39results about How to "Guaranteed interpretability" patented technology

The invention discloses a thermal power generating unit coordination control data and mechanism hybrid modeling method and device, computer equipment and a computer readable storage medium, and relates to the technical field of thermal energy engineering and power system modeling and control. Establishing a high-precision dynamic mechanism model of the working medium flow and heat transfer process of the boiler-steam turbine system; then, constructing an error correction model fusing the long-short-term memory network, the convolutional neural network and residual connection; and finally, fusing the mechanism model and the error correction model through parallel computing to form a dynamic hybrid model with physical interpretability and high precision. Through the hybrid modeling strategy, the prediction accuracy of key parameters such as the main steam pressure, the separator outlet steam enthalpy value and the unit load in the wide load range, especially under the dry-state operation working condition is remarkably improved, and a reliable model basis is provided for designing an advanced unit coordination control system.

The invention discloses a multi-modal contrast learning fault diagnosis method for a small sample scene, and the method comprises the following steps: carrying out the enhancement of a one-dimensional signal and two-dimensional image fused fault data set through physical simulation for the small sample scene with scarce industrial fault data, and constructing a positive and negative sample pair through a plurality of data enhancement strategies; based on heterogeneous multi-modal fault data, designing a double-flow encoder architecture of a time sequence branch and an image branch, extracting depth features and mapping the depth features to a unified feature space through a projection head; performing supervised contrast learning pre-training based on intra-modal and inter-modal dual contrast loss; supervision fine tuning is carried out based on multiple loss functions such as physical guidance, so that accurate diagnosis of equipment faults is realized in a small sample scene. According to the fault diagnosis method under the unbalanced sample and limited labeling conditions, the problem that a traditional data driving model depends on large-scale labeling samples is effectively relieved through supervised comparative learning and cross-modal information alignment.

The invention provides a clothing pattern intelligent generation method and system based on multi-modal visual identification, and relates to the technical field of visual identification. The method comprises the following steps: firstly, acquiring clothing image data and text description data, performing unified preprocessing, obtaining a style category label, an appearance attribute label and a local contour key point set through multi-modal visual identification, generating structure semantic elements and geometric anchor points by utilizing a semantic-to-structure mapping knowledge base, and constructing a plate type structure diagram; further analyzing the structural constraint and executing constraint solution to generate a candidate pattern; and in combination with manufacturability verification and constraint correction, closed-loop optimization is formed, a target plate type file meeting the structure and manufacturing requirements is output, and effective connection from semantic recognition to plate type structure generation is realized.

The application provides a spoken-to-written conversion method and device based on reinforcement learning, equipment and medium, wherein the method comprises: obtaining a spoken text; inputting the spoken text into a conversion model to obtain a written text output by the conversion model; the conversion model is obtained by reinforcement learning, taking the editing operation of each word in the sample spoken text as an action, and taking the semantic consistency between the sample written text obtained by performing the editing operation and the sample spoken text and / or the written degree of the sample written text as a reward. The method, device, equipment and medium provided by the application break the limitation of insufficient labeled data in the process of reinforcement learning, and the semantic consistency and written degree give high-level and interpretable rewards. The conversion model obtained by application of the conversion model ensures the reliability and interpretability of the conversion from spoken text to written text.

A dynamic statistics and result analysis system for watershed river and lake shoreline development and utilization comprises a remote sensing data acquisition module, a data preprocessing and classification module, a database construction module, a change trend analysis module, a river and lake directory and association retrieval module and an interaction management module. The data preprocessing and classification module is used for data preprocessing and statistical classification, the database construction unit is used for constructing a system database, the variation trend analysis module is used for variation trend analysis and statistical report generation, and the river and lake directory and association retrieval module is used for directory maintenance and result association. According to the dynamic statistics and result analysis system for watershed river and lake shoreline development and utilization, a remote sensing data statistical classification algorithm based on a neural network is proposed to classify remote sensing data; and a river-lake shoreline development and utilization change trend analysis algorithm based on deep learning is proposed to analyze the change trend.

The invention relates to the technical field of robot performance evaluation, in particular to a robot acceleration performance evaluation method and device, and the method comprises the steps: generating an acceleration mapping matrix of a robot according to a pre-constructed robot dynamic model; performing singular value decomposition on the acceleration mapping matrix to obtain at least one singular value representing the geometric features of the dynamic operable ellipsoid of the robot; and calculating at least one composite acceleration performance index of the robot according to the at least one singular value, and generating an acceleration performance evaluation result of the robot according to the at least one composite acceleration performance index. Therefore, the problem that the overall dynamic performance of the robot under the actual complex working condition cannot be accurately represented due to the fact that the evaluation result is easy to have one-sidedness due to the fact that a single acceleration related index is usually adopted as the evaluation basis in the related technology is solved.

The invention discloses a gastrointestinal symptom identification method and a sensing system, and relates to the technical field of health informatics and medical information processing, and the method comprises the steps: collecting excitation response and abdominal sound to calculate an acoustic transfer function, and employing a main formant frequency to invert a quality loading index representing a condensation water film effect; constructing an equalization gain based on the transfer function to carry out spectral shape correction on the abdominal sound time-frequency spectrum; constructing a symptom evidence vector and performing adaptive weighted scaling on the symptom evidence vector by using a quality loading index; and finally calculating the distance between the weighted vector and the symptom mode prototype library and mapping the distance into a prompt probability. According to the method, the problems of acoustic link drift and signal distortion caused by microenvironment humidity change in long-time monitoring are solved, and the accuracy and robustness of symptom identification are improved.

The application discloses a carbon footprint data quality detection method and device and a storage medium, and belongs to the technical field of data quality detection. The method comprises the following steps: acquiring to-be-detected data, searching for at least one field knowledge information associated with the to-be-detected data in a knowledge database, calling a data quality discrimination model, identifying data characteristic information of the to-be-detected data, determining data quality information of the to-be-detected data according to the data characteristic information, combining the to-be-detected data, the field knowledge information and the data quality information, generating enhanced prompt information, inputting the enhanced prompt information into a large language model, and obtaining a quality detection result of the to-be-detected data generated by the large language model based on the enhanced prompt information. According to the cooperative detection mechanism of the fusion of multi-source information and the artificial intelligence discrimination model, the accuracy and reliability of the multi-modal and heterogeneous carbon footprint data quality control are significantly improved.

The application provides an optical element surface simulation method based on a physical information neural network, relates to the technical field of element design and simulation, and comprises the following steps: constructing a feedforward neural network; generating a deformation control equation model library; constructing a three-dimensional simulation database; forming a machine learning parameter library; training a PINN deformation simulation model in combination with the deformation control equation model library, the three-dimensional simulation database and the machine learning parameter library; screening out a target PINN deformation simulation model meeting preset conditions; inputting design parameters, support structure parameters and given external load parameters of different combinations into the target PINN model to obtain key performance prediction results of the optical element; the application can not only quickly evaluate the key performance of the element under various parameter combinations, shorten the design iteration cycle and reduce the trial and error cost, but also provides direct data support for support structure optimization design, and effectively solves the bottleneck problem of the traditional method in restricting the research and development efficiency of a high-precision optical system.

The invention relates to the technical field of engine state monitoring, and provides an engine oil water pollution prediction method. The method comprises the steps that a condensation sub-model is obtained, and the condensation sub-model is established according to the engine blow-by mass flow and the blow-by temperature history and used for calculating the mixing amount of liquid water entering engine oil; an evaporation sub-model is obtained, and the evaporation sub-model is established according to the crankcase ventilation flow and the engine oil temperature and used for calculating the discharge amount of water vapor from the engine oil; and predicting the moisture content in the engine oil according to the condensation sub-model and the evaporation sub-model to obtain a predicted value of the moisture content. The problem that cost and precision are difficult to consider in the prior art is solved, and a low-cost and high-precision engine oil water pollution prediction scheme is realized.

The application relates to a Transformer-based power multi-modal full-element sample fusion labeling method and system, which comprises the following steps: S1: obtaining multi-modal original data of a production operation site, and obtaining a preprocessed multi-modal data set through preprocessing; S2: performing multi-modal feature coding and Transformer representation modeling according to the preprocessed multi-modal data, and obtaining a fusion feature representation through cross-modal feature fusion and information completion; S3: acquiring a multi-modal semantic alignment label set through semantic consistency detection and a semantic mapping mechanism according to the fusion feature representation and a corresponding candidate label set; S4: constructing a label system structure tree according to the multi-modal semantic alignment label set; and S5: constructing an automatic labeling module to generate preliminary labeling based on the fusion feature representation and the label system structure tree, and directly inferring labels based on similar samples and category probabilities. The application realizes efficient automatic label generation and sample dynamic classification.

The application provides a pre-stack slice energy adjustment method, device, equipment and storage medium, and belongs to the technical field of seismic data processing. The method comprises the following steps: forming a first data body before energy adjustment based on the seismic data migration of multiple work areas; obtaining a second data body after gain adjustment is performed on the first data body; extracting sample points in the first data body to obtain first samples, and extracting sample points in the second data body to obtain second samples; extracting envelopes of the first samples and the second samples; for each seismic trace, taking the ratio of the corresponding values of the first envelope surface and the second envelope surface of the seismic trace as the initial energy adjustment coefficient of the seismic trace, and taking the initial energy adjustment coefficients of all seismic traces to form an initial energy adjustment coefficient body; and sequentially performing time and space direction smoothing on the initial energy adjustment coefficient body to form a target energy adjustment coefficient body. The application realizes spatial direction energy unification, eliminates the structural false image of the splicing area, and maintains the time direction energy characteristics.

This invention belongs to the field of intelligent perception and simulation training technology for maritime navigation. It discloses a method and system for realistic training and evaluation of ship collision avoidance rules at sea. By constructing a hierarchical question bank, it generates scenario assembly lists and uniformly schedules ship motion simulation, 3D visual scenes, radar / AIS fusion display, and voice communication interaction. During training, it collects control inputs, motion states, target information, and communication records to form a traceable chain of evidence, and aligns sampling based on evaluation anchor points. An automatic scoring model is established based on result and process indicators, outputting an evaluation report with sub-scores, evidence location, a list of violations, and retraining suggestions. It is suitable for teaching, retraining, and assessment, improving the efficiency and achievement rate of collision avoidance decision-making training.

The application discloses a generator set vibration trend early warning method based on a deep timing model, comprising the following steps: collecting generator set operation data and performing data preprocessing; constructing an enhanced Neural RDE model; running a conditional rough driving construction unit to generate a logarithmic signature feature set; running a frequency band gate vector field unit to generate a gate coefficient set and a hidden state sequence; running a physical consistency constraint unit to calculate and generate a constraint signal sequence; based on the hidden state sequence, the logarithmic signature feature set and the constraint signal sequence, calculating and generating a trend index set and a risk index set; calculating a joint loss function and updating model parameters; inputting a real-time collected continuous data stream and combining the model parameters and a threshold set to generate a vibration trend early warning result and an early warning lead time. The application significantly improves the vibration trend prediction accuracy, prolongs the early warning lead time and enhances the operation reliability under complex working conditions.

The invention relates to a reinforcement learning-based variable configuration aircraft control law intelligent optimization method, and belongs to the technical field of aircraft attitude control. The method specifically comprises the steps that an aerodynamic parameter neural network model is established, model input, model output and a loss function are defined, and real-time aerodynamic parameters are obtained according to in-flight state quantity identification; establishing a basic control law, and designing according to a pole assignment method to obtain standard control parameters; and a control parameter increment model is established, a control parameter increment is calculated according to the real-time aerodynamic parameters and the flight state obtained through identification, and the standard control parameters, the control parameter increment and the basic control law jointly form an optimized variable configuration aircraft control law. The method has the advantages of global intelligence, strong adaptability and explainable control law main body, and can be used for improving the adaptability of attitude control of the aircraft in an extremely wide range.

The present application relates to dilution refrigerator temperature calibration technical field, and disclose a kind of dilution refrigerator thermometer in situ calibration system based on natural cooling dynamics, comprising: according to the dynamics equation of cooling power and temperature Curvature is calculated, according to the temperature corresponding to thermometer resistance value, the temperature is substituted into temperature curvature, and the calibration function of resistance value and temperature is obtained;Identify the multivalued region of temperature, and evolve multiple branch functions in multivalued region in calibration function, calculate the deviation measure of each branch function and calibration function;In multivalued region, the support degree of each branch function to calibration function is calculated, and real-time data is obtained by adjusting calculation load, to minimize the number of experiments to verify calibration function;According to the branch verification result of multivalued region, dynamically adjust the verification strategy of non-multivalued region, under the premise of not relaxing calibration accuracy, through dynamics branch and load guide, significantly reduce the repeated experiment cost of dilution refrigerator cryogenic calibration.

The invention discloses an HITL method and system for unloading a large model reasoning task in a heterogeneous GPU computing power cloud. The method comprises the following steps: constructing a system model of the heterogeneous GPU computing power cloud; an HITL system architecture based on multiple agents is designed; human expert feedback is introduced through an HITL method, and recognition of a large model on a user intention is corrected; human expert feedback is introduced through an HITL method, and recognition of a large model on a user intention is corrected; the multi-agent cooperation module maps the intention of a user to a utility function through interaction among a plurality of agents; an optimized cue word method is used, the thinking process of a large model is decomposed, and the intention recognition accuracy is improved in a chain reasoning mode. According to the method, dynamic scheduling of computing power resource management and large model reasoning tasks can be optimized, and the service quality and the user experience in the heterogeneous GPU computing power cloud environment are improved.

The application discloses a kind of fusion driving and cascading error attribution hydroelectric generating set multi-subsystem parameter identification method, comprising: construct the high-fidelity simulation model of four cascading subsystems of local control unit LCU, speed regulator, electro-hydraulic servo system, hydroelectric unit;Design dynamic fusion coefficient with iteration attenuation, measured signal and model simulation signal are fused as the input of each subsystem, realize the transition from data-driven to model consistency-driven;Each subsystem output error is decomposed into upstream propagation error and its intrinsic error, and the optimization objective function with intrinsic error as the core is reconstructed;Improved particle swarm optimization algorithm, based on intrinsic error dynamic distribution search weight and introduce propagation error suppression factor, realize multi-subsystem parameter collaborative optimization.The application can effectively suppress cascading error accumulation, improve the physical interpretability and identification accuracy of parameter, and is suitable for hydroelectric generating set digital twin and online control scene.

This invention relates to the field of natural language-driven clustering technology, specifically to an e-commerce customer classification method based on end-to-end goal-driven clustering, comprising: S1: acquiring business goals and raw consumption behavior data of all e-commerce customers; S2: standardizing the raw consumption behavior data of all e-commerce customers to generate an e-commerce customer feature matrix; S3: inputting the business goals and the e-commerce customer feature matrix into a large language model, and generating importance scores corresponding to each consumption behavior feature through the independent query mechanism of the large language model for each consumption behavior feature; S4: performing clustering based on proximity and volume clustering algorithms, combined with the importance scores of each consumption behavior feature, to generate cluster labels for each e-commerce customer; S5: distinguishing the importance of e-commerce customers based on their cluster labels and formulating corresponding service strategies. This invention improves the objectivity and goal orientation of e-commerce customer classification.

This invention belongs to the field of wireless communication and relates to a machine learning-based method for wireless communication channel estimation. The method includes: acquiring pilot signals, antenna array geometric parameters, and multipath propagation parameters from the transceiver end of a millimeter-wave massive MIMO system to construct a three-dimensional propagation structure model; determining candidate regions for the channel sparse support set and generating a prior constraint matrix for the channel sparse support; inputting the prior constraint matrix and pilot observation data into a sparse reconstruction algorithm for channel sparse feature extraction and dimensionality reduction; performing super-oscillatory feature enhancement on the dimensionality-reduced channel sparse features to form an enhanced channel feature vector; inputting the enhanced channel feature vector and the prior support vector matrix into a complex domain deep expansion network to output the channel estimation result; and outputting the final beamforming weights. Its beneficial effects are improved sparse support set matching accuracy and channel estimation precision with low pilot overhead, and enhanced system throughput and interference suppression capabilities.

The invention relates to the technical field of computer vision, and discloses an image forgery detection model interpretability analysis method and system, and the method comprises the steps: extracting the middle layer features of an image forgery detection model to be interpreted, and generating a semantic feature map based on the non-negative matrix decomposition of sparsity constraint; performing feature importance pre-screening on the semantic feature map to obtain an important feature map; for each important feature map, positioning a high activation area and extracting an image block, and analyzing a dominant frequency component and a bandwidth of the image block corresponding to the high activation area; constructing a band elimination filter in the frequency domain of the original image, generating a disturbance image, and endowing each feature with an initial weight based on a decision distance; and performing grouping fusion on the features according to the symbols of the initial weights, and respectively generating final visual saliency evidence graphs which support counterfeiting and reality. According to the invention, through combination of the non-negative matrix factorization and the frequency domain disturbance shielding method, the interpretability of the image forgery detection model can be effectively improved.

The invention provides a multi-expert collaborative knowledge tracking method and system for cognitive strategy perception, and relates to the technical field of knowledge tracking, and the method comprises the steps: building a memory consolidation expert module through combining a knowledge obtaining process with a forgetting gate and absorptivity parameters, building an attention regulation expert module through combining attention distribution of knowledge points with a time attention mechanism, and building a memory consolidation expert module; creating a structure adaptation expert module based on a correlation evolution process between knowledge points; generating a global memory matrix by combining an attention mechanism based on the long-term memory of the historical cognitive state of the student and the current interaction embedded information, and determining a corresponding expert weight; performing weighted fusion on knowledge state parameters generated by the memory consolidation expert module, the attention regulation and control expert module and the structure adaptation expert module on the basis of expert weights, splicing the obtained fused knowledge state parameters and feature embedding vectors of test questions to be predicted, and inputting the spliced information to a preset feedforward neural network, and obtaining the answer accuracy corresponding to the test question to be predicted.

The invention belongs to the technical field of laser precision machining and intelligent manufacturing, and particularly relates to a laser machining parameter transfer learning method, system and equipment and a medium, and the method comprises the following steps: S1, specifying a machining requirement, and inputting known physical characteristics and an initial laser parameter range of a to-be-machined material; s2, establishing a basic model library containing a multi-physics field coupling model, and constructing a laser parameter-electronic dynamics-processing result mapping database based on historical experimental data and model simulation results; and S3, based on the physical model library and the mapping database, training a machine learning or deep learning model as a prediction model. According to the method, a multi-physics field coupling model and a data driving model can be fused, the interpretability of the model is ensured by utilizing a physical mechanism, and the prediction precision is improved through mass data training; and the three-stage feedback mechanism realizes real-time adaptive adjustment in the machining process, so that the key index deviation of the machining result can be within an effective control range.

This invention provides a method and apparatus for evaluating the credibility of generated content, relating to the fields of computer science and artificial intelligence. The method includes: collecting information sources from multiple platforms; extracting features from the information sources to obtain multi-dimensional features; defining graph nodes and edges, assigning weights, and learning graph neural networks from the multi-dimensional features to obtain a directed weighted information source authority graph; performing end-to-end self-supervised learning on the information source authority graph using a graph convolutional network or graph attention network to obtain the graph neural network authority score for each node; performing conflict graph modeling and confidence propagation iterative algorithm processing on the information source authority graph to obtain a confidence propagation score; setting a timeliness factor, and weightedly fusing the graph neural network authority score, confidence propagation score, and timeliness factor to obtain a credibility score. This method achieves dynamic, accurate, and multi-platform collaborative evaluation of information source credibility.

The invention relates to the technical field of biological medicine, and discloses a multi-modal data analysis method for drug screening safety evaluation. By setting experiment duration and sampling intervals, multi-modal data such as genes and metabolites are collected from a drug treatment group and a control group at multiple time points, dimension standardization is performed on the two groups of data based on statistical characteristics of the control group, a comprehensive state vector is constructed, state changes of adjacent time points are utilized to form a discrete time differential component and a state evolution function, and a state evolution function is established. The method comprises the following steps: generating two groups of theoretical trajectories through initial state iteration, comparing the theoretical trajectories with actual observation at each time point to evaluate a multi-dimensional error, performing double accumulation in time and state dimensions to obtain a toxicity index of a drug treatment group and a baseline toxicity index of a control group, and calculating a dimensionless safety score for drug grading according to the relationship between the toxicity index and the baseline toxicity index. Therefore, the limitation of dependence on a single index or a single time point is overcome, and the multi-modal data fusion and full-cycle toxicity quantification capabilities are improved.

The invention discloses a neural network model pruning method and system, and relates to the field of model pruning, and the method comprises the steps: obtaining a first neural network model; replacing a standard layer in the model to obtain a second neural network model; correlation gating is added to each residual module in the model for controlling correlation propagation, a sparse filter is added to the output end of a linear layer for removing noise during correlation propagation, and finally a third neural network model is obtained; a correlation gating and filtering mechanism is added in a model needing pruning, so that the dependence on a nonlinear layer design complex propagation scheme is avoided, and the implementation complexity and the calculation amount are reduced.

This invention relates to the field of electricity theft detection technology, and in particular to a method for determining electricity theft using multi-source data. The method includes: determining initial electricity theft probabilities based on several evidence sources of a user; determining corresponding lower-level and upper-level credibility based on the evidence sources to synchronously adjust the initial electricity theft probabilities and generate a base electricity theft probability; determining a global conflict coefficient representing the differences between different evidence sources based on the base electricity theft probability; and constructing a formula for calculating the initial user electricity theft probability, which includes a confidence factor mapped from the global conflict coefficient. This invention effectively solves the problem of multi-source evidence conflict fusion by dynamically adjusting the weights of the corresponding initial electricity theft probabilities based on the upper and lower-level credibility of the evidence sources and adaptively updating them. The confidence factor preserves the weighted average information of conflicting evidence to avoid fusion paradoxes.

The present application belongs to the technical field of radar signal processing and target identification, and specifically provides a multi-target array structure inversion method based on two-dimensional power spectrum imaging, to solve the problem that the array structure in the multi-target scattering image is difficult to be stably recovered under the condition of strong aliasing, strong speckle and strong coherent interference background; the present application converts the collected radar scattering data into a power spectrum image, generates a global candidate point set with a level label through log power spectrum construction, sub-aperture decomposition, hierarchical candidate point extraction, consistency voting and density clustering deduplication, and further forms a closed loop through translation and combination prediction and bidirectional matching verification, and the original multi-target array structure is inferred from geometric evidence, which has good robustness, engineering feasibility and identification accuracy; and the present application does not depend on phase compensation, is suitable for observation scenes under multi-target, and meets the application requirements of complex target structure identification, multi-target imaging identification and target classification.

The application discloses a kind of based on reinforcement learning's multi-energy supply system collaborative scheduling optimization method, including the following steps: collecting the real-time operation data of multi-energy supply system and external environment data and preprocessing, form standardized data set;Establish the mathematical model of multi-energy supply system, construct system dynamic behavior equation;System dynamic data set is generated;Introduce dynamic belief propagation mechanism, the confidence of output prediction result;Form candidate scheduling action set;With dynamic game and strategy update mechanism, generate multi-energy collaborative scheduling strategy;The long-term benefits of multi-energy collaborative scheduling strategy are evaluated, and the optimal scheduling strategy is obtained;Output optimal collaborative scheduling strategy;Carry out joint iterative training, obtain the improved MBRL framework after updating, realize the coordinated optimization operation of multi-energy supply system, to reduce system operation cost, improve energy utilization efficiency and enhance the operation safety and stability of system.

The invention discloses a thermal power generating unit combustion system modeling method based on mechanism and data driving fusion, and belongs to the technical field of thermal power generating unit modeling and control. Aiming at the problems of an existing thermal power generating unit combustion system modeling method in the aspects of nonlinear description capability, dynamic response capability and multi-working-condition adaptation, firstly, unit operation data are preprocessed, and a simplified mechanism model is established according to a mechanism rule and used for describing a system basic relation; on the basis, a data driving model combining a convolutional neural network (CNN) and a long short-term memory network (LSTM) is designed, a mechanism-data driving parallel hybrid framework is further constructed, and a gate fusion network (GFN) is introduced to adaptively adjust weighting coefficients of a mechanism channel and a data channel. The method has remarkable advantages in the aspects of prediction precision, dynamic response and robustness.