China’s tourism industry has become a strategic pillar industry in China, playing an important role in developing the economy and providing employment. Therefore, how can we avoid or reduce the hazards of tourism emergencies and give full play to the development advantages that tourism brings to the city has become the focus of this paper. In this paper, the objective function is used to construct a two-stage stochastic optimization model without opportunity constraints to minimize the partial cost of the first stage and the expected total cost of the second stage. Considering the problem of maximizing the utilization rate of emergency shelters in tourist attractions, the opportunity constraint model is introduced to help decision makers allocate resources reasonably. Based on the center siting cost and vehicle distribution cost, a mixed integer nonlinear objective function model is constructed and the model is solved using the improved ant colony algorithm. Seven emergency management simulation scenarios are set up to analyze the effect of emergency management by combining simulation and empirical research. The experimental results show that among the emergencies at all levels of the sites in Y scenic area in the past 5 years, the number of level 2 emergencies is the highest, and the average number of emergencies occurred in each site in the past 5 years is 7.48. According to the model’s solution of the site selection results, the emergency center A covers 5 distribution warehouses, and the emergency center B covers 10 distribution warehouses.

The numerical simulation of the velocity decay characteristics of multilayer spherical fragments under bombardment loading is carried out by using LS-DYNA, and the distribution law of the velocity decay characteristics of multilayer spherical fragments is obtained. The ballistic limit (V50) of the multilayer spherical fragment on a 4mm 2024 aluminum target at 90° angle of attack is also obtained by ballistic test. Based on the consistency between the numerical simulation and the test results, the influence of the quality of the multilayer spherical fragment on V50 is analyzed. The air resistance coefficient is calculated with the numerical simulation results by constructing a rag flight distance calculation model. The maximum error between the calculated results and the test results is about 2%, and the theoretical calculated values are in good agreement with the numerical simulation and test results. Under the condition of the same initial velocity, the attenuation coefficient of the spherical fragment in long-distance flight is constant. The aerodynamic drag coefficient is related to the initial velocity of the fragment, which is linearly related to the initial velocity in the range of the design concern of the combat unit (1.2-2.2km/s).

Compared with traditional target detection algorithms, deep learning-based target detection algorithms trained on rich sample data do not need to design features artificially, are better adapted to environmental changes, and the accuracy and efficiency of detection are dramatically improved. This paper relies on the deep convolutional neural network structure to construct the YOLOv5 target detection model. On the input side of the model, three data enhancement techniques, namely mosaic data enhancement, adaptive anchor frame and adaptive image scaling, are adopted respectively to improve the accuracy, generalization ability and detection speed of the model in the target detection task. Attention mechanism is introduced and YOLOv5 framework is improved to construct a new network model. For the efficiency of the target detection task, a loss function is added and a global average pooling operation is used for feature mapping to realize a fully convolutional network. Two widely used evaluation metrics are chosen to evaluate the target detection efficiency of the model. The experiments show that the MAP value of the improved YOLOv5n network model is 2.9979 percentage points higher than that of the original YOLOv5 model, and at the same time, the FPS is substantially improved by 31%. The time taken to complete 100 rounds of training is 20 min, which is 10 min shorter than the pre-improvement algorithm.

The study constructs a solar cell simulation model and tracks the maximum power output from the solar cell using the MPPT algorithm. Simulation simulation experiments are conducted to analyze the effects of changes in environmental factors such as season, weather, light, temperature, wind speed, etc. on the current and power output of solar cells. The total output power and the peak output power of the solar cell are the largest in summer, which are 7407.69kW and 114.93kW, respectively, and the total output power and the peak output power of the solar cell are the smallest in fall, which are 1748.96kW and 31.58kW, respectively. The peak power output of the solar cell is the largest in sunny days, which is 107.56kW, and the smallest in rainy days, which is 37.06kW. The total solar cell power output is maximum (7896.93kW) on clear to cloudy days and minimum (1955.27kW) on rainy days. The solar cell output current and maximum power values decreased with decreasing light intensity. The ambient temperature has little effect on the short circuit current, the output current increases slightly with increasing temperature, the open circuit voltage decreases drastically with increasing temperature and the maximum output power decreases with increasing temperature. The maximum output power of the solar cell increases with increasing wind speed.

MOOC as a new teaching mode is developing in full swing, however, MOOC courses face the thorny problems of high dropout rate and low completion rate. Therefore, this paper selects 12 learning behaviors and uses logistic regression model, decision tree and other methods to predict the withdrawal behavior according to the MOOC data on 365 University platform. The logistic regression prediction is analyzed for prediction accuracy, and its AUC value is 0.83 and 0.75, which proves that the logistic regression analysis can achieve the prediction of MOOC withdrawal behavior more stably and accurately, and helps to provide scientific guidelines for improving MOOC learning mode and learning efficiency. From the case study, it is obtained that among all the learning behaviors, the weight of online rate is 0.7582, which has the highest weight, indicating that the online rate of college students is an important index for judging whether they will produce withdrawal behaviors, which deserves the attention of MOOC platforms and educators.

By optimizing the automation configuration of medium-voltage distribution lines, capturing the initial signals of cable insulation hidden danger, combining the real case data of 6 years of distribution network insulation faults and hidden danger in a city of Zhejiang, summarizing the waveform law and progressive signal characteristics in the process of insulation hidden danger deterioration, a set of real-time monitoring method based on the analysis of big data of the medium-voltage distribution line cable insulation deterioration of the corona hidden danger has been developed. The method is based on the master station to realize localization, instead of periodic on-site equipment charged detection, has been verified on-site and found discharge traces cable head in advance. This method utilizes distribution automation and dispatch automation configurations to capture the instantaneous zero-sequence overcurrent signals corresponding to insulation degradation discharges, waveform characteristics, acoustic mutations, and environmental information as input. A quantitative risk algorithm consisting of eight analysis dimensions such as zero-sequence spike characteristics, number of spikes, and synchronization of acoustic ripple and spike timing is used. Three optional computational media, including master station, enhanced DTU, and DTU external component, are used to give hidden risk localization. The two methods, local discharge detection robot and manual detection, are used to confirm the site and then carry out out outage maintenance to prevent the further expansion of hidden dangers. The method relies on the distribution automation of existing protection devices and master station configuration to assist a small number of sensors and edge computing devices to realize, through the protection device uninterrupted monitoring instead of manual periodic local discharge detection. It solves the problems of high cost of periodic testing, unavoidable accidents caused by continuous insulation degradation in the interval of testing cycle, hidden location of some cables and blind area of testing, and effectively improves the reliability of power supply.

Deep learning-based methods can be combined with skeleton data, but they only consider the feature vectors formed by joint coordinates and do not extract the spatio-temporal dependencies between skeletons. In order to provide a more comprehensive detection and recognition of spatio-temporal relationships in human action sequences, this paper proposes a graph neural network-based human action detection and recognition method by combining YOLOv5, AlphaPose, and spatio-temporal graph convolutional network (ST-GCN) algorithms under the interpretable artificial intelligence (XAI) perspective. Firstly, the improved YOLOv5s target detection algorithm is used to get the human body detection frame and obtain the human body position information, then the AlphaPose pose estimation algorithm is used to obtain the coordinate information of the joint points of the human skeleton, and finally the improved ST-GCN algorithm is used to construct the spatio-temporal graph and extract the spatio-temporal dependencies between the joints to complete the human body action recognition. Through experimental verification, the method can accurately recognize human fall, running, kicking, and squatting actions on the dataset, with a recognition accuracy of 92.04%, and compared with the five baseline models, the method has higher recognition accuracy, with the values of each index greater than 91%, which can provide technical support for human behavior recognition.

The development of society and the change of the times have brought some degree of change to the development of preschool music classroom. This paper introduces the OBE concept into the education of preschool music course, designs the teaching objectives of the music course according to the guidance of the concept in order to realize systematic teaching, and analyzes the students’ cognition of various dimensions in the preschool music course by using the cognitive level diagnosis method. Based on this method and the Hadoop system, a big data platform for integrated teaching of preschool music course is constructed, and teachers are assisted to intervene in teaching through the platform’s teaching data query, statistics and analysis functions, so as to realize the integrated teaching mode of preschool music course and mathematical statistical analysis. The results of the teaching practice show that after the implementation of the integrated teaching mode, students’ learning attitude towards the preschool music course and their knowledge of music-related knowledge increased significantly (P<0.05), and the level of independent and inquiry learning was also improved. This study can make the teaching of preschool music course more meaningful, more adaptable to the needs of talent training in today's society, and create an integrated teaching curriculum that is more conducive to the cultivation of students' musical literacy and interest.

ETC gantry data and other monitoring data provide data support for highway traffic flow prediction, for this reason, this paper proposes an attention mechanism-driven traffic flow prediction model to scientifically coordinate and schedule highway traffic conditions. Based on the fusion of multivariate monitoring data, the model utilizes ConvLSTM to generate global location coding, learns the data characteristics through the jump expansion attention structure, and completes the traffic flow prediction using the mask attention structure. The example analysis verifies that the predicted values of traffic flow and speed of this paper’s model are closer to the real values, and compared with the models such as ARIMA, LSTM and BiLSTM, this paper’s model has lower values of RMSE and MAE indexes in the prediction of traffic flow and speed, and the prediction error is smaller. The article also validates the model’s prediction under 5min, 15min and 30min prediction lengths, showing that the model has excellent performance and good prediction stability.

With the continuous development of high-power laser equipment and the continuous expansion of the scope of the application platform, the demand and application of high-power laser equipment in various fields are becoming more and more extensive, and its output power has also put forward higher requirements. In order to promote the development of high power laser equipment toward higher energy conversion efficiency, research and design temperature control device to manage the waste heat generated in the energy conversion process of high power laser equipment. On the basis of PID control algorithm using LADRC algorithm, rapid realization of temperature precision control, so as to enhance the energy conversion efficiency of high-power laser equipment. When the temperature control device in the temperature control range of 10 ℃ ~ 40 ℃, the temperature control accuracy is better than ± 0.03 ℃, and in 144s to reach the set temperature, the temperature control overshoot is less than 2.33%, to meet the requirements of the laser working temperature control in the working process of high-power laser equipment, and to lay the foundation for the realization of high energy conversion efficiency. Compared with the modified PID controller, the energy conversion efficiency is relatively improved by 1.57%. The temperature control device designed based on the improved PID control algorithm in this paper can significantly improve the energy conversion efficiency.

In today’s big data environment, the demand for digital transformation of traditional libraries is becoming more and more urgent. The article adopts BERT-BiLSTM-CRF model to extract digital library resources and retrograde entities, and constructs digital library resources knowledge graph. On the basis of digital library resources integration, it combines the collaborative filtering algorithm based on users and items to construct and improve the intelligent recommendation mechanism of digital book resources. The integration results of digital library resources and intelligent recommendation results are analyzed separately, and a survey on reader satisfaction is conducted. The recognition accuracy of this paper’s method is significantly higher than that of the traditional text-like processing data model. The collaborative filtering algorithm in this paper provides statistical analysis of the types of book resources read by each reader, and recommends the top 5 book types in terms of similarity to him/her. This paper’s method has better results in book resource division and book resource recommendation accuracy compared to other recommendation methods. The average value of readers’ satisfaction with the resource recommendation mechanism of the digital library in S city for each dimension and each index is more than 4 points.

Planted roofs have good heat preservation and insulation properties, which can effectively alleviate the urban heat island effect and reduce the energy consumption of buildings and the carbon dioxide content in the atmosphere. The study describes the heat transfer process of planted roofs into three parts, derives the heat transfer equations of the leaf layer, soil layer, and roof layer of planted roofs, and clarifies the calculation of relevant parameters in the model of planted roofs. Taking integrated design as the technical standard, the stereotypical design of planted roof buildings and their building parts, components, fittings, engineering equipment, etc. The insulation exterior wall panel enclosure system is standardized to realize industrialized production of wall panel components, integrated design of connection nodes, and assembly construction. The analysis results show that during the test time, the average convective heat transfer heat flow of Module H containing vegetation is a maximum of 119.21W/m2, and the total convective heat transfer heat flow of the whole day is 2835.99w/m2, which has the best thermal insulation performance. Among all the roof modules, only Module H has the heat transfer direction from outdoor to indoor throughout the day. Finally, based on the above conclusions, the self-insulated exterior wall system’s specific construction method and technology are given to provide the basis and reference for the specific construction in practice.

This paper first introduces the regional power marketing management platform, after which the 3 major functional modules of this power marketing management platform are designed. Then MobileFaceNet is used as the basic network for face recognition feature extraction in the context of deep learning, and the SE module is used to optimize the network performance and network expressiveness. Afterwards, the Taylor expansion of the negative log-likelihood function is used as an optimization criterion to optimize the face detection model (MTCNN) and the face recognition model (SE-MobileFaceNet). Finally, the running effect and performance of SE-MobileFaceNet model are measured. The main conclusions are as follows: in 1:1 mode, the accuracy of SE-MobileFaceNet model for the three datasets DRDS, DE and DPDS is 95.99%, 96.98% and 98.83%, respectively. In addition, the SE-MobileFaceNet model can avoid excessive redundant calculations, so that its recognition rate reaches 95%.The accuracy of the SE-MobileFaceNet model for monitoring and recognizing the information of the management platform ranges from 97.43% to 100%, and it has a good operating effect in the identification of the regional electric power marketing management information platform, and the overall satisfaction rate of the testers for the model is also >85%. The overall satisfaction of the testers to the model is also >85%. Obviously, the SE-MobileFaceNet model proposed in this paper has a very broad application in regional power marketing management information platform identity recognition.

The emergence of digital humanities echoes the paradigm transformation of literary research. In this project, natural language processing technology is applied to the analysis of ancient Chinese literature, and the attention mechanism is embedded in iterative null convolutional network to build a named entity recognition model based on ancient literature. Then we integrate MacBERT pre-training model, combine the dual-channel structure of aspectual word features and semantic features, design hierarchical attention mechanism, and complete the construction of aspectual-level sentiment analysis model. Through experiments to analyze the model performance and conduct the analysis of ancient literary works, the results can be obtained that the two models show better named entity recognition and sentiment analysis effects, and the values of each evaluation index are above 83%. Craftsmen (44.7%) and merchants (22.4%) appear more frequently in the sample Ming Dynasty fictional characters, revealing the social and cultural background of the development of the commercial economy and the emergence of the civic class at that time. Positive emotions accounted for 67.9% of the poetry samples of the Tang Dynasty, and the war of the country’s reward (0.334) and send-off feelings (0.226) co-occurred most frequently with positive emotions, reflecting the social and cultural background of the Tang Dynasty, which was characterized by prosperity and affluence, and the emergence of the literati to build up their careers.

The development of urbanization is rapidly changing, and various undertakings are flourishing, while the sports industry, as an important segment of urban regional economic development, plays an inestimable role in the development of the entire city construction. The study takes the sports industry and economic development of 27 provincial capital cities in China from 2018 to 2022 as the research object, establishes the evaluation indexes for the high-quality development of the sports industry based on the principle of index construction, and establishes the weights of the indexes. Taking Harbin as a case study, the effect between urban sports industry and economic growth is analyzed with the help of impulse response analysis, Granger causality test, and variance decomposition of VAR model. The results show that the development of urban sports industry and economic growth can promote each other, with a long-term cointegration relationship, and the positive effects between the two are slowly reduced over time when they are impacted in the long term. Granger test shows. It indicates that there is a unidirectional causal relationship between urban sports industry and economic growth.

Flexibility control and vision of robots are important acquisition and feedback links in robot control, and the study of multi-sensor data fusion is becoming more and more important as the complexity of robot tasks increases. This paper describes the robot kinematics and inverse kinematics process by studying the knowledge of D-H model theory and parameter definitions in the machine kinematics model, reveals the changing relationship between the robot joint control and end pose, and establishes a kinematics-based vision servo control model. On this basis, the coupling error compensation algorithm is used to combine the visual position control quantity as well as the force sensing position correction quantity to form the final visual and force sensing supple control strategy. Meanwhile, for the lack of adaptability of classical impedance force control on unknown constraint environments, a two-fuzzy adaptive sliding mode controller is designed according to the Lyapunov stability theorem to drive the robot end in order to achieve the actual position tracking expectation. The results of simulation experiments and motion contour tracking experiments show that the control algorithm proposed in this paper has better control accuracy and is more robust to noise and uncertainty, and the controller is also able to reduce the effect of torque saturation on the robot system.

Garden is an important support for regional economic development, but also an important support for regional ecological environmental protection, the rational allocation of water resources in the garden is one of the effective ways to solve the problem of water shortage. This paper takes the Internet of things, digital twin as the technical basis, uses the multi-objective optimisation algorithm to construct the water resource management model of the garden area, and uses the artificial fish swarm algorithm to solve the model. By constructing a digital twin irrigation district water resources scheduling management platform, the water resources elements of the garden area are comprehensively monitored and sensed, and the intelligent simulation of the water resources allocation management process and decision-making scheme evaluation and optimisation are achieved, so as to enhance the intelligent and refined management level of water resources scheduling of the garden area, and comprehensively realise the saving and intensive use of water resources. Taking X garden area as a research case, the water resources management model finally derives the optimal water resources allocation scheme under 50%, 75% and 90% in each planning year, which provides support for the efficient use of water resources in X garden area.

This paper evaluates the quality of university English teaching based on the hierarchical analysis algorithm (AHP) and fuzzy comprehensive evaluation algorithm (FCEA) in order to grasp the teaching situation more objectively. Based on the principle of evaluation index system construction, the evaluation indexes of university English teaching quality are determined. Using hierarchical analysis algorithm to calculate the weights of its indicators, and constructing a fuzzy comprehensive evaluation matrix based on expert ratings to finalize the assessment of university English teaching quality. Taking a university as the research subject, the English teaching quality assessment result of the university is 3.7351, and its corresponding fuzzy comprehensive evaluation A=(0.2893,0.3981,0.1359,0.1120,0.0648), which summarizes the teaching quality of university English as good according to the principle of maximum affiliation degree. In order to improve the teaching of college English in this university, corresponding teaching strategies of college English are proposed.

Deep learning, as a multilayer neural network structure for deep learning of data features, can describe the nonlinear mapping relationship for the assessment of college civic education. Aiming at the current education quality assessment model based on deep learning, this paper proposes an optimized convolutional neural network (HOA-CNN) based on Hummingbird Optimization Algorithm to assess the quality of Civic and Political Education in colleges and universities. According to the correlation coefficient between the objective assessment results and the subjective assessment results, the objective assessment results of the quality of Civic and Political Education in colleges and universities are obtained. The test results show that the linear correlation coefficient and the rank correlation coefficient between the assessment results of this method and the subjective assessment results are closer to 1. The goodness-of-fit of the assessment of the quality of college civic education under the model of this paper is significantly higher than that of the two control models. The simulation test results show that the assessment results of the university civic education quality assessment model constructed by the optimized convolutional neural network based on the hummingbird optimization algorithm are more accurate.

When a steam turbine blade has cracks, fractures, or other flaws, the steam turbine’s operating circumstances will change the vibration characteristics of the blades, complicating the problem identification process. The important defect features are difficult to automatically and effectively extract from the recorded vibration signals. In this study, the input signal characteristics for a particular operating situation are used as labels to reconstruct a trained autoencoder utilizing a reverse error. The supervised autoencoder receives the fault features for various speed circumstances, which it then protectively maps to a series of reference condition features. The goal is to eliminate the disruption brought on by variations in fault feature values brought on by alterations in operating circumstances. The experimental findings demonstrate that this approach can more effectively convert feature sequences under various working situations and address the issue of fault feature distortion brought on by changes in working conditions. In addition, comparison of clustering visualization and accuracy of classification methods on data before and after commutation demonstrates that the proposed supervised autoencoder model can extract accurate classifiable features for fault classification.

The research combines PBL teaching method, CDIO theory and school-enterprise collaborative education mechanism to construct a school-enterprise collaborative teaching model based on PBL-CDIO. And then, the empirical research of PBL-CDIO school-enterprise collaborative teaching mode is realized through the teaching experiment method. The independent sample t-test is used to test the changes in the professional knowledge level and basic working ability of the experimental group and the control group before and after the experiment, and to judge the teaching effect of the school-enterprise collaborative teaching mode based on PBL-CDIO in this paper. The pre-test sig values of professional knowledge and basic work ability of the experimental and control groups are greater than 0.05, and there is no significant difference between the two groups. The posttest sig values of the dimensions of professional knowledge in the experimental group increased by 10.20, 10.46, 10.49 and 9.47 respectively, and the sig values of the dimensions of basic work competence increased by 9.89, 9.72, 8.66 and 10.10 respectively. The overall change in the level of professional knowledge and basic work competence in the control group was less than 1 point. The posttest expertise and basic work ability sig of both groups were less than 0.05. After the experiment, the expertise and basic work ability of the experimental group were much better than that of the control group. The school-enterprise cooperative teaching mode based on PBL-CDIO proposed in this paper has good teaching effect.

This paper constructs a two-party evolutionary game model based on the perspectives of sharing platforms and consumers, exploring the dynamics of platforms’ decisions to actively operate with blockchain technology and the evolution of consumer rights protection behaviors. It is discovered from analysis that certain variables exert considerable influence on the stability of the strategies of both parties. From the consumer perspective, the improvements in the performance of the blockchain technology significantly increase the consumers’ willingness to protect their rights: the consumers with initially high levels of rights protection activation intensified their actions when their rights were violated. Thus, with the effective reduction of the cost of safeguarding rights, this trend has been additionally strengthened. As for the platform side, the performance of the blockchain technology exerts positive incentives on the operation of the platforms, although the marginal impact gradually declines with the developing blockchain technology, which in return reveals that platforms need to pay attention to a range of aspects including technology maturity. Measures of dual constraints including heavy fines from government and negative impacts of passive operations help to rein in passive operation among the platforms. Significantly, higher values of fines or negative effects lead to higher tendencies of having proactive operation strategy among the platforms.

Objective, to investigate the correlation between abdominal aortic calcification and paravertebral muscle degeneration, and to explore possible common risk factors for both. Methods, all patients with lumbar spinal stenosis admitted to Hospital X for MC and CT examination from 2016 to 2024 were selected, and through screening and exclusion, a total of 352 patients with LSS were included in the study, which consisted of 202 males and 150 females aged 40-80 years, with a mean of 63.24 years. The degree of paraspinal muscle degeneration in lumbar MRI, the degree of abdominal aortic calcification in lumbar CT scanning, as well as the patient’s age, duration of LSS, glomerular filtration rate and other indicators were counted, and the distribution characteristics of abdominal aortic calcification and its correlation with paraspinal muscle degeneration were analyzed by the method of multiple regression. Results, of the 352 patients with LSS who were included to meet the criteria, the calcification group (151, 42.90%) and the non-calcification group (201, 57.10%). Mild, moderate and severe paravertebral muscle degeneration accounted for 56.53%, 28.69% and 14.77%, respectively. The AACS in patients with mild PD degeneration stage, moderate PD degeneration stage and severe PD degeneration, all showed a gradual increasing trend with age (P<0.001). Regression results showed that age, paravertebral muscle degeneration and eGFR were risk factors for AAC in patients with LSS. Conclusion, there was a significant correlation between abdominal aortic atherosclerotic calcification and paravertebral muscle degeneration (P<0.001), and the degree of PD degeneration can be used as an effective indicator for early warning of the occurrence of AAC in patients with LSS.

In today’s society, ancient cities, as important components of historical and cultural heritage and urban development, are receiving increasing attention for their protection, utilization, and management. This research mainly focuses on the construction of an evaluation system for the spatial historical evolution of ancient city streets and the corresponding management strategies. Through a comprehensive evaluation of the spatial issues and characteristics of the ancient city streets, a multi-dimensional evaluation system for the historical evolution of the ancient city space with a total of 13 indicator factors, including historicity, is constructed. Taking Suzhou Ancient City as an example for empirical analysis, five typical types of ancient city streets are identified. Finally, corresponding update strategies are proposed for different types, especially the utilization of biomaterials and the design of plant landscapes, providing more innovative and sustainable management suggestions for the revitalization planning of the ancient city.

In this paper, the structures of three phosphorus-containing organosilicon compounds, including N,N-di-methylenephosphoric acid n-propylamine (DPPA), N,N-di-methylenephosphoric acid aminopropyldimethylsilanol (DPDS), and N, N-di-methylenephosphoric acid aminopropyldimethylsilylene glycol (DPMS), have been designed by using a molecular dynamics simulation method. And the preparation of three phosphorus-containing organosilicon compounds was accomplished experimentally by using raw materials such as bisphenol A-type epoxy organosilicon, n-propylamine and phosphite. The structures of the above several substances were proved by means of characterization such as Fourier infrared spectroscopy, hydrogen NMR , and epoxy value. Molecular dynamics simulation analysis revealed that the bond lengths of N atoms to Si atoms, N atoms to O atoms, and N atoms to were 3.03 Å, 3.05 Å, and 2.85 Å, respectively. Si did not participate in the addition reaction, but the intermolecular interactions caused a change in the chemical environment of Si, which reduced intermolecular distances and made it easier for the phosphorus groups to aggregate. This study is very important for the development of new preparation strategies of phosphorus-containing organosilicon and the promotion of phosphorus-containing organosilicon industry.

Social network structural characteristics of top management (TMT) are important variables that affect the outcome of team functioning, and variability in network structural characteristics leads to variability in TMT performance. This paper analyzes TMT social network structure characteristics based on TMT’s social relationship network using machine learning techniques. The top management interlocking network and technological innovation (machine learning technology) are divided into dimensions respectively, and the machine learning technology is used as a mediating variable to establish a model of the mediating effect of machine learning technology between top management interlocking network and green innovation. Statistical analysis of sample data and structural characterization of TMT social relationship networks by machine learning technology are conducted, and regression equations are used to verify the research hypotheses. The test results of the mediating effect of utilized innovation and exploratory innovation covered by the machine learning technology show that the overall regression effect of the model is good ( =0.537, =0.579, F-statistical test is significant), i.e., the mediating variables, utilized innovation and exploratory innovation, positively affect the green innovation performance and are significant. Meanwhile, the heterogeneity and size of TMT’s social relationship network, as well as relationship strength and relationship quality all have a significant and positive effect on green innovation.

Industrial processes are constantly developing towards large-scale and automation, and the smooth, safe, high-quality, and efficient operation of industrial processes has become a hot spot of concern, and higher requirements have been put forward for the control of production processes. This study analyzes the high-dimensional data in the closed-loop system of industrial network based on the HOPLS-SVM algorithm with higher-order singular value decomposition method. A BP neural network model is constructed with the processed data as the input set to realize the real-time prediction of the main data in the project, and the error of the prediction model is corrected by using linear regression method, and then the project prediction control system is constructed by piggybacking on the model. The results show that the prediction performance of the model in this paper is better than that of the comparison model, and the average absolute error is only 0.0347. At the same time, it is found that the control system in the decomposition project of CHP is able to regulate and optimize the temperature and flow rate of the crude product, which ensures the balance between the product temperature and yield, and the safety of the project operation. The engineering control method designed in this study has strong adaptability and effectiveness, and can provide solutions to engineering control problems in complex industrial processes.

This paper designs a military intelligent wearable device, aiming at realizing human-computer interaction and monitoring military status signs and data characteristics through this device. First of all, the overall system of the product contains temperature and humidity module, blood pressure detection module, heart rate measurement module and display module, and the extracted feature data are subjected to data intelligence preprocessing. Then the pre-processed feature data is functionally compressed and an artificial intelligence feature classification model is constructed, through which the compressed feature data is analyzed and displayed. Finally, the interactive performance of the wearable device is completed through data intelligent processing and device relevance calculation. After application analysis, it is found that the actual monitoring error is below 0.1 under different fatigue levels, and the specificity and positive prediction value of the wearable system can reach up to 100%. The highest accuracy of monitoring the physical state of military personnel is 99.31%, in addition to monitoring the heart rate in sedentary state and exercise state, with an average error value of 1.24 and 1.29. Therefore, the smart wearable device designed in this paper can well realize human-computer interaction, and the performance of product design is superior.

This study focuses on the Dingjiafen slope in Chuxiong City, China, with the aim of improving the accuracy of slope landslide risk prediction. Formulas for calculating the critical soil layer thickness at the onset of slope instability are derived based on the physical model of the slope. Using the Digital Elevation Model (DEM) and ArcGIS, the critical and maximum soil layer thickness of each slope unit are calculated to predict potential landslide areas. FLAC-3D is employed to simulate and analyze the slope’s stability under natural conditions, and the numerical simulation results are compared with the predictions in ArcGIS. The findings reveal variations in the critical and maximum soil layer thickness among different slope units due to diverse topography. The slope units on both sides of the Chumeng Highway slopes, with a critical soil layer thickness ( ) between 1 and 3 meters, are connected, aligning with the results of FLAC-3D three-dimensional numerical simulation and the actual sliding positions on-site. Applying this method to simulate the soil layer thickness at the critical state for each slope unit enables slope stability prediction, offering a new perspective for the analysis and prediction of slope stability.

Food security is an important foundation of national security, and the fundamental of guaranteeing national food security lies in arable land protection. In order to realize the protection of arable land in the context of ecological civilization, this paper designs a governance framework for arable land protection based on supply, empowerment, and control on the basis of the trinity of arable land protection policy of quantity, quality, and ecology, and constructs a multi-objective land use structure optimization model, and obtains a scenario prognosis for the optimal allocation of the land use structure by using a hybrid genetic algorithm. Taking County A as the specific research object, it can be seen by predicting the land use structure under the natural development scenario of County A that, relative to the status quo in 2023, the predicted share of arable land in 2050 has the largest decrease of 0.49%, and the shares of garden land, forest land, grassland and water area have all decreased, which is mainly converted into construction land (increased by 0.78%). From the Pareto frontier solution of land ecological benefit objective and economic benefit objective, three typical schemes of land use structure optimization were obtained, among which, the optimization scheme of balanced development of economy and ecology balanced economic and ecological development balanced economic development and ecological protection, and was selected as the optimization scheme of this paper. The increase of arable land area in this scheme is 0.38%, much higher than the -2.46% in the unoptimized case, which is in line with the requirement of arable land retention and can be used as a reference for further optimization of arable land protection framework.

The popularity of network video service, which leads to the specification of the network video service quality is becoming more and more urgent, and human is the ultimate watch users of network video, Evaluation of human observers on the video’s perception of the situation is becoming more important, depending on the source video network video know nothing, you will need to refer to the participation of video quality evaluation algorithm. However, when the quality evaluation is done by human rating, it is time-consuming and laborious, so the computer is required to make an objective evaluation of the video. In the objective evaluation, the excellent performance of convolutional neural network based on deep learning in feature extraction contributes to the rapid development of the research field of video quality evaluation. However, the development of deep learning algorithms requires appropriate data sets for training and testing. The existing data sets are relatively small in scale and not comprehensive in terms of video content types and distortion types. Therefore, it is necessary to provide a new data set to evaluate the quality of video without reference, expand the scale of the data set, expand the content and distortion type of the video. At the same time, considering the new development of network video services, the video resolution is positioned as high definition, and the original video sampling ratio is 4:2:2. The dataset is freely available to relevant researchers for scientific research.

Graph neural networks are an effective method for action recognition using human skeletal data, but previous recognition methods lack attention to spatial features. In order to improve this research deficiency, this paper conducts action recognition research based on ST-GCN. An action recognition network based on two-way skeletal joint information is proposed, where the human body is divided into various parts to calculate the representation vectors, and a graph convolutional neural network is trained to obtain the classification results. Attention mechanism is designed to minimize the effect of background noise, and data enhancement by means of flipping and shifting is performed to improve the model performance. Ablation experiments verify high accuracy when using both the attention mask matrix and the global self-attention mechanism, as well as when using both the joints network branching and the parts network branching. The model in this paper recognizes all 12 actions of the NW-UCLA dataset with accuracies higher than 92%, and the data enhancement effect is also verified.

Based on the research of digital economy and digital transformation of manufacturing industry, the article constructs the evaluation index system of digital economy development level and digital transformation of manufacturing industry in Yangtze River Delta respectively. The entropy weight TOPSIS method is used to measure and analyze the level of digital economy development and the level of digital transformation of manufacturing industry in the Yangtze River Delta respectively. The coupling coordination degree of digital economy and manufacturing digital transformation in the Yangtze River Delta in general and in each province and city is calculated and analyzed. On the basis of the relevant conclusions, recommendations for the digital transformation of the manufacturing industry and the elimination of the “digital divide” in the Yangtze River Delta are proposed. The overall trend of digital economy in the Yangtze River Delta (YRD) is on the rise, but there is a significant “digital divide”. The increase in the level of digital economy development in the Yangtze River Delta over the past 10 years is 10.76%. The average value of digital economy development water in Shanghai, Jiangsu, Zhejiang and Anhui is 0.358, 0.549, 0.491, 0.185 respectively, and the development of digital economy in Anhui is insufficient. Shanghai’s manufacturing digitalization water average is 0.750, the highest level in the Yangtze River Delta. Zhejiang and Anhui are slightly behind in manufacturing digital transformation. The coupling coordination degree of digital economy and manufacturing digital transformation in the Yangtze River Delta grew from 0.592 to 0.879, and the type of coupling coordination development shifted from barely coordinated to well coordinated. Shanghai and Jiangsu have reached the good coordination level. Zhejiang is at the intermediate coordination level. And Anhui is at the barely coordinated stage, which is the lowest level in the Yangtze River Delta.

As a folk traditional handicraft with a long history in Guangxi, mango weaving craft is facing the dilemma of shrinkage and decline. Starting from the application of AI technology in the protection and innovation of mang weaving technology, the article analyzes the text of collected mang weaving product reviews with the help of the perceived value theory and LDA topic model, and mines the consumer preference of mang weaving in order to better improve the production and manufacturing of mang weaving. Meanwhile, a lightweight generative adversarial network based on non-local attention mechanism is proposed to realize the construction of text-to-multi-objective image generation model, which is used in the innovative design of mango knitting. Consumers are more satisfied with the overall experience of mango knitting, and positive emotions account for 82.6%. The review texts were categorized into five themes with probability values of 0.181 to 0.227, and improvements should be made to the mango knitting product in terms of emotion, quality and price. The text-generated image model is able to output the mango knitting design images well, and the average values of IS and FID are 21.85% and 16.46% better than the comparison model, and the quality of the output images is better than the other models in different test sets. With the help of AI technology to improve the process of mango weaving, to enhance the design creativity of product quality, and to broaden the channels for the inheritance and development of mango weaving skills.

Artificial Intelligence has been applied in many aspects of life, however, AI algorithms have been less used in the field of music. In this paper, a multi-track based pop music generation model MuseGAN is proposed, due to its poor contextualization and excessive tempo jumps in generating pop music samples. In this paper, a new multi-track pop music generation model-Recurrent Feature Generation Adversarial Network RFGAN is proposed. the model addresses the temporal relevance of the music structure and the repetitive nature of the musical section, and proposes a temporal model that enhances the contextual relevance of the music samples in terms of the time series, and improves the generative model according to this temporal model by converting the unidirectional structure in the original model to a recurrent structure, adding the feature extractor to the previous level of training information, which is combined with arbitrary noise and passed to the next training. An average pooling layer is added at the end of the generative model as a solution to the situation where the model generates too much noise for pop music samples. The improved model is superior to the pre-improvement model in terms of stability, convergence speed, and overfitting in pop music generation. In the audience scoring experiment, 60% of the top 5 pop music scores were generated using the RFGAN model proposed in this paper, indicating that the pop music generated using the RFGAN model has reached a high level comparable to the level of artificial pop music composition.

Groundwater seepage has a greater impact on the stability of foundation engineering, and it is also an important factor that restricts the development of geotechnical engineering projects and the quality of engineering surveys. In this paper, tunnel engineering is selected as the foundation engineering project under study to investigate the specific influence of groundwater seepage in the process of tunnel excavation. The flow-solid coupling model is constructed, and the safety coefficients of the tunnel project in different situations are calculated based on the strength discount method and the ultimate strain method. Numerical analysis software is used to establish the calculation model of the influence of groundwater seepage on the stability of tunnel excavation. The displacement of surrounding rock around the hole is selected as the evaluation index of tunnel stability, and the effect of groundwater seepage on each index is calculated by the analysis software. The study shows that groundwater seepage will make the rock body around the palm face after tunnel excavation change significantly from the pre-excavation bending. The seepage increases the displacement of the surrounding rock, and the coefficient of increase of vertical displacement is larger than the coefficient of increase of horizontal displacement. At the same time, the flow-solid coupling effect of groundwater seepage increases the surrounding rock stress, and the increase coefficients of each key point of the tunnel excavation are between 1.11-1.50, resulting in significant deformation of the bottom of the arch, the top of the arch, and the arch girdle. In addition, the groundwater seepage makes the tunnel safety coefficient decrease from 9.03 to 5.18, which significantly causes the decrease of tunnel stability.

In the current business environment, artificial intelligence is becoming a key force driving performance management and organizational change. In this paper, finance, customer, internal process, learning and growth are selected as the indicators of performance evaluation of Enterprise A through the balanced scorecard model, and the fuzzy algorithm is used to provide comprehensive scores and grades for the above indicators. In addition, this paper sets up an organizational structure change evaluation model and analyzes the effect of the system on the organizational change of Enterprise A through the measurement of key indicators. The recognition rating of the questionnaire set up in this paper by the employees of Enterprise A is 4.15, and the recognition degree of the Intelligent Performance Management System is “basically recognized”. The intelligent performance management system improves the design and execution of internal processes in Enterprise A, and promotes the organizational change of Enterprise A in terms of total resource utilization. In conclusion, this study provides reliable technical support for enterprise performance management and organizational change.

Cultural heritage is an important symbol of the historical and cultural achievements of a country and a nation, and it is of great significance for the study of the evolution of human civilization, and the protection of national languages and scripts has also become the primary task of national work. The study is based on virtual simulation technology to design a virtual pavilion of Chinese language and writing, using image and text feature extraction algorithms and related technologies for image feature fusion and three-dimensional modeling of Chinese language and writing. The extraction effect of Chinese language and characters is verified by the matching of feature points, and the protection and inheritance effect of the virtual exhibition hall is reflected by the user experience score. The results show that the image and text feature extraction algorithm proposed in this paper has a good extraction effect, and there is no misrecognition. The order of users’ interest in each influential factor of the virtual pavilion of Chinese language and writing is text image>visual image>pavilion experience>scene art>language culture>image color>font charm>cultural art. Through the analysis of the feedback data of the eight subjects’ user experience, it can be seen that the average value of the total score of the user experience is more than 60 points, and the experience effect is good, which achieves the role of the inheritance and protection of Chinese language and writing culture.

In recent years, due to the adjustment of economic structure, the people’s living standard and the increase of leisure time, the sports industry has become a new economic growth point. This paper studies and analyzes the characteristics of the industry background and business background of the sports industry, explores the factors and internal driving force affecting the design of its business model, and fully analyzes the mechanism, functional role, and logical relationship of the elements for constructing the business model of the sports industry, and then explores the characteristics of the business style of the sports industry. From the perspective of knowledge state, using the reinforcement learning mechanism, the evolution process of the sports industry business model from the first stage to the fourth stage is described. Taking Company H as a research case, the process and economic effect of the transformation and upgrading of its business model through the reinforcement learning mechanism is analyzed and it is found that as of 2023 the company’s operating income has increased by 2.4 times through transformation and upgrading, and its net profit has increased by 125.57 percentage points compared to 2016. It further understands the role that the enhanced learning mechanism brings to the development of the sports industry, and expects to be able to provide a reference for the sports industry to carry out business model transformation in the future.

Blockchain technology has the characteristics of data anti-tampering and anti-forgery, which can provide solution ideas for the secure storage and transmission of data in distributed networks. The study applies blockchain technology to data auditing, constructs an aggregated signature based on conditional identity anonymization to protect user privacy, simplifies the auditing computation by using homomorphic hash function, and deploys three kinds of smart contracts on the blockchain to design a blockchain-based data integrity auditing scheme. For the privacy protection problem, a blockchain privacy protection model based on differential privacy is constructed by integrating the differential privacy policy into the blockchain smart contract layer. The experimental results show that the data integrity auditing scheme has superior blockchain storage cost and time overhead, and the average time overhead under different dynamic operations is below 30ms. The privacy protection model also exhibits high efficiency, with encryption and decryption times of 0.075s and 0.063s, respectively, under the largest data file, and a significant speed advantage in all phases of operation. The proposed scheme in this paper meets the needs of data integrity and privacy protection, and can provide efficient services for users.

Colleges and universities are an important part of higher education, providing a large number of talents for social development. The study optimizes the way of student management in colleges and universities based on artificial intelligence technology. Firstly, the K-means algorithm in cluster analysis is used to classify students’ campus behavioral characteristics. Then use Apriori algorithm to correlate students’ behavioral characteristics with academic performance. Finally, colleges and universities can take differentiated management measures for different categories of students. The clustering analysis of 12,885 students’ consumption behavior, work and rest behavior, and study behavior in college Z, followed by the correlation analysis between the clustering results and academic performance, and a total of 10 correlation rules were found. Colleges and universities can formulate management rules based on the analysis results to improve management efficiency. In addition, the student management work of colleges and universities can be optimized and upgraded in several directions, including the awareness of student management work in colleges and universities, the information platform, the archive management work, the student management team, and the information security work.

Under the background of the current information age, the electronic and intelligent transformation of the bidding industry has become an inevitable trend, and the e-bidding model stands out and greatly improves people’s understanding of bidding. Aiming at the traditional e-bidding system, in order to solve the problem of the lack of the traditional e-bidding system that provides the bidding body with referable opinions, this study firstly constructs the e-bidding risk assessment indexes and realizes the optimization of the evaluation module of the system. Then the recommendation algorithm based on deep learning implements the optimization design of the e-header bidding system. This study constructs an optimized recommendation model by fusing knowledge graphs on the basis of deep learning. Then the e-tendering optimization system is designed according to the actual needs of e-tendering, combined with the recommendation model of this paper. The accuracy index ACC of this paper’s recommendation model is improved by about 3% on average compared with other best-performing recommendation models on each dataset, which verifies the excellent performance of this paper’s recommendation algorithm. This study constructs an optimized e-tendering system and proposes suggestions for the development and operation strategy of corporate e-tendering, contributing to the development of e-tendering transactions and the participation of social capital.

Green building is becoming the mainstream mode of transformation and upgrading of the construction industry, with the advantages of energy saving, environmental protection and ecology, which can effectively alleviate the energy scarcity and improve the quality of the environment, and is needed to realize high-quality sustainable development. This study proposes a green building design implementation program based on BIM software and intelligent construction technology. The building energy efficiency assessment system is constructed, and the fuzzy Borda method and CRITIC method are used to calculate and correct the weights of indicators, and the energy efficiency assessment method is proposed by using the material element topable model. The assessment scores of all indicators of energy efficiency after green energy-saving retrofit of a district building are between 90.11 and 99.28, and the building achieves excellent performance in heating and cooling with lower primary energy demand during operation and use. It indicates that the objectives of this green retrofit project were basically realized, effective and produced energy-saving benefits. This study can provide guidance for subsequent green building energy efficiency retrofit work and further promote the energy efficiency retrofit of existing buildings in China.

The application of virtual reality technology in the field of teaching is becoming more and more widespread, and the study utilizes virtual reality technology to create contexts, create cross-cultural teaching contexts, and construct speech recognition models. In addition, the ecological model of language learning based on virtual reality is constructed, and the cross-cultural context teaching/learning VR system is developed based on it and introduced into language learning. After testing the speech recognition performance of the cross-cultural context teaching/learning VR system, the students’ learning interactions in the cross-cultural communication context in the language learning system of this paper are studied in depth. By comparing the pre- and post-test experimental data of the experimental group and the control group, the effectiveness of the cross-cultural contextual teaching/learning VR system in language learning is examined. The speech recognition efficiency and correctness rate of the cross-cultural contextual teaching/learning VR system are 99.7% and 99.5%, respectively, which are excellent. In the cross-cultural communication classroom situation, the teacher-student language ratio is comparable, and the teacher’s indirect influence is increasing and the direct influence is gradually decreasing. The pre-test English proficiency of the experimental and control groups was similar. After the experiment, the mean values of all dimensions and total scores of English proficiency of the experimental group were higher than those of the control group, and the p-value was less than 0.05, and the difference of post-test English proficiency between the two groups was significant. The cross-cultural contextual teaching/learning VR system has a significant positive effect on the improvement of users’ language learning effect.

The flipped classroom relies on a smart platform to assist the implementation of English translation teaching, combining the smart platform with the students as the core to realize the efficient interaction of English translation teaching and enhance the students’ interest in English translation learning. This paper develops an easy-to-use interactive system for English translation teaching in flipped classroom based on Fine Report, and utilizes MySQL database to store the relevant data generated in the process of use. In this system, the BERT model trained by matrix masking strategy is used as the basis, and the neural machine translation model that assists teachers in English translation homework correction is established by combining the NMT model. Then the K-Means clustering algorithm is optimized by the adaptive K-value selection method, and the students’ learning data on the system is clustered by using the improved K-Means, and the student performance evaluation model is established by combining the CART decision tree. A pedagogical comparison experiment was carried out for the feasibility of the interactive system for teaching English translation in the flipped classroom. The BLUE value of machine translation using the BERT-NMT model was always above 30, and the average accuracy of student performance prediction of the K-Means-CART model could reach 84.85%. The English translation performance of the students in the experimental class was significantly improved after the teaching experiment, and the overall satisfaction of the students with the interactive system for teaching English translation was 4.038 points, which was between the satisfied~very satisfied level. Fully combining intelligent technology to assist teachers in teaching English translation under the flipped classroom can help to enhance the quality of cultivating English translation talents in colleges and universities.

When a laser beam passes through a solid physical material with a nonlinear refractive index, it can produce an optical nonlinear effect, which depends on the refractive index that changes with the light intensity. Based on an analysis of the linear principle of nonlinear optics, the article describes the coupled wave equations under the nonlinear optical phenomenon. It introduces the phase-matching method of frequency conversion and the theoretical basis of optical waveguide. Starting from the classical Maxwell’s equations, the nonlinear optical transmission equations and the optical effect model are established, and then the finite element method (FEM) simulation model is constructed based on the FEM model to analyze the nonlinear optical phenomena of solid-state physical silicon materials. To verify the validity of the FEM model, the optical bistability effect and four-wave mixing spectrum of the nonlinear optical phenomena are simulated and analyzed, and the homochiral spinning effect and transmission spectrum are investigated. When the solid-state physical silicon material is rotating, the laser power required to observe the optical bistability is up to 9.51 W when the rotation rate is increased from 12 kHz to 24 kHz, and the four-wave mixing intensity decreases from 0.115 to about 0.028 when the oscillator frequency of the solid-state physical silicon material is increased from 15 MHz to 30 MHz. The plasma resonance absorption wavelength of the solid physical silicon material is at 791 nm, and the effective refractive index obtained from the simulation is 0.61 in the real part, which is only 1.64% lower than the actual refractive index. The trend of nonlinear optical phenomena in solid-state physics can be effectively obtained by using the FEM model, which provides a new idea for the application expansion of the optical force system.

With the development of the informationization era, it has become the norm for teachers of Civics and Political Science courses in colleges and universities to assist classroom teaching through network resources. In order to further utilize network resources to make them better serve the classroom teaching of Civics and Politics courses in colleges and universities, this paper optimizes the teaching resources recommendation technology based on deep neural network. Defining the network teaching resources data as a ternary group , we put forward the research hypothesis and LSTM model, and establish the G-LSTM recommendation model for recommending the teaching resources of ideological network. The overall framework of G-LSTM model is described, and the recommendation based on G-LSTM is applied to the ideological network teaching resources recommendation. Adopt AUC, MRR and NDCG as evaluation indexes to check the performance indexes of G-LSTM model. Combined with the actual teaching of ideologic theory class, the practical effect of G-LSTM recommendation model is analyzed. 67.81% of students and 39.71% of teachers recognize each recommended online teaching resources. It shows that the improved LSTM model in this paper can further screen the ideological and political network teaching resources, and the teaching resources recommended by the model are more suitable for the teaching of ideological and political theory.

Machine learning-based learning analytics can fully use the learner learning behavior interaction data recorded by online English teaching systems, providing support for observing students’ learning process from the perspective of learning behavior. In this paper, we construct a framework for recognizing college students’ English learning behavior patterns, propose an SGT-based feature extraction algorithm for learning sequences, and use Gaussian mixture models to identify the extracted learning characteristic sequences. Subsequently, a K-means clustering algorithm is used for sequence clustering and lag sequence analysis. At the same time, the English personalized teaching method is designed by combining the proposed personalized knowledge point recommendation method of multi-knowledge fusion in-depth knowledge tracking and group feature collaborative filtering. The results show that college students’ English learning behaviors are classified as active, passive, and passive, and the behavioral sequences of students in different modes are differentiated, in which the sequence residual value of active learners is greater than 1.96. There is a significant difference between the personalized teaching mode and the ordinary teaching mode in terms of the learning mode and the learning effect (P<0.05), and it can achieve a better English teaching effect.

The development of media technology profoundly affects the presentation mode, dissemination rate and scale of news information, which in turn reshapes the business chain and business landscape of the entire news media industry. Based on the analysis of the shortcomings of the LDA model, this paper proposes an improved LDA model with binomial distribution, and applies it to the analysis of the evolution of news topics. The model introduces binomial distribution to enhance the discriminative ability of lexical items, and parallelises it to improve the classification effect of news topics. In order to effectively obtain the relevant features of cultural communication in news documents, this paper introduces BERT to obtain word embedding and word vector matrix, and then realises the generation of theme word structure and theme words. The performance of the improved LDA model is verified through the THUCNews dataset, and the news topic morphology is visualised and analysed with the example data, and its morphological evolution, as well as the degree of contribution to cultural communication, is studied. The theme consistency score of the improved LDA model is -13.39 when the word generation probability is 1, which is 19.14% higher than that of the traditional LDA model. The intensity of the ‘cultural policy’ news format theme increases 14.44 times from 2010 to 2023, and the mean value of the ‘cultural governance’ news format theme’s contribution to cultural dissemination reaches 0.091. Based on the innovation and evolution of news forms, we can empower more communication channels for culture and spirit, so as to enhance people’s cultural self-confidence and national cultural soft power.

Dance drama is a comprehensive art with dramatic conflicts and plots based on the use of dance’s own language system, which plays an important role in cultural dissemination and aesthetic experience. The article designs a resource library of classic dance drama works in the way of WEB site, establishes a data dynamic distribution strategy to deal with structured data, and combines the consistent hash algorithm to optimize the load balancing of structured data in the resource library. Then, a graph convolutional neural network model and a sample-weighted aesthetic classification model are combined to establish an aesthetic assessment model for images of classical dance drama works, and a regularized matching module is designed. For the application effectiveness of the structured data processing strategy, the structured data processing of the classic dance and drama works resource library is verified, and the hyperparameters of the model, evaluation results and ablation experiments are also analyzed. Combined with the data in the resource library of classic dance drama works, the aesthetic experience of the audience was analyzed using a questionnaire. After using the dynamic distribution strategy to process the structured data, its write and query times were shortened by 40.05% and 17.89% compared to before use, and the response time under different index query load balance degrees did not exceed 55ms.The accuracy of the aesthetic assessment model for classical dance and drama works was 48.85%, and the accuracy improvement of the G-AANet model compared to BoTNet ranged from 0.93% ~ between 6.12%. The resource base of classical dance drama works established through structured data processing helps to enhance the audience’s aesthetic experience of dance drama works and helps them to appreciate the spiritual connotation of dance drama works.