11results about How to "Improve relationship" patented technology

A kind of detection method and device of fake APP, terminal, the method includes: determining training data;Keyword extraction is carried out to the brief introduction of each pair of target APP and the brief introduction of suspected APP, and the data vector of each keyword is determined;Determine the weight value of each keyword, and the data vector of each keyword in the target APP is weighted based on the weight value Operation is carried out to obtain target APP data vector, and obtain suspected APP data vector;The vector comparison result of target APP data vector and suspected APP data vector is calculated, the absolute value of the vector comparison result is determined as first data vector, and the square of the vector comparison result is determined as second data vector;Obtain the training text vector of the pair of target APP and suspected APP;Training fake detection model.The present application can enhance the association between keywords in model training phase, reduce the misjudgment rate.

The embodiment of the invention provides a 5G-Advanced sensing communication collaborative resource scheduling method and system for a smart substation, and belongs to the technical field of power system operation and maintenance. The method comprises the steps that a 5G-Advanced cellular-free unmanned aerial vehicle communication and sensing integrated network architecture is constructed, the network architecture comprises a passive sensing layer, an air-ground cooperative access layer and a centralized processing layer, and deep integration of sensing, energy supply and communication functions is achieved; establishing a system model based on the network architecture, wherein the system model comprises a network topology model, a communication and inductance integrated transmission model and a constraint optimization problem model; a cross-CPU dynamic resource scheduling algorithm based on MADDPG is designed, and joint optimization of user association, power distribution and load balancing is achieved through a centralized training-distributed execution mechanism; based on a scheduling algorithm and a system model, substation global real-time sensing, data transmission and operation and maintenance performance collaborative guarantee are achieved. The sensing fusion and coverage capability is greatly improved, the dynamic scene adaptability is better, and the sensing-operation and maintenance collaboration value is higher.

The invention relates to a qualitative and quantitative method for liensinine perchlorate. The qualitative method comprises the following steps: weighing 1mg of liensinine perchlorate and 1mg of liensinine, uniformly grinding and tabletting the liensinine perchlorate and the liensinine with 100mg of potassium bromide respectively, acquiring an infrared spectrum of 4000-400cm <-1 > by adopting an infrared spectrometer, and comparing spectrograms to find that the peak shapes of the liensinine perchlorate and the liensinine are similar, the peak shapes of the liensinine perchlorate and the liensinine perchlorate are common characteristic peaks and the peak shapes of the liensinine perchlorate are unique characteristic peaks of the liensinine perchlorate and the liensinine are common characteristic peaks and the peak shapes of the The quantitative method comprises the following steps: weighing a series of liensinine perchlorate reference substances with different masses, uniformly grinding and tabletting the liensinine perchlorate reference substances and 100mg of potassium bromide respectively, collecting an infrared spectrum, carrying out integration on a 625cm <-1 > characteristic peak to obtain a peak area, and drawing a standard curve by taking the peak area as a vertical coordinate and taking the sampling mass of the reference substances as a horizontal coordinate; the method comprises the following steps: weighing a sample to be detected, collecting an infrared spectrum, integrating a 625cm <-1 > characteristic peak to obtain a peak area, substituting the peak area into the standard curve equation, calculating the mass of the liensinine perchlorate in the sample, and substituting the mass into the content calculation formula to obtain the content of the liensinine perchlorate in the sample. The method is good in precision, repeatability and stability, wide in linear range, high in linear correlation coefficient and high in recovery rate, the problem that liensinine interference cannot be avoided in an existing content determination method is effectively solved, whether liensinine perchlorate is generated or not can be qualitatively judged, and the quantity of liensinine perchlorate generated can be quantitatively detected; and a feasible new method is provided for production process optimization and quality evaluation of liensinine perchlorate.

The invention discloses an image-text matching method based on a multi-modal knowledge-driven intra-modal and inter-modal interaction network framework, and provides a multi-modal knowledge-driven intra-modal and inter-modal interaction graph network for image text matching. The efforts of modeling cross-modal inter-modal, inter-modal and intra-modal and inter-modal interaction relationships are determined for the first time; introducing a framework, combining multi-modal implicit priori knowledge with local and global features, and learning feature embedding to enhance a relationship; the problem that an existing method which only considers the inter-modal or intra-modal relation is low in performance when semantic fuzziness and similar samples are retrieved is solved. A series of comprehensive experiments are carried out on a reference data set Flickr30k and MSCOCO, and the performance of an image text retrieval task is improved.

The present application relates to a kind of synthesis method and electronic equipment of coronary artery CCTA image, comprising: obtaining the image of paired NCCT and CCTA, after pretreatment, obtain high consistency image training pair;LDM model suitable for adapting coronary artery image synthesis is constructed, the LDM model includes frozen variational autoencoder, the denoising U-Net of trainable based on cross attention mechanism, and decoder, the denoising U-Net integrates ResNet2D module, Transformer2D module and multi-scale cross attention layer;After pre-processing, the NCCT image to be processed is input into the LDM model trained, and the latent representation of CCTA image is generated by the reverse diffusion denoising process in latent space, and finally the high-resolution Syn-CCTA image is output by decoder.Compared with prior art, the present application has the advantages of no contrast agent to realize coronary artery CCTA image with auxiliary diagnostic value.

The invention relates to a qualitative and quantitative method for isoliensinine perchlorate. The qualitative method comprises the following steps: weighing 1mg of isoliensinine perchlorate and 1mg of isoliensinine, uniformly grinding and tabletting the isoliensinine perchlorate and the isoliensinine with 100mg of potassium bromide respectively, acquiring an infrared spectrum of 4000-400cm <-1 > by adopting an infrared spectrometer, and comparing the spectrograms to find that the peak shapes of the isoliensinine perchlorate and the isoliensinine are similar, the peak shapes of the isoliensinine perchlorate and the isoliensinine perchlorate are common characteristic peaks and the peak shapes of the isoliensinine perchlorate are unique characteristic peaks of 625cm <-1 >. The quantitative method comprises the following steps: weighing a series of isoliensinine perchlorate reference substances with different masses, uniformly grinding and tabletting the isoliensinine perchlorate reference substances and 100mg of potassium bromide respectively, collecting an infrared spectrum, carrying out integration on a 625cm <-1 > characteristic peak to obtain a peak area, and drawing a standard curve by taking the peak area as a vertical coordinate and taking the sampling mass of the reference substances as a horizontal coordinate; the method comprises the following steps: weighing a sample to be detected, collecting an infrared spectrum, integrating a 625cm <-1 > characteristic peak to obtain a peak area, substituting the peak area into the standard curve equation, calculating the mass of the isoliensinine perchlorate in the sample, and substituting the mass of the isoliensinine perchlorate in the sample into the content calculation formula to obtain the content of the isoliensinine perchlorate in the sample. The method is good in precision, repeatability and stability, wide in linear range, high in linear correlation coefficient and high in recovery rate, the problem that an existing content determination method cannot avoid interference of isoliensinine is effectively solved, whether isoliensinine perchlorate is generated or not can be qualitatively judged, and the amount of isoliensinine perchlorate generated can be quantitatively detected. And a feasible new method is provided for production process optimization and quality evaluation of the isoliensinine perchlorate.

The embodiment of the application discloses a system aging state detection method, device, equipment and readable storage medium, the method comprises: obtaining at least one running state of the system to be detected and at least one state transition model corresponding to the running state; obtain the target parameter corresponding to the state transition model, and obtain the first weight of the target parameter by hierarchical analysis; determine the anti-decay index corresponding to each running state based on the target parameter and the first weight corresponding to the target parameter, and determine the aging state information of the system to be detected according to the anti-decay index. By analyzing the target parameter to determine the weight corresponding to the target parameter, the association between the target parameter and the system aging state is strengthened, so that the anti-decay index determined by the target parameter and the weight corresponding to the target parameter is more objective and accurate, thereby improving the effectiveness and accuracy of the aging state detection of the system to be detected when determining the aging state information of the system to be detected based on the anti-decay index.

The application discloses a static and dynamic combined fuzzy gesture recognition method and device and medium. The method comprises the following steps: extracting gesture feature points of a gesture image to be recognized of a user at a current time, and taking the gesture feature points as first feature points; normalizing a first position difference function of the first feature points to generate a spatial domain feature matrix; obtaining a plurality of historical gesture images of the user within a preset historical time length; extracting gesture feature points of each historical gesture image, determining gesture feature points at the same position in adjacent historical gesture images, and taking the gesture feature points at the same position as second feature points; normalizing a second position difference function of the second feature points to generate a space-time sequence feature matrix; inputting the spatial domain feature matrix and the space-time sequence feature matrix into a pre-constructed deep convolutional neural network model respectively, and outputting a gesture posture and a gesture action category of the user at the current time, thereby improving the gesture recognition accuracy.

A multi-period map correlation system based on graph optimization comprises a single SLAM mapping module, a data integration module, a global search module, a point cloud fine matching module and a global graph optimization module. The application focuses on the changing mine environment, constructs a global map for the data collected in different periods, and completes the information correlation between the global maps, provides a basis for long-period map updating, thereby converts the pose estimation problem into a joint optimization problem, realizes accurate correlation of multi-pass mapping, and significantly improves the positioning accuracy and environmental adaptability of the SLAM technology in the mine scene.

The invention relates to a qualitative and quantitative method of lotus plumule total alkali perchlorate. The qualitative method comprises the following steps: weighing 1mg of lotus plumule total alkali perchlorate and 1mg of lotus plumule total alkali, uniformly grinding and tabletting the weighed lotus plumule total alkali perchlorate and the weighed lotus plumule total alkali perchlorate and 100mg of potassium bromide respectively, collecting 4000-400cm <-1 > infrared spectrums by adopting an infrared spectrometer, and comparing spectrograms to find that the two peaks are similar in shape, 1515cm <-1 > and 110cm <-1 > are common characteristic peaks, but 625cm <-1 > is a unique characteristic peak of the lotus plumule total alkali perchlorate. The quantitative method comprises the following steps: weighing a series of lotus plumule total alkali perchlorate reference substances with different masses, uniformly grinding and tabletting the reference substances and 100mg of potassium bromide respectively, collecting an infrared spectrum, carrying out integration on a 625cm <-1 > characteristic peak to obtain a peak area, and drawing a standard curve by taking the peak area as a vertical coordinate and taking the sampling mass of the reference substances as a horizontal coordinate; weighing a to-be-detected sample, collecting an infrared spectrum, integrating a 625cm <-1 > characteristic peak to obtain a peak area, substituting the peak area into the standard curve equation, calculating the mass of the lotus plumule total alkali perchlorate in the sample, and substituting the mass of the lotus plumule total alkali perchlorate in the sample into the content calculation formula to obtain the content of the lotus plumule total alkali perchlorate in the sample. The method is good in precision, repeatability and stability, wide in linear range, high in linear correlation coefficient and high in recovery rate, effectively solves the problem that an existing content determination method cannot avoid interference of lotus plumule total alkali, can qualitatively judge whether lotus plumule total alkali perchlorate is generated or not, can quantitatively detect how many lotus plumule total alkali perchlorate is generated, and can be used for determining the content of the lotus plumule total alkali perchlorate. And a feasible new method is provided for production process optimization and quality evaluation of the lotus plumule total alkali perchlorate.

The application relates to the technical field of intelligent control, and discloses an unmanned water sample automatic analysis system and method based on artificial intelligence and a computer storage medium, which comprises a water sample access device, a water sample storage device, a water sample separation device and a water sample analysis device. Through the cooperative linkage of the water sample access device, the water sample storage device, the water sample separation device and the water sample analysis device, the system realizes the whole-process unmanned operation from water sample access, identification, control, storage, separation pretreatment to water quality analysis and result synthesis. It can be seen that the system described in the application can realize the full-automatic control and analysis monitoring of a plurality of water samples, and is favorable for improving the water quality analysis monitoring efficiency and the water quality analysis monitoring reliability.