Tunnel water gushing disaster prediction method and device and storage medium

Abstract

The invention relates to the technical field of tunnel water inrush safety assessment, in particular to a tunnel water inrush disaster prediction method and device and a storage medium, and the method comprises the steps: S1, building a data set based on tunnel water inrush disaster cases, analyzing and selecting disaster-inducing factors, and determining disaster grading standards; s2, dividing the data set into a training set and a test set according to a set proportional relation; s3, performing data preprocessing on a training set and a test set in the data set by taking the disaster-causing factor as a characteristic variable; compared with the prior art, the tunnel water inrush disaster prediction method has the beneficial effects that the tunnel water inrush disaster is intelligently predicted by using the machine learning method, the problems of strong subjectivity, poor applicability and the like of a traditional prediction method can be avoided, meanwhile, disaster misjudgment and missed judgment caused by technicians are avoided, and the model performance and the prediction precision are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel water inrush safety assessment, and in particular to a tunnel water inrush disaster prediction method, equipment and storage medium. Background Art

[0002] Traditional methods for predicting tunnel water inrush disasters include analytic hierarchy process, comprehensive evaluation method, weighted average method and expert judgment method. These methods are highly subjective and have poor applicability. In addition, the hydrogeological conditions during tunnel construction are complex and difficult to fully explore. When front-line construction personnel lack technical reserves, it is easy to make it difficult to accurately predict tunnel water inrush disasters, which may cause serious economic losses and casualties. In existing technologies, machine learning can be used to process complex data. In recent years, with the development of machine learning prediction models, more and more researchers have applied them to the fields of data analysis and disaster prediction.

[0003] In machine learning, prediction mainly includes three parts: data preprocessing, model training and prediction. Before performing machine learning tasks, the original data needs to be processed and converted into data that can be used for machine learning to improve the accuracy of machine learning. However, there are many types of machine learning models, and the learning ability and adaptability of different models vary. Therefore, when establishing an intelligent prediction model for tunnel water inrush disaster risk, it is necessary to select it according to the actual situation. Factors such as the number of features and the size of the sample set should be considered to evaluate the model, select a simple and easy-to-train model, and avoid overfitting or underfitting problems.

[0004] The prediction accuracy of the model is affected by many factors, including the size of the data set, the distribution of data set features, the way the data set is divided, and the complexity of the model. For a given model and data set, generally speaking, the larger the training set, the higher the accuracy of the model may be. However, the larger the training set ratio, the higher the configuration requirements for the model and computing carrier will be. When the training set ratio is too large, it will also lead to overfitting problems. Therefore, it is necessary to select an appropriate training set ratio according to the prediction type.

[0005] At the same time, previous researchers mostly used relatively simple traditional machine learning models or linear fusion of simple models when predicting tunnel water inrush disasters, resulting in the overall prediction accuracy of the model being less than ideal, which in turn affects the determination of the level of tunnel water inrush disasters and prevention and control measures. How to combine machine learning to predict water inrush disasters, and the problems of relatively simple models and less than ideal prediction accuracy in the field of intelligent prediction of tunnel water inrush by machine learning are the technical problems to be solved by the present invention.

[0006] Therefore, the development of a tunnel water inrush disaster prediction method, equipment and storage medium not only has urgent research value, but also has good economic benefits and industrial application potential, which is the driving force and basis for the completion of the present invention. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the inventors conducted in-depth research and completed the present invention after paying a lot of creative work.

[0008] Specifically, the present invention proposes an intelligent prediction method for tunnel water inrush based on algorithm optimization to quickly and accurately predict tunnel water inrush disasters, so as to solve the technical problems of insufficient prediction accuracy and single model.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A method for predicting sudden water inrush disaster in a tunnel, comprising:

[0011] S1: Construct a data set based on tunnel water inrush disaster cases, analyze and select disaster-causing factors, and clarify disaster classification standards;

[0012] S2: Divide the data set into training set and test set according to a predetermined ratio;

[0013] S3: Taking the disaster-causing factor as the characteristic variable, the training set and the test set in the data set are preprocessed respectively;

[0014] S4: Select precision, recall and F1 score as evaluation indicators of the learning model, train the machine learning model with preprocessed data, optimize the model hyperparameters, repeat the training, and select the suitable machine learning model;

[0015] S5: Use the Stacking ensemble method to improve the machine learning model, use the adapted single model as the first-layer base learner, use linear regression and ridge regression as the second-layer meta-learner, perform hyperparameter tuning on the single model, and test and compare the prediction effects of multiple groups of ensemble models under different combinations of base learners and meta-learners;

[0016] S6: Compare the optimal single model and the optimal integrated model using evaluation indicators and confusion matrix to obtain the evaluation accuracy of the optimal integrated model.

[0017] In the present invention, as an improvement, the disaster-causing factors are analyzed and selected, and the disaster classification standards are clarified to include:

[0018] Count the frequency of occurrence of influencing factors in the statistical data set, and use high-frequency influencing factors as disaster-causing factors for prediction and evaluation;

[0019] The impact levels of disaster factors are divided according to their influence on tunnel water inrush.

[0020] In the present invention, as an improvement, data preprocessing of the data set includes:

[0021] Disaster factors are divided into qualitative variables and quantitative variables, and they are quantified separately. Among them, quantitative variables and qualitative variables are assigned values ​​according to the corresponding disaster factor impact levels.

[0022] The box plot method was used to detect outliers on the characteristic variables;

[0023] The data are replaced with outliers and missing values. For the outlier replacement process of the same variable at different risk levels, the mode of the data at the current risk level is used as the replacement value of the outlier for qualitative variables; the average value of the data at the current risk level is used as the replacement value of the outlier for quantitative variables. For the missing data supplementation method in the data set, the mode of the data at the impact level is used as the supplement value of the missing data for qualitative variables; the average value of the data at the impact level is used as the supplement value of the missing data for quantitative variables.

[0024] The data set after outlier processing is normalized.

[0025] In the present invention, as an improvement, the machine learning model is trained with preprocessed data, and after optimizing the model hyperparameters, repeated training is performed to select and adapt the single machine learning model, including:

[0026] Select multiple machine learning models as training models, and input the preprocessed training set and test set into a single machine learning model;

[0027] Through K-fold cross validation combined with grid search parameter tuning method, the hyperparameters of the machine learning model are tuned to obtain the optimal hyperparameter values ​​of the model. The model hyperparameters are input, the model is retrained, and the evaluation indicators of each single model before and after hyperparameter optimization are compared to select the optimal n suitable single machine learning models.

[0028] In the present invention, as an improvement, the linear regression and ridge regression in the second-layer meta-learner adopt a hyperparameter tuning method to obtain the optimal hyperparameters of the two meta-learners.

[0029] In the present invention, as an improvement, Stacking integration is used to improve the learning model, specifically including:

[0030] The ensemble learning model is composed of n base learners and two meta learners to form at least m sets of ensemble model combinations;

[0031] The m groups of integrated models are trained with the training set and test set data to obtain the tunnel water inrush disaster prediction results and the evaluation indicators of each model;

[0032] Re-enter the optimal hyperparameters for the integrated model combination with precision, recall and F1 score values ​​above 0.80 in the m groups of integrated models for model training;

[0033] The evaluation indicators of the integrated model combination before and after hyperparameter tuning are compared to obtain the optimal Stacking integrated model.

[0034] In the present invention, as an improvement, the integrated model combination method is an integrated model composed of one or more base learners and any one of the meta learners.

[0035] A computer device comprising a memory, a processor and a communication component;

[0036] wherein the memory is configured to store one or more instructions;

[0037] The processor is loaded by the communication component and executes the memory instructions to complete the prediction method described in any one of claims 1-6.

[0038] A computer-readable storage medium, wherein executable instructions are stored in the computer-readable storage medium, and the executable instructions are loaded and executed by a processor to implement the prediction method according to any one of claims 1 to 6.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] (1) The use of machine learning methods for intelligent prediction of tunnel water inrush disasters can avoid the problems of strong subjectivity and poor applicability of traditional prediction methods, and at the same time avoid the misjudgment and omission of disasters caused by technical personnel. Secondly, the present invention improves the model and optimizes the algorithm through the method of integrated model, which can quickly and accurately predict tunnel water inrush disasters and improve model performance and prediction accuracy.

[0041] (2) In the present invention, a Stacking integrated model is used to adopt a classification prediction method for sudden water inrush prediction. Different from the previous regression prediction, the data is numerically processed, and the matched evaluation indicators are used to optimize the hyperparameters in a model integration combination manner to improve the model prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0043] Figure 1 It is a schematic diagram of the flow chart of the prediction method of the present invention;

[0044] Figure 2 This is a schematic diagram of the integrated model training process of the present invention;

[0045] Figure 3 are evaluation index parameters of the four models in Example 1 of the present invention;

[0046] Figure 4 This is a schematic diagram of comparing the accuracy values ​​before and after the single model hyperparameter optimization in Example 1 of the present invention;

[0047] Figure 5 This is a schematic diagram of comparing the recall values ​​before and after the single model hyperparameter optimization in the first embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of the comparison of F1 score values ​​before and after single model hyperparameter optimization in Example 1 of the present invention;

[0049] Figure 7 This is a schematic diagram of the integrated model evaluation index in the first embodiment of the present invention;

[0050] Figure 8 This is a schematic diagram of comparing the accuracy values ​​before and after the optimization of the hyperparameters of the integrated model in the first embodiment of the present invention;

[0051] Fig. 9 This is a schematic diagram of the comparison of recall values ​​before and after the optimization of the hyperparameters of the integrated model in the first embodiment of the present invention;

[0052] Fig.10 This is a schematic diagram of the comparison of F1 score values ​​before and after the optimization of the hyperparameters of the integrated model in Example 1 of the present invention;

[0053] Fig.11 Schematic diagram of the comparison of evaluation indicators of the optimal single model and the optimal integrated model in Example 1 of the present invention. DETAILED DESCRIPTION

[0054] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0055] A method for predicting sudden water inrush disaster in a tunnel comprises the following steps:

[0056] S1. Through on-site investigation and statistical collection of disaster cases, a sample database of tunnel water inrush disaster cases is constructed. Statistical analysis is performed on the data in the database to screen multiple influencing factors with high frequency as disaster-causing factors for evaluation and to clarify the disaster classification standards.

[0057] S2, dividing the data set into a training set and a test set according to a predetermined ratio, and performing data preprocessing on the divided test set and training set data separately;

[0058] S3, using disaster-causing factors as characteristic variables, preprocessing the data set;

[0059] S4. Select precision, recall and F1 score as evaluation indicators of machine learning models, train the learning model with preprocessed data, optimize the model hyperparameters, repeat the training, and select the suitable machine learning model;

[0060] S5. Use the Stacking ensemble learning method to improve the machine learning model, use the adapted single model as the first-layer base learner, use linear regression and ridge regression as the second-layer meta-learner, perform hyperparameter tuning on the single model, and test and compare the prediction effects of multiple groups of ensemble models under different combinations of base learners and meta-learners;

[0061] S6. Compare the optimal single model and the optimal integrated model using evaluation indicators and confusion matrix to obtain the evaluation accuracy of the optimal integrated model.

[0062] In step 1, by statistically analyzing the data in the database, it is concluded that six factors, namely, stratum lithology, unfavorable geology, rock formation inclination, negative terrain area ratio, surrounding rock grade and hydrodynamic zoning, are the main factors affecting tunnel water inrush disasters. The above six influencing factors are used as disaster-causing factors to evaluate the danger level of tunnel water inrush disasters.

[0063] Through the study of tunnel water inrush disaster level standards in previous literature and combined with railway tunnel risk assessment and management methods, the tunnel water inrush disaster hazard level is divided into level I, level II, level III and level IV. Among them, level I is the lowest risk level, level II is the medium risk level, level III is the high risk level, and level IV is the highest risk level.

[0064] The training set and test set are classified with random seeds through algorithm encoding, and the selected training set and test set are processed by the same data preprocessing method.

[0065] The data preprocessing process includes: selection of input feature variables, data digitization, outlier detection and replacement, missing data supplementation and data standardization, including:

[0066] S201: The disaster factor data obtained through statistical analysis is input into the data model as characteristic variables.

[0067] S202: Classify the data in the dataset, including qualitative variables and quantitative variables, and use different numerical processing standards. Among them, qualitative variables include: stratum lithology, adverse geological and hydrodynamic zoning, negative terrain area ratio, and quantitative variables include: stratum dip and surrounding rock grade.

[0068] S203: Quantitative variables and qualitative variables are divided into different disaster risk levels according to their characteristics, and are assigned values ​​based on the corresponding disaster factor classification standards. The assignment can adopt the assignment standards available in the prior art.

[0069] S204: Use the box plot method to detect and replace outliers in the numerical tunnel water inrush disaster data set. Among them, for the outlier replacement of the same variable at different hazard levels (I-IV), the mode of the qualitative variable at the current hazard level is taken as the replacement value of the outlier; for the quantitative variable, the average value at the current hazard level is taken as the replacement value of the outlier.

[0070] S205: For missing data, use step S203 to supplement the missing data. For qualitative variables, the mode at the current hazard level is used as the supplementary value for missing data; for quantitative variables, the average value at the current hazard level is used as the supplementary value for missing data;

[0071] S205: The standardization of the tunnel water inrush disaster data set is processed using the maximum and minimum normalization formula. The specific formula is as follows:

[0072]

[0073] Where, X nom is the standardized value, whose value is between [0,1]; X is the value of a single original data in the data set; X max is the maximum value of the original data under a certain characteristic variable; X min It is the minimum value of the original data under a certain characteristic variable.

[0074] When the influencing factors in the quantitative variables are discrete variables, the average value of the interval after classification is taken as the evaluation value.

[0075] Precision (P), recall (R) and F1 score (F1) are selected as evaluation indicators of the machine learning model. The data obtained after preprocessing in step S2 is input into the machine learning model and the training is completed to obtain the intelligent prediction result of the tunnel water inrush disaster level.

[0076] The construction and training of a single model includes:

[0077] S301: Select a single model as a machine learning training model. The single model selects at least n+1 different types, and inputs the divided and preprocessed training set and test set into the single model to obtain the prediction result of the tunnel water inrush disaster level.

[0078] S302: Perform hyperparameter tuning on the training model through K-fold cross validation combined with grid search parameter tuning method to obtain the optimal hyperparameter value, retrain the model after inputting the machine model hyperparameters, obtain the evaluation indicators of each single model after hyperparameter optimization, compare the evaluation indicators of each single model before and after hyperparameter optimization, and select the best n models as the single model for adaptation training.

[0079] The use of Stacking ensemble learning methods to improve machine learning models and optimize algorithms includes:

[0080] S401: Select n adapted single models as the first-layer base learners. In order to prevent the model from overfitting, select linear regression (LR) and ridge regression (Ridge) as the second-layer meta-learners, and use hyperparameter tuning methods for LR and Ridge to obtain the optimal hyperparameters of the two meta-learners.

[0081] S402: constructing m groups of integrated models by combining n base learners and two meta learners in different ways;

[0082] S403: Input the training set and the test set divided in the data set into the machine learning model, train m types of Stacking ensemble models, and obtain the tunnel water inrush disaster prediction results and the evaluation indicators of each model;

[0083] S404: Re-enter the optimal hyperparameters for the combination of integrated model P value, R value and F1 value above 0.80 before optimization, and conduct model training. Compare the evaluation indicators of the integrated model combination before and after hyperparameter tuning to select the optimal Stacking integrated model in this tunnel water inrush hazard prediction model.

[0084] The selected optimal Stacking ensemble model is compared with the previous optimal single prediction model, and the P value, R value, F1 value and confusion matrix are comprehensively compared to obtain the optimization degree of the Stacking ensemble model, thereby clarifying the improvement effect of the Stacking ensemble model.

[0085] A computer device and a storable medium applying the above prediction method, wherein the computer device includes a memory, a processor and a communication component, the memory and the processor are connected via the communication component, the memory stores one or more instructions, and the processor receives and executes the instructions.

[0086] The memory and the processor are both used in the above prediction method to complete the data transmission and learning model instruction actions of the prediction method.

[0087] Embodiment 1:

[0088] A total of 95 tunnels and 232 sets of cross-section data were selected to construct tunnel sudden water disaster cases and a database. The six most frequently occurring influencing factors were selected as evaluation factors for disasters, including stratum lithology, unfavorable geology, hydrodynamic zoning, negative terrain area ratio, stratum inclination and surrounding rock grade.

[0089] Based on the previous tunnel water inrush classification standards, the water inrush hazard level is divided into four levels, including: I-IV. According to existing research, the data in the dataset are divided into four levels according to their characteristics.

[0090] The data were randomly divided into training set and test set in a ratio of 8:2. The random division was performed by adding a random seed number in the program code to select the training set and test set separately without disrupting the order of the original data set.

[0091] The data in the dataset are preprocessed separately into training set and test set, and the precision P, recall R and F1 score are selected as the evaluation indicators of the machine learning model. Among them, P represents the accuracy of the model in predicting the danger level of tunnel water inrush, and its value is between [0,1]; R represents the comprehensiveness of the model in predicting the tunnel water inrush samples, and its value is between [0,1]; F1 is the harmonic mean of P and R.

[0092] Four different types of machine learning models, Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM) and Adaptive Boosting (AB), were selected. The training set and test set were input and trained into four single machine learning models to obtain the intelligent prediction results of tunnel water inrush disaster level of the four single models. Among them, the P, R and F1 values ​​of the four models are as follows: Figure 3 shown.

[0093] By using K-fold cross validation (K=5) combined with grid search parameter tuning, hyperparameters of the other three models except Naive Bayes are tuned to obtain the optimal hyperparameter values ​​of random forest, support vector machine and adaptive algorithm. The hyperparameters of the model are input to retrain the model, and the evaluation indicators of each single model after hyperparameter optimization except Naive Bayes are obtained. The evaluation indicators of each single model before and after hyperparameter optimization are compared. Figure 4-6 As shown in the figure, three better models are selected, namely random forest, support vector machine and adaptive algorithm.

[0094] Random forest, support vector machine and adaptive algorithm are used as the first-layer base learners, linear regression and ridge regression are used as the second-layer meta-learners, and the meta-learners are hyper-parameter tuned. The three base learners and two meta-learners are compared in different combinations, with a total of 8 groups of integrated model combinations. The specific combinations are as follows:

[0095]

[0096] The training set and test set were input into data, and 8 sets of Stacking ensemble models were trained to obtain the tunnel water inrush disaster prediction results and the evaluation indicators of each model, such as Figure 7 shown.

[0097] For the integrated model combination whose P value, R value and F1 value before optimization are all above 0.80, the optimal hyperparameters are re-entered for model training, and the evaluation indicators of the integrated model combination before and after hyperparameter tuning are compared, such as Figure 8-10 As shown in the figure, the optimal Stacking integrated model in the tunnel water inrush hazard prediction model was selected. After comparison, it was found that SNL was the optimal Stacking integrated model.

[0098] The SNL integrated model is comprehensively compared with the above four single models in terms of P value, R value, F1 value and confusion matrix. After hyperparameter optimization and comparative analysis, it can be seen that the optimal single model for the prediction of tunnel water inrush disaster is SVM, and the optimal Stacking integrated model is SNL. Compared with the optimal single model set, the optimal integrated model is Fig.11 As shown in the figure, it is concluded that the SNL integrated model is the optimal model, and the SNL integrated model is more accurate and efficient for predicting tunnel water inrush disasters.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for predicting sudden water inrush in a tunnel, characterized in that: include: S1: Construct a data set based on tunnel water inrush disaster cases, analyze and select disaster-causing factors, and clarify disaster classification standards; S2: Divide the data set into training set and test set according to a predetermined ratio; S3: Taking the disaster-causing factor as the characteristic variable, the training set and the test set in the data set are preprocessed respectively; S4: Select precision, recall and F1 score as evaluation indicators of machine learning models, train machine learning models with preprocessed data, optimize model hyperparameters, repeat training, and select suitable machine learning models; S5: The stacking ensemble learning method is used to improve the model. The adapted single model is used as the first-layer base learner, and linear regression and ridge regression are used as the second-layer meta-learner. The hyperparameters of the single model are tuned, and the prediction effects of multiple groups of ensemble models under different combinations of base learners and meta-learners are tested and compared. S6: Compare the optimal single model and the optimal integrated model using evaluation indicators and confusion matrix to obtain the evaluation accuracy of the optimal integrated model.

2. The method for predicting sudden water inrush in tunnels according to claim 1, characterized in that: Analyze and select disaster-causing factors and clarify the disaster classification standards, including: Count the frequency of occurrence of influencing factors in the statistical data set, and use high-frequency influencing factors as disaster-causing factors for prediction and evaluation; The impact levels of disaster factors are divided according to their influence on tunnel water inrush.

3. The method for predicting sudden water inrush in a tunnel according to claim 2, characterized in that: Data preprocessing of the dataset includes: Disaster factors are divided into qualitative variables and quantitative variables, and they are digitized separately, where quantitative variables and qualitative variables are assigned values ​​according to the corresponding disaster factor impact levels; The box plot method is used to detect outliers in the numerical data set; Replace outliers and supplement missing values ​​in the data; The data set after outlier processing is normalized.

4. The method for predicting sudden water inrush in a tunnel according to claim 4, characterized in that: The data outlier replacement and missing value supplementation include: For the outlier replacement process of the same variable at different risk levels, for qualitative variables, the mode of the data at the current risk level is taken as the replacement value of the outlier; for quantitative variables, the average value of the data at the current risk level is taken as the replacement value of the outlier; To supplement the missing values ​​in the data set, for qualitative variables, the mode of the data at the impact level is taken as the supplementary value of the missing data; for quantitative variables, the average value of the data at the impact level is taken as the supplementary value of the missing data.

5. The method for predicting sudden water inrush disaster in a tunnel according to claim 1, characterized in that: Train the machine learning model with preprocessed data, optimize the model hyperparameters, and then repeat the training. The selected suitable machine learning models include: Select multiple machine learning models as training models, and input the preprocessed training set and test set into the single machine learning model; Through K-fold cross validation combined with grid search parameter tuning method, the hyperparameters of the machine learning model are tuned to obtain the optimal hyperparameter values ​​of the model. The model hyperparameters are input, the model is retrained, and the evaluation indicators of each single model before and after hyperparameter optimization are compared to select the optimal n suitable single machine learning models.

6. The method for predicting sudden water inrush in a tunnel according to claim 1, characterized in that: In the second-layer meta-learner, the linear regression and ridge regression use hyperparameter tuning method to obtain the optimal hyperparameters of the two meta-learners.

7. The method for predicting sudden water inrush in a tunnel according to claim 1, characterized in that: The use of Stacking ensemble learning methods to improve machine learning models specifically includes: The ensemble learning model is composed of n base learners and two meta learners to form at least m sets of ensemble model combinations; The m groups of integrated models are trained with the training set and test set data to obtain the tunnel water inrush disaster prediction results and the evaluation indicators of each model; Re-enter the optimal hyperparameters for the integrated model combination with precision, recall and F1 score values ​​above 0.80 in the m groups of integrated models for model training; The evaluation indicators of the integrated model combination before and after hyperparameter tuning are compared to obtain the optimal Stacking integrated model.

8. The method for predicting sudden water inrush in a tunnel according to claim 6, characterized in that: The integrated model combination method is an integrated model composed of one or more base learners and any one of the meta learners.

9. A computer device, characterized in that: Includes memory, processor and communication components; wherein the memory is configured to store one or more instructions; The processor is loaded by the communication component and executes the memory instructions to complete the prediction method described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores executable instructions, and the executable instructions are loaded and executed by a processor to implement the prediction method according to any one of claims 1 to 6.

Images