48results about How to "Interpretable" patented technology

The invention discloses a physical information neural network hyperspectral band selection method for target identification, which uses physical information SDI as prior information to be combined with a channel attention mechanism added in a deep neural network to guide band selection, and evaluates the advantages and disadvantages of band weights through a reconstruction module after the weights are generated. Wave band selection is carried out accordingly; according to the hyperspectral image target recognition waveband selection method based on the physical information neural network, compared with a traditional method, the process is simplified and the precision is improved through end-to-end learning, the utilization of spatial context information can be enhanced by adding an attention mechanism, and the model has interpretability by adding prior SDI information.

This invention discloses a method, apparatus, electronic device, and storage medium for classifying license plate images. The method includes: in response to an image classification instruction for a target license plate image, determining image feature data of the target license plate image; inputting the image feature data into a pre-trained license plate classification model; and outputting an execution result for classifying the target license plate image, the execution result including at least two classification items and the probability of each classification item, wherein the at least two classification items are distributed in a tree-like structure. The technical solution of this invention achieves more accurate classification of license plate images, and the classification process is interpretable.

The present application relates to a kind of preparation methods of essence.The problems that traditional process parameter adjustment relies on artificial experience and is difficult to realize cross batch self-adaption, multi-modal feature extraction, parameter-function-stage three-dimensional label matrix generation, graph neural network behavior atlas construction and expert strategy distribution constraint dual-channel strategy learning method are proposed.By process parameter and derived feature multidimensional fusion, time series causal strength analysis and action instruction simulation verification, optimization process parameter combination with explainable function synergistic relationship can be output.The technical scheme effectively realizes the automatic optimization of process control decision and the rapid self-adaption of model under new raw material batch, improves product consistency, quality stability and control energy efficiency.

The invention discloses a front door adjustment-based harmful modal cause detection depolarization method, which comprises the following steps of: constructing a structural causal model, creating a back door path between a modal cause and a harmful label by using unobserved confounding factors, and eliminating harmful modal cause detection through front door adjustment; the front door adjustment then blocks the back door path by introducing reasoning as an intermediary between the memetic and the tag. The method comprises the following steps: decomposing the causal effect of a medal factor on a harmful tag into the influence of the medal factor on an intermediary, quantifying by adopting a multi-modal large-scale language model with different beam searches to calculate the probability of each reasoning sequence and the influence of the intermediary on the tag, and performing effective approximation through a normalized weighted geometric averaging method; finally, post-interpretation is synthesized from the inference sequence and the predictive tag using a large language model. According to the scheme, the most advanced performance is achieved while information interpretation is provided.

This application relates to the field of data processing technology, and in particular to a data fusion method and system based on neural pathways. The method includes the following steps: First, acquiring electroencephalogram (EEG) data and eye-tracking (EMT) data, aligning them using timestamps, and preprocessing them separately; then, extracting EEG features based on the preprocessed EEG data; extracting EMT features based on the preprocessed EMT data; next, fusion of features based on the EEG and EMT features by downsampling the data; finally, evaluating the synergy of the fused features. This application constructs a complete evaluation system by building a framework from a stimulus-visual paradigm to a signal acquisition platform and analysis methods related to neural structures. The time delay between the most relevant points in the time domain of eye-tracking and EEG features is used as an indicator of brain-eye synergy. The difference between these indicators has interpretability based on physiological structures, constituting a novel evaluation indicator for brain-eye synergy when assessing dynamic visual acuity.

The application provides a three-dimensional part retrieval method based on graph similarity search, relates to the field of computer graphics, and solves the technical problem that the prior art cannot fully utilize the geometry and design semantic information of CAD, and it is difficult to capture and display the topological relationship, resulting in low retrieval efficiency. The method comprises the following steps: obtaining part three-dimensional data of a computer-aided design (CAD) model, and constructing a training data set; constructing an edge-face connection graph based on the part three-dimensional data; calculating a graph edit distance (GED) matrix of all edge-face connection graphs in the training data set as a supervision signal; training a ranking model based on the GED matrix, mapping the edge-face connection graph to a hidden space, and constructing a part vector database according to the output graph-level embedding vector; the ranking model is constructed based on a graph attention network; inputting a CAD part to be queried into the trained ranking model to obtain a feature vector, performing nearest neighbor search in the part vector database, and returning a similar part result.

The application discloses a kind of robust direction of arrival estimation method based on ADMM-Net, by expanding ADMM algorithm into model-driven deep network ADMM-Net to improve DOA estimation accuracy, speed up DOA estimation speed and have robustness to array disturbance.Firstly, the sparse transformation of source and array received multi-shot data is carried out by space over-complete dictionary, and the DOA estimation is converted into compressed sensing sparse recovery problem;Then, ADMM algorithm is expanded, and model-driven deep network ADMM-Net with explainability is formed;ADMM-Net is used to reconstruct source power spectrum and carry out DOA estimation.The present application can learn the hyperparameters in iterative algorithm and array disturbance, solve the problem that existing compressed sensing DOA estimation method based on calculation speed is slow, and fails under the condition of array disturbance, realize fast, accurate, explainable and robust DOA estimation.

The invention discloses a cardiac magnetic resonance report generation method and system based on a multi-dimensional tissue feature knowledge graph. The method comprises the following steps: performing motion correction and multi-view feature extraction on a cardiac magnetic resonance multi-sequence image to obtain an original numerical attribute of an instance node; constructing a dynamic knowledge graph containing tissue characteristics and medical priori, and generating a target reasoning chain with a clinical basis in combination with neural symbol reasoning; then, in a controlled generation stage, an inference chain is injected into a prefix tree, in a decoding step, mask physical shielding logic conflict description is utilized, and a pointer network is synchronously started to directly copy original numerical value attributes into a text sequence; and finally, executing consistency logic verification through a text restoration technology, and identifying and intercepting factual errors. Through the atlas constraint and numerical unvarnished transmission mechanism, the factual illusion problem of a generative model is effectively solved, and the accuracy and reliability of a heart diagnosis report are remarkably improved.

The invention relates to the technical field of ultrasonic image analysis, and discloses an image detection method and system for prolonging the second birth process of double-fetal vaginal delivery and SPPH risk based on ultrasonic Speckle-tracing, and the method comprises the steps: obtaining an ultrasonic two-dimensional gray-scale image sequence; marking a conjoint analysis area between the cervical wall and the front and rear walls of the vagina; constructing a joint area displacement field; constructing a joint region strain trajectory; extracting parturition process characteristic indexes; and executing risk assessment through a fuzzy rule. The technical problem that in the prior art, risk judgment depends on clinical experience, and especially under the condition that continuous stretching occurs on the cervix uteri and vagina combined wall in the second birth process of double-fetal vaginal delivery, early recognition of the evolution process of the tissue from reversible stretching to irreversible instability is difficult to achieve is solved. Due to the fact that joint area displacement field modeling and logarithmic nonlinear strain analysis are introduced, quantitative characterization and continuous risk description of the mechanical behavior of the tissue in the labor process are achieved.

The invention relates to the technical field of injection molding, in particular to an intelligent control system and method based on injection mold opening of an injection mold, and aims to solve the problems that an existing injection mold opening control system depends on a single signal in safety judgment, lacks multi-physical field fusion and fault confidence evaluation, is difficult to distinguish disturbance and real faults, and is low in reliability. The interlocking logic is extensive, and the grading response based on the abnormal grade cannot be realized. Multi-source preprocessing data are deeply fused through the mold opening state monitoring and interlocking module, accurate recognition and causal traceability of faults are achieved by quantifying physical interpretable indexes such as temperature field uniformity, force sudden change, vibration spectrum and micro-strain and combining an evidence combination and credibility updating mechanism, disturbance and real abnormity are effectively distinguished, and the fault diagnosis accuracy is improved. And according to the hierarchical interlocking of the abnormal levels, the mold opening safety permission is output only when the whole channel is normal and no high-confidence fault exists, so that the safety and the intelligent level of the mold opening process are remarkably improved.

The present application relates to the technical field of aluminum electrolysis, and provides an aluminum electrolysis cell damage inversion method based on a machine learning algorithm, comprising the following steps: obtaining current data of an aluminum electrolysis cell through a fiber-optic current sensor, and obtaining temperature data of the aluminum electrolysis cell; performing discharge area division according to a discharger of the aluminum electrolysis cell; performing area division on the current data and the temperature data, and performing feature extraction on the current data and the temperature data; establishing a physical information forward model based on a neural network, and associating and mapping a damage state vector with current feature data and temperature feature data through the physical information forward model; constructing a cathode joint loss function and an anode joint loss function; respectively performing iterative solution on the cathode joint loss function and the anode joint loss function through an optimization algorithm, outputting an optimal damage state vector, and generating a damage space distribution result of the electrolysis cell. The present application can realize online inversion and spatial distribution visualization of anode and cathode damage states.

The invention discloses a sludge age self-adaptive regulation and control method and system based on dissolved oxygen trend recognition. Aiming at the problem of impact response lag caused by difficulty in COD on-line measurement, the method comprises the following steps: under the condition of stable water inlet and aeration, filtering and sliding window feature extraction are performed on an on-line DO signal to obtain a regression slope representing the change of DO along with time, and COD rising impact is reliably identified in combination with an ORP persistence criterion. A mechanism and machine learning fusion model is adopted to determine an identification threshold value and a target sludge age SRT, the sludge discharge amount is rapidly adjusted after impact triggering, the treatment capacity is synchronously matched, and aeration is used for assisting in maintaining DO stable. The system integrates an online monitoring module, a DO recognizable interval judgment module, a feature calculation module, a load recognition module, an SRT decision module and a sludge discharge execution module. According to the method, rapid impact recognition and closed-loop regulation and control can be realized without an online COD instrument, and the impact resistance and the operation stability of the process are remarkably improved.

The application discloses a kind of multi-agent learning method, device and equipment based on dynamic weighted average field, method includes: according to the action of dynamic weighted average action corresponding to agent selects action;Current position information of agent is obtained Calculation aggregation factor, the weight of agent is dynamically updated using improved PSO algorithm in combination with aggregation factor;According to the action update dynamic weighted average action with weight, execute joint action to obtain next state, according to the reward update action and state, and according to the weight and reward update individual weight optimal value and group weight optimal value;Experience replay buffer is sampled from experience data including current state, joint action, reward, next state and dynamic weighted average action and updates the Q function of agent, according to the updated Q function and specified learning rate updates the target network of agent.The application can guide multi-agent to tend to group performance optimization, and also ensure that individual agent has sufficient exploration ability.

The invention discloses a geological disaster dynamic early warning method driven by multi-source data and an intelligent model, and belongs to the technical field of geological disaster early warning. The method comprises the following steps: acquiring multi-source heterogeneous geological monitoring data; performing space-time alignment and semantic standardization processing, and constructing a standardized data set; constructing a multi-modal deep fusion neural network model, extracting features through a parallel feature extraction sub-network, and carrying out feature fusion by adopting a cross-modal attention mechanism based on a historical accuracy rate dynamic adjustment weight; disaster risk prediction is carried out based on fusion features, and online model updating is realized through a sliding time window mechanism; and generating an early warning report according to the risk level. According to the invention, an early warning effect feedback closed loop mechanism is also established, and model iterative optimization is realized through postmortem verification of returned data. According to the method, a complete closed loop from data perception to model self-optimization is constructed, and the problems of poor semantic consistency, static feature fusion and insufficient early warning real-time performance of multi-source data are solved.

The application relates to the technical field of data processing, and provides a business processing method, device and equipment under a parallel architecture of a new system and an old system. The method comprises the following steps: receiving a processing request; according to a shunting configuration, shunting the processing request to a target system for processing; the target system comprises at least one of a new system and an old system; when the new system fails to process the processing request, identifying a failure category of the processing failure according to a white-box model; when the white-box model fails to identify the failure category, identifying the failure category of the processing failure according to a black-box model; and according to the identified failure category, deciding to re-shunt the processing request. The embodiment of the application can reduce the processing burden and invalid processing cost of the old system under the parallel architecture of the new system and the old system.

The invention discloses a hierarchical alignment method and system for a multi-modal perception data set of a soft manipulator, and the method achieves the coverage of a whole process from data quality evaluation to feature space alignment to semantic consistency optimization through the three-stage design of single-modal noise evaluation, feature-level adaptive alignment and semantic-level constraint alignment. The limitation that a traditional method only pays attention to single-level alignment is broken through, and the model can gradually adapt to the complex characteristics of touch multi-mode perception. Secondly, an adaptive temperature function is designed based on modal pair comprehensive reliability, and a strict monotone mapping relation between temperature coefficients and modal noise characteristics is established, so that a high-noise modal pair automatically obtains a relatively large temperature coefficient to enhance robustness, and a low-noise modal pair automatically obtains a relatively small temperature coefficient to improve alignment precision; the technical problem that the fixed temperature coefficient cannot adapt to the touch multi-mode heterogeneous noise characteristic is fundamentally solved, and end-to-end sensitivity adjustment is achieved through the global learnable self-adaptive adjustment coefficient.

This invention discloses a big data-based EVA membrane product production management system and method, belonging to the field of industrial big data analysis and production management technology. It includes: acquiring multi-source heterogeneous production data from various stages of the EVA membrane product production process; performing data cleaning and standardization to obtain a standard production dataset; extracting key production features from the dataset and constructing a multi-dimensional feature vector space; using a density-based clustering-based anomaly detection algorithm to perform pattern recognition on the feature vector space, generating a set of abnormal production events; using an association rule mining algorithm to extract association rules between abnormal events and production parameters, obtaining a root cause parameter set; constructing a production parameter adjustment decision tree; and generating production optimization strategies based on the decision tree. This invention also provides a corresponding system that realizes automatic root cause analysis and parameter optimization feedback for EVA membrane product production anomalies.

This invention provides a method and system for precise source tracing of nitrogen compound pollution sources based on multimodal data fusion and graph neural networks, belonging to the field of pollution source tracing technology. This invention acquires and quantifies the multimodal fingerprint features of each typical pollution source to form a source feature matrix, obtains multimodal spectral data from downstream monitoring points to obtain actual monitored downstream fingerprint vectors, and constructs a spatial topology map based on the spatial topology between monitoring points. The source feature matrix and the spatial topology map are input into a graph neural network to obtain contribution weight vectors, and the predicted downstream fingerprint vectors are reconstructed accordingly. A composite loss function including spectral reconstruction loss, physical constraint loss, and sparsity constraint is constructed, and convergent contribution weights satisfying non-negativity and sum-to-one constraints are obtained through iterative optimization. This invention can output a physically meaningful and interpretable quantitative contribution rate of pollution sources for precise source tracing analysis in nitrogen compound pollution scenarios.

This invention relates to the field of environmental water conservancy and ecological restoration technology, and discloses a method for evaluating the effectiveness of river restoration based on multi-source data. The method includes: collecting target and measure-type indicator data; preprocessing the data; dividing the indicators into time-series and non-time-series types; applying exponential time decay weighting to the time-series indicators to generate time-series characteristic weighted indicators; performing robust standardization of the median absolute deviation with the non-time-series indicators to generate a standardized indicator dataset; calculating the proportion and information entropy of each standardized indicator within each sample to construct the total information entropy; calculating the residual average sum using the equally weighted average as the measured effectiveness value and the initial weighted average as the simulated effectiveness value; constructing a joint loss function; solving for the function with the goal of minimizing the joint loss function to generate the optimal weights for each standardized indicator; and finally calculating a comprehensive restoration effectiveness index to quantitatively evaluate the river restoration effect. This invention enables quantifiable and comparable evaluation of restoration effects in different watersheds and at different times.

The application belongs to the technical field of image compressive sensing reconstruction, and discloses an image compressive sensing reconstruction method and system based on optimization algorithm expansion. In the sampling stage, a convolution sampling method is used instead of a traditional random matrix sampling. In the reconstruction stage, a generalized iterative threshold shrinkage algorithm is expanded into a deep network, and a jump information connection structure is designed in a reconstruction submodule R. Residual modules are used to connect the feature information before and after the modules, so that the inherent information loss in the deep expansion network is avoided. Furthermore, a double-scale denoising module is designed at the back end of the reconstruction submodule R, and different scale features are combined to denoise the image. The application not only realizes the application of the algorithm expansion method in the image compressive sensing, but also improves the reconstruction effect by using the jump connection structure and the double-scale denoising module. The application has higher accuracy and better robustness.

This application relates to the technical field of computer vision, and in particular to a method and system for identifying paint formulation components based on multi-angle and multimodal measurement. The method includes: acquiring multimodal measurement data of a paint sample under test from multiple angles, including image data, spectral data, and texture data; extracting and fusing features from the multimodal measurement data to obtain a formulation-level feature vector; determining the types of colorants contained in the paint sample and the presence confidence of each colorant based on the formulation-level feature vector and a pre-constructed colorant standard feature library, using an attention mechanism and a multi-label classifier; and for colorants whose presence confidence meets preset conditions, performing physically constrained regression prediction based on the formulation-level feature vector, the colorant standard feature library, and the colorant presence confidence to determine the content proportion and content prediction confidence of the colorants. This application improves the formulation identification effect and accuracy under multiple colorant conditions.

The present application relates to the technical field of intelligent cockpit energy management and power dispatching control, and discloses a kind of dynamic adjustment method of intelligent cockpit equipment power priority.The power demand, minimum continuous power supply time, category and request state are collected by being numbered to all equipment, and the real needed equipment is screened out according to fixed period, the average power and reference duration are counted, the bidding factor is generated combined with category, relative power and relative duration, the factor is sorted and the assignable power is prefixed and cumulatively distributed, the priority is given and the record table is formed;the recursive delay count is carried out on the equipment with continuous request and not distributed at the end of the period, and the forced threshold is set;the fairness is guaranteed in the next period;the on-off instruction is executed at the same time, and the long-term non-requested equipment is identified and removed;if the conditions are met, it is included again, and the cycle is promoted.

A kind of defect detection method of magnetic material, original binary image is obtained by image acquisition and preprocessing;Extract the compactness, bite mark sharpness and four-corner asymmetry of original contour before closing operation, constitute Raw Mask Trident feature, retain the tiny defects covered by morphological operation;At the same time, 16-dimensional macro shape features are extracted by closing operation, combined with 10-dimensional microscopic texture features extracted by uniform pattern LBP, a multi-feature fusion system is constructed;The training of multi-feature fusion system is completed by using weighted XGBoost classifier, and the decision boundary is optimized by dynamic threshold search, and finally the defect is judged.The present application realizes anti-interference detection by the feature extraction method of Raw Mask Trident, balances the precision and recall rate by combining sample weighting and dynamic threshold, can realize high-precision, low-false alarm, interpretable automatic detection of edge collapse, bite mark, internal crack and color point, and realizes quality control in the production process of magnetic components.

The application discloses a kind of hierarchical alignment method and system of soft manipulator multi-modal perception dataset, through the three-stage design of "single modal noise evaluation→feature level adaptive alignment→semantic level constraint alignment", realize from data quality evaluation to feature space alignment again to semantic consistency optimization Full-process coverage, break through the limitation that traditional method only pays attention to single level alignment, make model can gradually adapt to the complex characteristics of tactile multi-modal perception.Secondly, based on the adaptive temperature function of modal pair comprehensive reliability design, a strict monotonic mapping relationship between temperature coefficient and modal noise characteristics is established, so that the high-noise modal pair automatically obtains a larger temperature coefficient to enhance robustness, and the low-noise modal pair automatically obtains a smaller temperature coefficient to improve alignment accuracy, which fundamentally solves the technical problem that the fixed temperature coefficient cannot adapt to the heterogeneous noise characteristics of tactile multi-modal, and realizes end-to-end sensitivity adjustment through globally learnable adaptive adjustment coefficient.

The invention is applicable to the technical field of computers, and provides an SQL (Structured Query Language) statement auditing method which comprises the following steps: receiving a to-be-audited SQL statement, generating an execution plan tree from the SQL statement, and extracting an operator node sequence from the execution plan tree; performing atomic feature extraction on each operator node in the operator node sequence to obtain a multi-modal feature vector; for each operator node, cost prediction and performance prediction are carried out based on the multi-modal feature vector, and a multi-modal feature portrait is constructed; performing multi-target causal analysis on the basis of the multi-modal feature portrait, and determining dominant features; on the basis of the dominant features, optimization suggestions are generated in combination with a large language model, the limitation of single-dimensional analysis is broken through, multi-objective collaborative optimization of performance and cost is achieved, the professional threshold and workload of database administrators and developers are greatly reduced, and the efficiency of SQL auditing is improved.

The application relates to a rolling bearing domain adaptive fault diagnosis method based on an attention mechanism. Collected rolling bearing vibration monitoring signals are extracted to deep fault features by a one-dimensional separable convolution and embedded channel attention mechanism and length attention mechanism feature extractor; a local attention domain adaptive module and a global attention domain adaptive module are constructed to screen signals and signal segments with good migratability, so that the generalization ability of the model is improved, the model can better cope with the variable working condition fault diagnosis problem; compared with a migration learning intelligent fault diagnosis algorithm, the algorithm considers that different signals and signal segments have different migratability, and the model has improved explainability; experiments on various bearing vibration data verify that the algorithm has good performance stability and can still have excellent diagnosis results under various working condition change conditions.

The invention discloses an ultrasonic transparent metal OFDM receiving method and device for resisting multipath fading, and relates to the technical field of ultrasonic transparent metal communication and digital signal processing. The method comprises the following steps: acquiring a frequency domain signal received in a multipath channel; an ultrasonic transparent metal OFDM system is constructed; the ultrasonic metal-penetrating OFDM system comprises an MCGBNet receiver, a metal-penetrating OFDM (Orthogonal Frequency The MCGBNet receiver comprises a channel estimation sub-network and a signal detection sub-network; a received frequency domain signal and a known sending pilot symbol are input into a channel estimation sub-network to estimate channel frequency responses of all subcarriers; and inputting the channel frequency responses of all the subcarriers and the received data symbols into a signal detection sub-network, and converting soft bits into final binary bits through a decision rule. According to the invention, the original information bit can be effectively extracted and restored from the fading signal.

The invention provides a service pushing method and device, equipment, a medium and a product, and relates to the technical field of data pushing.The service pushing method comprises the steps that service query information is generated from a user query request based on a preset graph database query model, and the service query information is used for querying a service database; executing the service query information to obtain at least one piece of candidate recommendation service information in a service database; determining target recommendation service information in the at least one piece of candidate recommendation service information according to the similarity between the service query information and the candidate recommendation service information; and pushing the target recommendation service information to a terminal associated with the user query request. Through the embodiment of the invention, the accuracy of the business recommendation scheme, the system fault tolerance and the business response efficiency are remarkably improved, and efficient and accurate intelligent recommendation service experience is provided for the user.

The invention provides a battle failure clue reactivation method and device and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: carrying out the data cleaning of obtained multi-modal data, and obtaining a clue wide table; performing text hierarchical classification on the clue wide table to obtain a hierarchical classification result; performing entity extraction on the hierarchical classification result to obtain a client intention; based on a preset rule, screening the customer intention and the corresponding sales clues, and taking the sales clues meeting all the preset rules as compliance clues; and matching a target dealer based on the compliance clues, so as to efficiently utilize the battle-failure clues.

This invention provides a composite detection method and apparatus for PCB defects based on logical operations and geometric analysis. The method includes using an AOI camera to photograph the PCB, calculating the adaptive local difference of the PCB image, and initially screening out discrepancy regions. Multi-scale evaluation is performed on the discrepancy regions, and differential geometric flow is used to evolve the linewidth anomaly regions to filter out process noise and obtain the region's geometric structure. The true topological manifold of the region's geometric structure is detected, and compared with the standard topological manifold to determine the PCB circuit defect type. This invention is based on differential geometric flow and topological manifold, possessing a certain degree of interpretability, and is not a deep learning algorithm, thus not relying on a large number of samples. Differential geometric flow is used to smooth the sharp burrs at the edges caused by the etching process, and the PCB circuit defect type is determined based on the topological characteristics of the PCB region, thereby eliminating interference from lighting conditions, PCB substrate color fluctuations, and nonlinear expansion and contraction during the lamination process.