67 results about "Conditional entropy" patented technology

The invention relates to a multivariate time series data abnormal root cause identification method based on a space-time cause and effect diagram, and belongs to the technical field of anomaly detection. According to the method, multi-window expansion causal convolution is adopted for multivariate time series data, mutual information screening is combined, and time embedding covering short-term mutation and long-time dependence at the same time is extracted; non-local space correlation is learned through multi-head self-attention, the directional causal intensity is measured through conditional entropy, and a sparse and interpretable space-time causal graph is generated through normalization-pruning; introducing a causal enhancement graph attention network on the space-time causal graph, and performing multiple rounds of causal propagation updating on node embedding; and calculating a root cause score by integrating the abnormal degree and the causal influence, identifying a key source node in an abnormal propagation path, and realizing accurate root cause positioning of the system abnormality. According to the method, the adaptability to the dynamic behavior mode and the capturing capability to the abnormal driving factor are enhanced, and the modeling precision and the root cause identification capability of the abnormal propagation process are improved.

The invention provides a lottery store violation detection method and system based on multi-modal data fusion, and relates to the technical field of intelligent monitoring, and the method comprises the steps: detecting a current abnormal event, carrying out time sequence perception target detection on monitoring video data, and recognizing violation electric equipment in a video image frame based on adaptive feature enhancement and multi-target tracking. The method comprises the following steps: acquiring time sequence data of current abnormity and illegal electric equipment detection, constructing a time sequence incidence relation of current abnormity, equipment detection and an electric state based on a dynamic causal network, calculating a time-varying weight and instantaneous causal intensity by utilizing conditional entropy increment, acquiring optimal time lag in combination with eigenvector conversion and a dynamic programming algorithm, and determining the current abnormity and illegal electric equipment detection according to the optimal time lag. And weighting the integral of the instantaneous causal intensity and the exponential function of the optimal time delay to obtain an event matching score, and distinguishing a temporary power utilization event and a continuous illegal power utilization event based on the event matching score.

The invention relates to the field of intelligent early warning of guaranteed power supply, and provides an abnormal early warning method and system for a guaranteed power supply system, and the method comprises the steps: obtaining the topological structure, real-time operation data and equipment state data of each node in a guaranteed power supply network, employing the conditional entropy and instantaneous causal entropy calculation technology, precisely evaluating the causal intensity between variables, and achieving the early warning of the abnormal state of the guaranteed power supply system. And a causal adjacency matrix dynamically changing along with time is constructed to reflect a complex causal relationship in the network. Then, in combination with an equipment topological structure and dynamic causal information, multi-scale time sequence features are extracted through feature updating and expansion causal convolution, and a comprehensive feature vector is formed; after the vector is input into the Bayesian neural network, a plurality of prediction value samples are generated through sampling weight distribution, a mean value is used as a prediction result, and the prediction uncertainty is measured through variance. Accurate prediction and timely early warning of potential anomalies of the power supply system are realized, and the stability and safety of the system are effectively improved.

The invention relates to a rolling bearing fault diagnosis method and system, and belongs to the technical field of bearing fault diagnos.The method comprises the steps that a diagnosis network is constructed, and the diagnosis network comprises a feature extractor and a classifier which are connected in sequence; inputting the source domain sample and the target domain sample into the feature extractor in parallel to extract source domain features and target domain features; the weight of the source domain sample is optimized through the source domain feature and the target domain feature, so that the source domain sample with the same category as the target domain sample obtains a higher weight; calculating the cross entropy loss of the source domain based on the weight of the optimized source domain sample, constructing a total loss function in combination with the conditional entropy loss of the target domain, and training a feature extractor and a classifier through the total loss function to obtain a training convergent diagnosis network; and carrying out fault diagnosis on a to-be-diagnosed unlabeled real sample through the trained and converged diagnosis network. According to the invention, the fault type of the rolling bearing can be effectively detected, and the detection precision is high.

The invention provides a remote sensing image change detection method and system based on information entropy, and belongs to the technical field of remote sensing data processing. The method comprises the steps that remote sensing image data and auxiliary data of a target area are acquired and preprocessed, and a plurality of change sub-areas of the target area are extracted based on the preprocessed remote sensing image data and auxiliary data, extracting the characteristic change representing the natural ground feature and the characteristic change representing the artificial ground feature corresponding to each change sub-region; and performing conditional entropy calculation and geographic detector analysis, and outputting a detection result and a driving force analysis result. Two types of feature sets are introduced, natural ground feature feature changes and artificial ground feature feature changes are reflected respectively, the two types of features are matched and verified mutually, interference of abnormal information on change detection is relieved, the changes can be rapidly detected through combination of conditional entropy and a geographic detector, meanwhile, corresponding driving factor explanation is given, and the detection accuracy is improved. And scientific reference is provided for decision-making of related departments.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.

The invention relates to the technical field of natural language processing, and provides a causal double-chain-based large language model illusion detection method and an intelligent question answering method.The causal double-chain-based large language model illusion detection method comprises the steps that for each input question, multiple rounds of independent sampling are initiated, and a response set containing multiple sampling responses is formed; and for the response set, extracting an inference chain and a causal chain, calculating an inference chain conditional entropy, a causal chain conditional entropy and mutual information of the inference chain and the causal chain, and taking a weighted sum of the inference chain conditional entropy, the causal chain conditional entropy and the mutual information of the inference chain and the causal chain as an illusion score. And multi-dimensional accurate recognition of the composite illusion is realized.

A processor-implemented method for estimating uncertainty includes receiving an artificial neural network (ANN) model and a calibration dataset. An upper-bound on a conditional entropy of a data distribution of the ANN model is computed using conformal prediction. The conditional entropy of the model is estimated based on the upper-bound. In turn, the uncertainty of the data distribution of the ANN model may be estimated based on the conditional entropy and a prediction set size.

The invention relates to the technical field of intelligent data processing, and comprises an intelligent algorithm-driven data analysis system, which comprises a feature screening module, a topology backbone extraction module, an information transmission optimization module, a classification boundary adjustment module and a self-adaptive classification hierarchy module. According to the method, the conditional entropy of a data characteristic value is calculated, the fluctuation degree of characteristic information is analyzed, one-way dominant characteristics are screened, interference of low-contribution characteristics is reduced, the topological adjacency relation of data points is constructed, a data classification trunk is optimized, and attribution of the data points is adjusted in combination with local information entropy change, so that a classification structure better conforms to data transmission characteristics; by combining the information entropy fluctuation of the classification boundary and the connection strength of the core data points, the classification boundary division is optimized, the hierarchical stability change rate is combined, the data hierarchical division strategy is adjusted, the classification structure is optimized, the stability and the calculation efficiency of data classification are improved, the classification boundary adjustment is more accurate, and the classification hierarchy can be adaptively adjusted.

The present invention discloses a test-time adaptation method for a calibration-free brain-computer interface, the method comprising the following steps: obtaining labeled training data from multiple source domain users to establish classification models for multiple categories; establishing the classification model, performing Euclidean alignment on the training data of each user, then merging all source domains, training multiple classification models using traditional cross-entropy loss, and obtaining multiple trained source domain models; obtaining the next test sample on the target domain data stream of the current user, performing incremental Euclidean alignment, and inputting the data into the trained multiple source domain models to obtain predicted probability values based on the multiple source domain models on the target domain data; using a spectral meta-learner method to perform integrated prediction of multiple models to obtain the predicted value of the current test sample. Based on the predicted probability value, each model is optimized separately by minimizing conditional entropy and using adaptive marginal distribution constraints within the batch to obtain optimized models adapted to the target domain; the present invention takes into account the real-time application of the cross-user brain-computer interface system, and adaptively adjusts the model without adding a calibration link.

The invention provides a target matching and tracking method and device, equipment and a medium. The target matching and tracking method comprises the following steps: constructing a non-uniform grid map under a polar coordinate system; and distributing the point cloud data acquired by the radar to the corresponding grids. And on the basis of the observation result of each grid, the conditional entropy corresponding to the grid is calculated, and the observation result comprises the observed point cloud or the unobserved point cloud. And determining a plurality of non-empty grids with point clouds based on the conditional entropy corresponding to each grid. A plurality of clusters is determined based on the plurality of point clouds in the plurality of non-empty grids. A plurality of matching cost functions between the plurality of cluster clusters and the plurality of predicted trajectories are determined. And based on the plurality of matching cost functions, determining a target cluster and a target prediction trajectory which are matched with each other. The point cloud data is directly processed under the polar coordinate system, so that the calculation error can be reduced, and the accuracy of point cloud matching is improved. And non-homogenization processing is carried out on the grid map, so that redundant calculation of a long-distance area can be reduced.

The present application relates to a kind of underwater dense jamming source condition based on entropy small volume movement obstacle detection method, which is first decomposed to time azimuth history matrix using LMD algorithm, obtain low rank matrix and sparse matrix;On this basis, respectively establish joint conditional entropy matrix and low rank similarity matrix;Finally, based on the pearson correlation coefficient of low rank similarity matrix and joint conditional entropy similarity matrix, the position of small target in matrix is located, the fast detection and tracking of mobile small target are realized.Compared with the traditional method, the proposed method significantly improves the computational efficiency and the generalization of model.The present application aims to solve the problem of small mobile obstacle detection under the shelter of underwater dense interference near the port.

The invention discloses a deep reinforcement learning actor-evaluator network structure based on double-flow information bottleneck and a path tracking control method for a four-wheel independent steering and independent driving vehicle, and the method comprises the steps: adding a known information bottleneck module in a Critic network before the estimation of a Q value, extracting known information from the known information bottleneck module, and carrying out the estimation of a Q value; designing a training target to minimize a time difference error and minimize mutual information, and constraining a parameter norm; in the Actor network, an unknown information bottleneck module is added in front of a strategy generation module, unknown class information is extracted from the unknown information bottleneck module, and a training target is designed to maximize expected accumulated rewards, maximize mutual information and minimize conditional entropy; in the training process, states and actions in samples are input into a Critic network and a mutual information estimator network, Q value estimation and mutual information estimation are obtained, and Critic network parameters are updated through a minimization objective function; actor network parameters are updated through a strategy gradient theorem and importance sampling so as to maximize an objective function; meanwhile, a mutual information estimator network is independently trained, and maximum estimation of mutual information is achieved through sampling and optimization; in order to realize dynamic adjustment, a weight scheduler is set, coefficients in an Actor objective function and a Critic objective function are dynamically adjusted according to the current training round number and the average return, and a linear attenuation strategy is used for adjustment.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.

The present invention discloses a blast furnace fault diagnosis method based on minimax entropy collaborative training, belonging to the fields of industrial process monitoring, modeling and simulation. First, a dual-view feature extractor is constructed using a deep neural network to extract features from the historical data and the data to be measured of the blast furnace, and its outputs are respectively fed into two classifiers to calculate the cosine similarity between the features and the representative vectors of each furnace condition. The knowledge transfer of the historical blast furnace data is realized by alternately maximizing and minimizing the conditional entropy of the blast furnace data to be measured by the classifier and the feature extractor respectively. When the recognition results of the two classifiers for the blast furnace condition are consistent and at least one classifier has a high confidence level, the output furnace condition label is assigned to the blast furnace data to be measured. The present invention solves the problem of low accuracy of traditional fault diagnosis methods caused by few blast furnace fault samples and large fluctuations in data distribution with the change of working conditions, and can be widely applied to industrial systems with high requirements for the credibility and accuracy of fault diagnosis.

The invention relates to a post competency matching method and device, equipment and a storage medium. The method comprises the following steps: acquiring original data, wherein the original data comprises talent features and post features; calculating a distance vector between the talent feature and the post feature; calculating mutual information and conditional entropy according to talent features, post features and distance vectors; optimizing the distance vector based on the mutual information amount and the conditional entropy; constructing a post competency model based on the optimized distance vector; the post competency model is used for matching talents and posts. According to the method, the AI algorithm big database and the post competency model are combined, an intelligent conditional entropy clustering calculation method is utilized, accurate classification matching of post competency is achieved, and a new and more efficient solution is provided for the field of human resource management.

The application provides a lightweight contrast learning image quality evaluation method and system based on quality decoupling, reconstructs the pre-scale features of each scale feature based on a reconstruction network in a semantic quality decoupling module to obtain three-dimensional reconstructed pre-scale features, models the local conditional probability of each scale feature and the pre-scale feature at a local position, obtains the overall conditional entropy of the scale feature and the pre-scale feature according to the conditional probability, obtains a weight matrix that maximizes the overall conditional entropy through a preset modeling optimization formula, makes the reconstructed pre-scale features respectively multiply the weight matrix to perform spatial transformation, and performs feature splicing, pooling and other processing to obtain a quality perception vector, and then maps and predicts the quality perception vector through a quality regression network and a quality prediction network to obtain a quality prediction score of the image to be evaluated. The whole training process does not need to involve subjective opinion scores, improves the objectivity of image quality evaluation, and reduces resource waste.

The application relates to a rolling bearing fault diagnosis method and system, and belongs to the technical field of bearing fault diagnosis, wherein the method comprises the following steps: constructing a diagnosis network, wherein the diagnosis network comprises a feature extractor and a classifier which are connected in sequence; inputting source domain samples and target domain samples into the feature extractor in parallel to extract source domain features and target domain features; optimizing the weight of the source domain samples through the source domain features and the target domain features, so that the source domain samples with the same class as the target domain samples obtain higher weights; calculating the cross-entropy loss of the source domain based on the weight of the optimized source domain samples, combining the target domain conditional entropy loss to construct a total loss function, training the feature extractor and the classifier through the total loss function to obtain a training-converged diagnosis network; and performing fault diagnosis on unlabeled real samples to be diagnosed through the training-converged diagnosis network. The application can effectively detect the fault types of rolling bearings, and the detection precision is high.

This application provides a context optimization method and apparatus for a retrieval-enhanced generation system, relating to the field of information retrieval technology. The method includes: receiving a user query and retrieving a knowledge document set related to the user query through a knowledge base retrieval; dynamically optimizing the knowledge document set by iteratively executing symmetric and asymmetric merging operations using an optimization objective function based on information bottlenecks to generate a compressed context; wherein, the symmetric merging operation is used for document pairs with low relevance scores; and the asymmetric merging operation is used for documents that identify and fuse semantic redundancy based on conditional entropy. The context optimization method and apparatus for a retrieval-enhanced generation system provided by this application, through dynamic intelligent fusion and compression of retrieved documents, can provide larger language models with higher information density and more accurate context at a lower computational cost, thereby obtaining more reliable and complete answers.

An unsupervised multi-view clustering method for the problem of missing non-aligned views is proposed for the situation where consistency learning of multi-view data is insufficient in the case of PVP and PSP. HmiMVC is proposed. First, the PVP problem is solved by maximizing the cross-view mutual information to achieve category-level alignment. For the PSP problem in the PVP problem, the idea of ​​dual prediction is used to predict the missing data, while minimizing the conditional entropy to achieve natural category-level alignment. Data recovery and alignment are integrated in a hierarchical consistency framework. HmiMVC adopts different hierarchical alignment strategies and methods for PSP and PVP respectively, but consistency learning in turn makes PSP and PVP learning reinforce each other. The present invention combines category-level alignment and instance-level recovery alignment, effectively overcoming the problem of insufficient consistency learning and significantly improving clustering performance.

Certain aspects of the present disclosure provide techniques for performing machine learning, including: processing a training data instance with a task model to generate an encoding and a task model output; processing a discriminator input based on the encoding using a discriminator model to generate an estimated mutual information between the encoding and the one or more input variables of the training data instance; updating parameters of the discriminator model using a first iterative optimization algorithm to maximize a discriminator objective function based on the estimated mutual information; and updating parameters of the task model using a second iterative optimization algorithm to minimize a task objective function based on a sum of the estimated mutual information between the task model output and the one or more input variables of the training data instance and a conditional entropy between the target variable and an encoding generated by the task model.

The invention provides a feature selection method based on information entropy, which can be applied to the field of cloud computing or big data. The method comprises the steps of obtaining a to-be-processed data set, wherein the to-be-processed data set comprises a plurality of high-dimensional features; dividing the to-be-processed data set into an unbalanced data set and a balanced data set based on the category distribution of the to-be-processed data set; for the unbalanced data set, calculating a joint entropy between high-dimensional features in the unbalanced data set, and iteratively selecting an optimal feature in the unbalanced data set according to the joint entropy to obtain a first optimal feature subset; and for the balanced data set, calculating the information entropy, the joint entropy, the conditional entropy and the information gain of the high-dimensional features in the balanced data set, and iteratively selecting the optimal features in the balanced data set according to the information entropy, the joint entropy, the conditional entropy and the information gain to obtain a second optimal feature subset. The invention further provides an information entropy-based feature selection device, equipment, a storage medium and a program product.

The present disclosure provides a privacy protection method of address information, an electronic device and a program product. The privacy protection method of the present disclosure comprises: decomposing address information, determining dimension information corresponding to address dimensions; combining dimension information of different address dimensions to determine several dimension information combinations; determining a conditional entropy value according to the dimension information combinations and the address information, the conditional entropy value being used to represent the difficulty of inferring the complete address information under the premise of knowing part of the dimension information; determining a privacy protection risk level of the address information according to the conditional entropy value; and determining a privacy protection strategy according to the privacy protection risk level.

This application discloses an image compression method, device, and readable storage medium. In this application, the latent representation corresponding to the image to be compressed is sliced, and each slice is then arithmetically encoded. One of the encoding criteria is conditional information, where multiple methods exist for generating conditional information, resulting in multiple pieces of conditional information. It is understood that arithmetic coding is a type of entropy coding, and since conditional entropy is less than or equal to entropy, this application uses conditional entropy encoding to achieve a higher compression rate.

The present application relates to the technical field of semantic analysis, in particular to an AIGC text detection method based on multi-dimensional semantic entropy and style fingerprint fusion, comprising: first, obtaining an environmental, social and governance report and splitting it according to logical chapters, extracting exclusive term density, syntactic complexity and emotional polarity by using a natural language processing tool, constructing a style fingerprint vector and calculating a style fault degree; then, extracting index items and their qualitative and quantitative data in the report to construct index triples, calculating narrative bias degree by combining semantic tendency and numerical change direction; then, calculating the conditional probability distribution of the text fragments to obtain the conditional entropy feature, calculating the similarity of adjacent sentences to obtain the semantic jump entropy feature, and comparing the statements across years to obtain the consistency degree of cross-period evolution; finally, mapping the information theory feature vector and the statistical feature vector to a unified implicit space, performing bidirectional isomerization feature cross-validation for fusion normalization, and outputting the machine generation probability score of the text fragments.

The application provides a ZDR arc automatic recognition random forest modeling method and system, relates to the meteorological radar data processing technical field, and includes the following steps: acquiring dual-polarization radar observation data, extracting a differential reflectivity field and a reflectivity field, determining an arc candidate area based on a spatial position relationship and extracting multi-dimensional feature parameters, calculating a mutual information matrix and a partial correlation coefficient matrix to screen feature pairs and perform tensor product operation to generate high-order interaction features, constructing a training sample set, initializing a basic random forest, and based on feature conditional entropy, reconstructing a sampling probability distribution to complete decision tree growth to obtain a basic classifier, extracting a decision tree discrimination path sequence, converting it into a topology graph, encoding it into a path embedding vector to train a meta-random forest classifier, inputting to-be-recognized data into the basic classifier and the meta-random forest classifier, and outputting a recognition result. The accuracy and automation degree of ZDR arc recognition are effectively improved.

The present invention relates to the technical field of intelligent data processing, and includes a data analysis system driven by an intelligent algorithm. The system includes a feature screening module, a topological backbone extraction module, an information transmission optimization module, a classification boundary adjustment module, and an adaptive classification hierarchy module. In the present invention, by calculating the conditional entropy of data feature values, analyzing the fluctuation degree of feature information and screening unidirectional dominant features, the interference of low-contribution features is reduced, the topological adjacency relationship of data points is constructed, the main trunk of data classification is optimized, the attribution of data points is adjusted in combination with the change of local information entropy, so that the classification structure is more in line with the data transmission characteristics. By combining the information entropy fluctuation of the classification boundary and the connection strength of core data points, the classification boundary division is optimized. By combining the change rate of hierarchical stability, the data hierarchy division strategy is adjusted, the classification structure is optimized, the stability and calculation efficiency of data classification are improved, the classification boundary adjustment is made more accurate, and it is ensured that the classification hierarchy can be adaptively adjusted.

A method, apparatus or system for processing point cloud information can involve a learned deep entropy model over octrees for lossless compression / decompression of 3D point cloud data, wherein self-supervised compression / decompression involves an adaptive entropy coder operating on a tree-structured conditional entropy model and utilizing information from the local neighborhood as well as the global topology from the tree structure.

The invention discloses a geostatistical modeling method uncertainty quantification method based on a mutual information entropy framework, and relates to the technical field of geostatistical modeling quality control, and the method comprises the steps: collecting the space sample data of an estimation domain, determining target methods, constructing a parameter matrix for each target method, and carrying out the calculation of the parameter matrix; carrying out multiple modeling on each target method according to the parameter matrix on the estimation domain to generate a plurality of modeling results; dispersing each realization modeling result to a unified grid to obtain a realization modeling result set of each grid, counting distribution of a plurality of realization modeling results for each grid, constructing probability distribution of each grid, calculating point entropy of each grid based on the probability distribution, and forming a spatial uncertainty entropy field. According to the method, quantification of spatial uncertainty is achieved by achieving probability distribution and entropy measurement, IMUI indexes are constructed through joint entropy, conditional entropy and mutual information, and evaluation of output convergence and structural consistency of the method is achieved.

The embodiment of the invention provides a conditional entropy coding method, device and equipment, and relates to the technical field of image processing. The method comprises the following steps: determining a continuous index value corresponding to a to-be-coded element through a conditional entropy model; determining a discrete index value corresponding to the continuous index value, and determining probability distribution corresponding to the discrete index value from a preset probability distribution set; determining a cumulative distribution function corresponding to the probability distribution from a pre-stored cumulative distribution function lookup table; and entropy coding is performed on the to-be-coded element through the cumulative distribution function. Therefore, only one continuous index value needs to be predicted, the discrete index value is determined through simple mapping operation, then the cumulative distribution function corresponding to the discrete index value is directly obtained through the pre-stored cumulative distribution function lookup table, and the complex process of dynamically calculating the cumulative distribution function is avoided. According to the method, the coding calculation complexity is reduced, and the coding efficiency is improved.