417 results about "Data dependence" patented technology

The invention relates to the technical field of chip design, and discloses a chip dynamic power consumption scheduling method and system based on an intelligent algorithm. The method comprises the following steps of: firstly, acquiring instruction stream data operated by a chip in real time, extracting a feature vector comprising an instruction dynamic change vector and context associated data, and determining a power consumption prediction mapping parameter according to the feature vector; and when the parameter exceeds a preset threshold value, an accurate power consumption prediction result is generated by adjusting the weight of the convolutional neural network. Subsequently, a synchronous timing demand is calculated based on the instruction switching frequency and the data dependency, and an initial power supply configuration is determined. By monitoring task load classification signals, the power consumption distribution proportion is adjusted when the signals are lower than a threshold value, the optimized power supply configuration is obtained, and the improvement index of the resource distribution efficiency is calculated according to the optimized power supply configuration. And finally, according to the index, dynamically adjusting a limiting condition of a scheduling period, and forming a self-adaptive optimization framework, thereby realizing accurate prediction and dynamic optimization scheduling of the chip power consumption.

The invention relates to the technical field of cloud edge collaborative computing power scheduling, and discloses a heterogeneous computing power scheduling optimization method based on a cloud edge collaborative architecture. The method comprises the following steps: acquiring real-time computing power state data of all available computing nodes in the cloud edge collaborative architecture; performing heterogeneous type division on the computing nodes according to the real-time computing power state data to generate a three-layer computing power resource pool containing cloud computing nodes, edge computing nodes and terminal computing nodes; extracting task calculation features for the current to-be-scheduled task set, wherein the features comprise calculation intensity, data dependence and real-time requirements; constructing an initial task allocation scheme based on the matching relationship between the task calculation features and the three-layer computing power resource pool; iteratively optimizing the initial scheme by adopting a dynamic load balancing strategy to generate a final task scheduling instruction; the instructions are distributed to the corresponding computing nodes to be executed, and computing power state changes in the task execution process are continuously monitored.

The invention discloses a heterogeneous computing power cooperative scheduling system and method for mixed precision training, and belongs to the technical field of artificial intelligence computing. The system comprises a computational graph analysis and operator portrait module which is used for analyzing and dividing a model computational graph and extracting operator features; the heterogeneous hardware capability sensing and matching module is used for managing performance files and real-time states of heterogeneous hardware in the cluster and matching optimal execution hardware for each calculation partition; and the data flow coordination and pipeline parallel controller is used for generating a global execution plan, managing cross-device data dependence and communication and calculating overlapping optimization execution efficiency through communication. According to the method, the problem of low scheduling efficiency of mixed precision training in a heterogeneous environment is solved, automatic and accurate mapping from a calculation task to heterogeneous hardware is realized, the training speed is remarkably improved, the training cost is reduced, and the overall resource utilization rate of a cluster is improved.

The invention discloses a dynamic leakage fault diagnosis method for a flexible hand for a deep-sea submersible vehicle, and belongs to the technical field of flexible hands for the deep-sea submersible vehicle, and the method comprises the steps: obtaining source domain pressure signals from a plurality of different bending angles, and carrying out the preprocessing of the signals, and obtaining an original multi-source domain data set; a fault diagnosis model is constructed and trained, and in the training stage, the fault diagnosis model is a student network and comprises an adaptive frequency spectrum intervener, a multi-scale feature extractor, an adversarial mask generator, a main classifier and an auxiliary classifier; and inputting a to-be-diagnosed pressure signal into the multi-channel feature extractor and the main classifier in the trained student network, and outputting to obtain a fault diagnosis result. The method has remarkable advantages in the aspects of improving diagnosis precision, enhancing generalization ability, improving weak fault detection, reducing data dependence and the like, is suitable for intelligent diagnosis of hydraulic leakage of the deep-sea submersible flexible hand under dynamic and multi-angle working conditions, and has a good engineering application prospect.

The invention discloses a weak supervision pathological image tissue segmentation method based on text prompt learning. The method comprises the steps of feature extraction and initial class activation graph generation; using an MCRM module to optimize the initial class activation graph to obtain a refined class activation graph; and aggregating the plurality of refined class activation graphs to form a fused pseudo mask, taking the fused pseudo mask as a supervision signal, training a segmentation model, and after the training is completed, segmenting the new pathological image tissue by using the segmentation model. According to the method, a text prompt learning mechanism is utilized to focus the model on learning high-discrimination features, so that the influence of tissue co-occurrence is reduced. An initial class activation graph is optimized through a multi-mode class activation graph refining module, and the integrity of boundary segmentation is enhanced. Meanwhile, pseudo masks from different network layers are fused to train a segmentation model, and semantic segmentation of the pathological image is realized. According to the method, high-annotation data dependence is effectively relieved, and the generalization ability of the model is improved, so that application in the field of artificial intelligence-assisted medical treatment is promoted.

The invention relates to a real-time process monitoring method based on data analysis, and the method comprises the following steps: S1, building a three-dimensional component priority evaluation model based on a component operation scene type, a real-time resource occupancy rate and a data dependence degree, and dynamically matching an acquisition strategy; s2, a cleaning rule is adapted according to a data source, a feature extraction dimension is adjusted in combination with process dynamic features, and an improved time sequence decomposition algorithm is used for separating data trends, fluctuations and abnormal residual errors; s3, constructing an exclusive baseline sub-model by using an online learning algorithm according to a scene label, and establishing a scene switching mechanism; s4, in combination with component interaction anomaly features, an anomaly level is judged through a mixed detection model; s5, on the basis of exception processing and user feedback, constructing an error correction model optimization parameter; and S6, generating a report containing an abnormal propagation path, and triggering hierarchical collaborative response of the associated component. The invention aims to solve the problems of single acquisition dimension, no scene adaptability in preprocessing, incomplete abnormal detection and the like in the existing monitoring technology.

The invention belongs to the technical field of fault diagnosis, and discloses a thermal defect identification method and system for a high-voltage switchgear, and computer equipment, and the method comprises the steps: firstly segmenting an infrared image through employing a transfer learning optimized Mask R-CNN model, reducing the dependence of annotated data through sharing pre-training parameters, and achieving the region extraction of pixel-level equipment; secondly, multi-dimensional temperature information is extracted in combination with a gray histogram and a gray co-occurrence matrix, and key features are screened through PCA to enhance noise immunity; and finally, the LSSVM is adopted for classification, so that the training efficiency is remarkably improved. According to the method, the equipment area is automatically segmented through deep learning, temperature distribution is quantified in combination with multi-dimensional features, man-made misjudgment is reduced, pre-training model parameter sharing is utilized, new tasks are rapidly adapted in a small sample scene, the generalization ability and efficiency are improved, feature dimensions are compressed through principal component analysis, the real-time monitoring requirement is met, and the monitoring efficiency is improved.

The invention discloses a vision-language-action model training method and system utilizing inference data closed-loop optimization, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, performing initial training on a vision-language-action model by utilizing a training data set; deploying the trained model in a task environment to execute a task, monitoring a task execution result in real time, and capturing and structurally recording failure track data of the current task when task execution failure is recognized; then, based on the captured failure trajectory data, generating a negative prompt text for guiding the model to avoid repeated error behaviors; and finally, combining failure trajectory data with the generated negative prompt text, retraining the vision-language-action model, and inhibiting the model from generating action output similar to the error action sequence. According to the method, the data utilization rate is greatly improved, the data dependence and acquisition cost are effectively reduced, and the complete closed loop of the VLA model training and reasoning process is realized.

The invention discloses a text-to-action generation method and system based on body part fine-grained representation, and belongs to the field of human body action generation. Body part-level fine-grained discretization modeling is performed on human body actions to obtain an action encoder and an action decoder which can stably reconstruct a continuous action sequence; the method comprises the following steps: taking a part fine-grained discrete action space as a producible space, introducing video potential representation as space-time dynamic priori, establishing an alignment modeling mechanism of the video potential representation and the action discrete space, and training to obtain a conditional generation network, so as to realize stable prediction and iterative completion of an action discrete index sequence in a reasoning stage; and a continuous human body action sequence is reconstructed through an action decoder, and finally a human body action sequence which is consistent with text semantics, richer in details and more coherent in time sequence is generated. According to the method, the technical threshold and data dependence of action content production can be reduced, and the controllability and generalization ability of action generation are improved.

The invention belongs to the technical field of edge computing, and discloses a lightweight AI model adaptive deployment system oriented to edge computing. A dependency intensity matrix is constructed by accurately quantifying a data dependency relationship between model layers, network stability is monitored in real time, an abnormal time period is identified, a communication penalty factor and a bandwidth attenuation factor are calculated based on time delay peak distribution characteristics, and then a communication overhead prediction model for cooperative calculation between edge devices is constructed. The system innovatively generates a multi-granularity model segmentation candidate scheme set, identifies a segmentation boundary triggering resource competition by monitoring and calculating load fluctuation and memory occupancy change, and dynamically adjusts a model partition granularity and a mapping strategy according to a gradient transmission quantity and an activation value size at the segmentation boundary. According to the invention, the overhead of cross-device communication is reduced, the utilization balance of computing resources is improved, and the real-time response capability in a time delay sensitive scene is ensured.

The invention discloses a Kevlar cable section creep prediction method and system based on a physical informed neural network, and belongs to the technical field of material performance prediction. The method comprises the following steps: acquiring creep experiment data of a Kevlar material at different constant temperatures and tensions, constructing a data set, and carrying out preprocessing and division; constructing a neural network taking temperature, tension and time as input and creep displacement or strain as output; the creep time, tension and temperature dependence are converted into mathematical constraints, the mathematical constraints are embedded into a loss function of a neural network, and a physical informed neural network is formed; and training the network by using the training set, adjusting and optimizing the verification set, and finally evaluating the performance of the model by using the test set. According to the method, the contradiction between data dependence and physical consistency of a traditional creep prediction method is solved, and high-precision creep behavior prediction conforming to the physical law can be realized under the condition of a small amount of experimental data.

The invention relates to the technical field of instruction set conversion, and discloses an instruction set conversion method of a GPU heterogeneous environment based on simulation software. According to the method, the key instruction stream in the simulation task is accurately captured through the dynamic instrumentation method, and a solid foundation is provided for subsequent processing; the method comprises the following steps: dividing an original instruction stream into a plurality of instruction blocks to be converted through a classification mechanism according to instruction semantic features and hardware suitability, and creating conditions for parallel conversion; a lightweight front-end translator is adopted to efficiently convert classified instruction blocks into architecture-independent intermediate representations, the degree of parallelism and the data dependency relationship between instructions are reserved, the intermediate representation instructions are deeply optimized, and the method comprises the key steps of instruction selection, register allocation, instruction recombination, SIMT mapping, instruction coding and the like. And generating a native instruction of the target GPU architecture through accelerated translation of the target GPU thread block. According to the method, the instruction conversion period is shortened, and the correctness and the execution efficiency of the conversion result are improved.

The invention belongs to the field of intelligent prostheses, and particularly relates to an intelligent prosthetic control algorithm based on EMG electromyographic signals, which comprises the following steps: S1, electromyographic signal acquisition: acquiring the electromyographic signals of the forearm of a user through a multi-channel surface electromyographic sensor, the electromyographic signals being sEMG signals; s2, signal preprocessing; according to the time-frequency feature enhancement and mixed learning architecture, the system can realize more accurate and stable small sample gesture recognition, the processing capability and classification performance of the non-stationary electromyographic signals are remarkably improved, and in addition, due to the fact that deep features and discriminative manual features are fused and a lightweight network and a multi-modal decision mechanism are combined, the recognition efficiency of the non-stationary electromyographic signals is improved. A user can realize reliable and smooth gesture interaction in a low-delay and low-data-dependence embedded environment, and does not need to depend on a large amount of labeled data or complex computing resources, so that the whole method has higher adaptability and practicability.

The invention discloses a software development cloud computing system with a big data processing module, which relates to the technical field of computer systems and data processing, and comprises a development input acquisition module used for receiving source code data, construction script data, dependency declaration data, configuration file data and development environment description data, and respectively executing integrity verification, structure analysis, dependency analysis, parameter extraction and environmental element analysis processing to form a standardized development input data set. According to the method, unified feature abstracting and aggregation are carried out on source codes, construction scripts, dependency declarations, configuration parameters and development environment elements, version fingerprint data capable of stably representing the software version state is formed, the strict degree of analysis, verification and influence analysis is remarkably enhanced in a high-difference version scene, and the software version state can be stably represented. Therefore, the problems of misjudgment, missed judgment or resource waste caused by adoption of a fixed threshold value or manual parameter configuration in the prior art are avoided.

The invention belongs to the technical field of computer vision and ecological monitoring, and particularly relates to a large-scale bird flock counting system and method based on pure synthetic data training. In a model training stage, a large-scale bird flock composite image and a pixel-level label thereof are used as a unique training set, and end-to-end training is performed on a point prediction deep learning counting network using VGG19-BN as a backbone network to obtain a trained bird flock counting model; in the model training stage, real world bird flock images to be counted are input into the trained bird flock counting model, the model directly outputs predicted bird individual position points, a final counting result of the bird flock is obtained by counting the number of prediction points with high confidence, and a bird flock density distribution diagram can be generated for visualization. The invention provides a method and a system for realizing real scene high-precision counting only through synthetic data training based on a point prediction network aiming at the technical problems of strong dependence of real labeled data and insufficient cross-domain generalization ability of a model in a bird flock counting task.

The embodiment of the invention provides a program conversion method and a compiling device, and relates to the technical field of computers, in the method, an IR file of a GPU program is obtained to serve as a to-be-converted file, for a function parameter of any function in the to-be-converted file, the function parameter is converted into a function parameter matched with a CPU, and the converted parameter is obtained. And determining the IR statement having data dependence with the converted parameter as a statement to be adapted. And for any statement to be adapted, adjusting the statement to be adapted based on the parameter type of the converted parameter and the thread execution mask of the CPU. And compiling the adjusted to-be-converted file to obtain an executable file adaptive to the CPU. The GPU programs written by different high-level languages can be converted into the IR file, so that the conversion is carried out from the dimension of the IR file, and the support for different high-level languages can be realized. Therefore, the limitation is lower.

The invention discloses an equipment abnormal behavior tracing method and system, a medium and a product, and relates to the field of Internet of Things security. According to the method, a resident service process is monitored to receive network data, version identification is dynamically updated, process fragment nodes are generated, logic isolation of process states is achieved, and precursor context association is established. Meanwhile, a cross-fragment data dependency edge is generated based on the resource version mapping table. And when an abnormal alarm is received, starting from a target process fragment node, and performing priority reverse search by utilizing the fragment association and the cross-fragment data dependency edge. According to the method and the device, the long-term running process is segmented into the discrete logic units according to the business boundary, so that the problems of state pollution and dependency explosion caused by existing full-life-cycle traceability graph construction are solved, irrelevant historical business interference is eliminated, and the accuracy of equipment abnormal behavior traceability is improved.

The invention discloses a joint blind denoising method and system based on self-heuristic learning and Bayesian reasoning, belongs to the field of computational imaging, and solves the problems that in the prior art, the mixed noise modeling capability is insufficient, the performance is degraded under the condition of low signal-to-noise ratio, the combination of uncertainty quantization and regularization is lacked, and the generalization capability is limited due to data dependence. Comprising the following steps: collecting an original image and preprocessing; generating a noise data pair; an enhanced residual attention U-Net model is constructed; a noise estimation sub-network is adopted to extract noise features, the noise features are fused with original image features, and the model is trained; adopting the trained model to carry out multiple times of forward propagation on the same input image to obtain multiple groups of denoising results; calculating a mean value and a standard deviation to obtain a de-noising prediction and uncertainty heat map; and training the trained model again based on the uncertainty heat map, optimizing network parameters, and obtaining a final denoising prediction result and uncertainty estimation thereof. The method is suitable for complex noise distribution processing scenes.

The invention discloses a sheet metal part manufacturability reasoning method based on space-semantic map alignment, and relates to the field of manufacturing-oriented design evaluation and industrial knowledge reasoning, and the method comprises the following steps: carrying out geometric analysis on a CAD geometric model of a sheet metal part to be evaluated; abstracting the geometric features and the topological / metric spatial relationship thereof into a computable spatial semantic graph; performing semantic analysis on the process specification described by a natural language, converting the process rule into formalized logic check expression by using a large language model through context learning, and generating an executable domain-specific language check script; executing the script on a spatial semantic graph, realizing deterministic reasoning through graph matching and attribute verification, and completing accurate mapping and violation detection of text rules and geometric features; and outputting an interpretable diagnosis result containing violation feature positioning, triggering rules and numerical evidence. In order to solve the problems that a process rule'natural language-geometric model 'has a semantic gap, a traditional rule system is poor in adaptability, and an end-to-end learning method is high in data dependence and cannot be explained, a new rule can be quickly adapted under the condition that a large amount of data does not need to be labeled and a model does not need to be retrained; the method can accurately identify the violation of the micro-size and spatial relationship, and has reasoning preciseness, interpretability and engineering availability.

The invention discloses a crystal grain detection and analysis method and related equipment, effective crystal grains are obtained through corrosion expansion pretreatment denoising, OfficientNet and bidirectional feature pyramid network detection, contour obtaining through region segmentation and three-step filtering, qualification is judged in combination with a threshold value, a report is generated, and the existing technical problems are solved in a targeted mode. On the aspect of reducing calculation complexity, preprocessing reduces model data volume and interference, the model abandons complex modules, parameters are few, calculation cost is low, hardware occupation can be reduced, and detection and training time can be shortened; on the aspect of improving generalization ability, features are preprocessed and purified, interference of imaging conditions and material types is reduced, the number of layers of the model is simplified, multi-scale fusion ability is achieved, and detection in different fields can be adapted without optimization of a specific data set; on the aspect of reducing data dependence, invalid and pseudo crystal grains are accurately removed through three-step filtering, defects of a small-scale or low-quality data set are cooperatively made up, dependence on a high-quality large-scale data set is greatly reduced, and robustness is improved.

The invention discloses a sediment prediction method and system for oscillation period strategy snow ablation optimization, and the method comprises the steps: obtaining sediment data characteristics, enabling a drainage basin to comprise a plurality of nodes, and calculating the snow melting runoff of each node according to the sediment data characteristics; according to the snow melting runoff of each node, calculating the initial sand production concentration of each node; and constructing a sediment prediction model, inputting sediment characteristic data and corresponding actual sediment concentration to the sediment prediction model to obtain a trained sediment prediction model, inputting real-time sediment data to the trained sediment prediction model, and outputting predicted sediment concentration by the trained sediment prediction model. According to the method, historical sediment data are acquired, and a graph convolutional neural network is constructed for learning complex nonlinear mapping from snow melting-runoff generation to sediment transportation, so that the problems of weak generalization ability and strong data dependence of an existing snow melting period sediment prediction method are solved.

The invention belongs to the technical field of remote sensing image processing and computer vision, discloses a semi-supervised ground feature classification optimization method for an urban remote sensing scene in a complex environment, and solves the problems of strong dependence on a large amount of annotation data, incomplete model feature extraction and low calculation efficiency in the prior art. According to the method, firstly, through a cross-view weak-to-strong consistency training framework, a weak enhancement view is utilized to generate a high-confidence pseudo tag, and through applying consistency constraint to a strong enhancement view, a self-optimization training cycle is constructed, so that the dependence on pixel-level annotation data is remarkably reduced. Secondly, a mixed CNN-Mama double-flow framework is adopted, and local texture features are extracted through a lightweight residual error convolution module; according to the method, the classification precision, robustness and generalization ability of the model in a complex city scene are effectively improved, meanwhile, the high efficiency of the method is ensured through lightweight design, and the method is suitable for actual application scenes such as disaster loss assessment and city planning.

The invention discloses a malicious code control flow feature extraction method based on a graph neural network. The method comprises the following steps: constructing a control flow graph, a data flow graph and a function call graph; designing a drawing neural network architecture; training a graph-level classifier; performing graph interpretation by using a GNNExplainer algorithm, attention mechanism analysis and a gradient analysis method; converting the extracted control flow mode into a structured detection signature, and mapping the structured detection signature to an original binary code; and integrating with a static analysis tool through a standardized interface. The invention further discloses a malicious code control flow feature extraction system based on the graph neural network. Multi-level graph structure representation is constructed, important information such as a control flow structure and a data dependency relationship is fully reserved, the deep structure similarity of malicious codes can be recognized, the deformation resistance is higher, and therefore the malicious code detection precision is improved; according to the method, key sub-graphs can be recognized, graph structure features are converted into detection rules, then the detection rules are integrated with existing static analysis tools, and practicability is improved.

The invention discloses a superheat degree identification method based on self-supervised pre-training and feature fusion, and the method comprises the steps: the first stage is self-supervised pre-training based on a priori guidance learnable mask, and the second stage is supervised fine tuning based on feature fusion and a KAN network. The first stage comprises video slicing and space-time embedding, learnable masks guided by priori knowledge, and asymmetric encoder-decoder training; and the second stage comprises double-flow feature extraction, cross attention-based feature fusion, KAN network classification and supervised fine tuning. The invention relates to the technical field of industrial process intelligent perception and computer vision, and solves the problems of strong dependence on labeled data, weak generalization ability under small samples, incomplete feature expression and insufficient interpretability in the prior art.

The invention discloses a monomolecular structure design and generation method based on a large language model, and relates to the crossing field of monomolecular electronics and artificial intelligence. In order to solve the problems of low single molecule design efficiency and insufficient data, SingMolT5 is obtained through field fine tuning on the basis of MolT5, and generation from a natural language to a molecular SMILES is realized. According to the method, data are collected from literatures in the single molecule field and an existing disclosed molecule library, a fine tuning data set containing 329 high-quality instructions is constructed, and the fine tuning data set comprises three basic data types including a molecular skeleton, an anchoring group and molecules. The model is initialized by a MolT5 check point, and a cross entropy loss function is used in the fine tuning process; reasoning, generating and using a beam search strategy; the follow-up evaluation indexes comprise BLEU, Levenshtein, MACCS, RDK, Morga and effectiveness. The method provides an innovative technical path for'low experience and data dependent type single molecule design 'in the field of single molecule electronics, and is particularly suitable for aided design of a single molecule device core function unit and a single molecule sensing probe molecule, namely, a target molecular structure can be quickly converted through a natural language, the design threshold of researchers is reduced, and the design efficiency is improved. And a traceable technical basis can be provided for screening and iteration of a monomolecular structure based on a high-quality data set and rigorous evaluation logic.

The invention discloses a light field microscopic self-supervised denoising system and method fusing a physical process. The system comprises a light field imaging subsystem and a self-supervised denoising subsystem. The light field imaging subsystem is used for capturing multi-view light field original data of a sample; the self-supervised denoising subsystem is used for processing original data of a light field, preprocessing the original data of the light field in a training stage, and decomposing the original data into multi-view sub-images; the method comprises the following steps: constructing original data of a training set through two different self-supervision strategies, and then generating a self-supervision training data pair through RL deconvolution according to a physical optical process; and finally, a denoising model is obtained through 3D neural network training. In the reasoning stage, light field original data to be reconstructed are preprocessed and then subjected to RL deconvolution to generate input data to be denoised, the input data are input into the trained denoising model, and a reconstruction result is output. According to the invention, the problems of noise amplification, data dependence and poor universality of the light field fluorescence microscope are effectively overcome.

The invention discloses a task decomposition and arrangement and exception retry method and system for a workflow engine, and relates to the technical field of task decomposition and arrangement management. According to the method, a service request received by a workflow engine is acquired, structured analysis is performed on the service request, the service request is decomposed into one or more groups of associated interaction subtasks, and an execution-oriented task arrangement relationship is dynamically constructed according to a data dependency relationship among the interaction subtasks. And generating a task graph containing nodes, edges and trigger conditions according to the task arrangement relationship, thereby generating a workflow which can be scheduled and executed in the workflow engine, monitoring the execution state of each interaction subtask in real time in the workflow execution process, and when the execution state is monitored to be abnormal, executing the task according to the task graph. And retry arrangement and rescheduling execution are carried out on the corresponding interactive subtasks, and validity verification is carried out in the execution process, so that the matching degree between the task decomposition arrangement process and the abnormal subtask self-adaptive retry strategy is improved.

The invention relates to the technical field of data processing, in particular to a localized low-power-consumption computing power aggregation scheduling system and method based on a heterogeneous SoC, and the system comprises a local networking module, a modeling module, a scheduling distribution module, an execution module, a result aggregation module and an optimization scheduling module. According to the method, a technical chain from dynamic perception to intelligent decision and then to closed-loop control is constructed, multi-dimensional parameters of computational nodes are deeply coupled with demand parameters such as the calculated amount of tasks and the data dependency relationship, the coupled parameters are input into a scheduling model with the total energy consumption of a system as an optimization target, and in a local dynamic network with power supplied by a battery, the optimal energy consumption of the system is obtained. The system can adaptively select the node combination with the lowest energy consumption cost and the task decomposition mode, and the problem that reliable and efficient persistent computing power aggregation cannot be realized in the scene due to the fact that an optimization target and a resource sensing model do not conform to the real constraint of a low-power-consumption dynamic network is effectively solved.