681 results about "Network computing" patented technology

The invention relates to the technical field of information resource fusion management, and particularly discloses a fusion and management system for multi-source heterogeneous science and technology information resources. Analyzing an equipment fault chain from an unstructured text of a historical operation and maintenance log, extracting a rated parameter constraint from a structured table of an equipment manual, and collecting an operation feature vector from a real-time sensing data stream to generate a knowledge graph containing N entity relationships; based on an entity attribute constraint rule of the knowledge graph, designing a bidirectional attention mapping network to calculate semantic similarity weights of multi-source data and knowledge nodes, and generating a graph embedding vector set with weight marks through Hadamard product operation; according to the method, the embedded vector set is input into the pre-trained graph neural network model, and the root cause equipment set causing feature offset is positioned, so that efficient fault diagnosis and positioning are realized, decision support is provided for a subsequent preventive maintenance strategy, and the reliability and the operation and maintenance efficiency of the system are improved.

The invention provides a scene adaptive projection vehicle lamp system based on deep reinforcement learning and a control method, and relates to the technical field of intelligent vehicle lamps and automatic driving perception systems. Comprising a multi-modal sensing module, a feature fusion module, a strategy generation module and an execution module. The multi-mode sensing module is used for collecting environment state data and performing primary processing to form an environment data information flow; the feature fusion module is used for generating a unified environment feature vector for the environment data information flow; the strategy generation module is used for receiving the environment feature vector and generating a vehicle lamp adjustment strategy through multi-layer neural network calculation; evaluating a result obtained by executing the vehicle lamp adjustment strategy based on the vehicle lamp, and optimizing strategy parameters of the strategy network based on a PPO algorithm; the execution module is used for controlling the vehicle lamp according to the vehicle lamp adjustment strategy output by the strategy network. The intelligent level of the vehicle lamp is remarkably improved, and the system is widely applied to night driving assistance, urban interaction prompt and low-visibility driving scenes.

The present disclosure relates to a multi-modal brain network computation method associated with structural function, apparatus, device, and medium. The method is applied to train a brain disease prediction model, and the brain disease prediction model includes an association perception dual-channel generation module, a disease feature regression module, a topological structure discriminator, and a time-space joint discriminator. In a model training process, by performing a multi-level interactive fusion learning on a high-order topological feature of brain functional magnetic resonance data and magnetic resonance diffusion tensor imaging data, a multi-modal time series activity signal of each brain region is obtained.

The invention discloses an intelligent operation abnormity monitoring and positioning method for a polypropylene cable, and relates to the technical field of intelligent operation and maintenance of a power system, and the method comprises the steps: collecting multi-source physical signals in the operation process of the cable, and constructing a multi-dimensional feature matrix fusing multiple physical quantities through multi-scale time window division and space mapping processing; extracting space-time coupling characteristics among nodes by using a graph attention embedding network, and training a running state recognition model in combination with a label perception contrast learning mechanism; constructing a cable topological graph based on an identification result, introducing an improved Bayesian space reasoning network, and calculating abnormal probability distribution of each node; a weighted abnormal heat map is further generated, an abnormal propagation path is extracted through an abnormal state flow model and a directional propagation scoring algorithm, and abnormal node positioning and trend evolution prediction are achieved; the method has the advantages of high spatial resolution, high identification precision and good online adaptability, and is suitable for intelligent state perception and abnormity early warning of the polypropylene cable in a complex operation environment.

The invention discloses a mine rescue training and danger dynamic simulation method based on virtual reality, and the method comprises the following steps: S1, modeling a rescue process into a directed graph structure, and outputting a task state diagram bound with a virtual reality scene; s2, collecting an operation behavior, a task state, an environmental parameter and a physiological response, and constructing a training state vector; s3, inputting the state vector into the deep Q network to calculate a jump node evaluation value, and outputting a jump node; s4, modeling the control rule as a rule node, constructing a directed acyclic graph, binding a weight, and outputting a rule graph; s5, performing self-evolution on the rule atlas according to training feedback, and outputting an evolution structure; s6, reasoning in the evolution rule map, fusing the rule recommendation node and the jump node, and outputting a final task node; and S7, executing jump control according to the final node, loading a virtual scene, and pushing environment parameters, task contents and risk information. According to the invention, intelligent path decision and training process adaptive optimization of the mine rescue task are realized.

The invention provides an underwater acoustic target recognition method based on autonomous task perception, and belongs to the field of underwater acoustic signal processing and artificial intelligence. S3, performing feature extraction on the time-frequency spectrogram by the task type extraction network to obtain a task embedding vector, calculating a similarity score, when the maximum similarity score is greater than a set threshold value, outputting a task representation vector, and entering S3, otherwise, inputting features output by the last Transform layer into a classifier; s3, selecting a router according to the task representation vector, selecting a trained expert network by the router, calculating a door control weight, processing universal acoustic features in parallel by the expert network, fusing output of the expert network, fusing deep features and fused features to obtain enhanced features, and enabling the enhanced features output by the last Transform layer to enter a classifier; the invention further provides a system. The problems that the task category autonomous recognition capability is insufficient and the correlation between tasks is ignored are solved.

The invention discloses a resource scheduling optimization method and system based on deep learning, and particularly relates to the technical field related to resource scheduling, real-time indexes such as CPU utilization rate, memory occupancy rate and network bandwidth are acquired through a lightweight monitoring agent, and resource demands in the future 3-10 minutes are predicted by using an improved LSTM (including a cross-cycle attention mechanism), so that resource scheduling optimization is realized. The heterogeneous resource matching degree is calculated in combination with a graph attention network, a hierarchical scheduling strategy and a dynamic fault-tolerant mechanism are implemented, and the scheduling effect is evaluated through a multi-objective optimization function. The system comprises a distributed sensing terminal, a predictive analysis engine, a decision center and other modules, and supports federated learning, elastic capacity expansion and contraction and visual evaluation. The resource utilization rate can be improved, delay and energy consumption are reduced, and the method is suitable for heterogeneous resource scheduling scenes such as cloud computing and edge computing.

The invention discloses a power network attack chain dynamic deduction and intelligent response process method, system and device based on deep reinforcement learning and a medium, and belongs to the technical field of network security and power system protection. Multi-modal data is aligned and normalized, an event view cache is constructed, and the generalization detection capability on process camouflage and memory injection attacks is improved through a federated learning collaborative detection mechanism; based on the event view cache and historical threat intelligence, generating a dynamic attack knowledge graph, constructing a deep reinforcement learning model taking the attack knowledge graph as an environment, calculating an attack influence index by using a Bayesian network, and generating a differentiated security response instruction; and realizing attack path backtracking and attack source positioning based on the attack knowledge graph. According to the method, multi-modal data fusion analysis and strategy adaptive updating are realized, and the attack chain identification accuracy and evidence chain construction integrity are remarkably improved.

The invention relates to the technical field of industrial mechanism models, in particular to a shock absorber performance optimization control method based on model fusion, which comprises the following steps: extracting a low-frequency disturbance state variable and inputting the variable-topology industrial mechanism model to generate a nominal reference state trajectory; utilizing a depth state observation network fused with energy passivity constraint to calculate a non-linear model mismatch compensation amount and an adaptive weighting parameter; performing dynamic fusion on the nominal reference state trajectory and the compensation amount based on the adaptive weighting parameter to generate a generalized state estimation value; and executing dynamic multi-objective optimization based on the generalized state estimation value, and generating mixed mode control input acting on an execution end. According to the invention, through adaptive fusion of a mechanism model and a data driving method, physical consistency, calculation real-time performance and robustness of a control process are considered.

The invention discloses a traffic accident detection method based on FFC and GCSA models. The method is innovatively improved based on a YOLOv8 network model. Firstly, a multi-scale feature fusion module FFC is designed in Backbone to replace an original C2f module, and the capability of fusing the multi-scale features of the network can be further improved on the premise of not increasing the network calculation amount, so that the network can fuse the multi-scale features on the level of finer granularity; then, a GCSA attention mechanism is introduced between a C2f module and a Deect module of a Neck layer, and the recognition capability of the model for key features in a complex environment is remarkably enhanced; and finally, establishing a loss function Focal-EIoU Loss for the improved YOLOv8 network structure, so that the network classification detection capability is improved, and the generalization capability of the model is improved. In a specific implementation process, a traffic accident image data set covering multiple scenes is constructed, and specialized data preprocessing is performed; then, end-to-end training and parameter optimization are carried out on the Traffic-YOLO network model obtained after improvement; and finally, integrating the optimized model to a traffic accident detection system for real-time target detection. Compared with the prior art, the method effectively improves the accuracy and robustness of traffic accident detection in a complex scene, and has important practical significance.

The invention discloses a water quality parameter prediction method and system based on multi-sensor data fusion, and the method comprises the steps: collecting and preprocessing original dissolved oxygen data and turbidity data, and obtaining dissolved oxygen data and turbidity data in a plurality of time windows; according to the dissolved oxygen data and the turbidity data in each time window, calculating a water quality feature vector, a dynamic convolution kernel and an abnormal discrimination probability of each sensor in the time window, and performing traversal elimination based on the abnormal discrimination probability to obtain a sensor sequence; according to geographic coordinates and water flow directions of sensors corresponding to data points in the sensor sequence, calculating spatial relationship weights among the sensors, according to the water quality feature vectors, calculating frequency dynamic features, and combining the spatial relationship weights and the frequency dynamic features to generate global feature vectors; and calculating a water quality parameter tensor according to the global feature vector and the long-short term memory network, and generating a water quality parameter thermodynamic diagram. According to the method, the problem of insufficient prediction precision caused by poor spatial collaboration of single-point abnormal data and multi-source data is solved.

The invention relates to a multi-scene facility site selection method based on a gridding population mapping and hybrid optimization algorithm, and the method comprises the following steps: S1, constructing regular rectangular grids covering a research area, each network having a unique grid identifier, a centroid abscissa and a centroid ordinate; s2, obtaining different forms of population data, performing conversion processing, integrating the population data into regular rectangular grids, and calculating the population quantity for each network to obtain a grid data set with standardized population weight; and S3, based on the data set and the coverage determination function, respectively constructing target functions of three scenes of full-facility re-optimization, partial-facility optimization and newly-added facility site selection, and solving the target functions to obtain optimal multi-scene facility site selection results of the three scenes. Compared with the prior art, the method has the advantages of improving the calculation efficiency of the optimal facility number range and the site selection position and the like.

The invention relates to an offshore wind power-energy storage-hydrogen production system cooperative control method and device and a medium, and the method comprises the steps: collecting wind power plant operation data, energy storage system data and hydrogen production system data in real time, and obtaining a state vector; the state vector is input into a strategy network, a current action vector is calculated, the strategy network is obtained through training of a double-evaluator reinforcement learning framework, a first evaluator evaluates an economical efficiency target value function, and a second evaluator evaluates a safety target value function; the strategy network outputs a control instruction corresponding to the current action vector, and issues the control instruction to each execution device for adjustment, including adjusting fan operation parameters according to the axial induction factor and the yaw angle; adjusting the electrolytic cell input power according to the electrolytic load power; and controlling the charging and discharging operation of the energy storage system according to the energy storage power. Compared with the prior art, the method has the advantages of high collaboration, high adaptability, safety and the like.

The invention discloses a graphic processing unit cooperative processing method and system for accelerating a three-dimensional generative model. The model comprises a diffusion processing stage and a Gaussian splash rendering stage. In the diffusion processing stage, the time step number and the data precision calculated by the neural network are dynamically adjusted according to the visual angle sensitivity, and a specific graphic processing unit core is scheduled for execution. In the Gaussian splash rendering stage, pixel block tasks are predicted and intelligently scheduled to a stream processor based on historical data; and in the stream processor, the processing sequence of the Gaussian ball by the rendering unit is optimized according to the geometric distance, and the close-range unit is preferentially processed. During back propagation, the built-in logic of the stream processor preaggregates the gradient contributions of the same Gaussian ball, and then updates the gradient contributions through a single write operation. Through collaborative optimization of software and hardware, the efficiency bottleneck of the 3D generation model on a graphic processing unit is effectively solved, the calculation speed, the throughput and the hardware utilization rate are remarkably improved, and the model generation time is shortened.

The invention relates to the technical field of equipment energy consumption monitoring and fault diagnosis, and discloses a large-scale equipment energy consumption anomaly detection method and a storage medium. The method comprises the following steps: synchronously acquiring equipment energy consumption, state and environment data, fusing to generate multi-dimensional initial features, and performing multi-scale transformation. And performing preliminary detection on each scale feature subset to generate abnormal confidence and mode description. And screening the feature subsets according to the confidence coefficient, and dynamically selecting a corresponding detection strategy according to the mode description. And performing deep feature extraction on the feature subset based on the selected strategy, inputting the obtained high-dimensional feature vector into a corresponding anomaly evaluation network, calculating a standard state matching degree, comparing with a dynamic threshold to generate a fine-grained judgment result, and finally finishing positioning and attribution analysis in combination with anomaly description to form a detection report. According to the method, efficient and accurate large-scale equipment energy consumption anomaly detection is realized.

The invention provides a multi-modal semantic fusion image and text relevance dynamic analysis method and system, and belongs to the technical field of multi-modal data processing. The method comprises the steps of image and text data preprocessing, feature extraction, fusion semantic vector generation through a bidirectional cross attention mechanism, dynamic relevance score calculation through a time sequence attention long-short-term memory network and combined loss function end-to-end training. According to the method, accurate alignment of image and text features can be realized through a bidirectional cross attention mechanism, the cross-modal matching accuracy is improved, the dynamic correlation analysis capability is enhanced by using time sequence modeling, and the problems of insufficient feature coding suitability and limited time sequence modeling capability in the prior art are solved.

A data acquisition method for online computing and a related device are applied to the technical field of online computing, and according to the method, a computing device is replaced by an access layer switch to realize a multi-path forwarding capability, so that quick switching recovery when a network path fails is ensured, and the failure recovery time and the backspacing frequency are reduced. And meanwhile, dynamic mapping of paths and data storage addresses is realized by applying a relative index technology, and the flexibility and efficiency of data access are improved. The access layer switch intelligently records and analyzes network requests and data forwarding conditions, and the problem of data inconsistency is solved. The upper layer switch intelligently adjusts the data processing flow according to the data forwarding amount, and network resource utilization is optimized. By adopting the method, the stability and availability of a system related to online computing are improved, and an efficient, reliable and flexible data acquisition scheme is provided for online computing.

The invention discloses a flood peak enhanced physical base flow and residual error correction collaborative runoff prediction method, which belongs to the field of hydrological prediction, and comprises the following steps of: dividing a training set and a verification set according to a proportion, performing oversampling processing on flood peak samples, and constructing a time sequence window; a Xinanjiang model is discretized and expressed by adopting an ordinary differential equation, rainfall and potential evaporation data are input, and intermediate variables are obtained. A physical base flow and residual error correction dual-channel module is constructed, and physical base flow and residual error correction is calculated through two full-connection networks. And calculating a final runoff predicted value by adopting a residual connection structure, taking basic NSE loss as a core, superposing a flood peak sample error weighted item, strengthening flood peak fitting precision, and updating physical parameters and neural network weight through a back propagation algorithm. And verifying the model, and respectively calculating prediction indexes of the training set and the verification set. According to the method, fusion of a traditional hydrological model and a deep learning method is realized, the physical interpretation of the model is enhanced, and the basin runoff prediction precision is improved.

The invention discloses a port container automatic scheduling method based on multi-agent reinforcement learning, and the method comprises the steps: S1, building a corresponding relation between equipment and agents, and constructing a task set; s2, collecting operation state data, and constructing global and local state vectors; s3, generating a scheduling constraint vector, and cutting actions according to the resource, storage yard and path state to form a feasible action set; s4, on the basis of an improved QPLEX algorithm, constructing an individual value network containing a dump structure, and calculating an individual action value; s5, constructing a joint action value hybrid network, and mixing individual values according to the global state vector to form joint action values; s6, constructing a training sample, differentiating and aggregating instant and delayed return, and updating network parameters; and S7, during online scheduling, selecting an optimal action combination according to the combined action value, and generating and issuing a scheduling instruction. According to the invention, automatic collaborative scheduling of port container operation is realized.

The invention discloses a large model system based on a calculation acceleration chip, and relates to the field of large models. Comprising a plurality of calculation acceleration units and a management server, and an inter-chip and off-chip data interaction network is formed and realized; a mixed video memory of the calculation acceleration unit is matched with an SSD to form a multi-source storage mode; a normalized network-on-chip, an interconnection transmission system, a storage control system and a plurality of calculation acceleration cores are arranged in the calculation chip; the normalized network-on-chip can read model parameters of a target position based on the storage control system and send the model parameters to the calculation acceleration core for calculation and recovery; and interacting with the management server and other computing acceleration units based on the interconnection transmission system, and reading and storing external model parameters and inter-chip model parameters. The technical problems of insufficient video memory capacity, too high hardware cost and limited transmission bandwidth in a traditional scheme are effectively solved through collaborative design of a mixed video memory architecture and a normalized network-on-chip in combination with a multi-stage routing control and dynamic configuration mechanism.

The invention discloses a task processing method and device, in-network computing equipment, a medium and a product, relates to the technical field of computers, can provide a task processing method based on the in-network computing equipment, and improves the task processing efficiency. The method comprises the following steps: acquiring a task model and task data of a to-be-processed task from a central processing device by an in-network computing device, storing the task model and the task data of the to-be-processed task to the in-network computing device, performing block processing on the task data to obtain a plurality of task block data, and performing block processing on the task block data based on a plurality of processor cores of the in-network computing device. And performing parallel processing on the multiple pieces of task block data in the task model to obtain a task processing result.

Circuitry for performing neural-network calculations includes a plurality of compute circuits, arranged in parallel with respective inputs and outputs, to receive function arguments for a node of a neural network on their respective inputs, compute values of a plurality of activation functions using the function arguments, and provide the values on their respective outputs. Each compute circuit of the plurality of compute circuits is to compute the values of a respective activation function of the plurality of activation functions. The circuitry also includes a multiplexor to select between the respective outputs of the plurality of compute circuits and to provide the values on a selected output as activation-function values for the node of the neural network, based on an activation-function selection signal.

The invention discloses a real-time target detection model and method fusing multi-scale feature enhancement and dynamic label distribution. The real-time target detection model sequentially comprises a data preprocessing unit, a backbone network, a semantic detail injection feature fusion module, a ShareSePhead detection head, a dynamic label distribution unit, a training module and a post-processing unit. After the backbone network is subjected to convolution processing, three feature maps with different scales are output; the semantic detail injection feature fusion module converts the multi-layer features into serialized features and forms a unified fusion feature tensor; the detection head uniformly extracts features among the scales through a shared convolutional layer, and outputs a classification prediction vector and bounding box regression result; the training module is used for training and updating parameters; and the post-processing unit is used for executing filtering operation. According to the method, the reasoning speed is remarkably improved, and high-frame-rate real-time detection is realized; network computing resource allocation is optimized, and a better cost-effectiveness ratio is achieved.

The invention provides a multi-agent reinforcement learning regional energy collaborative scheduling method and system, and belongs to the field of regional energy system scheduling. Coupling degrees and a coupling degree matrix between agents are constructed; inputting the observation vector into a strategy network to obtain a decision action; individual basic rewards and system economic rewards are calculated, and constraint reference rewards are constructed; individual differentiation basic rewards are calculated, and rewards are distributed; inputting the decision action into a physical quantity prediction network, calculating a physical consistency reward, obtaining a final reward and a global reward, and calculating a target return; splicing observation vectors and decision actions of all agents, splicing global joint observation vectors and joint action vectors, inputting the spliced vectors into a value network, and training; inputting the local state set into the trained strategy network, outputting a scheduling instruction, inputting the scheduling instruction into the trained value network, and outputting an evaluation result; the problems of depiction rigidness of an intelligent agent coupling relation, lack of a cooperative benefit distribution mechanism and insufficient decision physical consistency are solved.

The invention provides a construction safety risk grading method and system combined with fuzzy clustering, and belongs to the technical field of building construction safety risk management.The method comprises the steps that firstly, a real-time risk feature set of a construction scene is obtained, and environmental influences, equipment operation and personnel operation features of a construction area are covered; secondly, fuzzy clustering preprocessing is conducted on the real-time risk feature set, fuzzy membership degree distribution and a feature correlation degree matrix of all risk features are obtained, a risk transmission network is constructed based on the result, nodes are risk features, edges are correlation degree parameters between the features, and risk diffusion coefficients of all the nodes are calculated through the risk transmission network; and generating a risk grade division result according to a preset grading rule, and finally outputting a construction safety grading instruction containing the risk area identifier and the corresponding management and control strategy, thereby dynamically and accurately evaluating the construction safety risk.

The invention relates to the technical field of industrial clusters, and discloses an industrial cluster industrial chain construction method and device, equipment and a medium, and the method comprises the steps: obtaining supply associated data and property right associated data of an enterprise of an industry category to which a target industrial cluster belongs; constructing a directed contact network based on the supply association data; constructing an undirected contact network based on the property right associated data; calculating property right connection degrees among the nodes in the undirected connection network, and accumulating the property right connection degrees to paths with corresponding node relations in the directed connection network according to a preset weight to generate a multi-source data enhanced network; and traversing all node paths in the multi-source data enhanced network, calculating the accumulated connection strength of each node path, and determining the path with the highest accumulated connection strength as the industrial cluster core industrial chain. According to the method, the universality, professional interpretability and objective accuracy of the constructed industrial chain are improved.

The invention discloses a GPU (Graphics Processing Unit) adaptive liquid cooling control method based on deep learning, relates to the technical field of GPU adaptive liquid cooling control, and overcomes the core defect of the existing GPU liquid cooling control in a sparse load scene through deep fusion of a deep learning method and a physical law. The model structure analyzer dynamically associates the neural network calculation characteristics with the physical layout of the chip to realize the pre-judgment type tracking of the heat source movement track, so that the cooling blind area is reduced from the source; a space-time attention mechanism is combined with a microdiscretization technology, so that cooling liquid distribution can respond to a millisecond-level heat wave peak, and the physical realizability of flow control is kept; and a resistance residual module and thermodynamic hard constraint are introduced, so that the robustness of the system under extreme working conditions such as pipeline abnormity is remarkably improved.

The invention relates to the technical field of office automation and business process intelligent supervision driven by big data, and discloses an office operation supervision method and system based on big data. The method comprises the following steps: firstly, extracting original logs containing an initiator, a receiver and timestamps from an approval system, checking one by one, de-duplicating and sorting according to time; counting flow times based on the ordered logs, and constructing an approval flow times matrix and a directed network; calculating the initiating and receiving quantity of each node, and screening actual participating nodes; calculating a flow imbalance index for each node, adaptively setting a threshold value according to a whole network average value and a standard deviation, and identifying abnormal nodes as bottleneck candidates; an adjacent matrix is constructed for the candidate nodes, connected clustering is carried out, and a structural bottleneck group is revealed; re-calculating the imbalance index according to an isochronous window in the whole monitoring period and counting the trend; and finally, combining the static unbalance degree and the dynamic change to generate a comprehensive score, and automatically outputting a structured monitoring report.

The invention relates to the technical field of information security, in particular to a network security event association detection method based on big data analysis. Comprising the following steps: data acquisition; feature extraction and fusion; correlation detection is carried out, wherein an improved Apriori-Bayesian fusion algorithm is adopted, and discretization processing is carried out on the event feature vectors; mining a frequent item set by using an improved Apriori algorithm; and risk assessment and result output. According to the method, an improved Apriori-Bayesian fusion algorithm is adopted, discretization processing is carried out on event feature vectors according to types, meanwhile, a security event weight factor is introduced to calculate the item set weighted support degree, and a minimum support degree threshold value is dynamically adjusted to mine a frequent item set; the association confidence coefficient is calculated in combination with the Bayesian network, and the confidence coefficient is corrected through the space-time association coefficient, so that the association relationship between the network security events can be scientifically judged, the problems of limited association judgment accuracy and lack of quantitative correction in the traditional technology are solved, and the association false alarm and missing report probability is reduced.

The invention belongs to the technical field of demand response optimization, and particularly relates to a multi-time scale demand response optimization method and device based on a double Q network, and the method comprises the steps: stage 1, initialization stage: importing basic data of a power distribution network, and constructing a target function and a double deep Q network DDQN structure; stage 2, an agent interaction stage: the main evaluation network predicts Q values of all potential actions, an agent selects the actions according to a greedy strategy, the selected actions are executed in a simulation environment, and an instant reward is calculated according to a reward function; stage 3, a network training updating stage: forming a training sample set, calculating a target Q value of a selected action by using a target network, calculating a square difference between a predicted Q value and a target value, and updating network parameters; and 4, a strategy deployment stage: when the learning process is converged or reaches the maximum training round, outputting a final demand response strategy. The economical efficiency of the power grid can be improved, and stable operation of the power grid is ensured.