42197 results about "Encoder" patented technology

The application provides a fault prediction method and apparatus, an electronic device and a storage medium. The method comprises: obtaining a vibration signal collected by a sensor installed on a target component of a target device, and cleaning and segmenting the vibration signal to obtain a target vibration signal; inputting the target vibration signal into a target anomaly judgment model to obtain an output result, and according to the output result, determining whether the target vibration signal is abnormal to obtain an anomaly judgment result; when the abnormal judgment result shows that the target vibration signal is abnormal, inputting the target vibration signal into a target fault prediction model to obtain a fault prediction result, wherein the target fault prediction model is obtained by combining an encoder of the target anomaly judgment model and a newly added full connection layer. The application solves the problem in the prior art that a faulty device cannot be timely maintained because the fault can only be monitored when the device fault is quite obvious.

The invention provides a building health monitoring and evaluation method and system based on a physical neural network, and the method comprises the steps: collecting the monitoring data of vibration, strain, displacement and the like of a building through a sensor network, and carrying out the data preprocessing based on wavelet transformation and a neural network; inputting the processed data into a physical constraint encoder, mapping the processed data to a physical space by adopting a Hamilton quantity encoding method, and constructing constraint conditions in combination with physical model parameters; performing feature matching by using a physical constraint neural network, and extracting key features; adopting a principal component analysis method to decompose early warning indexes, and constructing parameter mapping through a deep neural network; generating a hierarchical decision rule based on a decision tree algorithm; and carrying out constraint check and cost calculation on the candidate schemes, and finishing scheme sorting through an analytic hierarchy process. Physical knowledge is embedded into a deep learning framework, and the accuracy and reliability of monitoring evaluation are improved.

The invention provides a dynamic health adaptive monitoring method and system using artificial intelligence, and relates to the technical field of health monitoring, and the method comprises the steps: carrying out the noise reduction through a hierarchical diffusion probability model through multi-source heterogeneous health data, extracting preliminary features through combining with an improved attention auto-encoder, learning discriminative features through a contrast learning network, and carrying out the recognition of the discriminative features; inputting the discriminative features into an adaptive wavelet neural network for multi-scale feature decomposition, inputting the discriminative features into a dynamic graph neural network to obtain a health feature tensor, obtaining time sequence features by using a hierarchical memory enhancement network, and generating a health knowledge graph in combination with a dynamic routing capsule network and a causal reasoning network; and inputting the time sequence characteristics and the health knowledge graph into a deep Bayesian network for health risk assessment, and obtaining an adaptive monitoring scheme through a model prediction control network by using a hierarchical reinforcement learning network and combining a multi-agent collaborative optimization system and a deep deterministic strategy gradient network.

The invention discloses a method for enhancing dynamic knowledge retrieval based on a large language model, belongs to the field of knowledge retrieval, and aims to solve the problems of knowledge solidification, insufficient timeliness and illusion of a traditional LLM (Logistics Language Model). A multi-granularity knowledge base is dynamically constructed, and a rule and semantic partitioning technology is combined, so that a text is converted into a normalized vector, and a hybrid index is established; a two-channel retrieval triggering mechanism is adopted, keyword matching scores and BERT semantic probability analysis are fused, and retrieval requirements are intelligently judged; vectorization retrieval is realized through a BGE-M3 model, and candidate results are reordered in combination with a cross encoder to improve the precision. The system supports multi-language adaptive processing, dynamic switching of word segmentation strategies and cross-language retrieval, and introduces real-time knowledge updating and version control. According to the method, the answer timeliness and accuracy are remarkably improved, the context coherence of multiple rounds of dialogues is optimized, the method can be widely applied to the fields of intelligent customer service, professional questions and answers and the like, the LLM illusion risk is effectively reduced, and the knowledge traceability is enhanced.

The invention provides an on-line quality monitoring method and system based on optical multispectral fusion, and relates to the technical field of multispectral fusion, and the method comprises the steps: collecting visible light and infrared multispectral images of an object to be measured, carrying out the preprocessing and registration, inputting the images into a variational auto-encoder, and carrying out the probability distribution modeling, and obtaining a spectrum basis vector and an initial abundance graph; and constructing a multi-scale morphological feature pyramid, performing graph segmentation in combination with spatial information to obtain a local consistency region, and fusing the local consistency region with the initial abundance graph to obtain an enhanced abundance feature. And fusing the spectrum basis vector and the enhanced abundance feature by adopting a multi-head cross attention mechanism to obtain a multi-spectrum fusion feature. And inputting the fusion features into a dynamic neural network, analyzing a topological connection relationship between nodes, obtaining a structured representation, performing discriminative enhancement, calculating node significance distribution, determining a quality defect area, analyzing a formation mechanism of the quality defect area, and finally generating a quality monitoring report.

The invention relates to the technical field of computer programming languages, and particularly discloses a coal-fired power plant safety monitoring system and method. The system comprises a multi-modal data fusion platform, a federal learning agent network and a digital twinborn simulation engine. The edge computing node carries out unified acquisition and feature extraction on multi-source heterogeneous data through multi-protocol conversion, quantum noise suppression and a preprocessing chipset; the multi-modal data fusion platform realizes semantic mapping based on a knowledge graph, and fuses time-space correlation characteristics of data such as an infrared image and gas concentration by adopting a time-space encoder and a cross-modal attention mechanism. According to the method, the problems of early warning delay and high false alarm rate caused by low multi-source data decentralized processing efficiency and insufficient nonlinear correlation analysis in a traditional scheme are solved, efficient data fusion, complex risk accurate prediction and automatic safety response are realized, and the real-time performance and reliability of a coal-fired power plant monitoring system are remarkably improved.

A Convolutional Neural network (CNNs) based system and method based on the same for image analysis including for computer aided detection / diagnosis is provided, enabling an efficient and accurate delineation of diseased volumes in images / medical images. More particularly, the system of the present invention is adapted to incorporate deformable convolution (DC) module based processor means, along the down- and up-sampling pathways of the underlying U-Net architectural framework of said system for effective understanding and attending to deformable geometry of unknown transformations, considering deformable convolution (DC), unlike the basic convolution is advantageously not constrained by predefined geometrical structures of the kernels. Said system of the present invention advantageously also permits weighted combination of image feature components along the encoder and decoder arms of the deformable convolution (DC) processor module based system architectural network due to introduction of Weight Generation (WG) modules in said system, such that dynamic assignment of importance to relevant spatial locations of the corresponding image feature maps could be given so as to also boost overall accuracy while ensembling to enable reduction in module analytic error by simultaneously maintaining the generalization in performance in respect of robustness to noise to attain accurate and faster demarcation of the ROI (region of interest). Added to the aforesaid, preferred integration of Focal Asymmetric Similarity (F AS) loss function analytic based processor module / means in said system, allowed effective handling of class imbalance for further improved performance.

A method is provided for estimating the number of distinct tokens in a text stream using a modified text-to-text variational autoencoder (T5VQVAE) model. The method includes receiving a continuous input of a text stream; dynamically maintaining a buffer that stores a probabilistic subset of tokens from the text stream; calculating a sampling probability for each token based on a condition related to the current state of the buffer; updating the buffer based on the sampling probability to include or exclude tokens; encoding the buffered tokens into a latent space using the T5VQVAE model; and estimating the number of distinct tokens in the text stream based on the tokens in the buffer and the corresponding sampling probabilities.

The invention provides an industrial robot motion planning method based on a diffusion model. The method comprises the following steps: firstly, pre-training a point cloud encoder to compress and embed obstacle point cloud under task conditions into a potential space, and constructing a forward kinematics robot state coding algorithm and a path data collision detection module; then, task information is coded based on the pre-trained point cloud encoder, noise adding and noise reduction are carried out on task data based on a Transform diffusion model, and modeling is carried out on data probability distribution of a physical relationship between robot connecting rods; and finally, based on the trained neural network model, combining a small amount of motion feedback, generating an image from random Gaussian noise, and further improving the generation speed and the success rate. Finally, the neural network model can output an optimal path under a specific task condition.

The present invention relates to a railway anomaly detection method and system based on multi-modal data fusion. The method comprises: separately encoding acquired modal data in a railway environment, and concatenating encoded modal data features, wherein the modal data comprises a one-dimensional vibration signal, two-dimensional image data, and 3D point cloud information; performing automatic weight classification on the concatenated multi-modal data features on the basis of an attention mechanism to obtain a weighted feature vector fused with multi-modal information; and adding a location code to the feature vector and using same as an input of an SAM encoder to obtain a segmentation result, and determining an anomaly condition of a railway on the basis of the segmentation result. The present invention achieves high monitoring accuracy, a real-time response capability, and specificity.

The invention provides an igniter robot production line control method and system based on deep reinforcement learning, and relates to the technical field of robot production line control, and the method comprises the steps: collecting the real-time state data of a production line station, extracting features through a multi-scale residual neural network and a spatial pyramid pooling module, and carrying out the feature extraction; channel attention and space attention modules are combined to perform feature enhancement, a cross-modal encoder is used to perform time sequence modeling, task decomposition is performed based on hierarchical reinforcement learning, soft constraint trajectory optimization and adaptive impedance control are used to generate a station control instruction, and a multi-target Pareto evaluation and priority dual experience pool is used to perform sample screening. Network parameters are optimized and updated through a near-end strategy, and a production line optimization decision scheme is output, so that the production line control precision can be improved, the system robustness can be enhanced, and the optimization of the production efficiency is realized.

The invention discloses a campus green space ownership perception assessment method and system based on multi-modal learning, and the method specifically comprises the steps: inputting the output results of a visual feature coding network and an auditory feature coding network into an audio-visual modal feature fusion module for fusion processing, and obtaining an environment joint representation; inputting the physiological response data set and the psychological assessment data set into a physiological and psychological collaborative encoder for processing to obtain a physiological and psychological joint representation; inputting the environment joint characterization and the physiological and psychological joint characterization into a global fusion module for deep fusion to obtain a final fusion feature; and inputting the final fusion feature into a multi-task prediction channel for processing, and training and optimizing in combination with a loss function to obtain an environment comfort comprehensive scoring result and an explanatory decision basis. According to the invention, comprehensive assessment of campus green space perception is realized, the accuracy and scientificity of assessment are improved, and decision support is provided for optimization of campus space design.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

The invention discloses an informatization project management system based on big data analysis, which belongs to the field of big data and comprises a data acquisition module, a time sequence modeling module, a task coupling analysis module, a risk clustering identification module, a resource allocation prediction module and the like. The data acquisition module asynchronously and parallelly acquires structured and unstructured data and uniformly encodes the structured and unstructured data; the time sequence modeling module constructs a multi-dimensional time sequence based on an autoregressive residual network; the task coupling analysis module fuses the task trajectory and the dependency relationship to generate a task influence directed graph; the risk clustering identification module identifies risks through variational graph auto-encoder mapping; the resource allocation prediction module constructs a dynamic resource priority based on a graph attention mechanism; a progress deviation traceability module identifies a deviation causal chain; the knowledge graph decision-making module corrects resource priorities and path strategies in a cross-graph manner; and the project global control module dynamically adjusts key paths and resource configuration and performs closed-loop self-correction. The beneficial effect is that the intelligent level and the risk response capability of project management are improved.

Disclosed in the present invention is a dynamic spatial-temporal graph attention method for ship trajectory prediction, comprising the following steps: spatial graph learning: using a graph neural network to aggregate neighbor embeddings of a target entity to learn a local structure representation thereof, then calculating the effect of neighbor entities and a collaborative relationship on the target entity by means of a knowledge-aware graph attention mechanism, and finally fusing semantics and attributes from different neighbors by means of an information aggregation operation to refine the embedding of the target entity; temporal graph fusion: using a temporal graph attention layer to learn a global temporal dependency relationship of ship trajectory data, and providing interpretability for a model, then using a GRU-based sequence encoder to replace positional encoding in a conventional Transformer architecture, and capturing more local temporal dependency relationships while providing a more reasonable inductive bias for an input sequence; and feature decoding: decoding a trajectory vector having spatial-temporal attributes, generating future relative position coordinates of a ship, and achieving high-precision ship trajectory prediction.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

The present application discloses a face image restoration method based on a state space model, which includes inputting the to-be-restored face image to a restoration model to obtain a restored face image; the restoration model includes an encoder and a decoder; the encoder sequentially includes a first image fusion module, a first multi-scale state space module, a second image fusion module, a second multi-scale state space module, a third image fusion module, and a third multi-scale state space module; the decoder sequentially includes a fourth multi-scale state space module, a first multi-scale attention fusion module, a fifth multi-scale state space module, a second multi-scale attention fusion module, a sixth multi-scale state space module, and a third multi-scale attention fusion module. This method ensures the consistency of face semantic information while restoring the detailed texture, especially low quality face images in real degraded scenes can achieve better restoration results.

The invention discloses a self-adaptive operation and maintenance root cause positioning method and system based on deep learning. The method comprises the steps that firstly, multi-source data such as system logs, performance indexes, alarm events and configuration changes are collected, and time sequence features, text features and associated features are extracted; performing anomaly detection in combination with a 3-sigma criterion and an auto-encoder; when an exception is found, reasoning diagnosis is carried out by utilizing the fault knowledge graph, and fault diagnosis is realized by combining an XGBoost classification algorithm; and then fault propagation analysis and root cause positioning are carried out, and a fault processing flow is continuously optimized. The problems of incomplete fault features, low detection accuracy, limited diagnosis capability and the like in an existing operation and maintenance system are solved, more accurate fault detection and root cause positioning are realized through a mode of combining multi-source data fusion, deep learning detection and knowledge graph reasoning, and meanwhile, the method has adaptive optimization capability and is suitable for large-scale popularization and application. And the operation and maintenance fault processing efficiency is obviously improved.

The invention discloses a Mama-based spectrum dynamic fusion and double-attention enhancement medical image segmentation method, which comprises the following steps of: firstly, constructing a Mama integrated spectrum domain and attention pyramid module, fusing spectrum dynamic characteristics and a self-attention pooling mechanism, and performing frequency domain information compensation and local characteristic enhancement to obtain a spectrum dynamic fusion image; the spatial correlation loss caused by image blocking processing is relieved; secondly, designing a layered enhanced U-shaped architecture, deploying an MISAP module in a shallow layer of an encoder to capture multi-scale global context features, introducing a bipolar routing attention mechanism in a deep layer, and dynamically allocating sparse attention weights to focus a key pathological region; according to the method, the segmentation precision of complex edge textures and tiny lesions in medical images can be remarkably improved, and the Dice coefficient in breast tumor, polyp and abdominal organ segmentation tasks is averagely improved by 6.5%.

The invention discloses a medical visual question-answering method and system based on multi-task modeling, and the method comprises the steps: carrying out the feature extraction of a to-be-analyzed medical image through a visual encoder, obtaining an image feature, inputting a preliminary question instruction and historical question-answering data into a dialogue large model to generate a question instruction, and obtaining a text feature through a text encoder; carrying out feature fusion on the obtained text features and image features, and carrying out self-attention image importance weighting processing and image-text alignment to obtain image-text fusion representation; and inputting a multi-target output projection layer, carrying out multi-task prediction, outputting question answers, image categories and important region masks, inputting the question answers and the image categories into a dialogue large model, and finally generating diagnosis opinions with detailed description in combination with dialogue context and multi-round interaction data and in combination with the important region masks. According to the invention, the interaction experience and the performance of the question and answer system are improved, and more accurate medical diagnosis in multi-modal complex information is facilitated.

The invention discloses a base station facility abnormity intelligent monitoring method and system, and the method comprises the steps: employing a multi-scale wavelet fusion pulse neural network to construct a dynamic signal perception topology according to the real-time data of a base station physical layer, and generating a space-time aligned base station full-dimension feature tensor; inputting the full-dimensional feature tensor of the base station into a fault mode confrontation distillation module, reconstructing a normal working condition manifold of the base station based on a physical constraint variational auto-encoder, and outputting an abnormal feature vector with a fault fingerprint identifier; fault propagation graph modeling is carried out on the abnormal feature vectors, and a base station fault root cause topological graph is generated in combination with back propagation credibility verification; and inputting the base station fault root cause topological graph into a toughness self-healing strategy generator, and finally outputting a base station facility self-healing strategy set meeting real-time constraint. By utilizing the embodiment of the invention, the accuracy and the real-time performance of abnormity monitoring can be improved, and the operation reliability and the communication service quality of the base station are improved.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

A nonvolatile memory device includes a plurality of latch groups, an address controller, an encoder, and a buffer. The address controller controls an input address and an output address to indicate one of the plurality of latch groups. The encoder receives sector data from a latch group corresponding to the output address among the plurality of latch groups and also compresses the received sector data. The buffer stores the compressed sector data. Among the plurality of latch groups, the compressed sector data stored in the buffer is overwritten in a latch group corresponding to the input address.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an intelligent anomaly recognition and intervention processing method, device, equipment and medium. The method comprises the following steps: carrying out feature fusion by using a gating fusion network and generating a preliminary abnormal score, determining a reconstruction error through an auto-encoder and triggering abnormal early warning, calculating a causal effect value of key features in combination with a causal graph model and anti-factual reasoning, and calibrating the abnormal score to generate a final abnormal score and an intervention instruction. And executing an intervention action and recording a result. According to the method, the multi-dimensional feature information and the causal reasoning mechanism are fused, the self-encoder reconstruction error is combined to carry out anomaly judgment, the intervention instruction is generated and executed, closed-loop control of anomaly detection, reasoning analysis and intervention execution is achieved, and the recognition accuracy of complex events and the system response capacity are improved.

An online system trains a transformer architecture by an initialization method which allows the transformer architecture to be trained without normalization layers of learning rate warmup, resulting in significant improvements in computational efficiency for transformer architectures. Specifically, an attention block included in an encoder or a decoder of the transformer architecture generates the set of attention representations by applying a key matrix to the input key, a query matrix to the input query, a value matrix to the input value to generate an output, and applying an output matrix to the output to generate the set of attention representations. The initialization method may be performed by scaling the parameters of the value matrix and the output matrix with a factor that is inverse to a number of the set of encoders or a number of the set of decoders.

The invention relates to a power equipment fault prediction method based on multi-source heterogeneous data and a twinborn model, and the method comprises the following steps: S1, obtaining multi-modal data related to the operation of power equipment, constructing a joint feature encoder through an attention mechanism in deep learning, and carrying out the joint modeling of multi-modal information, and obtaining a joint feature representation; s2, based on joint feature representation, adopting a dynamic twin model of self-supervised learning and fusion reinforcement learning, and dynamically updating the equipment health state; s3, constructing a complete-cycle prediction framework based on Transform, capturing long-term dependency and dynamic change characteristics in equipment operation, and identifying trigger factors of faults in combination with causal relationship analysis; and S4, based on the equipment health state and the fault prediction result, optimizing equipment operation parameters by adopting an intelligent operation and maintenance optimization engine, and dynamically generating an optimal operation and maintenance plan in combination with a genetic algorithm. The reliability and the operation efficiency of the power equipment are remarkably improved.

The invention provides a private domain live broadcast user behavior analysis and drainage recommendation method based on deep learning, and relates to the technical field of deep learning, and the method comprises the steps: collecting user behavior data, constructing a multi-mode deep neural network for processing, extracting user time sequence behavior features, extracting user text intention features through employing a residual connection structure and comparative learning, and carrying out the drainage recommendation of the private domain live broadcast user. User behavior link characteristics are acquired through a time sequence diagram attention network, user layering is performed through a Gaussian hybrid clustering model, a user loss probability is predicted by using a deep cross neural network, future activeness and purchasing power of a user are predicted in combination with a recurrent neural network, and commodities are matched through a diagram attention commodity knowledge network. And performing recommendation by using the improved double-tower deep neural network in combination with difficult sample mining and a variational auto-encoder, and searching an optimized push strategy to obtain an optimal push strategy.

The invention provides a network traffic anomaly detection model training method and device and a readable storage medium, and the method comprises the steps: extracting a traffic statistical feature vector according to original network traffic data, and generating an initial mixed data set; generating a confrontation disturbance sample output enhanced feature matrix based on the initial mixed data set; constructing a self-adaptive feature fusion rule based on the enhanced feature matrix, embedding asset association degree parameters into an attention calculation layer of a feature encoder, and outputting encoding features fusing threat intelligence; inputting the coding features fused with the threat intelligence into a pre-constructed initial detection model, generating false report and missing report correction labels based on the suspicious traffic fragments, and outputting an adversarial sample correction data set; and performing adversarial training on the initial detection model through the adversarial sample correction data set to obtain an incremental detection model for network traffic anomaly detection. According to the invention, the detection precision, the anti-interference capability and the real-time defense response capability of the detection model to novel attacks can be improved.

The invention is suitable for the technical field of video acquisition, and particularly relates to a video stream acquisition method based on deep learning, and the method comprises the steps: carrying out the video acquisition through a self-adaptive strategy, and obtaining real-time collected video data; performing parameter adjustment through edge calculation to obtain preprocessed video data; performing key frame selection on the preprocessed video data to obtain key frame data; performing inter-frame difference compression on the key frame data through the optimized variational auto-encoder model, and outputting video frame compression data; and when the original video needs to be recovered, analyzing the video compression data, reconstructing through the pre-trained neural network model to obtain a reconstructed video sequence, and generating a complete video according to the reconstructed video sequence. According to the method, the non-key frame is directly generated in the decoding process by using the deep learning model, so that the compression ratio can be remarkably improved, and the video playing continuity and the image quality, especially the performance in high-dynamic and complex scenes, can be improved.

The invention discloses a multi-modal-based power equipment health state monitoring method, and relates to the technical field of power equipment detection.The power equipment monitoring method is based on multi-modal data and knowledge graph fusion, cross check, expert rule cleaning and label correction are implemented by collecting sensing data such as chromatography, temperature, current and vibration in oil, and the detection result is obtained. Outputting high-credibility data; a graph model is constructed based on equipment topology by adopting self-encoder dimension reduction fusion, early anomaly detection is realized by utilizing a graph neural network, and an anomaly alarm is generated; mechanism matching and consistency evaluation are carried out based on the fault mechanism knowledge graph, and interpretable diagnosis is output; and when the diagnosis result is significantly deviated from the actual operation and maintenance conclusion, triggering an online increment and transfer learning updating model and expanding the knowledge graph to form a closed-loop self-learning mechanism. According to the method, the fault detection accuracy is remarkably improved, false alarms and missing alarms are reduced, the operation and maintenance decision-making efficiency is improved, and meanwhile operation and maintenance intelligence and real-time alarm are enhanced.