38results about How to "Avoid redundant calculations" patented technology

The invention relates to the technical field of three-dimensional data processing, and discloses a three-dimensional grid data processing and multiplexing method and system, and the method comprises the steps: S1, obtaining and analyzing grid data, obtaining three-dimensional grid original data, and carrying out the format recognition, geometric analysis and topology analysis of the three-dimensional grid original data; s2, carrying out reuse-oriented standardization processing; s3, constructing multiplexing description information; s4, grid resource storage and index management; s5, determining a subset based on the request; s6, on-demand conversion and result generation; and S7, unified scheduling control. By constructing multiplexing description information containing a unique identifier, a hierarchy mapping relationship, a block mapping relationship, version information and a service adaptation mark, unified management and efficient multiplexing of grid data under different hierarchy and service scenes are realized, and unified data semantic support is provided for hierarchical retrieval, on-demand extraction and multi-service collaboration; therefore, the reusability of the three-dimensional grid data and the system cooperation efficiency are remarkably improved.

The invention provides a directional ship detection method and system based on joint attention. The method comprises the following steps: acquiring image acquisition data; performing feature extraction by using a backbone network to obtain a multi-scale feature map, performing feature re-calibration on the multi-scale feature map, and outputting an enhanced target feature map; carrying out convolution operation on the enhanced target feature map by adopting self-adaptive geometric convolution to obtain ship direction characterization information; generating a candidate frame based on the ship direction representation information, calculating intersection-parallel-ratio statistical characteristics in combination with a ship real frame, and performing training sample adaptive distribution according to the intersection-parallel-ratio statistical characteristics; based on an Anchor-free detection framework, carrying out ship orientation detection by utilizing the training sample subjected to self-adaptive distribution to obtain a ship orientation detection result; through multi-scale feature re-calibration, adaptive geometric convolution and dynamic sample distribution, the ship direction and features in a maritime monitoring scene can be captured, and the detection precision and real-time performance are improved.

The invention discloses a building vector graph multi-scene intelligent simplification method and system, and belongs to the technical field of geographic information systems. Comprising the following steps: establishing a four-level data system comprising an original data layer, an engineering cache layer, a display cache layer and a terminal view layer; monitoring data change and user interaction events through an event bus; the event is responded, the current application scene is intelligently recognized, and the corresponding simplified parameter configuration is dynamically loaded; based on the configuration, executing simplification logic on the target building vector graph; querying a topological relation to carry out cooperative processing on the contours of the adjacent buildings; and synchronously updating a processing result to the four-level data system. Through four-stage data caching, dual-drive triggering and scene self-adaptive judgment, efficient, high-quality and self-adaptive processing of building simplification in multiple scenes such as cartographic integration, real-time display and spatial analysis is realized, and the system flexibility, the resource utilization rate and the user experience are improved.

The application relates to the technical field of underwater robot vision processing, and discloses a GAN-based underwater robot image real-time repairing and target identification method. The method acquires an original image sequence obtained by an optical sensor of an underwater robot, extracts degradation features of each frame of image, including scattering noise distribution, color distortion parameters and motion blur intensity. The original image sequence is input into a network, and based on the degradation features, a repaired image is generated frame by frame, and local structure consistency features and global semantic coherence features of the repaired image are extracted. A cascaded classifier is used for multi-scale target detection of the repaired image, local structure features and global semantic features are combined, and a target boundary box and a category label are output. According to the spatial distribution density of the target boundary box, the priority of the repaired area is dynamically adjusted, and the synchronous output of the repaired result and the target identification result is realized. The method can effectively improve underwater image quality and target identification precision.

This application provides a speech synthesis method, a vocoder, and its training and optimization method. The vocoder uses a ConvNext neural network as its backbone network. ConvNext replaces transposed convolution with channel upsampling, avoiding the periodic noise of transposed convolution. It employs depthwise convolution and separable convolution, which not only captures the time-frequency information of the vocoder input but also significantly reduces the computational load of the backbone network. Using frequency band fusion technology, the vocoder can simultaneously output audio from different frequency components of the synthesized audio, thereby reducing the output sampling rate and improving the vocoder's operating efficiency. Specifically, the vocoder uses multi-channel output, with each channel corresponding to an audio signal within a specific frequency band. The frequency ranges of the signals from each channel are orthogonal to each other, and the sampling rate is 1 / M of the original (M is the number of frequency bands). Finally, the audio signals from each frequency band are anti-mirror filtered and superimposed to obtain the audio at the original sampling rate.

Embodiments of the invention disclose an information retrieval method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-processed character string; if the length of the to-be-processed character string exceeds a set length value, according to the set length value, the to-be-processed character string is split in a non-repeated mode, a plurality of splitting results are obtained, the length of the to-be-processed character string is the number of characters contained in the to-be-processed character string, and the set length value is a positive integer larger than 1; retrieval is carried out on the basis of the multiple splitting results, multiple preliminary retrieval results are obtained, and each preliminary retrieval result comprises the multiple splitting results; and for each preliminary retrieval result, determining a screening result of the preliminary retrieval result based on the distance between two adjacent splitting results in the plurality of splitting results in the preliminary retrieval result. In the embodiment of the invention, the to-be-processed character string is split in a non-repeated manner, so that redundant calculation of repeated characters can be avoided, and the information retrieval efficiency is improved.

This invention proposes a method and system for diagnosing open-circuit faults in three-phase inverter IGBTs, relating to the technical field of power electronic device fault diagnosis. The method involves lightweight processing of acquired historical data to obtain feature vectors; training a pre-defined three-phase inverter IGBT open-circuit fault diagnosis model based on these feature vectors; real-time acquisition of three-phase current data to be processed, followed by bounded normalization to obtain normalized current amplitudes; and generating IGBT open-circuit fault judgment results based on these normalized current amplitudes. Real-time data related to the three-phase inverter IGBT open-circuit fault is collected based on the IGBT open-circuit fault judgment results, and this real-time data is input into the trained three-phase inverter IGBT open-circuit fault diagnosis model to output the three-phase inverter IGBT open-circuit fault diagnosis results. This invention effectively achieves lightweight, efficient, and accurate diagnosis of three-phase inverter IGBT open-circuit faults.

The invention discloses a deep learning-based intelligent recognition method for a motion mode of an unmanned surface vehicle. The method comprises the following steps: acquiring original sensing data in real time through a multi-source sensor system mounted on the unmanned surface vehicle, wherein the multi-source sensor system at least comprises an inertial measurement unit (IMU), a global navigation satellite system (GNSS) receiver, a laser radar and a visible light camera; performing time synchronization and coordinate system alignment processing on the original sensing data to generate a fused sensing data stream with a unified timestamp and a spatial reference system; dividing the fused sensing data stream into time window segments with fixed lengths, wherein each time window segment corresponds to one to-be-identified motion state sample; the IMU, the GNSS, the laser radar and the visible light / infrared camera are synchronously integrated, quadruple sensing dimensions are formed, the IMU captures instantaneous acceleration and angular velocity changes and reflects control instruction execution, the reliability of single-point observation is improved, and the system can still maintain the basic recognition capability when part of sensors fail.

This invention provides a rapid landslide area segmentation method based on high-resolution satellite remote sensing data and deep learning algorithms, belonging to the field of ground scene technology. The invention downsamples the original satellite remote sensing image to obtain a first image, extracts reflectance data from the red and near-infrared channels, calculates the reflectance difference and sum of reflectance values, and normalizes them to obtain a vegetation index to construct a vegetation layer. The first image and the vegetation layer are superimposed and stitched together, and feature enhancement is performed to obtain a vegetation feature map. This map is input into a convolutional neural network to output a landslide probability map. A two-dimensional coordinate set is constructed and cropped to obtain high-resolution test patches. The spatial gradient magnitude of the local vegetation index is calculated and weighted by a preset enhancement coefficient to generate edge-enhanced patches. The edge-enhanced patches are input into a semantic segmentation network to output a local landslide map, which is then backfilled into the initial image to obtain a landslide area segmentation map. This invention constructs a cascaded segmentation system to achieve efficient and accurate segmentation of landslide areas.

This application provides an intelligent monitoring method and system for engineering construction, relating to the field of engineering construction. The method includes: collecting multimodal raw data streams; converting the raw data streams into pulse events, each pulse event containing event type, timestamp, spatial coordinates, and semantic tags; binding pulse events of different modalities into spatially correlated pulse event clusters, and analyzing the temporal characteristics of these pulse event clusters in real time using a spiking neural network, triggering data processing tasks only when abnormal patterns or critical events are detected; dynamically adjusting sensor thresholds and event binding rules using the temporal dependence plasticity of pulses; binding the bound pulse event clusters to BIM model components to generate digital twins with spatiotemporal tags, and generating control commands through the digital twins. This solves the technical problems of redundant consumption caused by indiscriminate data processing and the formation of data silos by independent modules.

The invention discloses a severe environment unmanned aerial vehicle aerial photography target detection method based on multispectral iteration enhancement, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, acquiring RGB pictures and infrared pictures in severe environments such as rain and fog, night and the like, and constructing a data set; then, an unmanned aerial vehicle aerial photography target detection model is constructed, and efficient deep fusion of visible light and infrared multispectral features is realized by introducing a novel iterative hierarchical attention and differential enhancement fusion framework; meanwhile, a tail enhancement unit of an HGBlock module in the backbone network is redesigned; then training an unmanned aerial vehicle aerial photography target detection model by using the data set; and finally, using the trained detection model to detect an aerial target of the unmanned aerial vehicle and evaluate the performance of the model. Through a fusion mode of combining interactive alignment, differential enhancement and iterative feedback, the target detection performance and real-time performance of the unmanned aerial vehicle under complex weather and illumination conditions are improved.

Embodiments of the present application disclose a same-page detection method, device and equipment and a storage medium. The method comprises: performing target region detection on a currently photographed page image to obtain a target object region; extracting a local image region from the target object region, and determining local feature points corresponding to the local image region; calculating a matching success rate of the local feature points and image feature points of a stored historical page; and determining that the historical page and the page image are the same page when the matching success rate is greater than a preset success rate threshold. The present application scheme does not need to perform a complete correction process on the entire image, but only needs to extract a local image region and local feature points for matching, so that whether the currently photographed page and the historical page are the same page can be quickly and accurately determined, redundant calculation caused by repeated correction and information extraction is effectively avoided, user waiting time is reduced, and processing efficiency and user experience are improved.

The application provides a cockpit implementation method and system based on emotion enhancement and scenario service flow intelligent agent, and belongs to the technical field of automobile intelligent cockpits. The method comprises the following steps: acquiring multi-modal data of a target user in real time, fusing the multi-modal data to generate comprehensive user states, planning a service flow based on scenario semantics and the user states, and generating and outputting action execution instructions of internal and external resources according to the service flow. Through multi-modal deep fusion and scenario semantic understanding, the application can accurately capture user states and demands, provide the most suitable service at the most appropriate time, and change passive response into active care. The application sets a user memory vector library to continuously learn and adapt to user preferences, provides a truly 'thousand faces for a thousand people' service, and as the use time increases, the service accuracy and user satisfaction present a continuously rising curve, thereby solving the problem of static experience of traditional systems.

The application discloses a virtual anchor real-time driving system based on facial motion capture, aims to solve the problems of insufficient precision, lack of naturalness and weak scene adaptation of virtual anchor facial motion in the prior art, and through multi-thread parallel collection of audio and video streams, optimizes data quality through adaptive preprocessing; adopts multi-dimensional facial feature collaborative extraction, double-branch phoneme recognition, face function area semantic segmentation and confidence dynamic weight adjustment technology, realizes accurate representation and collaborative fusion of expression and lip feature; finally, through the lip-expression collaborative driving mechanism, the real-time driving characteristics of the adaptive virtual image are output; thereby effectively improving the precision and naturalness of virtual anchor facial motion, enhancing the complex scene adaptability, giving consideration to real-time response and low-cost deployment, and being applicable to virtual live broadcast, online education and other scenes, and having good application value.

The invention provides a microseism event identification method and system based on multi-dimensional feature fusion ensemble learning, and the method comprises the steps: collecting and processing microseism data, and constructing a multi-dimensional feature tensor; constructing a multi-dimensional feature fusion ensemble learning network model by using a feature fusion subnet and a target fusion subnet based on the multi-dimensional feature tensor; and based on the multi-dimensional feature fusion ensemble learning network model, identifying target micro-seismic data to obtain a micro-seismic event identification result. According to the method, efficient and accurate microseism event identification is realized through collaborative operation of data preprocessing and the secondary subnet, and the application value is remarkable.

The application discloses a self-adaptive wordpiece table level distillation method for a large language model, comprising the following steps: obtaining wordpiece probability distribution of teacher-student models at each generation step; extracting the union of the first K wordpiece indexes with the highest probability of each step respectively, and constructing an aligned candidate wordpiece set; calculating the absolute value of the teacher-student probability difference as the learning difficulty score of each candidate wordpiece, and collecting and constructing a global difficulty matrix; selecting high difficulty wordpieces from the difficulty matrix according to the current focus ratio to form a target distillation wordpiece set, and re-normalizing the student model probability; only calculating the divergence loss of the target wordpiece set and updating the student model parameters; and dynamically adjusting the focus ratio according to the real-time loss of the student during the training process. The application concentrates computing resources on difficult and high information wordpieces through dynamic self-adaptive screening, reduces the computing power consumption, improves the knowledge transfer accuracy, and is compatible with various distillation targets, and is suitable for deployment of large language models on resource-limited devices.

The invention relates to the technical field of biological information processing, in particular to a bar code correction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-corrected target bar code; generating a mode character string at each base position included in the target bar code, and replacing the base at the current position with the mode character string to obtain a preset number of new target bar codes; matching the new target bar code with each mode candidate set constructed by the bar code white list, and after the target mode candidate set is matched, matching the new target bar code with each new reference bar code in the target mode candidate set to obtain a first matching result; and correcting the target bar code based on the first matching result, and determining an inclusion relation between the target bar code and the bar code white list. According to the embodiment of the invention, index mapping is realized through the position mode, redundant calculation for generating a certain number of mutants is avoided, the query complexity is reduced, and the query speed is increased.

The application relates to the technical field of computer application, in particular to a list quota hanging and batch checking and modifying method based on a graphic element in a calculation software, which comprises the following steps: constructing an engineering model in the calculation software and selecting a graphic element; executing a graphic element automatic matching command based on the selected graphic element, completing matching and hanging of the graphic element and the list quota; quickly positioning and batch checking the graphic element whose matching and hanging of the list quota are completed; executing batch modification operation on the graphic element found in the checking result; and summarizing the list quota hung by the graphic element and exporting data to a pricing software. The application can improve the accuracy of list quota hanging and the checking efficiency.

This invention specifically relates to an optical target tracking method based on trajectory guidance and spatiotemporal joint decision-making, belonging to the field of computer vision and video information processing technology. The method first extracts image features through an anchor-free twin network architecture, outputting classification, centrality scores, and regression response maps; then, it constructs a sliding window weighted least squares trajectory prediction model, modeling target motion as locally uniformly accelerated motion to achieve target position prediction; subsequently, it generates an adaptive Gaussian heatmap based on trajectory prediction uncertainty, constructing a spatial attention mechanism for trajectory guidance; finally, it fuses visual features and prior trajectory information through a linear weighted fusion strategy to output the target position. This invention effectively utilizes temporal motion information, solving the problems of low tracking accuracy and poor robustness in existing technologies under occlusion and fast-moving scenarios, balancing real-time performance with low computational overhead, and is suitable for ordinary optical and infrared thermal imaging tracking scenarios.

The invention discloses a virtual anchor real-time driving system based on facial motion capture, and aims at solving the problems that in the prior art, virtual anchor facial motions are insufficient in accuracy, lack of natural sense and weak in scene adaptation. Audio and video streams are collected in parallel through multiple threads, and the data quality is optimized through self-adaptive preprocessing; the technologies of multi-dimensional facial feature collaborative extraction, double-branch phoneme recognition, face functional region semantic segmentation and confidence coefficient dynamic weight adjustment are adopted, and accurate representation and collaborative fusion of expression and mouth shape features are achieved; and finally, outputting real-time driving characteristics matched with the virtual image through a mouth shape-expression cooperative driving mechanism. Therefore, the accuracy and the natural sense of the face action of the virtual anchor are effectively improved, the adaptability of complex scenes is enhanced, real-time response and low-cost deployment are both considered, and the method is suitable for scenes such as virtual live broadcast and online education and has good application value.

The application provides a multi-welding seam path sequencing and scheduling method, an electronic device and a program product. The method of the application comprises the following steps: extracting welding seam features based on a workpiece point cloud and constructing a welding seam feature matrix; initializing a welded mask, a joint angle and a thermal field state vector; based on a state space defined by a Markov decision process, combining the welding seam feature matrix, the welded mask, the joint angle and the thermal field state vector into a current state at each decision step and inputting the current state into a policy network to obtain a joint action of the current decision step; and performing state transition to all welding seams to generate a path sequencing and direction sequence, plan a trajectory and control a robot to execute. The application can realize joint optimization of welding seam sequencing and direction.

The invention discloses a semantic communication privacy enhanced federal multitask learning method for mobile edge computing. The method comprises the following steps: initializing a global model comprising a shared encoder and a plurality of personalized decoders by an edge server, and issuing the global model; after each mobile edge client performs multi-task training locally, performing semantic compression processing of integrated error compensation, sparsification, quantification and coding on model updating, performing discretization mapping on features by using a local private codebook to enhance privacy, and uploading compressed data; and after the server side receives the data, inferring a nonlinear relation graph among global tasks through adaptive kernel learning, and according to the nonlinear relation graph, performing differential weighted aggregation of structure perception on updating execution of the shared encoder and each personalized decoder, updating a global model, and issuing the updated global model to the client side for next iteration. According to the method, the endogenous privacy protection is realized while the communication overhead is reduced, and the efficiency, safety and performance of federal multitask learning in a resource-limited mobile edge environment are effectively improved.

The application discloses a battery fault detection method and system based on multi-modal fusion and semi-supervised learning. The method comprises the following steps: obtaining battery original operation data, preprocessing the battery original operation data to obtain time series signal sample data; extracting the time domain dynamic characteristics of the time series signal sample data based on a one-dimensional convolutional neural network, and obtaining the time domain characteristic vector through global average pooling and flattening; calculating the statistical characteristics of the time series signal sample and converting them into structured text, extracting semantic features based on a pre-trained LLM to obtain a semantic feature vector; performing feature fusion based on a cross-attention mechanism to obtain a fusion feature vector, and inputting the fusion feature vector into a double-output branch to output a classification probability and a prediction confidence; and comparing the prediction confidence with a preset threshold to obtain a battery fault detection result. The application only needs normal battery management data for model training, the detection time is short, multi-modal data can be fused, and the accuracy of battery fault detection is effectively improved.

The application provides a video segment extraction method based on operation and maintenance key points, and belongs to the technical field of video segment extraction based on operation and maintenance key points. The application realizes video time sequence adaptive segmentation through recursive splitting based on a Mahalanobis distance minimum spanning tree, fuses frame-by-frame visual features and physical sensor signals to construct a multi-modal joint feature vector, adopts a Gaussian mixture model and a Bayesian deep learning to probabilistically model key point boundaries, uses an Actor-Critic reinforcement learning framework and an artificial intelligence strategy network to model key point search as a Markov decision process to realize adaptive frame skipping and close reading, determines video segment start and end frames in combination with boundary probability distribution based on the located key point moment, and then completes end-to-end inference output through a three-stage asynchronous pipeline, thereby solving the technical problem of insufficient operation and maintenance video key point moment positioning accuracy.

The invention discloses a client and sample joint optimization method for federated learning of the industrial Internet of Things, which comprises the following steps: S1, constructing a cloud-side-end architecture, S2, initializing a cloud server, S3, executing importance perception data shuffling by terminal equipment, S4, screening clients participating in federated learning training by an edge server, and S4, carrying out data shuffling by the edge server. S7, the edge server executes synchronous aggregation and uploads the updated data to the cloud server; S8, the cloud server executes global aggregation and issues the updated data to the edge server for synchronization; S9, the steps S3-S8 are repeated, and S7, the selected client device executes grouping importance sampling; S7, local model training is executed and the updated data is uploaded to the edge server; and the model converges or reaches a preset training round. According to the method, the training efficiency, the convergence speed and the prediction precision can be remarkably improved in a resource constraint scene.

The invention provides an electric quantity prediction method and system based on an improved multi-scale LSTM model, the prediction method is applied to a prediction system comprising a hierarchical processing module, a data processing module and a prediction module, and the prediction method specifically comprises the steps: constructing a power utilization hierarchical tree structure of a target region, extracting multi-dimensional features of the target region, and constructing a power utilization feature set; taking the power consumption feature set as input, and predicting through a multi-scale LSTM model fused with a KAN network to obtain a power consumption predicted value of each leaf node; and on the basis of the electric quantity predicted value of each leaf node, according to the hierarchical sequence of the power utilization hierarchical tree structure, accumulating the predicted electric quantity of each hierarchical node from bottom to top, and obtaining an overall power utilization prediction result of the target area. According to the method, the hierarchical tree structure is constructed, the improved multi-scale LSTM model is combined to predict the electric quantity of the lowest-level node, accurate prediction of the electric quantity is achieved through accumulation and summation of hierarchical relations, and the corresponding data dependency degree and calculation complexity are reduced.

This invention provides a method, medium, and system for real-scene 3D modeling based on stereo image pair satellite data, belonging to the field of 3D modeling technology. The invention divides stereo image pair satellite images into geographic grids and constructs Gaussian pyramids to extract multi-scale features. It then inputs these features into a multi-scale matching fusion model based on the principles of two dam water storage problems to obtain corresponding point sets with linear time complexity. A two-layer game theory model is used to optimize resource scheduling of the image processing unit. Based on the corresponding point sets, a dense parallax field is calculated and a 3D point cloud is reconstructed. Finally, a 3D mesh model is generated through registration fusion and a moving cube algorithm. Texture mapping and illumination consistency processing are applied to the 3D mesh model to output a real-scene 3D model of the target area. This invention solves the technical problem of low feature matching efficiency for large-scale stereo image pair satellite images.

The application relates to the technical field of electronic design automation, and provides a copper plating method and program for a printed circuit board, which comprises the following steps: determining an initial boundary of a copper plating area; generating a corresponding preliminary avoidance area; judging whether the preliminary avoidance area and the initial boundary of the copper plating area have an intersection relationship; if the intersection relationship exists, the vector contour information of the corresponding object is included in the intersection point calculation range; based on the initial boundary of the copper plating area and the vector contour information of all objects that need to participate in the calculation, the intersection points between all objects and the intersection points between all objects and the initial boundary are calculated, and an intersection point sequence is generated; a closed path containing a hollowed-out area is constructed according to the intersection point sequence, a copper plating contour is formed, the area threshold of the minimum allowed reserved copper island is dynamically adjusted, the isolated copper skin area in the copper plating contour is screened and processed, and a final copper plating pattern is generated. The application is used for efficiently generating a copper plating pattern with accurate avoidance structure and process adaptability in the design process of the printed circuit board.

The application relates to an intelligent interaction method and an interaction screen system supporting multi-modal input and output, aiming to improve the intelligent processing capability of voice, text and visual data in complex interaction scenarios. Through millisecond-level voice and text segmentation, endpoint positioning, semantic label generation and multi-modal time alignment, dynamic extraction and priority scheduling of semantic anchor points are realized. Combined with high-confidence control flow, attention mask generation and fine-grained visual modeling, semantic distillation and cross-modal contrast learning are adopted to effectively optimize the consistency of visual features and semantics. Based on real-time network status and interaction demand, the processing granularity and sampling frequency are dynamically adjusted to ensure the adaptability and synchronization of semantic understanding. The technical scheme improves the accuracy, real-time performance and robustness of multi-modal interaction, and is suitable for intelligent voice assistants, human-computer interaction systems and the like.

The invention discloses an FPGA-based run-length coding area rapid hole filling method, and relates to the technical field of digital image processing, and the method comprises the steps: firstly carrying out the binaryzation and run-length coding of a collected image, and obtaining an input area A; then calculating the minimum circumscribed regular rectangle of the A and expanding the coordinates towards the periphery; performing a first custom difference set operation on the A by using the rectangle after edge expansion to obtain a mutually exclusive region B; performing customized connected domain segmentation based on a two-time scanning method on the B, and extracting an edge background region C communicated with the outer frame; and finally, performing second-time customized difference set operation on the C by using the expanded rectangle so as to obtain a target area D after hole filling. According to the method, the FPGA assembly line technology is combined with the two-time difference set logic, and efficient and rapid filling of the holes in the image area is achieved.