16 results about "Nonlinear diffusion" patented technology

The invention relates to the technical field of artificial intelligence, and discloses an English teaching training system and method fusing semantic matching and cognitive assessment, and the method comprises the steps: synchronously capturing a text response, a voice intonation, an eye movement track, a facial micro-expression and a touch rhythm generated in a learning process; semantic deviation deconstruction and cognitive intention quantization processing are carried out on the learning interaction original sequence, and a bidirectional deep semantic matching network is adopted to carry out context alignment on student answers and target corpora; based on the word meaning divergence point set and the cognitive load multi-scale vector, extracting a nonlinear diffusion trajectory of a learning state by using a time gating multi-layer recursive trajectory evolution algorithm; the knowledge point nodes, the deviation type nodes and the emotion triggering nodes associated with the emotion instability candidate segments are fused to construct a local learning map; and forming an emotion cognition feedback result driven by learning interest based on the local learning map and the self-adaptive error correction intervention sequence. The method has the advantage of improving the learning interest of students.

The invention discloses an identity authentication method based on a secure computer, which relates to the technical field of computer security, and comprises the following steps: deploying an authentication module, and pre-burning an excitation-response pair library of a physical unclonable function; chaotic mapping parameters are randomly initialized, and a chaotic sequence is generated through improved Logistic mapping; sending random excitation to the PUF to obtain an original response, segmenting the original response, and mixing the segmented original response with the chaos sequence; the confusion response is recombined into a three-dimensional matrix, nonlinear diffusion is achieved through a rotation transformation formula, and then the confusion response is flattened into a final registration response; after the user submits a user name, the system generates a random challenge and a current timestamp; calculating a first authentication factor based on the registration response and the timestamp, and recursively generating a factor chain; and the server repeatedly generates a factor chain for matching, updates a registration response if the matching is successful, and triggers a locking mechanism if the matching is failed. According to the chained dynamic authentication method based on PUF response chaos confusion, the dynamic unpredictability of each authentication session can be realized.

This invention discloses a method and system for identifying enterprise association risks based on graph computing. The method constructs an association graph of multiple types of entities and their complex relationships, and introduces a risk transmission model based on dynamic edge weights and iterative feedback of node risk states. This model simulates the nonlinear diffusion process of risk in the association network, ultimately outputting an accurate list of risk nodes, quantified scores, and key transmission paths, and providing visualized rendering of the results. By dynamically quantifying the strength and probability of risk transmission along different association links, this invention effectively overcomes the shortcomings of traditional static association analysis, which cannot characterize the dynamic and non-uniform transmission process of risk, significantly improving the accuracy, foresight, and decision support value of risk identification.

This invention discloses an internet cloud security thumbnail preservation encryption method based on chain-based sum-diffusion. The main steps are as follows: Extracting the plaintext image size information and invariant features such as pixel sums for each color channel, hashing and fusing them with the master key to generate a derived key related to the image content; using the derived key to drive a chaotic system to generate a pseudo-random sequence with anti-degradation performance; employing a binary space partitioning strategy to process the three channels of the image into irregular rectangular blocks; within each independent sub-block, globally scrambling the pixel positions according to the pseudo-random sequence; finally, based on a pseudo-random traversal path, performing a chain-based sum-diffusion cyclic shift operation on each scrambled sub-block to achieve non-linear diffusion of pixel values. This invention effectively eliminates cross-channel boundary leakage that may result from regular block partitioning while ensuring the semantic usability of the encrypted image at low resolution, and significantly enhances encryption security through a dual mechanism of "scrambling-chain-diffusion".

The present invention belongs to the technical field of speech enhancement, and discloses a speech enhancement method and system based on the Schrödinger bridge diffusion model. This method transforms the diffusion process of the diffusion model into a solution process of a stochastic differential equation, determines the stochastic differential equation according to the theoretical principle of the Schrödinger bridge, and directly uses the complex spectrum as the input of the diffusion model, eliminating the cumbersome work of extracting the phase spectrum and amplitude spectrum from the complex spectrum and the memory overhead caused by the inverse transformation. At the same time, the alignment problem between the phase spectrum and the amplitude spectrum is also avoided. The speech enhancement method of the present invention captures the unique features of the time series signal through the Transformer module, then uses the U-Net module to fuse multi-scale information, and combines loss functions covering the time domain, frequency domain, and time-frequency domain to gradually reduce the difference between the predicted sample and the clean sample, and can directly learn the non-linear diffusion process from the noisy sample to the clean sample, thereby retaining more structural information of the initial sample.

This invention discloses a parameter estimation method, system, device, and storage medium for a nonlinear diffusion model. The parameter estimation method includes: constructing a spatial basis function based on system data snapshots for a nonlinear Fisher-type diffusion system applied to the heating and cooling process of an iron rod, and separating spatiotemporal variables using an orthogonal decomposition method; sparsely sampling the nonlinear terms using a discrete empirical interpolation method to obtain the optimal low-order approximation of the high-order system; initializing a particle swarm to obtain n particles corresponding to the m-dimensional solution vector of the low-order time series model, and calculating the fitness of each particle according to the calculation formula of the parameters to be identified and the objective function; iterating and optimizing each particle, and outputting the position of the particle with the global optimum value; adding a non-Gaussian Levy process to the traditional particle swarm algorithm, and avoiding premature concentration of the particle swarm in the same direction through the random jump of the Levy process, thereby increasing the mutual learning ability between particles.

The application discloses a kind of bill image content identification method and system, method includes: using nonlinear diffusion filter to the source bill image obtained with standard bill image is constructed to obtain nonlinear diffusion scale space;Using image block strategy removes the first layer scale space in nonlinear diffusion scale space, then carries out grid unit division to nonlinear diffusion scale space and obtains stable uniform point feature for feature point extraction;According to point feature, gradient position direction histogram algorithm is used to construct feature point descriptor;Using bilateral fast approximation nearest neighbor algorithm, the feature points expressed by feature point descriptor are matched, and the point pairs of false matching are removed by using random sample consensus algorithm to obtain matching point pair, and the bill image of successful matching is obtained;The bill image is preprocessed, target text is detected, and specific field detection is carried out to obtain the text image labeled with specific field and input into the text recognition model to recognize the text content and obtain the field information.

The invention relates to the technical field of environmental monitoring, in particular to a gas diffusion imaging processing method considering path confidence correction, which comprises the following steps of: calculating link input, establishing a relationship between observation and concentration by adopting a nonlinear diffusion imaging model, and improving inversion stability by adopting path length estimation and confidence correction. A reliable concentration field is obtained through energy functional optimization; based on the concentration sequence and the image sequence, combining brightness consistency and conservation error to estimate a wind speed field, and then using physical stepping and learning residual errors to obtain an evolution operator with physical and data constraints to predict the concentration of a plurality of steps in the future; a prediction module is embedded into system dynamics, the influence of equipment actions on the concentration is described, a risk measurement design and an optimization control strategy are configured, and a key area is controlled to keep the safe concentration under various disturbances. According to the scheme, the problems of unstable imaging error and diffusion prediction, uncontrollable intervention and the like in the traditional technology are solved.

The present application provides a pipeline early micro-leakage anomaly detection method based on deep learning, relating to the field of data anomaly detection, specifically comprising a disturbance coupling analysis and embedding module, a disturbance condition propagation module, a residual projection modulation module, and a model fusion and anomaly detection module. First, the monitoring data is encoded into a disturbance state tensor by the disturbance coupling analysis and embedding module, solving the response difference and asymmetric coupling problem. Next, the disturbance condition propagation module is used to model the nonlinear diffusion of the disturbance between time series and features. Then, the residual projection modulation module is used to realize multi-scale cointegration analysis and extract robust features. Finally, the model fusion and anomaly detection module integrates multi-scale information and obtains micro-leakage anomaly detection values.

The invention provides an Internet of Vehicles image encryption method based on four-dimensional memristor hyper-chaos, which comprises the following steps: calculating a hash value of a plaintext image, and calculating an initial value of a four-dimensional hyper-chaos system; substituting into a four-dimensional hyper-chaotic system for iteration, and quantifying to obtain four groups of chaotic sequences; dividing a plaintext image into a processing area, dividing the processing area into 36 sub-blocks, mapping the 36 sub-blocks into a pyramid magic cube, and scrambling by using a first group of chaotic sequences; dividing each sub-block into 36 micro-blocks again to construct a pyramid magic cube, performing scrambling by using a first group of chaotic sequences, dividing a generated middle area image into 9 sub-blocks, extracting 4 pixels from each sub-block to reconstruct the pyramid magic cube, and performing scrambling by using the first group of chaotic sequences; converting the scrambled image into a binary matrix, and dividing the binary matrix into four bit planes for nonlinear diffusion; and converting the diffused image matrix into a one-dimensional sequence for ciphertext feedback, and generating a ciphertext image. According to the method, high encryption efficiency is ensured, and meanwhile, the anti-attack capability is remarkably enhanced.

The application discloses a lithium battery energy storage monitoring method and system, which comprises the following steps: obtaining a historical solid-phase diffusion coefficient sequence and a historical liquid-phase impedance sequence, and establishing a coupling correlation matrix therebetween; obtaining a real-time solid-phase diffusion coefficient and a real-time liquid-phase impedance through online identification; selecting a first candidate period through sliding window correlation analysis; selecting a second candidate period through impedance spectrum shape similarity calculation; calculating a current capacity loss amount by using a nonlinear diffusion-impedance coupling model; determining a current calibration capacity based on an initial calibration capacity and an aging factor; and determining a remaining available capacity based on the current calibration capacity and the current capacity loss amount. By extracting the diffusion-impedance coupling correlation matrix from historical data and deeply embedding the whole process of parameter identification, candidate period screening, capacity loss calculation and remaining capacity evaluation, the accuracy and robustness of the estimation of the remaining available capacity of the lithium battery are significantly improved.

The present application provides a pipeline early micro-leakage anomaly detection method based on deep learning, relating to the field of data anomaly detection, specifically comprising a disturbance coupling analysis and embedding module, a disturbance condition propagation module, a residual projection modulation module, and a model fusion and anomaly detection module. First, the monitoring data is encoded into a disturbance state tensor by the disturbance coupling analysis and embedding module, solving the response difference and asymmetric coupling problem. Next, the disturbance condition propagation module is used to model the nonlinear diffusion of the disturbance between time series and features. Then, the residual projection modulation module is used to realize multi-scale cointegration analysis and extract robust features. Finally, the model fusion and anomaly detection module integrates multi-scale information and obtains micro-leakage anomaly detection values.

To address the lack of sufficient degradation data for long-life and high-reliability equipment, this paper proposes a method for predicting the remaining life of degraded equipment that accounts for multiple uncertainties. This method includes a step-accelerated degradation model based on a nonlinear diffusion process. The advantage of this model is that it requires only a small sample size and a short testing time. The model accounts for multiple uncertainties caused by the inherent characteristics of the degradation model, individual variability, measurement equipment performance, and human bias in the degradation process. The model considers time-varying uncertainty, individual variability, and measurement uncertainty of performance degradation and covariates. To estimate the remaining life of degraded equipment, the present invention derives an analytical approximate solution for the nonlinear diffusion process crossing a predetermined threshold in terms of first arrival time. Combining the maximum likelihood estimation (MLE) method with the simulation-based extrapolation (SIMEX) method, an MLE-SIMEX method is derived for estimating unknown parameters in the model. The effectiveness of the proposed model is demonstrated through simulations and real-world cases. Results demonstrate that this method achieves higher remaining life estimation accuracy and has practical engineering value.

The present application relates to the technical field of environmental monitoring, and more particularly to a gas diffusion imaging processing method considering path confidence correction, comprising: calculating link input, establishing the relationship between observation and concentration by using a nonlinear diffusion imaging model, improving inversion stability by using path length estimation and confidence correction, and obtaining reliable concentration field through energy functional optimization; based on concentration sequence and image sequence, combining brightness consistency and conservation error to estimate wind speed field, and then using physical stepping and learning residual to obtain evolution operator prediction of future concentration with physical and data constraints; embedding the prediction module into system dynamics to describe the influence of device action on concentration, configuring risk measurement design and optimization control strategy, and controlling the key area to maintain safe concentration under various disturbances. The present application solves the problems of imaging error, unstable diffusion prediction and uncontrollable intervention in the prior art.

The invention provides a chip data encryption method and system, and relates to the technical field of data encryption, and the method comprises the steps: obtaining to-be-encrypted chip data and an SRAM power-on initial state of a chip; performing block type nonlinear diffusion on the chip data to be encrypted by utilizing the power-on initial state of the SRAM; generating an encryption key through a chaotic mapping algorithm in combination with the power-on initial state of the SRAM; performing staggered encryption on the to-be-encrypted chip data after nonlinear diffusion through the encryption key to obtain a complete ciphertext; and performing anti-side channel verification based on Hamming distance on the complete ciphertext, if the verification is passed, outputting the complete ciphertext to complete the encryption process of the to-be-encrypted chip data, otherwise, increasing the chaotic coefficient in the chaotic mapping, and returning to regenerate the encryption key. According to the scheme, the hardware randomness of the SRAM is used as an encryption basis, the data blocks are subjected to nonlinear diffusion and staggered encryption, and the encryption security is enhanced.

The invention relates to the technical field of image processing, in particular to an optical key and high-dimensional chaos dynamics combined image encryption method and device, and the method comprises the following steps: obtaining a CIE color coordinate pair, generating RGB vectors, laying the RGB vectors into a key matrix, executing the pixel-by-pixel XOR fusion operation, and obtaining a fused optical key image; extracting an initial vector and a Hash fingerprint, constructing a high-dimensional chaotic power system, and performing Lyapunov spectrum adaptive optimization to obtain an optimal parameter group; dynamically generating one or more pairs of chaotic sequences, dividing the chaotic sequences into scrambling sequences and diffusion sequences, and dynamically constructing an S-box lookup table; performing global scrambling, forward depth nonlinear diffusion and backward global avalanche diffusion to obtain a final ciphertext block; and performing final chaos mask whitening to obtain a ciphertext image. According to the method and the device provided by the invention, the key system driven by the physical parameters can be quantified, the safety and the replaceability are improved, and the randomness and the anti-prediction capability are improved.