated; performing feature fusion on the user query content and the external knowledge representation result by using the correlation matrix to obtain a fused feature vector; performing image-text bidirectional semantic alignment on the fused feature vector based on an attention mechanism to generate a joint feature vector; and performing matching calculation based on the joint feature vector to obtain a matching score for representing the semantic correlation degree. According to the method, the user query content and the generated external knowledge representation result are fused through the correlation matrix, image-text semantics are aligned through an attention mechanism, the joint feature vector is generated, the matching score is calculated, and cross-modal retrieval is realized by using the matching score, so that the information retrieval accuracy of the community property management system is greatly improved.

The invention relates to the technical field of artificial intelligence security, and discloses a multi-modal large model confrontation security detection method and system, and the method comprises the steps: obtaining initial multi-modal data from original data sources, such as images, texts and audios, simulating the behavior of an attacker through reinforcement learning to generate a confrontation sample, and generating a cross-domain confrontation sample through transfer learning, extracting a multi-modal feature vector; the modal weight is dynamically adjusted through an attention mechanism based on the feature vector, the vulnerable modal weight is reduced, the credible modal weight is enhanced, inconsistency between abnormal modals is recognized in combination with disturbance analysis, and a weighted feature vector is output; abnormal input is detected by comparing semantic relevance of different modes, if semantic conflicts are found, an alarm is triggered, input is refused, and a corrected feature vector is output; and dynamically closing the untrusted mode and enhancing the trusted mode based on the semantic verification result, and outputting a final security detection result. According to the invention, the security of the multi-modal large model in a complex attack environment can be improved.

The invention provides a search engine-based standard substance and standard substance retrieval and sorting method, which relates to the technical field of data processing, and comprises the following steps: acquiring retrieval keywords input by a user, constructing a standard substance and standard substance knowledge base, mapping to a low-dimensional semantic space, calculating the semantic correlation between the retrieval keywords and the standard substance knowledge, and constructing a heterogeneous information network. Generating comprehensive relevancy measurement, and performing multi-granularity semantic matching to obtain candidate retrieval results; for structural features corresponding to the candidate retrieval results, adaptive feature weights are distributed, independent clustering is carried out, subspace clustering results are obtained, optimization is carried out, global optimal clustering results are obtained, high-order semantic association features are mined, cross-category semantic association is carried out, and high-quality retrieval results are generated; performing low-rank decomposition to obtain an initial comprehensive score, modeling a sorting problem as a Markov decision process, determining an action space and a state space, constructing a reward function, determining a sorting position, and obtaining an optimal sorting result.

The invention discloses a contrast learning unsupervised cross-modal hash retrieval algorithm based on a graph attention mechanism, and relates to the technical field of cross-modal retrieval. According to the graph attention mechanism-based contrast learning unsupervised cross-modal Hash retrieval algorithm, feature extraction is performed on image and text data through a pre-trained CLIP model to obtain image modal features and text modal features, and additional positive samples are generated through data enhancement; the similarity is calculated through Euclidean distance and cosine similarity on the basis of a graph attention network, and high weight is given to positive samples and low weight is given to negative samples by comparing adjacent matrixes. The method has the advantages that the features of the image mode and the text mode can be effectively fused and mapped to the common Hash space, a graph attention mechanism can adaptively adjust the connection weight between the features of the different modes, samples with high semantic correlation are highlighted, and therefore the semantic consistency between the image and the text is ensured.

The invention relates to the technical field of intelligent retrieval, in particular to an enterprise RAG intelligent question answering system based on vector database reordering. The system specifically comprises: a document recall module, which retrieves a vector database to obtain candidate document blocks containing business metadata; the comprehensive scoring module is used for calculating a semantic correlation score by adopting a later-stage interaction architecture based on bidirectional token importance weighting, performing path semantic matching and context sensing rule evaluation according to a preset metadata ontology graph to obtain a service attribute score, and analyzing the evidence sub-graph to obtain a fact path score; fusing the semantic correlation score, the service attribute score and the fact path score to generate a comprehensive correlation score; and the sorting output module performs optimization resorting based on a preset punishment mechanism and the comprehensive correlation score to generate an optimized context set, and calls a generation model to output answers based on the optimized context set. According to the method, semantic accuracy, business compliance and fact reliability can be considered, and more trustworthy high-quality enterprise-level answers can be generated.

The invention relates to the technical field of artificial intelligence, and discloses a man-machine dialogue history and semantic retrieval-based prompt automatic construction method, which comprises the following steps of S1, performing text preprocessing on historical dialogue data and user input, including dynamically generating query keywords, verifying and analyzing a file uploaded by a user, and extracting core contents; s2, utilizing a pre-training language model to map the historical dialogue and the user request into semantic vectors, matching in combination with the keyword weight, and constructing a historical vector set and a user request vector; and S3, extracting a context fragment most relevant to the user request from the historical dialogue vector based on a convex optimization method. The context information highly related to the user request is accurately extracted through the sparse optimization technology, and the background information, the user request and the generation instruction are organically integrated in combination with the dynamic Prompt template design, so that the semantic correlation and context coherence of the generated reply are improved, and the interference of redundancy and irrelevant information is avoided.

The invention provides a video plot generation and scene synthesis method and system based on natural language processing, and relates to the technical field of video generation, and the method comprises the steps: receiving a script text to construct a multilayer scene map, extracting keywords to calculate semantic relevancy, executing feature decomposition and reconstruction to obtain a scene synthesis vector, and generating a video scene based on distance measurement. And extracting spatio-temporal features by using the feature pyramid, executing adaptive feature fusion, segmenting the video by applying a self-attention mechanism, and after a transition effect is inserted, performing style migration to output a finished video.

The present disclosure leverages self-supervised learning to generate positive and negative question-context pairs, enabling the model to learn robust representations. This process involves data augmentation techniques to create variations of the original questions and contexts while preserving semantic relevance. A large corpus of unlabelled text data containing questions and their corresponding contexts, ensuring diversity and representativeness across various topics are used to train a self-supervised Large Language retrieval model.

The invention discloses a dialogue memory priority system based on multidimensional weighting, and the system comprises the following modules: a multi-factor scoring module which is used for calculating the importance score of dialogue memory, and multiple factors comprise a time attenuation factor, a semantic correlation factor, an emotion intensity factor and a user feedback factor; the hierarchical storage decision module is used for distributing memories to corresponding storage hierarchies according to importance scores; the dynamic weight adjusting module is used for automatically adjusting the weight of each factor according to the dialogue mode; and the memory retrieval priority ranking module is used for determining the ranking of the retrieval results based on the multi-dimensional scores. According to the invention, core information and secondary information can be distinguished conveniently, and waste of memory resources is avoided; key information of the dialogue context is captured more accurately, so that the memory retrieval efficiency and the system performance are optimized; and the method adapts to different dialogue scenes and user interaction modes.

The invention relates to the technical field of data processing, and discloses a multi-protocol fusion Internet of Things equipment intelligent gateway data conversion method and system. The method comprises the following steps: collecting a multi-protocol equipment data packet, and extracting protocol features to construct a vector library; protocol types are identified based on the vector library, data are analyzed, and a data object set containing semantic tags is constructed; semantic correlation is analyzed through an adaptive learning algorithm, and a dynamic protocol semantic mapping matrix is established; converting the data into a standard format according to the mapping matrix and recording a matching degree to form a target data pool; and extracting fusion data from the data pool, recoding according to a target protocol format, and outputting a data frame. The problem that an existing multi-protocol fusion data conversion method lacks protocol semantic understanding and self-adaptive learning ability is solved, and semantic consistency and conversion quality of data conversion among multi-protocol equipment are improved.

A computer-implemented method for searching electronic documents is provided. The method executing a non-semantic search, such as lexical search, to identify documents from a document corpus that meet the search criteria of the non-semantic search. A subsequent semantic search can be scoped based on the results of the non-semantic search. The method can thus include executing a semantic search scoped to the documents identified in the non-semantic search result to generate a semantic search result that identifies content that is semantically relevant to a natural language query. Thus, the semantically relevant content can have both non-semantic (e.g., lexical) and semantic relevance.

The invention relates to the technical field of customer service quality inspection, in particular to an online customer service intelligent quality inspection system and method based on artificial intelligence. And automatically extracting a user demand keyword, an emotion expression keyword and a potential violation term keyword, and generating a structured keyword sequence. Performing emotion analysis on each dialogue round through a Transform model, and accurately outputting a customer emotion classification and an intensity score; and semantic correlation of the context is carried out through a neural network model. And automatically identifying the content of each round of dialogue and counting illegal verbal skills. Furthermore, the customer emotion value, the context coherence score and the occurrence frequency of violation verbal skills are input into a quality inspection scoring model, a comprehensive quality inspection score is automatically calculated, and whether the service is qualified or not is judged according to the comprehensive quality inspection score, so that the dynamic evaluation of the service quality is realized, the quality inspection efficiency is improved, and the customer experience is truly reflected.

The invention provides a cross-domain multi-dimensional query feature index selection method, which comprises the following steps of: judging a query field and a query purpose of a user through query subject classification and query intention identification according to historical query behavior data of the user, and obtaining a field tag and an intention tag of the query; a navigation path of knowledge links is optimized, semantic correlation between nodes and small world index algorithm characteristics are comprehensively considered, an optimal knowledge navigation path is recommended for a user, and an optimization strategy is dynamically adjusted according to query historical behaviors and feedback of the user; a knowledge navigation result is presented in a visual interaction mode, a multi-dimensional attribute screening and sorting function is provided, exploration type browsing and deep mining of a user are supported, and personalized knowledge recommendation service is provided according to a query scene and preference of the user.

The invention provides a sensitive data security compliance processing system and method. The sensitive data security compliance processing method comprises the steps of obtaining sensitive data to be accessed; setting a plurality of sensitivity levels through semantic relevance; determining the information sensitivity of each piece of text information in each sensitivity level, and extracting a privacy risk value when a user accesses the text information in different sensitivity levels through all the information sensitivity; acquiring a historical access record, generating a behavior deviation mode of a user through the historical access record, and determining behavior credibility when the user accesses text information in different sensitivity levels according to the behavior deviation mode; and performing dynamic risk assessment according to all the behavior credibility and all the privacy risk values to obtain a plurality of risk situation values, and adjusting a security processing strategy when the user accesses the sensitive data in real time through all the risk situation values. By adopting the scheme of the invention, the sensitive data can be dynamically processed based on the behavior analysis of the user.

The invention provides a retrieval method and device based on document segmentation and a document retrieval system. The method comprises the following steps: acquiring a to-be-segmented document; based on an NLP algorithm, calculating the semantic similarity between the partial texts of the to-be-segmented document to obtain a first semantic relevancy; according to the first semantic relevancy of all the partial texts, the document to be segmented is segmented, a plurality of semantic text blocks are obtained, and each semantic text block comprises at least one partial text; under the condition that a query request is received, calculating semantic similarity between a query text corresponding to the query request and each semantic text block based on an NLP algorithm to obtain a plurality of second semantic relevancy, and determining the semantic text block with the highest second semantic relevancy of the query text corresponding to the query request as a target semantic text block, and displaying the target semantic text block in a display interface. According to the scheme, the problem that in the prior art, the accuracy rate is low during text retrieval is solved.

The disclosure relates to systems and methods of automatically generating unique content including natural language text based on a corpus of previously generated response documents and discrete requirements defined in a requirements specification. The system may use generative stitching that includes multi-layer processes that execute to influence the generation of unique content including natural language text through an artificial intelligence (AI) language transformer model trained to output the content based on previously written material that is semantically relevant to the discrete requirements and is weighted against labeled attributes. The labeled attributes may determine the influence asserted against the language transformer, thereby generating unique on-target content that may be combined to create a computer-generated response document.

The invention discloses a large model-based government affair official document quotation retrieval method, device and equipment and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: obtaining a government affair official document, determining a document slice corresponding to the government affair official document, and creating a document knowledge base and a vector knowledge base based on the document slice; identifying the terminologies in the government affair document by using a target pre-training natural language processing model to obtain a corresponding identification result; based on the document knowledge base and the vector knowledge base, performing keyword matching on the recognition result by using a target information retrieval algorithm to obtain a plurality of corresponding candidate quotation documents; and performing semantic correlation scoring on each candidate citation document and the recognition result through a Rianker model, reordering each candidate citation document according to a corresponding scoring result, and outputting a target citation document according to a corresponding reordering result. Therefore, the quotation retrieval efficiency can be improved.

The invention relates to the technical field of wireless high-definition audio and video transmission, and discloses a plug-and-play wireless high-definition audio and video transmission method and system.The method comprises the steps that foreground space texture features and audio and voice segments are obtained, and an initial feature set containing space and semantic features is obtained through semantic correlation analysis; a unified representation vector is output through multi-modal feature fusion, and a dynamic importance score is obtained by determining time sequence consistency, calculating an importance weight and performing normalization; and when the score exceeds a threshold value, segmenting the video frame in real time to determine an attention focus area and optimize a boundary, thereby generating an attention weight matrix, preferentially allocating bandwidth and forming a partition differentiation compression result. And in combination with a network bandwidth state, protection is enhanced for a key stream, the priority and the bit rate are dynamically adjusted, and high-quality audios and videos are output through decoding and recombination. According to the invention, the bandwidth allocation and compression strategy can be dynamically optimized, the transmission quality of a key area is guaranteed when the bandwidth fluctuates, and the audio and video transmission efficiency and experience are improved.

The invention provides a fluororubber field knowledge graph construction method based on a large language model, and the method comprises the steps: obtaining process related knowledge data of the fluororubber field, and carrying out the classification, and obtaining the classification knowledge data of the fluororubber field; based on a preset ChatGLM model, performing knowledge extraction according to the fluororubber field classification knowledge data to extract key entities and relationships; carrying out deep analysis on the key entity and the relationship by utilizing semantic correlation and context association analysis, and enhancing the connectivity of the key entity and knowledge in the relationship through semantic similarity and association strength to obtain fused knowledge data; explaining and expanding the fused knowledge data by using a ChatGLM model to obtain expanded triple data; and performing knowledge fusion on the triple data, and performing graph storage by using a Neo4j database to obtain a knowledge graph. According to the method, the knowledge graph construction efficiency is remarkably improved through automatic knowledge extraction and processing of the large language model, and the time cost of manual labeling and data processing is reduced.

The invention discloses a person and post matching recommendation method based on BERT and a latent semantic algorithm model, and relates to the technical field of person and post matching recommendation, and the method comprises the steps: obtaining the related data of job hunters and the post recruitment text data of employers; performing word segmentation and part-of-speech tagging on the obtained text data, screening out candidate words and noun phrases, obtaining candidate word and document word embedding vectors by adopting a trained BERT model, calculating semantic similarity of the embedding vectors, and creating BERT bitmap data according to a calculation result; a latent semantic model is adopted to analyze semantic correlation in text data, preference prediction scores of job hunters for posts are calculated, corresponding class vectors are calculated through a deep random forest method, the matching probability of the job hunters and the posts is extracted, and post matching recommendation is carried out according to a probability sorting list. By adopting the hybrid recommendation method based on the latent semantic model and the deep random forest, the recommendation is more accurate, and the efficiency is higher.

The invention relates to the technical field of causal reasoning, and discloses a traffic event analysis method, device and equipment based on multi-hop causal path exploration, and the method comprises the steps: constructing a knowledge graph based on multi-source heterogeneous data in the traffic field; calculating the semantic correlation between each node in the knowledge graph and the question semantic vector, and taking the node with the highest semantic correlation as an initial reasoning node; and performing reasoning by starting from the initial reasoning node and combining a heuristic scoring function and a Monte Carlo tree search algorithm to obtain a multi-hop causal path. According to the method, a complex input problem can be effectively analyzed, rapid matching with the most relevant nodes of the problem is realized by utilizing the knowledge graph, a complex causal path is effectively identified and explored by combining chain reasoning and path optimization technologies, and the method is more efficient by combining a heuristic scoring function and a Monte Carlo tree search algorithm. And carrying out multi-dimensional event analysis and decision support on the basis of dynamic optimization. And the efficiency and accuracy of causal path exploration are remarkably improved.

The invention provides an intelligent manufacturing field big language model construction method fused with field knowledge distillation, and relates to the field of intelligent manufacturing, which collects intelligent manufacturing field knowledge and performs knowledge clearness and structured coding to obtain an intelligent manufacturing field knowledge graph, and synchronously selects a pre-trained big language model as a teacher model. And the intelligent manufacturing domain knowledge graph is combined to obtain an intelligent manufacturing domain teacher model. Then, intelligent manufacturing field task data is collected, and knowledge distillation training is performed on the student model in combination with the intelligent manufacturing field teacher model to obtain an intelligent manufacturing field student model, so that structured field knowledge is effectively integrated, and the structural characteristics and semantic relevance of the field knowledge are concerned; therefore, the semantic similarity of the soft tag and the supervision signal of the hard tag are considered, and generalization and domain specificity are balanced.

The invention discloses an ultrasonic mammary gland image segmentation method based on fine-grained guidance, relates to the technical field of image segmentation, and attempts to use a fine-grained guidance attention decoding diffusion model. The defects of weak association of foreground and background semantics, unbalance of global and local features, poor fine-grained feature capture capability and the like in a traditional segmentation method are overcome. The core design is as follows: a clear de-noised image is obtained by using a de-noising diffusion probability model; based on a context cross-attention decoding diffusion network guided by fine granularity and a contained self-adaptive detail guide attention module, image prior information is learned and fused, and semantic correlation between a foreground and a background is enhanced; a context decoding cross attention layer is added, global information of input features and complex correlation between channels are effectively captured, and the image segmentation precision and efficiency are integrally improved. A contrast experiment result on a related data set shows that compared with a similar popular method, the method disclosed by the invention obtains a better image segmentation effect.

The invention discloses a semantic remote sensing image generation method based on a de-noising diffusion probability model. The method comprises the following steps: preparing data; constructing a de-noising diffusion model, and respectively constructing a forward diffusion structure and a reverse reasoning de-noising structure; in the training process, Gaussian noise is gradually added according to the initial remote sensing influence, and a noise target image is generated; and performing reverse reasoning sampling based on the target noise image and the semantic layout image to generate remote sensing influence. According to the method, through an improved conditional denoising network structure, a noise image is input into an encoder, meanwhile, semantic layout is embedded into the decoder through multi-layer space self-adaptive normalization operation, and the generation process of a semantic remote sensing image is fitted. By introducing a sampling strategy without classifier guidance, the semantic correlation is remarkably enhanced while the fidelity of the generated image is improved.

The invention provides a private deployment-oriented multi-modal AI knowledge base construction system. The private deployment-oriented multi-modal AI knowledge base construction system comprises a knowledge storage module, an intelligent document loading module, a document partitioning engine module, a data enhancement engine module, a multi-language semantic vector alignment module and a private deployment module, the knowledge storage module comprises a knowledge authority management sub-module and a knowledge source management sub-module, the knowledge authority management sub-module is used for managing and storing knowledge from different sources, and the knowledge source management sub-module is used for managing electronic documents and multimedia documents; according to the method, intelligent identification, partitioning, vectorization and source file storage can be carried out on different types of electronic files, knowledge graph construction is carried out for specific fields, semantic relevance between texts and topics and key entities is fully considered, the method has wider applicability, higher robustness and controllability, the data leakage risk is effectively reduced, and the method is suitable for popularization and application. The method is suitable for enterprise sensitive data protection and personal user elastic computing power requirements.

The invention relates to the field of data processing, and discloses an intelligent data processing system based on an AI large model, which comprises the following steps: when detecting that a plurality of candidate entities exist in a text, judging whether the candidate entities need to be subjected to semantic disambiguation processing or not according to context semantic relevancy and entity historical reference frequency; constructing a cross-domain context representation vector, introducing a pre-training language model to encode the context, generating deep semantic representation of candidate entities, and judging whether a clustering result has ambiguity or not; whether the candidate entities have conflicts or not is judged by fusing language model embedding and structuring knowledge graph information; constructing an entity relationship graph based on a graph neural network, performing causality, temporal and attribute dependence reasoning on the relationship between the existing candidate entities, and judging whether the relationship between the candidate entities should be combined or split; and carrying out label replacement on the candidate entities in the target text in combination with the context and the reasoning result. The method has the advantage of improving the accuracy of data processing.