13 results about "Spatial similarity" patented technology

The application discloses a dynamic prototype multi-model medical image classification method based on feature credibility evaluation, and relates to the technical field of medical image processing.The method effectively solves the problems in traditional medical image subtype classification, such as lack of high-quality labeled data, high uncertainty of pseudo-labels, and difficulty of static prototypes in adapting to dynamic changes of lesions, and the like.Through construction of a multi-structure feature extraction network and completion of hierarchical feature fusion, the method combines feature cross learning, local attention modeling and expanded convolution to supplement context information, and strengthens semantic consistency and structural continuity of lesion region features.Meanwhile, the method constructs a spatial similarity graph through cosine similarity, and models and fuses a spatial uncertainty graph with any and cognitive uncertainty based on a Dirichlet distribution, obtains a reliable evidence graph through exponential fusion, and generates a pseudo-label with sample-level confidence, so that effective supervision information is accurately screened from a feature level, cumulative deviation of false pseudo-labels is greatly reduced, and stability of a semi-supervised learning process is improved.

This invention provides a flexible production line control method and system based on a large vertical domain model. The method includes: constructing a pruning index combining temporal stability and spatial similarity for the original large vertical domain model to evaluate the redundancy of the activation tensors in the intermediate layers, and performing structured pruning accordingly to obtain a sparse structure model; performing mixed-precision quantization on the pruned model: allocating quantization bits according to the sensitivity of each network layer weight to task loss, and calculating scaling factors and zeros based on the range of non-zero weights to represent sparse weights; calculating the output deviation between the quantized pruned model and the original model under the same input, and training a feedforward network with the former's output as input to fit and compensate for the output deviation; combining the quantized pruned model and the feedforward network to form a composite control model; after deployment, adding the output command of the quantized pruned model to the compensation vector during inference to generate control commands.

The application relates to a power transmission line fault maintenance method and system under severe weather. The method comprises the following steps: performing baseline correction on a traveling wave current signal to identify a wave peak interval corresponding to the traveling wave, determining the symmetry deviation of the wave peak interval according to the difference between the trend item components of two sequences, screening a plurality of suspected fault traveling waves according to the fitting goodness of each wave peak interval, the shape similarity between the two sequences and the symmetry deviation, determining the spatial similarity according to the similarity between each suspected fault traveling wave and a plurality of suspected fault traveling waves at the opposite end, determining the incident waves at both ends of the power transmission line according to the energy intensity of the wave peak interval and the spatial similarity, correcting the initial speed of the incident wave according to the preset corresponding relationship and the main frequency of each incident wave, and positioning the fault point according to the corrected speed and the arrival time of the corresponding incident wave. The method improves the fault positioning accuracy and reliability, and reduces the operation and maintenance difficulty of the power transmission line.

The present application relates to the field of seabed terrain reconstruction, and provides a multi-beam sonar seabed terrain reconstruction method, system, device, product and medium, comprising obtaining an approximation coefficient and an approximation coefficient variance, thereby obtaining a state estimation point, obtaining an initial filtering data point according to the state estimation point, and performing adaptive filtering on the filtering data point to obtain a filtering data point; calculating attention weights and spatial similarity parameters of multi-source data, and then calculating spatial similarity; calculating a message vector according to the spatial similarity, obtaining a final node representation based on the message vector, calculating a data fidelity term, a smoothing constraint term and a terrain regularization term, and obtaining fused terrain data; inputting the fused terrain data into an encoder, decoding through a decoder, performing dense skip connection, and obtaining decoding output; calculating a terrain reconstruction total loss, adjusting model parameters according to the terrain reconstruction total loss, outputting reconstructed terrain data, and completing the reconstruction of the seabed terrain.

This application discloses a target matching method, a target matching device, and a storage medium. The target matching method includes: acquiring a first image and a second image of the same monitored area captured by different cameras; obtaining a first target set from the first image and a second target set from the second image; calculating the spatial similarity distance between each target pair in the first target set and the second target set, wherein each target pair includes one target in the first target set and one target in the second target set; and matching the two targets in corresponding target pairs whose spatial similarity distance is less than a first preset distance. Through the above method, this application can match targets in different images by calculating the spatial similarity distance between two targets and comparing it with a preset distance, thereby achieving the fusion of the same target and improving the accuracy of target fusion.

A method for UAV non-orthogonal communication and edge scheduling based on semantic symbol matching comprises the following steps: acquiring and partitioning the dataset, constructing an air-to-ground semantic system, matching semantic symbol sequences, correcting semantic errors and recognizing images, constructing a feature fusion strategy network, determining unloading, training the feature fusion strategy network, and testing the feature fusion strategy network. This invention employs a Transformer sequence prediction model, using semantic information to analyze the spatial correlation of the context, and repairs damaged semantic symbols caused by multi-vehicle non-orthogonal collisions or fading, thus improving the success rate. The UAV calculates the direction vector and spatial similarity of the observed signals, and uses the Hungarian algorithm to complete global matching, enabling concurrent vehicle unloading and improving the processing scale of the vehicle-to-everything (V2X) network. A multi-branch feature fusion strategy network is adopted, combining the policy network and the value network to construct a near-end policy optimization framework, achieving adaptive perception of real-time state changes of vehicles and UAVs, and improving system resource utilization.

This invention provides a dual-stream spatial-spectral fusion method and apparatus based on intermediate loss, comprising: inputting a panchromatic image into a spatial feature extraction subnetwork of a spatial-spectral fusion network to obtain intermediate spatial features output by the spatial feature extraction subnetwork; inputting an upsampled multispectral image into a spectral feature extraction subnetwork of the spatial-spectral fusion network to obtain intermediate spectral features output by the spectral feature extraction subnetwork; fusing the intermediate spatial features and intermediate spectral features and inputting the fused intermediate spatial features into a decoder of the spatial-spectral fusion network to obtain a spatial-spectral fused image output by the decoder; wherein, the loss function during the training phase of the spatial-spectral fusion network includes spatial similarity loss between the intermediate spatial features and the panchromatic image, and spectral consistency loss between the intermediate spectral features and the upsampled multispectral image. This invention solves the technical problem of the difficulty in simultaneously achieving spatial detail and spectral fidelity by introducing an intermediate loss mechanism during the training phase.

This application provides a blockchain-based intelligent processing method, system, electronic device, and storage medium for cross-border e-commerce orders, relating to the field of blockchain technology. The method includes: receiving order information, material spectral data, and genuine product feature data to construct a multi-dimensional knowledge graph; triggering hyperspectral scanning based on product identification to generate material composition data, and performing spectral matching with the knowledge graph to obtain a matching degree; simultaneously extracting key region feature sets from the hyperspectral image using the U-Net image segmentation algorithm, and comparing them with an anti-counterfeiting feature library to obtain spatial similarity; when both indicators meet customs thresholds, activating the target smart contract based on an emergency identifier and generating an execution record; finally, encapsulating the verification data into a verification package, generating a hash value, and writing it to the blockchain, establishing a bidirectional index with the order through the smart contract to achieve state synchronization. This application improves the automation level and data reliability of cross-border e-commerce product customs clearance verification.

The application discloses a distributed semantic trajectory similarity connection method, which comprises the following steps: establishing a global index for positioning semantic similar trajectories in two data sets from the text dimension, the time dimension and the space dimension; selecting the pruning boundary of text similarity, time similarity and space similarity according to a given similarity threshold and the similarity weight value of each dimension; pruning the global index process, and batch-pruning trajectory pairs which lack common text items, have a time distance lower bound greater than the time boundary and have a space distance greater than the space boundary; based on the trajectory summary, re-pruning the trajectory pairs in the local index space node after batch-pruning; reconstructing all trajectories, calculating the real similarity between the trajectories and obtaining trajectory pairs satisfying the similarity threshold constraint for the candidate trajectory pairs after re-pruning; and the extensive experimental research on the real world semantic trajectory set shows that the method is obviously superior to the baseline in the efficiency and scalability.

The application discloses a live working site safety management and control method and system linked with AR glasses and a control ball, relates to the technical field of image processing, and comprises the following steps: first, acquiring video streams of a first visual angle of AR glasses and a second visual angle of the control ball, and eliminating time offset through time synchronization processing; second, generating a target trajectory sequence through target detection and key point extraction, and determining a cross-view matching target pair; third, inputting the matching target pair trajectory into a cross-view similarity evaluation network CVRN, fusing spatial similarity, time consistency and semantic consistency to obtain a comprehensive reliability score R; fourth, correcting the original confidence of the double visual angles based on R through a confidence correction function; and finally, outputting a safety detection result according to the corrected confidence value and managing and controlling the site. The application avoids the limitation of a single visual angle, improves detection accuracy, and guarantees the safety of live working.

The present application relates to the field of artificial intelligence and clean room intelligent operation and maintenance technology, in particular to a clean room intelligent operation and maintenance method and system based on artificial intelligence, comprising: collecting business data sources, Internet of Things data sources and spatial topology configuration data; based on production scheduling, personnel authority and standard operating procedures, equipment account and maintenance records and spatial configuration data, an ideal benchmark space-time tensor organized according to preset time granularity and spatial partition is constructed; abnormal event operators are used for parameterized disturbance to generate an abnormal simulation state set; the real collected data and the abnormal simulation state are respectively differentiated with the ideal benchmark to obtain a real residual error matrix and a theoretical residual error matrix set; a diagnosis result is generated based on time sequence and spatial similarity, and an operation and maintenance work order or an observation record to be observed is generated according to conditions; the execution and review results are collected, the disturbance parameters and the dispatch threshold are updated, and the accurate identification and disposal of personnel violations, equipment degradation and logistics retention are realized.

This invention discloses a method and system for predicting intercity passenger transport demand distribution based on the similarity of land use in adjacent cities. Specifically, the method involves: acquiring urban characteristic data; calculating the spatial similarity matrix L of adjacent urban land use based on the urban characteristic data; calculating the urban size index considering the similarity of land use in adjacent cities based on L and urban size index data; constructing an intercity passenger transport demand distribution model based on the similarity of land use in adjacent cities; solving for the model parameters; and then using the parameter-calibrated intercity passenger transport demand distribution prediction model, with the characteristic data of the city in the year to be predicted as the model input, to obtain its intercity passenger transport demand distribution. This invention significantly improves the prediction accuracy of intercity passenger transport demand distribution.