43 results about "Probability model" patented technology

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.

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.

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 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.

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 application discloses a movable array element anti-interference position beam joint method facing unknown direction, introduces movable array elements, and makes array geometry structure be treated as adjustable optimization variable in deployment stage. By changing equivalent array element spacing and pattern structure of the array, the separable degree of expected signal and interference signal incident direction on the spatial response is improved, and the destructive influence of strong interference on the array output when falling in the high side lobe / grating lobe direction of the array is reduced. In each candidate position, an adaptive beam forming process with a pilot sequence as a reference is adopted to directly generate a beam forming weight vector corresponding to the position, so that the mean square error of the receiving output in the pilot interval is minimized. The "movable array element position-performance index" is modeled as a target function to be optimized, and a global adaptive search method based on a probability model is adopted to select the next evaluation position in an iterative manner, instead of exhausting evaluation on all candidate positions.

This invention discloses a system for identifying and warning of minors in special scenarios based on probability confidence, relating to the field of data analysis. It includes: a data acquisition module, used to dynamically adjust parameters according to the ambient light at the entrance of the system-configured location and the shooting angle, to acquire facial and body feature image data of the object to be identified; and an extraction module, used to receive the image data acquired by the acquisition module, extract facial proportions, facial contours, body lines, facial skin texture, and body proportion information from the image data, and construct a feature vector set. This invention dynamically optimizes acquisition parameters based on ambient light and shooting angle to ensure image data quality, comprehensively extracts multi-dimensional key information such as facial proportions, facial contours, and body lines, and quantifies and constructs feature vectors. Through dynamic weight allocation, it strengthens the role of high-discrimination features, and combined with a probability model of minor characteristics, it achieves accurate matching calculations and outputs a reliable probability confidence value.

The invention relates to a method (100) for controlling a software update, in particular OTA or flash updates, for a vehicle. The method (100) comprises: - Determining the necessary duration for performing a software update, - Determining a prediction of a vehicle's inactivity phase using a predictive model; - Determining the probability of error using a probability model; - Comparing the time required to perform the software update with the prediction of the vehicle's inactivity period; - Comparing the determined probability of interference with a predetermined threshold; - Initiating a software update based on the comparisons.

The application discloses a kind of wetland remote sensing image semantic segmentation methods based on double-layer object-level Markov random field and fuzzy area rejudgment, comprising the following steps: first, input remote sensing image is divided into a original image and four mutually overlapping subzone images, respectively on original layer and subzone layer performs superpixel segmentation, constructs region adjacency graph, feature field and label field;Then, a double-layer object-level Markov random field probability model is established, and the alternating optimization of first joint update and then independent update is performed;The temporary segmentation result of original layer and subzone layer is projected and compared, the fuzzy area set is defined, and semantic rejudgment is carried out;Finally, according to the convergence condition, the final pixel-level semantic segmentation result is output.Compared with single-layer object-level Markov random field method, the application can simultaneously use global context and local detail information, improve the segmentation accuracy and stability of complex wetland transition area, small target area and semantic fuzzy area.

This invention discloses a multimodal emotion recognition method based on uncertainty probability modeling and expert product, comprising: acquiring original signal sequences of multiple modalities and extracting features from the original signal sequences of each modality to obtain initial features for each modality; encoding the initial features for each modality to obtain features for each modality; performing uncertainty-aware probability modeling on the features for each modality to obtain a latent distribution for each modality, wherein the latent distribution for each modality is a Gaussian distribution, wherein the mean of the Gaussian distribution represents the semantic content of the modality, and the variance characterizes the uncertainty of the modality; employing an expert product fusion method to fuse the latent distributions of multiple modalities to obtain a fused latent distribution, wherein the fused latent distribution has a fused mean and a fused variance; and mapping the fused mean to obtain the emotion prediction result. This invention can achieve more accurate and reliable multimodal emotion recognition.

Entropy coding a sequence of transform coefficients includes determining a predictor value corresponding to a transform coefficient, selecting a probability model from a set of pre-defined probability models based on the predictor value, and entropy coding a symbol associated with the transform coefficient using the selected probability model. The predictor value can be calculated based on a previous predictor value used for coding an immediately preceding symbol associated with an immediately preceding transform coefficient of the sequence of the transform coefficients. The predictor value can be further calculated based on the immediately preceding symbol.

This invention discloses a method and system for calculating the time-varying reliability of cable corrosion fatigue in cable-stayed bridges. The method includes establishing and validating a finite element model of the cable-stayed bridge; simulating the time history of fluctuating wind speeds in the main girder and main tower using the harmonic synthesis method; obtaining the cable stress time history through buffeting analysis; establishing a probability model of equivalent stress amplitude and cycle number using the rainflow counting method and Miner's theory; constructing a probability model of the depth of dangerous pits and corrosion depth of steel wires under different corrosion degrees based on measured data; establishing a multi-stage series formula coupling pit evolution, pit-crack transformation, and crack propagation; constructing a limit state equation with a 2% wire breakage rate as a threshold; calculating the time-varying reliability of the cable under different wind speeds and corrosion degrees using random sampling; and statistically analyzing the mean and standard deviation of corrosion fatigue life. This invention accurately reflects the wind-corrosion coupling and multi-stage failure mechanism, is computationally reliable, and has strong versatility, making it suitable for safety assessment and life prediction of cables in various types of cable-stayed bridges.

The application discloses a content pushing method and device, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring a pushing object data set, wherein the pushing object data set comprises a plurality of pushing objects and original data corresponding to each pushing object; inputting the original data into a trained probability model to obtain a machine replacement and repurchase rate corresponding to the original data output by the trained probability model, wherein the machine replacement and repurchase rate is obtained based on a machine replacement rate corresponding to the original data and a repurchase rate corresponding to the original data; determining a target pushing object from the plurality of pushing objects based on the machine replacement and repurchase rate; and pushing content to the target pushing object. The application obtains the machine replacement and repurchase rate corresponding to the pushing object through the trained probability model of multiple tasks, and obtains the target pushing object of the content based on the machine replacement and repurchase rate of the pushing object, thereby improving the accuracy of content pushing and reducing the cost of content pushing.

The application relates to the technical field of bridge monitoring, in particular to a beam bridge action effect analysis and prediction method and system based on big data monitoring, which comprises the following steps: according to strain monitoring data of a bridge, bridge internal forces are backstepped, a time-varying probability model of annual extreme values of the bridge internal forces is established; according to automobile WIM (Weigh-In-Motion) data of the bridge and the time-varying probability model, a proxy model of vehicle loads to main beam internal forces is established; according to historical traffic volume data, a vehicle load prediction model within a preset time threshold in the future is established; the output of the vehicle load prediction model is taken as the input of the proxy model, a probability prediction model of annual extreme values of the bridge internal forces within the preset time threshold in the future is established, and a prediction result of the annual extreme values of the bridge internal forces within the preset time threshold in the future is obtained. The scheme is driven by multi-source data fusion, dynamic long-term probability prediction is carried out, the prediction result of the annual extreme values of the bridge internal forces within the preset time threshold in the future is obtained, and the accuracy, foresight and efficiency of analysis are effectively improved.

This invention discloses a method and apparatus for identifying electric vehicle user preferences based on historical behavioral data analysis. The method first collects historical charging order data from electric vehicle users, extracts statistical features of variables to generate a standardized dataset, then constructs a total utility expression using random utility theory, and builds a user choice probability model based on this expression using a binary logit model. Subsequently, based on historical order records in the standardized dataset, the charging selection probability is statistically calculated, and the user choice utility is calculated using a set formula based on the probability model. Finally, a Lasso regression model is trained using the standardized dataset and user choice utility to determine the undetermined parameters of the total utility expression. The influence of features is quantified through parameter weights, completing user preference identification and enabling charging choice prediction under a given environment. This invention solves the problems of existing technologies, such as reliance on questionnaire surveys, susceptibility to bias, lack of real historical data support, and difficulty in quantifying the influence weights of features.

Techniques for video data processing are disclosed. Probabilities of a probability model for a current frame are initialized based on a probability model associated with a reference frame. Further, counts of the probability model for the current frame are initialized based on prior counts from the probability model associated with a reference frame. The probability model for the current frame is subsequently updated based on these initialized counts. The counts may be initialized by applying a function to the prior counts, such as retaining three-quarters of the prior counts.

The application provides a thick alluvium controlled drilling trajectory optimization method, system and storage medium, the method comprises the following steps: generating a smooth candidate drilling trajectory by a first derivative continuous spline interpolation function, establishing a three-dimensional geomechanics model coupled with stratum parameters, and setting the wellbore stress meeting the rock strength criterion as a first hard constraint; performing probability modeling on geological risks to delimit boundaries, setting a safety distance as a second hard constraint, constructing a weighted spatial anisotropic drilling comprehensive cost objective function, fusing a trajectory length, a torque drag and a wellbore instability risk index, adopting a global optimization algorithm to minimize the comprehensive cost under the double constraints, solving optimal control point parameters, and interpolating to generate an optimized drilling trajectory.

This invention discloses a nested representation 3D reconstruction method based on a dynamic Gaussian framework, belonging to the field of 3D reconstruction technology. The method includes the following steps: acquiring a dynamic 3D data sequence of a dynamic 3D scene; constructing a temporal feature sequence; defining a dynamic kernel function and updating parameters; modeling and optimizing the dynamic Gaussian process; and deriving the posterior prediction distribution of the Gaussian process based on Bayesian inference. This invention achieves full-scale feature capture based on multi-scale nested features and adaptive weighted fusion of information entropy; designs a time-dependent dynamic kernel function to construct a Gaussian process probability model to complete accurate reconstruction inference; and achieves joint iterative optimization of feature weights and kernel parameters through closed-loop feedback of prediction errors. It combines the comprehensiveness of multi-scale features, the adaptability of dynamic modeling, and the robustness of closed-loop optimization, significantly improving the reconstruction accuracy and detail reproduction of dynamic 3D data. It is applicable to various scenarios such as dynamic point clouds and dynamic meshes, and has strong engineering practical value.

Techniques for determining a likeliness that a patient may incur an adverse health event are described. An example technique may include utilizing a probability model that uses as evidence nodes various diagnostic states of physiological parameters, which may include one or more subcutaneous impedance parameters. The probability model may include a Bayesian Network that determines a posterior probability of the adverse health event occurring within a predetermined period of time.

The present application relates to a kind of silicon carbide matrix composite damage monitoring methods based on resistance change, belong to composite damage monitoring technical field, the probability model of fiber failure in the resistance model composite is coupled to obtain composite damage monitoring model, the damage state of composite is monitored and evaluated in real time based on the composite damage monitoring model, ensure the service safety and reliability of composite, effectively predict the remaining useful life of composite, prevent the occurrence of catastrophic failure.

The application discloses a risk feature extraction method for a main microgrid, and comprises the following steps: firstly, constructing a new energy output probability model and a system element operation model, and generating multiple system operation scenarios by using a sequential Monte Carlo method; then, determining an active power and reactive power dispatching optimization model, wherein the active power optimization takes the minimum system operation cost as an objective function, and the reactive power optimization takes the minimum system operation network loss as an objective function; subsequently, determining decision variables and constraint conditions of the dispatching evaluation model, and solving system state physical quantities by power flow calculation; then, constructing a risk criterion, determining a risk state data set of each scenario, inputting a random forest algorithm model to quantitatively analyze the risk importance of system features. Finally, determining a risk quantification evaluation method, and constructing a multi-level risk index system according to system risk features. The application can identify key influencing factors under a risk scenario.

The present application relates to the technical field of geological mineral exploration, in particular to a space-air-ground integrated deep mineral prediction system based on Bayesian network, comprising a data layer, a fusion modeling layer, a prediction visualization layer, a decision optimization layer and an interaction layer. The data layer realizes integrated integration and standardized processing of space-air-ground multi-parameter data; the fusion modeling layer constructs and iteratively updates the Bayesian network model, and generates the posterior three-dimensional geological-metallogenic probability model; the prediction visualization layer calculates the favorable degree of prospecting and uncertainty and realizes three-dimensional visual display; the decision optimization layer outputs the optimal drilling scheme based on the partially observable Markov decision process and supports dynamic closed-loop updating; the interaction layer provides human-computer interaction and permission management. The present application realizes seamless linkage of data processing, modeling, prediction and decision-making, significantly improves data flow and decision response efficiency, reduces deep prospecting risk and cost, and has strong knowledge reuse and engineering promotion value.

The application relates to a TDOA / AOA data supplemented electromagnetic spectrum map construction method. The method comprises the following steps: a measurement point collects a received signal to determine the received signal strength of the measurement point to obtain TDOA measurement data and AOA measurement data, a probability model is constructed to probabilistically update an electromagnetic spectrum map of a target region, a posterior probability distribution of a signal source position is obtained, a signal source position corresponding to a maximum value of the posterior probability distribution is taken as a candidate signal source position, and the received signal strength of the candidate signal source position and the received signal strength at other non-measurement point positions are estimated; a candidate point set is randomly generated in the target region, a candidate point with the maximum target function value is selected as a target point and is added to an accurate data set; after adaptive mixed kernel function optimization parameters are constructed, a Bayesian Kriging method is used to interpolate and output an electromagnetic spectrum map of the target region after supplement, and the electromagnetic spectrum map construction precision is improved.

The application provides a railway rail joint failure time prediction method under multi-crack coupling, relates to the technical field of rail joint prediction, and comprises the following steps: stress intensity factors are calculated based on crack propagation test data, a deterministic relationship between crack length and loading times is established by combining Paris law, and a specimen expansion random model is constructed; the specimen expansion random model is expanded at the component level according to a weight function, and a component expansion random model is constructed; based on the component expansion random model, the time distribution of a single crack degradation amount reaching a threshold value is calculated through a preset crack failure threshold value and a Wiener process model, and a crack failure distribution is obtained; each crack failure distribution is connected according to a connection function, a multi-crack joint probability model is established by combining a competing failure mechanism; and the failure time distribution function of the joint under the multi-crack coupling competition condition is predicted based on the multi-crack joint probability model. The application solves the problem of rail welded joint fracture failure.

This invention discloses a method and system for precise positioning of cattle in a pen. The method involves deploying a Bluetooth beacon network within the pen, collecting RSSI signal strength data and RTT ranging data between positioning tags and each Bluetooth beacon node, and fusing the data using a secondary improved algorithm for edge estimation based on independent set queries to generate an initial set of cattle position coordinates. A grid map is then established based on the pen's structural features, and optimized using a low-diameter wiring decomposition technique and a fully dynamic algorithm. A static structure database of pen locations is established, and a Bayesian probability model is constructed using the initial position coordinate set to generate a mapping relationship between cattle and pen locations. The positioning results are optimized using an adaptive robust resettable flow algorithm to generate the final positioning result. A virtual geofence is then established based on the final positioning result to monitor and generate real-time status warning information for the cattle.