In the context of continuous innovation in science and technology, consumer demand is becoming increasingly diversified, especially in product packaging design, personalization and uniqueness have become a new pursuit. The article proposes a computer image fusion DPformer-GAN model based on Transformer model and GAN, which is used to realize personalized packaging image fusion and generation. The digital image is then converted into a personalized packaging object through digital printing technology, which then realizes the innovative practice of personalized packaging.The DPformer-GAN model reduces the overlap and occlusion by 12.81% and 2.98%, respectively, compared with the better-performing CGL-GAN model when fusing and generating personalized packaging images. When personalized packaging images fused with computer images are used for digital printing proofing, keeping the percentage of dots lower than 50% can achieve the maximum degree of color reproduction and better retain the visual effect of digital images. Consumers are more favorable to the aesthetics and user experience of personalized packaging, with a favorability rating of 9.16 points and 9.29 points, respectively. It is feasible to use digital printing technology to print the packaging images generated by computer image fusion into personalized packaging, which can also further enrich the image practice options of personalized packaging.

The current gemstone jewelry design is not specialized and systematic enough, and most of the gemstone jewelry styles are common and single, which makes the value of gemstone not reasonably reflected. Starting from the evolution of gemstone facets, facet texture and cut classification, the article takes the three-dimensional features of gemstone facets as the basis and optimizes the cut parameters of gemstone facets by combining with geometric transformation theory. The optimized cutting parameters were used as the basis for 3D modeling, and the 3D model of the round faceted gemstone facets was established with the simulation software, and the quantitative analysis of the data was carried out through the brightness, uniformity, and scintillation values. When the table width ratio is 50-60%, the difference between the crown angle and the inclination angle of the star facet corresponding to the circular faceted gemstone facets varies from 9.172° to 20.673°. When the length ratio of the lower girdle facets is 65% to 95%, respectively, the range of the difference between the lower girdle facet inclination and the pavilion angle is between 0.781° and 1.967°. The scintillation value obtained after designing the gem facets using the method of this paper is 4.67 times higher than that of the traditional method. The optimized design model of round faceted faceted gemstones constructed on the basis of geometric transformation theory can provide new ideas for the jewelry design of round faceted faceted gemstones.

Local colleges and universities are an important part of China’s higher education reform and development, and the quality of cultivation of top-notch innovative talents has a direct impact on the development speed and level of local economy. In this study, the decision tree algorithm is used to establish a prediction and early warning model for students’ performance in the process of cultivating new engineering top-notch innovative talents in colleges and universities, and the K cross-validation method is used to optimize the model parameters and improve the prediction accuracy. Then, based on the intelligent prediction model and the cyclic structure intervention theory, we constructed a dynamic adjustment model for the cultivation system of new engineering top-notch innovative talents. The results of the empirical application of the model show that the hardware and facility conditions of talent cultivation in college D have significant improvement under the application of the dynamic adjustment model. In addition, both graduates (>4.00 points) and employers (>3.67 points) gave a high degree of achievement to the training quality of the university’s top innovative talents in new engineering disciplines. This study helps to meet the demand for high-quality engineering talents for regional economic and social development, enhance the adaptability of higher education and improve the quality of talent cultivation.

The nation-state is regarded as the basic form of the modern state, but whether the modern state is really a “one nation, one country” type of political community as depicted by the nation-state narrative. This paper explores the influence of national narratives on national identity by constructing an evaluation index system, using a questionnaire survey method, and taking adolescents as the research object. The independent variables of this study are national narrative, including national language, national spirit and national memory, and the dependent variable is national identity, including cognitive tendency, emotional tendency and behavioral tendency. The weights of the indicators and regression results were calculated by AHP-entropy weighting method. The analysis results show that national vocabulary has a great influence on national language, while sense of belonging is the biggest factor affecting emotional tendency, and most of the dimensions of national narrative are positively correlated to national identity with a significant effect. The correlation coefficient between national etiquette and national identity is 0.203, and the correlation coefficient between national history and national identity is 0.254. National history and national etiquette have a significant effect on national identity.

The countries in East Asia are neighbors in one country, and their cultures are cross-fertilized with each other, so it is of practical significance to enhance the sense of regional community on this basis. In order to explore the effect of cultural exchange and cooperation on the enhancement of regional community consciousness, this paper constructs a semantic graph for the relevant comments on social platforms, combines GNN and LSTM, and constructs a GNN-LSTM sentiment recognition model to identify and quantitatively represent regional community consciousness. Regression analysis is used to test the enhancement effect of cultural exchange and cooperation on regional community consciousness. The experimental results show that the GNN-LSTM model has a better emotion recognition effect and can provide help for the extraction and quantitative representation of regional community consciousness. The regression coefficients of cultural exchange status on the two models are 0.423 and 0.439 (p<0.01), indicating that cultural exchange has an enhancing effect on regional community consciousness. Cultural distance acts as a mediating variable, the more frequent the cultural exchange and cooperation, the smaller the cultural distance, the more the regional community consciousness can be enhanced.

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).

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.