9results about How to "Improve digging ability" patented technology

The application provides a power equipment fault data mining method, device and equipment and a storage medium. The method comprises: performing classification processing on power signal data to be mined to obtain target power signal data corresponding to a target data type from the power signal data; determining a target data mining model matched with the target data type based on a preset model database, wherein the target data mining model comprises at least one data mining sub-model stored in the model database; and performing fault data mining processing on the target power signal data by using the target data mining model to obtain power equipment fault data. The method can effectively reduce the calculation amount in the mining process, improve the power equipment fault data mining precision and efficiency, and improve the mining effect by screening out target power signal data to be mined and using a corresponding and adaptive target data mining model for data mining on the target power signal data.

The application discloses a network protocol design knowledge automatic extraction method based on RFC documents, and comprises the following steps: acquiring a chapter list of the RFC document and a line list in each chapter; acquiring a structured description in the chapter list and the line list to generate a key line list; analyzing the structured description in the key line list to obtain a formatted field list containing partial information and / or an undefined name list of an automaton; supplementing the formatted field list containing partial information and / or the undefined name list of the automaton based on chapter content to which a key line corresponding to the structured description belongs; and obtaining a network protocol design knowledge extraction result based on the formatted field list containing complete information and the automaton migration list. The application can automatically extract relevant network protocol design information.

The application discloses a highway micro-grid fault positioning method and system, and relates to the field of relay protection of power systems.The method comprises the following steps: obtaining the reactive power amplitude and the reactive power direction of each measuring point on each line section in the highway micro-grid; calculating the fault feature vector of each measuring point according to the reactive power amplitude and the reactive power direction of each measuring point; the fault feature vectors of multiple measuring points constitute a to-be-tested data group; inputting the to-be-tested data group into a micro-grid fault detection model to obtain the fault line section on the highway micro-grid; the micro-grid fault detection model is obtained by training and optimizing a graph attention network based on a fault sample set by using multiple kernel functions; the fault sample in the fault sample set comprises fault simulation feature vectors of multiple measuring points on each line section in the highway micro-grid and corresponding fault positions.The application realizes rapid and accurate positioning of faults in the highway micro-grid.

The application provides a scene-based home linkage control method and system of a health-care robot, the control method comprising: collecting multi-modal sensing data of a health-care scene, and outputting a latent mean vector and a variance vector of each time step by means of a variational autoencoder; inputting the mean vector into a probability mapping model to obtain an initial probability distribution of an atomic predicate, and generating a space-time compound predicate by fusing according to a space-time co-occurrence frequency and a weighted point mutual information; constructing an initial probability graph by taking the atomic predicate, the space-time compound predicate and a preset scene as nodes, correcting a conditional probability by combining a state uncertainty factor and a time sequence tightness factor to obtain a probability graph model, completing Bayesian inference by relying on a real-time predicate probability to obtain a scene posterior probability vector, generating an initial control point by a strategy network, and combining a control cost function neighborhood optimization to decode and output a home linkage control instruction and execute the same.

The invention discloses a spinal cord injury post-neurological function comprehensive evaluation system based on big data. The system comprises a data acquisition module, a spinal cord injury multi-modal feature depth selection module, a pre-injury neurological function baseline construction module and a double-reference spinal cord injury neurological function comprehensive evaluation module. The invention relates to the technical field of medical data processing, in particular to a spinal cord post-injury neurological function comprehensive evaluation system based on big data, which innovatively combines a pre-injury neurological function baseline construction module and a double-reference spinal cord injury neurological function comprehensive evaluation module to improve the comprehensiveness and accuracy of evaluation results; a collaborative correction feature screening algorithm fusing ternary mutual information is provided, and the model evaluation precision and stability are improved; the clustering algorithm is innovatively improved by fusing a high-dimensional vector included angle variance quantification method and a core point secondary evaluation strategy based on a reverse neighborhood number evaluation mechanism, the accuracy of a clustering result is improved, and the accuracy of a neural function evaluation result after spinal cord injury is improved.

The invention discloses a dynamic library fuzz testing method, related equipment and a computer program product, and relates to the field of software security testing. The strategy network generates the test case of the current round based on the state characteristics of the dynamic library and the reference seed selected by the current round. And after the current round of test case is executed, obtaining an exploration signal and a vulnerability signal through a dynamic library instrumentation mode, calculating an exploration reward of the current round of the strategy network based on the exploration signal, carrying out reinforcement learning training on the strategy network, and updating the vulnerability value of the reference seed based on the vulnerability signal. The vulnerability value is used for guiding selection of reference seeds in each test process. The strategy network can optimize, train and learn how to generate a test case with better exploration capability based on exploration rewards, and guide each round of reference seed selection by the vulnerability signal, so that test resources can focus to a high vulnerability probability region, and the vulnerability mining capability is improved.

The application discloses a deep learning-based Internet of Things device firmware vulnerability automatic mining method, comprising the following steps: S1, constructing an interface keyword set; S2, optimizing the interface keyword weight to generate a dynamic weight interface keyword library; S3, analyzing firmware binary files to locate an interface function set; S4, performing static slicing analysis to generate a slicing path set; S5, performing symbolic execution on the slicing path to generate path constraint conditions and solve effective input data; S6, combining historical vulnerability features to determine the vulnerability type and generate a vulnerability type identifier; S7, generating context prompt words according to vulnerability metadata information, inputting a large language model, and generating a vulnerability exploit code PoC; and S8, performing PoC verification to complete the vulnerability automatic mining. The application realizes the improvement of the firmware vulnerability automatic detection efficiency, enhances the vulnerability exploit generation capability, and is suitable for multiple types of Internet of Things device security detection scenes.

The application provides a deep learning-based most unfavorable working condition identification method and system, relates to the technical field of engineering structure test, and comprises the following steps: performing an initial test to obtain data, training a prediction model; generating multiple groups of to-be-tested working conditions by using a conditional generative adversarial network, inputting each group of to-be-tested working conditions into the prediction model, and outputting a predicted comprehensive risk index and corresponding mean and variance; constructing working condition interaction terms, and selecting target interaction terms through a random forest model; calculating the expected improvement of each group of to-be-tested working conditions based on the mean and variance of the predicted comprehensive risk index of the to-be-tested working conditions and the target interaction terms, selecting the to-be-tested working conditions for impact test, updating the conditional generative adversarial network and the prediction model based on the test results, and iterating until convergence to obtain the most unfavorable working condition. According to the scheme, high-risk working conditions are generated by using the conditional generative adversarial network, the working conditions are screened in combination with the prediction model, the most unfavorable working condition is quickly approached, the number of tests is significantly reduced, and the research and development cost and period are greatly reduced.

The present application relates to the technical field of rotating machinery fault diagnosis and condition monitoring, and discloses a kind of blade crack fault feature mining and early warning method, comprising: obtaining blade simulation crack measured signal, source domain dataset is constructed, target domain dataset is constructed, and source domain dataset and target domain dataset form input tensor;Utilize one-dimensional deep residual network as feature extractor, and utilize source domain dataset to pre-train feature extractor, obtain pre-trained feature extractor;Unified framework containing pre-trained feature extractor, fault classifier and domain discriminator is constructed, and knowledge transfer from source domain to target domain is realized by joint optimization classification loss, domain adversarial loss and maximum mean difference, and the trained cross-domain transfer diagnosis model is obtained;Real-time monitoring signal is input into the trained cross-domain transfer diagnosis model, and fault probability vector is obtained, multi-level early warning is carried out in combination with adaptive threshold, which can provide technical support for unit safe service.