181 results about "Semantic labeling" patented technology

The invention discloses an intelligent monitoring management method and system based on archive digitization, and relates to the technical field of data management, and the method comprises the steps: collecting and preprocessing multi-source archive data, employing a multi-mode BERT model to carry out the feature fusion of different data sources, and generating a unified semantic representation; semantic labeling is performed on archive data through a multi-label classification model, a semantic graph of archive content is constructed by using a graph database, an association relationship between archives is represented, a semantic index tree is constructed based on the semantic graph, and rapid positioning and calling of the archive content are optimized; and recording the change of each file version, positioning the change position based on a semantic index tree, identifying the semantic change of the file through a semantic difference comparison algorithm, recording hash, carrying out granularity division on the file content through the semantic boundary of each level of node in the index tree, and generating a user access strategy. According to the invention, dynamic perception and risk early warning of user behaviors are realized, and the intellectualization and safety of the archive management system are effectively improved.

The invention provides an end-to-end automatic driving track generation method and system, computer equipment and a medium, and belongs to the field of path intelligent planning, and the method comprises the steps: obtaining traffic environment three-dimensional perception information and a natural language instruction; converting the traffic environment three-dimensional perception information to obtain a structured semantic mark, and adjusting the weight of the structured semantic mark through a natural language instruction; based on the weight of the structured semantic mark, visual flow features are extracted from the structured semantic mark, and language flow features are extracted from the natural language instruction; based on a cross-modal attention mechanism, the visual flow features and the language flow features are fused, fusion features are obtained, and a simulation track is generated; real-time collision time is calculated, when the real-time collision time is larger than a collision time threshold value, the simulation track is corrected based on physical constraints and a traffic regulation library, and a corrected driving track is obtained. The automatic driving simulation track constructed by the method conforms to the intention of a user, and the system reliability and the man-machine cooperation efficiency are improved.

The invention provides a data weaving platform-oriented self-service data preparation method, which comprises the following steps of: accessing original data and associated structured metadata of a target data source into a data weaving platform to generate standardized accessed original data and associated structured metadata; based on a semantic model of the data weaving platform, performing classified semantic annotation on the associated structured metadata, and positioning a transfer node of the associated structured metadata to generate a data blood relationship record; performing bidirectional quality verification on the data consanguinity record according to semantics and path continuity, and matching with a federated governance rule of a data weaving platform to generate a metadata governance list; and generating a unified metadata directory based on the metadata governance list, so that a user of the data knitting platform can obtain key segments containing complete data consanguinity records. According to the method, the problem of insufficient accuracy and efficiency in self-service data preparation can be effectively relieved, and the efficient preparation requirement of a data weaving platform for multi-source data is met.

The invention relates to the technical field of urban rail transit station-city collaborative planning, in particular to an ontology-based station-city collaborative data integration and planning prediction method, which comprises the following steps of: obtaining rail transit station passenger flow data, resident travel behavior data and station periphery built environment index data; forming a space-time sample sequence according to the unified space-time granularity of the site walking service area; constructing an urban rail transit station-city cooperation ontology, and carrying out semantic annotation and semantic fusion on the space-time sample sequence to generate a feature sequence; inputting the feature sequence into a multi-task space-time diagram convolutional neural network prediction model to output a passenger flow prediction result and establish an environment index prediction result; and calculating a feature contribution degree based on a Shapley additive interpretation value, optimizing a background sample set by using a genetic algorithm to determine a key action element set, outputting a planning index threshold and an intervention measure parameter, and realizing an interpretable station-city collaborative prediction and planning decision closed loop.

The invention discloses a semantic analysis-based user abnormal intention recognition method and system, and belongs to the technical field of computer data processing, and the method comprises the steps of analyzing logic contradiction word combinations in a user session text to generate abnormal semantic marks, and collecting a user operation behavior sequence and environmental parameters to construct a spatio-temporal behavior trajectory map. And matching the abnormal semantic mark with a preset extensible abnormal mode library, if the generated primary abnormal confidence exceeds a threshold value, further comparing the behavior trajectory map to generate a behavior abnormal index, associating the abnormal semantic mark with the primary abnormal confidence to form a comprehensive abnormal feature vector, and calculating an environmental risk coefficient in combination with environmental parameters. And finally, judging by a triple decision arbiter, and if the abnormity is suspicious abnormity, activating a secondary verification process and updating an abnormal mode library. According to the method, semantic logic contradiction analysis, behavior trajectory map analysis and environmental risk assessment are fused, deep and camouflage abnormal intentions can be accurately recognized, and the method has adaptive learning ability.

The invention relates to the technical field of intelligent decision rule base construction, and discloses an intelligent decision framework construction method and device based on a dynamic ontology. The method comprises the following steps: acquiring original data streams from a plurality of heterogeneous data sources in real time, and constructing an initial dynamic ontology structure through a dynamic ontology modeling unit; performing semantic annotation and relation extraction on the original data flow by using the structure to generate semantic enhanced data; generating a candidate decision rule set based on the semantic enhancement data, and obtaining a verified rule set through consistency verification and conflict detection; calculating the adaptability score of the verified rule set in combination with the real-time environment data, and screening out an optimal decision rule subset according to the score and a preset threshold value; the method is integrated into an intelligent decision rule base, and an optimization loop is triggered based on an update state of the base. According to the method, the data utilization efficiency and the rule quality are improved, the rule base can dynamically adapt to the environment, and decision effectiveness and reliability are enhanced.

The invention relates to the technical field of image analysis, in particular to a temporal bone and gallbladder sebaceous tumor detection method and system based on multi-modal medical image fusion. The method comprises the following steps: acquiring a multi-modal temporal bone and gallbladder sebaceous tumor image of a patient, carrying out multi-modal image time sequence space alignment, carrying out feature vector change rate fitting, and constructing a multi-time-point image feature vector map; performing multi-modal image voxel decomposition on the multi-time-point image feature vector map, and performing three-dimensional morphological analysis to generate a geometric morphological parameter set; carrying out potential pathological hierarchical structure mining based on the geometric morphology parameter set, carrying out semantic label labeling, and constructing a multi-modal lesion semantic labeling image; and carrying out multi-time-point image change analysis on the multi-modal lesion semantic marking image, and carrying out parallel lesion evolution state prediction so as to generate a cholangioma evolution state prediction map. According to the method, accurate positioning, effective segmentation and visualized display of the temporal bone and gallbladder sebaceous tumor focus are realized.

The invention discloses an Internet of Things equipment long protocol text sequence modeling method and device, equipment and a medium, and relates to the cross technical field of the Internet of Things communication technology, deep learning model optimization and the natural language processing technology, and the method comprises the steps: collecting Internet of Things equipment protocol texts of a plurality of manufacturers; performing data cleaning, word segmentation and semantic marking operation on the collected protocol text to generate a structured sequence; designing a hierarchical residual position correction module based on dynamic residual position coding, constructing a protocol model, and training the protocol model through the structured sequence; and analyzing the to-be-analyzed protocol text based on the trained protocol model, and generating a mapping rule and type conversion logic between the to-be-analyzed protocol text and the target protocol. The problems of position information attenuation, gradient instability, poor dynamic adaptability and the like in long protocol analysis can be effectively solved.

A method including receiving semantic data from a first user device, the semantic data comprising at least one semantic token; obtaining spatial and temporal information associated with the first user device; associating the semantic data with the spatial and temporal information to generate associated semantic data; grouping the associated semantic data based on spatial and temporal proximity to create a cluster;and fusing data within the cluster to generate a representation of a portion of an environment.

The invention relates to the technical field of industrial communication protocol analysis, in particular to a protocol semantic matching analysis method based on reinforcement learning, and the method comprises the steps: constructing an industrial interaction environment containing industrial control equipment, a communication module and a protocol simulation assembly, defining a state space containing a flow attribute and a communication state, field processing, semantic annotation and dependency configuration related action space are carried out; calculating a reward value through a multi-level reward function of dynamic weight adjustment; based on the preprocessed multi-source protocol data set, adopting a Transform and graph neural network dual model to pre-train and generate a template library, and embedding an intelligent agent state processor; the intelligent agent updates the strategy after state processing, action distribution output by the strategy network, verification and execution of the action executor and interaction with the environment; and storing the interaction experience for iteration, and finally outputting protocol structure analysis, field classification and abnormity prompt information. According to the method, low-manual-dependence automatic analysis, unknown protocol self-adaptive adaptation and high-precision semantic matching can be realized.

The invention discloses an image analysis method and system for recognizing a post-earthquake collapse building, and belongs to the technical field of image analysis. The method comprises the following steps: firstly, constructing an identification network according to a UNet + + network, a global context enhancement module GCEM and a dynamic feature interaction module DFIM; secondly, inputting the post-earthquake optical image into a global context enhancement module GCEM and a UNet + + network at the same time; a global context enhancement module GCEM extracts a feature map through a convolutional layer, generates a semantic mark set through a multi-scale semantic marker MST, carries out global modeling through a Transform encoder and a decoder, and outputs a global feature map; the UNet + + network outputs a local feature map through downsampling of an encoder and step-by-step fusion operation of a decoder; and finally, inputting the global feature map and the local feature map into a dynamic feature interaction module DFIM, realizing multi-scale feature fusion through adaptive weight adjustment, and generating a collapsed building recognition result.

The invention belongs to the field of cloud computing, and provides a risk management real-time monitoring method and system based on cloud computing, and the method comprises the steps: carrying out the semantic annotation and context fusion processing of data collected by a computing power center, and then forming a risk perception feature set; the cloud risk analysis center generates a dynamic business dependency graph according to the risk perception feature set reported by each computing power center; when the cloud system detects that the risk state of the father node changes, conduction is carried out among different nodes in a non-linear time sequence mode; when the cloud system detects that a father node is continuously in a high-risk state, a risk buffer layer is generated, and decoupling and filtering are executed before a risk data stream enters a child node; and identifying high-risk areas with similar contexts, and generating predictive early warning information when detecting that a semantic-related risk resonance phenomenon exists between different areas. According to the invention, the efficiency and accuracy of risk management of cloud computing can be improved.

The invention relates to a programming review method and system based on multi-modal data. The method comprises the following steps that source code fragments are collected, character format matching is carried out, consistent items are output, and initial node mapping is generated; extracting a pointer reference and calling sequence, carrying out node association recombination, screening node levels, carrying out semantic mark matching, summarizing a connection path, checking a code security scanning index, and generating a dynamic semantic structure; carrying out stack-up matching to compare pixel distribution and label similarity, scanning edge coordinates, checking label corresponding positions and visible area distribution, judging feature co-occurrence, and generating multi-modal associated features; and performing program logic checking, analyzing a variable initialization sequence, generating a checking element set, comparing code security scanning indexes, generating security scanning information, judging a risk identification level and generating a review instruction list. Compared with the prior art, the information utilization rate and the correlation analysis depth in the code review process can be improved, and the accuracy of program defect and risk discovery is enhanced.

A Multimodal Search System (MSS) is designed to enable accurate search and retrieval across different modalities of data, including images, videos, and text. The MSS leverages multimodal and domain-specific models to extract and represent features and information from multimodal data, enabling seamless querying using text-based search queries. The MSS integrates multiple pipelines, including feature vector-based and tag-based approaches, to ensure robust and scalable search capabilities. The MSS addresses current multimodal-search challenges by leveraging a hybrid approach that combines multimodal embeddings, text embeddings, and semantic tagging to enable cross-modal searching. Additionally, for visual data, both tagging and embedding techniques are integrated within a single modality, ensuring a comprehensive and accurate representation. By assembling multiple retrieval strategies, the solution harnesses the strengths of each, resulting in a balanced and effective search system.

The invention relates to the technical field of defect identification, in particular to a second-hand car appearance defect automatic identification and labeling method based on an AI algorithm. The method comprises the following steps: performing full-angle scanning on a target second-hand car to generate second-hand car appearance multi-modal data; performing point-image mapping alignment processing and appearance defect cross-modal fusion on the second-hand car appearance multi-modal data to generate a second-hand car appearance defect comprehensive feature vector; performing defect candidate area anchor frame identification and appearance defect correction classification detection based on the second-hand car appearance defect comprehensive feature vector to generate a second-hand car appearance defect classification result; and generating corresponding second-hand car appearance defect structured information based on the second-hand car appearance defect classification result, and performing defect area semantic annotation on the target second-hand car based on the second-hand car appearance defect structured information to generate a second-hand car appearance defect automatic semantic annotation result. According to the invention, full-automatic identification and structured labeling of the appearance defects of the second-hand car can be realized.

The invention discloses a port avionics hub digital twin multi-level simulation model construction and visualization method, which comprises the following steps: obtaining a multi-view RGB image of a target port area, obtaining a camera attitude of each view by using an SfM algorithm, and reconstructing a sparse three-dimensional point cloud; constructing an LOD2 shell model with a semantic mark; an LLO3 model with holes is constructed; the LOD0-LOD3 model is serialized into a glTF 2.0 binary format and transmitted to a client side through HTTP / 2, the client side calls WebGL 2.0 through a browser to complete decompression, uploading and PBR rendering, and interactive plug-in-free visualization is achieved; constructing an eight-fork-two-fork-four-fork mixed spatial index, and performing multi-stage division and persistence on the LOD < 0 >-LOD < 3 > tiles, so that a client locates visible tiles within constant time based on node numbers; visual cone cutting and screen space error judgment are adopted to execute progressive loading on visible tiles, LOD0 is loaded at first, then LOD1-LOD3 is subjected to incremental superposition, low-level tiles in the same area are replaced with the LOD3 in a cross fading mode at the ultra-close distance (the Euclidean distance d from the center of a camera to the center of a target tile is smaller than or equal to 100 m), and smooth visual experience is obtained in a browser.

The invention discloses a multi-view three-dimensional reconstruction method based on Deeplab semantic segmentation. The method comprises the following steps: acquiring a multi-view image sequence of a target scene; performing pixel-level semantic annotation on each view image by using the trained Deeplab semantic segmentation model to obtain a semantic segmentation map containing object category information; based on a semantic segmentation result, carrying out semantic constraint feature matching on regions belonging to the same semantic category in different views; performing optimization estimation on the camera attitude in combination with a semantic constraint feature matching result; differentiated deep optimization strategies are adopted for the regions of different semantic categories; and generating dense point cloud data of the target scene based on the optimized depth information, and finally outputting a high-precision three-dimensional reconstruction model. According to the method, class information of Deeplab semantic segmentation is introduced, so that the robustness of multi-view feature matching is enhanced, and the reconstruction precision of object boundaries and weak texture regions in a complex scene is effectively improved.

The invention discloses a flexible business process automatic configuration method and system based on semantic intention recognition, and relates to the technical field of semantic recognition, and the method comprises the steps of semantic fragment extraction, process fragment atlas construction, process structure generation, process configuration visualization and flexible business process configuration. The method comprises the following steps: carrying out word segmentation, named entity recognition, semantic role labeling and relation extraction on natural language input by adopting a hierarchical guide type semantic decomposition combined extraction model, establishing a business semantic labeling system, and realizing modeling and extraction of semantic elements such as actions, objects, roles and conditions; on the basis, a process fragment graph improved by structural semantic fusion is constructed, and through node-level splitting, semantic tag binding and logic connection abstraction, process fragment graph data with tag attributes are generated, so that semantic understanding, process matching and cross-scene multiplexing capabilities are improved, and efficient, flexible and intelligent configuration of a business process is realized.

The invention relates to the technical field of information, in particular to an intelligent short message platform management and control method and system based on multi-level risk control. The method comprises the following steps: reading a to-be-sent short message text, comparing the to-be-sent short message text with a preset interception keyword library, and intercepting a to-be-sent short message if a matched interception keyword exists; identifying the semantics of the short message to be sent, and comparing the semantics with a plurality of preset prohibited scenes to obtain a scene matching degree; if the scene matching degree is higher than a preset threshold value, intercepting the short message to be sent; according to the recognized semantics, marking a text corresponding to the semantics; reading the unmarked text, and if the word number of the unmarked text exceeds a preset word number threshold value, obtaining characters with similar fonts and characters with similar pronunciation; trying to perform semantic recognition according to the combination of the characters with similar fonts and the characters with similar pronunciation of the unmarked text; comparing with a plurality of preset forbidden scenes; and if the matching degree of any second scene is higher than a preset threshold value, intercepting the short message to be sent.

The invention provides a regional soil fertility space-time evolution prediction method and system, and relates to the field of data processing prediction.The method comprises the steps that agricultural management events such as fertilization and irrigation are captured in real time through an edge computing node cluster, and an asymmetric time window is constructed based on a soil permeation rate model; extracting meteorological and satellite data in the window, querying the coupling rule table by using a triple index, and generating a coupling factor data set with a semantic mark; calculating a sliding time variance of a coupling factor in a grid unit, marking a high-entropy region and starting real-time stream processing when the sliding time variance exceeds a threshold value, and generating a soil state Hash fingerprint and performing dormancy collection when the sliding time variance is lower than the threshold value; constructing a regional event path directed graph, selecting a similar neighborhood event chain as a prediction framework, and registering an empty window region; the neighborhood topology is scanned in a buffer zone of a window area, after a compliance event sequence is captured, a window is removed, similar neighborhood historical data is migrated and injected into a local sequence, and parameters are finely adjusted through incremental learning to reconstruct an exclusive prediction model.

Systems, methods, software, and devices are disclosed herein process context data to encode one or more semantic elements of a desired audio composition in a semantic token sequence, process the semantic token sequence to encode one or more structural elements of the desired audio composition in a structural token sequence disentangled from the semantic token sequence, and process the structural token sequence to encode one or more audio signal elements of the desired audio composition in an audio signal token sequence disentangled from the structural token sequence. The semantic token sequence, the structural token sequence, and the audio signal token sequence may then be processed to generate at least a portion of the desired audio composition.

Speech synthesis techniques are described herein, which relate to the field of artificial intelligence (AI). The techniques may include performing feature extraction on prompt audio to obtain a prompt semantic token and a prompt acoustic token; performing feature extraction on input text to obtain an input semantic token; acquiring an input acoustic token based on the prompt semantic token, the prompt acoustic token, and the input semantic token; and generating an output audio of the input text based on the input acoustic token. According to this application accuracy of speech synthesis can be improved.

The invention provides a large-scale pavement reconstruction and drivable area automatic marking method for a well mine road, and belongs to the technical field of intelligent mines and automatic driving, and the method comprises the steps: collecting inertial integrated navigation, laser radar point cloud and camera image data; de-noising and segmenting laser radar point cloud data and camera image data, constructing a local surface element map and a global key frame pose sequence based on the pose initial value, and splicing to obtain a three-dimensional point cloud model; constructing a ground grid surface element based on a three-dimensional point cloud model and the segmented camera image, performing visibility screening on a view cone to obtain a visible surface element set, performing block rendering on the visible surface element, performing exposure self-adaption and reflective mask constraint combined optimization on a BEV rendering image at the same time, and constructing a pavement reconstruction model in combination with a Meshgrid grid. And finally, performing semantic annotation based on the pavement reconstruction model to generate an image data set with a label. The method is suitable for complex scenes of well industry and mining, and the pavement reconstruction precision and the labeling automation degree can be improved.

One or more embodiments of the invention provide a power system standard clause labeling method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-labeled electric power clause; the to-be-labeled electric power clause is input into a pre-trained large language model-based labeling device to obtain a structural label and a semantic label of the to-be-labeled electric power clause, the labeling device comprises a plurality of large language models of transformer layers and a double-task output layer, an attention path of each transformer layer comprises a low-rank matrix, and the attention path of each transformer layer comprises a low-rank matrix; only the parameters of the low-rank matrix are updated in the training process of the annotator.

The invention relates to the technical field of multi-modal interaction, in particular to a vision, language and behavior linkage grassland robot inspection and driving integrated method, which comprises the following steps: acquiring a cattle herd image annotation coordinate attitude acquisition distance density input model to generate an inspection target sequence, driving a robot to acquire physical signs, judging abnormity and generating an abnormal individual identifier set, screening a monitoring target, inputting visual questions and answers, outputting a next inspection position coordinate, calculating an inspection path motion instruction set by fusing topographic semantics, completing detection and calculation of deviation, adjusting acousto-optic output, and generating a driving control instruction set. A semantic inspection sequence is generated in combination with text vision, target adaptive updating and real-time response are achieved, sign abnormity is recognized through infrared depth comparison, paths are optimized through image semantic matching, obstacle avoidance and adaptability are improved by fusing terrain semantics and motion parameters, and task continuity and recognition reliability are ensured.

The invention relates to an image processing method and device for an intelligent camera, and the method comprises the following steps: carrying out the pixel distribution statistics of an original image collected by the intelligent camera, obtaining a brightness histogram, carrying out the segmentation division of the brightness histogram, and obtaining a plurality of brightness intervals; performing contour extraction on the original image based on the plurality of brightness intervals to obtain an edge contour map; determining a category label based on the edge contour map, and performing semantic annotation on the edge contour map based on the category label to obtain a semantic annotation result; performing color mapping on the original image based on the semantic annotation result to obtain an enhanced image; and carrying out quality evaluation on the enhanced image, and if the evaluation result does not reach the preset threshold, carrying out color mapping on the enhanced image again based on the evaluation result until the enhanced image reaches the preset threshold requirement, thereby solving the technical problems of low contrast, fuzzy details and color distortion of the original image collected by the intelligent camera.

The invention relates to the technical field of building automation and machine vision, and particularly discloses a building decoration assembly system and method based on image point cloud processing. According to the system, semantic annotation and feature enhancement are performed on a three-dimensional point cloud through an image semantic segmentation map, and a semantic enhanced point cloud is generated; iterative registration based on semantic consistency is carried out on the decoration component digital model and the semantic enhancement point cloud, and an accurate installation pose is output; planning a collision-free assembly track according to the pose and the semantic segmentation map; and the robot is driven to execute assembly along the track, and pose deviation detection and dynamic compensation are carried out based on the real-time image and the point cloud. According to the method, deep penetration and unified driving of image semantic information in the whole process of environment perception, pose calculation, path planning and closed-loop execution are realized, and the technical problems of insufficient precision, poor adaptability and dependence on manual intervention caused by disjunction of perception, planning and execution links of an existing assembly system are effectively solved.

The invention discloses a four-dimensional index-based scientific and technical literature knowledge automatic labeling method and system, and relates to the technical field of natural language processing, and the method comprises the following steps: constructing a four-dimensional index architecture; the method comprises the following steps: receiving multi-format scientific and technical literatures through a data input layer, and performing index analysis to obtain a document layer semantic structure, a paragraph layer semantic relation graph, a sentence semantic relation network and an entity semantic relation; performing semantic density calculation and knowledge enrichment region recognition to obtain a knowledge enrichment region recognition result; and establishing a cross-hierarchy semantic association model, performing entity boundary prediction and multi-level labeling on a knowledge enrichment area recognition result to obtain a structured semantic labeling result, and performing visual output and display. The technical problem that in the prior art, scientific and technical literature knowledge recognition is not accurate, hierarchical labeling is insufficient, and consequently the literature processing efficiency and accuracy are low is solved, and the technical effects that precise recognition and multi-hierarchical labeling of scientific and technical literature knowledge are achieved, and the literature processing efficiency and accuracy are improved are achieved.

The invention discloses an axle industry information acquisition and analysis system based on a large language model, and belongs to the technical field of artificial intelligence and information processing. The system comprises an intelligence acquisition layer, an intelligence processing layer and an intelligence analysis layer, wherein the intelligence acquisition layer is used for acquiring multi-source intelligence data from different information sources; the intelligence processing layer is used for converting an unstructured text of the multi-source intelligence data into structured data with rich semantic marks by utilizing a large language model; and the intelligence analysis layer is used for analyzing the structured data with the rich semantic marks by using a large language model and generating an analysis report. According to the invention, automation of information acquisition, intelligence of analysis and scientization of decision making are realized.

The invention discloses an intangible cultural heritage information intelligent promotion method and system, and belongs to the technical field of intangible cultural heritage information promotion, and the method comprises the steps: obtaining multi-source intangible cultural heritage data, carrying out the emotional semantic annotation, and constructing an emotional semantic enhanced intangible cultural heritage knowledge graph. The emotion intensity weight, the cultural context weight and the stability weight are introduced, so that the matching degree calculation can be adaptive to the current emotion state and the cultural background of the user, the dynamically generated cultural emotion symbol set ensures the diversity of symbols, the richness of emotion expression and the depth of cultural connotation, disjunction of the cultural symbols and the emotion state is avoided, and the user experience is improved. And the emotional authenticity and culture accuracy of the non-perpetual promotion content are ensured.