196 results about "Semantic expansion" patented technology

The invention provides an intelligent retrieval method and system for unstructured asset content based on a large model, and relates to the technical field of data retrieval, and the method comprises the steps: carrying out semantic expansion on retrieval keywords through a knowledge graph enhancement module, obtaining asset feature vectors through a multi-modal feature extraction model, and constructing a hierarchical asset feature index database; the comprehensive similarity is calculated through a weighted fusion algorithm, and retrieval results are optimized and reordered through semantic comprehension and correlation analysis capacity of the pre-trained large model. According to the method, the retrieval precision and efficiency of the unstructured asset content are improved, and intelligent association analysis and semantic understanding of cross-modal assets are realized.

The invention relates to the technical field of intelligent recommendation, and discloses a hybrid retrieval RAG-based resource recommendation method and system, and the method comprises the steps: collecting resource text data, and constructing a vector library and a tag library; expanding the user question based on the language model to obtain a plurality of semantic extension questions; performing intention recognition, judging whether the user question is a resource recommendation question, and if yes, determining a target classification type; screening the data according to the field definition in the tag library to obtain a candidate knowledge fragment set; obtaining candidate vectors, mapping the user question and the semantic extension question into query vectors, calculating the similarity between the query vectors and each candidate vector, and selecting knowledge supplement content; and performing resource splicing on all the knowledge supplement contents to generate resource recommendation answers. According to the method, a structured label screening mechanism and a semantic vector fine arrangement mechanism are fused, and the problems of recall redundancy, matching deviation and the like caused by the fact that an existing RAG system only depends on semantic similarity retrieval are solved.

The invention discloses a long-tail image recognition method based on multi-modal semantic generation and image-text fusion. The method comprises the following steps: extracting structured semantic description from a tail image; carrying out semantic rewriting and enhancement based on a multi-modal visual language model, and generating an image semantic extension description; the image semantic extension description is optimized based on semantic duplicate judgment and a style alignment mechanism, and an optimized text description set is obtained; inputting the optimized text description set into a text graph model, generating a tail class image sample, performing semantic and visual quality screening, and constructing to obtain an enhanced image set for training; constructing a training data set based on the original long-tail data set and the enhanced image set, and training an image-text fusion classification model; and inputting a to-be-identified image into the trained image-text fusion classification model, and outputting classification results of all categories. According to the method, the discrimination capability in a long-tail distribution scene is enhanced, and the method has a stronger generalization characteristic.

The invention provides a method for generating an SQL (Structured Query Language) by a natural language based on bidirectional mapping and semantic parsing, which relates to the technical field of database query and comprises the following steps of: extracting natural language query elements and packaging the natural language query elements into structured data, and establishing a mapping relationship from a query field to a service attribute and a physical data table by adopting a bidirectional Hash index technology; and automatically identifying multi-table association keys, performing semantic extension and compliance verification, generating an abstract syntax tree, performing processing according to user permission, and finally converting the abstract syntax tree into an SQL statement conforming to a target database syntax specification. According to the method, the accuracy and the efficiency of converting the natural language into the SQL are improved, and the flexibility and the safety of the system are enhanced.

The invention provides a large language model knowledge retrieval method and system based on semantic vectorization, and relates to the technical field of artificial intelligence application, and the method comprises the following steps: constructing a vector knowledge base, collecting knowledge base files related to demand content, importing the knowledge base files into a knowledge document library, carrying out intelligent word segmentation on file content through a large language model, and obtaining a knowledge retrieval result; decomposing the document into a plurality of text blocks according to a preset format of the document, vectorizing the document blocks, and storing the vectorized document blocks into a vector knowledge base; and in response to a question request related to knowledge retrieval, performing anaphora elimination and semantic expansion on question content through the large language model, vectorizing the question content, selecting a corresponding vector knowledge base according to the category of the question content, and selecting a corresponding retrieval mode to retrieve and generate an answer to the question.

In accordance with an embodiment, described herein is a system and method for providing extensibility in an analytic applications environment, including a semantic layer that enables the use of custom semantic extensions to extend a semantic data model (semantic model). In accordance with an embodiment, when customizations are made to the semantic model, the system stores changes to the semantic model as an action-set, rather than as a changed-state. This allows the system to replay changes on the factory model, to get back to a desired end state, much as an operating system update does not affect the underling setup.

The invention discloses a metadata real-time self-adaptive standardization system for multi-field data sharing. The metadata real-time self-adaptive standardization system comprises a metadata information layering module, an intelligent information acquisition module, a real-time self-adaptive standardization module and a visual management module, the metadata information layering module identifies sources of various metadata, and sequentially performs cleaning, classification and layering preprocessing on the metadata; the intelligent information acquisition module uniformly acquires metadata information and converts the acquired data into standardized intermediate representation; the real-time adaptive standardization module is used for realizing rule dynamic adaptation and real-time optimization in a metadata standardization process, is internally provided with a dynamic rule library, is used for storing dynamically generated metadata mapping rules and supports automatic loading, updating and semantic extension of the rules; and the visual management module realizes management, analysis and dynamic adjustment of metadata through a visual interface. The method is high in accuracy of processing unknown data, can adapt to different data scenes in real time, and is high in semantic interoperation capability.

The invention relates to the technical field of natural language processing and information retrieval, and discloses a deep dense document recall method based on multi-view vector fusion, comprising the following steps: S1, preprocessing user query and candidate documents to generate a standardized text; s2, respectively constructing multi-view semantic vector representation of the query and the document, wherein multiple views at least comprise a keyword view, a semantic extension view and an intention view; s3, calculating a similarity score between the query and the document for each semantic view, and fusing the scores of all the views through a dynamic weight; and S4, sorting the documents according to the fusion score, and returning a front Top-K result. By constructing multi-dimensional semantic representation of keywords, semantic extension and an intention perspective, multiple semantic information such as term accurate matching, context association and task target consistency is effectively fused. The dynamic weight distribution mechanism adaptively adjusts the contribution degree of each view angle according to the query content, and overcomes the defect of insufficient semantic coverage of a single view angle.

The invention discloses a lightweight incremental question answering system based on graph structure index and double-layer retrieval. Comprises: a graph-based incremental index module for segmenting an input document into text blocks, extracting entities and relationships through a large language model (LLM), and constructing a dynamic knowledge graph; the double-level retrieval module is used for mapping user query into a graph structure, adopting a double-strategy retrieval mechanism associated with local keyword matching and global theme and combining graph vectors for collaborative query; and the path constraint sub-graph generation module is used for generating an identifier sub-graph based on an n-hop reasoning path on the basis of the retrieved content, and performing deep semantic extension and answer generation. During work, through the modular and progressive collaborative design, the system realizes full-process optimization from data acquisition to knowledge representation and from query response to deep reasoning.

The invention provides a knowledge graph-based government policy question and answer method and related equipment, which realize intelligent processing of government policy question and answer, contribute to improving the intelligent level of government policy service and meet the actual question and answer requirements of actual government policies. The method comprises the steps of obtaining multi-modal government affair policy data, wherein the multi-modal government affair policy data comprises structured policy data, an unstructured policy text, an OCR text, layout features and a policy document; the multi-modal government affair policy data are fused through a Transform hybrid architecture, a knowledge graph is constructed, and the knowledge graph comprises five elements including entities, relationships, attributes, time and space; constructing a time sequence diagram structure of policy conditions based on the dynamic graph neural network; receiving user query information, and extracting a geographic position keyword based on the query information; and carrying out semantic extension on the keyword by utilizing a Geo-BERT model, and obtaining a target keyword.

The invention provides a semantic input-based artistic font generation method, which comprises the following steps of: acquiring text data required by artistic font generation, and performing word segmentation processing on a text by adopting a word segmentation method to obtain a keyword list; performing semantic extension on each keyword in the keyword list according to a pre-constructed HowNet knowledge base to obtain synonyms, hypernyms and hyponyms of the keywords; performing word frequency statistics and TF-IDF weight calculation on the expanded keyword list, and screening out a core semantic concept required by the keyword art font generation with the highest weight; calculating semantic similarity among the core semantic concepts, and constructing a semantic similarity matrix; taking the screened core semantic concepts as nodes and the semantic similarity as weights of edges, and constructing a semantic network atlas; k-means clustering analysis is carried out on the semantic concept vectors, concepts with high semantic similarity are clustered according to a clustering result, and a semantic vector representation model required by artistic font generation is constructed.

The invention belongs to the technical field of text processing, and particularly relates to a method and system for retrieving DOCX document content based on keywords, which comprises the following steps: analyzing an Office Open XML structure of a DOCX document, combining with multi-dimensional features such as style names, and utilizing a title classification score model to accurately distinguish a title and a text, so that a semantic hierarchical structure of the document is effectively reserved; and secondly, a multi-level semantic extension mechanism is introduced, and a Sension-BERT, a HowNet knowledge base and a Word2Vec model are fused, so that intelligent extension of synonyms and synonyms of keywords is realized, and the recall rate and semantic understanding ability of retrieval are remarkably improved. And in addition, a BM25 model is combined with paragraph length normalization and structure position weight to calculate a correlation score, so that retrieval results are sorted more accurately and reasonably. The construction of the reverse index is combined with the position coding and compression optimization strategy, and the retrieval efficiency and the storage performance are both considered.

The invention provides a water conservancy industry electronic dark bidding document enterprise internal examination method and system based on artificial intelligence, and belongs to the field of water conservancy industry bidding. Performing automatic pre-auditing on the bidding file: performing compliance inspection and integrity inspection, identifying problems existing in the bidding file, and providing improvement suggestions to ensure that the problems conform to the basic requirements of electronic dark label review; carrying out data standardization and cleaning on the bidding file: carrying out semantic extension and ambiguity elimination, identifying images, tables and handwritten contents in the bidding file, identifying a main body structure of the water conservancy design drawing, extracting engineering quantity list data, and carrying out compliance verification; identifying an abnormal behavior in the bidding file through a machine learning model; and an internal examination decision tree is constructed according to preset key indexes and score weights of the water conservancy project, an interpretable artificial intelligence algorithm is utilized to carry out internal examination decision making on the bidding document, an internal examination score result is fed back, and specific score deduction reasons are explained. And the standardization and the accuracy of internal examination of the bidding document are improved.

The invention relates to the technical field of operation and maintenance automation, and provides an operation and maintenance field professional question and answer and diagnosis Agent design method and system, and the method comprises the steps: receiving and structurally analyzing an original query request of a user, carrying out the parameter validity check and safety verification, and extracting the query content and a session identifier; identifying task types through an intention classification algorithm based on the pre-training language model and performing content risk assessment; performing semantic extension on the query to generate an extended query word, performing similarity matching in the operation and maintenance knowledge base by using a hybrid retrieval algorithm, and fusing related knowledge fragments; inputting the enhanced query information and the task type into an inference engine for intelligent inference to obtain a diagnosis result; the reasoning result is stored in a historical memory library, and session context state information is updated; and performing formatting processing and security check on the reasoning result, packaging the result and context information, and outputting a standard response result. According to the method, the accuracy and the intelligent level of operation and maintenance professional question answering and diagnosis are improved.

The invention discloses a large language model training method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and reinforcement learning. The method comprises the steps of obtaining an initial prediction answer statement corresponding to a question statement; semantic expansion retrieval is carried out on the initial prediction answer statement, and a retrieval answer statement corresponding to the initial prediction answer statement is determined; scoring the retrieval answer statement, and determining a target reward value of the initial prediction answer statement based on a scoring result of the retrieval answer statement; and if the target reward value is smaller than a preset reward threshold value, adjusting the pre-trained large language model based on the target reward value, and inputting the question statement into the adjusted model again until the finally obtained target reward value is greater than or equal to the preset reward threshold value, thereby completing training of the pre-trained large language model. The optimization training efficiency of the large language model and the accuracy of model output can be improved, and the stability of large language model output is improved.

The invention discloses a weak supervision video anomaly detection method based on prompt learning knowledge enhancement, and belongs to the technical field of video intelligent analysis. A video side gives a section of abnormal scene video, video sequence features and audio sequence features are obtained through a feature extraction network, then a trained and complete feature aggregation network is input to carry out multi-modal feature aggregation, an abnormal score is obtained through a score prediction network, and text representation is carried out based on prompt learning. A prompt template is constructed for abnormal video tags through a knowledge graph, semantic expansion is performed on normal tags through a plurality of learnable parameters, cross-modal alignment is performed on the normal tags and a video side, so that features of the video side are close to different normal semantics, knowledge enhancement is performed by introducing external information, positive abnormal boundaries of the video are learned, and the detection performance is improved. And finally, multi-task joint optimization is carried out through different loss functions, and abnormal video clip positioning is carried out.

The invention relates to a knowledge graph enhanced multi-modal file retrieval method, and belongs to the field of artificial intelligence and multi-modal information retrieval. The invention aims to solve the problems of multi-modal information semantic segmentation, weak semantic reasoning ability and low semantic matching precision in the existing multi-modal archive resource retrieval process. Through four stages of archive multi-modal data preprocessing and feature extraction, knowledge graph construction and enhancement, semantic retrieval request analysis and intention modeling, and multi-modal semantic matching and sorting, a semantic relationship is enhanced by utilizing a knowledge graph, so that the semantic relevancy and context consistency of a retrieval result are remarkably improved; a user is allowed to input and inquire in various forms such as texts, images and voices, and semantic extension retrieval is supported. According to the method, more efficient and accurate archive resource retrieval can be realized, and the user retrieval experience and archive knowledge utilization are improved.

The invention discloses a semantic extension matching method and system based on a domain synonym library, and relates to the technical field of data processing, the method comprises the following steps: obtaining a query keyword input by a user, and generating a query context vector according to the query keyword and user context information; if the query keyword does not belong to the category word in the platform service category system, determining an extended synonym set matched with the query keyword from a pre-constructed field synonym library; for each extended synonym in the extended synonym set, calculating a correlation score between the extended synonym and the query context vector, and performing weighting processing to obtain a corresponding weighted extended synonym; and according to each weighted extended synonym and the query keyword, generating an extended query index for search matching. Therefore, dynamic expansion combining the field scene and the synonym library is realized, multi-dimensional semantic expansion can be carried out when complex and non-standardized user query is processed, and the intelligent level of the system is improved.

The embodiment of the invention provides a retrieval processing method and related equipment. The method comprises the steps of obtaining a to-be-retrieved first query statement; identifying a target word belonging to the target field from the first query statement, and performing semantic extension processing on the target word to obtain at least one extension word belonging to the target field; performing optimization processing on the first query statement based on the at least one expansion word to obtain at least one optimized query statement; and performing retrieval processing by adopting at least one optimized query statement. Through the embodiment of the invention, the optimization quality of the query statement can be improved from the source, and the retrieval accuracy is improved.

The invention relates to the technical field of artificial intelligence, and provides a search method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring a search term for searching; matching the search terms through a preset database to obtain an initial matching result; obtaining a target search term according to the search term and the initial matching result, and performing semantic extension on the target search term to obtain at least one extended search term; searching by utilizing a target search term and at least one extended search term to obtain a first search result corresponding to the target search term and a second search result corresponding to the at least one extended search term; and determining a target search result corresponding to the search term according to the first search result and the second search result. Through initial semantic matching, semantic extension and comprehensive analysis, a more accurate and comprehensive search result meeting the search intention of the user can be provided for the user.

The invention discloses a public opinion report generation method based on a large language model. The public opinion report generation method comprises the following steps: S1, extracting description information of a public opinion event from user input by adopting a pattern matching method; s2, performing keyword extraction and semantic expansion on the description information by utilizing a large language model (LLM); s3, using the processed keywords to retrieve information related to the public opinion event, and sorting the retrieved information; s4, performing multi-dimensional feature quantification processing on the public opinion information, reordering the public opinion information, and screening a specified number of information from the reordered public opinion information by adopting a down-sampling function to serve as background data of the public opinion report; s5, inputting the screened background data into a large language model, and generating a final public opinion report through iterative analysis; according to the method, the public opinion report is automatically generated, and a multi-dimensional feature quantification processing and information reordering mechanism is adopted, so that the selected public opinion information is highly related to the event and is important, and the public opinion report is more accurate and comprehensive.

In accordance with an embodiment, described herein is a system and method for providing support for extensibility and customization in an analytic applications environment. An extract, transform, load (ETL) or other data pipeline or process provided by the analytic applications environment, can operate in accordance with an analytic applications schema and / or a customer schema associated with a customer (tenant), to receive data from the customer's enterprise software application or data environment, for loading into a data warehouse instance. A semantic layer enables the use of custom semantic extensions to extend a semantic model, and provide custom content at a presentation layer. Extension wizards or development environments can guide users in using the custom semantic extensions to extend or customize the semantic model, through a definition of branches and steps, followed by promotion of the extended or customized semantic model to a production environment.

The invention provides a scientific research question answering and reasoning all-in-one machine based on multi-agent cooperation and a control method, and relates to the technical field of artificial intelligence and multi-agent reasoning, and the all-in-one machine comprises a first agent which is used for carrying out the semantic understanding of a scientific research problem inputted by a user, and obtaining a semantic understanding result; performing semantic extension on the semantic understanding result according to a configured extension rule to obtain a first query request corresponding to the scientific research problem; the second intelligent agent is used for screening response information associated with the query request sent by the first intelligent agent from a pre-constructed scientific research knowledge base and sending the corresponding response information to the first intelligent agent; and the third agent is used for evaluating whether the target response information, the corresponding semantic understanding result, the first query request and the second query request meet the configured evaluation rule or not to obtain an evaluation result. The scientific research problem of the user can be accurately, comprehensively and reliably responded.

The invention provides a class incremental learning method based on prompt guidance and multi-modal fusion, and relates to the technical field of artificial intelligence and computer vision. The method comprises the following steps: firstly, performing semantic extension on a category label, and constructing semantic enhanced text representation through a text encoder; then block embedding and hierarchical feature extraction are carried out on the input image by using a pre-trained visual encoder, a cross-modal unified embedding space is constructed, a bimodal prompt gating fusion module is introduced into the unified embedding space, and adaptive weighting is carried out on text prompt and image prompt according to gating weight to generate fusion prompt; through a bimodal prompt collaborative filtering module, screening out a prompt set most relevant to the current task according to the similarity of the semantic features of the image and the text; the pre-training backbone network is frozen in the increment stage, only prompt parameters and fusion layer weights are optimized, a joint loss function is used for parameter updating, finally, image and text data are input in the reasoning stage, cross-modal similarity is calculated, and a classification prediction result is output.

The invention relates to the technical field of information recommendation, in particular to an engineering information recommendation method and system, and the method comprises the following steps: S1, constructing an engineering domain knowledge graph; s2, user engineering project background analysis; s3, aligning the recommended contents with the technical nodes of the knowledge graph: preliminarily aligning the recommended contents extracted from the engineering information database with the matched technical nodes to obtain preliminary recommended contents, screening again to obtain final recommended contents, and pushing the final recommended contents to the user; and S4, semantic extension and technical completion: completing the technical background of the recommended content to ensure that the recommended content not only covers the dominant demand of the user, but also includes the technical scheme related to the potential demand of the project. According to the method, reasoning is carried out through the associated edges in the knowledge graph, the matching degree of the recommended content and the technical nodes required by the user is judged, the recommended content is screened and optimized based on the matching degree, and it is ensured that the content pushed to the user not only meets the current requirement, but also can adapt to the future project requirement.

The invention relates to the field of business type judgment, in particular to a method for judging the business type of an unknown business database based on a large model, which comprises the following steps of: connecting the unknown business database through a standardized interface to obtain metadata and sample data; extracting multi-dimensional meta-information according to database types; performing semantic extension on the meta-information by utilizing a pre-training language model BERT; fusing multiple features through an attention mechanism to generate a fused feature, and outputting a service type reasoning prompt in combination with a historical reasoning result; after LLM multi-round reasoning, the matching degree is judged through comprehensive confidence, a confidence matrix is constructed, and a final service type is output; the method realizes automatic and high-precision judgment of the service type of the unknown service database, and is suitable for scenes of database management, data analysis and the like.

The invention discloses a dynamic updating law and regulation knowledge graph construction and recall method. The method comprises the following steps: collecting law and regulation text data in real time; generating a structured law article object sequence through regular fragmentation processing; performing full-text structure recognition and semantic processing to generate segmentation-level and full-text-level semantic data; carrying out composite vectorization on the content of the law article, the outline of the segmented text and the abstract to generate a context enhanced semantic vector; fusing the full-text and segmented triads and enhancing relation attributes; respectively storing the vector and the original data to a vector database and an original index; importing the fused triple into a graph database to construct a knowledge graph; and based on the map response query, outputting a structured answer through entity recognition, semantic extension, multi-hop query and result fusion. According to the method, efficient, accurate and real-time retrieval and dynamic updating of law and regulation knowledge are achieved, and the recall rate and accuracy of complex legal questions and answers are effectively improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a target data sample set construction and screening method, device, equipment and medium, and the method comprises the steps: obtaining a target type description, carrying out semantic extension to generate an extension description, generating a reference image sample based on an image generation model, real data units are screened through feature extraction and similarity comparison, and a target data sample set is constructed in combination with knowledge base verification. According to the method, by introducing semantic extension, reference image generation, cross-domain feature comparison and knowledge base consistency verification, real samples highly fitting target type semantics are automatically screened from massive original data, so that the manual annotation dependence is reduced, the illegal sample construction efficiency is improved, and the manual annotation time is shortened. And the training quality and the expansion capability of a subsequent detection model are enhanced.

The invention belongs to the field of computer vision, and discloses an open set semi-supervised target detection method based on class contrast learning. According to the method, a solution is provided for the instance-level approximate distribution external data problem, an approximate distribution external data filtering strategy is provided by combining a clustering thought and a class contrast learning thought, a dynamic boundary is abstractly divided for each prediction instance, and error semantic extension caused by approximate distribution external data instances is prevented. Through effective integration of a dynamic threshold strategy and class contrast learning, the situation that excessive normal instances are misjudged as out-of-distribution instances by the model due to excessive strict out-of-distribution exception filtering at the initial stage of training, and then the generalization performance of the model is affected can be prevented; and the generalization ability of the model can be improved by using normal instances in unmarked data and a small amount of approximate distribution external data instances, and label distribution can be strictly controlled in the later stage of training, so that the situation that the model performance is rapidly lowered due to overlarge data variance caused by the fact that normal pseudo labels are distributed to excessive approximate distribution external instances is prevented.

The invention discloses a collaborative problem traceability and strategy matching method based on entity recognition, and the method comprises the steps: carrying out the semantic expansion of a negative problem text through a T5 generation type pre-training model, and extracting time, a subject, a problem, a strategy and other entities and position information through a BERT-BiLSTM-CRF model; splicing the subject entity, the question and the strategy entity to generate a text with a prefix, correcting by using a BART generation type pre-training model, and classifying and mapping the question to a subsystem for storage through a BERT-DPCNN model; coarse screening is conducted on texts in the subsystem through a regular rule base, vector representation is generated in combination with BERT and RoBERTa models, cosine similarity is calculated, and matching results are determined by synthesizing sentence positions and keyword overlapping degrees; constructing a question-strategy keyword knowledge graph based on a matching result, and inputting the keywords into a DeepSeek-V3 big language model to generate an optimization strategy scheme; according to the method, multiple deep learning models and large language models are fused, so that semantic understanding, entity extraction and accurate matching of negative problem texts are realized, and a final optimization strategy scheme is generated.