33results about How to "Both effects" patented technology

The present invention relates to an e-reader audience fatigue analysis platform that avoids damage to the eyes of parturients. The e-reader audience fatigue analysis platform includes: a facial image capture device embedded in the front frame of the e-reader, It is used to capture the image data of the face of the viewer of the e-reader, so as to obtain and output a high-definition face image.

The invention relates to a method for preventing the eyes of a puerperal from being injured. The method comprises the step that an electronic reader audience fatigue analysis platform is used for immediately analyzing the electronic reader audience fatigue and giving an alarm based on a self-adaption deep neural network, wherein the electronic reader audience fatigue analysis platform comprises face image capturing equipment which is embedded into a front frame of an electronic reader and used for carrying out image data capturing on the face of an audience of the electronic reader to obtain and output a high-definition face image.

The invention discloses a volleyball fast-spike training device. The volleyball fast-spike training device comprises an upright column, wherein a cantilever beam which can be raised and lowered horizontally is arranged on the upright column; a spike soft rubber sheet is hung below the cantilever beam, and hung on the cantilever beam through an elastic rubber tube, and comprises an elastic chip externally coated with a sponge layer, the sponge layer is externally coated with a dust-proof cloth, a counter trigger switch is arranged in the spike soft rubber sheet, a hit counter for receiving signals of the counter trigger switch and displaying and recording the whipping number is arranged in the upright column, a take-off pedal is further arranged on a corresponding floor below the spike softrubber sheet, and a gravity sensing switch for starting a timer when both feet of a player are off the ground is arranged in the take-off pedal. The volleyball fast-spike training device can assist the volleyball player to practice quick arm swing so as to perform spike skills with wrists, thereby improving the spike quality and the scoring rate.

A method, system, device and medium for automatically adding punctuation to text, obtaining text by recognizing audio; converting corresponding text into multiple index value sequences, and inputting the multiple index value sequences into a deep neural network model, Obtain the probability distribution of each index value sequence; determine the maximum probability distribution value corresponding to each word in the index value sequence based on the probability distribution of each index value sequence, as the index of the punctuation mark to be added after the word; pass the index Obtain the corresponding punctuation marks from the predetermined punctuation mark index table, and automatically add them to the text sequence to complete the addition of punctuation marks to the text; if the index corresponds to a blank label, the current word is skipped and no punctuation is added to the current word symbol. The invention can realize functions such as automatic punctuation, cross-domain transfer learning and radical adjustment, and can also change the radical of the deep neural network model to meet the requirements of accuracy and recall in different scenarios.

The embodiment of the present invention discloses a video denoising method, device, mobile terminal and storage medium. The method includes: acquiring original image data and reference image data in the video data, and the original image data is the image data to be denoised in the current frame , the reference image data is the denoised image data of the previous frame; the original image data is divided into original image blocks and the reference image data are divided into reference image blocks by various types of scales; according to various types of scales, The original image block and the reference image block calculate the target motion probability between the original image data and the reference image data; perform three-dimensional denoising processing on the original image data according to the target motion probability and the reference image data, and obtain the target image data. This embodiment takes into account the performance and effect of the three-dimensional denoising processing, and can realize real-time three-dimensional denoising processing in the case of limited performance such as a mobile terminal.

The invention discloses a capacity configuration optimization method for a power grid side energy storage system. The method comprises the steps of obtaining operation parameters of a power grid; establishing a lower-layer energy storage system operation model and obtaining a planned daily peak clipping amount; establishing an upper-layer planning model and obtaining the scale of the energy storage system; and jointly solving the upper-layer planning model and the lower-layer energy storage system operation model by using a particle swarm optimization algorithm to obtain a final capacity configuration result of the power grid side energy storage system. According to the method, a unit-scale application effect model of the power grid side energy storage system is established, a method for calculating the application effect of the power grid side energy storage system on a multi-voltage-level power grid and a power supply is provided, and the advantage that one part of energy storage isapplied and multiple parts are benefited is fully reflected; an upper-layer and lower-layer optimal configuration model of the power grid side energy storage system is established, and an improved particle swarm algorithm is adopted to perform optimal calculation, so that a comprehensive optimal configuration result can be obtained quickly; therefore, the method is high in reliability and good inpracticability, and gives consideration to the overall effect and utilization efficiency of the power grid side energy storage system.

The invention provides a three-dimensional acquisition device capable of horizontally moving, which comprises a horizontal rail and an acquisition frame, wherein the acquisition frame is movably connected with the horizontal rail; the acquisition frame comprises a stand column and a cross beam, and an image acquisition device is arranged on the acquisition frame; and the image acquisition device is connected with the acquisition frame. In the invention, a gantry support structure is adopted for the first time, so that three-dimensional information of a large object can be collected. The gantrysupport can be disassembled and expanded, can adapt to objects with different sizes, and is convenient to disassemble and assemble.