43 results about "Entropy model" patented technology

The invention relates to the technical field of industrial Internet of Things data processing, in particular to a dual-channel anomaly detection method based on local entropy and isolated forest, and the method comprises the steps: collecting multi-dimensional time sequence data of equipment operation in real time; extracting local data of the multi-dimensional time series data in each sliding window by using a variable step size sliding window technology, calculating four statistical indexes according to the local data to construct a multi-dimensional entropy model, and obtaining a local entropy score according to the multi-dimensional entropy model; utilizing an isolated forest algorithm to calculate an isolated forest abnormal score of the multi-dimensional time series data; and constructing a joint scoring model, dynamically adjusting the weight of the local entropy score and the weight of the isolated forest abnormal score to obtain a joint score, and judging the abnormal level of the equipment according to the joint score and a preset abnormal threshold value. Therefore, the problems of insufficient real-time performance, insufficient feature utilization, low decision collaboration efficiency and the like in an industrial scene are solved.

The invention discloses a Mama-based entropy model and an image compression method, and mainly solves the problem of limited compression performance caused by poor entropy estimation precision in the prior art. The scheme comprises the following steps: 1) constructing a two-dimensional state space hyper-prior network by a hyper-prior encoder and a decoder to obtain global hyper-prior features; 2) adopting a double-branch gating architecture to obtain a mixed context feature containing local and global dependency information; 3) constructing an entropy parameter fusion and probability modeling network, carrying out channel splicing and feature fusion on the mixed context features and global super-prior features, and outputting a conditional Gaussian distribution parameter of each latent variable position; according to the method, the entropy model estimation precision can be remarkably improved, meanwhile, the compression rate distortion performance is improved, and the balance between the rate distortion performance and the calculation complexity is achieved.

The invention relates to a man-machine mixed vision-oriented semantic perception video compression method and system, and the method comprises the steps: extracting the dynamic semantics of a video sequence, and generating a region of interest; generating a focusing frame with consistent vision according to the input frame and the corresponding interested area mask; predicting feature probability distribution of the focusing frame through an entropy model, and compressing the feature probability distribution into a code stream; decoding the code stream through a conditional decoder to obtain a semantic compressed reconstructed video; performing feature alignment on the decoded frames in the decoded frame buffer areas of the basic branch and the auxiliary branch to generate prediction features; inputting the prediction frame of the prediction feature and the video sequence into an entropy model, and compressing the prediction frame and the video sequence into a code stream through entropy coding; decoding the code stream to obtain reconstruction features; and converting the reconstruction features into fine reconstruction features to obtain a final compressed and reconstructed video. Compared with the prior art, the method has the advantages that high machine vision task accuracy can still be maintained under the condition of low code rate, and higher rate accuracy performance is achieved in the machine vision task.

The invention relates to a three-dimensional point cloud prediction geometric coding method based on deep learning, and the method comprises the steps: 1, forming a prediction tree through points collected by each laser transmitter, and converting an original laser radar point cloud LPC into a plurality of prediction trees for representation; 2, respectively designing different predictors and entropy encoders for each component of the coordinates of the points, and compressing each component of the coordinates of the points by applying different quantization step lengths; 3, selecting a quantization step size for quantifying each component by adopting a quantization step size selection strategy; 4, adopting an entropy model to model the probability distribution of the residual error of each component so as to encode the residual error entropy; and step 5, decoding is realized through a reverse process from the step 1 to the step 4. Compared with other methods, the method provided by the invention obtains the best rate distortion performance.

The invention relates to the technical field of education artificial intelligence, and provides a self-adaptive learning path recommendation method for artificial intelligence general recognition education, which comprises the following steps of: 1, calling a large language model to analyze unstructured course resources of AI general recognition education, mining semantic association and implicit dependency of knowledge points, and constructing a learning path; generating a space-time knowledge graph containing confidence scores, automatically capturing the latest literature and tool update of the field every 72 hours, and iteratively optimizing the topological structure of the graph; 2, deploying data acquisition points to acquire multi-source learning data of a user in real time, and calculating a dynamic cognitive state vector with knowledge points as dimensions by mastering an entropy model; the knowledge graph is automatically iterated through LLM, and the problem of update lag is solved; precise personalized recommendation is realized according to multi-dimensional data and a dynamic algorithm, and cognitive differences are adapted; visually presenting decision logic, and cracking a decision black box; the method can be migrated to multiple fields, supports multi-terminal and offline learning, exceeds an expected adaptive scene, and improves the learning efficiency and credibility.

An entropy-based technique is used to select a large language model capable of generating fluent natural language text. An entropy model, trained on fluent natural language samples, is used to determine the entropy of a large language model based on an output text generated by the large language model. The entropy of a machine-generated natural language text is used to quantify the amount of information that the large language model holds with respect to the tokens and context of an input text segment. The entropy score of a model is then used to select a large language model capable of generating fluent text or to select the most fluent machine-generated output text produced by a set of large language models.

The invention discloses a full-stream entropy encoding and decoding accelerator, which comprises an encoder and a decoder, the encoder comprises an encoding prefetching module and an encoding pipeline calculation core, the decoder comprises a decoding prefetching module and a decoding pipeline calculation core, the encoding prefetching module is used for reading information of a plurality of sets of entropy models at a time, and the decoding pipeline calculation core is used for decoding the encoding pipeline calculation core. Determining that the coding process and the decoding process of the to-be-coded characteristic value are not skipped according to the confidence coefficient, splitting the multiple sets of entropy model information into single sets of entropy model information in a parallel-to-serial mode, and inputting the single sets of entropy model information into a coding pipeline calculation kernel in combination with the corresponding to-be-coded characteristic value for coding to obtain a code stream; the plurality of decoding prefetching modules are used for polling and inputting the multiple segments of code streams and the corresponding entropy model information into the decoding pipeline calculation core for decoding, the decoding pipeline calculation core is used for intercepting the code streams corresponding to the reserved digits, calculating the anti-cumulative probability distribution value of the code streams, carrying out quantization processing on the anti-cumulative probability distribution value to obtain decoded characteristic values, and sending the decoded characteristic values to the decoding prefetching modules; the problems of computing resource waste and low storage efficiency are solved.

The application provides a digital semantic perception OFDM subcarrier allocation method based on an entropy model, and relates to the field of wireless communication. The method comprises the following steps: a semantic encoder in a joint coding and modulation module is used to perform semantic coding on an original image to obtain semantic features; the joint coding and modulation module is used to modulate the semantic features to obtain a modulation symbol sequence; a semantic importance evaluation module is used to process the semantic features to obtain a semantic importance vector; an orthogonal frequency division multiplexing transmitter is used to process the modulation symbol sequence into M to-be-transmitted orthogonal frequency division multiplexing data packets; the joint coding and modulation module is used to allocate the M to-be-transmitted orthogonal frequency division multiplexing data packets to M subcarriers according to the semantic importance vector and feedback channel state information; and the orthogonal frequency division multiplexing transmitter is used to send the M to-be-transmitted orthogonal frequency division multiplexing data packets to an orthogonal frequency division multiplexing receiver in a receiving end, so as to realize efficient and reliable transmission of digital semantic information in a wireless channel.

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.

An entropy-based technique is used to select a large language model capable of generating fluent natural language text. An entropy model, trained on fluent natural language samples, is used to determine the entropy of a large language model based on an output text generated by the large language model. The entropy of a machine-generated natural language text is used to quantify the amount of information that the large language model holds with respect to the tokens and context of an input text segment. The entropy score of a model is then used to select a large language model capable of generating fluent text or to select the most fluent machine-generated output text produced by a set of large language models.

An apparatus includes first and second circuitry, such as a first memory and a second memory. The first circuitry is configured to store compressed information representing a set of distribution functions associated with a set of entropy models. The second circuitry is configured to store mappings of requests for subsets of the set of distribution functions to one or more offsets in the first circuitry corresponding to the compressed information representing the subsets. The apparatus also includes circuitry that implements the set of entropy models. This circuitry is configured to perform entropy coding based on the subsets and a first entropy model selected from the set of entropy models. This circuitry can include one or more entropy engines that have a set of ports for encoding or decoding one or more streams of bits or symbols. Multiple streams can therefore be encoded or decoded concurrently or in parallel.

The invention discloses a long tribulus terrestris risk prediction method based on a multi-source data fusion maximum entropy model, and belongs to the technical field of long tribulus terrestris risk prediction. The objective of the invention is to solve the problem of accurate risk prediction of tribulus terrestris. The method comprises the following steps: collecting species distribution data and environment variable data of tribulus terrestris, and preprocessing; constructing a maximum entropy model; a three-level screening strategy is adopted, key environment variable screening is carried out on the preprocessed environment variable data in combination with the constructed maximum entropy model, and key link variables after screening are obtained; training a maximum entropy model by using the preprocessed species distribution data and the screened key link variables to obtain a trained maximum entropy model, and outputting a adaptability index of a grid unit; and carrying out potential suitable growth area division and early warning area delimitation on the tribulus terrestris. According to the invention, the space-time accuracy and prevention and control guidance value of the early warning result are greatly improved.

The invention discloses a privacy-enhanced image compression method, which comprises the following steps: constructing a semantic-frequency map based on frequency domain features and sensitive masks, and positioning a semantic unit set; performing spectral domain structure adjustment on the frequency domain features, performing entropy alignment generation in combination with an entropy model, and obtaining adjusted frequency domain features, parameterizing semantic differences and dual compensation; reversible dual decomposition is applied to the adjusted frequency domain features, and public potential features and dual potential features are obtained; an entropy model is utilized to compile the public potential feature entropy into a main bit stream, and the dual potential feature, the parameterized semantic difference and the dual compensation joint entropy are compiled into a safe bit stream; and generating a protected head containing access control information in combination with the access key, and packaging the main bit stream, the security bit stream and the protected head into a container code stream. According to the method, machine semantic recognition can be effectively shielded at a common end, meanwhile, an authorization end is supported to accurately recover semantics at low code rate cost, and multi-level access control of the same code stream is achieved.

The invention relates to a presentation strategy evaluation and optimization method based on a perception-judgment-decision link, and solves the problems that in the existing intelligent auxiliary information situation interface design, the cognitive load is difficult to quantify, the task completion time evaluation is inaccurate, and the causal logic understanding lacks scientific indexes. According to the method, by constructing a multi-dimensional information entropy model, a task completion timeliness model and a causal definition model, the interface cognitive load, the task operation efficiency and the understanding degree of a user on task logic are quantified, then an optimal interface design scheme is screened through a multi-objective optimization method, the operation efficiency and the situation understanding ability of the user are improved, and the user experience is improved. And the information presentation effect of the intelligent auxiliary system is optimized. The method provided by the invention can effectively reduce cognitive load, shorten task completion time, enhance understanding of users on task causal relationships, and significantly improve usability and security of an intelligent auxiliary system interface, and has wide application value.

The application provides a point cloud encoding method based on a multi-level spherical octree and a graph-driven attention entropy model, comprising: encoding point cloud data using an octree entropy model based on multi-level spherical coordinates; constructing an adjacency matrix of a parent graph and a distance graph; using a graph convolution network module to embed context information with the aid of the adjacency matrix; constructing a grouping graph attention module and a cross attention module to learn the relevance of parent node context and sibling node context; predicting the probability of each octree node placeholder symbol; compressing the placeholder symbol sequence into a binary floating point number sequence and converting it into a bit stream; converting the bit stream into an octree placeholder symbol sequence, reconstructing the octree and restoring the point cloud. The application combines multi-level spherical coordinate octree structure, graph convolution, grouping graph attention module and cross attention module, reduces quantization error, improves compression efficiency, balances calculation complexity and compression effect, and significantly enhances the adaptability to high-resolution point cloud data.

An apparatus includes first and second circuitry, such as a first memory and a second memory. The first circuitry is configured to store compressed information representing a set of distribution functions associated with a set of entropy models. The second circuitry is configured to store mappings of requests for subsets of the set of distribution functions to one or more offsets in the first circuitry corresponding to the compressed information representing the subsets. The apparatus also includes circuitry that implements the set of entropy models. This circuitry is configured to perform entropy coding based on the subsets and a first entropy model selected from the set of entropy models. This circuitry can include one or more entropy engines that have a set of ports for encoding or decoding one or more streams of bits or symbols. Multiple streams can therefore be encoded or decoded concurrently or in parallel.

The invention discloses an extremely low bit rate image compression method based on mixed attention and multi-scale entropy modeling, and the method comprises the steps: obtaining a standard image data set which comprises a training set and a test set; the method comprises the following steps: constructing an extremely low bit rate image compression network model based on double-branch mixed attention and multi-scale entropy modeling, constructing a loss function of an extremely low bit rate image compression network, and in a deployment stage, inputting an original image in a test set into the extremely low bit rate image compression network loaded with an optimal weight, and obtaining a coded and compressed binary code stream and a decoded and reconstructed image. According to the method, a multi-scale attention fusion mechanism is introduced into an autoregression entropy model, the problem of dimensionality fragmentation of feature representation is solved through three parallel branches, and cross-dimensional interaction, local spatial correlation and grouping channel correlation are modeled to jointly enhance context features. Therefore, potential space redundancy in the compression process is reduced.

The application discloses a kind of based on physical event anchoring and space-time decoupling's sea transport freight right fraud real-time blocking system, comprising: physical event four-dimensional tensor construction module: for building the physical event including space coordinates, time series, equipment signature and event type four-dimensional data tensor representation;Quantum fingerprint anchoring module: for generating anti-copy unique identification to physical event data by 12-bit quantum circuit;Helve space-time topology engine: for calculating the continuity score of the physical event of generating anti-copy unique identification;Three-level risk response execution module: for automatically triggering on-chain blocking operation according to physical event continuity score, three-level risk response is judged;Self-evolution risk control system: for dynamically optimizing rule weight and freight right entropy model by fraud mode clustering, generates the defense mechanism of triggering on-chain blocking operation.The system marks that international trade trust mechanism has entered the trend and possibility of new era of quantum level credibility.

This invention relates to the field of intelligent supervision and early warning management, proposing a work supervision and early warning management method and system based on multi-dimensional risk sources. A multi-dimensional risk entropy model is designed, and supervision and spot checks are conducted based on complex multi-dimensional risk data items. Through kernel density estimation of risk entropy calculation, dynamic spot check probability calculation, and cumulative probability stratified sampling, efficient extraction of high-risk items is achieved, while improving the coverage balance of sampling, reducing the time consumed in a single sampling, and improving the overall efficiency of supervision and spot checks. Furthermore, a multi-level fuzzy evaluation algorithm based on AHP-entropy weight combination is designed. Through AHP-entropy weight combination, the influence of subjective bias or data noise is avoided, and the weights are adaptively adjusted according to changes in data distribution, improving the accuracy and stability of early warning monitoring. This invention improves the efficiency and stability of work supervision and early warning management methods based on multi-dimensional risk sources.

The application discloses a cluster task capability evaluation method, device and system and a storage medium. The method proposes a cluster structure negative entropy model to describe the influence degree of a cluster static structure on cluster task capability. The correlation between single machine behavior decision and the cluster structure negative entropy model is considered, and then a cluster dynamic behavior negative entropy task capability evaluation model based on behavior decision is proposed to realize the purpose of evaluating cluster task capability. In view of the proposed cluster task capability measurement index, the application analyzes the influence factor sensitivity of the index from the angles of a cluster control structure, a cluster size, a task node ratio and a cluster link capability change, and verifies the correctness and accuracy of the index in describing the cluster task capability.

The invention provides a power load prediction method based on adaptive federal mark distribution learning, and relates to the technical field of the Internet of Things, and the method comprises the steps: continuously collecting power load data and related feature data through terminal equipment, and carrying out the data preprocessing; optimizing the data after data preprocessing through Gaussian distribution; the client adopts a maximum entropy model to establish a prediction model by taking a weighted combination of KL divergence and absolute value loss as a loss function, and calculates to obtain a model parameter gradient of the client; aggregating the model gradients of all the clients by adopting an average aggregation algorithm to obtain a global parameter gradient; each client updates the local model parameters by using the global parameter gradient to complete a round of iteration until the model parameter gradient converges, and inputs the power load data into the convergent model for prediction to output a prediction result; the method can improve the prediction precision, and guarantees the safety and reliability of the data of the intelligent power grid.

The invention discloses a driving risk assessment method, and belongs to the field of data processing. According to the evaluation method, a risk entropy concept is introduced, the uncertainty of three types of core risk sources of vehicles, roads and vulnerable participants in a driving system is converted into quantifiable entropy values, and a vehicle risk entropy model, a road risk entropy model and a vulnerable participant risk entropy model are constructed respectively; based on a combined optimization strategy of an analytic hierarchy process and an entropy weight method, a man-vehicle-road coupling risk entropy model is established, and comprehensive quantitative evaluation of multi-dimensional risks is realized; the method can accurately capture the dynamic risk in the driving process, is timely and effective in intervention response, and can be widely applied to the fields of intelligent driving and advanced auxiliary driving systems.

A method for learned image compression implemented in an autoencoder includes: a) extracting from an image a latent space by the learnable encoder; b) quantizing the latent space by a quantizer to obtain a quantized latent space; c) entropy coding the quantized latent space by an entropy encoder to obtain a bitstream, wherein an entropy model used to encode the latent space is represented by a probability distribution; d) entropy decoding the bitstream by an entropy decoder to obtain an entropy decoded bitstream; e) feeding the entropy decoded bitstream to the decoder; f) recover a reconstructed image by the decoder; g) training the autoencoder via standard gradient descent of the backpropagated error gradient by finding learnable parameters of the learnable encoder and of the decoder that minimize a rate distortion cost function, wherein the entropy encoder is based on a differentiable formulation of a soft frequency counter.

The invention belongs to the technical field of learning type point cloud compression and entropy coding probability modeling, and particularly relates to a point cloud context neighborhood selection method for an entropy model, which is applied to a learning type point cloud compression system. The potential variable is divided into a first coding feature and a second coding feature according to a checkerboard grouping rule, the first coding feature is entropy-coded and recovered at a decoding end, and the first coding feature is used as decoded side information; the conditional probability of the second coding feature is jointly determined by the decoded context neighborhood feature of the first coding feature and the hyper-priori side information, and the neighborhood feature of the second coding feature is retrieved in the decoded feature space of the first coding feature for decoding the second coding feature. According to the method, the uncertainty of conditional distribution is reduced by eliminating redundant / mismatched neighbors from the candidate pool, so that coding bits are reduced.

The invention relates to the technical field of data processing, can be applied to the field of finance, and provides an insurance risk identification method, device, equipment and medium: performing entropy processing on insurance structured data and insurance unstructured data through an entropy model to obtain a time distribution entropy and a channel use entropy; generating a behavior complexity score according to the time distribution entropy and the channel use entropy; weighting all text data in the insured unstructured data to obtain a keyword weighted score and a semantic weighted score; and performing risk identification on the keyword weighted score, the semantic weighted score and the behavior complexity score through a preset scoring model to obtain a risk scoring result corresponding to the target customer. According to the method, the information contribution degree of the structured data and the non-structured data in risk assessment is quantified by calculating the information entropy value. And the structured data and the unstructured data are combined, so that the identification of non-structural factors is increased, and the accuracy of insurance risk identification is improved.

This invention discloses a method, apparatus, and system for evaluating the degree of harmonic pollution in a power grid. The method includes acquiring harmonic sample data from various power grids and calculating the central moments of each order of the harmonic sample data; constructing a maximum entropy model for the harmonics based on the central moments of the power grid harmonic sample data; converting the maximum entropy model into an optimization model; optimizing the optimization model using a modified hole-punching function to obtain the global optimum value of the optimization model; generating a harmonic probability distribution function based on the global optimum value and the maximum entropy model; and using the harmonic probability distribution function to evaluate the degree of harmonic pollution in the power grid. This invention enables accurate solving of the harmonic probability distribution function and allows for the evaluation of the degree of harmonic pollution in the power grid using the harmonic probability distribution function.

The invention discloses a hyperspectral image compression network and compression method based on a 3D convolution set and a causal entropy model, and mainly solves the problems that the spatial-spectral features of a hyperspectral image cannot be jointly extracted and balanced and an entropy model depends on a fixed causal relationship in the prior art. The method comprises an encoder based on a 3D convolution set, an asymmetric decoder based on the 3D convolution set, a super-prior encoder, a decoder and a context causal adaptive entropy model. The encoder comprises a 3D convolution set attention residual block, a spectrum self-attention module and a convolution module, and is used for converting input into potential features and balancing spatial spectrum features; the asymmetric decoder comprises a 3D convolution set attention residual block, an up-sampling 3D convolution set module, a spectrum self-attention module and a convolution module, and is used for recovering potential features into images; the super-prior encoder comprises a convolution layer and an activation layer and is used for extracting statistical information output by the encoder; after the network is trained, lossy compression of the hyperspectral image can be realized. The method can improve the image space and spectrum reconstruction quality, reduces the bit number required by coding, and can be used for environmental monitoring and resource exploration.

The application provides a malicious lawsuit intelligent supervision method and system based on a dynamic legal knowledge graph, equipment and a storage medium, and belongs to the technical field of legal artificial intelligence. The method obtains dynamic judicial data, identifies the data type and sets a decay coefficient, calculates the time limit weight by using an exponential decay model, and generates a dynamic data vector. A knowledge graph is constructed based on the dynamic data vector, the relationship weight between entities is updated in real time, and the behavior abnormality intensity value is calculated by using an information entropy model. The matching degree of the judicial data and a legal case library is calculated in parallel as a compliance index value. When the compliance index is lower than a first threshold value or the behavior abnormality intensity value is higher than a second threshold value, a supervision process is started. According to the supervision result, the rule library is dynamically updated in combination with a legal compliance loss function, intelligent and dynamic supervision of malicious lawsuits is realized, and the judicial efficiency and accuracy are improved.

The invention discloses a volume video parallel coding and decoding accelerator based on octree partitioning, and relates to the field of volume video coding and decoding, the volume video parallel coding and decoding accelerator comprises an interpolation module and an MLP calculation module of a binary multi-resolution Hash grid, the binary multi-resolution Hash grid is obtained by adopting an octree partitioning strategy to cut volume elements in a volume video, and the MLP calculation module is used for calculating the volume elements in the volume video. The interpolation module is used for processing linear interpolation calculation of the binarized multi-resolution hash grid to obtain a multi-dimensional interpolation vector, and the MLP calculation module adopts a reconfigurable systolic array, distributed access and layer fusion technology to perform MLP calculation on the interpolation vector in a pipelined manner by taking a block as a unit to obtain a multi-dimensional interpolation vector; and predicting entropy model information output by the entropy model corresponding to the characteristic value of each individual primitive. According to the method, the problems of high calculation complexity, extremely high requirements on calculation resources and bandwidth, difficulty in realizing efficient deployment on edge calculation equipment with limited resources and the like in a volume video encoding and decoding process are solved.

The invention belongs to the technical field of man-machine decision fusion. The invention provides a multi-label medical diagnosis man-machine cooperation method based on a confusion matrix and a hybrid expert system. According to the embodiment of the invention, a man-machine decision fusion framework based on expert mixing is provided, the human experts are combined with the global modeling capability of the AI model, the initial man-machine weight is generated by the gating network, and the initial weight is calibrated through the multi-label confusion matrix. The correlation between the labels is fully considered to construct a confusion matrix to evaluate the confidence of the human experts, a maximum entropy model which does not need to be assumed on the premise is used to better conform to a real scene, the dependency relationship between the labels is captured, systematic deviation of expert prediction is quantified, and accurate evaluation of the confidence of the human experts is achieved. For heterogeneity of multi-label classification, an independent decision threshold is optimized for each label, Hamming loss is minimized through grid search, probability output is converted into a binary diagnosis result, and the phenomena of missed diagnosis and misdiagnosis are effectively reduced.