3 results about "Packet sampling" patented technology

The invention relates to a priority-based high-visibility stream-by-stream data packet sampling method and system. Comprising the following steps: step 1, flow initiation and priority marking; step 2, flow establishment and controller decision making; step 3, rule issuing and strategy execution; and step 4, data forwarding, scheduling and sampling: a priority scheduling mechanism of a data plane and global optimization of a control plane are decoupled and coordinated. In a data plane, a terminal host marks a degradation priority for a data packet according to the number of bytes sent by a stream, and a switch performs strict queue scheduling and probability sampling based on the priority. In a control plane, a controller carries out collaborative modeling on the configuration of routing, sampling probability and degradation threshold as a nonlinear optimization problem with maximization of sampling utility as a target, and an efficient online primitive-dual interior point method is adopted for solving. According to the method, high visibility and load balancing are finally ensured, and meanwhile, the control and calculation overhead is remarkably reduced.

The invention provides a micro-expression recognition method and system based on balanced adaptive grouping sampling, and relates to the technical field of micro-expression recognition, and the method comprises the steps: obtaining a data set; the similarity among a plurality of samples of the same student is calculated based on multi-scale structural similarity measurement, so that the identification difficulty of the samples is judged. According to the method, the structural similarity between the samples is calculated through multi-scale structural similarity measurement, so that the recognition difficulty of the samples is judged, grouping sampling is performed according to the recognition difficulty, and a micro-expression recognition model is trained based on a data set obtained through sampling. And meanwhile, the identification difficulty is adjusted according to a model output result, and sampling is performed again. Thus, re-sampling and model training are periodically performed, and the sampling weight of the sample is continuously updated according to the information fed back during model training, so that continuous reinforcement and feature optimization of the specific sample can be realized during training of the model, and the stability and generalization performance of the model are improved.

Techniques for sampling and capturing central processing unit (CPU)-bound packets in a network device are provided. In one set of embodiments, the network device can receive a command to enable packet sampling for a class of network traffic, where the command specifies one or more sampling parameters. The network device can identify at least one CPU queue in a plurality of CPU queues of the network device to which the class of network traffic is mapped. The network device can then configure a driver of an operating system (OS) of the network device to begin sampling packets from said at least one CPU queue in accordance with the one or more sampling parameters.