2830 results about "Computational resource" patented technology

The invention relates to the technical field of cloud side end computing, and discloses a cloud side end cooperative computing resource dynamic allocation method based on task-aware migration. The method comprises the following steps: acquiring real-time load characteristics and resource demand characteristics of calculation tasks in a cloud side end system, and dividing task priority queues in combination with task type identifiers; extracting historical execution records of tasks at cloud, edges and terminal nodes, constructing a task execution feature library, and generating a resource demand prediction model in combination with real-time load features; analyzing network transmission time delay characteristics of a cloud end and edge nodes, measuring real-time calculation capability fluctuation data of terminal equipment, and establishing an inter-node resource collaboration degree evaluation matrix; generating an initial migration strategy according to the prediction model and the evaluation matrix, monitoring actual resource occupancy deviation of the task, forming a final decision in combination with a node resource state correction strategy, triggering cross-node migration, and synchronously updating the priority queue and the evaluation matrix.

The invention provides an end-side multi-modal large model accelerated reasoning method and system, and the method comprises the steps: carrying out the two-stage screening and rearrangement of visual tokens based on the CLS attention and text-to-visual attention in a visual encoder and pre-filling stage, and constructing a sparse attention and sparse key value cache; in a decoding stage, an important neuron set is judged according to activation gating or historical statistics, only a corresponding feedforward network weight is pulled and calculated, missed weights are loaded on demand through asynchronous I / O, and hot neurons are maintained in a high-speed memory to utilize model sparsity, so that video memory / memory occupancy and calculation overhead are remarkably reduced on an end side; throughput and time delay performance are improved. According to the method, the internal memory and computing resources required by reasoning of the multi-modal large language model are reduced from two dimensions by utilizing the endogenous sparsity of the end-side large language model in input and the model, so that a higher reasoning speed is achieved by utilizing fewer resources on the premise of keeping the size of the model unchanged, and the performance of the whole system is improved.

The present invention relates to a system and computer implemented method for cost-aware autoscaling of artificial intelligence workloads using predictive queueing models, designed to achieve proactive and economically optimized scaling of computational resources across cloud and edge environments. The invention introduces a predictive queueing-based technique that anticipates future workload congestion by modeling dynamic task arrivals and service times using a stochastic queueing process. A cost estimation unit computes the total projected operational cost of potential scaling actions by integrating real-time infrastructure pricing data, predicted delay penalties derived from service-level objectives, and estimated energy consumption. A scaling decision unit applies reinforcement learning-based optimization to select the scaling action that minimizes total cost while ensuring compliance with latency and throughput constraints. The system includes a hardware-integrated autoscaling controller device comprising a predictive computation processor, cost-decision processor, and scaling actuation interface configured for real-time execution of predictive and scaling operations.

The invention relates to a wellbore multiphase flow model numerical solution and gas-liquid distribution state inversion method and system, and belongs to the technical field of petroleum engineering, and the method comprises the steps: 1, constructing and training a physical information neural network for drilling wellbore multiphase flow dynamic simulation and overflow gas distribution state inversion; determining input and output of the physical information neural network; determining a loss function of the physical information neural network; training a physical information neural network; 2, designing an adaptive optimization algorithm, optimizing the final solution precision and convergence speed of the physical information neural network, and obtaining an adaptive physical information neural network; designing an adaptive activation function; designing a self-adaptive sampling mechanism based on residual errors; 3, based on the self-adaptive physical information neural network, numerical solution and gas-liquid distribution state inversion of the shaft multiphase flow model are achieved. According to the method, the problem that a traditional numerical method usually needs high-precision grid division and a large number of computing resources is effectively solved.

The invention relates to the technical field of cable laying management, and discloses a power industry cross-domain computing power dynamic scheduling system based on super intelligent fusion. According to the system, computing power demand data of each business domain in the power industry is collected in real time, computing resource demand characteristics in different business scenes are identified, and a cross-domain computing power demand characteristic graph is generated; meanwhile, the real-time load state and the available resource quantity of each computing node are continuously tracked, and a distributed computing power resource state matrix is constructed; analyzing and calculating a matching relationship between resource demands and available resources, and generating a multi-objective optimized computing power scheduling strategy scheme; according to the scheme, power business calculation tasks are distributed to optimal calculation nodes according to priorities and resource requirements, and a cross-domain execution process is triggered; and finally, the task execution state and the resource use condition are monitored in real time, an evaluation report is generated and fed back to a strategy generation module, closed-loop optimization is formed, and efficient collaboration and dynamic scheduling of cross-domain computing power resources in the power industry are achieved.

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 embodiment of the invention discloses a resource scheduling method and device, equipment and a medium, and relates to the technical field of resource scheduling. The method comprises the following steps: acquiring a service quality constraint index of a data processing task, and resource states of a cloud center and an edge node; constructing a three-dimensional dynamic resource feature space according to the resource state fluctuation information of the edge node, the spatio-temporal information of the cloud computing and the edge node and the historical occurrence probability of the service quality constraint index; and performing particle swarm optimization based on the three-dimensional dynamic resource feature space to obtain an initial strategy set, scheduling computing resources in the cloud center and the edge node based on the initial strategy set, and processing the data processing task based on the scheduled computing resources. According to the technical scheme, scheduling is flexibly carried out according to the condition of the data processing task and the resource condition of the cloud center and the edge node, and the actual requirement of the data processing task is accurately met.

The present invention provides a road crack detection method, a medium, and a product. The method comprises: acquiring a road crack image and inputting same into a pre-trained lightweight YOLO-MCS road crack detection model to obtain a road crack detection result, wherein the lightweight YOLO-MCS road crack detection model is constructed on the basis of an improved yolov8 network. A yolov8 network improvement method comprises: replacing a feature extraction network backbone with a lightweight convolutional neural network MobileNet V3, and embedding a coordinate attention (CA) mechanism module in the lightweight convolutional neural network MobileNet V3; adding a small target detection layer and a squeeze-and-excitation (SE) module at a neck end; and introducing a power IoU loss function to a head prediction structure. The low detection accuracy of existing detection algorithms for fine cracks and the difficulty in applying existing detection algorithms to edge devices having limited computing resources are overcome.

The invention provides a node task migration and scheduling system based on digital twinning, and relates to the technical field of computer system structures and data processing. Computing resource interference in a multi-tenant sharing environment is quantized by sensing a cross-tenant noise coefficient and a state synchronization complexity entropy in a node micro-architecture; extracting track features of the mobile terminal, calculating spatial discrete variance, generating a self-adaptive migration decision hysteresis factor, and converting the migration decision hysteresis factor into decision damping to inhibit invalid high-frequency reciprocating migration; constructing a digital twin sandbox before physical cutover, cooperating with a chaos scene injection engine to inject a composite fault operator into a bottom layer, and performing actuarial calculation on service continuity retention after risk adjustment by using a fidelity integrator; and finally, a bottom layer controller is linked through safety baseline comparison to execute physical flow switching. According to the method, network boundary deduction is completed on the premise that physical bandwidth is not consumed, the interruption risk caused by state hard switching is avoided, and smooth transition of stateful services is effectively guaranteed.

The invention discloses a dense small target detection method for an unmanned aerial vehicle aerial photography scene, and belongs to the technical field of computer vision and target detection. In order to solve the problems of small target scale dynamic change and feature expression weakening caused by flight height change, imaging resolution difference and scene complexity in aerial photography of an unmanned aerial vehicle, the invention provides a detection framework fusing an attention scale selection (AGSS) module and a dynamic local self-attention (DPSA) module. The method specifically comprises the following improvements: (1) an AGSS module enhances the significance and discrimination ability of small targets in multi-scale features through global context modeling and a dynamic weight distribution mechanism; and (2) a DPSA module introduces a sparse selection mechanism in a channel dimension, and focuses computing resources on a channel sensitive to a small target, so that efficient and lightweight attention modeling is realized. The above modules cooperate with each other, so that high reasoning efficiency is maintained, and small target detection precision and robustness in a complex background, low illumination and dense target scene are significantly improved. Experimental results show that on typical unmanned aerial vehicle aerial photography data sets such as VisDrone-DET2019 and the like, the method is superior to an existing mainstream method in multiple indexes such as the average precision (mAP), the accuracy rate and the recall rate, especially has obvious advantages in the aspects of integrity and stability of small target detection, and has good practical application value and popularization prospects.

A scalable expert foundry system enables creation, management, and coordination of multiple specialized expert domains, each developing autonomous cognitive capabilities through geometric manifold formation while maintaining hierarchical oversight and cross-domain knowledge transfer. The system utilizes a Persistent Cognitive Machine architecture with hierarchical supervisory networks that provide multi-layered coordination, conflict resolution, and quality management across distributed expert domains. Cross-domain coordinators orchestrate communication and knowledge sharing between domains through geometric abstraction and manifold projection techniques that preserve semantic integrity while enabling beneficial knowledge propagation. Executive manifold supervisors implement second-order control architectures managing meta-cognitive capabilities and system-wide reasoning strategies. The system supports enterprise deployment across multiple geographic regions with distributed computing resources. Expert domains achieve operational readiness through statistical observables monitoring including cache hit rates, distance distribution shifts, and trajectory coherence measurements that validate manifold maturity. The architecture enables scalable expert-level performance across diverse knowledge domains while maintaining coordination effectiveness and quality standards.

The invention relates to the technical field of electrical digital data processing, and discloses a lightweight-based multi-modal data enhancement method, which comprises the following steps: acquiring a multi-modal feature tensor; extracting a vector orthogonal projection scalar and determining the novelty; updating the global covariance matrix when the novelty is greater than a redundancy threshold, and maintaining the global covariance matrix in a register state when the novelty is not greater than the redundancy threshold; extracting a main diagonal variance component to determine a differential modulation coefficient; calculating a second-order moment manifold projection operator according to the global covariance matrix, and calibrating the operator by using a differential modulation coefficient; the calibrated operator is used for carrying out orthogonal projection on random noise to generate a structured disturbance vector, the structured disturbance vector is superposed to a multi-modal feature tensor to output enhanced features, a novelty judgment mechanism is used for restraining statistical deviation caused by steady-state redundant data, computing resource occupation is reduced, and it is ensured that semantic alignment between modals is maintained in enhanced feature distribution.

The invention relates to the field of artificial intelligence and computer science, in particular to a causal structure and latent variable-based adaptive reinforcement learning reasoning migration method, which comprises the following steps of: constructing a causal world model fused with multi-modal observation and a decoupling latent variable space; establishing a hierarchical inference engine comprising an intuition layer, a conventional layer and a planning layer; pre-training a quick response and judicial planning dual-mode strategy and generating an interpretable fuzzy rule base; performing calculation level coarse tuning based on task identification and causal complexity; evaluating the real-time state criticality through an adaptive neural fuzzy system and dynamically switching a decision mode; after the action is executed, the threshold and the rule are subjected to closed-loop optimization, and cross-environment efficient migration is realized by utilizing a causal modularization characteristic. According to the technical scheme, consumption of computing resources is remarkably reduced on the premise that decision precision and safety are guaranteed, and the response speed and cross-scene adaptive capacity of a system on edge equipment are improved.

The invention relates to the technical field of low-altitude equipment, in particular to a low-altitude resource intelligent scheduling method and system based on deep learning, and the method comprises the steps: collecting the real-time state and network load data of a low-altitude flight equipment group, and constructing a dynamic operation data set; generating an operation mode feature set through multi-dimensional airspace situation awareness and analysis, and performing sparse clustering division based on the feature set to form a network resource demand priority mapping table; traversing the mapping table to dynamically calculate the resource demand, determining a multi-dimensional weight coefficient, and performing high-dimensional feature dimension reduction and optimization through a mixed integer nonlinear programming solver to obtain a resource demand feature vector; constructing a resource scheduling strategy optimization model by adopting a deep reinforcement learning algorithm based on the vector; inputting real-time data into the model to execute a resource scheduling decision, and outputting a dynamic allocation strategy; simulation deduction and compliance verification are carried out on the strategy in the digital twin simulation platform, and cooperative intelligent scheduling of communication, calculation and spectrum resources is achieved.

The invention discloses an explosion-proof and intrinsic safety type combined feeder switch state monitoring method based on big data, and relates to the technical field of industrial electrical equipment state monitoring and fault diagnosis, and the method is realized based on a three-level architecture constructed by an edge computing node, a region computing node and a cloud platform. Comprising the following steps: S1, collecting multi-source sensing data of a feeder switch in real time by an edge computing node, and performing feature extraction and fusion calculation on the multi-source sensing data; according to the method for monitoring the state of the explosion-proof and intrinsic safety type combined feeder switch based on the big data, the contradiction between the real-time performance and the accuracy in multi-source heterogeneous data fusion processing is effectively solved, abnormity can be found in the first time, early warning can be triggered, and the reliability of a diagnosis conclusion is improved; and the accuracy and foresight of fault diagnosis are ensured. According to the grading processing mechanism, computing resources are reasonably distributed, the network transmission load is greatly reduced, and the system can stably operate in a complex industrial environment.

The invention provides a storage resource optimization method and system based on a time sequence dependence hypergraph neural network, and belongs to the field of artificial intelligence computing. Based on medical health big data and computing resources, constructing and fusing data and computing resource dependency matrixes to obtain a static dependency relationship matrix; the method comprises the following steps: collecting a computing resource multi-source operation log, generating dynamic characteristics of each moment according to a fixed interval, introducing time sequence position coding and self-attention mechanism weighting in a sliding time window to obtain attention optimization characteristics, and generating a dynamic dependency weight matrix by combining a modeling historical hidden state and the dynamic characteristics; the static and dynamic dependency weight matrixes are fused to obtain a comprehensive dependency matrix, attention optimization features are used as nodes, hyperedges are constructed in combination with the comprehensive dependency matrix, and hypergraph association and other matrixes are generated; and inputting the matrix into a graph neural network, learning node representation in combination with a time sequence attention network, classifying nodes and mapping the nodes into scheduling actions, and realizing self-adaptive allocation of storage resources in combination with target function optimization of medical scene constraints.

The invention relates to a computing power resource dynamic scheduling method, device and equipment based on deep reinforcement learning and a medium thereof, and the method comprises the steps: constructing a joint state vector through real-time fusion of a network layer channel state and computing layer node load data, and driving a strategy network to generate transmission parameters and resource allocation actions of cooperative control; the code modulation parameters of the wireless transmission module and the computing resource proportion of the target node are synchronously configured in the execution layer, and dynamic task scheduling in the channel decay environment is achieved; a multi-target reward mechanism is designed to couple transmission bit error rate penalty, resource utilization efficiency and task timeliness evaluation indexes, and a reinforcement learning agent is guided to balance communication stability and computing power demand conflicts; according to the method, strategy network parameters are optimized through time difference errors, closed-loop feedback is formed in combination with channel state prediction and node load updating, the problems of network and calculation layer splitting decision, insufficient dynamic adaptability and multi-target optimization imbalance in the prior art are effectively solved, and the task scheduling success rate in the time-varying wireless environment is improved.

The invention relates to the technical field of multi-agent cooperative control, and discloses a multi-agent autonomous decision-making method based on deep reinforcement learning. The method comprises the steps of synchronously detecting an initial collaborative state of a cluster, performing joint situation assessment, and judging a collaborative operation mode according to a quantitative situation. And analyzing the capability of each agent and the real-time task load, and constructing a distributed task knowledge graph. And utilizing the atlas to drive a deep reinforcement learning network, coupling computing resource allocation and a task path, and generating a preliminary behavior strategy of each agent. And performing cluster-level conflict detection and iterative negotiation adjustment, and finally issuing an executable action instruction sequence. According to the method, integrated optimization of resource allocation and action paths is realized, the situation understanding and negotiation mechanism is enhanced through the knowledge graph to guarantee the collaborative consistency, and the collaborative decision-making efficiency and task execution robustness of a multi-agent system in a dynamic environment are improved.

The invention relates to the technical field of high-performance computing resource management, and discloses a computing resource allocation method for a distributed supercomputing center. The method comprises the following steps: on the basis of obtaining real-time computing task and supercomputing center resource data and uniformly quantifying, integrally predicting resource requirements of future tasks; constructing a mixed integer linear programming model with the minimization of the total operation cost as a single target, wherein the total operation cost is the sum of the energy cost, the carbon emission cost, the data transmission cost and the SLA default penalty cost; solving the model by taking the time-varying electricity price, the green energy ratio, the resource capacity and the network parameters of each center as constraint conditions to generate an optimal resource allocation scheme; and then, by dynamically monitoring the resource state and the task progress, the model is triggered to resolve when the resource utilization rate is detected to be unbalanced or default risks, so that self-adaptive adjustment is realized. According to the invention, global collaborative resource allocation across super computing centers is realized, and operation economy, environmental sustainability and service reliability are considered.

The invention discloses an mRNA non-coding region sequence optimization method and system and electronic equipment, and the mRNA non-coding region sequence optimization method comprises the steps: constructing an initial candidate library according to a target protein; inputting the initial candidate library into a pre-trained mRNA sequence optimization model to obtain a prediction data set; performing multi-dimensional scoring and sequence optimization on the prediction data set to obtain a sequence recommendation group; performing biological verification on the sequence recommendation group to obtain an optimized mRNA sequence; wherein the prediction data set comprises a sequence ID, a sequence content, a prediction TE score and a confidence interval. According to the method, the translation efficiency of the mRNA sequence can be efficiently and accurately predicted, the candidate sequence with high expression potential is screened out, meanwhile, the consumption of computing resources is reduced, and the overall design cost is reduced.

An illustrative method for performing a risk scenario assessment and remediation may include identifying, based on posture data associated with a compute environment, one or more compute resources deployed in the compute environment that are configured to be connected to a network, accessing runtime workload data associated with the one or more compute resources representative of network activity for the one or more compute resources, and performing, based on the posture data and the runtime workload data, a remediation operation associated with the one or more compute resources.

The invention provides a long video understanding method capable of relieving time sequence illusion in a video language large model. The long video understanding method is based on a static bias adaptive frame selection mechanism and a cross-modal feature fusion strategy. According to the static bias mechanism, inter-frame similarity is evaluated through a discriminator, redundant frames are identified, key frames are selected or a complete sequence is reserved, so that calculation overhead is reduced, and spatio-temporal information integrity is kept; a video frame and a text are mapped to a shared semantic space, the single-frame semantic understanding ability is enhanced, then an embedded sequence serves as a soft prompt to be input into a large language model, and a final answer is generated in an autoregression mode. According to the method, the efficiency and accuracy of long video understanding and video question and answer tasks can be remarkably improved; the problem of low training and reasoning efficiency caused by time sequence dependence redundancy and excessive computing resource consumption is effectively relieved; and through a dynamic multi-modal task processing framework and a space-time memory bank compression mechanism, the modeling capability and generalization performance of the model on a long video sequence are further improved.

Systems and methods for intelligent data sanitization employing PCM and AI / ML are provided. The idea uses AI / ML to detect specific facts that needs sanitization rather than full properties in incoming records. Data sanitization is optimized using this focused method, saving computational resources. To properly manage changing data volumes, PCM shifts between Logical 0 and Logical 1 states. Logical 0 processes smaller volumes with high resistance and low conductivity, while Logical 1 processes large volumes with low resistance and high conductivity. The AI / ML module organizes and directs data to maximize resource and processing efficiency. The PCM processes data in-memory and directly overwrites, eliminating erasure. AI / ML and PCM integrate to sanitize data quickly, efficiently, and securely, improving system performance and data integrity without a central repository. The system dynamically adjusts to changing data patterns, protecting and optimizing data.

The invention relates to the field of resource adaptive scheduling, and discloses an intelligent door lock control method and system based on deep learning, and the method comprises the steps: obtaining the system load, execution time, resource occupancy rate and other data, and obtaining the overall performance state description; according to the state description, a dynamic conflict quantized value is calculated, execution time deviation is evaluated, and a reasoning stage list needing to be adjusted is determined; extracting fluctuation trend characteristics based on historical records, and optimizing a resource allocation proportion to obtain an adjusted execution strategy scheme; judging whether the actual accuracy rate reaches the preset accuracy rate or not by applying the strategy scheme; if yes, the cycle interval duration of the self-adaptive control mechanism is determined; and scheduling the next monitoring process through the cycle interval duration, repeating the dynamic conflict evaluation, and dynamically regulating and controlling the execution strategy scheme. According to the method, real-time and self-adaptive allocation of computing resources of the door lock control system can be realized, dynamic conflicts are effectively solved, and millisecond response speed and recognition accuracy under high load are guaranteed.

An AI-connected-electrified (ACE) heavy truck system equipped with an intelligent multi-mode hybrid (iMMH) powertrain system and a vehicle supervision control strategy based on machine learning (ML) or reinforcement learning (RL) paradigm are presented. This system ensures industry-leading power and braking performance of the ACE heavy truck while automatically optimizes both energy saving and emission reduction based on the vehicle's dynamic driving data and 3D electronic map information of roads for any transport event. In this application, the conventional analog electronic control (AEC) method is replaced by a novel digital pulse control (DPC) method on the instantaneous power function of the engine. The DPC method converts the complex surface working conditions of the AEC engine of the hybrid vehicles into simpler pre-defined working condition lines of the DPC engine. Consequently, the multi-variable nonlinear technical problem of simultaneously optimizing real driving environment (RDE) fuel consumption and pollutant emissions of the ACE heavy truck is simplified into two decoupled quasi-liner optimization problems, and ensures the reduction of on-vehicle computing resources for real-time AI inference computation and the improvement of the optimal performance, the convergent rate, and the robustness of the corresponding fuel-saving algorithm for the trained ML model or the learned RL model. Ultimately, the ACE truck achieves in the engineering sense the global minimum RDE fuel consumption and pollutant emissions meeting the standard consistently at high performance to cost ratio for any transport event and the RDE fuel consumption is decoupled from the vehicle configuration parameters and the human driver.

The invention relates to a method for deploying a spiking neural network to a hardware device. The method includes providing the spiking neural network, training the spiking neural network to obtain a trained spiking neural network, mapping neurons and synapses in the trained spiking neural network to corresponding components of the hardware device, simulating deployment of the trained spiking neural network on a hardware device using the obtained mapping, and deploying the trained spiking neural network to the hardware device using the mapping and the simulation. The training, mapping, simulation and deployment steps are executed by using hardware information of the hardware device; wherein the hardware information comprises at least one of hardware resource constraints, hardware connection constraints, dynamic range of hardware design parameters, characterization or statistics of neurons and synapses, reconfigurability, programmability, yield, computing resources, temporal characteristics, constraints on pre-processing, interfaces and peripheral devices, and available encoders and / or decoders.

The invention provides a wind-induced response prediction method and device for a large-span bridge structure and electronic equipment, and the method comprises the steps: obtaining the wind power response data of a bridge in a wind environment; decomposing the wind power response data by adopting a dynamic mode decomposition algorithm to obtain first mode information in the current wind environment; and inputting the mode information into a pre-trained target neural network model, and outputting a wind-induced response prediction result. According to the method, through the synergistic effect of the physical insight of the DMD and the data analysis capability of the neural network, the multi-scale flow mode can be accurately analyzed in real time, meanwhile, the dependence on a large number of computing resources is reduced, the DMD and the neural network model are fused, and the fusion strategy not only solves the limitation of the traditional DMD on nonlinear response prediction, but also improves the prediction accuracy of the DMD. And the defects of the neural network in physical law understanding are overcome, and high efficiency, accuracy and intelligence of wind-induced response prediction are realized.

In the implementation of techniques for deploying machine learning models with automated resource management, a system receives logic corresponding to a machine learning model and computing resource data corresponding to a plurality of computing resources available. Based on the logic and the computing resource data, the system generates the machine learning model and an allocation of one or more computing resources of the plurality of computing resources available for the machine learning model, in which the machine learning model conforms to the logic. Upon generation of the machine learning model and the allocation of the one or more computing resources, the system deploys the machine learning model and the allocation of the one or more computing resources of the plurality of computing resources available for the machine learning model.

The invention discloses a heterogeneous computing network resource collaborative scheduling optimization method based on self-adaptive multi-agent, and aims to solve the scheduling problem caused by resource heterogeneity, load dynamics and task high concurrency in a heterogeneous computing network system. According to the method, cross-domain resource collaboration is realized by constructing three sub-domain adaptive agents of a computing resource domain, a network resource domain and a storage resource domain and a global collaboration layer. According to the method, a deep reinforcement learning algorithm and an 'LSTM + GNN' fusion model are integrated, and multi-target adaptive optimization of resource utilization rate, task time delay, service quality and energy consumption is achieved through closed-loop optimization of state perception, strategy generation, value evaluation and strategy updating. The heterogeneous computing network resource fine-grained sensing, cross-domain cooperative scheduling and multi-target dynamic optimization are realized, the resource utilization rate and the task completion rate are high, the service quality and the energy consumption performance are good, and the dynamic response capability and the overall performance of the heterogeneous computing network system are improved.

The invention relates to the technical field of information processing, and discloses a method for dynamically regulating and controlling production parameters of a plastic film by utilizing program process scheduling. The method comprises the following steps: converging a real-time parameter sequence to a digital twinborn body to establish virtual mapping, and constructing a multi-dimensional data model; analyzing a material state evolution trend in the digital twinborn body, synchronizing with a physical production line state, fusing historical data to predict a potential influence range, and generating a regulation and control demand report; generating an adjustment scheme draft, performing priority ranking on simulation tasks in the adjustment scheme draft by adopting a program process scheduling algorithm, dynamically allocating computing resources, executing the simulation tasks in parallel, and determining an optimization parameter set in combination with a gradient descent algorithm; and iteratively correcting the parameters in the digital twinborn body through feedback circulation to generate a final coordination control instruction, inputting the final coordination control instruction into the digital twinborn body, confirming synchronism and outputting a report. According to the invention, the precision of dynamic regulation and control of the production parameters of the plastic film is improved.