240 results about "Probit" patented technology

The purpose is to easily manage abnormal program operation. [Solution] The abnormality management device 1 includes a first learning unit 11 that uses normal data indicating processing resource usage data in which the processing resource usage corresponding to each process ID is normal as training data from among a plurality of processing resource usage data each including the usage of processing resources used in executing a process corresponding to each process ID, and learns parameters of a probability model that outputs a posterior probability that the processing resource usage corresponding to each process ID is normal by maximum likelihood estimation, and a derivation unit 12 that derives a probability distribution of abnormal data indicating processing resource usage data including abnormal processing resource usage based on the posterior probability estimated by the learned probability model, the probability distribution of the normal data, and the prior probability of normality.

The invention discloses a power equipment health evaluation method and system based on time sequence analysis and probability modeling, equipment and a medium, and relates to the technical field of power equipment state monitoring and fault prediction, and the method comprises the steps: obtaining and preprocessing multi-source operation data of power equipment, outputting a predicted value and a confidence interval of a future parameter through a time sequence prediction model, calculating a residual sequence of an actual observation value and a predicted value, fitting distribution through a probability distribution model, establishing a statistical characteristic model of a normal operation state of the equipment, performing anomaly judgment, calculating a health degree index of the equipment based on a deviation degree and a dynamic weight of a monitoring parameter and weighted accumulation, and dividing equipment state grades according to the index. Quantitative evaluation of the health state of the equipment is realized. According to the method, accurate quantification and early abnormity identification of the health state of the power equipment are realized, a reliable basis is provided for predictive maintenance, and the intelligent level and the safety guarantee capability of power grid operation and maintenance are remarkably improved.

The invention relates to the technical field of power system operation and control, and particularly discloses a time-sharing electric quantity prediction method based on a logarithmic load density growth curve, which comprises the following steps of: firstly, performing causal detection and dynamic time-delay optimization on historical load and multivariate external data through convergence cross mapping and mutual information technologies, and constructing a causal time-delay feature set; and the problems of multi-element coupling and time-delay effect quantization are solved. Secondly, fitting a load trend by using time-frequency decomposition in cooperation with a segmented logistic model, extracting dynamic parameters representing a growth rate and a saturation capacity, and endowing the model with a sensing ability for a load evolution stage; then, causal features, growth parameters and load components are deeply fused through cross-domain modulation and a gating mechanism, the nonlinear modulation effect of an external environment on a load mode is explicitly modeled, and finally, a probability interval is generated in combination with quantile regression and residual error correction. According to the scheme, accurate and probabilistic prediction of the time-sharing electric quantity in a complex scene is realized, and the scientificity of an agent electricity purchase decision is improved.

The embodiment of the invention provides a large language model training method and device and a question and answer processing method and device, and the method comprises the steps: obtaining a plurality of samples, enabling each sample to comprise a sample question, a first answer corresponding to the sample question, and a second answer corresponding to the sample question, and according to the similarity between the lexical element of each answer in each sample and the lexical element of another answer, obtaining the lexical element of each answer; determining the weight of lexical elements in each answer, inputting the sample question into a large language model for each sample to obtain first probability distribution and second probability distribution, weighting the probability of each first lexical element in the first probability distribution according to the weight of each lexical element of the first answer, and weighting the probability of each second lexical element in the second probability distribution according to the weight of each lexical element of the second answer; and weighting the probability of each second lexical element in the second probability distribution, and adjusting model parameters in the large language model according to the difference between the weighted first probability distribution and the weighted second probability distribution corresponding to each sample. Based on the method, the quality of model output answers is effectively improved.

The invention provides a privacy protection multi-energy load day-ahead probability prediction method based on a diffusion model, and belongs to the field of multi-energy load prediction of an integrated energy system. Comprising the following steps: S1, acquiring respective energy consumption load data by a local main body, and preprocessing and normalizing the data; s2, dividing the energy consumption data into historical loads and labels, and respectively training two groups of self-encoders-self-decoders; s3, the local main body uploads the latent variables obtained after coding to the cloud; s4, grouping and integrating latent variables by the diffusion model of the cloud, and constructing a joint probability prediction model; and S5, during model reasoning, after a latent variable generated by the cloud is downloaded locally, a final predicted value is obtained through decoding by a self-decoder. According to the method, a prediction framework based on longitudinal federated learning is designed for a multi-energy load probability prediction scene related to a cross-energy form in an integrated energy system, and a diffusion model capable of predicting multi-energy load joint probability distribution is constructed by considering a coupling relationship among multi-energy loads.

The invention discloses a machining parameter self-adaptive tuning method and system, and relates to the technical field of numerical control machining. According to the method, by obtaining initial cutting parameters and cutter parameters of a process planning system and combining machining signals collected by a machine tool in real time, dynamic sensing of the machining process is achieved. A working condition result is output through prediction of a fusion physical model and a data driving model, meanwhile, a real-time signal is processed through a machine learning model to generate a working condition index, the two are combined and then input into an optimization method based on probability modeling, and candidate parameter combinations meeting constraint conditions are obtained and screened. Dynamic threshold monitoring is introduced in the processing execution stage, and parameters can be corrected or retreated in real time when abnormity is detected. And an execution result and processing data are fed back to the process planning system. According to the method, parameter self-adaptive adjustment and optimization can be achieved, prediction precision and machining stability are improved, the service life of the tool is prolonged, risks are reduced, and the method has the continuous optimization capacity and is suitable for intelligent manufacturing under complex working conditions.

The invention discloses a post-earthquake railway structure state evaluation method and system based on multi-source data fusion. The method comprises the steps that a finite element model is constructed according to the structure of a regional railway network, a simulation data set is generated, a physical information neural network model is trained, and a proxy model library is formed; acquiring multi-source observation data, and performing inversion according to the Bayesian theory, the structural damage parameters of the physical information neural network agent model and the multi-source observation data to obtain complete posterior probability distribution of the damage parameters; according to the method, statistical characteristics of damage parameters are extracted from posterior probability distribution, probability grading is carried out on the damage degree of the structure, driving constraint suggestions are generated according to the combination of damage probability grading and specifications, and Bayesian inversion time is reduced from several days to several hours through a physical information neural network agent model, so that the evaluation efficiency is improved; the output of the Bayesian method is probability distribution, the uncertainty range of the evaluation result is clearly displayed, and the uncertainty is quantified.

The invention discloses a multi-dimensional distribution offset adaptive threshold detection method and system, and the method comprises the steps: obtaining real-time data, extracting a multi-dimensional statistical feature, and obtaining a feature vector; based on historical normal data, using an expectation maximization algorithm to train a Gaussian mixture model, and determining parameters to obtain a normal distribution model; inputting the feature vector into the model, and calculating a probability value of the feature vector belonging to normal distribution as a first offset judgment index; based on the real-time data distribution of a plurality of detection objects in the same group, the distribution difference of any two objects is calculated by using a Wasserstein distance, and the similarity between the objects is obtained; and constructing a similarity network and calculating connectivity as a second offset judgment index. Setting a fixed-length sliding window, dynamically updating two indexes in the window, and obtaining a first self-adaptive threshold value and a second self-adaptive threshold value; and when any index is lower than a corresponding threshold value, determining distribution offset and giving an alarm, and updating model parameters in real time by using an incremental expectation maximization algorithm. According to the invention, accurate detection and intelligent analysis of data distribution offset are realized.

Provided are techniques for the calibration of distillation learning from a teacher model to a student model. Specifically, the present disclosure proposes systems and methods that provide convergence with both high quality and speed. That is, example proposed systems both enable the distillation loss to be minimized at the probability mean value in the probability domain of the teacher's predictions distributions while also providing a loss that is nicely (e.g., symmetrically and / or strongly) convex around an optimum in the logit and / or probability domains (e.g., including far from the minimum) to encourage fast convergence of gradient based methods (e.g., irrespective of distance from the minimum).

The invention belongs to the technical field of uncertainty probability characterization analysis, and discloses a thermoplastic composite material leading edge structure design allowable value probability characterization method and system under a small sample condition, and the method comprises the steps: defining a plurality of candidate probability distribution models; fitting each model based on the original sample data and calculating an AIC value and a BIC value; a dynamic weight factor alpha is calculated according to the sample size n, and then a hybrid information criterion HIC value is calculated; generating a plurality of sample sets through Bootstrap self-service sampling, recalculating the HIC value on each sample set, and counting the selected optimal frequency of each model; and determining an optimal probability distribution model according to the frequency, wherein the optimal probability distribution model is used for representing a design allowable value. According to the method, the dynamic weight factor alpha is introduced, AIC and BIC criteria are effectively unified, optimal balance between prediction precision and model complexity is achieved under the condition of small samples, and engineering practicability and robustness are remarkably improved.

The invention discloses a probability model quantification method for flexibility potential of a building air conditioner, which comprises the following steps of: extracting an upper and lower bound cumulative distribution function by adopting a probability box method, and describing a flexibility fluctuation range of an air conditioning system in an interval probability form; a Wasserstein distance index is introduced, the difference of load probability distribution before and after regulation is quantified, and a flexible potential expected value is represented according to the difference. According to the method, the adjustable load range of the building can be accurately described under the multi-source disturbance condition, and reliable support is provided for flexible resource scheduling and response strategy making.

The invention discloses a probabilistic optimal power flow calculation method based on a second-order cone and unscented transformation, belongs to the field of power system optimization, and efficiently processes the uncertainty of new energy output and load by coupling the probabilistic sampling capability of unscented transformation (UT) and a convex optimization framework of second-order cone programming (SOCP). According to the method, unscented transformation efficient sampling is utilized, a covariance matrix is directly embedded to simplify correlation processing, and accurate probability distribution of network loss, voltage and line power can be output. Test results show that the calculation efficiency is improved by dozens of times compared with Monte Carlo simulation, the error is lower than 3%, and the method is suitable for risk assessment and operation optimization of the power system.

The embodiment of the invention provides a tool determination method and device, equipment, a medium and a product, and relates to the field of data processing. According to the method, the input risk intention is automatically judged by carrying out multi-dimensional compliance detection on the statement input by the user and combining a probability calculation model, and the input safety does not need to be verified by manually contrasting static rules; meanwhile, the credibility and the risk value of the tool are automatically calculated according to the state data of the target tool, and the reliable and low-risk first tool is screened out, so that the complexity of manually sorting tool rules and intervening in complex scene correction is avoided; in the subsequent process, a final adaptive tool can be determined by automatically calculating the deviation degree between user input and the first tool behavior sequence, automatic processing of all links in the whole tool determination process is achieved, and process delay caused by manual intervention is reduced; the problem that in the prior art, tool determination depends on static rules, the process is tedious, and the efficiency is low due to manual intervention is solved, and the tool determination efficiency is improved.

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The purpose is to appropriately manage abnormal communications with a simpler configuration. [Solution] The abnormality management device 1 includes a learning unit 12 that uses the characteristic directions of normal data as training data to learn, by maximum likelihood estimation, parameters of a probability model that outputs the posterior probability that the number of packets received in each time period corresponding to each of the characteristic directions of the normal data is normal; a derivation unit 13 that derives a probability distribution for the characteristic directions of abnormal data that indicates the number of abnormal packets received in each time period that deviates from the range of normal packet numbers, based on the posterior probability estimated by the probability model learned by the learning unit 12, the probability distribution for the characteristic directions of the normal data, and the prior probability of normality; and a calculation unit 14 that calculates a first index value that indicates the degree of spatial agreement formed by the probability distribution for the characteristic directions of the abnormal data derived by the derivation unit 13 and the probability distribution for the characteristic directions of the normal data.

The object is to manage signal abnormalities even when there is little measurement data of the abnormal signal. [Solution] The abnormality management device 1 includes a learning unit 12 that uses the characteristic directions of normal data as training data to learn, by maximum likelihood estimation, parameters of a probability model that outputs the posterior probability that the intensity of each frequency component corresponding to each of the characteristic directions of the normal data is normal; a derivation unit 13 that derives a probability distribution for the characteristic directions of abnormal data that shows abnormal intensities of frequency components that deviate from a normal intensity range, based on the posterior probability estimated by the probability model learned by the learning unit 12, the probability distribution for the characteristic directions of the normal data, and the prior probability of normality; and a calculation unit 14 that calculates a first index value that indicates the degree of spatial agreement formed by the probability distribution for the characteristic directions of the abnormal data derived by the derivation unit 13 and the probability distribution for the characteristic directions of the normal data.

The invention provides a composite beam reliability optimization method based on a failure probability function. The method comprises the following steps: 1) defining a random input variable, a design variable, a target function and a performance function; 2) calculating a failure sample and an extended failure probability based on an autonomous learning Kriging agent model and a Monte Carlo method according to the Bayesian theory; the method comprises the steps of (1) calculating a design parameter failure sample, (2) calculating a joint probability density implicit function on the basis of an adaptive K-nearest neighbor method and autonomous learning Kriging according to the calculated design parameter failure sample, and (3) calculating a failure probability implicit function on the basis of the Bayesian theorem.By means of the method, the problem that in the reliability optimization process, the calculation cost is difficult to bear due to reliability analysis is solved.

The invention discloses a foundation pit horizontal displacement probability prediction method and system based on a sparse Bayesian extreme learning machine, and belongs to the technical field of civil engineering monitoring and artificial intelligence crossing. According to the method, a probability model containing input and output noise is constructed, feature selection and uncertainty quantification are automatically carried out by using a sparse Bayesian framework, and probability prediction of horizontal displacement at the position where a sensor is not arranged is realized. The method can output the prediction mean value and the confidence interval, effectively solves the problems of data sparsity and noise, and improves the prediction reliability and the engineering decision support capability. The method has the advantages of being high in automation degree, high in anti-interference capacity, suitable for actual engineering monitoring and the like.

The invention discloses a machine abnormal sound detection method based on enhanced self-coding reconstruction and probability modeling, and aims to solve the problem that in an existing unsupervised machine abnormal sound detection method based on a generative adversarial network, the time-frequency feature reconstruction result of machine operation sound is too smooth, so that the machine abnormal sound detection capability is insufficient. According to the method, time-frequency feature extraction is carried out on collected machine operation sound signals, modeling is carried out on machine operation sound time-frequency feature distribution under a normal working condition in combination with a probability statistical model, and the time-frequency features of the machine operation sound under the normal working condition are reconstructed and learned by using an auto-encoder of a structure enhancement mechanism. The method realizes unsupervised machine abnormal working condition determination by combining the reconstruction error and the probability determination result, can improve the determination stability and robustness of abnormal sound detection, reduces the model complexity, and is suitable for application scenarios such as industrial equipment operation state monitoring and fault early warning.

Some embodiments provide a method for training a machine-trained (MT) network. The method receives a network comprising a plurality of parameters. The method trains the network by iteratively (i) propagating inputs through the network to generate outputs and adjusting the parameters based on differences between the generated outputs and expected outputs to minimize a loss function with respect to the parameters, (ii) probabilistically projecting the parameters to minimize the loss function with respect to a set of constraints on the weight values, the probabilistic projection treating the parameters as probability distributions, and updating a set of variables of the loss function based on the probability distributions.

The invention discloses a method for constructing a mapping knowledge domain of a metallogenic time-space event fused with a large model, which belongs to the technical field of computers and comprises the following steps of: acquiring multi-source heterogeneous geological data, generating a unified semantic primitive carrying a dynamic credibility weight through multi-modal semantic fusion, constructing a dynamic cognitive energy field based on a probability theory and a dynamics principle, and constructing a mapping knowledge domain of the dynamic cognitive energy field. Releasing a probability event probe in an energy field, generating an initial spatio-temporal event chain containing a plurality of possible paths through potential energy gradient descent and probability exploration, constructing a cognitive isomer system containing an expert simulator, a data insight body and a meta-cognitive arbiter, performing cognitive game on the initial event chain to obtain a game result, and performing cognitive game on the initial event chain. State prediction is carried out based on multi-dimensional health indexes, and predictive self-repairing is carried out on the knowledge graph; by adopting the technical scheme of constructing a dynamic cognitive energy field and a cognitive isomer system for coevolution, dynamic evolution, deep cognitive gaming and predictive self-repairing of the knowledge graph can be realized.

The invention relates to the technical field of data processing, in particular to a threat recognition system and method.The method comprises the steps that a self-adaptive collection module obtains network flow data and operation log output feature vectors; the multi-dimensional rule module generates rule confidence; the statistical modeling module outputs an abnormal probability score; the machine learning module outputs a classification probability in response to the abnormal probability score dynamic selection model combination; the simulation decision module is fused with the multi-source data to execute threat diffusion simulation and output hazard indexes; the grading execution module triggers grading response according to the hazard index; and the feedback optimization module adjusts model parameters in a cross-layer manner. According to the method, noise interference is eliminated through feature optimization, a multi-dimensional model is fused to calibrate an output result, a threat grading mechanism preferentially responds to key threats, and closed-loop feedback is continuously injected into a false alarm data training model, so that the problem of high false alarm rate caused by insufficient training data coverage of a machine learning model in a complex dynamic network environment is solved; security resource allocation is optimized and key threat response delay is shortened.

A system and method include reception of a plurality of code samples and corresponding ground truth classifications, generation, for each of the plurality code samples, of a plurality of perturbed code samples, generation of first probabilities for each of the plurality of code samples and the perturbed code samples using a first classification model, generation of second probabilities for each of the plurality of code samples and the perturbed code samples using a second model, determination of a causal probability for each code sample based on the first probabilities and the second probabilities, determination of a causal performance metric of the first classification model based on the ground truth classifications and the causal probabilities, and presentation of the causal performance metric.

The invention discloses a probabilistic power supply guarantee capability assessment method considering new energy uncertainty, which comprises the steps of obtaining historical statistical data of new energy in different time periods, constructing a new energy output probability density function based on the historical statistical data, and determining new energy probability density distribution; time sequence production simulation calculation is carried out based on the source network load storage calculation boundary in the target research area, and a conventional unit output curve, a tie line power exchange curve, a pumped storage energy output curve and a demand side response working curve are obtained; based on the conventional unit output curve, the tie line power exchange curve, the pumped storage energy output curve, the demand side response working curve and the load demand curve, constructing a power demand curve which needs to be satisfied by new energy output; and based on the power demand curve and the new energy probability density distribution which need to be satisfied by the new energy output, obtaining the power gap probability and the power shortage expectation of the target time period, and carrying out supply guarantee capability evaluation based on the power gap probability and the power shortage expectation.

The invention relates to the technical field of formation data acquisition, in particular to a logging formation information intelligent analysis system which comprises a response model construction module, a dynamic weight generation module, a composite evidence distribution module and a multi-source information fusion module. According to the method, core calibration data are obtained, a probability density distribution function of basic lithologic logging response is constructed through a kernel density estimation algorithm, dependence on a fixed plate and a static cut-off value is eliminated, dynamic probabilistic description of stratum response characteristics is achieved, and then the initial reliability and sensitivity weight of response numerical values are calculated based on distribution; the method is used for adjusting evidence distribution, then calling an evidence theory combination rule to fuse adjusted multi-source information, determining the stratum state according to the highest cumulative reliability, effectively solving the problem of misjudgment caused by response overlapping, and remarkably improving the accuracy and objectivity of stratum lithology and fluid property identification.

The invention relates to a method (100) for determining an uncertainty in connection with motion trajectory predictions of a vehicle (1), comprising the following: - Providing (101) at least one trained machine learning model, wherein the at least one machine learning model is trained to predict motion patterns based on sensor data and assigns ratings that reflect a probability of each predicted motion pattern, - Providing (102) at least two predicted motion pattern distributions (3) by means of appropriate predictions based on the sensor data by the at least one trained machine learning model, - Using (103) a Monte Carlo sampling to estimate an entropy of a respective predicted motion trajectory distribution (3), thereby obtaining an estimate of an aleatory uncertainty, - Using (104) a Monte Carlo sampling to estimate an entropy of the at least two predicted motion trajectory distributions (3), thereby obtaining an estimate of an overall uncertainty, - Determining (105) an epistemic uncertainty by subtracting the aleatory uncertainty from the total uncertainty, - Providing (106) the definite epistemic uncertainty and the aleatory uncertainty for the predicted motion trajectories of the at least one machine learning model. Furthermore, the invention relates to a computer program, a device and a storage medium for this purpose.

The invention discloses an elevator prediction scheduling method and system based on user habit self-learning, and the method comprises the steps: carrying out the statistical analysis based on historical elevator taking event data, and judging whether a floor combination meeting a preset condition exists or not; combining all the independent floors with the floors meeting the preset conditions to serve as a self-learning unit; for each self-learning unit, updating the elevator calling probability of the respective learning unit by using an exponential weighted average algorithm; when the elevator does not have the real-time task, all elevator calling probabilities corresponding to the current time window are inquired, and the self-learning units meeting the triggering condition are extracted as a target candidate set; calculating an optimal pre-stop layer by utilizing a mathematical model based on the target candidate set, and calculating a comprehensive probability corresponding to the optimal pre-stop layer; and calculating an income evaluation function based on the comprehensive probability, and generating an instruction to drive the elevator to run to an optimal pre-stop layer to enter a prediction waiting state when an obtained value meets a condition.

To provide a congestion probability prediction device capable of facilitating power generation control of power generation equipment with non-firm type connection while especially considering the uncertainties.SOLUTION: A disclosed congestion probability prediction device for predicting the congestion of a power system includes: a weather forecast data input unit that acquires weather forecast data regarding the weather a predetermined number of days after the current date; a power system data input unit that acquires demand data regarding electricity demand a specified number of days after the current date and that acquires system data regarding the power system after the predetermined number of days after the current date; a system congestion probability prediction unit that predicts congestion points and congestion probability data of the power system the specified number of days after the current date.SELECTED DRAWING: Figure 1

The invention belongs to the technical field of data filling, and particularly relates to a data completion method based on inverse probability and computer equipment, and the method comprises the following steps: filling a missing data set by using a trained improved machine learning filling model, the improvement comprises that a loss function used for training the machine learning filling model is an improved loss function, a data set in the improved loss function is a data set obtained by weighting each piece of data, the weighted weight of the data is obtained according to a corresponding inverse probability, and the lower the inverse probability of the data is, the larger the corresponding weight is; the process of calculating the inverse probability of the data comprises the following steps: carrying out preliminary filling on a data set for training, calculating the missing probability of each piece of data in the data set subjected to preliminary filling, and calculating the inverse probability of each piece of data according to the missing probability of each piece of data in the data set. The filling capability of the machine learning filling model for non-random missing data is enhanced, and the filling precision of the machine learning filling model is improved.

The invention discloses a semantic feedback guided structure adaptive federated learning method and system and a medium, and belongs to the technical field of federated learning and deep neural network training, and the system comprises a FedBR basic framework, a multi-source feedback statistics module, a block scheduling strategy module and a coverage fair constraint module. According to the method, a probabilistic deep block scheduling strategy is introduced, so that the system can gradually deviate to block combinations with better effects according to accumulated feedback, and a certain degree of online self-adaptive capability is shown in an experimental scene. A time window and exponential moving average non-stationary feedback smoothing mechanism is adopted, the influence of single-round noise and partial observation on strategy updating is reduced, the strategy updating is more stable, and the frequency of strategy oscillation and extreme bias conditions is reduced. And when the probability distribution P is updated, probability distribution smoothness and coverage fairness constraints are introduced, so that extreme conditions that the deep block is not selected for a long time are obviously reduced, and the overall training participation degree of the deep block is improved.