436 results about "Collaborative computing" patented technology

The invention discloses an adaptive task division and decision joint optimization-based cloud edge computing resource collaborative scheduling method for a complex manufacturing system. The method comprises the following steps of 1, constructing a hierarchical cloud-edge collaborative computing network model; constructing a multi-objective optimization model, and defining an objective function and constraint conditions; 2, dynamically predicting and calculating a resource state through a resource sensing module based on an LSTM neural network, and generating a node resource prediction matrix; 3, dividing a calculation task generated by the manufacturing system into fine-granularity, medium-granularity and coarse-granularity subtask sets by adopting a multi-granularity subtask division algorithm (MSPA), and mapping the subtasks to corresponding calculation nodes; 4, constructing a task unloading decision model based on the D3QN, and dynamically selecting unloading nodes and an execution sequence of the subtasks in combination with a multi-objective optimization reward function; and 5, iteratively optimizing parameters of the D3QN model through a target network updating mechanism and a self-adaptive exploration strategy to realize real-time dynamic adjustment of a task scheduling decision.

The present application relates to the field of information collaborative processing. Provided are a task collaborative scheduling method and apparatus, a device and a medium. The task collaborative scheduling method is applied to a collaborative computing system comprising a plurality of nodes, and the method comprises: first, on the basis of original task description information of a target task, performing splitting and orchestration on the target task to obtain a plurality of sub-tasks and a task logic topological relationship between the sub-tasks; then allocating, on the basis of node information of the nodes, from the collaborative computing system a corresponding execution node for each sub-task, and generating sub-task description information; and finally, issuing the sub-task description information to the execution nodes, such that all the execution nodes can complete all the sub-tasks according to the orchestrated logic topological relationship, thereby obtaining an output result of the target task. The present application can cover diversified task collaborative scheduling scenarios and enables compatibility with access and scheduling of devices having different capabilities, thereby meeting the collaborative processing requirements for diverse service types and scales.

The invention relates to the technical field of slope protection, in particular to a slope protection intelligent detection system based on deep learning. According to the technical scheme, the system comprises a multi-source heterogeneous data sensing module, a data fusion and feature extraction module, a slope state intelligent diagnosis and early warning module, an edge-cloud collaborative computing architecture and a system optimization module. Registration and feature complementation of multi-source heterogeneous data are realized through a multi-modal detection network, an overfitting phenomenon is effectively inhibited through a physical information neural network architecture, risk quantitative evaluation is realized through construction of a dynamic risk evaluation model, early warning response time is shortened in cooperation with a four-level early warning strategy, the false alarm rate is reduced, and the early warning efficiency is improved. Besides, the detection precision of the system in an extreme scene is improved through a physical constraint adversarial training method, so that the environmental adaptability of the system is improved, continuous updating and evolution of the model are realized through an online incremental learning module, and the problem of performance degradation of a traditional system caused by change of geological conditions is solved.

The invention discloses a data annotation method and system of a collaborative computing architecture based on quantum computing, and belongs to the field of data annotation. The method comprises the steps that S1, multi-modal data are input and preprocessed; s2, extracting features of each mode after preprocessing; s3, coding the features of each mode into a quantum state, and carrying out mode fusion; s4, performing label reasoning on the quantum state after modal fusion, and performing label constraint optimization by using a quantum approximate optimization algorithm; s5, based on a quantum Bayesian network or an approximate causal graph generation method, generating explanation according to a modal contribution causal path, and deducing marginal contribution of each modal to final label prediction by using a joint probability measurement result; and S6, outputting a labeling result. According to the method, a quantum-classical cooperative computing architecture is designed, the efficiency and accuracy of multi-modal data labeling are remarkably improved, the interpretability, the distributed processing capacity and the high-dimensional feature modeling capacity of the system are enhanced, and a brand new solution thought is provided for development of the multi-modal labeling technology.

The invention relates to the related technical field of distributed computing power resources, and discloses a distributed computing power resource dynamic fusion and cooperative computing system which comprises a resource sensing module, a task analysis module, a dynamic scheduling module, a virtualization adaptation layer, a cooperative computing engine, a global controller and a hierarchical communication bus. The resource sensing module collects and quantifies the hardware computing power of the heterogeneous computing nodes in real time. According to the invention, a complete closed-loop control system is formed through a five-layer dynamic fusion architecture (a sensing layer, an analysis layer, a scheduling layer, a virtualization layer and a collaboration layer), so that a distributed computing system can adapt to a scene that edge nodes are dynamically added and pushed out; meanwhile, through the purpose of developing virtualization middleware supporting cross-platform instruction real-time conversion and based on a multi-target dynamic weight adjustment mechanism of online learning, the heterogeneous task scheduling success rate can be greatly improved through the overall structure of the system, and the fault recovery time is shortened.

The invention discloses a distribution network low-voltage equipment state intelligent analysis method and system based on edge computing, and relates to the technical field of distribution network equipment state detection.The method comprises the steps that mesh network topology between edge computing nodes is constructed, and task allocation weights between the nodes are set; constructing a fault knowledge graph based on the multi-dimensional state features of the edge computing nodes; collaborative calculation is carried out based on the edge calculation nodes, calculation results of the edge calculation nodes are fused based on a weighted voting mechanism of a consistency algorithm, and a state evaluation result is obtained. According to the method, the multi-dimensional state features and the edge computing technology are combined, and intelligent analysis of the distribution network low-voltage equipment state is achieved. A mesh network topology is constructed based on electrical characteristics and environment characteristics, and efficient allocation of computing resources is realized through comprehensive evaluation of load complementation characteristics and state evaluation. The accuracy of fault propagation path identification is improved through double constraints of a feature association propagation chain and an equipment physical connection relationship.

The invention discloses a hotspot acquisition equipment adaptive control system based on multi-modal data fusion, and relates to the technical field of intelligent sensing and adaptive control, the hotspot acquisition equipment adaptive control system comprises a heterogeneous sensor array and a space-time alignment engine, each sensor clock is synchronized through an event trigger mechanism, and asynchronous data is processed by adopting B-spline interpolation; the feature pyramid fusion network extracts multi-scale features, and key information is enhanced through a channel and a space attention mechanism; the self-adaptive hot spot tracking module predicts a trajectory by adopting volume Kalman filtering; the dynamic resource allocation module is used for optimizing equipment scheduling according to a hotspot priority evaluation result; the multi-agent cooperative control layer is used for realizing autonomous negotiation among equipment through reinforcement learning; according to the edge-cloud cooperative computing architecture, computing resources are dynamically allocated according to task complexity. According to the method, the omission ratio is reduced through multi-modal data fusion, space-time alignment, temperature measurement errors and a self-adaptive resource allocation mechanism, and the reliability and practicability of the system are remarkably improved.

The invention discloses a dynamic scheduling method and system for a satellite-ground cooperative computing task, and the method comprises the following steps: constructing a satellite-ground cooperative computing system comprising a remote sensing satellite cluster, a satellite server node, a ground server / data center and the like, and enabling the satellite cluster to generate an in-orbit task and to describe dependence through DAG; available computing power, task queues and other resource states of a satellite and a ground server are collected in real time, and global observation is formed; on the basis of an MADRL framework, each node is regarded as an independent agent, a task allocation action is generated through a strategy network, and a collaborative decision is modeled through POMDP; optimizing the task execution sequence of the same node by using an EFT algorithm; issuing a task and monitoring execution; task completion time and energy consumption are collected, and a network optimization strategy is updated through a reward function and experience playback; the scheduling strategy is adjusted through loop iteration, satellite offline and link fluctuation are adapted, and the resource utilization rate and the task processing efficiency are improved.

The invention relates to an aviation equipment manufacturing digital main line engine system supporting multi-source heterogeneous data access, and belongs to the technical field of aviation manufacturing data management. The system comprises a multi-source heterogeneous data access adaptation module, a data fusion processing module and a full-process data link construction module. The multi-source heterogeneous data access adaptation module passes through a data interface protocol and format conversion component; the data standardization and fusion processing module completes association fusion through an aviation heterogeneous data collaborative computing framework by means of an aviation manufacturing field data element standard library, a unified heterogeneous data model is generated, and the framework comprises a data fragmentation layer, a parallel node layer and a result aggregation layer; and the full-process data link construction module constructs a data link covering the full life cycle of the product based on a time sequence association algorithm and a product unique identifier mapping mechanism. The system can effectively solve the integration and management problems of multi-source heterogeneous data in aviation equipment manufacturing, and improves the data processing efficiency and the whole-process data tracing capability.

The invention discloses a self-adaptive battery life calibration method for cloud-side cooperation, and belongs to the crossing field of an energy storage system and cloud-side cooperation calculation. According to the invention, a cloud-edge double-layer collaborative framework is provided; an edge end estimates the health state and the residual life of a battery in real time through a recursive least square extended Kalman filtering model; the error observer calculates a prediction error based on a sliding window, and a dynamic threshold triggers an uploading mechanism; the edge end adopts an auto-encoder to compress original time sequence features into abstract vectors, and the abstract vectors and error statistics are uploaded together; the cloud performs incremental learning by using a deep sequential network, and only finely adjusts tail level parameters of which the gradient sensitivity exceeds a threshold value to generate a correction value; and the correction value is compressed and issued to an edge end, local model parameters are updated through weighted fusion, and a covariance matrix is adjusted. The method realizes high-precision life prediction and dynamic calibration, remarkably reduces the communication load, and is suitable for electric vehicles, power grid energy storage and other scenes.

The invention discloses a self-adaptive 4D Gaussian splashing high-precision three-dimensional reconstruction system and method, and belongs to the technical field of computer graphic processing. The invention aims to realize high-precision automatic registration of multi-source heterogeneous data and improve the calculation efficiency. The method comprises the following steps: collecting multi-source heterogeneous data; constructing a multi-modal fusion registration method, which comprises the following steps: combining satellite image data and low-altitude oblique photography data to realize spatial distribution geometric coarse registration, fusing low-altitude laser radar point cloud data and ground acquisition vehicle laser radar point cloud data to realize luminosity fine registration, establishing semantic features to assist registration, and obtaining registered multi-source data; initializing a 4D Gaussian primitive and executing adaptive splashing reconstruction to obtain an optimized 4D Gaussian splashing model; designing a cloud edge cooperative computing architecture oriented to 4D Gaussian splash reconstruction, and performing distributed parallel processing on the obtained optimized 4D Gaussian splash model; and executing quality evaluation and adaptive optimization, and outputting a final adaptive 4D Gaussian splash model.

The invention relates to the field of smart city management and information security, and provides a federated learning CIM system information security protection method based on a block chain and a TEE, and the method achieves the security sharing and cooperative computing of multi-party data through combining the data tamper resistance of the block chain technology and the security computing capability of the TEE, and improves the security of the multi-party data. And the data privacy and the security of the model training process are ensured. According to the core technical scheme, the method comprises the steps of deploying an intelligent contract in a block chain network, and managing data access permission; local model training and security aggregation are carried out in a trusted execution environment, and global model parameters are protected through a differential privacy technology. The method can be used for traffic management, environment monitoring, energy optimization and other scenes in a smart city, and provides efficient, safe and intelligent decision support for a city management system.

The invention belongs to the field of edge computing acceleration, and relates to a fast Fourier transform and neural network reasoning collaborative computing acceleration method, which comprises the following steps of: deploying a computing method which is based on butterfly computing merging and a tensor mapping strategy and is mixed with DFT (Discrete Fourier Transform) and FFT (Fast Fourier Transform) in an operator deployment level; on the interface integration level, a bus interface of a register access path in a tensor accelerator control path is subjected to lightweight reconstruction, so that the bus interface is adaptive to an edge computing platform; in an operation level, a user-defined instruction is introduced into a tensor calculation unit, and an accelerator is enabled to independently complete a whole-process task of FFT signal processing and NN intelligent identification. According to the method, an operation instruction set is expanded on hardware, and delay overhead caused by returning a large amount of intermediate data to a processor is avoided, so that efficient execution of FFT and neural network tasks on unified hardware is guaranteed, and multiple requirements of high real-time performance, high precision and low power consumption are met.

The invention discloses a battery health management system and method, and belongs to the technical field of battery management, the system comprises an implantable sensor network, an edge and cloud collaborative computing platform, a multi-modal prediction model and a dynamic optimization execution unit; the implantable sensor network integrates various sensors to collect multi-physical field parameters in a battery, and the energy collection unit supplies power through cross-shielding communication transmission. The edge and cloud collaboration platform processes data, trains a model and carries out block chain evidence storage; the multi-modal prediction model is fused with space-time double-flow Transform and causal reasoning, SOH and RUL are predicted, and thermal runaway is early warned; the dynamic optimization execution unit realizes efficient control through layered equalization and self-adaptive thermal management; the method comprises an initialization stage, an operation stage and a maintenance stage to form a closed loop. The method breaks through the traditional limitation, improves the safety, reliability and economy of the battery, and is suitable for electric vehicles, energy storage power stations and other scenes.

The invention discloses a forest degradation monitoring and evaluation method and system based on machine vision, and relates to the technical field of information. Comprising a multi-source data acquisition module, a multi-dimensional dynamic degradation index calculation module, an environment situation perception module, a monitoring strategy self-evolution engine module, a sensor mode switching module, an edge-cloud collaborative calculation module and a visual decision terminal module. The system has the advantages that the problem of poor assessment capability in the prior art is solved by integrating a plurality of functional modules such as the multi-source data acquisition module and the multi-dimensional dynamic degradation index calculation module, the multi-source data acquisition module acquires data in multiple aspects such as vegetation, soil, climate and human activities in real time, rich information is provided for comprehensive assessment, and the assessment efficiency is improved. And the multi-dimensional dynamic degradation index calculation module integrates the data, so that accurate evaluation and differentiated treatment are realized, and the comprehensiveness and accuracy of forest degradation evaluation are greatly improved.

Techniques for identifying faults in a collaborative computing system including a plurality of disparate, geographically separated computing systems are described herein. An intelligent monitoring (IM) server computing system may receive data from the plurality of computing devices and may monitor the health of the collaborative computing system. The IM server computing system may analyze the data and identify one or more faults associated with a portion of the collaborative system (e.g., an associated computing device, platform, network, etc.). In some examples, the IM server computing system may be configured to identify potential future faults associated with the portion of the collaborative system. Based on the fault, the IM server computing device may determine an action to take to remedy the fault and / or prevent the potential future fault. The IM server computing device may either automatically perform the action or send a notification to the associated computing system to perform the action.

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 relates to the technical field of data processing, in particular to a data processing system and method based on cloud edge collaboration, and the system comprises an edge calculation module, an area monitoring module and a cloud calculation module. Wherein the edge computing module comprises a plurality of edge computing nodes and is used for carrying out data processing on corresponding edge side original data, sending a data processing result to the cloud computing module and determining a computing power representation state of the edge computing nodes; the region monitoring module comprises a plurality of region collaboration nodes and is used for acquiring computing power representation states of the connected edge computing nodes so as to determine a computing power collaboration strategy; and the cloud computing module is used for acquiring the data processing result and the data co-processing request of each edge computing node, and responding to the data co-processing request. According to the method, the problem of tension of cloud computing power is avoided through cooperative computing between the edge sides.

The invention provides a data driving and multi-element cloud edge cooperative computing method for intelligent workshop construction, which comprises the functions of multi-protocol heterogeneous equipment sensing, edge node adaptive load balancing, lightweight real-time edge computing processing, cloud centralized management control, industrial intelligent application service deployment scheduling, cloud edge task unloading and the like. The system comprises a data acquisition and transmission middleware, an edge stream processing engine and a cloud service center. The method has the characteristics of real-time performance, low delay, flexibility, expandability, loose coupling, low resource occupancy, high availability and privacy security.

The invention discloses an Internet of Vehicles vehicle information interaction system based on a YTS engine, and relates to the technical field of vehicle information interaction, a data acquisition module fuses multi-source sensing data, and an AI computing power optimization module adopts a dynamic computing power scheduling strategy; the 3D modeling and physical simulation module ensures the real-time performance of modeling based on an AI-driven 3D environment reconstruction and physical simulation technology; the cloud cooperative computing module processes multi-vehicle data in a distributed manner by using a cloud computing architecture of a YTS engine, optimizes a local model and improves the accuracy of an automatic driving decision; and the intelligent interaction module adaptively adjusts a modal man-machine interaction mode according to the dynamic change of the automatic driving decision, so that the driving experience is improved. The technical bottlenecks of information interaction delay, insufficient 3D modeling precision, poor decision stability and the like of the existing vehicle networking system in a high-speed dynamic environment are broken through; efficient energy consumption management, intelligent cloud optimization and accurate interaction are realized, and the safety and reliability of automatic driving are improved.

The invention relates to the technical field of monitoring, and discloses a multi-modal video public opinion intelligent monitoring method and system, and the system comprises a multi-modal data collection module, a data processing module, a coefficient generation module, an intelligent analysis module, a dynamic threshold module, and a public opinion visual platform. According to the method, a visual, voice and character cross-modal cooperative computing framework is established, and the one-sidedness problem of traditional single-modal analysis is solved; a recognition-tendency-propagation three-dimensional index system is constructed, and accurate quantitative evaluation of public opinion evolution is achieved; designing a static comprehensive coefficient threshold value and a dynamic growth threshold value of the dual-threshold grading system, and cooperating with an imaginary main body filtering algorithm and KOL polarization value calculation, so that the false alarm rate is remarkably reduced, and meanwhile, rapid early warning response is realized; a three-dimensional propagation map is generated through propagation path concentration analysis, content feature evolution tracking and influence radiation, and a complete public opinion evolution chain and hotspot traceability are provided.

The invention relates to the technical field of smart home and mobile terminals, and discloses a smart home anti-theft system based on a smart mobile terminal, which comprises a dynamic behavior learning module, a multi-modal sensor collaborative network, a dual-channel verification unit and a cross-platform emergency linkage engine. According to the smart home anti-theft system based on the smart mobile terminal, a false alarm scene is effectively eliminated and the false alarm rate is reduced through a multi-modal sensor collaborative network and a dual-channel verification unit, and a personalized security policy is dynamically generated by adopting a mixed learning algorithm and an edge-cloud collaborative computing architecture, so that the privacy data of a user is protected; through the cross-platform emergency linkage engine, hierarchical alarm and multi-dimensional response are supported, the intrusion event processing efficiency is improved, it is ensured that an evidence chain cannot be tampered, judicial evidence obtaining standards are met, and the problem that evidence of a traditional system is prone to being lost or tampered is solved.

The invention discloses a cpu + gpu-based tensor parallel computing algorithm for a large model, which comprises the following steps of: S1, combining row parallelism and column parallelism for a linear layer in the model by adopting a mixed-dimension tensor segmentation mode, and dynamically adjusting a segmentation proportion according to a model structure and hardware resources; s2, a CPU and GPU cooperative computing mechanism is constructed, part of tasks which have large video memory requirements and are relatively simple in computation are allocated to the CPU, the GPU is responsible for computing intensive tasks, communication between CPU-GPU is optimized, and overlapping of CPU-GPU communication and GPU computation is achieved; and S3, implementing a dynamic resource allocation and load balancing strategy, monitoring load conditions of the CPU and the GPU in real time, dynamically adjusting task allocation according to calculation requirements of different layers of the model and use conditions of hardware resources, and adopting a self-adaptive batch processing size adjustment strategy. The invention obviously reduces the occupation of the video memory, reduces the communication cost and improves the utilization rate of computing resources.

The invention discloses an intelligent video monitoring system and method supporting AI strategy cloud side end cooperative execution. According to the system, unified management of computing power resources and dynamic deployment of an AI algorithm are realized based on an extended standardized protocol through a three-level architecture of a cloud side center platform, an edge computing node and an end side camera. The method comprises the following steps: a cloud platform acquires computing power information of edge equipment; an AI algorithm execution strategy is generated and issued according to service requirements; if the required algorithm is not deployed in the equipment, the equipment is controlled to download and automatically deploy an algorithm module; and finally, the driving equipment executes AI analysis and recovers the structured data. According to the invention, AI computing tasks are reasonably distributed through a cloud side-end cooperative computing architecture, so that the computing power construction cost of a central platform is effectively reduced; through algorithm and hardware decoupling and a standardized protocol interface, ecological binding is broken, on-demand loading and flexible scheduling of the algorithm are realized, and the economical efficiency, the flexibility and the intelligent level of the system in large-scale scenes such as smart cities and the like are remarkably improved.

The invention discloses an SM2 collaborative signature and encryption and decryption system and method fusing anti-quantum characteristics, and relates to the field of cryptography and information security. According to the method, an anti-quantum cryptographic algorithm and a national cryptographic SM2 cooperative computing framework are deeply integrated, and a key security system is constructed: SM2 sub-private keys, anti-quantum key pairs and public keys are acquired and generated through an anti-quantum algorithm software and hardware enhancement module, and the private keys are encrypted and stored and are regularly alternated; on the basis of anti-quantum collaborative signature, encryption and decryption modules, an anti-quantum verification mechanism is embedded, and data is transmitted in combination with a national secret TLCP protocol, so that signature, encryption and decryption operations are completed; the equipment integration and dynamic security control unit monitors a security state, calculates a threat index to generate a protection strategy, and dynamically switches a security mode, so that the problems of insufficient security, vulnerability to attacks and data tampering of a traditional SM2 algorithm under the threat of quantum computing are effectively solved; and the long-term anti-attack capability and the operation reliability of the equipment in a high-security demand scene are remarkably improved.

The invention discloses an intelligent transport capacity dispatching system and method based on a GPS. The system comprises a transport capacity state monitoring subsystem and an intelligent dispatching management subsystem. And by deploying a GPS positioning and multi-parameter sensor, real-time acquisition and analysis of information such as the position, the speed and the energy consumption of the transport capacity unit are realized. According to the system, CNN and Transform structure extraction features are fused, LSTM is combined to predict a transport capacity demand, and a PPO reinforcement learning algorithm is adopted to dynamically plan a path. Abnormality detection (SVM), PID feedback adjustment and cloud edge cooperative calculation are integrated in the scheduling process, and the scheduling precision and the response speed are improved. The system has the capabilities of task filing, online optimization and data security guarantee, and is suitable for complex traffic and logistics scheduling scenes.

The invention discloses a smart building energy management system based on deep learning, which comprises a multi-modal data acquisition layer, an edge computing node, a cloud deep learning engine and a dynamic execution layer, dynamically fuses environment, equipment and personnel data through an attention mechanism, and realizes high-precision energy consumption prediction by adopting a Transform model. And an optimization control strategy is generated based on reinforcement learning and a genetic algorithm. The invention relates to the technical field of smart buildings and energy management. According to the intelligent building energy management system based on deep learning, a dynamic weight distribution formula is provided to realize multi-modal data adaptive fusion; an edge-cloud cooperative computing architecture is constructed, and the prediction precision is improved while the real-time performance is guaranteed; and a digital twin verification mechanism is introduced to ensure the security of the control strategy. The system is suitable for various commercial buildings, industrial parks and other scenes, has the characteristics of flexible deployment and strong expansibility, and provides an intelligent solution for building energy management.

The invention discloses a cloud side-end collaborative architecture and task unloading method for an airport apron intelligent monitoring system, and relates to the technical field of cloud side-end collaborative computing. Comprising a terminal layer, an edge server layer and a cloud server layer, the task unloading method of the system under the cloud side-end collaborative architecture is designed and comprises the steps that a task model, a time delay model, an energy consumption model and an accuracy rate model of the system are constructed, and a multi-objective optimization problem of time delay-energy consumption-accuracy rate is formed; modeling an optimization problem into a Markov decision process, and designing a state space, an action space and a reward function required by deep reinforcement learning; and designing a task unloading method based on multi-agent deep reinforcement learning, and finding an optimal task unloading strategy of the system. According to the method, the computing tasks can be dynamically, scientifically and reasonably distributed and cooperatively scheduled among the terminal, the edge and the cloud, so that the time delay, the energy consumption and the accuracy are comprehensively optimized, and the overall performance of the system is improved.

The invention provides a key frame extraction method for a multi-modal large model. The multi-modal large model video data processing efficiency and generation quality are improved through cooperative computing of a user side and a cloud side. According to the technical scheme, the method comprises the following steps: 1) after a client application submits data, an interface service performs primary processing on the data, and video frames and audio frames are divided and merged into data pieces according to a time sequence; 2) dynamically extracting n key video frames in each data piece of the user side, and compressing, packaging and transmitting the n key video frames and corresponding audio frames to the cloud side; 3) the cloud performs coding fusion on the multi-modal data and then inputs a large model generation result; and 4) the cloud evaluates the generation quality, and the user side adaptively adjusts data preprocessing and key frame extraction parameter configuration according to the generation quality and the response time delay. By reducing redundant data transmission and dynamically optimizing calculation and transmission resources, the response speed and the output quality of the multi-mode large-model cloud service are remarkably improved.

The embodiment of the present invention discloses a method, device, equipment, medium and program product for edge collaborative computing power allocation. It includes: obtaining the business logistics information of each terminal node in the current business cycle; inputting the business logistics information of each terminal node into the pre-trained business classification prediction model to determine the real-time terminal node and the real-time computing power prediction value; determining the real-time computing power demand according to the real-time terminal node and the real-time computing power prediction value, and dividing the total computing power resources into the real-time business container area and the non-real-time business container area according to the real-time computing power demand; determining the non-real-time access node for each time slot corresponding to the next business cycle according to the non-real-time computing power resources of the non-real-time business container area and the node weight of each non-real-time terminal node, and allocating non-real-time computing power resources to each non-real-time access node in the non-real-time business container area. This enables the computing power resources of the edge node to be fully utilized, distributed services to be flexibly deployed, and improves the processing capability of the power Internet of Things network for services.