653 results about "Attention model" patented technology

Disclosed is a complex scene deformation monitoring and classifying method based on interferometric synthetic aperture radar (InSAR) and a deep learning self-attention model, including: generating a deformation interferogram by using an InSAR extraction technology combining persistent scatterer (PS) points and distributed scatter (DS) points and relying on a shuttle radar topography mission digital elevation model (SRTM DEM) image; constructing a Delaunay triangulation network and an annular zone, obtaining a time series deformation data of PS points and DS points through adaptive arc densification and omni-directional point expansion, and extracting settlement points on a bridge; decomposing a time series by an SAR-self-attention model, decomposing InSAR time series data into a trend component and a seasonal component, and interpreting and analyzing deformation of the sea-crossing bridge; and describing time series dynamics and a seasonal pattern by comparing a curve fitting method with a seasonal and trend decomposition method.

The invention discloses a defect detection method and system based on joint distribution optimization and structural knowledge guidance. The method comprises the following steps: analyzing an equipment structured document to construct an equipment physical topological graph containing a physical connection relationship; processing the topological graph by adopting a graph convolutional network to generate a structured feature vector, and extracting a sensing feature vector of the multi-modal sensing data; constructing a knowledge-enhanced attention model, and guiding a perception feature vector to perform cross-modal fusion by using a structured feature vector as a key and a value; and training the model through a combined optimization target containing joint distribution divergence loss and Lipschitz stability constraint so as to ensure the consistency and physical authenticity of the multi-modal features in the shared semantic space. According to the method, the defect detection accuracy can be remarkably improved, and the root cause diagnosis report with physical interpretability is generated.

The invention relates to an immersive VR psychological detection system and method based on multi-modal AI. The system comprises a data acquisition and processing module which is used for acquiring a multi-modal data set of a user in a virtual reality scene based on unified clock synchronization, performing time-space alignment and noise reduction standardization processing on the multi-modal data set, and extracting key biological characteristics. And the correlation model construction module performs space-time correlation mapping through a spatial transformation network, constructs a three-dimensional space attention model, and generates a real-time fluctuation curve after inputting the key biological characteristics into the trained model. And the state report generation module identifies a real-time fluctuation curve by using a time sequence analysis model, performs backtracking analysis in combination with the psychological state conversion node and a multi-modal cross validation result, and finally generates a three-dimensional interactive report. By adopting the method, multi-modal data fusion can be realized, the dynamic change of the psychological state of the user can be effectively captured, the psychological state of the user can be comprehensively and deeply analyzed, and a scientific basis is provided for psychological health assessment and intervention.

The invention discloses a petroleum pipeline abnormity early warning and monitoring method and system based on a multi-source data fusion attention mechanism and a petroleum pipeline abnormity early warning technology, and aims to realize early-stage tiny leakage abnormity detection of a petroleum pipeline through a multi-source data fusion technology and a deep learning technology. According to the technical key points, historical data of pipeline operation states are collected from sound wave, temperature, negative pressure wave and vibration sensors, and a data set is constructed; obtaining a time sequence segment code for algorithm training; constructing a fusion attention module for algorithm training; on the basis of the obtained multi-source data, an attention Transform model is fused, and an adversarial learning method is adopted for training so as to predict the future operation state of the petroleum pipeline; training a petroleum pipeline early warning model by using Gaussian distribution with learnable scale parameters; the trained multi-source data is fused with an attention Transform model to serve as a petroleum pipeline abnormity early warning model, future operation state abnormal behaviors are recognized, and the failure probability is obtained. According to the method, the multi-source data analysis technology and the deep learning technology are fused, and the innovative Gaussian kernel scaling parameters and the failure probability calculation method are combined, so that the accuracy and reliability of early warning of the abnormity of the petroleum pipeline are effectively improved, and the method particularly has important application value in the aspect of micro leakage detection.

A convolutional layer of a computer model generates a dynamic convolutional filter based on the input feature map of the convolutional layer. The convolutional layer includes an attention model that generates a set of attention weights to dynamically adjust the convolutional filter applied by the model based on the input to the convolutional layer. The attention weights are generated with respect to multiple dimensions, which may include spatial position, input channel, output channel, and a respective combination of a set of static convolutional filters. The weights be generated with respect to each of the static convolutional filters, such that the different types (i.e., dimensions) of the weights may be applied element-wise to the respective convolutional filters and the filters, after application of the weights, may then be combined to generate the dynamic convolutional filter.

The invention discloses a question and answer generation method based on a knowledge graph, and relates to the technical field of artificial intelligence and natural language process.The method comprises the steps that a bidirectional semantic encoder is adopted to process input text corpus, entity words and relational words are extracted, a first semantic vector is formed, and the first semantic vector is converted into a basic knowledge structure through a triple decomposer; aligning the basic knowledge structure with deep semantic information in a preset knowledge graph by using a hierarchical knowledge fusion network to generate a multi-dimensional knowledge feature matrix, calculating association strength among knowledge nodes by using a dynamic weight distributor, and constructing a hierarchical question and answer path according to a sequence of the association strength from high to low; and inputting the hierarchical question and answer path into a constructed attention model, and generating a question and answer pair data set according to a question and answer template library. According to the method, the knowledge extraction accuracy and the knowledge fusion effect are improved, the question and answer path construction process is optimized, and a question and answer pair data set with a complete structure is formed.

The invention discloses a multi-language object illusion relieving method based on a cross-language attention mode, solves the problem of how to relieve multi-language object illusion during detection of a large visual language model under non-English questions, and belongs to the technical field of multi-mode questions and answers. The method comprises the following steps: identifying a cross-modal attention head set of which a visual language model shows obviously different behaviors for English and a target language when same semantic questions in different languages are processed; constructing image description queries of English and target languages for the same image, respectively inputting the image description queries into respective visual language models for reasoning, obtaining attention output under the English and target languages, and taking an average difference between the attention output as a language migration vector of the target languages; and in the reasoning process of the target language question, intervening the attention heads in the attention head set by using the language migration vector, so that the visual understanding ability of the visual language model under the non-English question is closer to the English question.

The invention provides an artifact restoration method for an ultrasonic image, a program product, electronic equipment and a storage medium, and the method comprises the steps: inputting a feature map corresponding to a to-be-restored ultrasonic image and a classification result into an artifact perception attention model, and obtaining an attention mask outputted by the artifact perception attention model, the feature map is obtained by performing feature extraction on the to-be-repaired ultrasonic image, and the classification result represents the type of artifacts in the to-be-repaired ultrasonic image; inputting the attention mask into a dynamic condition generator to obtain a depth feature output by the dynamic condition generator; the depth features are input into an ultrasonic image generator, a target ultrasonic image output by the ultrasonic image generator is obtained, and the target ultrasonic image is an image obtained after artifacts in the ultrasonic image to be repaired are repaired. According to the scheme, the artifact repairing algorithm fusing the dynamic condition generative adversarial network and the artifact perception attention model is provided, and the accuracy of repairing the artifacts in the ultrasonic image is improved.

The invention relates to a dexterous hand multi-mode motion trail prediction model generation method and a related device, which are used for a dexterous hand simulation grabbing process, and the method comprises the following steps: generating a motion trail of a dexterous hand according to initial position information of the dexterous hand and end position information of a target object; based on the plurality of motion track points, a multi-modal data set of motion of the dexterous hand in the motion track is obtained, and the multi-modal data set comprises environment image data, first multi-modal data and second multi-modal data; performing multi-modal feature fusion on the environment image data, the first multi-modal data and the second multi-modal data to obtain an input sequence; and based on a preset sparse self-attention mechanism, inputting the input sequence into a to-be-trained self-attention model for training to obtain a motion track prediction model. According to the scheme provided by the invention, the real-time performance and the accuracy of the motion trail prediction of the dexterous hand can be improved through the fusion of the multi-modal data, and the grabbing success rate of the dexterous hand is improved.

The invention provides an intelligent traceless erasing method and system for video picture characters, and relates to the technical field of video stream processing, and the method comprises the steps: carrying out the space-time dual-domain feature extraction of a preprocessed first video frame sequence, and obtaining a first space-time feature; and establishing a space-time double-domain attention model according to the first space-time feature, the space-time double-domain attention model calculating fusion space domain and time domain features through cross attention, dynamically distributing fusion weights based on the character movement speed, obtaining a second video frame sequence of the to-be-processed video stream, preprocessing the second video frame sequence, and extracting a second space-time feature. Texture and motion characteristics of front and back frames are synchronously referenced through a space-time double-domain attention model, so that the time sequence coherence of a repaired area is improved, a time sequence consistency compensation mechanism driven by an SSIM is combined, the flicker frequency is reduced, and the time-space domain weight is adaptively adjusted according to the character speed through a dynamic weight distribution strategy, so that the time sequence coherence of the repaired area is improved. And stable erasing and rapid moving of characters are realized.

The invention relates to a geological analysis technology, and discloses a multi-head attention model training method fused with geological rules, which is used for improving the scientificity and accuracy of geological body model prediction and improving the interpretability of a geological analysis process. According to the scheme, firstly, feature vectors of geological attribute data and geological coordinate data are spliced to obtain a fusion feature vector, then spatial locality and directivity are considered at the same time, geomorphic multi-head attention calculation is conducted on the fusion feature vector, and an attention feature sequence is obtained; then extracting multi-scale features from the input geological map, constructing a cross-fault weight mask matrix based on fault constraints, and obtaining comprehensive features through fusion; calculating a loss value by adopting a joint loss function containing prediction loss and fault non-penetrability constraint terms, and updating model parameters through a back propagation algorithm to complete model training; and finally, drawing an attention thermodynamic diagram for visual display, and superposing the attention thermodynamic diagram with the three-dimensional geologic model.

The present invention belongs to the field of computer vision technology, and provides a generalizable deep fake image detection method and system based on noise perception. The method comprises the following steps: obtaining a video containing a face identity to be detected; preprocessing the video data to be detected to obtain a facial image; inputting the facial image into a pre-trained deep fake image detection model to extract deep fake evidence features of the image; the deep fake image detection model mines the noise information in the image as fake evidence through an adaptive noise perception attention model; and uses the features as fake evidence to determine whether the facial image has been deeply faked. The present invention has lower testing costs, higher efficiency, better generalization, and can cope with a wide range of deep fake image detection scenarios.

The invention discloses a code generation method based on dynamic hierarchical sparse attention, and belongs to the technical field of data processing, and the method comprises the following steps: S1, collecting an input data set; s2, constructing a dynamic hierarchical sparse attention model; s3, optimizing the dynamic layered sparse attention model by using the input data set, and generating a final dynamic layered sparse attention model; and S4, generating a code by using the final dynamic hierarchical sparse attention model. According to the method, the model can still keep high-quality code generation capacity at extremely low labeling cost, and a flexible and efficient solution is provided for agile development and automatic testing.

The invention provides a crop early-stage remote sensing identification method fusing effective accumulated temperature, and provides a crop extraction method based on a space-time multi-level attention model and a long-short time memory neural network and integrating effective accumulated temperature and multi-source remote sensing data aiming at an early-stage crop growth environment and own characteristics. Complementary information between SAR and optical data is fully utilized, fusion is carried out in a feature layer, and further fusion with effective accumulated temperature data is carried out to realize enhancement of crop environment information, so that the model can better understand relevance between early-stage characteristics of different crops and the environment, and the early-stage recognition performance of the crops is improved.

The invention relates to a cultural scenic spot people flow prediction and scheduling method based on machine learning, and belongs to the field of scenic spot management. 2, constructing and training a mixed attention model, wherein the constructed mixed attention model comprises a spatial-temporal feature extraction module and a mixed attention mechanism module; step 3, people flow prediction and result output: inputting real-time data into the trained mixed attention model to carry out people flow prediction, and outputting a future time period passenger flow volume value; a quantile regression technology is combined to output a confidence interval of the passenger flow volume; step 4, scheduling strategy implementation: constructing a dynamic thermodynamic diagram based on a prediction result, and marking crowd density levels of different areas in the thermodynamic diagram; early warning information is pushed in real time, and touring suggestions are sent to tourists in advance.

The invention provides a patent agency whole-process intelligent management method based on artificial intelligence and big data, and the method comprises the steps: carrying out the real-time access of a global patent database, a legal status platform and a customer document through the collection of multi-source heterogeneous data and the construction of a dynamic patent knowledge graph, and storing technical feature entities, legal clause nodes and the like through a Neo4j graph database, calculating an edge weight in combination with the semantic vector to realize knowledge association; text feature dimension reduction and technical scheme similarity calculation are carried out through an improved TF-IDF algorithm and an LSTM-Attention model, and context dependency is effectively captured; and optimizing a reply strategy based on a deep reinforcement learning framework (DQN), defining an opinion feature vector and an action space, and dynamically adjusting a reply decision through a reward function (delta P is an authorization probability improvement amplitude, and T is time cost). The method is suitable for patent retrieval, technical scheme analysis, reply strategy generation and process automatic management.

A method estimating a depth of an environment includes generating, via a cross-attention model, a cross-attention cost volume based on a current image of the environment and a previous image of the environment in a sequence of images. The method also includes generating, via the cross-attention model, a depth estimate of the current image based on the cross-attention cost volume, the cross-attention model having been trained using a photometric loss associated with a single-frame depth estimation model. The method further includes controlling an action of the vehicle based on the depth estimate.

The invention discloses an airport ground guarantee work key time node automatic identification method and device, and relates to the technical field of image processing, and the method comprises the steps: inputting each airport scene image in an airport scene monitoring video into a trained target detection model, obtaining category information and position information of behavior subjects in each airport scene image; by using a target tracking model, according to category information and position information of key time node behavior subjects in all airport scene images, determining space-time motion information and confidence of each behavior subject in the airport scene monitoring video; and inputting the category information, the space-time motion information and the confidence coefficient of each behavior subject in the airport scene monitoring video into a trained dynamic graph attention model to obtain an identification result of the airport scene ground support work key time node. According to the invention, the accuracy and efficiency of important ground guarantee working time node identification in the airport scene image are improved.

The invention relates to the field of computers, in particular to an NIWPSO + CNN + LSTM + Attention-based power load prediction method, which comprises the following steps of: acquiring power data, and performing preprocessing and standardization operation on the power data; the preprocessed data are used as input, and a CNN-LSTM-Attention model is constructed; carrying out hyper-parameter optimization on the CNN-LSTM-Attention model by utilizing an NIWPSO (Non-International World Weighted Particle Swarm Optimization) algorithm; setting a residual error monitoring and dynamic updating mechanism, monitoring the residual error in real time during model prediction, and automatically triggering a retraining process once the residual error exceeds a preset threshold value; a nonlinear variation inertia weight strategy is innovatively adopted, dynamic adjustment is carried out according to an algorithm iteration process and a particle search state, a PSO algorithm is prevented from being caught in a locally optimal solution too early, meanwhile, a mutation thought of a genetic algorithm is used for reference, mutation operation is carried out on particles in a one-dimensional mode, the algorithm is assisted to efficiently obtain a globally optimal solution in a complex solution space, and model parameter optimization is guaranteed.

The invention belongs to the related technical field of image processing, and discloses a texture surface defect generation method and system based on a mask perception image redrawing network, and the method comprises the steps: (1) obtaining a low-frequency structure feature based on a defect sample image of a to-be-processed product category, a binary mask for marking a defect position, and a convolutional coding module; (2) a context sliding window attention modeling module carries out long-range dependence modeling on the feature sequence, and attention calculation is carried out between effective feature marks to obtain high-frequency detail features; (3) inputting the low-frequency structural features and the high-frequency detail features into a collaborative feature fusion module for fusion to obtain fusion features; (4) a style modulation decoding module performs up-sampling on the fusion features based on the comprehensive style tensor; and (5) generating a defect image based on the trained generator network model, the defect-free sample image of the to-be-processed product category and a user-defined defect mask. According to the invention, the authenticity of defect generation is improved.

The embodiment of the invention provides a multi-modal semantic understanding method and device based on multi-order progressive alignment, computer equipment and a storage medium, and the method comprises the steps: inputting each kind of received data into a corresponding preset encoder, and grouping at least two kinds of output data features, inputting each data feature group into a preset coarse alignment module, determining a matching score corresponding to each data feature group, and screening the data feature groups of which the matching scores exceed a preset threshold value; constructing a graph attention network, inputting each screened data feature group into the graph attention network, and iterating the output first fusion feature; inputting the iterated features into a preset semantic correction module, inputting the output aligned features into a preset multi-modal attention model, and generating second fusion features of all feature groups, through a three-stage dynamic alignment mechanism of a coarse alignment module, a graph attention network and a semantic correction module, the problem of serious semantic information loss in existing cross-modal semantic understanding is solved.

The invention discloses a river water level prediction method and system based on a TCN-LSTM-Attention model, and the method comprises the following steps: obtaining the monitoring data of a plurality of sensors related to the water level, carrying out the sorting according to the collection time, obtaining the multi-feature variable time series data, carrying out the data preprocessing of the multi-feature variable time series data, and filling the missing data; dividing the preprocessed data into a training set and a test set, extracting input features and output features by using a sliding window, and performing standardization processing on the data to obtain a feature data set; a TCN-LSTM-Attention model is constructed, and model training is carried out; and performing river water level real-time prediction based on the trained TCN-LSTM-Attention model, and outputting a river water level prediction result. According to the method, the river water level can be accurately and effectively predicted by using the historical water level and rainfall data of the river, and high-accuracy multi-step water level prediction is realized.

The invention provides a data center interconnection link fault self-healing and path switching method, which comprises the following steps of: acquiring multi-dimensional link performance monitoring data, establishing a standardized time sequence database, realizing link health degree multi-index trend prediction by combining an LSTM-Attention model, and determining the link health degree according to the LSTM-Attention model. Risk-aware dynamic path selection and switching for multiple business scenes are realized by combining business service sensitivity modeling, path inherent stability quantification, nonlinear adaptive switching criteria and a debounce switching process, the response accuracy and the business adaptation degree of path switching are improved, false triggering and service interruption risks can be remarkably reduced, and the path switching efficiency is improved. And the high availability and robustness of routing in a complex network environment are enhanced.

The invention discloses a power consumption time sequence prediction method and system based on a self-attention mechanism, a medium and a processor, and relates to the technical field of power consumption time sequence prediction. The method comprises the steps of obtaining original data, preprocessing the original data, dividing the original data into a training input set and a label set, extracting time and power unit features through convolution operation, calculating and fusing the features through double attention, obtaining a prediction value through convolution operation, optimizing model parameters, and finally predicting a future power consumption value based on an optimization model. The system comprises a preparation module, a first operation module, a fusion module, a second operation module and a prediction module. A computer readable storage medium and a processor store and run programs for executing the method, respectively. According to the method, the nonlinear features and the long-term dependency relationship of the data are effectively captured through a self-attention mechanism, the feature extraction capability is improved through a double attention model, and the prediction precision is improved.

A method for controlling a vehicle in an environment includes generating, via a cross-attention model, a cross-attention cost volume based on a current image of the environment and a previous image of the environment in a sequence of images. The method also includes generating combined features by combining cost volume features of the cross-attention cost volume with single-frame features associated with the current image. The single-frame features may be generated via a single-frame encoding model. The method further includes generating a depth estimate of the current image based on the combined features. The method still further includes controlling an action of the vehicle based on the depth estimate.

The invention relates to the technical field of information security management, in particular to a multi-modal data dynamic desensitization method and system based on machine learning, multi-modal features such as texts, images and time sequences are jointly extracted through CNN-Transform-LSTM, 1-5 sensitive levels are evaluated by adopting a cross-modal attention model, a self-adaptive desensitization strategy is generated through an improved MOEA / D-DE algorithm, and the dynamic desensitization of the multi-modal data is realized. And realizing cross-modal collaborative desensitization by combining GNN. The system dynamically adjusts parameters through TD3 reinforcement learning, the response delay is less than or equal to 100ms, the Bi-LSTM-AE model evaluates privacy and utility in real time, and the block chain evidence storage whole process is realized. The method solves the problems of precision and utility imbalance, poor dynamic adaptability and insufficient multi-mode collaboration in the traditional technology, and is suitable for the fields of finance, medical treatment and the like.

The invention relates to a GIS (Gas Insulated Switchgear) equipment mechanical defect diagnosis method based on a Gramb angle field and a dual-channel PCNN-Attention neural network, and belongs to the technical field of gas insulated switchgear mechanical vibration defect diagnosis. The method solves the problems that traditional diagnosis depends on artificial feature extraction, so that subjectivity is high, information mining is insufficient, and defect severity evaluation is missing. According to the technical scheme, the method comprises the steps that a one-dimensional vibration signal is converted into a GASF two-dimensional image and a GADF two-dimensional image through a GASF field so as to completely reserve time sequence topological features; carrying out data enhancement by adopting an image geometric transformation technology so as to improve the generalization ability of the model; and a dual-channel PCNN-Attention model is constructed, and synchronous intelligent identification of defect types and severity is realized through parallel feature extraction and dynamic weight optimization of an attention mechanism. According to the method, the diagnosis accuracy, reliability and adaptive capacity are improved, and support is provided for equipment state operation and maintenance.

The invention provides a power grid data anomaly detection method and system based on a hybrid deep learning model, and belongs to the technical field of power grid data processing. According to the method, a convolutional neural network is combined with a recurrent neural network, a gating circulation unit, a long-short-term memory network and an attention model to carry out hybrid modeling, an initial detection model is obtained, and meanwhile, a model collaborative optimization mechanism is adopted to carry out distributed parallel training on the initial detection model; constructing an adaptive optimizer through an adaptive optimization algorithm, and dynamically updating model parameters and a model structure by using the optimizer and a dynamic training mechanism to obtain a hybrid detection model; and inputting the real-time data stream of the power system into the hybrid detection model for anomaly detection, and executing an active security protection operation on the power system according to the detected abnormal data and potential attack behaviors according to a preset defense strategy. According to the invention, accurate detection and real-time early warning can be carried out on complex abnormal behaviors of the power system.

The invention discloses a method and equipment for eliminating network environment defects and self-healing a closed loop based on RAG and a medium, and the method comprises the steps: constructing a multi-modal knowledge base, and carrying out the regular updating based on a large-scale language model; performing fusion analysis by using a long-short term memory attention model and a graph neural network model, capturing time sequence and topology anomalies, generating a structured early warning report, and associating the structured early warning report with a knowledge base; a three-level retrieval strategy is adopted, and emergency, radical treatment and prevention schemes of multi-objective optimization are extracted from the knowledge base; utilizing an improved time sequence directed acyclic graph algorithm to dynamically select parallel self-healing operation; and automatically adjusting the knowledge base based on the self-healing execution result and the feedback index. According to the method, through deep fusion of the dynamic multi-modal knowledge base and the retrieval RAG technology, normal form transition of equipment defect elimination from passive response to active prediction is achieved, compared with a traditional method, the defect positioning accuracy is greatly improved, and the problem of misjudgment caused by single data source analysis is solved.

Systems and methods are disclosed for efficient memory allocation for processing large language model encoders and decoders based on an attention model. The system can utilize a plurality of two types of processors suitable for different types of LLM processing. These include Neural Processor Units and Graphic Processing Units. Each NPU processor has dedicated DDR memory coupled to each NPU. The DDR memory caches the neural network weights used in the generation of neural network activations. A plurality of GPUs provides KVQ token processing. LLM tokens processing can be performed in parallel batches or sub-batches to utilize idle NPU processors within the neural network. In some embodiments, the NPUs are structured in a matrix with a bus between adjacent processors. In another embodiment, NPUs provide both KVQ processing and neural network processing. The system can be integrated on a silicon substrate using chiplets in a 2.5 or 3-D architecture.