539 results about "Semantic layer" patented technology

The invention provides an AI-based marketing video auditing method, and relates to the technical field of AI marketing video auditing, and the method comprises the steps: obtaining a multi-modal data original structure set, and extracting image semantic features, voice expression features, text semantic features and scene label information, and obtaining an image semantic feature set, a visual rhythm feature set, a voice expression feature set, a voice and picture synchronous association vector structure, a text semantic feature set and a subtitle semantic and image main body linkage relation graph. By constructing an image semantic feature set, a voice expression feature set, a text semantic feature set and a visual rhythm feature set and fusing the image semantic feature set, the voice expression feature set, the text semantic feature set and the visual rhythm feature set into a multi-modal content fusion feature tensor, unified modeling of an AI marketing video at visual, auditory and semantic levels can be realized; and subsequent microscopic consistency detection, compliance knowledge graph and emotion semantic conflict identification are effectively performed, so that full-link risk perception and accurate auditing of video contents are realized.

The invention discloses an intelligent approval rule modeling method oriented to process automation, and relates to the technical field of business process management, and the method comprises the following steps: S100, in a process of constructing a rule candidate set, extracting scene features, field semantic hierarchy and participation role information of each piece of historical approval data, generating a context semantic tag set, and establishing a rule candidate set; the method is used for subsequent rule difference modeling. According to the method, context semantic tags are introduced to be aligned with ternary features, so that the semantic boundary recognition capability of the rule is enhanced; constructing a rule feature matrix and a differentiation candidate set, and realizing accurate classification and processing of ambiguity rules; in combination with expression sensitivity enhancement and simulation verification, approval offset and risk are identified in advance; finally, the dynamic optimization of the rule model is realized through backtracking correction, the stability and accuracy of the rule model in multiple scenes are improved, and a closed-loop credible intelligent approval rule system is constructed.

The invention discloses an unmanned aerial vehicle image small target detection method based on dynamic filtering and an adaptive sparse Transform. According to the method, an end-to-end target detection framework is adopted, a dynamic filtering module is introduced into a backbone network, global feature interaction is achieved through data-dependent frequency domain operation, and linear calculation complexity is maintained. For feature interaction in a scale, an adaptive sparse Transform module is introduced to enhance the capability of focusing key information on high semantic hierarchy features of a model, and noise interference and feature redundancy are effectively suppressed at the same time. Through the combination of dynamic filtering and adaptive sparse Transform, the model can extract image foreground information more effectively on the premise of not significantly increasing the calculation burden, and the problem that a traditional target detection model is susceptible to complex background interference is significantly relieved.

The invention provides an RAG knowledge base construction method and system based on hierarchical semantic indexes. The method belongs to the cross technical field of artificial intelligence and information retrieval. The method comprises the following steps: performing multi-level semantic analysis on an input original document set to generate document semantic hierarchical structure data; constructing a hierarchical semantic index tree based on the document semantic hierarchical structure data; performing dynamic knowledge graph initialization according to the hierarchical semantic index tree to generate an initial dynamic cognitive graph; and collecting real-time interaction data through a user feedback interface and a new data access module, and performing incremental updating on the initial dynamic cognitive map to form a knowledge representation system supporting life cycle evolution. Through multi-level semantic analysis and construction of a hierarchical semantic index tree (HSIT), deep semantic analysis can be performed on an original document set, the context integrity of knowledge is ensured, structured storage is realized, the knowledge can be expressed and stored more accurately, and information loss or semantic ambiguity is avoided.

The invention relates to the technical field of big language models, and discloses a big language model training method based on knowledge graph enhancement, comprising the following steps: S1, constructing a multi-source heterogeneous knowledge graph; s2, coding the mixed attention heterogeneity map; s3, bidirectionally mapping a pre-training task; and S4, position specific gating fusion. According to the big language model training method and system based on knowledge graph enhancement, a same proton graph is established for a structured triple and text entity description, nodes are connected across graph edges to form a heterogeneous graph, associated edges are established through entity linking and syntactic analysis, multi-source knowledge is modeled in a unified mode, and the problem of low fusion efficiency is solved; mixed attention coding adopts a layering mechanism, a semantic level calculates weights according to type compatibility, a node level calculates similarity aggregation features through cosine distance and path length, entity vectors are generated through pooling, map structures and semantics are explicitly learned, reasoning accuracy is improved, and the problem of knowledge understanding superficial layer is solved.

The invention provides a semi-supervised image semantic segmentation method and system based on a visual basic model, and the method comprises the steps: constructing a multi-task model which comprises a visual basic model and a depth estimation basic model, and the visual basic model is connected with a task solution head, an adapter parameter efficient fine tuning module and a multi-modal cross fusion module; the task solution head comprises a semantic segmentation head and a depth estimation head; extracting semantic hierarchy features and a depth feature map of the RGB image, performing cross attention fusion on the semantic hierarchy features and the depth feature map, and inputting obtained fusion features into a semantic segmentation head and a depth estimation head respectively; semi-supervised learning is adopted to train a multi-task model, only parameters in the adapter parameter efficient fine tuning module and the multi-modal cross fusion module are trained, and a multi-task loss function is adopted. The image semantic segmentation model obtained through training can improve semantic segmentation performance, reduce training cost and is suitable for different tasks.

An illustrative method for querying multiple datasets may include generating, based on models each associated with and defining attributes of a different datasets stored in a plurality of data stores, a semantic layer defining relationships between the models and that provides a centralized application programming interface (API) for exposing the datasets by way of a common query language, receiving, by way of the centralized API, a query request for information that depends on data included in multiple datasets included in the plurality of datasets, querying, based on the query request and the relationships between the models defined by the semantic layer, the multiple datasets, and presenting, based on the querying, a query result representative of the information that depends on the data included in the multiple datasets.

The invention provides a code generation method and system based on a waterfall model and multi-agent collaboration, and the method comprises the steps: constructing a multi-agent collaboration framework which comprises a problem analysis agent, a solution agent, a pseudo-code agent, a coding agent and a restoration agent based on a software development waterfall model thought; and the interaction process of each agent is coordinated through a dynamic cooperation algorithm. Wherein the problem analysis intelligent body checks similar problems and solutions; the solution intelligent agent generates and evaluates candidate schemes; performing scheme conversion by the pseudo-code intelligent agent; the coding agent generates an executable code; and the repair agent performs fine-grained repair on the code in grammar, runtime and semantic levels through a two-dimensional repair mechanism. According to the method, the limitation of a single agent in a complex programming task is broken through, automatic code generation covering the whole process of demand analysis, scheme design, code implementation and test repair is realized, and the quality of generated codes and the reliability of operation are remarkably improved.

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 relates to the technical field of natural language processing, in particular to a context-based Prompt generative model optimization system, which comprises a context analysis module, a cue word generation module, a context optimization module, a semantic check module and a structure reconstruction module. According to the method, the context path and the semantic hierarchy information of the semantic unit are introduced, the fine degree of semantic matching degree recognition is improved, semantic guide deviation caused by statement template solidification is avoided, the cue words are recombined in combination with the semantic coherence weight and the logic dependency relationship, and the recognition accuracy is improved. The consistency and expression accuracy of the prompt content in the context are enhanced, the prompt word insertion sequence and connection mode are dynamically adjusted through a semantic conflict detection and structure rechecking mechanism, coherence and stability of a semantic structure and controllable generation of the prompt content are kept, semantic conflicts and expression chaos caused by static matching are effectively avoided in the generation process, and the generation efficiency is improved. And dynamic adaptation of prompt configuration and smooth optimization of language output are integrally realized.

The embodiment of the invention discloses a dynamic metadata sensing and self-adaptive mapping method and system, and the method comprises the following steps: deploying a lightweight probe to be agented to a plurality of heterogeneous source database systems, and building a trusted communication channel between the probe and a coordination center through equipment fingerprint generation and security authentication; a database log event is captured in real time, log analysis is carried out through an FPGA module, the change of a field structure or a semantic level is identified, and structured event data is generated; performing context embedding representation on the captured event based on a semantic understanding model, performing strategy reasoning in combination with a historical strategy and a knowledge graph, and generating a matched mapping strategy; loading and executing the mapping strategy in a trusted execution environment (TEE) to realize data conversion, cleaning and complementation, and performing desensitization processing on sensitive data through a differential privacy mechanism; and collecting performance indexes and abnormal logs of a strategy execution result, continuously training the model through a closed-loop optimization mechanism, and correcting an unreasonable strategy or updating a rule base.

The invention relates to the technical field of intelligent abstract generation, in particular to an intelligent archive abstract generation system and method based on a natural language processing technology. The system comprises a multi-layer semantic generation core unit which performs semantic hierarchical segmentation analysis on an original file text to construct a multi-layer semantic graph, and constructs an abstract generation model to generate abstract content; the knowledge graph fusion engine unit associates and extracts terms in an original file text, constructs an entity mapping relation, and sets semantic graph node expression weights in an abstract generation model according to semantic association confidence scores; a paging index cache retrieval unit performs fragment division processing on each node in the multi-layer semantic graph, and constructs an abstract content fragment index structure containing a node set; and the version tracing transaction management unit carries out version recording on generation and modification operations of the abstract contents. The invention discloses an intelligent archive abstract generation system which is constructed by fusing a multi-layer semantic graph and is associated with a knowledge graph.

The invention belongs to the technical field of artificial intelligence and multimedia processing, and discloses a multi-modal content conflict resolution method based on modal time sequence dependence modeling, which comprises the following steps of: constructing a modal representation vector by unifying time, space, semantics and priority information of modeling modal contents; and further structuring and quantifying complex dependency and conflict relationships among different modal contents by utilizing a modal time sequence dependency graph, and constructing a context relationship by combining a graph neural network, so that the system can identify conflicts of the contents in time, space and semantic levels, and realizes self-adaptive content reordering and display configuration based on conflict scores. According to the method, the limitation of traditional single-dimension conflict detection is overcome, the accuracy rate and the coverage range of conflict identification are improved, the method can be widely applied to multi-modal content-intensive scenes such as intelligent media generation, AI broadcasting, virtual navigation and XR interaction, information shielding and semantic redundancy are reduced, and the interaction experience of users and the system content quality are enhanced.

The invention belongs to the field of artificial intelligence, and particularly relates to a disaster risk early warning algorithm based on multi-modal fusion and a space-time propagation model, which comprises a multi-modal data management module, a cross-modal semantic alignment module, a space-time propagation graph modeling module, a propagation constraint deduction module, a graded early warning generation module and an online closed-loop calibration module. Depth alignment of multi-modal data on a semantic level, dynamic deduction of a disaster propagation process under constraint of a physical mechanism and operable conversion of an early warning result in a business scene are realized, and the whole system takes a unified space-time framework as a base, takes a propagation graph as a link and takes closed-loop calibration as a guarantee, so that the accuracy of the system is improved. The structural defects of extensive data splicing, propagation modeling deficiency and decision chain fracture in a traditional early warning method are fundamentally overcome.

The invention relates to the technical field of intelligent recommendation, and discloses an AI intelligent matching method based on a knowledge graph, and the method comprises the steps: constructing a quaternary knowledge graph containing a time dimension; identifying legal entities and semantic relationships by adopting an entity identification and relationship extraction technology; multi-level semantic features are extracted through a two-layer progressive semantic matching algorithm of a grammar layer, a semantic layer and a reasoning layer; constructing lawyer ability portraits based on a heterogeneous graph neural network and a time sequence perception graph convolution technology; progressive matching calculation is adopted, the optimal matching weight is learned through a multi-layer attention mechanism, and dynamically optimized intelligent matching is achieved. The technical problems of cold start, insufficient semantic understanding ability and poor timeliness processing ability in the existing legal consultation matching system can be solved, and the matching precision and the user satisfaction are improved.

The invention provides a data conversion method which can be applied to the technical field of big data. The data conversion method comprises the steps of obtaining metadata and relational statements in a source database; analyzing the metadata, converting the metadata into an intermediate format, and constructing a metadata intermediate model; analyzing the relation statement, extracting semantic levels in the relation statement, and constructing a semantic intermediate model; and associating the metadata intermediate model with the semantic intermediate model, converting the metadata intermediate model into metadata corresponding to a target database according to a preset conversion rule, and converting the semantic intermediate model into a relation statement corresponding to the target database. The invention further provides a data conversion device and equipment, a storage medium and a program product.

The invention relates to a visual narrative generation method oriented to a Chinese ancient time sequence image. Coherent creation under a historical context is realized through multi-modal collaboration and knowledge guidance. According to the algorithm, a culture-enhanced CLIP-ct model is adopted to carry out multi-modal feature fusion, an ornamentation semantic layer is expanded in a traditional CLIP architecture, and visual culture symbols such as traditional painting features and clothing patterns are accurately decoded; constructing a KG-Transform hybrid generation framework, and fusing a knowledge graph through a dynamic knowledge gating mechanism; meanwhile, culture conflict detection is designed to ensure time consistency, and finally plot development is optimized through Monte Carlo tree search to ensure rationality and creativity of plots. According to the method, an extensible technical normal form is provided for the field of cultural computing, the method can be applied to scenes such as cultural relic digital narration and non-cultural skill inheritance, and intelligent decoding and innovative expression of traditional cultural resources are promoted.

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 discloses an Internet of Things multi-source heterogeneous data management method based on artificial intelligence, and the method comprises the following steps: collecting voice data and text data in an Internet of Things system, and constructing a voice and text pair; inputting the voice data into an improved Whisper model, and outputting an enhanced transliteration text; inputting the enhanced transliteration text and the text data into a semantic encoder based on dynamic weighting to generate a fused semantic embedding vector; calculating semantic similarity between the fused semantic embedding vectors, and screening semantic consistent sample pairs; performing event aggregation on the semantically consistent sample pairs; performing semantic level coding and confidence adaptive fusion processing to generate a unified semantic fusion vector; and constructing a backmarking training set based on expert feedback, and executing periodic increment optimization on the updatable parameters. The voice and text multi-modal data fusion quality and semantic consistency recognition precision are improved, and the method has good expandability and is suitable for intelligent data governance tasks in a complex Internet of Things environment.

The embodiment of the invention provides a big data analysis visualization method and device based on a big model, a medium and a product. The method comprises the following steps: receiving a natural language demand input by a user; performing semantic layer, logic layer and task layer decomposition on the natural language demand by adopting a preset hierarchical analysis model to generate an executable data analysis instruction; obtaining target data required by the data analysis instruction; according to the data analysis instruction, the target data, a preset chart recommendation algorithm and an aesthetic evaluation optimization algorithm, generating a basic visual chart; and learning the user preference characteristics through the visual generative adversarial network, dynamically adjusting the basic visual chart according to the user preference characteristics, and generating a personalized visual result corresponding to the natural language demand. According to the scheme, the defects of an existing dragging type visualization system and an existing programming type visualization scheme in the visualization process are overcome.

The invention relates to a pavement disease detection method, system and device based on a hybrid architecture, and a storage medium. The method comprises the following steps: obtaining pavement image data; the method comprises the steps that data are input into a re-parameterized feature extraction network, the network is based on an HGNetV2 architecture, a RCHGBlock module is formed by embedding a RepConv structure into HGBlock, and a plurality of modules are cascaded and stacked to construct a four-stage progressive feature pyramid structure; based on a high-level semantic layer of a feature pyramid, integrating a space edge perception enhanced attention mechanism, enhancing disease edge features through a dual-path complementary processing framework of an edge extraction path and a standard convolution path, and performing multi-scale feature fusion by using an improved C3K2-SEAM module as a feature fusion unit; and performing end-to-end disease detection based on the fusion features, and outputting disease types, positions and confidence information. Compared with the prior art, the method has the advantage that the disease detection precision and robustness in a complex scene are remarkably improved.

The invention relates to the technical field of visual navigation, in particular to a blind person navigation path planning method combining visual SLAM and semantic segmentation. The method comprises the following steps: acquiring an environment image and pose data; performing front-end tracking by using the pose data, and determining a key frame sequence; generating a depth map based on the environment image, and identifying a passable area according to the depth map; constructing a three-dimensional point cloud map according to the key frame sequence; semantic segmentation is carried out according to the three-dimensional point cloud map, and obstacle type labels are recorded; according to the obstacle type label, carrying out safety level layering on the passable area, and determining a path cost weight; performing global path planning based on the path cost weight, and generating a semantic enhancement navigation trajectory; and driving real-time voice guidance by using the semantic enhancement navigation trajectory, and calculating a path execution deviation corresponding to the real-time voice guidance. According to the method, obstacle types are distinguished through semantic segmentation based on a visual navigation technology, a semantic enhancement path is generated, semantic hierarchical navigation is realized, and the intelligence of path decision is improved.

The invention relates to the technical field of natural language processing, and discloses a question retrieval method and system, electronic equipment and a storage medium. The method comprises the steps of performing semantic understanding and decomposition processing on an original question to obtain a plurality of candidate sub-questions; constructing an initial problem tree structure by taking the original problem as a root node and the candidate sub-problems as sub-nodes; rationality scores of the child nodes are determined, and the rationality scores represent rationality of candidate sub-problems corresponding to the child nodes; determining a relevance score between the nodes, the relevance score representing a semantic repetition condition between the nodes; based on the rationality score and the relevance score, optimizing the initial problem tree structure to obtain a target problem tree structure; and performing retrieval based on the target question tree structure to obtain answer data for the original question. By means of the method, rationality and relevance evaluation can be conducted on the problem tree nodes, and architectural disassembly and semantic hierarchical management of complex problems are achieved.

The invention provides a multi-model scheduling and structural semantic fusion document review method, which comprises the following steps of: rearranging contents in a to-be-reviewed document on the basis of a semantic hierarchical structure of the to-be-reviewed document to obtain a structured recombined document; constructing a review task graph of the to-be-reviewed document; and configuring a task route for each review task in the review task graph, executing the plurality of review tasks based on the review task graph configured with the task routes, and determining a review result of the structured recombined document. In the face of a large number of dense document scenes, the automatic document review process is achieved, the review efficiency is effectively improved, meanwhile, the accuracy and consistency of review results are guaranteed by means of structured processing and accurate model calling, and the requirements of services for high efficiency, high accuracy and high consistency are fully met.

The invention relates to the field of target detection, and particularly discloses an electric power work target detection method based on multi-modal large model knowledge distillation, which utilizes a vision-language multi-modal large model as a teacher model, and improves the target detection efficiency by expanding prompt word guidance. A high-quality pseudo label and a region-text pair are generated for an unlabeled electric power work image as a supervision signal, and on this basis, through joint optimization of detection loss, feature distillation loss, logic distillation loss and multi-modal contrast learning loss, a lightweight YOLO student model is guided to learn positioning and classification knowledge and to learn a multi-modal contrast learning loss. And deep alignment with the open vocabulary understanding ability of the teacher model is carried out on the feature space and semantic level, so that a semantic gap between closed category detection and open world perception is effectively bridged. Through the mode, the detection precision and generalization ability of the student model on common, rare and even unseen targets in the electric power work scene are remarkably improved.

An object identification system includes: a category module configured to, for a category of a vocabulary of objects, retrieve a hierarchy including at least: a sub-category that is more specific than the category; and a super-category that is less specific than the category; a sentence module configured to generate a set of sentences for the category that describe the hierarchical relationship between sub-category, super-category, and the category; an encoder module configured to encode the sentences into encodings, respectively, for the category; an aggregator module configured to generate an aggregated encoding for the category by aggregating the encodings of the category; and an identification module configured to selectively identify an object included in a region of interest of an input image as being in the category based on a comparison of (a) an encoding of the region of interest and (b) the aggregated encoding for the category.

The invention provides a multi-level semantic map construction method based on multi-sensor fusion, and the method carries out the construction of an environment grid layer, and comprises the steps: constructing an environment grid map in real time through fusing perception data; scene semantic layer construction: extracting image scene semantic probability distribution by using a deep convolutional network, fusing time sequence observation through Bayesian filtering, and mapping a scene category to a grid unit by using an occupation probability model; constructing an object semantic layer, namely identifying an object by adopting a target detection network in which an information aggregation-distribution mechanism is introduced, extracting an object point cloud, and dynamically updating object semantic attributes of grid units through multi-source observation fusion; and scene atlas generation: constructing a hierarchical scene atlas which takes the marker object as a reference core and comprises a spatial topological relation. According to the method, the dynamic environment adaptability and the multi-modal data fusion precision of semantic mapping are improved, a more visual environment understanding mode is provided for the robot, and the practicability of the semantic map in robot positioning and navigation is improved.

The invention discloses a ship knowledge graph construction method based on a large model and a graph neural network, and the method comprises the steps: carrying out the format conversion and protection type partitioning processing of a professional document, and completing the recursive segmentation through a placeholder protection formula, a table and other structures according to the semantic hierarchy, and obtaining a text block suitable for the extraction of an entity and a relation; extracting domain entities by utilizing a large language model containing thinking chain cues, and positioning candidate entities in combination with an AC automaton so as to improve the coverage rate and accuracy of relation triple extraction; performing new entity backfilling and relation standardization on an extraction result, and constructing an initial knowledge graph with a consistent structure; and inputting the initial knowledge graph into a graph neural network model with directional expansion and a multi-scale decoder, and complementing a missing relationship through link prediction, so that node distribution and a relationship structure of the graph are more complete. According to the method, a continuous processing chain from text preprocessing, knowledge extraction to graph completion is formed.

The invention discloses a dual-machine target positioning method based on semantic prior and spatial intersection constraint. The method comprises the following steps: 1, acquiring images of a camera 1 and a camera 2, and determining the spatial orientation of a camera coordinate system relative to a reference world coordinate system; step 2, obtaining a target normalized coordinate under a coordinate system of the camera 1; step 3, obtaining a target normalized coordinate under a coordinate system of the camera 2; 4, converting the normalized coordinates of the target into geometric rays in a three-dimensional space; 5, constructing an optimization function with the minimum distance sum of squares; step 6, performing semantic-level foreground and background division on the image content through a YOLOv5 network, and constructing a three-dimensional space feature point library of a semantic background; and 7, performing single-view semantic neighborhood retrieval and depth compensation by using the three-dimensional space feature point library of the semantic background constructed in the step 6, and realizing target three-dimensional positioning in a high-altitude long-distance complex scene. According to the invention, the detection robustness and the positioning precision of the high-altitude long-distance target in the environment are improved.

The invention discloses an electric power system data anomaly prediction method based on deep learning, and relates to the field of data anomaly prediction.The method comprises the steps that firstly, a graph convolutional network and LSTM are used for deeply mining time series data of an electric power system and spatial-temporal characteristics of a topological structure, and high-precision anomaly detection and positioning are achieved; and when an exception is detected, an exception attribution mechanism is introduced, and exception signal features (such as exception fragments and positioning information) at a mathematical level are converted into a structured query object at a semantic level. And then, a barrier between numerical data and the unstructured operation and maintenance knowledge base is broken through a vector retrieval technology, and related maintenance regulations and historical cases are accurately recalled. And finally, an executable recommended disposal scheme is automatically generated based on recall knowledge in combination with the generation capability of a large language model, so that an intelligent closed loop from anomaly perception and knowledge matching to decision assistance is constructed, and the accuracy and efficiency of power system fault handling are remarkably improved.