4 results about "Generation process" patented technology

The invention discloses a preparation method of polyarylether containing quaternary ammonium side groups, comprising the following steps: a) adding bisphenol containing tertiary amine side groups, a halogenated organism monomer or nitrated organism monomer, a catalyst and a solvent, thus obtaining mixed solution; b) obtaining polyarylether containing tertiary amine side groups by polymerization reaction of the mixed solution obtained from the step a) at temperature of 30-180 DEG C; and c) adding halogenated hydrocarbon in the polyarylether containing tertiary amine side groups, and stirring at temperature of 0-100 DEG C, thus obtaining the polyarylether containing quaternary ammonium side groups. The invention also discloses a polyarylether containing quaternary ammonium side groups, and the sites and the number of the quaternary ammonium side groups are controllable. Compared with the prior art, the materials used in the invention is bisphenol containing tertiary amine side groups, no additional tertiary amine side groups or quaternary ammonium side groups are introduced in the generation process of the polyarylether containing quaternary ammonium side groups, so that the sites and the number of the quaternary ammonium side groups in the polyarylether are controllable, in addition, the conversion rate is complete and the laboratory yield is higher than 95%.

The invention discloses a tumor MRI weak supervised learning analysis modeling method, which comprises the following steps: S1, constructing a tumor MRI segmentation network based on a full convolutional neural network to realize tumor MRI preliminary segmentation; S2, taking the tumor MRI segmentation network as a generator, taking the classification model as a discriminator, and proposing a generative adversarial training algorithm of the tumor MRI segmentation network; and S3, taking unlabeled image data in the medical image as additional input condition information of the generator model and the discriminator model, guiding a data generation process, and enhancing the stability of the segmentation-generative adversarial network. The invention also discloses a model established by usingthe tumor MRI weak supervised learning analysis modeling method. According to the method, the tumor target region and the endangered organ can be more accurately and automatically segmented under thecondition of fewer training samples, and the method is applied to target region and endangered organ sketching of tumor radiotherapy.

The embodiment of the invention discloses method and device for generating configuration files. The method comprises the steps of: selecting configuration files of the original base station of the network as initial configuration files for expanding network capacity, wherein the original base station is an adjacent base station of a network newly-added base station; obtaining base station configuration parameters of the newly-added base station; and generating configuration files of the newly-added base station and configuration files of all adjacent base stations of the newly-added base station after the capacity of the network is expanded according to the initial configuration files of the original base station and the base station configuration parameters of the newly-added base station. According to the invention, the configuration files of eNB after the capacity of the network is expanded are generated through the configuration files of the original eNB before the capacity of the network is expanded, thus the generation process of the configuration files of the eNB in an LTE system is simplified.