27results about How to "Improve digging ability" patented technology

The invention discloses a migration working condition bearing remaining service life prediction method based on a contrast double-confrontation mechanism, and the method comprises the steps: obtaining a bearing vibration signal of a single time step and a corresponding label, decomposing the bearing vibration signal of the single time step, obtaining an intrinsic mode IMF, reconstructing the bearing vibration signal of the single time step, and obtaining a prediction result of the bearing remaining service life. Fault point detection is carried out; constructing a sample containing time sequence information; constructing a residual service life prediction model, inputting the sample into the residual service life prediction model, and outputting the residual service life corresponding to the sample; the residual service life prediction model comprises a dynamic convolution long-short memory neural network feature extractor and a predictor; and constructing a migration training framework of a contrast double-confrontation mechanism. According to the method, noise reduction processing is carried out on an original vibration signal in combination with multi-scale permutation entropy, and fault occurrence point detection in the bearing degradation process is carried out by using hidden Markov based on Bayesian reasoning. Through the technology, the influence of non-degradation data information on the residual service life after degradation is reduced, and the workload and prediction difficulty of a prediction task are reduced.

The invention discloses a method for measuring and calculating carbon emission of enterprise users in a high-energy-consumption industrial park, and relates to the technical field of carbon emission monitoring. According to the method, aiming at direct carbon emission of enterprise users in a high-energy-consumption industrial park, on one hand, a multi-source feature and direct carbon emission mapping model is constructed and trained to carry out direct carbon emission measurement and calculation by utilizing wide coverage and real-time performance of electric power and thermal data, and on the other hand, a multi-source feature and direct carbon emission mapping model is constructed and trained to carry out direct carbon emission measurement and calculation. In order to solve the problem of data privacy security of a park, park enterprise users and an electric power and heating power company, an information interaction method based on a PP3-FL framework and a mapping model construction method based on a FedPSW strategy are introduced. High-frequency, accurate and efficient measurement and calculation of the carbon emission of the park enterprise users are achieved, and then the problems that according to an existing carbon emission measurement and calculation scheme, accounting is imperfect, the accuracy of a measurement and calculation result is limited, and user privacy is not considered during model training and application can be solved.

The utility model relates to the technical field of landscape gardens, in particular to an earth boring machine for garden planting, which comprises a support. A rotating mechanism is connected to the inner side of the support and comprises a supporting ring, the supporting ring is slidably connected to the inner side of the support, two rotating plates are rotatably connected to the inner side of the supporting ring, driving blocks are slidably connected to the rotating plates, a limiting block is rotatably connected to the bottom end of the supporting ring, and a moving rod is slidably connected to the inner side of the limiting block. The tail end of the moving rod is fixedly connected with a driving ring, and the driving ring is arranged on the outer side of the driving block in a sleeving mode. The driving of the excavating structure, the reciprocating motion of the excavating structure and the rotation of the excavating structure are synchronously controlled by a single motor through the arranged linkage type rotating structure, so that the use of the motor is reduced, and the subsequent maintenance operation is facilitated while the winding of an electric wire is avoided.

The invention discloses an intelligent contract vulnerability mining method based on feedback information fuzzy testing. Comprising the following steps: in a static analysis stage, converting a contract source code into an abstract syntax tree, extracting a control flow graph and function list information of a contract, and defining a function sequence priority calculation method; in the seed pool and test transaction construction stage, a seed pool is initialized, and a variation mode of a transaction sequence is defined. Then the system performs instrumentation in the EVM for collecting feedback information and defining judgment modes of different types of contract vulnerabilities; in the dynamic test stage, a mass fraction formula of a seed case is designed, whether the seed case is reserved or not is determined by comparing mass fractions, the seeds are varied according to a certain probability, and a seed pool is updated. According to the method, the fuzzy test technology based on the feedback information in the test process is constructed and is used for carrying out the vulnerability mining task for the smart contract, more deep states of the smart contract can be explored, and the efficiency and the accuracy of the vulnerability mining task are improved.

The invention provides an emotion recognition method and device, a storage medium, a system and a program product, and the method comprises the steps: outputting first task information, so as to prompt a target user to execute a first task corresponding to the first task information; in the process that the target user executes the first task, obtaining first physiological data of the target user; processing the first physiological data by using a first emotion recognition model to obtain coarsely screened emotion information; determining second task information from the multiple pieces of candidate task information according to the coarse screening emotion information; outputting the second task information to prompt the target user to execute a second task corresponding to the second task information; in the process that the target user executes the second task, obtaining second physiological data of the target user; and processing the second physiological data by using a second emotion recognition model to obtain emotion recognition information. According to the method, a self-adaptive task arrangement scheme is adopted, the emotional tendency stably existing in the user can be deeply stimulated and explored, and long-time emotions can be accurately recognized.

The invention discloses a vacuum pump cooling control system and method based on data analysis, and belongs to the technical field of vacuum pump cooling. The system comprises a control module, a data acquisition module, a database, a model analysis module, an intelligent calculation module, an intelligent adjustment module and an interaction module. The control module is used for controlling the vacuum pump and the cooling device; the data acquisition module is used for acquiring parameter data of the vacuum pump and acquiring operation data in the operation process of the vacuum pump; the database is used for storing historical data; the model analysis module is used for establishing a vacuum pump temperature analysis model and fitting a curve of a vacuum pump cooling effect under different cooling liquid flows and temperature differences; the intelligent calculation module is used for calculating the cooling liquid flow needing to be adjusted in the cooling device at the next moment; the intelligent adjusting module is used for dynamically adjusting the flow of the cooling liquid; and the interaction module is used for providing a man-machine interaction platform and performing digital display.

The present invention relates to the technical field of power grid fault diagnosis, and specifically to a power grid fault diagnosis method, system, device and storage medium. After preprocessing and synchronous compression wavelet transform processing are performed on collected original fault recording data and fault recording simulation data, fault features are obtained. The fault features are successively subjected to full convolution mask processing and decoding processing and input into a power grid fault diagnosis model for model training to obtain a trained power grid fault diagnosis model. Shallow feature extraction is performed on newly input fault recording data, and then multiple convolution processing is performed to obtain deep features. Then, non-parameter attention processing is performed, and weighted deep features are obtained after fusion processing with the deep features. After downsampling processing, the final weighted deep features obtained are fully connected, and the corresponding fault type labels are output, which can improve the accuracy and efficiency of power grid fault diagnosis.

The present invention relates to the technical field of big data analysis, and provides a user credit analysis system based on big data; a data collection module of the system collects structured data and unstructured data; sentiment features are extracted from unstructured data such as text, image, audio and video data through a multimodal fusion network, and fusion feature data is generated by combining numerical features in structured data; a strategy combining dictionary annotation and reinforcement learning is introduced to train SVM to obtain a LeELSVM classification model to evaluate user credit risk; through the above steps, the system can comprehensively and accurately analyze user credit status, effectively improve the accuracy and efficiency of credit risk management, and provide strong technical support for intelligent risk control and user management in the financial industry.

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.

A method and device for extracting wind power fault information are provided, the method comprising: obtaining text data about wind power faults; performing entity noun extraction processing on the obtained text data; and determining first extraction information and second extraction information of the text data based on the obtained text data and the entity noun extraction processing result, wherein the first extraction information is used to characterize the fault point where the fault occurs, and the second extraction information is used to characterize the fault-related description for the fault point. The method and device for extracting wind power fault information according to the exemplary embodiment of the present invention effectively improve the text mining effect of the wind power industry.

The invention belongs to the technical field of earthquake phase arrival time picking and image processing, and is an earthquake P wave picking method based on a SAIP-Unet network; the SAIP-Unet network is established on the basis of a codec structure; firstly, a network encoder uses a multi-scale residual module to deeply mine effective features and fuses and outputs them through a multi-scale feature extraction module to accelerate the network convergence speed; then, a spatiotemporal attention mechanism is added to the decoder to generate a high-precision arrival sequence and then perform point-by-point prediction, thereby enhancing the network's perception of arrival features and improving recognition accuracy; compared with traditional methods and deep learning methods, the invention has higher arrival time picking accuracy; and solves the problems of poor efficiency, low accuracy, weak robustness, etc. of existing earthquake arrival time picking algorithms.

The invention relates to the field of financial business risk control, in particular to an illegal fund legalization risk team and user detection method and device, and the illegal fund legalization risk team detection method comprises the steps: obtaining teams divided based on a knowledge graph; whether each member in the team hits the early warning rule or not is judged, different machine learning models are matched according to whether the early warning rule is hit or not, the illegal fund legalization risk probability of each member in the team is obtained, and therefore the illegal fund legalization risk detection result of the team is determined. According to the method, the problems that the quantitative analysis of the illegal fund legalization risk of the team is difficult, the individual illegal fund legalization risk detection effect is poor, and the cost is high are solved.

The invention relates to the technical field of anti-compression peptides, in particular to a blood vessel anti-compression peptide recognition method combining prior knowledge embedding and multi-view enhancement, which comprises the following steps: constructing an ACEIP sequence data set, a nonACEIP sequence data set and an ACE sequence data set, and preprocessing; constructing feature vector codes of the peptide sequences by utilizing the priori knowledge similarity and the molecular docking adaptation degree; and taking coded vectors of ACEIP and nonACEIP sequences as input, and constructing a Deep4ACE model which comprises a feature enhancement module, a model learning module and a model prediction module and is used for predicting the ACEIP and the nonACEIP. The method solves the problems that an existing method utilizes sequence similarity search, molecular modeling and the like, focuses on a primary structure of the peptide, neglects interaction between a space structure and a receptor, and is high in false positive rate of the identified compression-resistant peptide.

The present invention provides a method, device, equipment and storage medium for image processing, the method comprising: obtaining an image to be processed sent by a user; determining the scene to which the image to be processed belongs according to the environment in which the image to be processed is generated, and extracting feature information of the image to be processed by using a feature extraction method corresponding to the scene; establishing an image library for each scene, performing a numbering and labeling operation on new images entering the image library, and after the numbering and labeling operation is completed for the new images entering the image library, similarity calculation is performed between the new images and the old images previously stored in the image library, and the value of each identifier of the new image is adjusted based on the similarity calculation result; after the value of each identifier of the new image is determined, the new image is reviewed according to the value of each identifier of the new image to obtain a processing result; the method of the present invention can improve the recognition ability of risk images in different scenes and improve the recognition efficiency, and reduce the cost of manual review.

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 provides a judicial data time sequence rule type knowledge mining method, which comprises the following steps of: randomly acquiring exponential data of various different case types from a judicial data table as original data for training a time sequence mining model, including various different case quantity data, and taking a set number value as a training set; preprocessing data, and dividing a training set and a test set; correlation analysis is carried out through correlation coefficients and chi-square verification; performing ADF test on the training set to obtain a test result, and performing parameter selection after the data is stable; inputting the training set into various models to obtain a training set prediction result; applying the trained model to a test set to obtain a test set prediction result; and comparing the prediction precision of the multiple models, endowing prediction results of the multiple models with weights based on different characteristics of data captured by different models, and combining the prediction results to obtain a new combined prediction model. According to the method, the data quality is improved, the model prediction effect is improved, and the mining performance of the time sequence mining model is remarkably improved.

The invention relates to the field of distributed optical fiber sound wave sensing foreign matter intrusion monitoring, in particular to an urban cable network third-party intrusion positioning and recognition method. According to the method, the capturing capability of the model for dynamic intrusion event positioning information is improved through a trajectory tracking image processing algorithm, the mining capability of the recognition method for intrusion event multi-scale information is improved through ViT, and the recognition robustness is improved. The problem of accuracy degradation caused by unbalanced data set sample category is solved through balanced random extraction; and a Nesterov acceleration algorithm based on learning rate dynamic change is used to improve the convergence speed of the network model.

The present application relates to a kind of gamma spectrum based on branch fusion network's spectrum and dose prediction method, using Monte Carlo method to construct the model consistent with actual detection system, obtain the single-energy response spectrum under different energy gamma radiation, and establish the response relationship between energy spectrum and air absorption dose;Through the construction of detector response matrix and energy spectrum superposition principle, generate multi-energy mixed energy spectrum and corresponding dose label data set, while covering point source and body source radiation scene.Based on the data set, establish the spectrum model based on residual network, realize the inversion reconstruction of each energy component in mixed energy spectrum, to construct multi-branch feature fusion neural network to realize the nonlinear mapping from spectrum to dose rate.Model is based on homologous data progressive drive, output energy spectrum structure information is used to output dose information after the information, realize the energy composition and dose level collaborative representation of radiation field.It avoids complex inversion algorithm, improves the applicability and stability of model in complex radiation field.

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 invention belongs to but not limited to the technical field of topic mining, and discloses a Wasserstein auto-encoder-based network event topic mining method and system, a Wasserstein auto-encoder-based neural topic model EWTM is constructed, text data in an event is input, the text data is firstly subjected to data cleaning, word segmentation and stop word removal operations, and word bag representation is obtained; in each training period, carrying out encoding operation on the word bag representation to obtain a topic vector of the document; sampling from the hidden variables by using beta distribution to calculate MMD loss; calculating reconstruction loss, and finally obtaining total loss; carrying out back propagation, and carrying out parameter updating by using an optimizer so as to optimize the EWTM model; the process is continuously iterated until a specified training cycle number is reached. According to the method, the theme of the social network event can be automatically discovered and extracted, so that the core information of the event and the focus of user attention can be better understood.

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.