Search

Corrosion of mechanical components has been of wide interest in recent decades. Corrosion is caused by physicochemical action between a metal and its environment, which can result in changes in the metal’s properties and functional damage in mechanical components. The main corrosion manifestations of zinc alloy coatings in marine environments are discussed in this paper, which first explores the application of high-performance aluminum alloy coatings in industry. Subsequently, the ZAS35 alloy used for this paper was experimentally prepared, and orthogonal tests were utilized to determine the optimum matching values of process parameters for zinc alloy coatings to generate materials. The hardness and wear resistance of ZAS35 were evaluated against other zinc alloys. An iterative learning control algorithm was employed to determine the thickness of the zinc alloy coating. The optimal control of the steady-state process of coating thickness can be achieved by using the NARX dynamic neural network model as a predictive identification model for zinc alloy coating thickness. Finally, data were collected using an optical microscope to quantitatively analyze the effect of zinc alloy plating on mechanical life. When the thickness of zinc alloy is 1.7 μm, the probability of life is [947.56,978.36]×103h interval t=0.999, which is improved by 409~684.11×103h compared with the plating thickness of 1.10μm . After adding aluminum elements to zinc plating, the corrosion potential of the plating decreases from −800mV to −1000mV, and the zinc-aluminum alloy prevents electrochemical corrosion of the plated layer with cathodic corrosion inhibition.

We use deep learning to extract and identify the physiological indicators, sports, and data analysis parameters, providing scientific references for athletes’ personalized training. This paper aims to construct an optimization system for personalized training for athletes based on machine learning. Initially, we designed the system’s overall structure, hardware, and software scheme, and then we modeled the algorithms for measuring four physiological parameters. The NTC thermistor thermometry method was utilized to measure body temperature, the photoelectric volumetric method for determining blood oxygen and heart rate, and the ECG signal method for calculating blood pressure. The adaptive threshold method uses the human body’s steady-state recognition algorithm, based on a single triaxial acceleration sensor, to recognize steady-state motion states such as resting, running, and walking. After the construction of the system was completed, it was applied to the sports team of a university in Guangzhou, and a semester of personalized training optimization experiments for athletes was conducted. The system found a maximum error of 0.02 °C between the measured body temperature and the results from the medical temperature gun, ensuring stable performance during short-term body temperature changes like training. Except for B, C, D, and G errors of 1%, the rest of the athletes monitored by the system in this paper’s blood oxygen results are consistent with the oximeter. The accuracy of recognizing each sport is above 90%. In the eight swimming events that need to be assessed, the average score before the beginning of the semester was 65.43, and after the experiment, it was 87.14, an improvement of 21.71 points. The system in this paper has a great auxiliary effect on the optimization of personalized training for athletes in terms of physical function monitoring, sports status statistics, and training intensity setting, which provides new ideas and methods for the integration of personalized training for athletes with cutting-edge information technology.

Accurate recognition and analysis of English semantics is of great significance in the application field of computer and artificial intelligence technology. Traditional text analysis technology has poor real-time analysis accuracy and efficiency. This paper constructs an English semantic analysis model based on neural networks. By designing an English semantic framework that integrates LSTM and RNN and optimizing it on the basis of LSTM and RNN models, an English semantic analysis model with improved attention mechanisms and Bi-LSTM is constructed. By comparing the Bi-LSTM+Attention model proposed in this paper with other semantic analysis models, the classification accuracy of the model constructed in this paper reaches 98%. Through the practical application of the model to analyze the semantic coherence of English, the average score of the semantic coherence quality measured by the model is 15.76, and the average score of the manual judgment is 16.03, which indicates that the application of the semantic analysis model constructed in this paper is close to the effect of the manual judgment.

Digital technology has revolutionized and changed the way of interactive experience, among which digital art is widely acclaimed nowadays. This paper combines digital art with local cultural elements to create cross-cultural visual communication and constructs an evaluation index system for its effects. The weight values of the indicators calculated by the gray correlation and Euclidean distance methods are combined using the combination assignment formula. Afterward, the cloud model is used to determine the degree of affiliation of each indicator, and finally, the comprehensive evaluation results of cross-cultural visual communication of cultural elements in this paper are obtained. The cloud evaluation results show that the overall cloud body distribution interval of the cross-cultural visual communication of Guangdong local culture is (6.47, 9.65), indicating that the visual communication effect of Guangdong local cultural elements is at an excellent level. Furthermore, the study revealed that the audience spent the longest total gaze time (3.96s) on the photographic style-text bottom-left type visual images. This paper explores the role of digital art in promoting the development of local culture and cross-cultural communication, and the visual communication enhancement strategy proposed from the perspective of visual presentation opens up a new path for the visual communication of local culture.

Students are the main body of the classroom, and their learning status reflects the quality of classroom teaching to a certain extent. This paper aims to manage students’ learning status in industrial education classrooms by designing a student learning status assessment system. The collected video data from industrial education classrooms are processed by binarization and histogram equalization. The key technologies, such as face detection and eye movement analysis, are used to detect the learning status of students in the industrial education classroom, and the functional modules, such as data acquisition and statistical analysis, are combined to form this paper’s student learning status assessment system based on facial feature detection. It is found that the face detection algorithm of this paper’s system improves the detection accuracy by 11.35% compared with the baseline algorithm when the standard difficulty is difficult, and this paper’s algorithm is able to successfully detect and display the students’ facial features through 68 key feature points. The system in this paper is able to detect students’ learning states, such as concentration, fatigue, and doubt, by analyzing their eye movement frequency and other indicators. After applying the system discussed in this paper, the final grades of students in industrial education have significantly improved.

Land use change has gradually developed into a core area of global environmental change research. In this paper, we use object-orientated modeling to construct a model that combines Markov models, neural networks, and cellular automata. We extend the Markov model to the traditional CA, fully utilizing the advantage of ANN in simplifying the definition of land use transformation rules and obtaining a large number of spatial variable parameters of the model. This successfully simplifies the structure of the model and the definition of transformation rules. We apply the constructed Ann-CA-Markov land use change analysis model to the evolution and prediction of land use in County A. It has been found that the proportion of arable land area in County A decreased from 23.3% to 12.1%, and the proportion of construction land increased from 28.07% to 50.87%. From 2000 to 2020, other land continued to converge into construction land in large quantities, so the land area of County A increased from 1224.73km² to 1295.15km² in 2020. The area of arable land converted out is the largest among the five types of land, with an arable land area of only 308.11km² by 2020. The probability of conversion of four land types, namely, arable land, forest land, grassland, and watershed, to construction land is 21.7%, 10.5%, 10.9%, and 9.2%, respectively, by 2030, while the probability of conversion of construction land to arable land is 21.7%, 10.5%, 10.9%, and 9.2%, respectively. The probability of converting land to cropland is 13.9%. The model constructed in this paper shows strong performance in the analysis of land use change evolution and prediction of County A, which is in line with the design expectation and makes an innovative exploration for realizing the effective simulation of spatial and temporal land use changes.

Machine vision technology improves the ability to detect the environment of industrial robots, which contributes to the improvement of the collaboration efficiency of swarm robots. This paper proposes a roadmap extraction algorithm that utilizes the improved Mean Shift algorithm to extract the roadmap information from images acquired by binocular cameras. Subsequently, the IEO algorithm with K-Means++ is used to optimize the task allocation of the swarm robots. The experiments show that the average error of this paper’s algorithm’s road sign extraction is 0.025m, the ratio of full scene and homing reaches 90.6%, and the results of the scheduling algorithm under the three kinds of task volume are 59.89, 773.08, and 2704.67. The efficiency of scheduling task completion in dispensing experiments is 9.56% higher than that of the comparative algorithms. The experiment proves that the algorithm proposed in this paper has good performance and practical effects on optimizing the industrial robot control system.

Pedestrian re-recognition is the process of retrieving pedestrians with the same identity information as a given pedestrian from a cross-domain view candidate image dataset or a non-overlapping surveillance video sequence using computer vision techniques. The goal of this paper is to use convolutional neural network techniques to re-recognize pedestrians in dynamic scenes. Through the use of convolutional calculations, activation function selection, and other techniques, this paper provides basic technical support for the research of pedestrian re-recognition technology. A Siamese network is obtained by applying convolutional neural networks to pedestrian recognition as the main discriminative model for subsequent research. In order to effectively solve the problem of occlusion, illumination, and other possible interference with the recognition effect in dynamic scenes, this paper adopts the image enhancement method of random erasure and introduces the attention mechanism to improve the robustness of the model to the occlusion of pedestrian images. Through the examination of the model on the dataset of the average accuracy mean (MAP) and other indicators and the actual application in the construction site and other scenes, it is proved that the pedestrian re-recognition model used in this paper has a more significant recognition performance compared with other models, and can still maintain more than 80% of the accuracy rate under the application of dynamic and complex scenes.

In the process of applying traditional teaching forms, problems such as low participation in classroom activities and poor independent learning are gradually highlighted. This paper first designs the task-based cooperative language acquisition model then constructs the supervision and management system for cooperative learning, and finally establishes the evaluation mechanism for task-based cooperative learning. This paper uses the questionnaire survey method, Pearson correlation coefficient method, principal component analysis method, and multiple regression analysis methods as data analysis methods. By establishing a mathematical model, the parameters to be estimated are listed, and then these data are fitted, and finally, a statistical analysis is performed. Through the questionnaire survey method, this paper verified that the method had a positive effect on students’ Japanese learning; 46.2% of students enjoyed learning Japanese, and 92.3% participated in group discussions. The effectiveness of Japanese language teaching was assessed by extracting three main factors through principal component analysis, which were summarised as pre-study performance, classroom performance, and individual thinking performance. Under the language acquisition model, teachers can improve students’ learning effectiveness by monitoring and encouraging their performance on these three indicators.

In the context of cultural and tourism integration, the study of Shanxi folk songs’ dissemination path and multicultural integration has important practical significance and far-reaching influence. Through an overview of cultural and tourism integration in Shanxi folk songs, the characteristics and mutual influence of the two are summarized. The digital communication path of Shanxi folk songs under the background of cultural and tourism fusion is explored by constructing a database of Shanxi folk songs, an automatic evaluation system of sight-singing, and an offline communication mode, respectively. The results show that the response time of the database remains within 4 seconds when the number of users reaches 2000. In the analysis of the note alignment module, the F1 data value of this paper’s method is 13.42% higher than that of the LSTM model, and this paper’s model is more suitable for the note alignment of Shanxi sight-singing. In the offline communication model, the construction of facilities has the greatest influence on the communication effect, with a regression coefficient of 0.812, a T-value of 35.421, and a P-value of 0.003. This study not only enriches the cultural life of the people and enhances the sense of identity of the national culture but also promotes the inheritance and development of the culture of Shanxi folk songs and contributes positively to the prosperity of the culture and tourism industry in the Shanxi region.

This paper proposes the integration method of athlete training volume monitoring information based on deep learning, preprocessing the monitoring information using wavelet transform, obtaining the athlete training volume information after denoising and dimensionality reduction, combining with the theory of deep learning, utilizing convolutional neural network for feature extraction and integration of the processed information, and performing simulation test and analysis. The average Gini coefficient is 84.926, which proves the effectiveness of the method used in this paper. After exercising, the athletes’ weight and body fat rate were monitored to reduce a certain degree, and their lung capacity was improved. A deep learning algorithm generated personalized exercise program training achieved a heart rate interval of 94% for safe and effective workouts. The three stages of the test subjects’ training were tracked and analyzed, and the use of training monitoring can effectively promote the efficiency of training. The physical fitness program (P < 0.01) and physical fitness test (P < 0.05) in the first stage compared with the third stage showed significant improvement.

This paper proposes a values sentiment analysis model based on RoBERTa-BiLSTM-Attention based on the mechanism and path of values process evaluation under sentiment analysis. After extracting and presenting the values and sentiment features data, we build the values dataset of college students, finish the training of the model, and obtain the classification results of values and sentiment. The college students’ value identity model is established to analyze the value shaping of education at the national, social, and individual levels. The correlation coefficients of the influencing factors of college students’ values were analyzed, and the correlation coefficients of the influencing factors were less than 0.75, and the p-value was less than 0.01. The hypotheses were put forward, and the standardized regression coefficient of the “social role model” was 0.2658, which was significantly higher than that of the other indicators, and the standardized regression coefficient of “emotional satisfaction” was 0.2658. The regression coefficient of “emotional satisfaction” is 0.1987, second only to cognitive identity. In view of the existence of the problem of values, the proposed political education intervention guidance strategy, after the political education intervention, 71.3625% of the students think that the values of guidance have a great help, but there are still some shortcomings, compared with this paper puts forward the optimization of the values of guidance recommendations.

The outcome-oriented e-education concept is one of the current international advanced education concepts, and its generation and development fit with the development of information technology and the social demand for the quality of talent cultivation. In this paper, a knowledge mapping system for university English courses based on the concept of outcome-orientated education is investigated to enable the integration of university English course knowledge and its visualization in the form of web pages. Knowledge points, concepts, definitions, and other information about the university English subject are extracted, and various data sources, which contain structured, semi-structured, and unstructured data, are collected, integrated, and extracted in the form of English knowledge triads. The system testing results indicate that, in comparison to the traditional DistMult method, this paper’s method enhances the classification accuracy of the three English course datasets by 0.93%, 1.68%, and 0.85%, respectively. The experimental results validate the effectiveness and superiority of the system. Meanwhile, the questionnaire survey found that the system can effectively help learners improve their confidence, interest, and initiative in learning, enhance their learning effectiveness, improve their learning efficiency, and provide them with high-quality learning resources that have good application value.

This paper borrows the concept of entropy and refers the information entropy to the computer-aided English translation to build up the information entropy assessment and evaluation model and the information entropy-based English translation optimization model. The information entropy operation formula is used to calculate the fuzziness between the original text and the target translated text, and at the same time, the segmentation function is utilized to find the approximation value of the information entropy value obtained in a sufficiently fine segmentation of the translated text. Obtain the rectangular window function of semantic Gaussian marginalization, project the information entropy data, add the semantic correlation factors of words, identify the features of semantic information, and realize the optimization of English translation. Simulation experiments are carried out to verify the performance of the model. The information entropy evaluation and analysis model in this paper can achieve convergence after 45 iterations. In contrast, the word error rate and the cut-off error rate of the English translation optimization model are both lower than 10%, and the feature recognition and classification are higher than 80%. The fuzzy statements in Chinese writer Lao She’s work “Teahouse” are selected to explore the naturalness of translation. The information entropy value of the translation optimization model in this paper is closer to the original text, and the English translation’s naturalness is better than that of the GLR model.

The countryside contains rich tourism resources and business opportunities due to its beautiful natural scenery and unique humanistic environment. The purpose of this paper is to create an innovative path for rural tourism e-commerce development by designing an e-commerce mobile service platform. The F-PBFT algorithm, hybrid collaborative filtering algorithm, and panoramic VR technology are comprehensively applied to provide technical support for platform design. Combining the analysis of tourists, tourist attractions, and other platform service objects, this paper designs and completes a rural tourism e-commerce mobile service platform containing a variety of functions. Exploring the application case of Battle Flag Village, the net profit margin of e-commerce sales in Battle Flag Village after the application of rural tourism e-commerce mobile service platform can reach up to 47.84%, with a year-on-year increase of 18.88%. At the same time, the platform has attracted the attention of a large number of tourists after its application, and the search volume of Battle Flag Village on the platform reaches up to 241,968.33 during the peak hours of the tour, which significantly enhances the popularity of Battle Flag Village and effectively promotes the innovative development of rural tourism e-commerce business in Battle Flag Village.

Spanish folk music is characterized primarily by folk song tunes, dance rhythms, and folk instrumental music. This paper combines the understanding of the artistic expression of “7 Spanish Folk Songs” and “Don Quixote to the Intended One” music works, proposes to start the sound envelope computation to perceive the music beat, and utilizes the dynamic planning algorithm for real-time tracking. Combined with the three-dimensional model of stereo-visual rendering, an interactive module for presenting Spanish folk music has been established. The selected dataset, the dynamic programming algorithm of this paper, and other algorithms are used to compare the results of music beat recognition. Design the questionnaire of instinctive layer emotional experience and behavioral layer emotional experience, analyze and process the research data, and compare the advantages and disadvantages of the traditional music presentation with the music embodiment of the augmented reality group. This paper proposes a music beat recognition algorithm that has the advantage of real-time detection. In terms of automatic music emotional experience, the mean values of instinctive layer emotional experience for the traditional group and augmented reality group are 5.22 points and 6.125 points, respectively. By combining reality and information interaction, the augmented reality group is more adept at conveying the flavors and art of Spanish national music.

The classification of jade grade has always been a very critical part of the jade industry, and improving the accuracy of jade grade classification is of great significance to the sustainable development of the jade industry. The study constructs a mineral identification classification model based on Raman spectroscopy + PCA through Raman spectroscopy and PCA principal component analysis and analyzes the data of jade grades and constituents. The actual performance of this paper’s model is explored by comparing its effectiveness with other algorithmic models in jade classification and the accuracy of classification parameters. The model in this paper is feasible in classifying the four grades of Hetian jade (seed material, gobi material, shanliushui material, and shanmu material). Green dense jade’s main minerals are -quartz and a few other minerals, including albite, hematite, graphite, and tourmaline. The main compositions of the sample jade are SiO2, Al2O3, and K2O. The overall accuracy of this paper’s model in classifying Xinjiang Hotan jade grades is 97.9%, which is significantly higher than that of the KNN classification algorithm and SVM classification algorithm. The total accuracy of this paper’s model on each parameter of jade grade is 85, which is higher than the 60 of the KNN algorithm and the 62 of the SVM algorithm, and the classification accuracy grade is high.

The increasingly competitive market situation in the construction industry requires that construction enterprises strengthen the cost control of construction projects in order to improve the economic efficiency of enterprises. This paper is based on the improved genetic algorithm to realize the optimization of the cost control strategy of the construction project and effectively overcome the problems of weak cost control consciousness and high material procurement cost in the previous cost control. A construction company is selected as the object for the case study, and the genetic algorithm is used to calculate and analyze the cost control of the construction company. The return on investment, net present value, and internal rate of return are used as indicators to measure the economic benefits before and after optimizing cost control strategies. The improved genetic algorithm calculates that among the cost control factors of the construction company, procurement management, and field operation have a high probability of being selected in the genetic calculation, and the final project cost is 36.7849 million yuan through the genetic algorithm, which achieves the goal of project cost control. At the same time, this paper finds that cost control has a significant positive effect on the improvement of economic efficiency, and the economic efficiency of this construction company before and after the optimization of the cost control strategy is significantly improved.

The consciousness and behavior of students in the Ideological and Political Education curriculum generate massive amounts of data information, how to allow educators to quickly obtain information from the massive amount of text data is very important to improve the energy efficiency of classroom education. SVM technology is employed in this paper for data mining and text classification. Firstly, using the web crawler method, the text of messages related to the Ideological and Political Science course posted by students on social networks is collected. The short text was preprocessed before performing sentiment analysis, which mainly included interaction information filtering, word segmentation, and lexical labeling. Then, the SVM model suitable for students’ ideology analysis is constructed, using the Gauss radial basis kernel function to accurately depict the distribution structure of the data, and the L1-SVM model with more stable computational performance is also proposed. The extension method of the classification algorithm in the real number domain is summarized at the end. This algorithm’s accuracy is 78%, and its F1 value is 80%, which is higher than the other three algorithms. DAG-SVM and recall are both optimized to a lesser extent. Overall, the classification efficiency of the algorithm in this paper has been improved. The positive effect of this paper’s algorithm on improving the effectiveness of Ideological and Political Education can be seen in the significant increase in the learning interest of the experimental class.

As an important part of the raw materials for building construction, high performance concrete is well known for its many properties. This paper analyzes the prerequisites for high-performance concrete proportioning from the technical point of view and processes involved in designing high-performance concrete proportioning. A particle swarm algorithm combined with a neural network is used to establish the relationship model between concrete strength and proportion, and the constructed PSO-BP model is used for the prediction of concrete mixing ratio strength to get the best material proportion. The prediction ability of the BP neural network model, GP model, and PSO-BP model is compared. In order to test the applicability and reliability of the high-performance concrete formulated by the PSO-BP model in members, static load tests were carried out in this paper on a 20m test single girder to test the strain and deflection of concrete in the control section. The results show that the relative error of the high-performance concrete strength predictions predicted by the PSO-BP model is within 2%. It shows that the optimum high-performance concrete can be formulated using the PSO-BP model. The test beams can meet design and practical engineering requirements in terms of strength and stiffness and can be applied to real bridges. Based on the research and analysis, suggestions have been made for the application of high-performance concrete in bridge construction from four aspects.

Automatic tobacco grading systems can promote the standardization and unification of tobacco acquisition activities, improve production efficiency, and promote the long-term stable development of this industry. In this paper, we first extract the shape and color features of tobacco leaf structure, use a support vector machine to determine the difficult samples, add the difficult samples to the training set, and use the deep convolutional neural network method to assign initial values to the model, which reduces the occurrence of a model overfitting phenomenon and improves the prediction accuracy. Constructing a convolutional neural network based on EfficientNetV2-S for an automatic tobacco grading model. The performance of the model was tested on HSV and RGB images, and finally, automatic tobacco grading was applied to two batches of high-quality and good tobacco. It is found that the accuracy of the model training set and test set of this paper is 0.077 and 0.094 higher than that of the VGG16 model on HSV and RGB images, respectively, and there is no upward trend in the loss function. The model’s training operation time for grading two batches of tobacco is 27.56 seconds, which is more efficient. The accuracy rate of the two batches of tobacco is higher than 90%. The model in this paper in the practical application performance in addition to a higher degree of grading efficiency and accuracy, which is stronger than the manual identification in terms of efficiency and accuracy recognition stability. This paper’s research offers a feasible path and useful exploration to effectively improve production efficiency and optimize the process in China’s tobacco industry.

The use of big data comprehensively serves physical education, so that students can clarify their learning situation and make reasonable changes in physical education teaching. In this paper, firstly, we do an analysis and investigation on the application of big data in physical education teaching in colleges and universities, apply the tree hierarchy algorithm to collect the key data indexes of physical education teaching classrooms, and use the SMDA aggregation algorithm to aggregate and analyze the collected key data. The weight of each index system of teaching evaluation is calculated using the hierarchical analysis evaluation method. The role and application of analytical methods in physical education teaching are discussed in the context of big data. This paper constructs a system for evaluating teaching effects, which includes 5 primary indicators and 20 secondary indicators. The evaluation results of the 10-factor index system in the teaching process are divided into five grades to obtain the distribution intervals of excellent, good, medium, qualified, and poor students’ learning performance. The results of data analysis of the attributes of this paper show that the percentages of Cluster l, Cluster 2, and Cluster 3 are 22%, 66%, and 12% respectively. The weights of teaching ability, method, content, attitude, and effect in the actual teaching process were 20.97, 24.29, 24.08, 3.89, and 6.31, respectively. This paper elaborates on the effects and roles of four aspects of the interactive platform Big Data application in physical education teaching and learning in the context of Big Data analytics methods. Ideas for the use of big data analysis methods in sports teaching in colleges and universities are presented.

With the deepening of higher vocational English teaching research and the continuous advancement of reform, this paper combines in-depth learning with higher vocational English teaching and makes an in-depth study of higher vocational English teaching practice based on in-depth learning theory and learning theory. First of all, the paper expounds on the concept of higher vocational English teaching and the research of English teaching. Explain the related concepts of psychological factors and the composition of psychological factors, then describe the model of in-depth learning, elaborate the related algorithms of in-depth learning optimization methods and the functions of various data of in-depth learning-related research, and finally, based on in-depth learning, explain the psychological factors of teachers and students in higher vocational English teaching. It reflects the importance of psychological factors in higher vocational English teaching. With the development of in-depth learning, we should apply in-depth learning to higher vocational English teaching and optimize the teaching mode of in-depth learning reasonably, including formulating comprehensive higher vocational English teaching objectives, adjusting students' psychological status reasonably, and carrying out cooperative learning.

The cultural hedging and fusion of the new era embodied in literary works is of great significance to the communication, development, and prosperity of Chinese and Western cultures. This paper selects the English works compiled and published by Lin Yutang as the research object and analyzes the communication value generated in the process of its compilation and publication. After designing a questionnaire qualified by reliability and relevance analysis, the questionnaire is used to investigate the audience’s exposure to English works and the degree of understanding of the newage cultural hedging embodied in the works. The results of the survey show that multimedia has become the main channel for audiences to access Lin Yutang’s English works. The audience’s understanding of the new age cultural hedges embodied in the works is poor; the acceptance of the new age cultural hedges is at a medium level (3.514 points), and there is a significant correlation between the acceptance level and the understanding effect. It is also found that the multimedia communication method consisting of video and text in a compiled publication has the best comprehension effect (4.857 points) on the new age cultural hedging of the audience. This paper provides a reference path for the compilation and publication of Lin Yutang’s English works under multimedia and lays a foundation for deepening the audience’s understanding of the new age cultural hedge.

With the rapid development of the information age, new technological means are constantly applied to the field of education and produce good results. This paper uses data mining algorithms to extract and analyze data on college English education and explore how to adjust the teaching methodology. On the basis of improving the inherent defects of the DPC algorithm, this paper determines the clustering center through a scoring function, uses the K-neighbor method to form the cluster backbone, and proposes a nearest-neighbor-based label propagation method to propagate the labels to their adjacent nodes to complete data mining. After mining and analyzing the current situation of English education, it was found that the age group over 30 years old accounted for 77.6%, female teachers accounted for 74.6% of the total number of teachers, teachers with the titles of lecturer and assistant professor accounted for 58%, and 33% of the students were not too satisfied or dissatisfied with the content of the English course. It shows that the English teaching team of universities in this province has shortcomings such as gender imbalance, insufficient young and senior teachers, and less than satisfactory content of English courses, which need to be improved in several aspects.

Migration learning is a kind of deep learning that plays an important role in risk prediction and warning. In this paper, we use the Triplet-loss representation learning technique to map data samples of the same category to adjacent spatial regions, map data samples of different categories to different spatial regions, and add domain adaptive computation to complete domain adaptation. XGBoost performance is also optimized to improve the prediction results. After completing the risk prediction model construction, this paper also incorporates indicator weights to propose a risk warning model based on a weighted knowledge graph. The analysis found that the model accuracy of the compliance risk prediction model is 1.155% higher than that of two traditional prediction models on average, and the indicators of accuracy, F1-score, and AUC are all over 0.99, which indicates that it has high accuracy. After applying the optimized risk management system in an enterprise, it is found that the weight of the indicators of the enterprise’s compliance management system reaches 25.71%, the combined weight of the legal audit system and the risk prevention and control mechanism is 16.23% and 14.10%, respectively, and the combined weight of the two indicators of the appraisal and evaluation of the performance of the compliance management and the accountability for the violation of the law exceeds 8%. The weights of the indicators related to the degree of business standardization are close to 16.51%, indicating that the enterprise’s daily production and operation activities are standardized and orderly, and the perfection of the compliance management system is in line with the real situation of the enterprise. It can be seen that the risk management system makes accurate judgments on the compliance risk of the selected enterprise, which reflects the feasibility of the application of the new model.

This paper builds a business English intelligent teaching network platform through cloud computing, virtual reality, corpus and automatic scoring system, and other information technologies. Educational information technology helps construct a linguistic corpus by utilizing vocabulary lookup and MI values to create a one-stop solution for multi-level language analysis and application. The essay scoring project in the Business English Smart Teaching Network Platform utilizes the bag-of-words vector model to extract the features of each word, text, and topic to complete automatic essay scoring. After analysis, it can be seen that the business skills and interests of the experimental group have significantly improved after the teaching of the Business English Wisdom Teaching Network Platform. After the corpus-scaffolded writing teaching training, the mean values of students’ vocabulary richness ranged from 3.869 to 4.108, and sentence variety ranged from 3.961 to 4.135. Automatic scoring of compositions resulted in a significant improvement in the writing quality of students (P=0.000). The smart teaching network platform mentioned in this paper can be utilized to improve business English teaching in the context of informationization.

Nautical talents are the first resource and fundamental guarantee for the development of marine careers, strengthening the construction of nautical talents and realizing the effective supply of nautical talents have become the urgent task of building a strong marine country. This paper combines the basic situation of the current nautical personnel training and the training requirements of nautical personnel, constructs the vocational literacy and ability enhancement path of nautical students based on the integration of post-course, race, and certificate under the guidance of the OBE concept, and constructs the corresponding index system. Subsequently, combining the hierarchical analysis method and entropy weight method, the weights of the indicators in the evaluation system of nautical students’ vocational quality and talent ability are calculated, and the cloud model is utilized to evaluate the vocational quality and talent ability of nautical talents after cultivation. The results of the study show that the comprehensive evaluation level of the vocational quality and talent ability of the maritime students of Jimei University after the implementation of the pathway is “good”. Among the secondary evaluation indexes, the vocational concept evaluation cloud has the highest degree of affiliation, which is 9.31. This indicates that the vocational concept of navigation students is being cultivated at a very high level. The evaluation result of “vocational behavior” also belongs to the “good” level. The cultivation path proposed in this paper provides a reference for the enhancement of the vocational quality and ability of nautical talents, and it can improve the cultivation of nautical talents through the synergistic approach of government, industry, enterprise, and school, and guarantee the enhancement of the vocational ability and career expansion of nautical talents.

Recent years have seen intensive research and widespread application of 6G wireless transmission technology, providing a technical bridge for the application of speech network analysis to spoken English teaching. Thus, this paper suggests a method for improving 6G technology. This paper primarily focuses on the following areas: First, to prevent overfitting, the dropout technique under 6G is added to the model, and the speech feature extracted from the data by the coding network is directly utilized. We then utilize the feature for either reconstruction or classification purposes. Initially, we perform unsupervised reconstruction using unlabeled data, and once we obtain the network parameters, we use the labeled data for classification. The next step involves feeding both data simultaneously into the model to calculate the error. Finally, we use gradient descent to minimize the error and optimize the parameters until the model converges. This model can convert sound-related symbols or information into visual symbols, and it can also convert speech into text. Comparative analysis shows that the improved method in this paper is far better than other methods in terms of noise reduction, and the signal-to-noise ratio of this paper is 3.76 dB higher than that of the LMS algorithm and 1.36 dB higher than that of the spectral subtraction method, which can stimulate the students’ interest in learning spoken English and increase the student’s interest in learning by 13.64% as a whole. It can be summarized through the comparison that this paper’s improved method increases the clarity of speech network analysis, which helps students teach spoken English.

In this paper, the convolutional neural network is applied to the processing of stylistic features in the images of landscape paintings of Wei Jin and North and South Dynasties. After convolution and pooling activation, rich and less parametric feature maps are generated to lay a solid foundation for generative adversarial networks. Meanwhile, in order to ensure the rigor of the image dataset of landscape painting images under scene transformation, an improvement is proposed on the basis of traditional GAN technology, and a function represents the improved CycleGAN model. The experimental dataset has been constructed, and the loss function, network training, and hyperparameters have been designed for the model. The visual and conversion outcomes of the model-generated images are evaluated through simulation experiments. The migration of all landscape painting style textures is within the range of (0.5,2.4) at a gray level of 8. The migration styles increase as the gray level increases, and the data between groups does not overlap. In the subjective evaluation of the landscape painting style transformation generated by the model used in this paper, the score of the generated image is 3.8135 points, while the number of high scores is more than 65% of the votes. The model constructed in this paper has a better effect on the transformation of the image style of the Wei, Jin, and North and South Dynasties, and it can satisfy people’s visual needs.

This paper takes green finance policy as the research object and collects local government policy texts about green finance so as to study its policy structure in depth. Then, it studies the theory of green finance to support the low-carbon economy, empirically analyzes it in terms of measurement using the panel vector autoregressive model, and tests its smoothness and covariance to explore the impact of green finance in the development of the low-carbon economy. According to the findings, the proportion of demand-based green financial policies is the lowest among the five provinces, with a mean value of 22%. The extreme differences in development levels of a low-carbon economy and green finance are 1.52 and 1.46, respectively, showing different characteristics. The model regression coefficient of the level of green financial development is 0.08, and the development of a low-carbon economy positively influences it. Although the effectiveness of green financial policies will fluctuate, the overall trend is upward. This paper analyzes the panel vector autoregressive model and the effectiveness of policy tools to provide suggestions for improving the policy system.

In the face of people’s growing spiritual civilization needs, the application of traditional art colors in modern visual communication design has become a hot spot of attention. In this paper, a model for extracting traditional art color features is constructed to provide a methodology and theory for applying traditional art color in modern visual communication design. In the model construction, the max-min clustering algorithm is proposed to achieve color segmentation, measure the distance between the clustering center and the samples, and improve computing speed. Based on the K-means algorithm, the initial clustering center selection and the number of class clusters are improved, and the color feature extraction method is optimized to improve the accuracy of color extraction. In the performance experiments of the model, the All, Noncc, and Disc parameters of this paper’s color segmentation algorithm are lower than those of other algorithms in color segmentation of different pictures, and the performance is good. The accuracy of the color feature extraction test in different color spaces is close to 100%, the average verification accuracy is as high as 99.8%, and it takes less time. The aesthetic, originality, symbolism, and spirituality evaluation indexes of the poster work “Lead,” designed by combining the model of this paper, have an average score of more than 4, which reaches a good level.

How to carry out scientific and reasonable teaching design and then improve the teaching effect is a problem faced by many college English teachers. Aiming at such problems, this paper is based on the six elements of the BOPPPS teaching model to design a blended teaching mode of university English and finally designs a blended teaching mode of university English based on the BOPPPS teaching model. In order to confirm the practicality of the teaching model, research subjects and research materials are identified, and after collecting sample data through questionnaires, the independent sample t-test algorithm is used to analyze the effect of the teaching model designed in this paper. The data show that there is a significant difference between the experimental group and the control group in the five qualities of scientific thinking, with a p-value of less than 0.05, and in terms of English achievement, the corresponding t-test result is a sig (two-sided) of 0.007

In the context of energy saving and emission reduction to protect the environment has become a social consensus, environmental benefit is a social responsibility that enterprises must actively undertake, and the technological advantages of information technology companies make them more equipped to enhance environmental benefits. Therefore, this paper proposes countermeasures for information technology companies to enhance their social responsibility and environmental benefits. To achieve practical countermeasures for energy savings and emission reduction, this paper proposes a method to improve the LSTM power prediction model using the Sparrow search algorithm for the company’s electricity management. The model optimizes the network structure of traditional LSTM by searching for parameters such as learning rate, iteration number, and the number of neurons in the two hidden layers of LSTM through the sparrow fitness function. The model proposed in this paper has an average prediction error rate of 3.32% in predicting the annual electricity consumption of a county for five years from 2018 to 2022. After an enterprise introduced the social responsibility practice countermeasures proposed in this paper, the company’s net profit margin increased by 12.2% on average, CO2 emission reduction was 963.2 tons, the average monthly electricity consumption was reduced by 24936.5 kWh, and the environmental performance score increased from 3.2 to 5.4.

In the context of practical education, deepening the reform of quality education and implementing the fundamental task of cultivating moral integrity have become the guidelines and the basis for the development of curriculum reform in colleges and universities. This study conducts data mining based on the association rule model on the influencing factors of the reform of the Civic and Political Theory Course in colleges and universities to obtain the key influencing factors in the process of the reform of the theory course. Then, under the perspective of deep learning, the idea of practical parenting is integrated, and the structural framework of Civic and Political Theory course reform is designed from four directions: learning theme, learning objectives, learning activities, and evaluation feedback, and finally, the course reform method of this paper is examined through teaching practice. The results show that the influence weights of self-factors, school education factors, family factors, and social factors are 0.3022, 0.3521, 0.1381, and 0.2076, respectively, with self-factors and school education as the key influencing factors. After the teaching practice, the P-value of each dimension of the students under the curriculum reform based on this paper is less than 0.05, and the grade of the Civics and Political Science Theory course is improved from 81.47 to 90.45, which is an increase of 7.49 points compared with the class of the regular course. The reform method based on deep learning in this study can promote students’ development and improve their academic performance, which provides a reference for the research on the reform and development of the Civics and Political Science Theory course.

This paper proposes a reform of the teaching methodology based on the exercise prescription course centered on intelligent exercise prescription recommendation and designs a specific implementation plan. A criterion function is used to determine and represent the constant terms of the user-set data using the K-means clustering algorithm. The personal data of users is added on this basis, and the attribute weighting is used to calculate user similarity and construct the user matrix. The core parameters of intelligentized exercise prescription are examined, and the relevant data of the exerciser group is obtained through modeling. The set of similar cases is determined, and the exercise effects in the set of similar cases are fused and calculated, and the effect level of the fused effects in the cases is discriminated. The model developed in this paper is implemented in the college physical education classroom, and the student’s attitudes toward physical exercise and fitness levels are analyzed. The results show that the attitude towards physical exercise behavior of students in group A is significantly better than that of those in group B. The significance test (F = 7.985, Sig = 0.005) is less than 0.05. Taking the 50-meter sprint as an example, the difference in the duration between male students and female students in groups A and B is 0.83s and 0.9s, respectively, which is a large enhancement, which shows that the intelligent exercise prescription has a positive impact on physical education teaching.

Ethnic music culture is a rare and precious artistic treasure in all national cultures, and the inheritance and promotion of ethnic music culture is an essential part of music education teaching in colleges and universities. This paper delves into the characteristics of the development and dissemination of ethnic music culture in the Internet era, with the aim of studying the integration of ethnic music culture into music education teaching in colleges and universities through the use of Internet technology. Through the collaborative filtering algorithm, students’ preferences for ethnic music works are mined so as to recommend accurate teaching resources for college students on the ethnic music online teaching platform constructed based on the collaborative filtering algorithm. In order to fully prove the effectiveness of the teaching platform designed in this paper, the rough set theory and neural network algorithm are used to construct the online teaching quality evaluation model for college ethnic music. The questionnaire survey method is used to study the status quo of ethnic music teaching in colleges and universities, and it is concluded that at present, there are problems in ethnic music teaching in colleges and universities, such as insufficient concepts of students learning ethnic music and insufficient attention to ethnic music in colleges and universities themselves. Through the analysis of the effect of the recommended algorithm, the design of the evaluation index system, and the practical application, the quantitative assessment value of the teaching quality of the ethnic music online teaching platform designed in this paper in the practical application is 92.11, which indicates that the comprehensive rating of the quality of the ethnic music online teaching in colleges and universities in this paper is excellent.

Cultivating innovative talents is an important goal of the talent cultivation strategy in the new era, and ideological and political education is an indispensable part of cultivating a correct outlook on life and the spirit of innovation. In order to fully leverage the supporting role of ideological and political education in cultivating innovative talents, this paper proposes an enhanced collaborative filtering algorithm and content recommendation algorithm. The traditional Civic and Political learning evaluation algorithm is improved by considering the forgetting factor and introducing disciplinary abilities and sequence dependence. The results of the experimental analysis point out that the average grade improvement of the seven Civics and Politics knowledge points of the students in the experimental class reaches 10.3%, the mean value of the four innovation dimensions reaches 14.95 points, and the average agreement rate between the self-assessment results of the learning effect and the results of the evaluation model is 90%. It shows that the optimized Civics personalized learning and evaluation method, based on this paper, has positive effects.

In recent years, with the interaction and integration of modern cultural and creative industries with Chinese excellent traditional culture, various innovative cultural and creative products have been introduced, ushering in new opportunities for the inheritance and development of Chinese excellent traditional culture. In order to integrate Chinese cultural elements into the design of cultural and creative products. This paper draws on the characteristics of DNA inheritance and mutation in living organisms to construct a multi-objective optimization model of DNA elements, and by applying the model to the analysis stage of cultural and creative product design, the designed products can be more completely integrated into the elements of Chinese characteristic culture to effectively guide the design practice of cultural and creative products. This paper takes Dunhuang Tang Dynasty Feitian cultural elements as an example for practical research through the integration of Dunhuang Tang Dynasty Feitian cultural elements of a series of cultural and creative products for the satisfaction survey from the symbolic perception, beautiful shape, functional and practical, cultural connotations, innovation and novelty of the five dimensions of the design effect assessment, the furniture category of cultural and creative products scored the highest, the average value of 4.766, the cultural and creative products in the symbolic perception of the dimensions of the score is high. It shows that in the Dunhuang Tang Dynasty, Feitian cultural and creative products can be perceived as symbols of the characteristic culture of the period.

The rapid development of the digital economy makes the center of gravity of enterprise development accelerate from the consumer field to the production and manufacturing field, penetrating all aspects of the daily operation and management of an enterprise. This paper presents relevant management strategies by exploring the impact of the ecosystem model of enterprise management innovation on the impact of enterprise management in the digital context. In order to measure the comprehensive efficiency value, the efficiency value of capital absorption, and the efficiency value of investment after enterprise management, the theory of antagonistic cross-efficiency is introduced, the antagonistic cross-DEA model is constructed, and the evaluation steps of enterprise management effect are given. Using this model to empirically analyze the management effectiveness of China’s construction industry, enterprise performance=4.563+0.352*digital innovation ecosystem index+0.236* periodic cost+0.362*number of R&D personnel, and the digital innovation ecosystem is significantly related to enterprise performance. Finally, this paper designs a corporate management strategy for the digital innovation ecosystem in the context of the digital economy from three perspectives.

The trend of our country into an aging society is becoming more and more obvious, and the elderly education service has become the focus of social attention. The integration of artificial intelligence into elderly education is one of the inspiring ideas in which the personalized recommendation algorithm can recommend educational resources according to the characteristics of older people, and it has the prospect of application. In this paper, we first provide a CTransD-GAT recommendation model based on a knowledge graph, which improves traditional problems such as data sparsity by setting weight preference and feature aggregation. A dynamic preference-capturing method is proposed based on contextual interaction to capture the variable user learning interests more accurately and flexibly. This paper examines the practical utility of personalized recommendation methods for educational resources based on these two improved techniques. The post-test mean score of each knowledge module test of the experimental group is improved by 1.83 points compared with the pre-test, 11.46 points improve the score of teaching ability, and the scores of perceived usefulness, ease of use, and intention to use are 3.82, 3.89, and 3.97, respectively. It shows that the improved educational resource recommendation model has an excellent effect on improving knowledge structure and teaching ability, and it is characterized by simplicity and ease of use.

This paper takes three colleges and universities in a province as an example, designs relevant questionnaires and distributes them, and analyzes the collected data by using statistical methods such as independent samples t-test and ANOVA one-way ANOVA. The paper analyzes the data collected using statistical methods such as independent sample T-tests and ANOVA to infer the overall situation of the current level of emotional identification with Marxist theory among Chinese college students. The data was examined in detail to determine the variations in the emotional recognition of Marxist theory among college students based on their gender, ethnicity, and professional classification. The results show that more than 50% of college students understand Marxism and strongly identify with it. The overall mean score of affective identification is 35.324, which is a good status for identification. In terms of different genders, the P-values of value identity, knowledge identity, social identity, and behavioral identity are less than 0.1, and there are significant differences. Emotional identity does not have significant differences in different ethnicities (P = 0.382 > 0.05) and different majors (P = 0.426 > 0.05).

Based on digital media technology, this paper defines Chinese art theory and, at the same time, combines digital media technology and the characteristics of Chinese art aesthetic discourse to construct an art aesthetic discourse system that covers the stage of sensory experience and the stage of “emotional experience”. In order to promote the digitalization of the art aesthetic discourse system, the MCFF algorithm is used to extract the features of art aesthetic discourse, match the features, and then merge the features of art aesthetic discourse based on the weighted summing algorithm so as to achieve the digitization of art aesthetic discourse features. The art aesthetic discourse system in digital media is analyzed based on the research data. The results show that compared with the traditional algorithm, the algorithm of this paper is better than the traditional algorithm in three aspects: pre-emphasis (growth rate of 62.70%), frame-plus-window (growth rate of 68.71%), and data conversion (growth rate of 72.14%). In addition, the aesthetic experiences of landscape painting and figure painting were 96.49±8.4 and 108.00±9.35 points, respectively, and F(1, 20)=20.746, p

In recent years, the number of psychological problems occurring in college students has been increasing day by day, and timely, convenient, and accurate psychological warning is an important way to prevent college students from psychological crises. Starting from the basic needs of the system and aiming at realizing the embedding of data mining technology in the psychological management system, this paper elaborates on the design and implementation of the data mining technology module suitable for the psychological management system. The clustering algorithm-K mean algorithm of data mining is used to distinguish groups of students with different categories of psychological problems, which provides data support for the next decision-making. Through simulation experiments between the system designed in this paper and four other mental health management systems, the clustering performance and system evaluation performance of this paper’s system are better than those of the other systems. The result of mining the mental health of college students through this system shows that 82.2% of the student’s assessment results show normal, and 8.35% of the students need to focus on, and this result is not much different from that obtained from the statistical survey of a personality questionnaire, which indicates that the use of clustering analysis in the system can be an effective prediction of the mental health of college students.

Carbon emission from building construction is an important issue in the construction industry, and the continuous application of management and assessment techniques forms a new trend of carbon emission reduction. This paper establishes a multi-objective optimization model for building construction carbon emission based on multidimensional data analysis of four objectives: schedule, cost, quality, and carbon emission. The particle swarm algorithm is improved by dynamically adjusting the inertia weight factor and penalty function to deal with constraints and is used to solve the multi-objective optimization model. Building construction cases are selected to predict and analyze the combinations of optimal execution modes under different teams, to compare the optimization results of configuration schemes and the efficiency of algorithms, and to further propose the practical path of carbon emission reduction in building construction. The study addresses the construction combination mode that meets the needs of various decision-makers, and the team 3 combination mode has the lowest carbon emission (228.41kg). The multi-objective optimization scheme under carbon emission constraints optimizes between 3.93% and 21.78% in the four objective dimensions. This paper further expands the scope of the multi-objective optimization model for building construction focusing on the “low carbon” objective, improves the feasibility of the configuration scheme, and then promotes the green and stable development of the construction industry.

Along with the continuous development of multimedia technology and the deepening of teaching information, virtual reality design factors are crucial to enhancing the impact of the teaching experience. The purpose of this paper is to address traditional art education’s transformational needs and develop an art education teaching system that utilizes virtual reality technology. It also uses the eye-tracking instrument to collect student eye movement data, and after preprocessing the data, such as missing data and noisy trajectory points, it counts the results of each eye movement index in the teaching process. The study showed that some of the students’ eye movement indicators during teaching had a strong correlation with the level of cognitive engagement in learning (P 0.05) when the design elements of the teaching interface were paired with the top of the bottom of the picture and the middle size and the top of the picture and the bottom of the picture and the large size. This paper provides references and their significance for related research, as well as the design of a virtual simulation platform for art teaching.

The quality of higher vocational nautical English teaching is not only related to the student’s vocational ability and job competence but even related to the safety of the ship and personal safety during the voyage. In this paper, we design a reform plan for higher vocational nautical English teaching based on the Hadoop-MapReduce distributed system framework, design the reading and writing algorithms of teaching resources, use a genetic algorithm to improve Pick-KX dynamic load balancing algorithm and construct a nautical English project-based teaching resource base. The effectiveness of the improved Pick-KX dynamic load balancing algorithm in this paper is tested through experiments with 200 to 1000 concurrent users. Finally, two senior nautical English classes are selected to conduct a semester of controlled variable experiments on project-based teaching reform and analyze the changes in performance. It was found that when the number of online users increased from 200 to 1,000, the IO and memory occupancy increased by 60% and 458M, respectively, and the average time taken increased from 0.8 to 5.8 seconds, which was in a reasonable range, and the repository was able to run smoothly. After one semester of experiment, the average score of the experimental class increased by 10.88 points, and the distribution of scores changed towards the high end of the range, while the scores of the control class did not change significantly. This paper’s nautical English project-based teaching resource library is effective, and the project-based teaching reform is a significant improvement in students’ nautical English scores. This study provides unique ideas and feasible methods for the reform of nautical English teaching, as well as the application and innovation of project-based teaching.

In the context of big data, traditional detection algorithms can no longer meet today’s needs. For traditional sensors, there are shortcomings such as long working times, high complexity, and high false detection rates. This paper proposes a new type of sensor and an algorithm for detecting anomalies in sensors based on Flink. The sensor network senses the monitoring targets in the monitoring area in real time and transmits them to the end users through wireless communication. Then, the fusion rule for target detection in sensor networks is studied. Then, the detection algorithm is computed using Flink and predicted using a sliding window and ARIMA model on the Flink platform. Then, the confidence intervals of the prediction results are calculated, and the outliers are evaluated. Finally, the K-Means++ algorithm is used for clustering and probability assessment of previously obtained outliers. Then, compared with traditional sensors, comparative analysis shows that the proposed method in this paper has some advantages in terms of both sensitivity (S) and quality factor (Q). The value of S is more than 320 than the 2D PhC sensor array. The value of Q is more than 5295 than the 2D PhC sensor array. This paper’s new sensor detection method is more diverse than the traditional method. The detection time is reduced. The detection accuracy is also improved compared to the traditional method. It can be summarized by comparison that the new sensor in this paper is more excellent than the traditional method of detection.

The explosive development of artificial intelligence technology greatly promotes the intelligent construction of museums and strengthens their cultural inheritance role. This paper takes artificial intelligence technology as its guide, analyzes the advantages of AI technology in the intelligent museum, and establishes the specific structure of an intelligent museum by combining VR technology. Wisdom Museum can realize the effective repair and presentation of cultural relics data. This paper uses three-dimensional laser scanning technology to obtain cultural relics point cloud data, repair the holes in the point cloud data through RBF, optimize the point cloud data by combining texture mapping, and input the optimized data into the GC-GAN model to realize the three-dimensional digital repair of cultural relics images. Moreover, the smart museum’s intelligent interaction system is built by combining virtual reality technology and related equipment. Taking Dunhuang mural point cloud data as an example, the number of point clouds of the RBF hole repair algorithm differs from the original data by only 5.86%, and the SSIM and PSNR values on the repaired portraits are 0.83 and 26.36 dB, respectively. The SUS total score for the user on the intelligent interactive system is 73.875, and the UEQ factor scores are averaged out at 1-3 points. The creation of a smart museum can be realized using AI technology, providing users with an immersive cultural relics viewing experience and activating the vitality of all kinds of cultural relics in the museum.

Enhancing the mainstream ideological identity of young people is an unavoidable issue in the ideological construction of socialism with Chinese characteristics in the new era, which is closely related to strengthening the national identity and expanding the mainstream ideological positions. In this paper, we refer to the E-learning platform framework to design a Marxism online learning platform to achieve the online dissemination of Marxism and ideological education for youth. The HRNN model is utilized to extract and identify the behavioral traits of youth on the Marxism learning platform and investigate the link between youth behavior and ideological identity. The results of the study show that the Marxist online learning platform has a better communication effect and can improve the identification of the youth group with Marxist ideology. Meanwhile, the correlation analysis shows that there is a significant correlation between video viewing completion, quiz completion, and ideological identity (P=0.000), which is highly positive. The suggestions put forward in this paper regarding communication management, communication technology, and publicity provide a reference for further online communication of Marxism and lay the foundation for the enhancement of youth ideology education.