11results about How to "Realize dynamic deployment" patented technology

The embodiment of the invention provides a resource management method and system based on cloud edge collaboration. According to the method, firstly, an intelligent AI management platform can be constructed to better allocate computing, storage and network resources; and then resource requirements of the static resources and the dynamic resources can be accurately estimated by monitoring calling frequencies of data interfaces of the static resources and the dynamic resources, so that dynamic allocation of the computing resources is realized, enterprises can be helped to better manage and utilize the computing resources, the stability and reliability of the system are improved, the operation cost is reduced, and the economic benefit is increased. And greater value is created for enterprises. Meanwhile, intelligent scheduling of resources can be achieved based on load balancing, tasks can be automatically distributed to nodes with low loads according to the load conditions of all the nodes, and therefore load balancing is achieved, and the overall performance of the system is improved. Through the dynamic resource allocation process, the resource allocation is more reasonable.

The present invention discloses a deep-sea aquaculture monitoring method and system based on sonar images. The method acquires target area information to construct a three-dimensional visual monitoring model, monitors the marine environment and divides the aquaculture sub-areas. Sonar technology is used to detect fish schools, identify statistics and analyze the growth and distribution changes of fish schools. Based on the analysis results, a feeding and monitoring plan is formulated, and an equipment deployment plan is generated to realize dynamic deployment of monitoring equipment and improve the utilization rate of monitoring equipment, so as to optimize the automated management of deep-sea aquaculture and the allocation of monitoring equipment resources.

The application provides a method and system for checking the cross-modal information consistency of a maintenance plan based on a large model, and relates to the technical field of big data analysis. The method comprises the following steps: identifying a target maintenance plan through a power large model, determining key maintenance content, an unstructured proportion, and an attachment type complexity; obtaining a text data complexity and a business risk index based on key maintenance content analysis, as a first checking difficulty coefficient and a second checking difficulty coefficient; determining a third checking difficulty coefficient according to the unstructured proportion and the attachment type complexity evaluation; taking the expected review time limit of the target maintenance plan as a constraint, formulating an adaptive checking depth and an adaptive checking breadth based on the first checking difficulty coefficient, the second checking difficulty coefficient, and the third checking difficulty coefficient; and performing cross-modal information consistency checking on the target maintenance plan according to the adaptive checking depth and the adaptive checking breadth. The dynamic allocation of resources for checking the cross-modal information consistency of a maintenance plan is achieved.

The invention relates to the technical field of resource scheduling, and discloses a resource scheduling distribution management method and system, a medium and a processor, and the method comprises the steps: obtaining heterogeneous resource information of each node under a system computing power network; acquiring quotas of various heterogeneous resources applied by the configuration file of the Pod to be scheduled in the system; according to the heterogeneous resource information of each node and the quota of various heterogeneous resources applied by the to-be-scheduled Pod, calculating a node load score and a node resource balance degree score of the to-be-scheduled Pod scheduled to each node; obtaining a scheduling scoring result of each node according to the node load score and the node resource balance degree score; and according to the scheduling score result, selecting the node with the highest scheduling score in all the nodes to schedule the current Pod to be scheduled. According to the method, two factors of node load and node resource balance degree can be comprehensively considered, various heterogeneous resources under the computing power network are managed and scheduled, and the load of each node and dynamic allocation of the resources are balanced.

The invention provides a multi-unmanned aerial vehicle task allocation system based on a two-stage multi-population wolf pack algorithm, and the system comprises an initialization module which defines the position of an individual wolf in the two-stage multi-population wolf pack algorithm as a multi-unmanned aerial vehicle task allocation scheme, and divides a wolf pack into a plurality of sub-populations, including a common group and a leader group; the wandering module is used for re-ordering task numbers by adopting different wandering frequency calculation methods for the common group and the leader group for wolf detection; the calling module is used for learning the scheme of the current first wolf at different convergence speeds by the common group and the leader group; according to the purse module, except the head wolf, the individual wolves of the common group and the leader group adopt different threshold values to carry out variation or learn the scheme of the low-fitness individual wolves; the individual wolf reconstruction module is used for reconstructing by adopting a roulette mechanism; and the sub-population adjustment module is used for starting a multi-population mechanism after reconstruction is completed, and reforming a leader group. The wolf pack algorithm is improved through multiple mechanisms, and the solving efficiency and accuracy are improved.

The invention discloses a machine learning-based wing-shaped structure lightweight design method, which comprises the following steps of: (1) importing load and boundary constraint to obtain weight and rigidity indexes of a wing-shaped structure, and deducing a corresponding mathematical optimization model; (2) constructing an optimization population by considering a space filling characteristic; (3) evaluating a population feasibility state, and designing a sub-population evolution operation to generate candidate individuals; (4) constructing a global or local radial basis machine learning prediction model based on the update rate of the population; (5) designing two screening strategies according to the feasibility of parent individuals; and (6) evaluating the selected optimal candidate individual by adopting a wing-shaped structure rigidity and weight simulation model, updating the population and turning to the step (3) until the optimized structure meets the requirement. According to the information dynamic distribution evolutionary strategy fed back in the optimization process, the self-adaptive modeling prediction model and the reasonable selection screening strategy, the optimization efficiency for the wing-shaped structure lightweight design problem is improved.

The present invention relates to a virtual reality simulation method and system for an electric power substation, which belongs to the field of virtual reality simulation technology and solves the problem that existing simulation tasks and assessment items are solidified and cannot be flexibly updated. It includes: creating a simulation scene in a simulation project, obtaining multiple scene objects by importing a three-dimensional model of power equipment and simulation resources; dragging multiple task nodes in an extended process editor and connecting them through lines to obtain a simulation process; writing scene objects and simulation processes into a configuration file through an extended deployment window, and uploading the executable file generated by compiling the simulation project to a server to generate simulation task information; downloading simulation task information according to the selected simulation task, parsing the scene objects and simulation processes therein, generating a virtual scene by rendering the simulation scene and superimposing and displaying the task nodes in the simulation process; ending the simulation task when all task nodes have been executed. Flexible editing and updating of simulation tasks are achieved.

The application discloses an engineering safety risk perception method based on deep learning, which comprises the following steps: step one, collecting engineering safety data of a construction site; step two, performing data preprocessing to generate a standard multimodal sample set; step three, generating a risk perception tensor sequence through the improved FusionNet network from the standard multimodal sample set; step four, constructing an engineering risk perception vector sequence based on the risk perception tensor sequence; step five, inputting the engineering risk perception vector sequence and the risk perception tensor sequence into a risk reasoning model to generate a construction site risk perception result; step six, collecting safety event feedback information of the construction site, and updating the improved FusionNet network and the risk reasoning model; and step seven, redeploying the updated improved FusionNet network and the risk reasoning model. The application improves the perception ability of engineering safety risks through the improved FusionNet network.

The embodiment of the invention provides a vehicle defrosting method and electronic equipment, and the method comprises the steps: responding to a received defrosting instruction of a target structure in a vehicle, determining a target defrosting type corresponding to the defrosting instruction from a plurality of defrosting types, obtaining the layout information of a heating system in the vehicle and a heating demand value of the target structure, and on the basis of the heating system layout information, a first sub-heating area in the target structure and a first heating line corresponding to the first sub-heating area are determined, and on the basis of the target defrosting type, the first sub-heating area is heated by using a heating current value and a heating demand value corresponding to the first heating line, so that the target structure is defrosted. The technical problem that the defrosting efficiency of the vehicle is low in the related technology is solved.

The invention relates to the technical field of robot dynamic task allocation methods, in particular to a multi-agent track bolt operation robot dynamic task allocation method, which comprises the following steps of: acquiring coordinates of track bolts needing to be operated and the number of robots; environment features are extracted based on the obtained track bolt coordinates; performing task region division according to the extracted environment features; performing task allocation on the divided task areas by adopting a heuristic algorithm; the track bolt operation robot is controlled to execute the distributed tasks, the problem that a fixed task distribution scheme is difficult to deal with non-uniform task distribution is effectively solved by introducing an environment feature extraction and dynamic region division mechanism, the size and boundary of a task region can be adaptively adjusted according to the actual distribution condition of track bolts, and the task distribution efficiency is improved. And the task load in each area is ensured to be balanced, so that the resource utilization efficiency is improved, and the condition of uneven load of the robot is avoided.

The invention relates to the technical field of intelligent decision, and discloses a satellite network controller deployment method based on satellite communication, which comprises the following steps: generating an initial layout of a satellite network controller, calculating a layout coverage rate of the initial layout, and calculating a coverage balance degree of the initial layout; selecting a to-be-optimized layout from the standard layouts, calculating the transmission delay of the to-be-optimized layout, calculating the controller load of the to-be-optimized layout by using the flow data, and analyzing the packet loss condition of the to-be-optimized layout; constructing a state space of the satellite network controller, performing layout normalization on the standard layout, and constructing an action space of the satellite network controller by using the normalized layout; and analyzing a state transition reward of the satellite network controller, determining an initial state of the satellite network controller by using the state transition reward, obtaining a target layout corresponding to the initial state from the normalized layout, and determining a final layout of the satellite network controller from the target layout. According to the invention, dynamic deployment of the satellite network controller can be realized.