7results about How to "Reduced Quantity Requirements" patented technology

The application discloses a kind of weakly supervised image semantic understanding methods based on multi-task learning, comprising the following steps: obtaining task missing image, constructing multi-level task sharing encoder, extracting high-level semantic information layer by layer, input corresponding decoder branch;Construct public space-task space feature mapping module, through the unaligned task fusion module and task interaction mapping module, update each subtask feature by mapping;Task adaptive feature update module is constructed, and multi-level iterative update unaligned task feature;Task adaptive weakly supervised image semantic understanding framework is constructed, model loss function is established, image data with task missing is input into model, and obtains multi-task prediction result such as semantic segmentation, depth estimation, surface normal estimation.The application is according to the data information of task label unaligned, through the mapping interaction of public space and task space, fully fuses unaligned task feature, iteratively generates high-quality multi-task prediction result, can effectively handle weakly supervised problem with task missing, and simultaneously improves each task prediction accuracy.

This utility model discloses a gas distributor for a chloromethane synthesis reactor. The main support pipe and the main distribution pipe are arranged parallel to each other and positioned below the main distribution pipe. Distribution branch pipes are provided on the main distribution pipe, symmetrically arranged at a 45-degree angle to the horizontal line of the main distribution pipe. A supporting inclined pipe connects the distribution branch pipes to the main support pipe at a 90-degree angle. Both the main distribution pipe and the distribution branch pipes have three rows of distribution holes, arranged on the lower side of the main distribution pipe and the distribution branch pipes. Two rows are symmetrically arranged at a 45-degree angle to the horizontal line of the main distribution pipe and the distribution branch pipes, and one row is arranged at a 90-degree angle to the horizontal line of the main distribution pipe and the distribution branch pipes. This utility model's gas distributor device has a simple structure, uniform stress on the distribution pipes, and a firm connection. It requires fewer pipe openings at the bottom of the equipment, reducing the risk of material leakage. The steel-lined support rods with a double-layer anti-corrosion design have strong corrosion resistance, extending the service life of components and the equipment maintenance cycle.

The application provides a communication radiation source identification method, device and equipment and a storage medium. The method comprises the following steps: obtaining a signal feature of a radio signal; inputting the signal feature into a pre-trained communication radiation source identification model to obtain a communication radiation source identification result corresponding to the radio signal; wherein the communication radiation source identification model comprises a feature reconstruction subnetwork and a feature classification subnetwork, and the feature reconstruction subnetwork is obtained through feature reconstruction training by taking the signal feature of a radio signal sample as a training sample and a training label respectively. The communication radiation source identification method greatly reduces the quantity requirement of labeled samples, can achieve the purpose of communication radiation source identification under the condition of a small number of labeled samples, and thus makes the method competent for more communication radiation source identification tasks.

The application discloses a kind of wide temperature range thermoplastic resin-based composite interface strength real-time testing methods, and the application belongs to the field of composite materials, to provide new method for the real-time testing of thermoplastic composite interface strength under variable temperature environment and the interface strength testing of thermoplastic resin softening under high temperature.The application realizes the real-time testing of fiber reinforced thermoplastic resin-based composite interface strength under wide temperature range by measuring the impedance of magnetic fiber embedded in thermoplastic resin in variable temperature environment.The method is simple to test, high in testing efficiency, widely applicable, can realize the real-time testing of thermoplastic resin-based composite interface strength under wide temperature range of-60 DEG C to 150 DEG C, and provides data support and performance guarantee for the service safety of materials under high and low temperature complex environment.

This invention discloses a natural electric field source inversion method based on a genetic algorithm, belonging to the field of geophysical inversion technology. It solves the technical problems of low inversion accuracy and large source location errors in natural electric field inversion caused by optimization algorithms. The key points of the technical solution are: first, expanding the input electrical resistivity data using head-to-tail cross-interpolation; second, using the extreme values ​​and dispersion of the electrical resistivity data as the center and radius of the population distribution area; third, forming a population by describing individuals based on the number and location of source sources; and finally, using a genetic algorithm based on double-threshold cross-iteration to achieve natural electric field source inversion with smaller source fitting errors. This application can effectively utilize a small amount of input electrical resistivity data, reasonably expand and extract extreme value features, and largely solve the problems of large inversion fluctuations caused by large spatial areas, small data volumes, and the inherent multiple solutions in geophysical inversion, while achieving smaller source fitting errors.

The embodiment of the application provides a kind of image denoising method, device, system, edge device and storage medium, the method comprises: obtaining to be denoised image;With preset multi-head attention mechanism module, the first feature matrix of to-be-denosed image is extracted, wherein, preset multi-head attention mechanism module includes self-attention mechanism and channel attention mechanism;First feature matrix is up-sampled, and second feature matrix is obtained;Based on second feature matrix, the denoised image corresponding to to-be-denosed image is generated. The technical scheme provided in the embodiment of the application can improve the image denoising efficiency, reduce the consumption of computing resources, and then reduce the performance requirements of the device.

The application provides a polypeptide generation method and device, and relates to the technical field of polypeptide design. The method comprises the following steps: obtaining preset polypeptide information pool and structure information of a target protein, wherein the preset polypeptide information pool comprises amino acid sequence information of at least one existing polypeptide; performing ladder element extraction on the amino acid sequence information of the at least one existing polypeptide to obtain a plurality of ladder elements, wherein the ladder element is a repeated amino acid fragment in the amino acid sequence information of the at least one existing polypeptide or a basic amino acid constituting the amino acid sequence information; reconstructing at least one new amino acid sequence information according to the plurality of ladder elements; and determining a target new polypeptide from the at least one new amino acid sequence information according to a molecular docking result of the at least one new amino acid sequence information and the structure information of the target protein. The application can reduce the dependence on a large amount of training data and improve the interaction effect of the generated polypeptide and the target protein.