41 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 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 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.

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.

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 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.

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 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.

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.

This invention relates to the field of user churn prediction technology and discloses a member churn prediction method based on model evaluation, comprising the following steps: extracting member behavior data, time series data, member feature data, and churn tag data from a member management system; performing data cleaning and normalization; and extracting time features; quantitatively evaluating the importance of features in member behavior data based on information entropy and conditional entropy calculations, and screening key features with conditional entropy values ​​below a preset threshold; constructing a synergistic effect function between features, and determining a dynamic weight allocation scheme for features through a game theory model; and based on the screened features and their corresponding weights. By quantifying the explanatory power of each feature for churn tags and screening key features, this method achieves the technical effect of improving model training efficiency and reducing interference from irrelevant features, solving the problem of model performance degradation due to insufficient feature importance evaluation.

This invention relates to a method and system for generating route guidance information for urban rail transit, specifically in the field of traffic flow guidance. The method includes: constructing a utility model for the display format of guidance information and a utility model for the content of guidance information based on information entropy, conditional entropy, and information gain; a route attribute includes multiple display formats, and each display format includes multiple display format levels; determining the perception coefficient of the route's guidance information based on the utility model for the display format and the utility model for the content of guidance information; constructing a passenger route selection model based on the perception coefficient, wherein the passenger route selection model is an improved Logit model; calibrating the model parameters of the passenger route selection model according to different types of passengers; and generating guidance information based on the passenger route selection models calibrated with different model parameters, with the goal of minimizing the uneven distribution of passenger flow. This invention alleviates the problem of uneven passenger flow distribution in the road network.

The invention discloses an AI pet cat behavior monitoring method and system, and relates to the technical field of pet behavior monitoring, and the method comprises the steps: carrying out the DWT of a fusion feature, obtaining a multi-scale wavelet coefficient, generating a fractional order enhanced wavelet coefficient through a fractional order derivative operator, constructing a causal enhanced rhythm feature through the combination of a Granger causal value and a gray correlation degree, and carrying out the recognition of the behavior of an AI pet cat. Topological entropy and conditional entropy are calculated, and final features are generated in combination with biological rhythm modulation and entanglement weight; according to the method, multi-scale wavelet coefficient analysis is introduced, periodicity and rhythm characteristics of behavior data are extracted in combination with fractional order enhanced wavelet coefficients, behavior mode changes of the pet cat under different time scales are effectively captured, and the accuracy of the pet cat behavior model is improved through rhythm adjustment weight and dynamic confidence calculation in combination with biological rhythm modulation and environmental factors. The accuracy of behavior classification and health assessment is improved, and the behavior recognition precision and the reliability of health early warning are improved.

The present application relates to the technical field of electric data processing, and particularly relates to a lightning arrester test interaction control method based on virtual reality technology, which comprises the following steps: obtaining an initial aliasing sequence in a virtual simulation environment; obtaining a conditional probability distribution of an initial aliasing signal about each interference component, thereby obtaining a conditional entropy and calculating a static contribution degree of each interference component; obtaining a standard physical evolution track of a lightning arrester, calculating a variation rate deviation of the initial aliasing signal and the track to determine a physical tracking operator; determining a suppression weight based on the static contribution degree and the physical tracking operator, and using the suppression weight to weight and combine a characteristic direction matrix of each interference component to construct a characteristic decoupling matrix; and decoupling the initial aliasing signal by using the matrix to restore a response characteristic signal and recover a leakage current value. The present application reduces the masking of test feedback by analog interference through dynamic and static dimensional characteristic decoupling, and improves the evaluation accuracy.

The application provides an information transmission method, system, electronic equipment and readable storage medium. The information transmission method comprises the following steps: acquiring an information block to be transmitted, acquiring a bit position reliability sorting table and a conditional entropy sorting table corresponding to a first component code, wherein the conditional entropy sorting table is used to determine a shaping bit in the bit position, and the number of shaping bits of the first component code is greater than or equal to 1; determining the bit position of each component code according to the bit position reliability sorting table and the conditional entropy sorting table corresponding to the first component code, wherein the bit position comprises an information bit, a frozen bit and / or a shaping bit; and generating a modulation symbol sequence according to the information block to be transmitted and the bit position of each component code. In the application, the probability shaping construction process in the information transmission process determines the bit position by constructing a table, and has low execution difficulty, low complexity, high flexibility and practicability.

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.

This invention discloses a learning-based method for joint geometric and color compression of point clouds. The method specifically includes: preprocessing the initial training point cloud input, inputting it into an encoding module to obtain a feature matrix and a mask matrix, inputting the feature matrix and mask matrix into a decoding module to obtain an initial reconstructed training point cloud, calculating the geometric reconstruction training loss, color reconstruction training loss, and information entropy loss to obtain the point cloud training compression loss result, and then passing the initial inference point cloud through an optimized target learnable conditional entropy model to obtain the learning-based joint geometric and color compression result. This invention fully considers the mutual influence between geometric and color reconstruction losses by weighted summation of the geometric reconstruction loss, color reconstruction loss, and information entropy loss; the proposed learnable conditional entropy model enables more flexible conditional distribution modeling and can be widely applied in the field of point cloud processing technology.

Methods and devices for encoding and decoding 3D point clouds. A learned deep entropy model over octrees is proposed for lossless compression of 3D point cloud data. The self-supervised compression consists of an adaptive entropy coder which operates on a tree-structured conditional entropy model. The information from the local neighborhood as well as the global topology is utilized from the octree structure. In an embodiment, the features from the parent level is up-sampled to bring them to the resolution of the current level before further feature aggregation. For processing dense massive point clouds and to facilitate parallel processing, a block-based compression scheme is proposed to reduce the required computation and time resources.

A multi-source-domain adaptive cross-subject motor imagery electroencephalogram decoding method based on feature cascading comprises the steps that source domain data and target domain data are sequentially input into a local feature extractor and a global feature extractor to achieve progressive feature extraction, and source domain features and target domain features are output; calculating maximum mean value difference loss and semantic loss according to the source domain features and the target domain features; performing feature distribution alignment on the source domain features and the target domain features by minimizing the maximum mean value difference loss and the semantic loss; performing classification prediction according to the aligned source domain features and target domain features to generate a source domain pseudo tag and a target domain pseudo tag; calculating cross entropy loss; calculating conditional entropy loss; constructing and minimizing total loss to train a cross-subject motor imagery electroencephalogram decoding model, wherein the total loss comprises maximum mean value difference loss, semantic loss, cross entropy loss and conditional entropy loss; and testing the test set of the target domain data to obtain a classification result.

Embodiments of the present application provide a feature selection method and device, electronic equipment and storage medium. The method comprises: obtaining a training sample set, calculating the conditional entropy corresponding to each dimension of features in a feature set composed of the same dimension features of multiple samples, and calculating the selected probability corresponding to the features of the dimension based on the conditional entropy; initializing a preset number of particles based on the selected probability corresponding to the features of each dimension, for each element in each particle, if the value of the element is greater than a preset feature threshold, determining that the feature corresponding to the element in the particle is selected, obtaining a selected feature subset corresponding to the particle; determining the value of the objective function based on the selected feature subset corresponding to each particle, if the objective function converges, determining the selected features of each sample as target features; and if the objective function does not converge, adaptively updating each particle. By using the method, the convergence speed of the machine learning algorithm is improved.

The invention discloses a medical examination index reduction method based on mixed fuzzy conditional entropy. The method is suitable for high-dimensional data attribute reduction and knowledge discovery in scenes such as medical data analysis. In a fuzzy information decision-making system, each inspection index is grouped by adopting a fuzzy clustering method, hard division labels and fuzzy membership degrees are separately stored, and a dual information framework is established. In the iterative reduction process, a joint cluster is generated by using hard division label intersection, and exponential calculation and storage space brought by Cartesian product calculation are avoided; meanwhile, fuzziness is reserved through the fuzzy membership degree, boundary object information is reserved, and the classification error rate is reduced. Attributes are iteratively selected by using a mixed conditional entropy model, the problem of feasibility of attribute reduction of a large-scale fuzzy information decision system is solved, and a more accurate reduction set is obtained. Key diagnosis indexes are conveniently focused, the diagnosis efficiency and accuracy are improved, the clinical interpretability is enhanced, unnecessary detection items are reduced, and the medical cost is reduced.

The invention provides a data processing method, device and equipment, a computer readable storage medium and a computer program product. The method comprises the steps of performing word segmentation processing on a first text to obtain different first words; determining the importance degree of the first word based on the occurrence frequency of the first word in the first text; querying a context word of the first word in a first text comprising the first word; based on the occurrence frequency of the context word of the first word, determining a conditional entropy of the context word corresponding to the first word; and based on the context window, the number of the first words, the conditional entropy of the context words corresponding to the first words, and the importance of the first words, determining the word vector dimension of the first text. The word vector dimension determined by the method and the device is adaptive to the word distribution condition in the first text, so that the first text can be represented more accurately.

The application relates to a kind of multivariate time series data abnormal root cause identification methods based on space-time causal diagram, belong to abnormal detection technical field.The method, to multivariate time series data, uses multi-window expansion causal convolution, combines mutual information screening, extracts time embedding covering short-term mutation and long-time dependence simultaneously;Non-local spatial correlation is learned using multi-head self-attention, then the directional causal strength is measured by conditional entropy, and a sparse, interpretable space-time causal diagram is generated by normalization-pruning;Causal reinforcement graph attention network is introduced on the space-time causal diagram, and the node embedding is updated by multiple rounds of causal propagation;The root cause score is calculated by combining the abnormal degree and the causal influence, the key source node in the abnormal propagation path is identified, and the precise root cause positioning of system anomaly is realized.The application enhances the adaptability to dynamic behavior patterns and the ability to capture abnormal driving factors, and improves the modeling accuracy and root cause identification ability of the abnormal propagation process.

The present application relates to the technical field of natural language processing, and provides a large language model illusion detection method based on causal double chains and an intelligent question and answer method, which comprises: for each input question, initiating multiple rounds of independent sampling to form a response set containing multiple sampling responses; for the response set, extracting reasoning chains and causal chains, and calculating reasoning chain conditional entropy, causal chain conditional entropy and mutual information of the reasoning chains and the causal chains, and taking the weighted sum of the reasoning chain conditional entropy, the causal chain conditional entropy and the mutual information of the reasoning chains and the causal chains as an illusion score. Multi-dimensional accurate identification of complex illusions is realized.