179 results about "Probability model" patented technology

The invention provides a steel plate surface defect image generation method based on a de-noising diffusion probability model and a visual Transform, relates to the technical field of industrial surface defect detection, and aims to solve the problems of low quality of generated samples, lack of detail richness and insufficient global dependency relationship modeling capability in the conventional defect image generation method. The performance improvement of a defect detection algorithm is limited; according to the generation method provided by the invention, by introducing the ViT model, the capability of capturing the global dependency relationship in the image by the model is remarkably enhanced, the limitation of the traditional DDPM in modeling the global structure of the image is overcome, the diversity and quality of the generated image are effectively improved, and the method is suitable for further improving the modeling precision of a complex defect structure. A channel-space self-attention module is designed, and the CSSAM of the module can dynamically adjust the attention between different space regions and channels, so that the details of complex defects are finely simulated, and the authenticity and high fidelity of a generated image on the aspects of a global structure and local textures are ensured.

A power consumption prediction and management method and system based on a solid state disk, a medium and a product relate to the field of solid state disks. The method comprises the following steps: predicting the workload intensity of a host in a first preset time window based on an I / O (Input / Output) instruction stream to obtain an expected host workload curve, and determining an expected host idle time period; calculating an expected host power consumption value in the expected host idle time period; extracting internal state parameters of the solid state disk according to the historical operation log data; establishing a background task triggering probability model, and calculating the triggering probability of starting the high-power-consumption background task by the solid state disk in a first preset time window; performing power consumption conflict judgment according to the expected host power consumption value and the triggering probability, and generating a comprehensive predicted power consumption value; and based on the comprehensive predicted power consumption value, determining an optimal target power consumption state, and instructing the solid state disk to be switched to the optimal target power consumption state. By implementing the technical scheme provided by the invention, the stability of state switching of the solid state disk is improved.

The invention discloses a power transmission line microtopography icing risk early warning method and system, and relates to the technical field of power transmission line monitoring, and the method comprises the steps: dividing a power transmission line region, collecting multi-source data, carrying out the processing, analyzing the related parameters of a power transmission line, analyzing the influence of the microtopography on the power transmission line, and extracting the icing features of the data; the method comprises the following steps: constructing an icing probability model and an icing severity model by adopting XGBoost, optimizing a training weight and calculating a calibration score through historical icing data, calculating the calibration score in combination with a weighted PAV fitting non-drop function, carrying out optimization training on the icing probability model, and calculating a load utilization rate based on the icing severity to judge the risk of the power transmission line. According to the method, the icing feature system is constructed through fusion of multi-scale terrain and meteorological factors, the power transmission line is analyzed from the micro-terrain scale, an equivalent regression calibration mechanism based on verification external prediction is introduced, the icing probability model is optimized, and the credibility and stability of a prediction result are remarkably improved.

The invention relates to the technical field of monitoring, in particular to an intelligent camera monitoring data storage and data enhancement processing method, which effectively solves the image quality problem under a complex illumination condition through the combination of illumination invariant feature extraction and a weighted Gaussian probability model, especially the influence of dynamic shadow, uneven illumination and the like. According to the dynamic shielding synthesis mechanism, the dynamic shielding in a real scene is simulated through a Poisson fusion method based on a semantic segmentation result and a physically reasonable shielding object generation algorithm, the limitation of a conventional fixed template shielding method is avoided, the diversity and spatial rationality of shielding objects can be better reflected, and the real-time performance of the real scene is improved. The robustness of the model to shielding is improved; according to the invention, through combination of the cross-scale residual aggregation module and the gating channel-space attention mechanism, multi-scale feature reservation and deep fusion are realized, and detail information under small targets and complex illumination can be effectively captured in a complex monitoring scene.

The invention relates to the technical field of power distribution networks of power systems, in particular to a power distribution network elasticity improvement method based on distributed dynamic recovery, which comprises the following steps: step 1, acquiring operation data of a power distribution network; 2, establishing a topology reconstruction and rolling optimization dual-stage recovery model, taking maximized load recovery as a target, considering network constraints and resource operation constraints, and converting a probability model into a deterministic mixed integer linear programming problem through opportunity constraint conversion; 3, decomposing the model into distributed sub-problems by adopting an alternating direction multiplier method, introducing a boundary variable compensation mechanism to enhance the robustness under communication interruption, and realizing a multi-period dynamic recovery decision based on rolling optimization; step 4; an integer variable processing method combining projection and relaxation iteration is designed, and an induced acceleration objective function is constructed, so that the solving efficiency of a mixed integer sub-problem is improved, and the convergence and calculation speed of a distributed algorithm are ensured.

This invention discloses an intelligent control system for a space-type atomic layer deposition equipment, belonging to the field of intelligent control technology. The system of this invention includes: an acquisition module that acquires the pressure difference and flow rate values ​​of the gas curtain pipeline and performs low-pass filtering to obtain a pure signal matrix; a feature extraction module that calculates the flow field impedance and impedance residual based on this matrix and converts them into an empirical probability distribution vector; a model building module that constructs a degenerate distribution uncertainty set and a scheduling objective cost function based on this vector, and converts them into a mixed integer second-order cone programming model; an offline solution module that discretizes and classifies the dynamic distribution divergence tolerance and solves the model, and pre-generates a scheduling strategy library; and an online control module that looks up tables in the strategy library according to the real-time divergence tolerance and outputs substrate transmission speed control and channel switching commands. This invention transforms the minimization-maximization probability model into a convex optimization problem for offline solution, breaking the computing power bottleneck and balancing control response speed and scheduling decision-making through efficient table lookup.

The present application relates to the technical field of data compression, in particular to a data compression method and system, comprising: an LZ module, a text stream module, a sequence stream module, an interval entropy encoding framework, the LZ module is used for screening repeated data of original data, generating a text stream and a sequence stream; the LZ module screens repeated data through a hash verification method, specifically: calculating a hash value for the input data block, determining repeated data based on hash value comparison to avoid direct data content comparison; the text stream module is used for entropy encoding the text stream; the present application innovatively proposes an interval entropy encoding framework, constructs a more optimal probability model through artificial intelligence and mathematical methods, trains a more optimal finite state machine, and uses the optimal state machine in the compression and decompression process, efficiently solving the problem of slow decompression speed of neural network type methods.

One or more methods, apparatuses, computer-readable storage mediums, and systems for entropy coding vertex information of an edge in a voxelized space of a point cloud are disclosed. Symbols of a neighborhood configuration of a current edge may be determined based on one or more already coded edges. The already coded edges may be selected from a spatial topology of edges. The use of a motion-compensated point cloud for coding centroid residual values may enhance interframe correlation used for determining a context or probability model. This increased correlation may improve the selection of coders, leading to enhanced compression of centroid residual values.

The embodiment of the invention discloses an extended target detection method, belongs to the technical field of radar detection, and solves the problem that the detection performance is reduced due to the fact that excessive noise is introduced or target energy is omitted during energy accumulation in an existing extended target detection method. Comprising the following steps: constructing a dynamic planning accumulation detection model of a distance extension target based on an echo matrix; on the basis of the minimum energy loss criterion, balancing parameters are configured for the value function, a double-probability joint constraint optimization model about the target energy and the noise energy is established, and the balancing parameters are determined by solving the optimization model; updating a value function and a state transition matrix of the joint state variable among the plurality of pulses through recursive operation based on the trade-off parameter; and for the value function obtained after updating is completed, extracting a corresponding energy ridge line, constructing an approximate probability model of the variation amplitude of the energy ridge line, and obtaining a target extension length value by solving an optimal variation threshold of the approximate probability model under a preset false alarm probability.

A mechanical arm grabbing attitude estimation method based on a de-noising diffusion probability model aims at the problems that a traditional grabbing method outputs a single pose and does not have the generation capacity, the de-noising diffusion probability model is adopted for modeling probability distribution of grabbing attitudes, and multiple grabbing attitude candidates with high quality and reasonable structures can be generated in the reasoning stage; and the grabbing diversity and robustness in a complex environment are greatly improved. And meanwhile, a scoring network is introduced as a post-processing module, and the grabbing feasibility of each candidate attitude is estimated in combination with target point cloud and attitude features, so that the judgment capability of the model is further improved.

The invention relates to the technical field of body sensing, in particular to a body intelligent super-flexible wire harness sensing system, which comprises a fiber response acquisition module, a state monitoring and correction module, a feature fusion module, a topological field reconstruction module and a control instruction generation module. According to the method, accurate extraction of the fiber response points is achieved through comparison of differential operation and the reference displacement, the bending position and angle change can be recognized in time and corrected in the threshold exceeding state, noise in signal transmission keeps stable after being weakened through a numerical method, and the stability of the fiber response points is improved. Further performing weighted integration on the deformation characteristics in multi-scale fusion to enable touch and deformation information to form continuous mapping under the same perception distribution, and finally positioning an action center through a probability model and outputting a topological mapping image, so that accurate capture and spatial position identification of an external force peak value can be realized in a complex environment, and the accuracy of the external force peak value is improved. And the sensitivity of the flexible wire harness to fine mechanical changes and the integrity of global perception are improved.

The present application belongs to the field of rail transit signal technology, and specifically relates to a rail circuit interference test analysis method, system and device, aiming to solve the problems of difficult accurate positioning of mixed interference sources, inability to capture occasional faults and subjective diagnosis. The present application comprises: multi-channel synchronous acquisition and real-time storage of voltage signals and current signals of the rail circuit; real-time processing of the original signals, analysis of different frequency components through high-resolution spectrum analysis, comparison with a preset threshold to trigger an alarm and generate a real-time analysis report in combination with time domain analysis; intelligent analysis of historical data, verification and feature recognition of fault period data through establishment of a probability model of normal working conditions to generate a diagnostic analysis report. The present application can realize accurate separation and positioning of interference sources, automatically capture transient faults, and provide objective and intelligent fault diagnosis, significantly improving the efficiency and reliability of rail circuit fault troubleshooting.

In a test method, first test operations are performed on semiconductor products mounted on a test board to determine whether each semiconductor product is normal or defective. The test board includes a plurality of test channels, and two or more semiconductor products share a single test channel. A test map representing results of the first test operations is generated. The test map is divided into a first region and a second region, and the first region identifies semiconductor products that share the same test channel and have been determined to be completely defective. The second region identifies semiconductor products other than those identified in the first region. Using information of the first region and the second region, a first probability model, and a second probability model, a second test operation is performed to determine whether defects of semiconductor products included in the first region are board-related defects caused by characteristics of the test board.

Disclosed are techniques for initializing probability models in video coding. A single combined probability model for a current frame is generated based on a plurality of probability models determined for each tile of a subset of tiles in a reference frame, where the subset of tiles is fewer in number than a total number of tiles in the reference frame. For each tile of a plurality of tiles of the current frame, a respective probability model is initialized for the respective tile using the single combined probability model as an initial probability model.

The invention discloses a probability model analysis method for a secondary accident of an over-limit transport vehicle, and the method comprises the following steps: obtaining traffic accident related data, including numerical data and classification data; inputting the data into a trained over-limit transport vehicle secondary accident probability model, wherein the model is constructed by combining a random forest model after Bayesian optimization with a logistic regression model; and carrying out influence analysis on a model prediction result through an SHAP interpretation framework. According to the method, the interpretability of logistic regression and the nonlinear modeling capability of the random forest are fused, and the model precision is improved by combining Bayesian optimization, so that accurate prediction of the secondary accident probability of the over-limit transport vehicle and quantitative analysis of key influence factors are realized, the blank of model research in the field is filled up, and the method has a wide application prospect. And a scientific basis is provided for traffic safety management and accident prevention.

The invention relates to the technical field of electric power systems, and particularly discloses an electric vehicle cluster multi-market collaborative transaction decision-making method based on double-layer optimization, and the method comprises the steps: integrating dispersed EV charging behaviors into a virtual energy storage unit, and firstly building an energy state and a power boundary of a cluster; secondly, describing uncertainty caused by user behaviors through a probability model; and finally, deducing the auxiliary service capacity which can be provided by the cluster on the basis of the deterministic constraint. The step of constructing a double-layer collaborative optimization market transaction decision model comprises the substeps of constructing an upper-layer EV cluster participation multi-level market joint clearing model by taking minimization of system power consumption cost as a target function; constructing a lower-layer EVA multi-level market bidding decision-making model by taking comprehensive income maximization as an objective function; and solving the double-layer collaborative optimization market transaction decision model to obtain a decision scheme. The method has the advantages that the multi-market bidding decision can be optimized, the adjustable capability of the EV cluster is fully played, and the economic benefit is improved.

The present application relates to power system power source planning method technical field, especially a kind of multi-region power system power source planning method considering capacity sharing, including the construction load growth driven time sequence uncertainty probability model;Establish the effective capacity refined evaluation model under the random failure of multi-source unit;System capacity distribution analytical transformation based on semi-invariant and series expansion.The present application breaks the limitation of traditional single region independent planning by establishing the capacity sharing mechanism between receiving end and sending end regional power grid.Can dynamically adjust inter-regional power resource allocation according to the degree of capacity scarcity, significantly reduce cost under the premise of guaranteeing reliability.

The invention discloses a probability model-driven smelting furnace life prediction method and system. The method comprises the following steps of collecting multi-source alarm and process data of smelting key components; feature engineering is carried out, degradation features are extracted, and discrete health states are divided; the current health state of the component is accurately recognized under the small sample condition by using the gray correlation degree theory; constructing a state transition probability matrix in combination with a Markov chain, and quantifying the randomness of the degradation process; and predicting the remaining service life of the component by solving an equation set taking failure as an absorption state. According to the method, the problem of life prediction caused by lack of historical failure data is effectively solved, dynamic, quantitative and interpretable evaluation of the residual life of key components such as an oxygen lance, a furnace lining and a flue is realized, and reliable technical support is provided for predictive maintenance decision-making of the smelting furnace.

This invention relates to the field of wind power generation technology and discloses a method, device, equipment, and storage medium for assessing the instability tendency of wind turbine towers. The invention utilizes a preprocessing method to process acquired wind turbine monitoring data, then substitutes the preprocessed data into a wind turbine tower instability tendency probability model. This model comprehensively considers factors such as flange displacement and angle changes at various tower connections, as well as wind speed, operating time, and load, thereby obtaining a more accurate tower instability tendency probability value. Finally, by using judgment conditions to assess the stability of the tower, the invention more comprehensively and accurately reflects the stability assessment results of the wind turbine tower in actual operation, achieving the goal of meeting the current requirements for accurate and real-time monitoring of tower stability in wind power generation systems.

The application relates to the technical field of quantum computing, and discloses a quantum computer probability model optimization processing method and system, which solves the technical problems of low probability distribution processing precision and limited computing efficiency in traditional quantum computing through innovative technologies such as adaptive parameter screening based on a probability amplitude range, dynamic quantum state fidelity monitoring, hierarchical entanglement degree mapping strategy adjustment and adaptive quantum interference optimization. The system core comprises a quantum state probability distribution mapping module, a quantum interference optimization processing unit and a classical-quantum hybrid computing interface. Experimental verification shows that, compared with a classical Monte Carlo method, the method can improve the speed by 127 times in high-dimensional probability model processing tasks such as financial risk analysis and drug molecule structure prediction, while maintaining a computing precision of 99.3%, thereby providing key technical support for practical application of quantum computing in the field of probability model processing.

Methods and apparatuses are described for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into segments in the spatial dimensions and in the channel dimension, each segment including at least one latent tensor element. An arrangement of the segments is processed by a neural network: the neural network includes at least one attention layer. Based on the processed segment a probability model is obtained for entropy encoding or decoding of a latent tensor element.

An example method of video decoding includes receiving a video bitstream comprising a plurality of frames and identifying a set of reference frames for a current frame of the plurality of frames. When the set of reference frames includes more than one frame, the method also includes obtaining respective contexts for the set of reference frames and initializing a current frame context for the current frame by performing a weighted average of the respective contexts. When the set of reference frames includes only one frame, the method also includes initializing the current frame context for the current frame based on a context of the one frame. The method further includes entropy decoding one or more syntax elements for the current frame using the current frame context and reconstructing the current frame using information of the one or more syntax elements.

Embodiments of the present disclosure provide a software testing method and device based on a probability model, equipment and a storage medium. The method comprises: obtaining at least two test operations corresponding to a to-be-tested interface, wherein the test operation is used to trigger a control in the to-be-tested interface; determining a target test operation according to a probability distribution model and the at least two test operations, wherein the probability distribution model is used to represent the probability distribution of interface components that can be covered after different test operations are executed, the probability distribution model is generated according to historical test data, and the target test operation is a test operation in the test operations, which has the largest coverage of a target interface component after being executed; and sending the target test operation to a testing machine to enable the testing machine to test the to-be-tested interface. Since the target test operation has the largest coverage of the target interface component after being executed, testing the to-be-tested interface based on the target test operation can improve the coverage effect of the test and improve the test efficiency and test effectiveness.

The present application relates to the field of robustness and security evaluation of deep neural networks, and in particular to a kind of adversarial sample generation method based on multi-space probability enhancement, which introduces two random data enhancement branches in the adversarial sample generation method, each branch realizes image random cropping and filling and random color transformation based on pixel space and HSV color space respectively, and controls the returned image sample by constructing a probability model, while increasing the diversity of original samples, reduces the dependence of adversarial samples on original data set, thereby improving its transferability.

The application relates to the technical field of air transportation management, and discloses a dynamic determination method and system for flight check-in closing time, aiming to solve the problems of insufficient guarantee resource utilization and inaccurate operation risk control of the existing method. The scheme mainly comprises the following steps: obtaining the calculated wheel blocking time and operation success probability parameter of a target flight from an airport collaborative decision system; calling a passenger and baggage path time probability model; calculating an execution key time limit; determining a quantile point based on the operation success probability parameter, calculating a path quantile point time consumption through the probability model; calculating the latest check-in time of the passenger and baggage paths respectively, and taking the earlier one as the theoretical latest check-in time; and finally combining a safety buffer time to obtain the flight check-in closing time. The application effectively prolongs the check-in service window and significantly improves the ground guarantee resource utilization efficiency under the premise of ensuring the punctuality rate of the flight.

This invention relates to a Bayesian trajectory confidence estimation method and apparatus based on crowdsourced map aggregation, comprising: registering and tile-slicing map fragments using the ICP algorithm based on trajectory data sampled multiple times; rasterizing the tiled map fragments and generating rasterized trajectory density according to the trajectory direction; forming road vectors based on the raster and trajectory direction and establishing a correlation with the original trajectory data; fitting a probability model based on the density generated when generating road vectors and sampling to obtain a posterior distribution; and calculating the trajectory confidence value based on the posterior distribution. This invention significantly improves computational efficiency by using trajectory density and direction division as the primary input format, rather than directly substituting trajectory coordinates and other information into a complex model for calculation.

This invention discloses a method for optimizing the dynamic transmission error distribution characteristics of a harmonic reducer, comprising: establishing a static transmission error probability model to obtain the probability distribution of the overall static transmission error; constructing a dynamic transmission error mathematical model considering static transmission error and dynamic parameters; constructing a high-precision surrogate model of dynamic transmission error including the probability distribution of static transmission error and the range of dynamic parameters; obtaining the probability distribution of dynamic transmission error; and dynamically adjusting the range of dynamic parameters based on a particle swarm optimization strategy to find the parameter range that optimizes the dynamic transmission error distribution. By introducing static transmission error into the dynamic model of the harmonic reducer, considering the influence of the processing and assembly of the harmonic reducer on the transmission error, a probability-range hybrid uncertainty model is used to mathematically describe the probability distribution characteristics of static transmission error and the range of dynamic parameters, and a Chebyshev polynomial method is used to construct an approximate model of dynamic transmission error.

The invention provides a user portrait construction method under an AI platform, and belongs to the technical field of user portray.The method comprises the steps that microscopic interaction data are obtained through a user behavior collector, and a behavior state vector set is constructed according to a time sequence; a probability model and an interest energy function are established based on a Maxwell-Boltzmann distribution principle to automatically identify and filter noise data, and sparse matrix decomposition is adopted to project filtered clean data to a low-dimensional semantic feature space. A semantic enhancement model is utilized to perform clustering analysis on high-quality behavior data to identify a real user interest mode, a user individual graph structure based on semantic association is constructed through a knowledge graph technology to accurately express user preferences, and MCP protocol packaging is adopted to realize fusion processing of clean microscopic behaviors and accurate macroscopic features. The technical problem that the accuracy of the formed user portrait is not enough due to the fact that the user microcosmic behavior data is easily interfered by noise is solved.

The invention discloses a polynomial chaos expansion wind power plant generating capacity prediction method and system fused with an active learning algorithm, and the method comprises the steps: obtaining a small number of parameter samples of a wind power plant through a Latin hypercube sampling method, generating wind rose data representing the statistical characteristics of wind climate through wind direction sector division and wind speed interval joint statistics, and carrying out the prediction of the generating capacity of the wind power plant. Therefore, a probability model of wind speed and wind direction is established, a key wind regime area with the largest contribution to prediction precision is automatically identified and calculated, a polynomial chaos expansion proxy model building module is formed, an active learning module fusing exploration and utilization criteria is introduced, and rapid and accurate prediction of the generating capacity of the wind power plant is achieved. According to the scheme, the simulation cost can be remarkably reduced, the calculation efficiency is greatly improved on the basis of ensuring the prediction precision, the output uncertainty can be effectively quantified, and efficient and reliable technical support is provided for layout optimization, operation evaluation and global sensitivity analysis of the wind power plant.

The invention provides an inverse reinforcement learning automatic parking method and system based on driving habits. The method comprises the steps that an expert parking state data set is constructed according to expert tracks under typical parking working conditions; constructing a maximum entropy probability model based on an expert track according to a parameterized reward model based on linear feature combination; by utilizing a maximum entropy inverse reinforcement learning algorithm, optimizing and solving a weight vector of a reward function in the maximum entropy probability model by maximizing a log-likelihood function of an expert track, and obtaining an optimal reward function; based on the optimal reward function, adopting a depth deterministic strategy gradient algorithm to train a strategy network so as to obtain an optimal parking strategy; and according to the optimal parking strategy, a two-stage parking control architecture is adopted to execute parking control on the vehicle. According to the method, the learning efficiency and convergence stability of automatic parking are remarkably improved, the smoothness of the parking track and the accuracy of final parking are guaranteed, and the reliability and riding comfort of the automatic driving vehicle in the parking process are improved.