10results about How to "Efficient selection" patented technology

The application discloses a driver fatigue behavior detection method and system based on video posture invariance, and relates to the technical field of computer vision. The application proposes a key frame selection model based on facial geometric information and a head and face action information fusion space-time network. First, the driver video captured by the vehicle-mounted camera is subjected to sequential processing, and image preprocessing is performed. Then, the key frame selection model based on facial geometric information is constructed based on the geometric features of the facial key points and a two-stage decision mechanism, and the key frames in the video sequence are extracted. Finally, the facial action modalities under any posture are extracted based on the facial forward processing, and the head posture attributes obtained based on the head posture estimation are combined to construct the head and face action information fusion space-time network, which is used for detecting the yawning, speaking, normal and other driver states. The application fully considers the head posture attributes, has high posture robustness, and can effectively distinguish the yawning and other fatigue behaviors from other driver states.

This invention provides an Indel molecular marker closely related to the soluble sugar content of pepper fruit and its application, belonging to the technical field of nucleic acid-based assay methods. The nucleotide sequence of the Indel molecular marker is shown in SEQ ID NO.1 of the sequence listing; the Indel molecular marker is located at positions 5274716-5274727 of the full-length sequence of chromosome 3 of the pepper reference genome. Primers for amplifying the Indel molecular marker include a forward primer and a reverse primer. The nucleotide sequence of the forward primer is shown in SEQ ID NO.2 of the sequence listing, and the nucleotide sequence of the reverse primer is shown in SEQ ID NO.3 of the sequence listing. This molecular marker can be directly applied in early generations of breeding, avoiding the destructive sampling of chemical detection, significantly reducing breeding costs, effectively shortening the breeding cycle, and greatly improving the selection efficiency of molecular marker-assisted breeding in peppers.

The invention discloses a low-earth-orbit satellite communication network routing method based on reinforcement learning, and relates to the field of low-earth-orbit satellite communication networks in 5G NTN, in particular to the low-earth-orbit satellite communication network routing method based on reinforcement learning. The objective of the invention is to solve the problem that existing reinforcement learning Q-Learning applications are mostly focused on a ground network, and the unique dynamic topology and three-dimensional space routing problems of a satellite network are not solved. The invention provides a lightweight and adaptive low earth orbit satellite communication network routing optimization method based on reinforcement learning. The method is realized through distributed Q-Learning: dynamically adapting to topological change, dynamically adapting to three-dimensional space routing, balancing link load, minimizing end-to-end delay, and reducing on-satellite computing overhead.

A method and apparatus in a communication node used for wireless communication are disclosed. The communication node receives first signaling indicating a configuration of a first cell; performs a first handover from a source cell to the first cell; determines that the first handover fails; performs a first operation in response to the act of determining that the first handover fails; the act of performing a first handover from a source cell to the first cell includes applying the configuration of the first cell; the first operation is one candidate operation in a first candidate operation set, the first candidate operation set includes at least two candidate operations of returning to the source cell and performing a second handover; the first operation is related to at least whether the first node is configured to conditionally reconfigure a candidate cell; when the first node is not configured to conditionally reconfigure a candidate cell, the first operation is to return to the source cell.

The utility model discloses a dynamic mixing tube type continuous flow reactor, and belongs to the technical field of chemical engineering reaction continuous flow. The reactor comprises a pipe body and a stirring device rotatably arranged in the pipe body, wherein the upper end and the lower end of the pipe body are respectively provided with at least one upper interface and at least one lower interface for introducing and discharging materials. The stirring device is composed of a stirring shaft on the central axis and fixedly connected blades, the blades extend in the radial direction and the axial direction of the stirring shaft and are provided with a plurality of overflowing holes arranged in an array mode in the length direction, and the length of the blades is smaller than the distance between an upper connector and a lower connector so that materials can be prevented from splashing out. A first paddle and a second paddle can be attached to the stirring shaft, and overflowing holes of the first paddle and the second paddle are divided into a first hole group and a second hole group respectively and are staggered in the length direction of the stirring shaft to enhance the mixing effect. A positioning seat is arranged at the bottom of the pipe body, and the stirring shaft is positioned through a bearing and is connected with a variable frequency motor through a coupler for speed regulation. The upper end and the lower end of the pipe body can be provided with two staggered connectors to improve operation flexibility. The reaction kettle realizes efficient mixing and uniform distribution, improves the reaction efficiency, and is suitable for the fields of chemical industry, materials, environment, pharmacy, food and the like.

The invention discloses a heat dissipation assembly type selection method and system based on three-dimensional simulation and PINN collaborative optimization. The problems that an existing radiator model selection method needs a large amount of calculation resources and time and is low in precision are solved. The method comprises the following steps: constructing a heat dissipation system three-dimensional model comprising a heat dissipation assembly, and simulating the three-dimensional model according to different working conditions of the heat dissipation assembly; acquiring working conditions and simulation output data to establish sample data; constructing a physical information neural network model, and training to obtain a heat dissipation performance prediction model; inputting the working condition data of the to-be-tested heat dissipation assembly into the heat dissipation performance prediction model to obtain heat dissipation performance prediction data; and the optimal heat dissipation assembly is selected by integrating the heat dissipation performance, the cost and the space limiting factors. According to the method, three-dimensional simulation and physical information neural network training are combined for application, and the radiator assembly meeting the heat dissipation requirement can be accurately and efficiently selected.

The embodiment of the application provides a method and device for determining a target EIR. The method is applied to an AMF and includes the following steps: determining, based on the state of deployment of multiple EIRs, whether the multiple EIRs are centrally deployed or globally deployed; if the multiple EIRs are centrally deployed, sending a first request message to an NRF to determine a target EIR that matches user equipment information carried in the first request message; the NRF locally stores user equipment information served by each EIR of the multiple EIRs; and if the multiple EIRs are globally deployed, determining a target EIR based on a link state monitoring table. The link state monitoring table includes the IP address, port number and service state of each EIR of the multiple EIRs. The method for determining a target EIR provided by the embodiment of the application can meet the needs of different deployment scenarios of EIRs, ensure the accuracy of EIR device selection, and ensure timely switching in the case of link failure.

This invention relates to the field of pharmaceutical preparation technology, specifically to a sulfachlorpyridazine sodium-methotrexate suspension, its preparation method, and its application. The sulfachlorpyridazine sodium-methotrexate suspension of this invention comprises the following components per 100 ml: 20-50 g of sulfachlorpyridazine sodium, 4-10 g of methotrexate, 0.1-0.25 g of suspending agent, 0.05-0.125 g of wetting agent, 0.2-0.5 g of antioxidant, 0.1-0.25 g of disodium edetate, and purified water to a final volume of 100 ml. The suspension prepared by this invention can delay the in vivo clearance of sulfachlorpyridazine sodium, prolong the synergistic effect time, and improve its bioavailability; in the treatment of coccidiosis infection in chickens and sheep, it can significantly improve weight gain, reduce intestinal lesion values, rapidly clear oocysts, and maintain a long-lasting protective effect after drug withdrawal.

The invention relates to the technical field of cell culture monitoring data management, and particularly discloses a cell culture monitoring data management system and method.Three-dimensional visual monitoring of the culture process is achieved by constructing an initial digital twinborn model and combining real-time monitoring data to generate a dynamic digital twinborn model; meanwhile, three-dimensional imaging data are further fused, a fused three-dimensional model containing a cell structure and biochemical parameters is generated, an optimization strategy is generated based on an intelligent decision algorithm, and management is improved from passive response to active prediction; the cell growth state is comprehensively and visually monitored, the monitoring depth is enhanced, through a virtual environment preview strategy, the actual adjustment risk is reduced, a closed loop feedback mechanism is established, cross-batch learning and self-optimization are supported, meanwhile, man-machine interaction is supported, the experience of an operator is fused into a decision, the adaptability and robustness are improved, and the method is suitable for popularization and application. Finally, the stability and the product quality of the culture process are improved.

The invention provides a detection path selection method and device, equipment, a medium and a program product, relates to the technical field of cyberspace surveying and mapping, solves the defect of poor concealment of a selected detection path during concealed surveying and mapping of a cyberspace, and realizes the purpose that the detection path can be effectively selected in a high-intensity banning or detection scene. And a hidden detection path is selected to complete hidden surveying and mapping of the network space. Comprising the steps that a BGP routing table, an AS relation data set and IXP connection data are acquired, and the BGP routing table comprises routing information of multiple nodes; performing feature analysis on the BGP routing table, the AS relational data set and the IXP connection data to obtain feature data; screening nodes of which the topological similarity index TSM is greater than an index threshold from the plurality of nodes to construct a topological similar node pool, wherein the nodes in the topological similar node pool are used for generating a plurality of detection paths from the source node to the destination node; and based on the feature data, selecting an optimal detection path from the plurality of detection paths to detect the destination node.