143 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 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.

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 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.

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.

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.

This invention relates to a semi-supervised remote sensing image semantic segmentation method based on double consistency. The semi-supervised semantic segmentation method includes: establishing a semi-supervised learning model based on a teacher-student architecture; using labeled data to perform supervised learning training on the teacher model and optimizing the teacher model parameters; the student model consists of a single-encoder, double-decoder deep learning model; using a sharpening function to reduce the information entropy of the student model's predictions; firstly, using the teacher model to generate pseudo-labels from unlabeled data to semi-supervise the prediction results of the student model; secondly, cross-supervision through two sets of pseudo-labels converted from the prediction results of the two sets of student models; and alternatingly training the student network through these two consistency tasks, enabling the model to fully understand the large amount of information in the unlabeled data; after training, the test data directly passes through the student network to obtain the predicted semantic label map, and the semantic label map is mapped onto the original image to visualize the segmentation results.

The invention discloses a structured layer module combination system and method for video generation, and relates to the technical field of video shooting and generation, and the method comprises the steps: S1, obtaining N continuous layers to generate a layer image stack, where N is a natural number and is greater than 2, and each layer comprises image data and focal length data of image data imaging of the layer; s2, through image segmentation, target detection and semantic annotation, constructing a layer mark with a spatial level, a shielding logic and a semantic mark, and providing a structural constraint for subsequent generation; s3, processing at least one image layer to generate an animation image layer; and S4, according to the layer mark, synthesizing the animation layer with other layers to generate a video sequence frame. The method has the beneficial effects that each layer has spatial depth, semantic label and shielding logic, and is suitable for structural modeling and expression of a complex scene; the animation can be visually smooth and semantically coherent on the basis of an inter-layer structure and action prediction model.

The power grid standard analysis method, device, equipment and storage medium provided by the application relate to the field of power systems. The method comprises the following steps: obtaining a power grid standard document, wherein the power grid standard document comprises standard text clauses, circuit diagram images and parameter table data; performing semantic labeling on the standard text clauses to identify power terminology entities; performing disambiguation processing on the power terminology entities to obtain disambiguated standard text clauses; generating standardized knowledge units based on the disambiguated standard text clauses, the circuit diagram images and the parameter table data; and performing logical reasoning on the standardized knowledge units to determine a content consistency checking result of the power grid standard document. Through the application, the drawbacks of low efficiency, strong subjectivity and unstable quality of manual analysis are overcome, and efficient, objective and standardized processing of the power grid standard is realized.

This invention discloses a method and system for breaking down and calculating campus recipes with volume, belonging to the field of data processing technology. The method and system include the following steps: S1, acquiring the execution data of the recipes with volume and performing weight semantic labeling and normalization; S2, constructing the recipe penetration relationship and evaluating the convergence of the weight semantic mapping; S3, identifying the calculation start point and calculation end point, generating ingredient nutritional contribution vectors, and constructing a recipe calculation dataset; S4, evaluating the consistency recursion verification between the current calculation link and the execution link, identifying abnormal link states, and generating calculation behavior labels. This invention effectively improves the accuracy, continuity, and traceability of the breakdown and calculation of recipes with volume, solving the problems of inconsistent data definitions, disconnected links, mixed use of weight semantics, and difficulty in backtracking calculation results.

Embodiments of the present application provide a semantic representation processing method and device, electronic equipment and computer readable storage medium, relating to the field of autonomous driving, comprising: extracting features from an image to obtain a plan view feature, and extracting features from lidar data to obtain a radar feature; performing geometric attention fusion on the plan view feature and the radar feature to obtain a plan view feature and a radar bird's eye view feature; cutting the plan view feature to obtain a plurality of plan view feature blocks, marking the plurality of plan view feature blocks as semantic labels, and cutting the radar bird's eye view feature to obtain a plurality of radar bird's eye view feature blocks, and marking the plurality of radar bird's eye view feature blocks as semantic labels; performing semantic fusion on the plan view feature blocks and the radar bird's eye view feature blocks based on the semantic labels to obtain a semantic representation; and performing semantic reconstruction on the semantic representation based on a mask to obtain a reconstructed semantic representation. Embodiments of the present application combine the advantages of geometric fusion and semantic fusion.

The present application relates to a kind of satellite feature component image automatic labeling and database construction method, comprising the following steps: (1) key component marking is carried out to satellite three-dimensional model;(2) in unreal engine, build earth background, satellite orbit, camera and other scene components, build simulation space scene;(3) for the satellite three-dimensional model marked in step (1) and the simulation space scene obtained in step (2), batch generates satellite picture and its key component semantic labeling diagram;(4) for the semantic labeling diagram obtained in step (3), label remapping is carried out, standard database format, complete database construction.The present application provides satellite three-dimensional model key component automatic labeling and batch drawing method, and accurately and efficiently realizes the construction of satellite simulation image key component semantic segmentation database.

The invention discloses a computer operation and maintenance log intelligent analysis system and method based on semantic recognition. Comprising a log collection and preprocessing module, a log semantic annotation and knowledge base construction module, a log semantic analysis module, an abnormal mode recognition and classification module, a root cause positioning and recommendation module, a log analysis result visualization and feedback module and a system self-optimization module. According to the method, the problem of log heterogeneity is solved through multi-protocol access and format standardization, deep semantic analysis of different types of operation and maintenance logs is realized in combination with a domain dictionary and a fine-tuning BERT model, and the limitation of traditional keyword matching is broken through; the abnormal confidence coefficient is calculated by fusing the semantic anomaly degree and the frequency anomaly degree, the anomaly is judged by integrating the log content semantics and the occurrence rule, and the false alarm and the missing alarm caused by single-dimension judgment are reduced.