37results about How to "Reduce the number of labels" patented technology

The invention provides a multi-label anti-collision algorithm, which comprises the following steps: resetting, transmitting inquiry commands of labels by a reader writer; judging the inquiry commands received by a responder, inquiring, responding and judging the labels received and signed by the reader writer; carrying out data processing to the responder by the reader writer; setting a pd value to 1, and setting Q value to Q; transmitting inquiry variation commands by the reader writer and back transmitting the inquiry variation commands by the responder; inquiring, responding and judging the labels received and signed by the reader writer; and carrying out data processing to the responder by the reader writer. Therefore, the algorithm can circulate in a quick exclusive manner, has the higher practical recognition efficiency to the collision labels and can rapidly reduce the quantity of responders in the working range of the reader writer; moreover, on one hand, the recognition efficiency is improved through reducing the quantity of the responders at a high speed, on the other hand, the disturbance of the electromagnetic environment in the working range of the reader writer can be reduced so as to further improve the recognition quantity.

The invention provides a scheduling method to prevent conflicts in intelligent RFID read system. The method utilize the mechanism that reader controls multiple antennas, which is: all the antennas are controlled by the reader in order; the reader polls the antennas connected to the reader, and control the interactive between the single antenna and label; each time only one antenna can be activated to respond instructions from the reader; every two antenna effective covered regions are connected to reduce the overlap. The invention uses multiple antennas, at any time only one antenna takes effect, and then labels are divided into groups to recognize. The number of labels in the coverage covered by one antenna is reduced, thus the probability of conflicts is effectively reduced.

The invention relates to a digital circuit, and discloses a memory optimization type static time sequence analysis method and system. According to the method, on the premise that the subgraphs are notexpanded, in the traversing and scanning process, false paths are identified and discarded in real time, the influence of the false paths on downstream nodes is reduced, redundant calculation is reduced, meanwhile, multiple time sequence constraints on each node are dynamically and differentially processed in the traversing process, dichotomy coverage is correspondingly carried out, and the number of labels on each node is reduced. According to the application, occupation of system memory space can be greatly reduced, the system operation efficiency is improved, and the system performance isimproved.

The invention provides a VPN route label distribution method, ASBR, PE and a distribution system, the method comprising: receiving a VPN route update message; judging whether to assign a label for a new VPN route according to the VPN route update message; if necessary, assigning a new VPN route Label. Through the implementation of the present invention, after receiving the VPN route update message, it is first judged whether a label needs to be allocated for the new VPN route, and only when necessary, the label is allocated, which is different from the prior art after receiving the VPN route update message. Compared with assigning labels for VPN routes, the number of labels for VPN routes can be reduced, which relieves the pressure on ASBRs.

The present application discloses an active learning event extraction method based on memory loss prediction and delayed training. The scheme screens unlabeled samples by predicting their losses, and obtains high-quality unlabeled samples for labeling. Firstly, two memory modules are constructed, which are the learned memory module and the selected memory module. During the training process of the supervised learning model, the learned memory module stores the learned information to the learned memory module. In the process of sample selection , the selected memory module stores the information of the selected sample along with the selection of the sample, and predicts the loss of the new sample by combining the information of the two memory modules. After obtaining the sample loss, heuristically selects the valuable At the same time, a delayed training strategy is proposed to simulate the sample selection scene to supervise the sample loss model, and finally a high-quality event extraction model with low labeling cost is obtained.

Embodiments of the present application provide a model training method, device, and server based on active learning, which can automatically retrieve training samples for each application scenario indicated by the started training task, without the need for developers to manually export data for model training. After the initial deep learning network model pre-matched with each application scenario labels the training samples, the active learning service is dispatched to actively screen the labeled training samples, without the need for developers to participate in labeling, thereby effectively reducing the number of sample labels. After the active screening samples are calibrated according to the user's calibration instructions, the training service associated with each application scenario can be flexibly scheduled to perform model training based on the calibrated active screening samples and released to the corresponding software application for each application scenario. Furthermore, training services of different application scenarios can be flexibly connected, and automatic labeling, training and business updates of the training process can be realized.

The invention provides a data processing method and device, and a storage medium. The method includes: performing feature recognition processing on the data to be processed according to preset dimensions to obtain the dimensional features of the data to be processed; wherein, the preset dimensions include: behavior dimension, field dimension and purpose dimension; thus, according to the identification Label the data to be processed based on the obtained dimensional features. The technical scheme provided by the invention can reduce the labeling cost and improve the processing capacity.

The embodiment of the present application provides a message transmission method and device, the method includes: obtaining the first message, and determining the forwarding entry corresponding to the first message; the forwarding table includes the main path forwarding entry and the standby path Publication item, the outgoing interface included in the standby path forwarding table item is the tunnel identifier of the TE tunnel; if the main path corresponding to the main path forwarding table item fails, and the second node is not the destination node corresponding to the destination address included in the first message, Then obtain the section routing label pointing to the destination node on the second node and the tunnel label corresponding to the TE tunnel from the standby path forwarding table item; add the section routing label and the tunnel label in the first message to obtain the first Second message: sending the second message to the second node through the TE tunnel corresponding to the tunnel identifier, so that the second node uses the segment routing label to send the second message to the destination node. Through the technical solution of the embodiment of the present application, the message can be correctly forwarded through the standby path.

The invention provides a weakly supervised in-depth station logo detection method, the steps of which are: preprocessing massive network video data files to obtain a large data set that only marks the station logo category and a small data set that only marks the station logo position ; Input the above-mentioned small data set into the station logo positioning network for training, and obtain a station logo positioning network capable of predicting the station logo area; input the above-mentioned large data set into the above-mentioned trained station logo positioning network, and obtain each piece in the large data set Some predicted station logo regions of the picture, and several predicted station logo regions of each picture are input into the station logo classification network for training, and the station logo classification network that can be classified as the station logo is obtained; the video to be detected is carried out with the same part as above Preprocessing, and inputting the image obtained after preprocessing into the trained station logo positioning network to obtain the predicted station logo area of ​​the picture; inputting the predicted station logo area of ​​the above picture into the trained station logo classification network to obtain the image's predicted station logo area The location and category of the station logo.