38results about How to "Reduce computing resource consumption" patented technology

The invention discloses an encryption method and system based on error-correcting codes and low-round AES. The related system includes: a low-round AES encryption module, which is used to perform low-round AES on input data by using the acquired AES Advanced Encryption Standard key. Encrypt to obtain AES ciphertext data; the error correction code encoding module is used to generate an error correction code encoding key of the length of the difference according to the difference between the length of the AES ciphertext data and the length of the error correction code, and convert the error correction code The code encoding key is spliced ​​with the AES ciphertext data to perform error correction encoding to obtain the error correction code encoding result; the error correction code encoding key in the error correction code encoding result is discarded to obtain the encrypted and error corrected data. The method and system disclosed in the present invention can achieve better performance with less computing resource consumption (including CPU time consumption during software calculation, area and power consumption during hardware calculation) in applications with bit errors and requiring error correction. AES encryption performance.

The invention provides a tumor mutational load detecting method, a device and a storage medium. The method comprises the steps of acquiring mutation frequency data of a single testing sample, whereinthe mutation frequency data comprise the site mutation frequency of a sample target area, comparing the site mutation frequency with a preset threshold for obtaining a mononucleotide mutation which ishigher than the threshold, and eliminating meaningless mutation in mononucleotide mutation for obtaining the number of effective mononucleotide mutations; acquiring Indel mutation frequency data of the single testing sample, wherein the Indel mutation frequency data comprises the Indel mutation frequency of the sample target area, comparing the Indel mutation frequency with a preset threshold forobtaining the number of the Indel mutations which are higher than the threshold; calculating the number of the tumor mutational load according to a number evaluation formula of the tumor mutational load, wherein the number estimation formula comprises the weight item of the number of the effective mononucleotide mutations and the weight item of the number of the Indel mutations. The method according to the invention accurately detects the TMB index of the lung cancer sample under a precondition of no dependence to a common database and a normal pairing comparison sample.

The present invention relates to artificial intelligence, and discloses a method for analyzing medical images, including: using a pre-built disease history picture set to train a pre-built deep learning network model to obtain a disease identification model; constructing a disease identification model based on the disease identification model and the pre-built initial diagnosis model Distillation loss function; perform distillation training on the initial diagnostic model according to the distillation loss function to obtain the first diagnostic model; perform training and output adjustment on the first diagnostic model according to the preset diagnostic target to obtain the target diagnostic model; when receiving the medical In the case of image images, the target diagnostic model is used to analyze the medical image images to be analyzed, and the analysis results are obtained. The present invention also relates to a block chain technology, and the data of the training model can be stored in the block chain. The invention also proposes a medical image analysis device, electronic equipment and a computer-readable storage medium. The invention can reduce the model calculation resource consumption of medical image analysis.

An object rendering method, device, storage medium, and electronic device are provided. The method comprises: obtaining a two-dimensional image obtained by performing image collection on a target object (S202); recognizing a first pixel point set from all pixel points of the two-dimensional image, pixel points in the first pixel point set being points on a contour of the target object (S204); recognizing one or more second pixel point sets in the first pixel point set by means of calling an image processor, each pixel point in the second pixel point set indicating a line segment of the contour of the target object (S206); and respectively connecting each pixel point in the second pixel point set to form line segments of the contour of the target object, and displaying, according to a preset rendering manner, each connected line segment (S208). The method resolves the technical issue of the related art in which computing resource consumption of a CPU of a computer is large when real-time rendering is performed.

The invention discloses a sensor node positioning method. The method comprises the following steps of: collecting the position information of each beacon node in a communication range at the node to be positioned to obtain the positioning information set of each beacon node; broadcasting the position information set to each beacon node by the node to be positioned; respectively independently operating a particle group algorithm by each beacon node according to the position information set to respectively obtain the corresponding the optimum particle position information; detecting the optimumparticle position information by the node to be positioned to fix the coordinate position of the node to be positioned. The invention can obviously reduce the calculation consumption of the node to be positioned.