Search

In modern society, innovation and entrepreneurship education have gradually transcended the traditional paradigm, intertwined with the concept of commonwealth, and constructed a new picture of vitality and social sentiment. In terms of research ideas, this paper extracts value-shaping elements, service learning elements, social creation faculty elements, social creation curriculum elements, organizational leadership elements, interest group elements, and social creation practical elements as the elements of entrepreneurial competence cultivation of college students according to their growth pattern, the entrepreneurial environment they have, and entrepreneurial resources they possess. We obtained the four crucial factors for individual, group, school, and social levels through micro-level analysis. We constructed the model for cultivating entrepreneurial competence in college students with the support of seven elements and four hierarchical factors. In the end, the cultivation model was analyzed using the PLS-SEM model. It has been verified that 11 out of the 13 hypotheses proposed in this paper were supported through testing. 11 cultivation paths that passed the significance test were found after further analysis. The most significant path is the SF->IE->PO path under the policy anchoring force, with effect sizes and t-statistics of 0.325 and 7.494, respectively. In this way, we have refined the methodology of cultivating co-enrichment and entrepreneurship skills among university students.

As a classic representative of traditional culture, Chinese calligraphy art has more and more obvious advantages in today’s digital media art creation. In this paper, the calligraphic text image is binarized by the OTSU method, the image enhancement is realized by linear gray value stretching, and the optimal tilt correction method is used to preprocess the traditional calligraphic text image and make a font library. Based on the data from the calligraphy font library, an immersive digital interactive context of traditional calligraphy is designed using digital media art. Pix2Pix network is introduced to combine with the PatchGAN network to establish a style migration network for traditional calligraphy text images, and three different types of loss functions are designed to ensure the accurate generation of traditional calligraphy text. The L1 loss of this paper’s model in generating traditional calligraphy characters is only 0.0359 at the lowest, the similarity values of the generated samples of calligraphy characters are mainly between 90% and 96%, and the maximum error of the relative position and relative size of the radicals is only 1.18%. The average value of the G2R indicator for the users’ images of calligraphic characters was 75.23%, and 89.86% of the users indicated that they were basically satisfied with the immersive interactive context of traditional calligraphy. Traditional calligraphy can achieve digital transformation and provide audiences with more diverse cultural experiences by relying on digital media art.

The guerrilla warfare behind enemy lines of the national government is still a weak link in the study of the history of the war of resistance, and the naval guerrilla warfare on the Yangtze River is even less specifically discussed. This paper first analyzes the change in the national government’s naval operational thinking after the July 7 Incident and up to the Battle of Wuhan and divides the naval operations in the Yangtze River Basin during the period of total war of resistance into four stages. Then, combined with the ontology theory and taking various archives, museums, libraries, and memorial halls as sources, after fusing heterogeneous data, it adopts the relevant writings, notes, diaries, speeches, photographs, objects of the Navy’s Yangtze River Resistance as well as the results of the archive compilation formed later to construct the Navy’s Yangtze River Resistance Archives Knowledge Graph Model. After the reasoning and searching of the knowledge map, it is concluded that in 1938 and 1940, the Yangtze River Bray Guerrilla Group killed 950 and 3020 enemies, respectively, destroyed 20,400 tons and 118,400 tons of warships, strongly supported the Battle of Wuhan and two Battles of Xiangbei, and prevented the Japanese army from invading to the west along the river, and in 1940, it destroyed the Japanese large-scale transports and merchant ships of a total of 58,700 tons, which dealt a heavy blow to the Japanese army on the Yangtze River and the Yangtze River. Heavy blows to the Japanese water transport capacity of the Yangtze River delayed its front and rear troops, weapons, supplies, and transportation plans so that its ability to expand received a major limitation, unable to continue the attack on the Yangtze River west of Wuhan, to defend the safety of Chongqing and Sichuan. This paper makes up for the research gaps in the history of the National Government’s naval resistance and the history of guerrilla battles in the Bray of the Yangtze River Basin and provides a useful exploration of the combination of resistance history research and information technology.

In the long historical evolution of humanity, religion has always demonstrated social, and cultural patterns and historical forms and has silently influenced some people’s ideological concepts and moral behaviors at all stages of development. This paper uses deep learning to investigate how the popularization of religious culture affects the dissemination of the concept of racial justice. The LBP-ORB algorithm model is constructed for the popularization method of religious culture, which is based on the improvement of the ORB algorithm, and the cognitive degree of different religious cultures can be improved by feature extraction through the LBP-ORB algorithm model. The model of this paper will be compared experimentally and then through fieldwork. The LBP-ORB algorithm model will be used to extract the features of local religious culture and popularize the local youths. Based on the analysis results, we explore the effect of the popularization of the cognition of religious culture on the spread of the concept of racial justice. After the popularization of religious culture, the college student group and middle school student group’s knowledge of the concept of racial justice increased substantially, with the number of people familiar with the college student group increasing by 88 and the number of people with general knowledge increasing by 122. The number of people in the middle school student population who were familiar with it reached 112, and the number of people with a general understanding reached 92. This paper’s LBPORB algorithm model has significantly increased the dissemination of the concept of racial justice after popularizing religious culture.

The ADDIE model is highly compatible with teaching in terms of educational purposes, concepts, and processes and has a positive contribution to teaching. In this study, the ADDIE model is used to teach a comprehensive practice course for automobile majors in order to promote the systematic design and implementation of teaching. In this paper, the main problems to be solved are firstly extracted through the elemental analysis of the comprehensive practice course system of automobile majors, and the expected level of learning objectives to be achieved is pre-set. Then, a complete integration of educational media resources is carried out to test the effectiveness of the developed course instructional design. The fuzzy evaluation model is utilized to assess the quality of the course constructed by the ADDIE model. Specifically, the hierarchical analysis method is applied to calculate the index weights, and then the entropy weight method is used to correct the obtained index weights to obtain the final weights, determine the fuzzy operator, and make a comprehensive assessment of the teaching quality. It can be seen through the analysis that the method proposed in this paper makes the average final grade of the experimental class higher than that of the control class by 3.4524 points, and the final rating of teaching quality obtained by the method of this paper using the fuzzy comprehensive evaluation model is 3.7968 points, which is a good level. This indicates that the upgraded method of teaching practical courses is more effective than the original method, enhances the overall performance of students, and fulfills the requirements for teaching practice in automotive specialties.

Under the era of intelligence and informational technology, society has set higher requirements for the cultivation of talents in colleges and universities. This paper builds up a school-enterprise cooperation training model on the cultivation demand of applied talents in finance and taxation, and the employment quality data after the application of the model is statistically analyzed with the data of H universities in Guangdong Province. At the same time, after constructing the evaluation index system of the quality of the training of applied talents in finance and taxation under the model of school-enterprise cooperation by using the hierarchical analysis method and assigning weights to it, the quality of the training of the talents is comprehensively evaluated by the fuzzy comprehensive evaluation method. It was found that the employment rate of H college increased from 74.17% to 97.59% in the past ten years, and the counterpart rate increased from 73.54% to 89.24% in 2014. The study shows that A10 Employer Enterprise Satisfaction, A2 Enterprise Cooperation Platform, and A6 Enterprise Mentor Guidance have the highest scores of 86.215, 84.296, and 84.137, respectively, indicating that enterprises play an important and positive role. The A3 curriculum and A9 employment quality scores are below 80, which suggests that there are still problems to be resolved in both the course and employment quality. This paper provides useful exploration to address the problem of inadequate and misplaced school-enterprise integration and to ensure a comprehensive improvement in the quality of training talent in finance and taxation.

In order to promote the development of the Chinese gardening field, this paper proposes a data-driven, multi-sensory design for Chinese gardens. The multisensory design of Chinese gardens, which combines data-driven technology and VR technology, is explored from two perspectives: the visual and auditory senses. It is found that the design easily leads to the loss of the natural beauty of the garden. For this reason, the layout optimization model is constructed using the improved PSO algorithm, and the corresponding analysis method is applied to analyze the effect of the multi-sensory design of the garden. The results show that the model in this paper is better than the other two control models in terms of weighted mean (4.078) and convergence time (0–4 ms). It was also found that the basis for visitors to make experience visual satisfaction evaluations was basically whether the floral landscape was beautiful (39.18%) and whether the field of view was open (23.27%), and the auditory experience design evaluation scores were higher for acacia forests (5.436), red-leafed ridges (4.091), snapdragon forests (3.872), and metasequoia forests (3.657) in the gardens. The research in this paper reveals the focus of multi-sensory design in Chinese gardens, which can provide theoretical references for research in the field of Chinese garden design.

Education informatization is an important initiative for the country to realize education modernization, which is related to the development of China’s education. The use of a single evaluation of teaching effectiveness obviously cannot meet the assessment needs. Based on the premise of intelligent assistance through a hybrid brain-computer interface, this paper aims to study an evaluation method for teaching effectiveness using artificial intelligence. Firstly, EEG signals are collected through an EEG acquisition device, and then they are preprocessed. Second, the pre-processed signals are subjected to feature extraction, and then the features are classified using a specific pattern recognition method, and finally the classification results are used to assess the effectiveness of English teaching for college students. Based on the evaluation results, the learning system is optimized and improved. The signals collected by EEG devices carry a lot of noise, and in this paper, the processing of the original signals includes a smoothing filter, de-baseline filter, filter filter, and Kalman filter to achieve a higher signal-to-noise ratio. Multivariate evaluation results are provided by the evaluation system that is assisted by artificial intelligence. Compared with other evaluation methods to enrich the evaluation information, based on the above system effectiveness evaluation study, as far as the F1 value is concerned, this paper’s method is the highest, reaching 0.815, which is 0.048 higher than the highest F1 value of the traditional algorithm, and in the other two values, this paper’s method is also higher than other methods. This verifies the rationality and effectiveness of the teaching effectiveness evaluation system based on a hybrid brain-computer interface proposed in this paper.

Although AI technology has been widely utilized in many fields and has reaped good reviews. However, there is a vacancy in the education field for AI technology to achieve personalized recommendations for the English language. In this paper, based on the traditional cognitive diagnostic model, we propose optimizing two aspects, namely question type and mastery state. Combining the neighborhood recommendation algorithm, the English learning recommendation model is constructed using fuzzy cognitive diagnosis. Based on the theory of adaptive learning, we have designed a personalized bank of recommended English learning questions. The model is utilized in the real world of English learning, and a control experiment is designed to evaluate the student’s knowledge mastery and the impact of the model application. The experiment shows that student A has a better mastery of S1 and S3, with mastery levels of 0.856 and 0.815, respectively, but only 0.235 for S4, and needs to customize a more targeted personalized learning plan and strategy for S4-related content. The average scores of D1 and D2 before practice were 73.51 and 72.18, and after practicing through the personalized recommending English learning methods proposed in this paper, the English score of the D2 class was improved to 85.33, and the t-test result between the two groups was significant p-value of 0.002, which is less than 0.01, indicating that there is a significant difference between the two groups and that the model proposed in this paper has a significant enhancement on English learning.

Under the requirements of the educational background of the new era, establishing moral character has become the fundamental task of education, and at the same time, it also brings new challenges and opportunities for English education in higher vocational colleges and universities. Based on the core qualities of the curriculum Civics and Politics, we explore the point of fit between English education and it so as to deeply analyze the integration mechanism of the curriculum Civics and Politics in English education and complete the construction of the teaching model of the curriculum Civics and Politics in English education by combining with the big data technology. On this basis, taking S higher vocational colleges applying this model as an example, the expert scoring method is used to construct the teaching quality evaluation index system and assign weights, and the fuzzy comprehensive evaluation model is used to assess the quality of education. Core literacy and comprehensive ability have the highest weights of 0.2836 and 0.2866 respectively, respectively, which are key areas for cultivation. Finally, through the quality evaluation of the education model of this paper, it can be seen that the highest score of comprehensive ability is 90.21, which is at the excellent level, and the lowest score of values cultivation is 81.98. and the scores of each index are above 80. The average score of the education model of this paper is 85.13, which proves that the quality of teaching under the teaching model is good. It has an excellent performance in the cultivation of English talents. It is a good example of Big Data Technology, and the integration of the English education program Civics provides a feasibility with practical significance.

Under the advancement of reform and opening-up policy, the development direction of e-commerce enterprises has gradually shifted from the city to the rural areas with lower levels of economic development. This paper builds a rural e-commerce intelligent logistics system based on the Internet of Things (IoT) technology and proposes an improved ant colony algorithm to plan the optimal path of rural e-commerce logistics and distribution by mining the transfer probability of each distribution point in logistics and distribution as well as pheromone updating mechanism, so as to improve the logistics efficiency and customer satisfaction. Experiments show that the improved ACO algorithm in this paper performs significantly better than the genetic algorithm and particle swarm algorithm in logistics and distribution path planning and can control the transportation cost and penalty cost at a lower level. When considering the cargo loss of fresh products in logistics distribution, the satisfaction rate of traditional logistics distribution is only 65.2%, while the satisfaction rate of logistics distribution based on intelligent logistics technology is 87.9% on average. The distribution path planned by the ant colony algorithm has less mileage, lower cost, and higher logistics efficiency. This paper provides a feasible path for further improvement of rural e-commerce logistics efficiency, which can promote the development of the logistics industry in the direction of more intelligent, personalized, and green.

Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise management. The purpose of this paper is to apply agricultural mechanical engineering automation to wheat yield prediction, and a UAV multimodal data wheat yield prediction model is developed using the RMGF algorithm. Different data sources, such as vertical distribution of terrain and spatial variability, canopy height and wheat plant height, canopy temperature difference, vegetation spectral characteristics, and vegetation index, were extracted using an agricultural UAV. Then GF decomposition algorithm based on MSD decomposes the multimodal image into an approximate image and detail image, and after optimization of the fused weight map using RSA, the fused image is obtained by IMST according to the optimized weight map. The model was used to carry out regression analysis of yield prediction for three types of wheat, heat-tolerant, medium heat-tolerant, and high-temperature-sensitive, and finally predicted the wheat yield from 2015 to 2024 in a production area. It was found that the R² of the RMGF multimodal model in this paper predicted the three kinds of wheat yields as 0.7936, 0.8609, and 0.9262 with excellent accuracy results. The predicted yields were basically in line with the actual yields in the high-yield portion, with large prediction errors above 9000 kg/ha. The prediction error for wheat was within 0-2.26%, and the predicted yield in a main wheat production area was 7050 kg/ha in 2024. This study provides a feasible method for large-scale yield estimation in the main production area, which contributes to high-throughput plant phenotyping and agricultural precision reform.

Music education, as an important part of art education, can also take advantage of artificial intelligence technology to achieve more efficient personalized teaching. The direction of the application of artificial intelligence technology in music course learning is explored in this paper. Therefore, a music data technology interactive learning system is proposed. The music recognition module’s design utilizes a deep neural network model to model the complex problem of speech signal recognition. The encoder formula is obtained by representing the implicit layer feature vectors in the sample through a mathematical model. After encoding and decoding, as well as designing the activation function, the HMM algorithm is introduced to realize the application of DNN-HMM in acoustic modeling. Using a digital filter, the spectrum of the speech signal is smoothed, and the spectrogram is obtained by Fourier variation to visualize the representation of the speech frequency domain. The design of a music Internet teaching course is based on the method proposed in this paper. The melody recognition accuracy of the system is tested through simulation experiments, in which the distribution of auditory feature points of the piano ranges from 0.66 to 0.69. The distribution of rock music is above 0.7, and there is no overlap between the two audio datasets, which indicates that the system proposed in this paper has good recognition accuracy of audio features. Using the speech analysis module, the students’ music learning performance is analyzed. After the model designed in this paper to assist music learning, students’ music performance mean value is 4.397, and the control group’s performance is 3.565. The difference is 0.832. The system designed in this paper is more effective for music learning.

In the era of smart tourism, its emergence not only provides crucial technical support to meet the needs of tourists but also prompts the reform and improvement of the development mode of the tourism and culture industries. This study begins by examining the current state of smart tourism and the development of the tourism and culture industries. It then conducts a thorough analysis of the mechanisms driving these developments and establishes an industry analysis model based on the RMP theory. The study then employs fractional regression to identify the factors that influence the development of the smart tourism and culture industry. It then constructs a model for smart tourism and culture development, which includes government and industry support, economic and cultural support, digital information technology support, personnel support, talent cultivation, cultural participation, and social participation. Finally, it analyzes the impact of this model’s application using the RMP analysis model. This paper’s development model sees annual increases in tourism and culture industry indexes, rising from 105.85 to 145.79, with an average growth ratio of 17.35%. The overall satisfaction rating for the product experience stands at 4.152, suggesting that under the development mode of the smart tourism and culture industry in this paper, both the market economy and the product experience exhibit excellent phenotypes. This paper supports the construction of a smart tourism cultural industry development model using digital technology and provides references for the tourism cultural industry model.

In recent years, the accuracy and linguistic fluency of translation based on intelligent algorithms have been relatively close to that of human beings, and the application of intelligent algorithms has gradually become a research hotspot in the academic world. In this paper, it is found through relevant research that semantic retention, cultural appropriateness, linguistic fluency, content comprehensiveness and text readability are important factors in the application of intelligent algorithms for the translation of literary works for cross-cultural communication. To explore the degree of influence of these factors on the translation quality of literary works, this paper analyzes them using a multiple linear regression model. The first step in building the mathematical model for multiple linear regression is to construct it. Then, the formulas for calculating the goodness-of-fit and significance test of multiple linear regression equations are introduced. Finally, the regression model was tested using residual analysis and multicollinearity. The regression results show that the quality of literary translation = 0.165+0.124*Semantic retention + 0.356*Cultural appropriateness + 0.254*Linguistic fluency - 0.001*Content comprehensiveness + 0.256*Text accessibility. According to the results of the analysis, the impact of content comprehensiveness on the translation quality of literary works is not significant, and cultural appropriateness has the greatest impact on the translation quality of literary works.

In recent years, the way of air travel is gradually popularized, and the security check system in the airport is facing corresponding pressure. In order to guarantee the security problems in the aviation field, this study investigates the security check system in the civil aviation field. After investigating the security checking process in civil aviation, the Faster R-CNN has been improved based on both multilayer feature fusion and loss function to adapt to the target detection of millimeter wave images. Then, the detection and radiation characteristics of millimeter waves are introduced, and the target detection algorithm based on edge extraction is constructed. On this basis, artificial intelligence, big data, augmented reality glasses, and other technologies are incorporated to establish a security check system in civil aviation and analyze it experimentally. In terms of the overall recognition performance of mAP, this paper’s method improves by an average of 3.098-6.504% and 3.740-8.706%, respectively, with the highest FPS of 45 and 36, and its generalization ability is better compared to other methods. In addition, in the practice of contraband detection in unmixed and mixed backgrounds, the devices based on the security system of this paper have higher than 90% detection in all seven types of contraband, which is able to improve the accuracy of contraband detection, while still maintaining good performance in the case of overlapping targets. This study can assist security personnel in completing the task of detecting contraband and improving the efficiency of security checks.

We urgently need to explore the communication security guarantee mechanism to ensure the security of transmitting important information, and the steganographic communication model plays a crucial role in achieving this security. In this paper, we focus our research on secure communication methods using images, a widely used multimedia transmission medium. We design two covert communication models, LSTM-ACGAN and CNN-GAN, to enhance the security of deep image steganography algorithms while also improving their generalization ability. This paper’s model is compared with three current mainstream steganographic communication models on a dataset, and the CNN-GAN model is applied to a confidential unit dataset transmission. The research reveals that the two models in this paper possess the ability to detect across multiple domains, remain unaffected by specific domains, and require only 30%–33% of the parameters and arithmetic operations compared to mainstream models. Furthermore, they exhibit greater versatility and practicability, with training accuracy reaching 90% or higher. The model presented in this paper can meet the computer information security communication task after several rounds of iteration and meets the design expectations. This study provides a useful exploration for the establishment of computer information security guarantee mechanisms and designs a proven secure covert communication scheme.

In recent years, with the continuous development of the tourism industry, changing the education model has become a fundamental problem that must be solved to cultivate the quality of professional talents, and the OBE education model has become the trend of higher education development. In this paper, the program design of tourism management mode based on OBE education is carried out in two aspects of personality characteristics cognition and personality learning resources, then constructs the learner characteristics model from several aspects of style similarity, behavioral similarity, learner influence relationship, and proposes the personality recommendation method based on deep learning after the selected experimental objects are experimental class and control class respectively, and through the analysis of the cognitive level of the students, learning style, interaction behavior characteristics were analyzed to verify the validity of the learning characteristic model and program design constructed in this paper. After the experiment, the average post-test score of the experimental group was 84.91, which is higher than the average post-test score of the C1 group, which is 83.63, indicating that the OBE education model based on the deep learning recommendation can improve the student’s learning performance.

In this paper, we propose an adaptive gamma transform that adjusts the local values of bright and dark parts to enhance the effect of low-illumination images, thereby improving the light component. We then apply diff texture enhancement to enhance the contrast of images processed by the Retinex algorithm, thereby optimizing the perception of overexposed and underexposed imagery. Analyze the effect of image brightness enhancement based on a nonlinear transformation combined with the LOL dataset. Use PSNR and SSIM image quality evaluation criteria to analyze the visual effect of improving low-illumination images based on Retinex theory. Create a dataset of power marketing field operation inspection images and examine the effects of overexposure and underexposure image processing on four types of images: high-voltage towers, transmission lines, high-voltage fixtures, and high-voltage wireframes, using the low-light image texture fusion algorithm based on Retinex theory. Overall, this paper’s algorithm and the three DeblurGAN and DMCNN models achieve the effect of deblurring overexposed and underexposed power marketing field operation inspection images. From the local details, the model in this paper has a better effect on the de-exposure of the image, which can provide effective help for the electric power staff to understand the situation of the electric power marketing operation site and has strong practicality.

Automation in securities trading offers advantages over human subjective trading, such as immunity to subjective emotional factors, high efficiency, and the ability to monitor multiple stocks simultaneously, making it a cutting-edge development path in the securities trading industry. In this paper, we first apply the concept of time-frequency decomposition, gradually moving from the first-order moments of securities prices to the higher-order moments. We then combine this with the EMD time-frequency decomposition method to analyze the securities price sequence and extract the characteristics of the securities price fluctuations. Finally, we use the differential long- and short-term memory network to construct an automatic optimization trading system. We compare the system’s performance with traditional technical analysis indexes, as well as the annualized returns of PPO and A2C models on various securities, to verify its performance under unilateral rising, oscillating rising, and plummeting quotes. Finally, we conducted a live test on 1000 GEM stocks. The system in this paper outperforms all traditional technical indicators, with an average annualized return of 71.85% at the lowest and 127.27% at the highest among 5 securities, demonstrating excellent performance. In the three quotes of Ningde Times, Aier Dental, and Goldfish that are rising one way, rising and falling over time, and rising again, the annualized returns of this paper’s system are 77.13%, 67.16%, and 12.66%, which are higher than those of the PPO and A2C models.

Classical poetry embodies the essence of traditional Chinese culture, and its lyricism and infectiousness provide an ideal platform for educating about emotions. However, due to the West’s influence in modern times, the teaching of classical poetry has not expanded to include the emotional aspect. Therefore, this paper establishes the JSA model as the research model for recognizing emotions in classical poetry, based on an analysis of existing methods for recognizing emotions in Chinese literature. Upon scrutinizing the JSA model’s construction, we discovered that it overly relies on the distribution of emotions for theme generation. Consequently, this paper enhances the JSA model by situating the emotion layer between the theme layer and the word layer, builds the reverse JSA model, and employs Bayesian estimation to estimate the model’s parameters. In this paper, we use classical poems as an example to demonstrate how to analyze the sentiment of classical poems by recognizing tone auxiliaries. The improved JSA model’s emotion recognition effect closely aligns with the actual expression effect of the poems, demonstrating the effective application of the advanced JSA model in this paper for emotion recognition of classical poems.

In the education system, teachers and students as the main body of the classroom; their emotional state in the classroom school is an important indicator of the effectiveness of the classroom. This study first explores biometric recognition, based on the needs of the classroom curriculum and the classroom monitoring as a sensor, to propose a multimodal biometric fusion detection method based on the fusion of face and gait recognition. The PCA algorithm is used to optimize the face recognition as well as the occlusion situation in the classroom to improve gait recognition, and then the face and gait are fused based on the decision layer to achieve the detection and recognition of the identity situation of teachers and students. On this basis, an expression recognition model is established using the attention mechanism, and an emotion analysis system is designed for the classroom curriculum. According to the empirical evidence of multimodal biometric fusion sentiment analysis, the mAP accuracy of this paper’s fusion method is 100% in Euclidean distance, and the accuracy is higher than 99% in cosine distance, which is obviously better than other methods, and the accuracy of this paper’s fusion recognition is above 95% under any condition limitations. At the same time, the correct rate of recognition of emotions such as listening, appreciation, resistance, doubt, and inattention are all higher than 85%, and the five indexes of average absolute error, Pearson correlation coefficient, Accuarcy5, Accuarcy2, and F12 score of this paper’s sentiment analysis have achieved the best results comparing with other sentiment analysis models, which proves the generalization and validity of this paper’s sentiment analysis.

Enterprises are the key participants in realizing the development of a green and low-carbon economy and are the main promoters of the environmental transformation and healthy development of the industry, and the green accounting information disclosure truly reflects the important indexes of green development of enterprises. In this paper, the relevant data of 15 listed companies in the paper industry from 2013 to 2023 are selected as samples to carry out empirical analysis, and their green accounting disclosure reports are used as the basis for calculating the GAID scores of the companies. A multiple linear regression model is created to test the disclosure-related research hypotheses, with the goal of discovering the factors that influence the current quality of enterprises’ green accounting disclosure. The fluctuation range of GAID scores of most of the fifteen listed enterprises in the paper industry is between 40 and 70, and there are also 20% of enterprises with GAID scores lower than 40. Enterprise size, proportion of outstanding shares, enterprise value, and enterprise development ability are significantly positively correlated with the quality of corporate green accounting disclosure at the 1% or 5% level, and the quality of disclosure increases by 0.151% for every 1% increase in enterprise size. In the enterprise green accounting information disclosure, enterprises need to be, based on their situation, reasonable and comprehensive information released in order to effectively enhance their corporate image and promote the green and sustainable development of enterprises.

In order to improve the defect recognition efficiency of transmission lines, the industry is currently using aerial images for automatic visual defect detection to ensure the safe operation of transmission lines. This paper proposes a method for defect recognition from coarse to fine, based on convolutional neural networks and connected domain algorithms, to improve recognition accuracy. The recognition speed is improved by using the knowledge distillation method of target detection networks based on decoupled features, adversarial features, and attention features. It has been found that the optimized recognition model improves the precision rate by 7%, the recall rate by 8%, and the average accuracy rate by 10%. The FPS of the model optimized by knowledge distillation is 62.5, and the average value of the FPS of other versions of this model is 47.35. It is believed that the two optimization ideas introduced in this paper can enhance the previous transmission line defect recognition algorithm in terms of accuracy and recognition speed.

Labor education is an important educational course for secondary school students to learn and grow comprehensively. This paper first collects the current improvement direction of secondary school labor education through relevant questionnaires and then introduces cloud computing technology to design an online learning platform for secondary school labor education courses, which assists teachers in completing the labor teaching process. The design of the platform adopts MVC development mode, AJAX asynchronous refresh technology, and other key technologies, analyzes the requirements from three aspects of objectives, performance, and functions, and finally realizes five major modules, including user management, course management, and evaluation management. To address the problem of insufficient evaluation of labor courses, this paper constructs a model of students’ online learning behavior based on the K-means algorithm in the application process of the platform and evaluates the behavior of students’ online participation in labor education courses. By standardizing students’ platform learning information data and analyzing and calculating the learning behaviors of 300 students can be divided into 4 categories, accounting for 16.0%, 34.3%, 23.0%, and 26.7%, respectively, and the teachers of the labor courses can formulate personalized teaching plans for each type of labor learning behavior.

Criminal activity has always been a problem that seriously affects people’s sense of security and well-being in life, and it is also the focus of public security departments in terms of security prevention and control. This study aims to use scientific methods to analyze the time series of existing historical data related to criminal activities and to advance inference or determination of the future trend of criminal activities. In this paper, after mining the spatiotemporal pattern of criminal activities using the centered moving average method, the spatiotemporal cycle characteristics and time distribution characteristics of criminal activities are analyzed. Based on the conclusions drawn, an improved LSTNet algorithm is proposed by combining deep learning spatio-temporal network, convolutional neural network CNN, recurrent neural network RNN, autoregressive AR, and specially designed Skip-RNN, and a GRU-gated recurrent unit structure is used to realize the optimization of the prediction accuracy of the criminal activities, to solve the problems related to the spatio-temporal dependencies, and to establish an improved ST- Res Net crime prediction model. Finally, the prediction performance of the model is examined. The RMSE, MSE, and MAPE values of this paper’s prediction model are 0.88, 5.12, and 5.12%, respectively, which are better than other models. The experiments demonstrate that the prediction model presented in this paper can enhance the accuracy of criminal activity prediction to a certain extent and can be employed in the prevention and management of criminal activities.

Leaf Area Index (LAI) and biomass (BIO) are essential agronomic parameters that reflect the growth of potatoes and are related to their biomass. Their precise estimation is capable of monitoring crop growth, guiding field management, and optimizing planting spatial patterns. Traditional potato leaf area indexing and biomass estimation primarily rely on field sampling surveys. This method is low in efficiency, high in cost, and limited by the number of samples. It cannot accurately reflect potato growth and meet the real-time estimation needs of large areas. Compared to the use of satellite remote sensing data (RSD) for estimating LAI and biomass, research on estimating these two phenotypic parameters using crewless aerial vehicle (UAV) RSD is relatively immature. Research on estimating crop growth index parameters by remote sensing primarily focuses on data obtained from specific types of sensors, targeting specific growth stages to compare and analyze the accuracy of different methods. However, there are few estimates of the impact of optimizing the best data types and optimal growth stage for LAI and biomass estimation by comparing and analyzing different sensor data and different growth stages. Multi-sensor integration technology has made it possible to study different crop phenotype information and estimate the best data type and optimal growth stage in crop phenotypic data estimation, establishing it as a new hot spot in the field. This paper integrates high-definition digital cameras and imaging hyperspectrometers on the UAV platform to obtain digital images and hyperspectral data simultaneously, along with ground-measured potato leaf area index and biomass data. Using the partial least squares regression (PLSR), random forest (RF), support vector machine (SVM), and backpropagation (BP) neural network methods, we got digital images and hyperspectral data from different stages of growth, put together a digital image index and a vegetation index, and looked at how they related to LAI and BIO. Then, we chose the index that had the strongest correlation. To establish LAI and biomass estimation models at various growth phases, this paper compared and analyzed the estimation impacts of various data types and models at various growth phases. It then selected the best data types for LAI estimation and biomass estimation at different growth stages, as well as the best growth phases for LAI and biomass estimation. The outcomes indicated that when potato LAI was estimated, the mean values of R2 and RMSE of the four estimation models were 0.75 and 0.30 Kg/mu at the tuber growth stage, respectively, and the estimation effect was the best, indicating that this was the best growth phase for LAI estimation. The average values of R2 and RMSE in the LAI estimation model using the hyperspectral vegetation index were 0.73 and 0.33 Kg/mu, respectively, indicating that hyperspectral data was the best data type for LAI estimation. When potato biomass was estimated, the mean values of R2 and RMSE of the four methods were 0.67 and 15.25 Kg/mu, respectively, at the tuber growth stage, which were better than other growth phases, demonstrating that this was the best growth phase for biomass estimation. The average values of R2 and RMSE of the biomass estimation model using the hyperspectral vegetation index were 0.67 and 20.08 Kg/mu, respectively, indicating that the hyperspectral data was the best data type for biomass estimation. The average values of R2 of the LAI and biomass estimation model at the maturity stage were only 0.56 and 0.36, both of which indicated poor estimation effects. Our study can serve as a guide to selecting the most effective method for estimating parameters for essential indexes in crop growth monitoring.

The arrival of the big data era makes the amount of data explosive growth, which puts forward new challenges and demands for computer network technology, and the integration of big data and network technology has become an important trend. This paper uses the optimization strategy and the elimination mechanism of the genetic algorithm to optimize the inertia weight and particle position speed updating mechanism of the particle swarm algorithm and combines the searching method of the Tennessee whisker algorithm with the sharing mechanism of the particle swarm algorithm to achieve the optimal data searching ability. Finally, the improved artificial intelligence algorithm and MapReduce are combined to improve the performance of the computer neural network algorithm in big data processing. The average data redundancy rate of this paper’s algorithm for big data processing is only 1.18%, and the resource integration checking rate always exceeds 85%, according to simulation experiments. In addition, the algorithm also shows good performance in practical applications, and it can achieve accurate classification of big data labels in big data label classification tasks while maintaining a low energy overhead. Meanwhile, it can accurately recognize electronic medical record data in large medical databases. Big data processing can benefit greatly from the proposed neural network algorithm in this paper.

From the perspective of juvenile delinquency prevention theory, this paper explores the current situation of juvenile delinquency in rural areas of W County and the mechanism of relevant functional departments in local community governance based on the questionnaire survey method. Then, six juvenile delinquency prevention service programs are selected as the object of evaluation research, and the intelligent decision analysis system of system dynamics is used as the tool of evaluation research to evaluate the six juvenile delinquency prevention programs systematically and comprehensively. The following conclusions were obtained after the analysis. The crime rate of rural youths in County W is as high as 15.8%, with a wide range of crimes. 81.6% of the relevant departments in community governance did not establish rural juvenile records, and about 13% of the departments did not conduct crime prevention training. The Green Clay People Juvenile Crime Prevention Program, which uses social connection theory as a strategy, has an evaluation value of 0.242, and the completion rate of the agreed service indicators specified in the contract is more than 100%. The overall evaluation of the six programs was 87% satisfied. Therefore, the intelligent decision analysis system in this paper has been well applied in the evaluation of juvenile crime prevention strategies, with the progress and development of society, and will occupy an important position in the future for a considerable time.

The use of smart contract technology for contract execution and real-time payment can ensure the timely availability of funds, thus ensuring the security and authenticity of data in power grid transactions. In this paper, we design a digital RMB smart contract model based on blockchain technology and use the hexadecimal model to create, deploy, and execute smart contract functions. And through the DTSC algorithm, smart contracts can be applied to the grid smart payment settlement. At the same time, a privacy protection algorithm for transaction data is proposed, and finally, the grid smart payment settlement system is designed based on smart contracts and privacy protection algorithms. Simulation test results show that the cost required for the digital RMB smart contract proposed in this paper is lower than the existing schemes in terms of invocation and deployment costs. The average chain code invocation delay in smart contract technology decreases when the transaction sending rate increases from 250TPS to 300TPS. Moreover, the on-chain operation time of this system is only 2.69 seconds, which meets the demand of practical power grid smart payment settlement applications. This paper sets the foundation for the efficient operation of the grid smart payment and settlement system and provides a guarantee for payment and settlement security.

Education informatization is an important means to improve the quality of education and teaching as well as a basic condition for the innovative reform and application of education and teaching, which also means that education informatization cannot be separated from the construction of digital learning resources. This paper utilizes the advantage of Flash technology’s integration of multiple media elements to design physics animation courseware. Then, it combines the color histogram and edge density analysis algorithm to segment the animated visual scene of physics courseware, optimize the production process of Flash physics animated courseware, and establish a scientific evaluation standard for courseware quality. The average scores of the four dimensions of manipulability, stability, aesthetics, and compatibility in the evaluation results of physics animated courseware in this paper are all higher than 4 points. The students who apply physics animated courseware to teach improve their learning attitudes, learning behaviors, and learning effects by 11.61, 7.33, and 6.54, respectively, compared with the traditional physics teaching, and all of them are significantly different (P

The laboratory is an important place for talent cultivation and scientific research activities. However, at present, there are problems such as backward management mode and low management efficiency in the laboratory. This paper combines the “Internet +” technology to study the effective means to improve the efficiency of business laboratory management. Through the Internet of Things, Android, and other key technologies, we can build an intelligent business laboratory management platform. The management level of the business laboratory management platform designed in this paper is evaluated and classified using the neural network algorithm. The designed and completed intelligent management platform for business labs contains functional modules such as intelligent control, equipment management, faculty management, and user management. The evaluation study found that the management level score of university laboratories after applying the intelligent management platform for business laboratories maintains more than 85 points in general, and the evaluation grade shows an excellent level of A grade.

In this paper, according to the process of remote sensing monitoring of soil salinity and alkalinity process as well as the conditions, the remote sensing images were radiometrically corrected and aligned, and the remote sensing images were enhanced by using digital models to change the gray structure relationship of the image elements and change the gray value of the image elements, and then the changes in the patches of the remote sensing images were analyzed to extract the soil salinity and alkalinity data. In this paper, we also used statistical methods to analyze the acidity and salinity characteristics of soil samples, the soil spectral reflectance characteristics, and the sensitive bands for estimating the soil acidity and salinity characteristics, and we performed the multispectral inversion analysis of soil salinity on the basis of the spectral data. The results show that the remote sensing monitoring and early warning model of the soil salinization process established in this paper has a coefficient of determination R2 =0.697, RMSE=0.946, p=1.06*10-7 in the research calculations, and the root-mean-square error between predicted and measured values RMSE=2.33, which indicates that this model has a better performance in monitoring and prediction. The theoretical significance and practical value of this study are crucial for protecting the ecological environment and managing soil salinization.

It is especially important to solve the psychological pressure of college students’ employment if they want to complete their employment and get better development. This paper proposes a cognitive interaction model based on the full information emotion theory and develops the psychological analysis of employment and entrepreneurial pressure on college students on this basis. In the construction of the cognitive interaction model, the basic assumptions of the all-information affective theory are first proposed, the concepts of the individual’s a priori information, a posteriori information, actual information, and expected information are introduced, the individual’s emotional model is established, and the assumption of information-emotional equivalence is proposed. Combining the PDA model with the information theory of emotional motivation completes the model construction based on this basic assumption. In the model performance test, the accuracy of emotion dimension recognition in this paper’s model is more than 95%, which is better than other models. Taking college students in 2 general colleges and universities in Hunan Province, China, as the research object, the study shows that the total psychological mean score of college students’ employment and entrepreneurship stress is 2.75, and the stress psychology is at a medium level. In the data of the randomly sampled student samples, 70% of the student’s emotional tendencies are anxiety, and anxiety is the mainstream emotion of college students. College students’ feelings of employment and entrepreneurship stress and negative coping styles are both at a high-intensity level.

This paper elaborates on the technology related to augmented reality interaction, introduces in depth the augmented reality device HoloLens, including its composition and the principle of generating indoor three-dimensional data, and designs a teaching interaction model of augmented reality fusion learning environment. The Kinect somatosensory device is introduced into the teaching interaction model, and virtual interactions between virtual objects and real objects are accomplished by judging the human body’s position and posture changes in real time. Group experiments were conducted to examine the learning effect of augmented reality-based technology with or without interactive behavior in terms of interest in sports learning. According to the findings, the augmented reality physical education interactive teaching experiment resulted in a 23-point increase in the average value of physical education knowledge mastery level test scores. Further one-way ANOVA was conducted and the p-value of the scores of group B of the experiment with interaction before and after teaching was 0.001, which is less than 0.05. Augmented reality sports interactive teaching can significantly enhance students’ interest in sports learning, attention to sports, and so on. Therefore, the augmented reality sports interactive teaching technique mentioned in this paper serves as an effective way to improve students’ performance and interest in sports education.

Data is an important production factor in the era of the digital economy, and cross-border data flow is a prerequisite for digital trade. The Digital Services Trade Restrictiveness Index (DSTRI) is the basis of this paper’s research on the impact of cross-border data flow on digital trade. Firstly, cross-border data flow and digital trade are refined into cross-border data flow restrictive measures and digital service trade, and the mechanism of cross-border data flow restriction on digital service trade is investigated. Then, the impact model is constructed based on the gravity expansion model, the variable selection is carried out, the model variables are tested from the perspective of Pearson correlation and multicollinearity, and the optimal regression model is selected. Finally, baseline regression results are derived based on the model, and heterogeneity analysis and robustness tests are conducted. Cross-border data flow restrictions have a correlation coefficient of −2.176 with total digital services, and they have both negative and positive effects on the total trade in digital services. The total trade in digital services in DSTRI is negatively impacted by all policy areas of restrictions, which suggests that restrictions in any policy area can hinder the development of digital trade. When conducting the robustness test, cross-border data flow restrictions still have a significant inhibitory effect on digital services trade, which is consistent with the results of the benchmark regression, indicating that the results of the benchmark regression in this paper are reasonable and valid.

Along with the flow of clothing designer personnel, clothing style design technology will be lost, so the intelligent design of the clothing industry, with the development of artificial intelligence technology, has received great attention. In this paper, based on the real-time style migration algorithm to study and design the local pattern of clothing, based on the principle of real-time style migration of images with perceptual loss function, it is proposed to optimize the real-time style migration network by using the group normalization method to obtain the style migration image that is more in line with the visual habit. The fusion of the style migration image with the garment base map through Poisson fusion achieves the end-to-end intelligent design of garment local patterns. The AdaIN-based style migration network model designed in this paper has an average accuracy of 75.758% when trained. Then, the model is applied to the clothing fashion design to evaluate the effect of the garment. The average scores of the overall, front, side, and back evaluation of the dressing effect of the garment are 4.04, 4.15, 4.01, and 3.92, respectively. The garments show a better effect. AI technology will bring more innovative possibilities to the clothing fashion industry and inject new vitality into the fashion industry.

In order to confirm the performance of recessed green space in rainwater collection and utilization of urban roads, this paper proposes a corresponding experimental test program, which mainly covers the evaluation of rainwater infiltration, the evaluation of rainwater purification, and the simulation of rainfall-runoff reduction. Using the above test methods, the effectiveness of recessed green space in collecting and utilizing rainwater was analyzed. The results showed that in the one-way analysis of the compositional structure of the undercroft green space, the gravel layer, the media layer, and the vegetation layer had no significant difference in the infiltration rate sig red loam reactor (23.04 ml/min) > 2/8 mixed media reactor (23 ml/min) > black loam reactor (23.08 ml/min), while the order of purification effect was 3/7 mixed media > 2/8 mixed media > red loam > black loam. In addition, the combined high infiltration hypolimnetic green space had a better retention effect (flow yield range from 0 to 10 L) in rainfall-runoff with a reproduction period of 3 and 4 years. Based on the analysis results, the application effect of undercroft green space in urban road rainwater collection and utilization is comprehensively verified, and it is hoped that the investigation of this paper can bring certain references and references to the relevant personnel.

In this paper, using the loss function of image stylization, combined with the development of image stylization based on deep learning, the proposed convolutional neural network in the style of image conversion fitting and overfitting response. Based on this, the multi-scale feature fusion method is chosen to train the style conversion network, with the help of deep feature extraction of the image for style conversion, reconstruct the multi-scale feature fusion image, and send it to the decoder for deep coding to realize the style conversion. To evaluate the effectiveness of the proposed multi-scale feature fusion style conversion algorithm, the content loss and style loss parameters of the algorithm are analyzed using the lightweight encoder and VGG encoder, respectively. Calculate the number of algorithmic model parameters and the amount of computation. Analyze the change in the iteration number of the personalized art style conversion process and select the performance evaluation index to evaluate the results of the personalized art style image conversion process. In the process of personalized art style conversion, the multi-scale feature fusion algorithm network proposed in this paper can basically reconstruct the original image after 1000 iterations. Personalized style image reconstruction has a PSNR of 25.26 dB when the number of iterations is 1000. With the deepening of training, the reconstruction effect becomes better and better, and the advantages of personalized art style image conversion applications are significant.

This paper explains the dilemma of artificial intelligence in relation to the development of teacher education based on the functional structure of artificial intelligence and the activity characteristics of teacher education. Then, after designing a survey questionnaire on the factors affecting the development of teacher education empowered by artificial intelligence and completing the reliability test, the paper collects initial data in the form of distributing questionnaires and analyzes in detail the least squares estimation of mean, variance, standard deviation, correlation coefficient, and regression coefficient needed in the process of analyzing the data to carry out the analysis of instances. The correlation coefficients of teacher training, professional development, policy support, resource allocation, teacher literacy, educational information technology behaviors, and AI-enabled teacher education development are 0.674 (0.003), 0.496 (0.001), 0.259 (0.009), 0.371 (0.008), 0.639 (0.004), and 0.325 (0.007). Their corresponding regression coefficients were 0.616 (t=59.852, P=0.003), 0.021 (t=0.018, P=0.007), 0.078 (t=5.668, P=0.005), 0.032 (t=3.282, P=0.009), 0.239 (t=29.734, P=0.008), 0.137 (t=5.406, P=0.001), indicating that these factors have a significant impact relationship on AI-enabled teacher education.

With the help of automation technology, the efficiency and reliability of substation operations are synchronized. However, the equipment will operate under abnormal problems for a long time. If the problem is not resolved promptly, the consequences will be unimaginable. For timely detection of problems, this paper proposes a method for the construction of remote operation and maintenance systems. The remote operation and maintenance system is mainly composed of two-factor authentication, responsibility area authentication, and permission authentication. The security of remote operations and maintenance operations is guaranteed with the support of these key technologies. This paper enhances the safety and stability of automation equipment by offering remote wake-up, remote reset, historical information retrieval, and forwarding table monitoring services in the operation and maintenance service module. Adopting IoT technology, the core management module of remote management of master stations is constructed to ensure the safety of remote operations and maintenance data interaction between master stations and sub-stations. Simulation experiments are being conducted to evaluate the performance of IoT technology in remote operations and maintenance interactions at the main station. The energy consumption of the data interaction module of substation automation equipment is 0.19 and 0.012 mA for 1 hour and 1 day, respectively, for the equipment to operate for 5-10 days, where the advantages of IoT technology are reflected. The processing time of the operation and maintenance personnel under the traditional operation and maintenance and remote operation and maintenance modes were analyzed through comparative experiments, and the processing time of the device dead time was reduced from 175.46 minutes to 4.356 minutes after using the remote operation and maintenance system, and the efficiency of the operation and maintenance personnel was improved.

More and more modern technology is applied to traditional cultural and creative industries, which enhances the technicality and novelty of traditional cultural products, and the fusion of culture and modern technology profoundly changes people’s way of life and learning. This paper explores the Internet of Things (IoT) technology and the intelligent transformation process of cultural and creative products and constructs cultural and creative products that integrate intelligent voice series. Specifically, a speech recognition model is integrated into the design process of cultural and creative products, and the designed model is applied to the design of intelligent cultural and creative products by analyzing the Hidden Markov Model (HMM), proposing a solution to the shortcomings of the HMM model, and choosing to perform noise reduction of speech signals through the fixed beam algorithm. Based on the speech recognition model designed in this paper, an intelligent cultural and creative product with a speech recognition function is designed, taking the ‘owl wine container’ from the Shanxi Museum as an example. The regression equation of the audience’s satisfaction with the product is Y (satisfaction) = -0.000263 + 0.208X1 (practicality) + 0.265X2 (innovation) + 0.253X3 (culture) + 0.271X4 (interactivity) - 0.296X5 (fun). This paper’s intelligent cultural and creative products have a greater impact on satisfaction due to their innovativeness and interactive function.

The increase in complexity and quality standards of civil engineering projects continues to drive the innovation of construction materials from the traditional ordinary concrete-steel structure combination to the combination of high-performance concrete and steel structure. In this paper, the application of the combination of high-performance concrete and steel structures in civil engineering projects is investigated based on the mechanical properties of the two structures. The structural reliability index and the corresponding functional function are used to measure the structural reliability of the combination of high-performance concrete and steel structures. After measuring its reliability, a finite element simulation is carried out to investigate the application value of the high-performance concrete-steel structure combination in civil engineering projects. Considering the reliability index of resistance and load time-varying effects decreases with the service time of the combined structure, if the reliability index of the components during the service period is not allowed to be lower than the target reliability index, the time to reach the limit state of the selected high-performance concrete-steel combined building in this paper is about 75 years. The ultimate load-carrying capacity of the high-performance concrete-steel structure combination is increased by 28.74% compared with that of the ordinary concrete-steel structure combination, and the end slip of the high-performance concrete-steel structure combination is smaller than that of the ordinary concrete-steel structure combination under the same load. It shows that the advantages of high-performance concrete-steel structures in civil engineering are much more than ordinary concrete-steel structures.

This paper focuses on the functional characteristics of BIM technology, emphasizing the need to develop a combination of BIM technology tailored to the user’s interior design process. We utilize the hardware and software to establish the BIM technology environment, construct the interior design model using the Autodesk Revit software platform, import it into Lumion for color rendering, and utilize Navisworks Simulate software to gather project data and monitor the interior design project’s progress. Autodesk Ecotect software was used to find out how lighting affected the interior design using BIM technology. Next, an interior layout optimization model based on the improved whale algorithm was made to solve the interior layout problem, and the impact of using AI was confirmed. The data show that the error range for the daylighting coefficient using BIM technology and the old method is between 0.04 and 0.91. The old method takes 131 minutes longer than BIM technology. This means that the BIM-based lighting simulation model pre-processing process is still much more efficient than the old method. Furthermore, this paper maintains all the model’s index values above 0.68, demonstrating the model’s ability to achieve a reasonable interior space layout while simultaneously enhancing both the layout speed and the layout effect.

Point cloud segmentation, as a key link in 3D point cloud data processing, can realize power transmission and distribution positioning, object identification, classification, and feature extraction, which helps to refine power grid management. In this paper, firstly, dense point cloud transmission and distribution 3D digital corridor modeling is carried out. Alignment splicing and noise reduction are carried out after obtaining the original dense point cloud. Contour line extraction, geometric modeling, and texture mapping are realized after processing the data to ultimately realize the transmission and distribution of 3D digitization. Then, the conversion formula for the pixel coordinate system and world coordinate system is derived to extract features from point clouds. Finally, a distance-based feature fusion method is designed to extract spatial features from point clouds and use the joint attention layer to segment them by fusing RGB pixel information. The original dense point cloud of a transmission and distribution digital corridor is segmented using the model presented in this paper for application after testing the dataset. It is found that the under-segmentation ratio of this paper’s algorithm is 0.96%, 3.44%, and 2.87% for the three scenarios of regular, irregular, and multi-targets, respectively, which is much lower than that of RANSAC+ECS with FCM + ECS. The intersection and concatenation ratios of this paper’s algorithm for the scenarios of irregular geometry as well as multi-target objects are 91.49% and 89.56%. It is much higher than 64.31% and 72.17% for RANSAC + ECS and 76.85% and 60.91% for FCM + ECS, which illustrates that this paper’s algorithm has a significant advantage in performance. In this study, the target point cloud can be segmented with high accuracy from the dense point cloud of a 3D model of power transmission and distribution with a large amount of data, effectively avoiding the phenomenon of under-segmentation and over-segmentation and contributing to the accurate control of power grid data.

Inventory management plays a very important role in the process of business operation, providing favorable backing for the smooth operation of production and sales. In this paper, LightGBM and PSO-LSTM models in big data technology are combined to improve inventory management and demand forecasting in supply chains. Then, the relationship between inventory, order, and forecast is elaborated, the two-level inventory cost components and the relationship between them are analyzed, the model constraints are formulated, and a mathematical model for two-level multi-cycle inventory control is constructed. Finally, the single demand forecasting model is compared with the improved model to explore the optimization effect of inventory management after the application of the LightGBM-PSO-LSTM model. The LightGBMPSO-LSTM model is the best fit and can be used for actual demand forecasting. After the optimization of inventory management, the inventory turnover ratio of Company H increased from 8.2 in 2022 to the maximum value of 9.2 in 2023, and the OTIF achievement rate of sales orders increased from 97.9% in 2022 to 99.3% in 2023. This paper provides a successful example of optimizing supply chain inventory management using big data analytics.

In the era of information technology, with the deepening of cultural heritage protection, the importance of digital technology intervention in traditional art and culture for protection and inheritance has become more significant, and the digital inheritance of Chinese traditional music culture has also received widespread attention. In this paper, we first preprocess the traditional music signal and extract the Meier multifrequency coefficients, then use the feature as the input of the deep confidence network, and then keep tuning the parameter training to get the optimal network model, and finally utilize the obtained optimal model to recognize the traditional music. Based on this basis, this paper focuses on the concept of the digital heritage of Chinese traditional music culture through three steps: recognition, processing, display, and dissemination. We also designed and developed a Chinese traditional music culture APP for Chinese traditional music lovers and inheritors and examined the effect and performance of the APP application based on the music recognition model in this paper. The modeling methods proposed in this paper meet the usage requirements by having accuracy rates above 90%. 73.25% of the audience expressed satisfaction and very satisfaction with the overall application effect of the Chinese traditional music APP. In this paper, the Chinese traditional music digital APP proposes an effective means of communication for the solution of digital inheritance and also provides a realizable path for the digital inheritance of Chinese traditional music culture.

Virtual reality, as a computer simulation system that can create virtual environments, is a fusion of multiple key technologies that are applied in different fields with important practical value and significance. This paper focuses on optimizing the artificial intelligence-based dynamic scene generation and perception mechanism in virtual reality. Firstly, a virtual dynamic scene generation method combining scene management technology and image rendering technology is proposed. In order to optimize the dynamic scene perception mechanism in virtual reality, a perception model based on spatial interaction perception and based on the analysis of user dynamic interaction is proposed. A two-layer perception management strategy is proposed. The paper finally uses the virtual reality technology proposed in this paper to create a Chinese classical garden attraction in a scenic spot. It carries out modeling accuracy assessment and comparison experiments and invites garden professionals and tourists to evaluate the overall effect of the virtual scene. The survey results show that more than 80% of the tourists are satisfied with the generation of the dynamic scene and think that it has spatial continuity and immersive experience.

In view of the current situation that the curriculum construction of calligraphy education needs to be perfected, a more comprehensive and in-depth study is carried out for the curriculum setting and development of calligraphy education in higher teacher colleges and universities, starting from the core - curriculum system in calligraphy education. Based on information technology, this paper constructs a path of calligraphy education construction, from which the learning resources design, learning content design, learning activities design, and learning evaluation design of the practical calligraphy classroom are carried out. For the learning evaluation of the calligraphy education curriculum system, a calligraphy word evaluation model is proposed, which consists of three parts: overall structure, stroke form, and font layout. Ultimately, students can be scored according to the evaluation standard of calligraphy words. In the overall evaluation of the curriculum system constructed in this paper, 75%, 74%, and 72% of the students agreed strongly with the system in the cultivation of “knowledge”, “ability,” and “thinking and literacy,” respectively. The students indicated that they “strongly agree” with this system. With regard to the cultivation of “thinking and literacy”, this paper proposes corresponding improvement strategies to improve the calligraphy education program system.

Emerging technologies such as big data, the Internet of Things and artificial intelligence are developing rapidly and entering into many fields and industries, while their role in the field of news communication and brand image shaping has an important role in influencing. This paper selects WeChat, a Tencent product, as the research object and divides brand image shaping into four dimensions, namely brand awareness, brand trust, brand loyalty, and brand value, to test the relationship between emerging technologies and brand image shaping. Then, we put forward the research hypothesis of this paper and use empirical analysis to test the hypothesis and the empirical results show that the r-value of emerging technology and brand loyalty is 0.591, p