93 results about "Semantic query" patented technology

The invention belongs to the technical field of artificial intelligence and information retrieval, and provides a multi-modal retrieval method and system based on a lightweight knowledge graph and an index table, and the method comprises the steps: obtaining multi-modal source data, and extracting a structured semantic tag set; constructing a lightweight knowledge graph and a metadata index table; analyzing a natural language query input by a user to obtain a semantic query vector and a keyword set, executing semantic retrieval in the knowledge graph to obtain a text candidate result, and executing keyword matching in the metadata index table to obtain a non-text candidate result; for each non-text meta record, fusing the cross-modal similarity between the non-text meta record and the text candidate result, performing index matching on an original score and a graph semantic evidence score, calculating a comprehensive correlation score, and performing reordering; and generating a natural language answer containing a non-text record link according to a reordering result. The method is suitable for efficient cross-modal knowledge retrieval in a high-security and low-resource scene.

The invention discloses a water conservancy intelligent question-answering system and method based on knowledge enhancement and data driving, and aims at water conservancy business structured and unstructured data query, through loop optimization driven by positive and negative examples, precise classification of secondary intentions of water conservancy problems is realized, knowledge questions and answers, data query and professional water conservancy subclass questions and answers can be distinguished, and the system and the method can be applied to water conservancy business. And the semantic analysis efficiency is improved. Aiming at the problem of low query accuracy of retrieval enhancement generation in the field of water conservancy, a differential water conservancy knowledge base oriented to professional books, industrial standards and laws and regulations is constructed, local and networking information is processed through a multi-source knowledge fusion and conflict resolution mechanism, and the accuracy, interpretability and traceability of question and answer content are improved. Aiming at the problems of complex operation and low semantic query accuracy in query of massive water conservancy business data and monitoring data, multi-layer constraint Text-to-SQL conversion is performed based on water conservancy business knowledge, high-precision semantic query and automatic visual output of water conservancy structured data are realized, and query efficiency is improved.

The invention discloses a large language model semantic query acceleration method based on a sparse KV Cache index. The method comprises a KV Cache semantic pruning strategy based on an attention mechanism and a set of asynchronous pipeline reasoning architecture with overlapped calculation and I / O. According to the method, the attention sparsity characteristic of the large language model in the reasoning stage and the asynchronous transmission capacity between the Host memory and the GPU video memory are fully utilized, calculation redundancy and video memory occupation in repetitive semantic query are greatly reduced, and high-throughput, low-delay and high-performance batch semantic data processing service is provided. Through a mechanism for mapping a static text into a compressed semantic index and combining a prefix cache technology in a reasoning process to realize state multiplexing, high-performance reasoning acceleration and high-efficiency storage compression are provided for a data-intensive semantic analysis task in a resource-constrained environment.

The invention discloses a meteorological intelligent question-answering system and method based on a domain knowledge graph and dynamic optimization, the system comprises a multi-source fusion training module, a meteorological knowledge graph and other modules, and the term analysis accuracy is improved through multi-source data training, knowledge graph supporting and dynamic optimization; according to the method, questions and answers are realized through multi-modal input analysis, meteorological element analysis and data feedback optimization. Compared with a traditional NLP model, the meteorological term analysis accuracy is improved from 68.2% to 92.7%, the composite query understanding bottleneck is broken through, three-layer nested semantic query is supported, the model new term adaptation period is shortened to be within 2 hours, the timeliness is improved by 10 times, meteorological element correlation analysis is achieved, and powerful support is provided for disaster reduction decision making.

The invention discloses an intelligent decision data inquiry system and method based on a generative large model, and belongs to the technical field of artificial intelligence. Natural language inquiry input by a user is received, and an inquiry intention and a target field are extracted; extracting structured and unstructured cost data from the real estate project database, and constructing a candidate field set; performing semantic matching by utilizing the generative large model to generate an intention field mapping matrix; constructing a field dependency graph based on a mapping result, and extracting a minimum closed-loop field set; performing credibility evaluation on the fields, and constructing a weighted field set; generating a dynamic query template, outputting a natural language answer, and attaching a field tracing path; if the field is missing or the credibility is insufficient, automatically generating a reverse query until a credibility requirement is met; according to the method, automatic association and accurate question and answer between complex semantic query and heterogeneous cost data are realized, and the method has good interpretability, traceability and intelligent interaction capability.

The invention is suitable for the technical field of data processing, and provides a database query method, system and device based on a natural language and a medium. Based on the natural language text and the field library, calling a root matching strategy, a semantic matching strategy and a fuzzy matching strategy through a hierarchical collaboration mechanism to perform field mapping, and determining a target field; splicing the target fields to obtain an initial semantic query statement; loading and executing the plurality of modifiers in sequence through a service discovery mechanism to obtain a target semantic query statement; converting the target semantic query statement to obtain a target physical query statement; and executing the target physical query statement to obtain a target query result and returning the target query result to the query party. Through hierarchical cooperation of the root matching strategy, the semantic matching strategy and the fuzzy matching strategy, the expandability and adaptability of the matching strategy are improved, the field recognition accuracy is improved, the field matching range is expanded, and the matching efficiency is optimized.

The invention discloses a fine-grained unsupervised cross-modal pedestrian re-identification method based on large model semantic driving, and relates to a computer vision and mode identification technology. The method comprises the following steps: inputting an unlabeled visible light-infrared pedestrian data set, generating an image text description by using a vision-language model, and analyzing the image text description into a structured semantic attribute vector through a large language model; extracting visual features of the image and semantic query embedding corresponding to attributes, and generating fine-grained features of semantic alignment through a multi-head cross attention mechanism; fusing the visual similarity and the attribute similarity to generate a cross-modal pseudo tag; combining attribute-visual alignment loss and inter-attribute decoupling loss to optimize features; in the test stage, cross-modal matching retrieval is completed based on the optimized features. Through semantic analysis and enhancement, the problem that cross-modal feature alignment is insufficient in an unsupervised scene is solved, and experiments show that compared with a mainstream method, the model performance is improved, and the method can be applied to the fields of intelligent monitoring, cross-modal retrieval and the like.

The invention provides a data management method and device based on a space-time hybrid index and a program product. The method comprises the steps of obtaining to-be-queried data; querying the double-layer index structure according to the to-be-queried data to obtain a query result; wherein the double-layer index structure comprises a first-layer index and a second-layer index, and the first-layer index is obtained by dividing a minimum containing area corresponding to each physics teaching space on the basis of a teaching behavior data set and constructing a concept hierarchy tree on the basis of each minimum containing area; the minimum containing area represents a minimum area which completely covers all activity ranges of the corresponding physics teaching space geometrically, the second-layer index is obtained on the basis of constructing a balance tree in each teaching unit, and the teaching units are used for representing the minimum containing area after the concept hierarchy tree is constructed in the first-layer index; and updating the double-layer index structure according to the teaching behavior data when determining that the to-be-queried data is the teaching behavior data based on the query result that the to-be-queried data is the non-queried data. The method can support complex space-time semantic query.

The invention provides a large model illusion detection method based on deep learning and semantic structure information, and aims to solve the problems that model imaginary information is difficult to judge and locate in a verifiable knowledge range and evidences are not traceable in an existing method. The method comprises the following steps: extracting standardized recognition features, retrieving candidate objects and forming a distinguishing condition set by minimum condition combination, generating a semantic query plan and recording ambiguity exclusion, retrieving a knowledge base and a document library and forming an evidence list, affiliating evidence according to distinguishing conditions, generating claim-level support and conflict and unknown judgment, and calculating an external consistency value on a target object. The illusion detection method has the advantages that the illusion detection accuracy and interpretability can be improved, and the illusion detection method is suitable for scenes such as model output auditing and fact verification.

The invention discloses an import and export commodity intelligent classification method based on knowledge graph metadata topology, and relates to the technical field of reinforcement learning, and the method comprises the steps: inputting an initial data packet into a dynamic interaction model, carrying out explicit association mining through a semantic enhancement layer, optimizing a rule matching path through a rule evolution layer, and constructing a dynamic commodity knowledge graph; performing topological structure derivation on the dynamic commodity knowledge graph to generate a graph topological analysis report and a metadata list, and performing knowledge reasoning integration on the graph topological analysis report and the metadata list to generate an intelligent navigation engine; calling an intelligent navigation engine to execute multi-path semantic query and rule verification on the dynamic knowledge graph to generate a candidate classification scheme set; and performing multi-target collaborative optimization on the candidate classification scheme set to generate a sorting scheme sequence, performing traceability packaging on the sorting scheme sequence, and outputting an intelligent classification scheme. According to the invention, through the dynamic interaction model and multi-target collaborative optimization, the rule adaptation efficiency in a complex scene is improved.

The invention discloses a refined target detection method based on superpixel guidance and double-flow feature fusion, and belongs to the field of computer vision. According to the method, a global semantic flow and super-pixel contour flow parallel architecture is constructed, high-level context features are extracted from the global semantic flow, super-pixel boundary significance of the super-pixel contour flow is modeled through a boundary feature attention graph convolutional network (BA-GCN), and fine contour features are obtained. A semantic query gating fusion (SQ-GF) module is innovatively designed to realize deep interaction of semantics and contour features, and a refined bounding box fitting a real contour of a target is output in combination with a dual-supervision detection head. The method solves the problems that a traditional rectangular frame is limited, fine-grained information is lost and feature fusion is insufficient, improves irregular target boundary positioning precision, and is suitable for high-precision scenes such as medical images and industrial defect detection.

The invention relates to a zero sample semantic segmentation method and device based on adaptive prompt and dynamic query. The method comprises the steps of obtaining image data and corresponding category semantic information, and performing preprocessing to obtain an input image and an input category semantic text; constructing a zero-sample semantic segmentation model based on adaptive prompt and dynamic query, wherein the model comprises a visual encoder, a text encoder, an adaptive visual prompt module, a dynamic semantic query module and an image segmentation prediction module; inputting the input image and the input category semantic text into the zero sample semantic segmentation model, designing a loss function combining segmentation supervision and different modal alignment constraints, and performing model training and optimization; and under conduction type or induction type zero sample setting, testing the zero sample semantic segmentation model by using an image to be processed, and outputting a corresponding segmentation result. And the zero sample semantic segmentation accuracy and robustness in a complex scene are remarkably improved.

The invention discloses an SAM2 small sample segmentation method based on semantic-visual dual-memory fusion, and the method comprises the steps: constructing semantic query memory, visual query memory and query-related support visual memory, and fusing the semantic query memory and the visual query memory through a memory refinement module guided by the query-related support visual memory. SAM2 dense matching and decoding module end-to-end training are combined. The problems of single memory and foreground-background confusion of an existing method are solved, target semantic consistency and fine-grained modeling ability are enhanced, segmentation precision and generalization ability are remarkably improved in a complex scene, and the method is suitable for the fields of medical image analysis, automatic driving and the like.

The invention discloses a standard text semantic analysis and key clause extraction method and system, and the method comprises the steps: carrying out the multi-level semantic analysis of a standard text, recognizing a to-be-evaluated clause and a corresponding type in the standard text, extracting a key parameter entity of the to-be-evaluated clause, and constructing a clause-level semantic association structure; based on the semantic association structure, a standard term parameter knowledge graph is constructed, and the knowledge graph supports semantic query of technical parameters; and performing weight calculation and screening on the to-be-evaluated terms based on the standard term parameter mapping knowledge domain, and generating a structured standard requirement abstract list based on the screened key terms and associated parameter information in the corresponding mapping knowledge domain. In combination with multi-level semantic analysis and parameterized knowledge graph construction, automatic and structured extraction of standard text core requirements is realized, and the technical problems of low efficiency, incomplete key information coverage and lack of semantic association caused by dependence on manpower or shallow text processing are solved.

The invention relates to the technical field of computer vision and artificial intelligence, in particular to a cross-domain three-dimensional perception method combining geometric and semantic dual paths, which comprises the following steps of: 1, acquiring a multi-view image, and extracting a multi-scale two-dimensional feature map by using a two-dimensional feature encoder; 2, inputting the extracted two-dimensional feature map into a geometric generalization path, and carrying out the operation of self-supervised depth enhancement and explicit fusion to obtain geometric enhancement features; 3, inputting the extracted two-dimensional feature map into a semantic generalization path, and carrying out semantic query and domain confrontation fusion operation to obtain semantic enhancement features; and 4, finally fusing and decoding the geometric enhanced features and the semantic enhanced features to obtain a three-dimensional occupancy graph. The generalization performance of the method is improved in a breakthrough mode, and the method has the advantages that the practicability of the model is greatly enhanced, geometric perception is more accurate, three-dimensional reconstruction is more fidelity, semantic understanding is more consistent, and cross-domain recognition is more reliable.

This invention presents a face forgery detection method based on a query-driven forensic adapter, belonging to the fields of artificial intelligence and machine learning. It aims to address issues such as insufficient modeling of local forgery regions, limited interaction between semantic and visual features, and poor cross-distribution generalization performance. First, this invention proposes a dynamic semantic query module. This semantic query is injected as a dynamic attention signal into the multi-head attention mechanism of the CLIP encoder, effectively guiding CLIP to focus on potential forgery regions, improving its response to local anomalies such as boundary discontinuities and texture inconsistencies, and compensating for its insufficient local modeling capabilities without altering the CLIP's core structure. Second, this invention proposes a multi-scale feature aggregation mechanism. It proposes a semantically guided attention fusion module and a feature enhancement strategy based on linear interpolation. This method can effectively improve sample diversity and enhance the model's robustness and generalization ability across forgery methods and datasets.

The application is suitable for the technical field of data processing, and provides a database query method, system, device and medium based on natural language. The method comprises the following steps: acquiring a natural language text; based on the natural language text and a field library, calling a root matching strategy, a semantic matching strategy and a fuzzy matching strategy through a hierarchical cooperation mechanism to perform field mapping and determine a target field; splicing the target field to obtain an initial semantic query statement; loading and executing multiple correctors in sequence through a service discovery mechanism to obtain a target semantic query statement; converting the target semantic query statement to obtain a target physical query statement; executing the target physical query statement to obtain a target query result and return the query party. Through hierarchical cooperation of the root matching strategy, the semantic matching strategy and the fuzzy matching strategy, the application improves the scalability and adaptability of the matching strategy, improves the field recognition accuracy, expands the field matching range, and optimizes the matching efficiency.

The invention relates to the technical field of artificial intelligence, in particular to a large language model access control method and system fusing semantic intention and authority, and the method comprises the steps: obtaining query content input by a user, and carrying out semantic decomposition to obtain structured intention elements; performing matching verification on the intention elements and an authority strategy library; according to a verification result, performing dynamic treatment of releasing, rewriting or refusing on the query intention of the user: if the query intention exceeds the permission range and does not violate the permission strategy, rewriting the query intention, and performing matching verification again; and refusing the query request if the permission range is exceeded and the permission policy is violated. By applying the method, the semantic query intention of the user can be understood, access control of accurate permission judgment is performed based on the intention, the user experience can be improved, and the system security can be ensured.

A query processing system for providing a generic query interface for different customers' industrial systems, wherein the query processing system (1) comprises: - an application query interface AQI (2) adapted to input a customer query Q of a customer's industrial system; - a query processing unit (4) configured to automatically perform a query decomposition of the input customer query Q into query parts QP based on a query reformulation model QRM stored in a database (5) of the query processing system (1), wherein for each decomposed query part QP it is determined by the query processing unit (4) whether the decomposed query part is available in an application semantic model ASM stored in a database (6) of the query processing system (1), wherein the query processing unit (4) is further configured to automatically reformulate query parts not available in the application semantic model ASM based on the query reformulation model QRM and to automatically perform a query recombination of the query parts available in the application semantic model ASM and the reformulated semantic query parts to generate a generic query gQ which is applied to an application logic (3) of the query processing system (1) to provide a query result QR output by the application query interface AQI (2).

The application belongs to the field of intelligent ticket management, and specifically relates to a financial ticket information automatic input system based on artificial intelligence, which comprises a ticket collection module, a multi-scale self-adaptive noise reduction module, an intelligent classification module and an intelligent partition input module; the application adopts a feature double-domain self-adaptive enhancement method based on transpose self-attention, improves noise reduction robustness, specifically processes different noise types, overcomes the limitation of a single domain, restores the global structure while retaining the details, increases the noise reduction capability of the ticket image, and improves the text detection efficiency; the application adopts a document intelligent partition method, unifies heterogeneous tasks into the combination of instance and semantic segmentation, avoids model redundancy, maps the category name into a semantic query, supports open set classification and zero sample migration, realizes the dynamic interaction of instance and semantic query through hybrid query, enhances the understanding of the model to the complex document structure, and realizes efficient ticket image partition information extraction and input.

A semantic query processing system enables data analytics through a metadata-driven architecture. The system processes analytical queries through a layered execution path that maintains consistent logic across system components. For incoming semantic queries, the system coordinates processing between semantic and storage layers instead of, or in addition to, requiring pre-materialized calculations. A gateway service receives semantic queries while a query preparer generates execution plans based on semantic model metadata defining relationships, measures, and dimensions. A query generator transforms these plans into optimized SQL operations, with complex calculations handled through post-processing. The system reduces analytical complexity by eliminating pre-calculation requirements, enables real-time metric computation through coordinated query processing, and maintains semantic consistency through metadata-driven execution. This architecture achieves improved response times for complex metrics while preserving consistent calculation logic across distributed components.

The application discloses an import and export commodity intelligent classification method based on knowledge graph metadata topology, relates to the technical field of reinforcement learning, and comprises the following steps: inputting initial data packets into a dynamic interaction model, performing explicit association mining in a semantic enhancement layer, optimizing rule matching paths in a rule evolution layer, and constructing a dynamic commodity knowledge graph; performing topology structure derivation on the dynamic commodity knowledge graph, generating a graph topology analysis report and a metadata list, integrating knowledge reasoning on the graph topology analysis report and the metadata list, and generating an intelligent navigation engine; calling the intelligent navigation engine to perform multi-path semantic query and rule verification on the dynamic knowledge graph, generating a candidate classification scheme set; performing multi-objective collaborative optimization on the candidate classification scheme set, generating a sorting scheme sequence, performing traceability packaging on the sorting scheme sequence, and outputting an intelligent classification scheme. The application improves the rule adaptation efficiency in complex scenarios through the dynamic interaction model and multi-objective collaborative optimization.

The application discloses an ontology-based lithium ion battery degradation analysis and predictive maintenance method and system, wherein the method comprises the following steps: acquiring test data of a lithium ion battery, preprocessing the test data, and storing the preprocessed test data into a relational database; constructing a battery health analysis ontology, and defining classes, attributes, constraint relationships and reasoning rules of the ontology; mapping the test data in the relational database to the battery health analysis ontology, and constructing a virtual knowledge graph; searching and analyzing a battery degradation state in the virtual knowledge graph through semantic query, and generating a battery degradation analysis result; training a machine learning prediction model based on the battery degradation analysis result, and predicting the battery degradation state of a to-be-tested battery based on the trained machine learning prediction model, so as to realize predictive maintenance of the battery.

Properties for an ontology, such as used for semantic query execution, automated analytical reasoning, or for machine learning, are determined using instance graphs. A corpus of documents is received, representing a plurality of domain instances of a domain. Instance graphs are generated for instances of the plurality of instance graphs to provide a plurality of instance graphs. Properties represented in the plurality of instance graphs are determined. At least a portion of the properties are assigned to an ontology for the domain.

The invention discloses a maritime affair information processing and decision making system based on multidimensional data analysis, and relates to the field of maritime affair data analysis, and the system comprises a graph construction module which uses a maritime affair data set to define a maritime affair ontology library, carries out the filling, trains a bidirectional LSTM model through a maritime affair situation data set, and obtains a maritime affair ontology library; identifying an implicit mode of the maritime scene and integrating the implicit mode with an external knowledge base to form a maritime knowledge graph; the query module is used for constructing a semantic index tree and querying an entity relationship in the maritime affair knowledge graph by utilizing the semantic index tree to obtain a semantic query result; and the evaluation module is used for constructing a maritime affair digital twinborn model according to the semantic query result, carrying out multi-physics field simulation by utilizing the maritime affair digital twinborn model, evaluating the comprehensive risk of the maritime affair environment and generating a risk evaluation data set. According to the method, environment-ship-event semantic association deduction is realized by constructing the maritime affair knowledge graph, a single risk assessment dimension is improved, and global maritime affair decision support is realized.

The embodiment of the invention relates to an information processing method and device, equipment and a storage medium. The method comprises the steps that query information is received, path condition information is extracted from the query information, vector data corresponding to a directory path indicated by the path condition information is determined from directory index data of a vector database, and a vector data set is formed. The directory index data comprises a corresponding relation between vector data in the vector database and a directory path, and the directory path is used for identifying a storage position of the vector data in the vector database. And performing vector retrieval in the vector data set according to the query information to obtain a retrieval result. The directory semantic query capability is supported, the vector retrieval range of the query information can be determined based on the directory hierarchical structure, vector retrieval is performed on the query information in the range, and the quality of a vector retrieval recall result is improved.

The present application belongs to but is not limited to the technical field of shale gas production, and particularly relates to a method and system for ontology graph construction and abnormal cause-effect chain tracing, comprising: S1, well, pry, process, pressure difference, alarm, operation event object and relationship mode; S2, cause-effect chain coding: forming a calculable path of 'upstream equipment-process-downstream abnormality'; S3, realizing bidirectional linkage of ontology graph and detection result. The ontology knowledge graph of different business scenarios in the field of shale gas is constructed, and the well, pry, process, sensor entity and their relationships are defined; when the abnormal detection model outputs the result, the result is mapped to the graph; through graph query or graph traversal algorithm, the upstream and downstream associated entities of the abnormal node are automatically traced, and natural language explanation is generated; an interface supporting semantic query is provided, and the user is allowed to ask questions in an exploratory manner.

Aspects of the invention may comprise a method for improving execution speed of a semantic query on a database by executing the semantic query on a subset of relevant documents in the database. The method may provide for improving execution speed without sacrificing accuracy because the subset of documents comprises documents relevant to the semantic query. Aspects of the invention may further provide for identifying key concepts in a semantic query and generating a filter query based on the identified key concepts. The filter query may be used to select the subset of relevant documents. Aspects further provide for generating one or more keyword queries based on a key concept and at least one search operator. The filter query may incorporate at least one keyword query. Aspects of the invention further comprise implementing entity recognition, metadata filtering, and essentialness to improve the selected subset.

This invention discloses a method, apparatus, and storage medium for converting natural language to SQL in the securities industry, relating to the field of natural language processing technology. The invention first matches natural language with a knowledge graph to obtain a target sub-graph. Then, it extracts all triples from the target sub-graph and matches each triple with the original text fragment from the natural language. Each triple can be used as a smaller unit of the text fragment for semantic querying, thereby retrieving the original text fragment from the natural language. This invention uses triples in the target sub-graph to segment the natural language, thus filtering out the most reasonable M text fragments. Because the process of determining the text fragments is relatively reliable and reasonable, the table template determined based on the text fragments is also more reliable. Filling the table template with natural language yields a more reliable tabular language, and ultimately, based on the tabular language, a more accurate SQL statement can be obtained.

A multi-path recall rearrangement method, comprising the following steps: step 1, establishing a combined query of a structured query, a keyword query and a semantic query according to information input by a user query; step 2, performing specific recall according to different queries of step 1, thereby performing corresponding entity recognition, synonym processing and vector similarity judgment to form a candidate set; step 3, sorting the candidate set according to problem relevance, vector similarity, timeliness and business characteristics; and step 4, forming an ordered list and outputting the most relevant, latest and most authoritative result.