12results about How to "Quick Discrimination" patented technology

The application relates to the technical field of network security, in particular to a self-defined private network asset fingerprint management method and system, which comprises the following steps: based on network access events, analyzing behavior tracks and historical modes, identifying abnormal activity paths, judging abnormal relations between asset permission groups and access actions, screening risk assets and checking permission levels, adjusting fingerprint permissions, analyzing security event aggregation conditions to identify invalid states, and detecting fingerprint behavior deviation rates through operation time sequence analysis. The application identifies path deviation and traffic anomaly by analyzing the multidimensional changes of network access behavior, comprehensively judges operation risk and permission matching conditions by combining the time sequence correlation of permission allocation and access actions, dynamically adjusts fingerprint permission categories, further identifies the abnormal state of the fingerprint in real time through the aggregation analysis of security events and operation time sequences, and realizes behavior consistency verification in the use process of the asset fingerprint.

The invention provides a 20K liquid phase chip for simultaneously and accurately identifying various goose varieties and application, the 20K liquid phase chip covers 22005 SNP molecular markers, and the SNP molecular markers are specifically composed of a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt The SNP molecular marker is composed of 4991 genetic differentiation specific sites, 12 important character associated sites and 17002 whole genome background sites of 22005 goose varieties, and the specific positions of the 22005 SNP molecular marker sites are shown in a table 1 in the specification. According to the method, 16 goose varieties can be accurately distinguished, the identification efficiency is high, the detection process can be completed within 24 hours, 48-96 samples can be detected at a time, and the technical repetition rate is gt; the cost of the chip is far lower than that of a high-density chip, and the chip is suitable for carrying out multi-variety and large-scale germplasm monitoring and identification work in a breed conservation field, a research and development unit and the like, and is high in practicability.

The invention discloses a dynamic game-based immediacy decision-making method, which specifically comprises the following steps of: establishing a combat action dynamic game selection model, and determining a red-blue action set of the combat action selection model; determining a battlefield state transition probability of the battlefield action selection model; obtaining a red-blue confrontation strategy according to the red-blue action set and the state transition probability; constructing a state utility function in the battle action selection model; and determining the optimal strategy of the red and blue parties through the zero-sum game. Compared with the prior art, the method not only can dynamically evaluate the advantages and disadvantages of different tactical selections, but also can preferably select an appropriate action sequence and select an optimal action decision in a complex game environment of friend or foe in combination with intelligence update and battlefield feedback.

The application relates to an equatorial ionospheric irregularity automatic detection method and system, and belongs to the field of artificial intelligence. The method comprises the following steps: downloading GOLD satellite data, pre-processing and labeling, and constructing an original data set; inputting the original data set into a deep learning network model for training to obtain a trained deep learning network model; calculating the performance index of the trained deep learning network model, and outputting an equatorial ionospheric irregularity identification result. The application solves the problem of low accuracy in identifying and detecting equatorial ionospheric irregularities caused by the influence of factors such as slant range, background airglow intensity, instrument characteristics and threshold.

The application provides a vehicle lamp fault detection system and a vehicle, and relates to the technical field of vehicle lamp control. The system comprises a photosensitive module, a thermosensitive module, an electric signal detection module and a vehicle lamp control module. The photosensitive module is used for detecting a light intensity signal of a target vehicle lamp. The thermosensitive module is used for detecting a temperature signal of the target vehicle lamp. The electric signal detection module is used for detecting an electric signal when the target vehicle lamp is working. The vehicle lamp control module performs fault type detection of the target vehicle lamp based on the light intensity signal, the temperature signal and the electric signal. Through multi-dimensional signal acquisition of the photosensitive module, the thermosensitive module and the electric signal detection module, the application can realize accurate diagnosis of the fault type of the vehicle lamp, break through the limitation of traditional binary detection, can distinguish the fault type of the vehicle lamp, and thus significantly improve the vehicle lamp fault detection effect.

This invention discloses a method for sensing the operational status of a distribution network, relating to the field of distribution network monitoring and intelligent operation and maintenance. The method includes: synchronous acquisition of multi-source ubiquitous data to construct a low-cost ubiquitous sensing network; edge-side data preprocessing and lightweight analysis; topology-adaptive multi-source data fusion: constructing a distribution network topology map based on neural networks and mining the spatial and temporal correlations of multi-source data; multi-dimensional quantitative assessment of operational status: constructing a multi-dimensional status assessment system; precise fault location and hierarchical early warning: fusing multi-terminal information to achieve precise fault location; and online model iteration and closed-loop optimization. This distribution network operational status sensing method, by employing a low-cost ubiquitous sensing network combined with dedicated sensors and non-intrusive monitoring, covers the entire distribution network—from source to grid to load to storage—solving the problems of large blind spots and high deployment costs associated with traditional sensing methods. It achieves effective monitoring of end nodes and branch lines, realizing the goal of full-area, blind-spot-free sensing.

The invention relates to the technical field of power distribution network fault line selection, and discloses a fault line selection method, system and equipment based on a bus zero sequence current neutral point ungrounded device and a medium. Fault judgment is carried out according to phase comparison of the zero-sequence current of the two buses associated with each line; and for the edge distribution line, calculating the zero-sequence current of the edge line, respectively comparing the zero-sequence current with the starting current, and carrying out fault judgment by combining the phase and amplitude comparison of the bus zero-sequence current. Based on the bus zero-sequence current formed by converging the line zero-sequence current, the fault line identification method based on phase comparison is provided according to the access mode of the bus zero-sequence current, the method does not depend on zero-sequence current information of all lines in the system and does not need to test alternate cutting lines; whether the line is a fault line or not can be quickly judged only depending on the bus zero-sequence current information related to the line.

The invention relates to the technical field of power equipment fault positioning, in particular to a power equipment fault positioning method based on a graph neural network, which comprises the following steps of: establishing a Chain-GNN model to be matched with hardware deployment to pre-process data during normal operation of a circuit, and determining normal operation baseline data; step 2, setting an abnormal score threshold and a bidirectional traveling wave fault rule base, and oppositely and synchronously injecting bidirectional traveling waves into a preliminarily alarmed line, and step 4, after a fault point is confirmed, ensuring normal operation of other equipment; after the sublines are erected, first-aid repair is carried out, and after first-aid repair is completed, all the sublines are disconnected, and original circuit connection is recovered; comparing the normal operation baseline data in the step 1 to determine whether the line recovers normal operation, if so, entering a step 6, and if not, returning to the step 3 to re-determine the fault point; and the Chain-GNN model can automatically archive the whole process data of the fault processing at this time.

The invention discloses a flexible monitoring sensor for actively sounding fish and a signal analysis method, and relates to the technical field of aquaculture, and the flexible monitoring sensor mainly comprises a flexible substrate, an interdigital electrode arranged on the substrate, and a piezoresistive sensitive layer covering the electrode. The sensitive layer is made of a PDMS and graphene composite material, and the surface of the sensitive layer is provided with a regularly arranged micro-pyramid structure array. The sensor is attached to the body surface of a fish sounding part, the micro-pyramid structure responds to body surface sound vibration in a preset frequency range to generate deformation, and the sound vibration is converted into a resistance change signal between the interdigital electrodes by utilizing the piezoresistive effect of the composite material. Through the design of the PDMS-graphene composite material and the surface micro-pyramid structure, high-fidelity and direct capture of body surface vibration signals generated by initiative sounding of individual fishes is realized, and the problems of group sound mixing and weak signal relevance in a traditional method are effectively avoided.

The application discloses a frequency stability quantitative discrimination method and system suitable for different scenes and belongs to the technical field of power systems. The method comprises the following steps: obtaining model parameters of a target frequency response physical model of a target power system; identifying the model parameters based on a discrimination model to obtain a frequency response curve of the target frequency response physical model for the target power system; and quantifying the frequency stability of the target power system by discriminating the frequency response curve. The application can identify the model parameters of the frequency response physical model to quickly discriminate the discrimination frequency response curve of the power system, thereby quantifying the frequency stability of the power system.

The invention discloses a crude oil production layer judgment method based on a neural network learning model, and belongs to the technical field of oil reservoir exploration, and the method comprises the following steps: S1, obtaining crude oil samples of different oil production layer sections in a research block; s2, setting gas chromatographic analysis conditions; s3, acquiring a chromatographic curve graph; s4, performing homogenization processing on the chromatographic curve graph to obtain a label data set; s5, establishing an image learning network model, and inputting the training set into the image learning network model for training; s6, adjusting the trained image learning network model through the verification set; and S7, extracting a crude oil sample of an unknown output interval, carrying out gas chromatographic analysis test, carrying out homogenization treatment on a test result, and finally inputting the image learning network model to judge the crude oil source of the unknown output interval. According to the method, on the basis of the neural network, by performing feature matching on the chromatogram of the crude oil sample of the production well of the unknown oil production layer section, the source of the crude oil of the unknown production layer can be quickly identified with high precision.

The invention discloses a hydrogen production mode identification method and system based on a tree classifier, and belongs to the technical field of hydrogen analysis, the hydrogen production mode identification method based on the tree classifier comprises the following steps: S1, extracting the original component content of a hydrogen sample; s2, constructing engineering features based on the original component content, wherein the engineering features comprise a component proportion, a composition entropy, logarithm transformation, a component interaction item and a principal component; and S3, hydrogen production mode identification: taking the engineering characteristics as input, synthesizing minority class oversampling for relieving class imbalance, and performing hydrogen production mode judgment through a tree classifier. By adopting the technical scheme, the hydrogen production mode can be quickly analyzed by utilizing the tree classifier based on the original component content and engineering characteristics of the hydrogen sample.