45results about How to "Increase hierarchy" patented technology

The invention discloses an accurate soil sampling device, and relates to the technical field of environmental detection. The accurate soil sampling device comprises a mounting plate, wherein the surface of the mounting plate is provided with a mounting hole; the mounting hole is internally and rotationally connected with a shaft sleeve; the shaft sleeve is internally, slidably and cooperatively provided with a sampling cylinder; the upper surface of the mounting plate is connected with a fixing plate through a plurality of connecting rods; the fixing plate is rotationally connected with a screw rod; the upper end face of the sampling cylinder is fixedly connected with an end cover; the center of the end cover is rotationally connected with a screw rod nut cooperating with the screw rod; the circumferential side face of the screw rod nut is fixedly connected with a limiting rod through an ear plate; the limiting rod penetrates through the fixing plate; the lower end of the screw rod isrotationally connected with a pressing plate. The accurate soil sampling device has the advantages that by arranging the sampling cylinder, a motor is utilized to drive the sampling cylinder to rotate, the screw rod is utilized to drive the sampling cylinder to move up and down, and the problems are solved that existing manual sampling is large in labor intensity and low in efficiency; by arranging the limiting rod, the control over the sampling depth of the sampling cylinder is achieved, and the problems that the existing sampling depth is not accurate, which affects the detection accuracy.

The present invention provides for Ni-based lithium transition metal oxide cathode active materials used in lithium ion secondary batteries. The cathode active materials are substantially free of Li2CO3 impurity and soluble bases.

The invention discloses a personalized recommendation method based on deep learning. The method comprises the steps of according to the viewing time sequence behavior sequence of the user, predictingthe next movie that the user will watch, including three stages of preprocessing the historical behavior characteristic data of the user watching the movie, modeling a personalized recommendation model, and performing model training and testing by using the user time sequence behavior characteristic sequence; at the historical behavior characteristic data preprocessing stage when the user watchesthe movie, using the implicit feedback of interaction between the user and the movie to sort the interaction data of each user and the movie according to the timestamp, and obtaining a corresponding movie watching time sequence; and then encoding and representing the movie data,wherein the personalized recommendation model modeling comprises the embedded layer design, the one-dimensional convolutional network layer design, a self-attention mechanism, a classification output layer and the loss function design. According to the method, the one-dimensional convolutional neural network technologyand the self-attention mechanism are combined, so that the training efficiency is higher, and the number of parameters is relatively small.

A method and a system for distributing a mobile broadcast service are provided. The method includes: adding header information into broadcast service contents, the header information comprising integrality information and version information of a service packet containing the broadcast service contents; distributing the service packet to a user terminal; updating or accepting, by the user terminal, its own service data by use of the service packet in accordance with the integrality information and version information of the service packet. The method and the system according to the embodiments in the present invention may bring about higher transmission efficiency of data packet.

The present invention relates to a personalized text recommendation method based on deep learning, comprising the following steps: S1: preprocessing historical behavior data and text data of users browsing news; S2: feature extractor modeling, specifically including: S21: hidden layer design ; S22: Output layer design; S3: Personalized recommendation model modeling, including: S31: One-dimensional convolutional network layer design; S32: Classification output layer and loss function design. The present invention effectively solves the problem of operation data sparsity, and enhances the efficiency of model training by using negative sampling technology; introduces browsing time as a global variable, and optimizes the coding effect through the final purpose; by using the coding method of item embedding, and then Effectively solve the problem of cold start of the project; reduce the deep structure, increase the parallel hierarchy, weight sharing in the convolutional layer, and relatively few parameters.