In the era of artificial intelligence, online learning of English courses in colleges and universities has gradually become one of the mainstream learning modes. Based on the traditional teaching methods, this paper carries out the research on the optimization of English teaching path in colleges and universities. A micro-learning unit clustering model is constructed with four modules: data preprocessing, learning pattern mining, learning path diagram construction and micro-learning unit clustering. The model analyzes the learning state of learners through sequence pattern mining technology, and conducts orderly planning of learning resources based on learners’ characteristics. On this basis, this paper defines the online learning path planning problem and online learning path planning according to the continuity characteristics of learning knowledge points, and constructs the online learning path planning model. At the same time, the dynamic planning algorithm is selected to carry out the optimization of path planning. Based on the learning status of different learners, the optimal online learning path is planned to realize the optimization of English teaching path. Compared with similar classical algorithms, the online learning path planning model has the highest matching degree of 0.8 between the planned paths and the learning states of users under different learning resources conditions, which verifies the superiority of this paper’s model in the optimization of English teaching paths in colleges and universities.

The evaluation of labor education under the modernization of education should establish a long-term evaluation mechanism of labor education to achieve the goal of educating people by labor to build morality, labor to enhance intelligence, labor to strengthen the body, labor to cultivate beauty, and labor to innovate. In this paper, we use fuzzy clustering algorithm to construct labor education evaluation mechanism based on teacher evaluation standard. The results of this model for labor education evaluation are basically the same as those of manual evaluation, and can be used for the evaluation of the quality status of labor education. Based on this, the study plans in detail the preimplementation preparation, specific implementation steps and continuous optimization process of the evaluation mechanism. It also analyzes the implementation path of the labor education evaluation mechanism based on the fuzzy clustering algorithm by taking the example of Z elementary school in city A. The overall evaluation score of the quality of labor education in Z elementary school is 4.013, and there are still many areas that need to be improved. The evaluation mechanism of labor education based on fuzzy clustering algorithm was run in this school for 8 weeks, and the educational effect was continuously optimized through the incentive mechanism. Finally, the second-level fuzzy judgment method is introduced to further optimize the mechanism. Based on the new evaluation mechanism of labor education, individual student development can be evaluated, curriculum quality can be assessed, and operable solutions can be provided for the improvement of the quality of school labor education.

The aim of this paper is to construct a data model applicable to youth sports training in the IoT environment and develop efficient pattern recognition algorithms to achieve accurate analysis and assessment of youth sports training status. The features of youth sports training data collected by IoT technology are extracted through a combination of deep learning and feature decomposition. The feature vectors obtained from feature extraction are inputted into the Long Short-Term Memory (LSTM) network to generate the data model of youth sports training in this paper and predict the state of youth sports training. The prediction results are input as features into the Support Vector Machine (SVM) algorithm, and these features are extracted using the Empirical Modal Decomposition (EEMD) method, and at the same time, the hierarchical idea is utilized to realize the recognition of youth sports training patterns. The results of the study showed that the errors of the results of predicting youth sports training states using the LSTM model were mostly within 0 ± 0.5. The prediction accuracies of the model on the test set for the three athletic training state metrics were 96.80%, 99.40%, and 98.80%, respectively. Meanwhile, the performance of the SVM model for youth athletic training state pattern recognition using the SVM model was significantly superior, with 100% accuracy on the test set for four models, including pattern 2.

In this study, we first collected and preprocessed data from 500 basketball players between the ages of 13-35 years old in the same-court rivalry training in Northwest China, after which we utilized the Global Chaos Bat Algorithm (GCBA) for the mental training anxiety emotion feature extraction, and analyzed the correlation between each feature and the anxiety emotion through the Pearson coefficient. Finally, the LightGBM-based emotion prediction model was constructed, and the SHAP value was introduced to evaluate the feature importance of the model. The results show that the LightGBM model performs better and has higher prediction accuracy, which is as high as 96.68%; the interpretation results of the SHAP algorithm indicate that the gender and age of the basketball players are the main real-world factors for assessing their anxiety in same-court rivalry training. In addition, their game scores, opponents’ strengths and injury histories during the same-court rivalry training were the main intrinsic factors for their anxiety. In conclusion, the psychological state of basketball players can reflect the severity of their training anxiety, and it further reveals the relationship between the psychological characteristics of basketball players and their training anxiety.

In this paper, leisure tourism is taken as the entry point of the research, and the fused location key point features are added and integrated with the multidimensional features of time, location and space to construct an accurate portrait of social media tourism users. On the basis of tourism user profiles, a two-step clustering algorithm is combined to carry out cross-cultural analysis of social media data, to explore and excavate the performance of users’ tourism preferences under the cross-cultural ability of social media. Meanwhile, in order to realize the prediction of leisure tourism preference, a combined model based on BP neural network and ARIMA is proposed to improve the accuracy of leisure tourism preference prediction by fully considering the linear and nonlinear laws of tourism statistics. The ARIMA-BP combination prediction model is applied to predict the leisure tourism preference in the future from 2027-2034. During the period 2027-2029, the number of leisure tourism tourists maintains a high annual growth rate of more than 15%, while the growth rate slows down after 2029, with an average annual growth rate of 4.44%. In 2033, the number of leisure tourism tourists will reach 1,691,280,000, and the leisure tourism preference of tourism users has been significantly strengthened.

During the operation of transmission lines, there are sudden failures and a large number of slowdeveloping, preventable “gradual” failures, which have seriously threatened the safe and stable operation of the transmission system. Based on analyzing the multidimensional environmental factors affecting line safety, the study proposes a method for identifying the operating state of transmission lines based on the AdaBoost integrated learning algorithm, and develops a set of transmission line hidden danger monitoring system. A decision pile based on Ginin indicators is used as a weak classifier, and the hidden danger monitoring results and their confidence levels are output by training and weighted summation of multiple weak classifiers. Using historical data for validation experiments, the proposed method achieves an accuracy of 95.92% in recognizing the operating state of transmission lines, which is a more superior performance compared with traditional machine learning methods. The system can basically realize the hidden danger monitoring of transmission lines, so as to assist the field operation and maintenance personnel of transmission lines to carry out fault investigation, and reduce the transmission line tripping due to the development of hidden danger into fault.

School-enterprise integration is an effective way to improve the running level of higher vocational colleges and universities and stimulate the innovation vitality of enterprises. This paper takes the higher vocational hotel management profession as the research object, combines IPO model and intuitionistic fuzzy hierarchical analysis method (IFAHP) to realize the construction of schoolenterprise integration performance evaluation index system, and utilizes the fuzzy comprehensive evaluation method (FCE) to carry out specific application of this evaluation system. On this basis, the fuzzy set qualitative comparative analysis (fsQCA) was used to explore the specific path of schoolenterprise collaborative education in higher vocational colleges. The empirical study shows that the constructed evaluation system of school-enterprise integration has high reliability and operability, which is conducive to horizontal and vertical comparisons of higher vocational colleges and universities, and is also applicable to the authorities of higher vocational colleges and universities and the third-party evaluation organizations for the performance evaluation of school-enterprise integration. At the same time, it also indicates that the realization of high-performance schoolenterprise collaborative parenting programs in higher vocational hotel management majors cannot be achieved through a single variable, but rather through the form of conditional grouping to play a key role. There are five paths to improve the effectiveness of university-enterprise collaborative parenting in colleges and universities, and in the paths, the enterprise scale, the pre-project input and the project implementation process are the core conditions to improve the effectiveness of university-enterprise collaborative parenting in higher vocational colleges and universities, and the combination of changes of the three plays a decisive role in different condition grouping states.

In this paper, Kernel density estimation method is used to analyze the distribution characteristics of continuing education resources and reveal the distribution pattern of resources in different communities. On this basis, CCR model and BCC model are introduced to optimize the DEA model of data envelopment analysis and evaluate the resource allocation of continuing education institutions. The resource allocation optimization and dynamic planning system of continuing education is further constructed, and the system dynamics simulation method is used to simulate the optimization process of resource allocation, which provides a scientific basis for the governance of community education. The results show that: continuing education resource input is polarized in quantity, its performance level is not high, regional differences are significant, and scale efficiency is a key factor restricting quality improvement. This paper constructs a system dynamics model for the quality and user use of educational information resources, and in view of the difficulties of optimization and dynamic planning of the allocation of continuing education information resources, it is proposed that the managerial and digital educational resource platform construction-based inputs such as teachers’ information technology application ability, assessment system construction, etc. should be improved to promote the high-quality and balanced development of continuing education informatization.

Aiming at the bridge monitoring system, some of the monitoring data are abnormal due to equipment failure and environmental impacts. In this paper, the time-frequency domain convolutional neural network method is applied to the calculation of monitoring data and the risk assessment of bridge structure. The data collected by the acceleration sensor is firstly sliced and sampled and visualized. Then wavelet analysis is used to preprocess the cluttered data, and Wigner-Ville distribution and Fast Fourier Transform are introduced to extract time-frequency features from the collected data. A convolutional neural network is proposed and the network is trained on dual channel images fusing time and frequency domain images. By analyzing the spectrogram and and time-frequency diagram of the bridge monitoring data, the method of this paper classifies the bridge health condition into three kinds: no disease, slight disease and disease, which can accurately determine the health condition of different bridges, and the assessment accuracy of the risk assessment model based on the fusion of time-frequency domain information reaches 97.78%, which indicates that the high efficiency and feasibility of the bridge inspection data computation and the risk assessment model in this paper can meet the actual engineering construction needs of bridge inspection.

As the global climate change problem is getting more and more serious, carbon emission quota allocation is more and more emphasized by countries all over the world, while the traditional carbon quota allocation program has the problem of single objective. In order to improve the scientificity and acceptability of the carbon quota allocation scheme, this paper constructs indicators and forms multiobjective functions to formulate the carbon quota allocation scheme from the three perspectives of efficiency, fairness and sustainability, and builds a multi-objective optimization model for carbon quota allocation and decision support. Aiming at the solution problem of the carbon quota allocation model, an improved hybrid swarm algorithm based on Gaussian perturbation, tournament selection strategy and proposed Newtonian local optimization search operator (L-BFGS) is proposed. The model is used to explore the quota allocation scheme for cities in the Bohai Economic Rim in 2030. In the three single-target pre-allocation schemes based on the principles of efficiency, fairness, and sustainability, the difference between the cities with the largest and smallest quotas is 319 Mt, 289 Mt, and 256 Mt, respectively, which lacks scientificity and rationality. In contrast, the allocation results of the multi-objective pre-allocation scheme proposed by the carbon quota allocation model in this paper are relatively balanced and the difference is small, which can eliminate the conflict between multiple principles.