8 results about "Network sampling" patented technology

The present application belongs to the technical field of optimization method, and particularly relates to a combined optimization method and device, computer equipment and storage medium. The method comprises: constructing a combined optimization environment model; constructing a stage-aware double-network intelligent agent; using a proximal policy optimization algorithm to perform end-to-end joint training on the double-network intelligent agent, so that the design policy network and the control policy network evolve in a unified optimization framework; during the joint training process, for the magnetization configuration generated by the design policy network sampling, the control policy network performs multiple control evaluations and aggregation to serve as a performance evaluation signal of the magnetization configuration. The present application realizes deep collaborative optimization of magnetic robot form design and control optimization, not only enables the magnetization configuration parameters to be adjusted based on the magnetic field control signal feedback, but also enables the control policy network to adapt to the changes of the magnetization configuration in real time, thereby significantly improving the overall task performance and optimization efficiency of the magnetic robot.

The application discloses a kind of based on partial quantification's hybrid expert network optimization method, it is related to information technology field, including the following steps: S1, selected data sample set, carries out hybrid expert network sampling;S2, establishes the corresponding relationship of subnet and data set, selects high-frequency subnet and corresponding data set;S3, with corresponding data set to selected high-frequency subnet is iterated quantization processing.The application obtains the corresponding relationship of different data set and different subnet in hybrid expert network by carrying out data flow sampling to the reasoning process of hybrid expert network, then carries out quantization optimization to different subnet on corresponding data set, to reduce the calculation burden required for the overall optimization of hybrid expert network, to improve the service throughput of entire network.The data set corresponding to the subnet used frequently is used to carry out quantization processing on the subnet, i.e.to avoid quantization processing on the entire network, simple and efficient, improve the performance of entire network.

The invention relates to the field of block chains, and discloses a lightweight extensible BFT protocol method suitable for a sleep model, and the method comprises the following steps: S1, generating a temporary block sequence; in the step S1, the provisional block sequence comprises the following steps: S11, through a local lot drawing mechanism based on a verifiable random function VRF, selecting a proposal, and generating and broadcasting candidate blocks; s12, performing multiple rounds of communication with a random subset of the node to achieve a provisional consensus for the candidate blocks, and adding the candidate blocks achieving the provisional consensus into the provisional block sequence; and S2, executing a final determination protocol through a final determination committee, processing the temporary block sequence, and outputting a final determination block. By adopting a limited number of block proposals, a pre-consensus mechanism based on network sampling and a constant-scale final determination committee, the communication overhead under a thousand-node scale is reduced, and the method can be efficiently expanded to a larger-scale network.

The invention relates to the field of supply chain management, in particular to an intelligent goods source matching method, which comprises the following steps of: acquiring orders, warehousing, a transportation network and remote sensing data to construct a dynamic graph; establishing an incremental Vietories-Rips complex on the graph, calculating a differentiable coherent bar code, and generating a topological risk tensor; constructing a secondary unconstrained binary optimization model according to a risk tensor weighted graph state, obtaining candidate matching through quantum annealing, and outputting a matchmaking decision by combining generative flow network sampling and digital twin multi-subject inference; executing CKKS homomorphic encryption calculation on the matchmaking decision, generating a Groth16 zero-knowledge proof, and writing the Groth16 zero-knowledge proof into an alliance chain; and each node adopts safe multi-party calculation with a threshold of 5 to aggregate privacy gradient, updates an embedded model and generates flow network parameters to form a self-evolution closed loop. According to the method, cost, timeliness and privacy are considered, and the delay delivery rate is reduced under extreme road conditions.

The invention relates to a method, storage medium and device for semantic segmentation of airborne multispectral laser radar point cloud, which belongs to the technical field of airborne laser radar point cloud data processing. In order to solve the problem of poor point cloud segmentation caused by the uneven size and distribution of objects in the existing airborne multispectral point cloud. The present invention synthesizes a multispectral point cloud based on the airborne multispectral original point cloud, selects samples according to a uniform grid, and samples the density center spherical neighborhood of each object by a k-clustering method. The two sampling results are then spliced ​​to complete a comprehensive dense network sampling, and then separated according to the bands. The semantic segmentation network is used to perform semantic segmentation on the single-band point cloud band by band, and then a splicing matrix is ​​obtained and fused using a fusion network to obtain the final semantic segmentation result. The present invention also uses a joint training strategy for training to improve the overall fitting ability of the network, thereby improving the segmentation effect of the network.

The application provides a point cloud sampling method for perceptual reconstruction, comprising the following steps: S1, point cloud sampling network sampling: a residual block based on graph convolution is used for local feature extraction of the point cloud, and the sampled point cloud is obtained through mapping according to the point cloud features; S2, point cloud up-sampling network recovery perception: the sampled point cloud is up-sampled to obtain the point cloud data after perceptual reconstruction; S3, point cloud classification network identifies the up-sampled point cloud: the point cloud data after perceptual reconstruction is input into the point cloud classification network, and the training of the point cloud sampling network and the point cloud up-sampling network is supervised through the point cloud classification network. The method can obtain the sampled point cloud which is easier to recover perception.

This invention discloses an AUV hull docking method based on deep reinforcement learning, including: s1: real-time acquisition of the current state s t Using the current parameterized strategy network sampling action a t , will a t The probability density value is denoted as p(a t ); s2: will a t Substitute into the dynamic equation and calculate the state s at the next time step. t+1 and reward function r t s1: Form tuples and store them in the experience pool; s2: If the number of tuples in the experience pool meets the condition, go to s3; otherwise, go to s1; s3: Transfer the tuples in the experience pool to s4. t s t+1 The input is fed into the state-value network to obtain function values, and the advantage function is calculated. b is sampled from the experience pool. s Each tuple is used to perform gradient descent on the parameters of the state-value network using temporal difference error to achieve policy evaluation; s5: Sample b from the experience pool. s Each tuple is used to introduce a rollback mechanism to perform gradient descent on the parameters of the policy network, thereby improving the policy; s6: AUV ends when the termination condition is met, otherwise it goes to s1.

The invention discloses an automatic drainage pipe network sampling analysis device based on the Internet of Things, and relates to the technical field of sampling analysis, the automatic drainage pipe network sampling analysis device comprises a multi-dimensional moving mechanism, the multi-dimensional moving mechanism comprises a vertical depth adjusting assembly and a transverse depth adjusting assembly, the vertical depth adjusting assembly comprises a mounting part fixedly connected with the inner wall of a drainage pipe network, and the transverse depth adjusting assembly comprises a transverse depth adjusting assembly; and the top of the mounting part is fixedly connected with a first motor. Through the arrangement of the multi-dimensional moving mechanism, the vertical depth adjusting assembly drives a first screw rod through a first motor to drive a second mounting frame to slide along a first mounting frame, and different vertical depths are accurately adapted; a first adjusting assembly and a second adjusting assembly of the transverse depth adjusting assembly cooperate, a second motor drives a second screw to drive a sliding block to move, the transverse position is synchronously adjusted, the limitation of traditional single-dimensional movement is broken through, a key area on the inner side of a pipe network can be covered, and a sampling blind area is avoided.