1425results about How to "Improve forecast accuracy" patented technology

The invention discloses an agricultural load prediction method and system based on multivariate time sequence decoupling multi-modal learning, and belongs to the technical field of agricultural load prediction. Comprising the steps of collecting historical agricultural load and meteorological data; decomposing historical agricultural load and meteorological data by using multivariate variational mode decomposition to obtain cycle, trend and residual mode components; and respectively constructing a time convolutional neural network, a bidirectional gating cycle unit and a support vector regression model for the decomposed period, trend and residual modal component data set, and fully mining feature information of each mode after decomposition, thereby realizing accurate prediction of agricultural load. According to the method, the potential nonlinear space-time coupling relationship between the agricultural load and the meteorological factor is captured, the prediction effect in a seasonal periodic fluctuation scene of the agricultural load and a long-term trend and agricultural load abnormal scene is improved, the agricultural load prediction precision is improved, and a support is provided for reliable and stable operation of a power grid.

The invention provides a BIM-fused port infrastructure digital twinborn operation and maintenance management system and method. The method comprises the steps of collecting a port infrastructure BIM full-life-cycle multi-source heterogeneous data set, constructing a port infrastructure real-time three-dimensional digital twinborn body, constructing an equipment health prediction model and generating a fault diagnosis result; simulating tide influence to form a stress distribution prediction result; a three-level linkage optimization model is constructed, a scheduling scheme is generated, a multi-energy collaborative optimization engine optimization scheme is used, a three-dimensional safety matrix is constructed through unmanned aerial vehicle inspection and visual recognition, risks are monitored in real time, and safety early warning is generated. The prediction model is constructed, faults are accurately diagnosed, the tide influence is quantified, and the prediction precision is improved; multi-target collaborative optimization is realized through a linkage optimization model and an engine, and the problem of single-target optimization is solved; and on the basis of a monitoring and early warning system, rapid identification and hierarchical response are realized, a closed-loop link is formed, and the port operation and maintenance adaptability is improved.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention discloses a dynamic space-time diagram flow prediction method and system based on course learning, and relates to the technical field of supply chain logistics data analysis, and the method comprises the steps: building a space-time matrix based on historical multi-source data, generating a dynamic adjacent matrix through learning, and carrying out the smooth fusion through combining a static diagram, and forming a dynamic diagram structure. And then space and time features are respectively extracted by using a graph convolutional network and a gating loop unit, and deep interaction and fusion are realized through a bidirectional cross attention mechanism. A multi-dimensional difficulty estimator is innovatively introduced, the prediction difficulty of each training sample is quantified from three dimensions of space, time and time-space coupling, the selection sequence of the training samples is dynamically adjusted based on an adaptive course scheduler, and progressive learning is realized. And finally, feature representation is obtained through global pooling, and multi-step traffic prediction is realized by adopting a parallel independent decoder, so that error accumulation is avoided. According to the invention, prediction precision and model training efficiency in a complex supply chain logistics scene are effectively improved.

The invention discloses a short-term wind power prediction method and system based on a dynamic graph neural network, and belongs to the field of wind power prediction. Dividing a power sequence into a high-frequency fluctuation set and a low-frequency stationary set by using VMD-CEEMDAN joint decomposition and SSA clustering optimization; a DGAT module is adopted to fuse geography, data and learnable prior, a local sub-graph is dynamically constructed to extract spatial features, meanwhile, a multi-scale convolution block is utilized to parallelly capture high-frequency mutation and low-frequency trends through an MS-TCN module, multi-scale time features are generated, time feature fusion is guided through space and geography combined representation, and time feature fusion is realized. Collaborative modeling of multi-source heterogeneous data is achieved, finally fusion features are input into a full-connection layer to predict fluctuation set prediction power, the prediction power is combined with stationary set prediction power, and a short-term wind power prediction value is output; according to the method, the modeling capability of wind power plant complex association is remarkably improved, and reliable support is provided for real-time scheduling of a power grid.

This invention discloses an IGBT lifetime prediction method based on a GA-Elman-LSTM combined model. Specifically, the method involves: acquiring IGBT aging data; preprocessing the data; using a GA-optimized Elman neural network to import the training dataset into the GA-Elman model for training; constructing error correction training and validation sets using the trained GA-Elman preliminary prediction model; training the LSTM error correction prediction model; and building a GA-Elman-LSTM error correction combined model based on the GA-Elman preliminary prediction model and the LSTM error correction prediction model for final combined prediction. This invention conveniently and efficiently enables the model to converge to the global optimum, effectively improving the model's prediction accuracy; it also improves the model's prediction stability and reduces prediction risk.

The invention relates to the technical field of industrial vision and artificial intelligence, and discloses an aluminum coating formula prediction method and system based on industrial vision and double-model fusion. The method comprises the following steps: acquiring visible light and near-infrared band images of the surface of an aluminum material coating through multispectral image acquisition, identifying a defect area to generate a binary mask, extracting three types of features of color, texture and spectral reflection, and respectively inputting feature vectors into a random forest regression model and a convolutional neural network model to obtain a target image; and dynamically calculating a fusion weight according to the verification set error, and carrying out weighted fusion on the prediction results of the two models to generate a formula component content prediction value. According to the method, the technical problems of low precision, low efficiency and insufficient generalization ability of a traditional aluminum coating formula determination method are solved, and rapid and accurate prediction of the formula is realized.

The invention discloses a dynamic fusion prediction method and system for photovoltaic power generation power, and a storage medium. The method comprises the steps of collecting historical photovoltaic power generation power and corresponding multi-dimensional meteorological parameters; based on time sequence fragments in the historical data set, similarity measurement and clustering analysis are carried out on hour-level weather-power time sequence fragments in historical data by utilizing a dynamic time warping method, different weather-power mode clusters are divided, and a representative cluster center is determined for each cluster; training a long time sequence baseline prediction model and a plurality of short time sequence correction models in parallel; performing weighted fusion on the two prediction results by using the weight to obtain a final prediction value; and the prediction is updated by using the latest meteorological data by adopting an hour-by-hour rolling mechanism. According to the method, the problem that the long-period trend and the short-time fluctuation are difficult to consider at the same time is effectively solved, and the prediction precision, the stability and the adaptive capacity of the photovoltaic power generation power under the complex and changeable meteorological conditions are remarkably improved.

The invention relates to the technical field of load prediction, and provides a power load prediction method and system based on time sequence decomposition and an attention mechanism, and the method comprises the steps: carrying out the adaptive time sequence decomposition of an obtained original load sequence, calculating the sample entropy of each decomposed component, and carrying out the clustering; constructing a group of encoder and decoder networks for each piece of clustered data, performing parallel encoding to extract features, performing serial decoding reconstruction on the features from low frequency to high frequency, and outputting prediction data from low frequency to high frequency step by step; the weight is initialized based on the sample entropy, the trained weight is obtained through optimization in the encoder and decoder network training process, and the predicted value of the power load is obtained through weighted fusion. According to the method, adaptive time sequence decomposition, a weight mechanism guided by sample entropy and an attention-enhanced encoder-decoder structure are introduced, so that multi-component collaborative modeling and cross-scale dynamic prediction are realized, and the prediction accuracy and stability in complex load data and small sample scenes are effectively improved.

The invention provides a multiple-input-multiple-output soft measurement method and device and a medium. The method comprises the steps that historical multi-sampling-rate process variable data and historical multi-quality variable data are acquired; obtaining a plurality of historical task specific features from the historical multi-sampling-rate process variable data; inputting the plurality of historical task specific features to obtain historical cross-task sharing interaction features; training according to the historical cross-task sharing interaction features, the plurality of historical task specific features and historical multi-quality variable data to obtain a trained feature interaction hybrid expert network model; and obtaining a plurality of online prediction results according to the trained feature interaction hybrid expert network model. According to the method, the device and the medium, the problems that information loss, time alignment errors and task negative migration are easily caused when different variable sampling frequencies are inconsistent in an existing multi-input multi-output soft measurement method, an irregular sampling phenomenon exists, and the prediction precision of multiple quality indexes is not high can be solved.

The invention relates to a heat supply prediction method and system based on spatial-temporal feature fusion deep learning, and the method comprises the following steps: S1, carrying out the collection and fusion of multi-source heterogeneous data, and constructing an integrated data set; s2, preprocessing the data; s3, constructing a graph structure model of the heat supply system, and constructing a weighted undirected graph; s4, constructing and executing forward calculation of the space-time double-flow deep network; s5, designing a composite loss function including mean square error loss and physical constraint loss, and performing joint optimization training on the space-time double-flow deep network; and S6, performing multi-step heat supply load prediction by using the trained model, outputting a heat supply load curve of each heat exchange station in a specified time period in the future, and integrating a prediction result with a heat supply scheduling system. The method has the advantages that the prediction precision is improved compared with that of a traditional machine learning model by capturing the spatial-temporal characteristics at the same time, and the advantages are more remarkable in extreme weather.

The invention discloses a group of molecular markers related to the oil yield of carya illinoensis and application of the molecular markers, and relates to the technical field of biology. The nucleotide sequence of the SNP molecular marker is as shown in SEQ ID NO. 1-2. The molecular marker disclosed by the invention can be used for marker assisted selection (MAS) and genome selection (GS) of the carya illinoensis, so that the genetic improvement progress of the variety of the carya illinoensis can be accelerated.

The invention discloses a load prediction method and system based on error division multiple tasks, a medium and equipment, and the method comprises the steps: combining an error division task with a continuous learning mechanism, firstly calculating a sample relative error in a training process, classifying low-error data into a data set corresponding to a learned load feature mode, and carrying out the calculation of a data set corresponding to the learned load feature mode; the high-error data is delimited as a new task to be learned; measuring model parameter importance through a Fisher information matrix of EWC, introducing an L2 regularization item to constrain core parameter updating, and avoiding forgetting a learned old mode; and circularly executing task division and model training, so that a single model gradually masters various load characteristic modes in continuous learning. A division basis does not need to be set manually, a multi-mode learning process is simplified, and prediction accuracy and robustness in a complex load scene are improved.

The invention discloses a photovoltaic power prediction method based on improved empirical mode decomposition and an optimized long short-term memory network, and the method comprises the steps: firstly carrying out the preprocessing of abnormal value elimination, missing value filling, normalization and the like of photovoltaic power and related meteorological data, and improving the data quality; then, an improved empirical mode decomposition (EE-ANEMD) algorithm is adopted to decompose the preprocessed power sequence into a multi-scale intrinsic mode function component and a residual term, and high-frequency noise, intermediate-frequency fluctuation and a low-frequency trend are effectively separated; global optimization is carried out on the hidden layer unit number, the initial learning rate and the maximum number of training times of the LSTM network through an improved sparrow search algorithm (ISSA), finally, the optimized LSTM is utilized to carry out training prediction on each component, and results are fused and subjected to reverse normalization to obtain a final value. Experiments show that the test set RMSE of the method is reduced compared with that of a single LSTM, the mid-term prediction precision is remarkably improved, and reliable technical support is provided for power system dispatching, new energy consumption planning and photovoltaic power station operation and maintenance.

A self-adaptive control method of an aircraft wing and the aircraft wing wherein the self-adaptive control method comprises: constructing a prediction model, inputting a real-time external aerodynamic disturbance parameter to the prediction model, predicting a predicted disturbance error at a next moment, and realizing feedforward prediction compensation of external aerodynamic disturbance. The influence of predictable disturbance on the airfoil profile is eliminated in advance; and then monitoring the airfoil pose to obtain tracking airfoil parameters, and carrying out deviation calculation on the tracking airfoil parameters and the target airfoil parameters to obtain an actual tracking error so as to provide a real-time airfoil pose feedback signal. And finally, the control assembly generates a control instruction based on the predicted disturbance error, the actual tracking error and the target airfoil profile parameter, the control instruction acts on the mechanical neural network to realize adaptive adjustment of the airfoil profile, and the airfoil profile continuously approaches the target airfoil profile neighborhood through a feedforward and feedback composite control mechanism.

The invention discloses an ocean flow field generation method and system, a storage medium and an environment forecasting device, belongs to the field of ocean current generation and prediction, is used for carrying out randomized prediction on ocean current according to historical observation data of an ocean flow field, and comprises the steps of obtaining multi-source ocean current observation data and carrying out data preprocessing on the data; a deterministic background flow field model and a random disturbance model are constructed, the background flow field model and the random disturbance model are coordinated and coupled under physical constraints of mass conservation and quasi-earth-to-balance, a probabilistic flow field set is generated by adopting a Monte Carlo method, and an ocean flow field is constructed. According to the method, the physical certainty and the data randomness of the ocean current are coordinated and coupled under the same physical constraint, the ocean current generation model containing random disturbance is constructed, and the prediction precision of the ocean current is improved.

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The invention discloses an arch bridge tensioning method and system based on a physical constraint space-time diagram attention network, and the method comprises the steps: constructing a dynamic topological graph of an arch bridge cantilever construction structure, taking a structure initial state parameter, a control force system parameter and a real-time environment parameter as node input features, and taking a structure state response parameter as an output label, generating a training data set based on finite element model simulation; designing a deep learning network model combined with space diagram attention and time sequence causal convolution, and modeling a space-time dependency relationship; defining a mixed loss function of the data fidelity item and the physical residual loss item of the structural mechanical control equation; and training the model through a back propagation algorithm and deploying the model to a field decision control system. According to the method, through graph structure abstraction, spatio-temporal joint modeling and physical constraint embedding, multi-source monitoring data driven structure state online prediction and tension control strategy intelligent optimization are achieved.

According to the double-fed fan wiring terminal contact fault on-line detection system provided by the invention, through electric-thermal-mechanical multi-physical quantity collaborative analysis, the early recognition rate of the terminal contact fault is remarkably improved; precise alarm under different load working conditions is realized by utilizing a self-adaptive threshold adjustment function of the edge calculation module; based on a multi-dimensional feature fusion algorithm of a cloud digital twinborn model, a material degradation rule calibrated by a laboratory is combined with real-time operation data, so that the prediction accuracy is greatly improved; an automatic response chain from early warning to emergency disposal is achieved through a grading decision mechanism, the manual inspection frequency is reduced, and meanwhile the fault positioning precision is further improved through three-dimensional coordinate positioning and adjacent terminal cooperative detection.

The invention provides an aero-engine residual life parallel prediction method, system and device and a medium, and relates to the field of aero-engine health management.The aero-engine residual life parallel prediction method comprises the steps that sensor time sequence data of an aero-engine is obtained, and an input feature sequence is obtained; inputting the feature sequence into a continuous dynamic modeling path and a multi-resolution feature extraction path at the same time, and outputting a first residual useful life prediction value and a corresponding first uncertainty measure as well as a second residual useful life prediction value and a corresponding second uncertainty measure; and identifying the current flight condition of the engine, and based on an uncertainty perception fusion mechanism, according to the first uncertainty measure, the second uncertainty measure and the current flight condition, performing adaptive weighted fusion on the first prediction value of the remaining useful life and the second prediction value of the remaining useful life to obtain a prediction result of the remaining useful life. According to the method, continuous dynamic and multi-scale transient characteristics are captured at the same time, and high-precision and high-reliability prediction of the remaining useful life of the aero-engine is realized.

The invention relates to the technical field of micro-grid load prediction, and discloses a multi-factor efficient fusion micro-grid load short-term prediction model optimization method. According to the method, micro-grid load historical data and multi-source factor data including information such as meteorology and electricity price are collected, and one-hot coding and normalization processing are carried out. Load data is decomposed into high-frequency and low-frequency components by using a variational mode decomposition technology, and prediction is carried out by respectively adopting a long-short-term memory network integrated with an attention mechanism and a linear regression model. And by calculating the difference between the source domain data and the target domain data in the model hidden layer feature space, the domain adaptive capacity of the model is enhanced, and accurate short-term prediction of the microgrid load is realized.

The invention provides a power load prediction method and device, equipment and a medium. Relates to the technical field of power load prediction. The method comprises the following steps: respectively mapping historical time sequence data from different data sources of a to-be-predicted power system into single-source time sequence characteristics representing overall time sequence change characteristics of the corresponding data sources, and modeling a dependency relationship of the single-source time sequence characteristics corresponding to the data sources, obtaining time sequence embedding representing overall dynamic evolution of the to-be-predicted power system; historical time sequence data from different data sources are converted into natural language texts expressing data source attributes, time sequence characteristics and power load associated information, the natural language texts corresponding to the data sources are coded, and prompt embedding including semantic information of the data sources is obtained; fusing the time sequence embedding and the prompt embedding to obtain cross-modal enhanced embedding; and decoding the cross-modal enhanced embedding to obtain a power load prediction result of the to-be-predicted power system.

The invention discloses a power distribution network power demand prediction method and device based on big data analysis and a medium, and belongs to the technical field of power demand prediction, and the method comprises the steps: dividing a power distribution network into a plurality of power nodes, collecting the power data of the power nodes, and carrying out the screening to obtain power abnormal nodes; demand information of the power abnormal node is collected, and a power consumption demand event is extracted according to the demand information; acquiring event information of the power consumption demand event, and evaluating according to the event information to obtain a propagation effect condition of the power consumption demand event; acquiring a real-time prediction demand value of a power abnormal node, and determining power change values of other power nodes in combination with a propagation effect condition; and collecting real-time environment data of the power node, predicting according to the real-time environment data to obtain a basic power demand value, and superposing the power change value to obtain a real-time power demand value. The accuracy of power distribution network power demand prediction based on big data analysis is improved.

The invention discloses a large-range landslide mass displacement early warning method based on GNSS and radar data fusion, and the method comprises the steps: obtaining GNSS monitoring sequence data in a landslide region based on the position information of a reference station and a GNSS monitoring station in a GNSS monitoring system, and further obtaining the displacement related information of the landslide region; collecting data through a satellite InSAR, and generating deformation field data of a landslide area by comparing radar images at different time points; performing space-time alignment on the obtained data, and performing two types of data fusion S by adopting an adaptive Kalman filtering method after alignment; decomposing time series data of the fused landslide mass displacement by using wavelet transform, and extracting multi-scale features of a time domain and a frequency domain; the proposed features are combined with historical data of landslide mass displacement, a landslide mass displacement trend prediction model using an LSTM method added with a memory decline factor is input, and future trend prediction of landslide displacement is carried out; setting a multi-level threshold value, judging the change trend of the landslide mass displacement according to the displacement rate, the acceleration and the prediction result, and generating a multi-level early warning signal.

The invention discloses an interactive load prediction method based on fusion of prior knowledge and data driving, and the method comprises the steps: reconstructing a load sequence into a trend load sequence and a disturbance load sequence through modal decomposition, and constructing a prior knowledge base of tag-feature weight according to SHAP interpretability analysis; and through a prior knowledge base and feature contribution analysis, channel-level weight learning is carried out by using an automatic correlation determination module, and key input features are obtained. And inputting the reconstructed load sequence and the key input features into an improved Transform model, mapping a priori knowledge base into a priori knowledge matrix, embedding the priori knowledge matrix into the model, and generating a load prediction result. And carrying out interpretability analysis on a prediction result, and feeding back and updating an analysis result to a priori knowledge base to realize dynamic collaborative updating of prediction and the knowledge base. According to the invention, organic combination of expert knowledge and a data-driven model is realized, and the precision and stability of load prediction are improved.

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.

The invention belongs to the technical field of coal quality detection, and particularly relates to a method for rapidly predicting coal quality parameters based on Raman spectrum in combination with machine learning. According to the method, a Raman spectrum technology and machine learning are combined, a Raman spectrum systematic preprocessing process is adopted, an adaptive iteration reweighted least square method Air-PLS is applied, spectral signals and baseline drift are accurately separated, Savitzky-Golay filtering is applied, peak shape features are reserved, random noise is effectively suppressed, and the method is suitable for large-scale popularization and application. Maximum-minimum normalization or Z-score standardization processing is provided, and the intensity difference between samples is eliminated; moreover, a data-driven Raman spectrum intelligent feature screening mechanism is introduced, and an optimal feature wavelength subset which is highly related to coal quality parameters and low in redundancy is screened out through automatic iteration; according to the method, the data quality in Raman spectrum coal quality detection is improved, the feature correlation is enhanced while the feature dimension is reduced, the model precision and generalization ability are improved, and rapid, lossless, high-precision and high-robustness coal quality parameter prediction is realized.

The invention discloses a low-sodium myofibrillar protein flavor prediction method and a low-sodium myofibrillar protein flavor prediction device. The method comprises the following steps: firstly, constructing a protein-flavor interaction system containing myofibrillar protein, potassium chloride, kappa-carrageenan and representative aldehyde flavor compounds; then, by means of spectroscopy, rheometer combination, an electronic tongue and the like, protein conformational change, typical aldehyde molecule binding rate and taste features are represented in a multi-dimensional mode. And establishing a random forest prediction model, taking protein conformation parameters as input, and taking a flavor binding rate and effective taste intensity as output. The model can reveal cross correlation between protein conformations and functions and identify key conformation parameters that affect flavor. And in combination with quantification and prediction capabilities of the model, a conformation-flavor relationship can be systematically analyzed, a basis is provided for optimization of a low-sodium formula, flavor is enhanced while salty taste is increased and bitter taste is inhibited, and healthy and sustainable development of low-sodium meat products is promoted.

The invention belongs to the technical field of power transmission line monitoring and dynamic capacity increasing. A power transmission line dynamic current-carrying capacity prediction and capacity increase method based on double-model adaptive fusion comprises the following steps: data acquisition and preprocessing: acquiring historical weather and current-carrying capacity data, and cleaning and standardizing the historical weather and current-carrying capacity data; weather-driven prediction: optimizing a kernel extreme learning machine through an artificial egret optimization algorithm to predict future meteorological parameters, and substituting the future meteorological parameters into a heat balance equation to calculate a first current-carrying capacity predicted value; performing data-driven prediction, optimizing variational mode decomposition by adopting a dynamic perception and accurate capture algorithm, and directly predicting a second current-carrying capacity predicted value in combination with a long-short-term memory network; in the fusion step, weights are dynamically distributed according to errors of the two models on the verification set, and self-adaptive weighted fusion is carried out to obtain a final point prediction value; and a probability modeling step: fitting probability distribution based on historical errors, and constructing a confidence interval. According to the invention, the precision and reliability of current-carrying capacity prediction are improved, and dynamic capacity increasing and safe operation of the power transmission line are realized.

The invention relates to the technical field of machine learning, and provides a drill hole rock mass structure quantitative prediction method and system based on machine learning, and the method comprises the steps: constructing an associated data set with a drill hole television image and / or an actual rock mass structure disclosed by an exploration adit as a benchmark, and taking an actual rock mass structure quantitative value as a benchmark; and calculating an overall deviation correction coefficient of a rock mass integrity coefficient and a rock quality index based on the associated data set, performing deviation correction on original data by using the correction coefficient, and realizing automatic mapping from double-index input to rock mass structure quantitative predicted value output by a machine learning model. The decision coefficient of the prediction model on a test set reaches 0.9 or above, the average absolute error does not exceed 0.3, the prediction time of a single group of data does not exceed 1.5 seconds, and the prediction precision and efficiency are far higher than those of a traditional experience method. The method supports local off-line deployment, adapts to a field network-free environment, constructs a data closed-loop mechanism to realize continuous iteration of the model, and provides a reliable basis for dam foundation safety assessment.