Search

In the era of big data, efficient classification of rapidly growing data volumes is a critical challenge. Traditional algorithms often fall short in handling the scale and complexity of big data, leading to inefficiencies in classification accuracy and processing times. This study aims to address these limitations by introducing a novel approach to algorithm selection, which is essential for advancing big data classification methods. We developed an advanced classification algorithm that integrates a fuzzy multi-criteria decision-making (MCDM) model, specifically tailored for big data environments. This integration involves leveraging the analytical strengths of MCDM, particularly the analytic hierarchy process, to systematically evaluate and select the most suitable classification algorithms. Our method uniquely combines the precision of fuzzy logic with the comprehensive evaluative capabilities of MCDM, setting it apart from conventional approaches. The proposed model is meticulously designed to assess key performance indicators such as accuracy, true rate, and processing efficiency in various big data scenarios. Our findings reveal that the proposed model significantly enhances classification accuracy and processing efficiency compared to traditional algorithms. The model demonstrated a marked improvement in true rates and overall classification performance, showcasing its effectiveness in handling large-scale data challenges. These results underline the model’s potential as a pragmatic solution for big data classification, offering substantial improvements over existing methodologies. The study contributes a groundbreaking perspective to the field of big data classification, addressing critical gaps in current practices. By combining fuzzy logic with MCDM, the proposed model offers a more nuanced and effective approach to algorithm selection, catering to the intricate demands of big data environments. This research not only enhances the understanding of classification behaviors in big data but also paves the way for future advancements in data mining technologies. Its implications extend beyond theoretical value, providing practical tools for practitioners and researchers in the realm of big data analytics.

To understand the deep learning model, the author proposed the research of interactive texture replacement of cartoon characters. For image segmentation, if you want to fill a cartoon without any texture in detail, or replace the unsatisfied texture area, first, we need to separate the filled or replaced area from the cartoon. For this reason, the traditional image segmentation algorithm has been carefully studied and analyzed, and the author chooses the Graphcut texture synthesis algorithm, the algorithm is parallelized and improved, and the innovative point of lighting customization is proposed based on the original algorithm, which can affect the synthesis effect according to the input lighting image. In terms of timeliness and synthesis effect, the Graphcut algorithm has been improved. Experimental results show that the algorithm can maintain the brightness distribution of the original cartoon and the practicability and efficiency of the algorithm proposed by the author.

The use of emerging technologies to construct an interactive academic field of Li Zehou’s aesthetic theory aims to promote the study of Li Zehou’s aesthetic thought and the development of contemporary Chinese aesthetics. Based on the content and characteristics of Li Zehou’s aesthetics theory, the article describes the innovative application of emerging technology in academic communication, constructs the academic field of Li Zehou’s aesthetics theory on the basis of Bourdieu’s field theory, and designs the framework of the interactive academic field by combining with emerging technology. Relying on Li Zehou’s interactive academic field for the construction of a multi-layer innovation network model and providing relevant quantitative methods for interactive academic field network metrics. The dataset is constructed with the relevant literature of Li Zehou’s aesthetics theory from 2005 to 2022 as the search target, and the network density, central potential, clustering coefficients, and path lengths of the interactive field are analyzed, and the evolution characteristics of the multilayer field network are explored. The cross-border innovation multilayer network density of the interactive field of Li Zehou’s aesthetic thought fluctuates around 0.092, approaching the mean value of central potential up to 65.76%, and the average clustering coefficient fluctuates in the range of [0.25,0.35]. The cooperative sub-network and the technology sub-network have smaller path lengths with larger clustering coefficients, indicating small-worldness. The interactive academic field combining emerging technologies can promote the widespread dissemination of Li Zehou’s aesthetic ideas.

Software testing faces problems such as low automation and difficult reuse of testing methods. The purpose of this paper is to explore software testing automation methods with the aid of artificial intelligence. In this paper, based on the BS algorithm, the RF algorithm is constructed by Bagging integration, the RF algorithm is optimized by reducing the generalization error through the residual function, and the random forest model for software automation detection is constructed. After that, the model is examined and analyzed using automated detection of malicious software samples as a case study. The experimental results show that the accuracy of the Random Forest algorithm after feature selection reaches 98.9%, its prediction time is the least (7 seconds), and the Random Forest algorithm for training is the best. Z software’s optimized RF algorithm model has an accuracy of between 86% and 99.3% when detecting seven malicious types of samples. This paper’s proposed random forest algorithm model based on artificial intelligence assistance is well-suited for automated software testing, and the detection method is feasible.

In order to effectively identify the type of partial discharge of SF6 gas-insulated switchgear combinations and then to ensure the safe and stable operation of the equipment, a method for identifying the type of SF6 gas-insulated partial discharge based on crossover frequency features and the transformer model is proposed. First, four types of SF6 gas-insulated partial discharge signals are gathered. These are then broken down into their modal components using variational modal decomposition. The energy moments of each crossover signal are then calculated to find the crossover frequency characteristics. Finally, the Transformer model is used to identify the types of SF6 gas-insulated partial discharge signals. The experimental results show that the proposed method can effectively recognize different partial discharge types of SF6 gas insulation, and the recognition accuracy is as high as 99%, which verifies the validity and superiority of the proposed method of recognizing partial discharge types of SF6 gas insulation.

Teachers have been researching how to effectively improve the English writing ability of contemporary college students. The article utilizes web crawler technology to establish an English writing knowledge database and preprocesses the data through a word division algorithm, lexical annotation, and word form reduction. The article employs Bayesian classification algorithms to model the English writing style of students. The English writing grammar error correction model was constructed based on the BiGRU model, combined with the BERT pre-training task, fused with the attention mechanism. The English writing knowledge database was used to analyze the data for the model mentioned above. The sentence length of English written text fluctuates between -0.095 and 0.436, and the Bayesian classification model’s AUC value is 0.814. The grammar error correction model for English writing text has a GLEU value of 63.24, with an automatic scoring mean of 26.69, which is only 0.35 higher than manual scoring and a scoring error of only 1.29%. Through the English writing text style and grammar error correction model, teachers can optimize the English writing teaching mode and help students improve their English writing abilities.

The intelligent equipment manufacturing cycle is long, resource consumption is large, in the manufacturing process often needs for different production stages to take multiple batches of resource procurement strategy and resource optimization configuration. Based on this situation, this paper proposes an intelligent equipment procurement strategy and resource optimization design. The problem description is established, the variables and constraints are introduced, and the construction of the objective optimization model is completed. The corresponding optimization model is solved using the improved Gray Wolf algorithm and the improved differential evolution algorithm. After the training and optimization of the improved gray wolf algorithm, the total cost of intelligent equipment procurement is 180150 yuan, and the procurement strategy is to select the preferred supplier at the corresponding point in time, according to which the procurement strategy can be a realistic intelligent equipment procurement task. In addition, the average deviation of resource optimization allocation based on the improved differential algorithm is only 0.35%, which is better than the performance of the traditional differential algorithm and genetic algorithm, confirming the feasibility of this paper’s algorithm in intelligent equipment resource allocation optimization model aiming at cost optimization.

With the development of industrial IoT and the arrival of smart manufacturing, the field of edge computing has gained more and more attention. However, traditional industrial computing scenarios relying on industrial clouds make data latency a greater challenge. In this paper, for the contradiction between edge devices and task resource allocation encountered in edge computing scenarios in smart manufacturing, we propose an industrial internet task scheduling model for smart manufacturing and introduce a scheduling node state matrix to realize the state management of each scheduling subtask. Aiming at the problem of multiple tasks seizing resources in a complex, intelligent manufacturing environment, the study combines the caching mechanism to realize the task offloading computational processing of order scheduling, in which the caching mechanism is used to solve the problem of computational resource limitations at the edge. It is found through simulation that when the computational task factor ξk =2 is larger, more offloading power is allowed to be transmitted to the edge ser ver for computation. For computational tasks with smaller task factor ξk, the device tends to allocate more computational rate to that computational task. Eventually the data queue length will be continuously reduced and the data queue is concentrated in the interval of very small values, this result verifies that the task scheduling algorithm is able to perform task scheduling efficiently and reduce the latency.

In recent years, there have been mixed evaluations of the performance of pre-stressed bridges in society. Based on this, this study proposes to integrate adaptive neural networks with BP networks to build a bridge tolerance detection model and combines support vector machines and radial basis function networks to build a bridge wind vibration detection model. The results showed that in the detection results of angle adjustment and detachment, Sample 1 was the closest to the true value, with a difference of only 0.01. As the number of samples increased, the difference became larger, and the difference in sample 5 reached its maximum value of 0.3. The turbulence level of 0.5% had the lowest initial vibration wind speed at a wind attack angle of 10°, with a maximum value of 21m/s. This indicates that the proposed combination model should be more accurate in detecting the tolerance of bridges and more timely in detecting wind-induced vibration risks. In general, research methods have a significant technical value for the safety maintenance of bridge engineering.

Online classrooms are characterized by a large number of resources and a complex composition of student users, so how to mine the association between students’ learning habits, grades and other characteristics to achieve more effective resource provisioning and optimization. To achieve this objective, this paper proposes an Apriori classroom resource provisioning model that is optimized using the MPM algorithm. The model regards the data points as prime points, uses the MPM algorithm to track the trajectory of the prime points to avoid redundant polling, and then projects the data points onto the background grid, derives the derivation, and then projects it onto the data points to discover the correlation between the data and realize the effective allocation of classroom resources. According to the experimental findings, MPM-Apriori’s average BRPD and average RPD values are 0.32 and 3.33 when dealing with large-scale online classroom resource data, indicating improved optimality and stability. The average post-test mean score of each dimension of “Introduction to International Politics” is 0.378 points higher than the pre-test, and 66.6% of the indicators in the satisfaction survey on the effectiveness of classroom resource allocation have a satisfaction rate of more than 50%. It shows that the proposed online classroom resource allocation model has good application effects.

The research of Chinese and Japanese machine translation technology is of great practical significance for promoting and inheriting Chinese excellent culture and advancing the development of economy, education, and culture in China and Japan. In this paper, a cross-lingual keyword extraction machine translation model is investigated. The traditional model is improved on the basis of recurrent neural networks RNN and attention mechanism, and the problem of low information memory capacity of LSTM and GRU algorithms is optimized. By introducing the self-attention mechanism, important information can be filtered from a large amount of information, and a keyword recognition system can be constructed. The system covers three levels: word embedding layer, encoding layer, and CRF layer, and the model effectively utilizes the feature extraction mechanism of the Transformer model and introduces the bidirectional mechanism to obtain the richer semantic representation of word vectors. After the above strategies, the scores on the task of extracting the keywords of the discourse system with Chinese characteristics reach up to 89 in word inference and 83 in cultural adaptation, which effectively improves the performance of machine translation compared with other neural machine translators. The keyword “community of destiny” appears frequently in Japanese media reports, and the content involves the excellent cultural essence of the discourse system with Chinese characteristics, which has a benign influence on the dissemination process in Japanese society.

This paper formulates and adjusts investment portfolios based on machine learning techniques, adopts the B-L model after combining the GJR-GARCH-M model and the RBF model, combines the subjective view of the investor with the market equilibrium rate of return, and realizes the optimization of the implicit strategy in the management of the financial assets in the process, and finally analyzes the economic returns through the B-L model. The return of the asset portfolio under the improved B-L model is 0.37% higher than that of the market capitalization-weighted asset portfolio. The Improved B-L model’s asset allocation improves economic returns. In terms of cumulative return, the mean cumulative return of the improved B-L model is 50.7%, which is higher than the economic return of the regular B-L model and the equal-weight portfolio strategy.

In the process of rural revitalization, rural e-commerce is gradually realizing the development of scale and is transforming into the live broadcast e-commerce mode. This paper investigates and expands on the live broadcast e-commerce marketing model for agricultural products. Firstly, the strategy of the live broadcast marketing model is explored from the digital level, and three divisions of the e-commerce business model are discussed. The data were obtained by questionnaire survey, and the effect of live agricultural e-commerce on farmers’ sales was empirically analyzed by using the ordered Logit model, which provides a theoretical basis and support for the implementation of the rural revitalization strategy and the promotion of agricultural income. Secondly, the problems and deficiencies in the field of live marketing are analyzed in combination with the 4C theory. The current situation of live marketing is analyzed in the light of consumer characteristics, cost composition, and the convenience of the shopping process. Finally, targeted strategies and suggestions are put forward for the problems of the e-commerce live marketing model. The results of the Logit regression passed the significance test of 5%, which indicated that the agricultural products e-commerce live marketing model can Improve the income level of farmers.

This paper analyzes the engineering characteristics of loess and the factors affecting wet subsidence, briefly outlines the application effect of PP modular cisterns, and combines the two to design a PP modular cistern based on rainwater harvesting. Combined with the analysis of the pre-engineering conditions of the storage tank, propose the treatment method for wet subsidence loess foundations. Design the structure of the storage tank by determining the volume of the tank by comparing the difference between the inlet and outlet flow during the storage time integral. Simulate the modeling of storm floods and the process of emptying stormwater regulating ponds. Evaluate the geologic conditions for the construction of the regulating pond project. Compare the original investigation report with the results of this paper’s test of the engineering foundation’s wet subsidence coefficient. Set different thicknesses of bedding layers and calculate the settlement of the center of the pool under different humidity levels of the loess layer. Simulate the 2.3-hour rainstorm process, analyze the storage volume of the storage pond during the period, and calculate the cumulative storage volume of the storage pond. This project’s foundation loess wet subsidence coefficient is medium, and the actual additional pressure is much smaller than the starting pressure of wet subsidence. It is appropriate to use the soil bedding program (1.6m plain soil bedding layer and then rammed 0.4m thick 2:8 gray soil, with PP module seepage control). Combined with the local hydrological conditions, it is known that the peak present time of the peak outflow from the regulating pond TP =85min, and the volume of the regulating pond is 22543.47 m3.

Magnesium alloys, as the lightest commercial metal engineering structural materials, have good application prospects in the automotive, communication equipment, aerospace, and military industries because of their light specific gravity, high strength properties such as specific strength and stiffness, shielding from electromagnetic radiation, and easy recycling. In this paper, starting from the density and microstructure of magnesium alloy, the mechanical properties and corrosion resistance of magnesium alloy are proposed to measure the indexes, and the corresponding prediction model is constructed. Then, fine-crystal magnesium alloys are prepared sequentially by ingot casting and isometric channel extrusion, and then the microstructure of magnesium alloys is observed by scanning electron microscope and transmission electron microscope to extract the micro-parameters of magnesium alloys. A martensitic phase transition topology model was introduced to determine the macroscopic shape strain of magnesium alloy crystals. Complex network analysis is used to quantify the topological structure parameters of a magnesium alloy network in terms of degree, clustering coefficient, and average path length. Finally, the correlation between the macroscopic features and microstructure of magnesium alloy is explored with the obtained data, and the mechanical and corrosion resistance properties of magnesium alloy are analyzed through simulation experiments by combining them with the constructed prediction model. The microstructural topological characteristic parameters of magnesium alloys show that when the pressure is 50 kPa, the average path length after weighting decreases from 36.012 × 10−3 to 34.015 × 10–3, and the force transfer efficiency is gradually increasing. The AZ31 alloy samples obtained from casting in this paper have a capacitive arc diameter of about 1600 Ω-cm² and the best corrosion resistance among the tested samples.

This study introduces a dynamic graphic feature extraction algorithm rooted in the design principles of dynamic visuals. Utilizing visual perception algorithms, it establishes a priori frames to accurately extract image features through a minimized loss function, enhancing the precision of the extraction process. Concurrently, it advances a refined geometric constraint-solving algorithm that employs trigonometric columnar equations to facilitate the generation and transformation of dynamic graphics, thereby effectively capturing the dynamic attributes of geometric visuals. Additionally, this paper presents a specialized pathway for applying dynamic graphics, including a practical analysis of the dynamic illustration portfolio by Chinese illustrator Lu Tao. In terms of user satisfaction, the dimensions of interestingness and aesthetics garnered mean scores of 3.98 and 3.92, respectively, while the dissemination tendency dimension achieved a notably high mean score of 4.17. This suggests that dynamic illustration design possesses significant aesthetic appeal and can effectively encourage viewer engagement and sharing. Overall, the comprehensive evaluation indicates a generally positive reception among viewers, with all indicators, except for the emotional identity connotation—which scored slightly lower at 3.87—receiving ratings above 4. This reflects a broadly affirmative attitude toward the dynamic illustration portfolio within the realm of dynamic graphic design.

Cognitive computing technology realizes the processing of complex data and problems by simulating the human cognitive way, which is inspiring for the optimization of emotional expression in dance creation. In this paper, we propose a cognitive computing-based model for optimizing dance action emotions, using the improved 3DCNN model for dance action recognition and then CNN-BLSTM based on deep and shallow feature fusion for dance emotion recognition. The experimental results show that the students in the experimental group improved their movement emotion performance by 117% compared with the control group. Their professional level score was 8.42 points higher than that of the control group, the expert assessment score reached 43.98 points, and 82.5% of the students showed interest in dance learning. It shows that the optimization method for expressing dance emotions in this paper has good effects.

In the rapid development of the petrochemical industry in the context of the increasing number of large tanks, large tanks in the production and installation process encountered the first problem the pontoon plate welding deformation and weld seam is too large and other defects, through the construction of the ship plate welding special robotic arm of the intelligent perception and decision-making system to solve such defects. Summarize the Structure of crude oil storage tanks and welding process characteristics based on the ultrasonic distance measurement in the distance sensor to obtain the characteristic data set, combined with the distinct data and computer programming language to build the intelligent perception and decision-making system of the unique robotic arm for ship plate welding. They set the relevant parameter values based on simulation experiments on the welding of a particular robot arm perception and decision-making system for the application of example analysis. Compared to the traditional LSTM algorithm, the YOLO-v5 network-driven weld target detection algorithm has a 5.5% higher accuracy and a 9.1% higher success rate in time robustness evaluation. In addition, the welding decision model based on the DDPG algorithm possesses excellent computational accuracy, and the average error of each parameter in the welding decision of the ship plate is controlled within 5%. This study greatly improves the welding quality of the pontoon plate of crude oil storage tanks and provides solid technical support for the successful completion of the project.

Traditional Transformer machine translation cannot effectively deal with translation errors due to the lack of an explicit evaluation mechanism for the correctness of the target language text, which not only hinders the improvement of the translation quality of the target language but also makes the decoding process highly complex. This paper constructs a model for language translation based on decoding optimization. The problem of choosing the number of decoding rounds is transformed into a Markov decision-making process, and a reinforcement learning algorithm is used, which is based on the translation quality of the target-language translation and the number of decoding rounds obtained from the translation. The appropriate number of decoding rounds is selected according to the different complexity of the source language text to be translated, so that the translation model can achieve a balance between the translation quality of the target language translation and its corresponding time consumption. The optimization of the traditional Transformer machine translation algorithm has finally been achieved. The optimization effect is examined on the dataset. It is found that when the dimension is 1024, the number of parameters of the optimized model decreases by 16.03%, the average reasoning time is under 55 seconds, and the decoding time is always lower than that of the Transformer baseline model. The convergence trend of its Loss is similar to that of the Transformer model but with a faster and better convergence speed. On the six Chinese-English bilingual datasets, the average BLEU score of this paper’s model is 64.586. On the five Chinese-German bilingual datasets, compared with Transformer’s average BLEU value of 44.078, the score of this paper’s model is still the first one, which is 18.29% higher than that of the traditional Transformer model’s BLEU value, and it has a good language translation performance. The language translation model based on decoding optimization in this paper provides a useful exploration for machine translation optimization in terms of improving translation quality, enhancing Loss convergence speed, reducing the number of parameters, and improving decoding speed.

The museum incorporates historical resources, stores them in a systematic classification, and then presents them as objects for viewing and learning training. Intangible cultural heritage is the aesthetic crystallization of the wisdom and aesthetics of ancient Chinese people. Combining museums and intangible cultural heritage culture and developing the intangible cultural heritage cultural tourism industry of museums can fully utilize the advantages of museums in terms of location and dissemination, as well as achieve high-quality promotion of intangible cultural heritage culture. The digital era has brought new changes and numerous challenges to the development environment and spatial design methods of the intangible cultural heritage tourism industry in museums. This paper builds a museum intangible cultural heritage cultural tourism platform based on digital tour interaction technology. It considers the advantages of the development of the cultural tourism industry from the “museum + intangible cultural heritage” model, establishes a digital resource management system for museums, digital talent training, and management mode, and digital branding in light of the current development status and challenges of the museum intangible cultural heritage cultural tourism industry. Additionally, we will create a digital resource management system for museums, a digital talent training and management model, and a digital brand marketing system to boost the industry’s ecological development.

In recent years, with the performance improvement of deep neural network models, neural semantic parsing has entered a new stage and has been widely used in many fields such as classification tasks, speech recognition, linguistic annotation and syntactic analysis. In this paper, we design a strategy for recognizing and parsing English rhetorical devices using the neural semantic parsing method. In this paper, we first use the Skip-gram model to train word vectors, and then based on the convolutional neural network model to recognize the platitudes, metaphors, and similes in English text, and apply BiLSTM-Att model to acknowledge the English quoted rhetorics. The prediction accuracies of the CNN recognition model on platitudes, metaphors, and similes are 91.7%, 92.5%, and 90.2%, respectively, greater than 90%, indicating that the model can successfully recognize the platitudes, metaphors, and similes. The model can recognize platitudes, metaphors, and anthropomorphic rhetorical devices. Compared with the CNN+BiLSTM model, the precision, recall, and F1 value of the BiLSTM-Att model are improved by 0.22%, 11.44%, and 7.09%, respectively. Its recognition accuracy of English quotations under different similarity thresholds is very high, with 94% when the similarity reaches 50% and even 98% when the similarity reaches 90%. This suggests that the present paper BiLSTM-Att English quote rhetorical recognition model is adequate. This paper’s neural semantic-based English rhetoric strategy is paving the way for the development of natural language processing technology.

This paper aims to improve the effectiveness of civil engineering construction safety management (CSM)and ensure the safety of civil engineering construction. Firstly, an examination of contemporary CSM methods in the field of civil engineering in China is being undertaken. An innovative Civil Engineering Construction Safety Early Warning System (EWS) based on Bayesian Network (BN) principles addresses the unanticipated emergence of safety incidents during construction endeavors. Finally, a comprehensive evaluation model for civil engineering construction safety has been formulated, using the Bayesian framework to assess the efficacy of the previously mentioned Civil Engineering Construction Safety EWS based on BN. The incidence of safety-related accidents in the Chinese construction industry has consistently declined over the past decade, as the empirical findings indicate. Moreover, compared to international counterparts, the frequency of such incidents in China remains significantly below 600. Additionally, the Civil Engineering Construction Safety EWS created using BN consistently achieves a functional realization score exceeding 75 points, with the highest possible score reaching an impressive 93 points. Notably, through the utilization of the Civil Engineering Construction Safety evaluation model, which integrates Bayesian methodologies, it is discerned that machine tool quality and the placement of construction organization carry a substantial weight, each exceeding 0.3. Remarkably, the indicator of illegal operations is identified as having the highest risk level.

The United Kingdom is one of the countries globally known for its high level of integrity and has essentially developed a relatively comprehensive mechanism for preventing and addressing corruption. Effective management of conflicts of interest among public officials is a crucial aspect of corruption prevention in the United Kingdom. The United Kingdom emphasizes establishing a system of ethical norms that encompasses standards for public life more than other nations. By constructing a two-dimensional analysis framework for conflict-of-interest management tools and categories of public officials and utilizing the NVivo14 text analysis tool, we conducted a content analysis of the relevant portions in the British Code of Ethics text concerning managing conflicts of interest among public officials. The study revealed that conflict-of-interest management rules demonstrate a high degree of transparency orientation. The focus is on teaching public officials how to effectively handle conflicts of interest, not just prohibiting or dispossessing them of their private interests. The coordinated use of various management tools tailored to different conflict-of-interest scenarios results in effectively managing conflicts of interest among public officials.

At this stage, along with the rapid development of science and information technology, the era of artificial intelligence is gradually coming. This topic takes the travelogue text of leisure sports and rural tourism as the research object, uses the improved TF-IDF algorithm for keyword extraction, and analyzes tourists’ image perception of leisure sports and rural tourism. Then, we combine the tourists’ perceptions with the selection of relevant variables, set the fixed effect and moderating effect models, and use the OLS method to carry out regression analysis and heterogeneity analysis to verify the role of artificial intelligence in the development of leisure sports and rural tourism. The perception of tourist attractions (48.33%) and tourist facilities (20.87%) in leisure sports and rural tourism was the most impressive to tourists. It confirms that AI has a significant inverted “U”-shaped effect on the development of leisure sports and rural tourism. The development of leisure sports and rural tourism should conform to the new pattern of “AI+Sports Tourism”, highlight the “characteristics” of leisure sports and rural tourism, and let “AI+” become a “help” for the development of leisure sports and rural tourism. Let “Artificial Intelligence+” become a booster for the development of leisure sports and rural tourism.

With the deepening of cultural digitization in recent years, researchers have begun to explore the use of digitization to promote the innovation of traditional culture, trying to seek new paths for the promotion and revitalization of conventional culture under new visions, new disciplines, and new technologies. Based on the development history and current situation of Batik in Malaysia and Indonesia, this paper takes Malaysian Batik works as an example. It develops a Batik particle engine-generated painting system-”Particle Batik.” This system is innovative because it ensures that every particle is accurately set up according to the color samples and position of the Batik works during the creation process. When the search engine loads the next Batik artwork, all the particles will be resampled and generated according to the newly loaded artwork, and the trajectories of the particles and their resulting line traces will be continuously superimposed and fused on the canvas, thus forming a dynamic generative artwork evolving. The Particle Batik system enhances the multidimensional expressiveness of Batik, significantly contributing to the global dissemination and cultural value of Batik art. The system successfully integrates traditional handicrafts and modern digital technology and facilitates the mutual exchange and symbiotic development between traditional culture and modern art forms. Promoting the integration and exchange of Batik culture globally allows it to adapt and integrate more closely with contemporary society and culture.

The development of ChatGPT technology has made its application in the teaching field increasingly mature. This paper takes ChatGPT technology as the basis to study its important role in the cultivation of students’ English discursive ability. The description of ChatGPT, English discursive ability, and the application of ChatGPT in the teaching of English discursive ability provide theoretical support for this research. Based on the Business English course, the course design focuses on cultivating English discursive ability, and the teaching effectiveness of the course is evaluated after its implementation. Questionnaires and classroom observation were used to explore the effect of ChatGPT on students’ English critical thinking ability with the help of tools such as the Critical Thinking Emotional Tendency Questionnaire and the Critical Thinking Cognitive Skills Rating Scale. After designing and practicing the English discursive cultivation course in this paper, 74.8% of the students thought that the feedback effect of the ChatGPT teaching method was good. The average scores of the students in Classes A, B, and C taught with ChatGPT were 82.46, 80.37, and 80.06, respectively, which were greatly improved compared with Class D, which was taught with the traditional teaching method. After the teaching experiment, the mean values of the development of discursive ability were 286.82, 281.49, 283.52, 294.79, and 287.94. This significantly improved the students’ discursive emotional tendencies through ChatGPT.

Multimodal signals are susceptible to external environmental disturbances, such as weather conditions, electromagnetic interference, etc., which may affect the accuracy and stability of the data. This paper utilizes the characteristics of continuous and discrete wavelet transforms to study the wavelet threshold denoising algorithm in-depth, and by adjusting the parameters therein, it avoids the problem that the traditional threshold function is set to zero when the wavelet coefficients are smaller than the threshold value. Then, the deep learning algorithm in artificial intelligence is used to complete the signal adaptive denoising and realize the suppression of deceptive signal interference. The test results show that the adaptive denoising optimization model based on the deep learning algorithm has significantly improved signal characteristics compared to the original signal. Under a 15% noise environment, the average error of the model is less than 0.1, and the signal-to-noise gain of the signal is 5.0547 dB, which can reliably complete the interference suppression of both multiple interference and single interference and realize the adaptive anti-jamming optimization of the signal.

Against the increasing level of science and technology, such as the Internet of Things and Artificial Intelligence, the intermingling of museums and science and technology has gradually become essential in developing Chinese museums. Firstly, this study applies the bibliometric method to draw a knowledge map with the help of the CNKI database and uses CiteSpace software to visualize and analyze the research hotspots in terms of the number of publications, authors, institutions, keywords, hotspots, and so on. Secondly, a user satisfaction survey using the Kano model is conducted to confirm the reliability of the research hotspots. Finally, the trend in domestic museum digitization research is summarized according to the results of the analysis. The bibliometric and kano model analysis shows that technological innovation is still dominant in Chinese museum digitization research. Still, the sustainable development of museums in the future needs to fully consider user preference and engagement so that the exhibition experience will become a hotspot in museum digitization research. Analyzing the trajectory of Chinese museum digitization research and exploring its evolution path, core themes, and emerging important areas can provide a reference for subsequent museum digitization research and design.

Gyro is a new type of widely used micro-inertial sensor, which can realize high-precision, small-size, and anti-interference angular velocity measurement and is widely used in aerospace, platform drilling, autonomous driving, wearable devices, and cell phones. The study first analyzes the influence of the angle of control torque on the stability of the gyro and deduces the relationship between the gyro rotational inertia, spin angular velocity, feed angular velocity, and stability. Then, through the research of industrial gyro products research status, the factors affecting the precision of the gyro elaborated on the key technologies that need to be broken through in the process of gyro precision assembly and combined with the sequential stacking method to realize the gyro in the industrial close assembly. The results show that both the shape factor and scale factor are the influencing factors of gyro stability. The shape and position error of each part, as well as the coupling of the error, cause the uneven force on the motor shaft, the local stress concentration, and, therefore, local deformation, which ultimately leads to the offset of the motor shaft center, and the influence of the shape and position coupling error on the assembly precision of the gyro.

The regional unified electricity spot market plays an important role in promoting the optimal allocation of power resources over a wider range and cross-regional consumption of renewable energy. This paper examines the supply and demand uncertainty and price volatility of power grid agency power purchases in the context of the Beijing-Tianjin-Tangshan unified spot purchase. It delves into the specific mechanism of unbalanced costs in agency power purchase decisions and investigates the specific channeling methods of unbalanced costs in the dual-track system. Based on the dual-track unbalanced cost under the unified spot market, a dual-track power balance model is proposed based on the typical daily load curve, and a time-based unbalanced cost calculation model is designed. Using the typical daily electricity load data from the power supply enterprise in X province as an example, the calculation and simulation of unbalanced costs are carried out. The spot electricity price fluctuates between 0.25 yuan/(kW•h) and 0.45 yuan/(kW•h) in different periods. The overall unbalanced power purchased by the power grid in the load trough stage is only 6.24% of the total monthly electricity consumption. Still, the unbalanced cost in the study period is of a deficit nature, and its average value reaches −268 million yuan. The calculation method of unbalanced costs caused by agency power purchases clearly reveals the unbalanced cost-sharing mechanism in the context of the unified spot.

In this paper, the effect of temperature on the extraction efficiency of oil and grease from anaerobically fermented kitchen waste was investigated through the analysis of pilot tests. Based on the results of multifactorial experiments, factors such as solid-liquid ratio and extraction time that affect oil and grease extraction were conditioned by combining the principle of response surface optimization experimental design. The optimal conditions for anaerobic fermentation for extracting kitchen waste oil and grease were obtained through response surface optimization experiments. Using the microwave-assisted solvent method, the effects of solvent type, extraction method, microwave power, temperature, time, and solid-liquid ratio on the oil and fat yield were investigated, and the experimental model was obtained by using the response surface. It was found that the extraction time (50 min), extraction temperature (110 ℃~130 ℃), and solid-liquid ratio (1:15 (mL/g)) had a greater effect on the oil yield. The experimental values basically coincided with the predicted values of the model, indicating that the model is real and reliable and can well predict the extraction efficiency of high-temperature anaerobic fermentation on kitchen waste oil and grease.

The transformation of old neighborhoods is related to the quality of life and happiness of neighborhood residents, and the needs of residents must be fully considered in the development of transformation strategies. The problem to be transformed according to the needs is summarized in this paper, and the key indicators of the neighborhood’s spatial pattern are abstracted. Under the guidance of the perception-behavior correlation model, the correlation and regression curves between spatial indicators and behavioral density are estimated, and the optimal value of the correlated behavioral density is calculated to provide data support for intelligent transformation strategies. The CRITIC method and the cloud model are combined in the article to create an evaluation model for the transformation effect. Taking Kangfu Village in Nanjing as an example, the perception-behavior correlation analysis points out that each public space perception index has an extremely significant statistical correlation with residents’ spontaneous activity density and long-time activity density. The best-fit function curves were obtained through further curve estimation regression analysis, and the ideal value intervals were determined for each perception indicator. After the implementation of the retrofit strategy, the expectation value of the owners’ cloud evaluation of the “community intelligent retrofit” is 3.677, and the similarity between the comprehensive evaluation of satisfaction and the comparative satisfaction level reaches 0.905, which makes the evaluation result more satisfactory. There are sufficient reasons to believe that the intelligent transformation strategy proposed in this paper is generally accepted, and the formulation of the strategy based on the perception-behavior correlation is scientific.

This paper analyzes the integration process of the Kano model and the QFD model, combines the advantages of the two, and proposes a method of obtaining the importance of user requirements based on the integration method of the QFD and Kano model. Organize older people’s smart tourism needs and use the Kano model analysis method to categorize each demand attribute. Obtain the self-scoring importance degree of the elderly demand, calculate the satisfaction index of the elderly demand, and get the comprehensive ranking of the importance degree centered on the elderly demand according to the SII, DDI, Ti, and K values of the demand elements. Clarify the elements of smart tourism APP interface design services, establish the relationship matrix between the needs of older people and the service index, and build the service quality house of smart tourism APP interface design for the elderly. Use the smart tourism APP functional interface planning strategy to present the functional design of the APP interface. It can be found that those with higher importance ratings are mainly basic functional requirements, attraction guides, and personalization center, of which the four importance indexes of U6 personalization center are U61=4.72, U62=4.75, U63=4.16, and U64=4.23. The calculation results of the quality house show that the importance of the service elements of the interface design of the APP for senior citizens’ smart tourism is ranked as APP content professionalism, service attitude, recommendation rationality, and service quality. Degree > service attitude > recommendation rationality > after-sale reliability.

At present, the daily operation and maintenance of large-scale data centers such as banks in China, due to a variety of reasons, often brings about the problem of unexpected events that are difficult to locate. In order to ensure that the systems running in the data center work efficiently, this paper proposes a method for improving the operation, maintenance, and monitoring of financial data centers based on the cloud-native model. First, we sequentially cleanse and process the financial center data to eliminate any negative impact and generate a time-trending correlation of financial attributes. We then apply association mining to data center operation and maintenance, using stock information as an example to analyze the operational results in stock trading transactions. The result of correlation mining is component B index (up)⇒ component A index (up), support = 12/100, confidence = 12/19, which indicates that in 100 trading days, the number of days that the component B index and the component A index rise together is 12 days, while the number of days that the component B rises alone is 19 days. In the case study examining the impact of association mining in stock trading, on March 15, 2022, the stock price experienced a rise from 11.456 to 11.498 within a mere 0.1s. The financial data operation and maintenance system, using association mining, identified this as “abnormal,” demonstrating the model’s successful detection of abnormal behavior.

In recent years, the swift advancement of artificial intelligence (AI) has significantly propelled the capabilities of data generation, a pivotal technology underpinning AI development. This has led to remarkable innovations across various domains, including images, text, and speech. In this study, we introduce a sophisticated image translation network tailored for AI-driven art generation of landscape painting elements. This network is enhanced by integrating a self-attention mechanism with orthogonal Jacobi regularization, aiming to elevate the quality of the generated artwork. Furthermore, we developed a landscape style transfer model using the image above translation network to encapsulate elements of Chinese landscape cultural paintings. This model emulates the artistic process employed by human artists, effectively capturing the essence of the content and infusing the intended style. The efficacy of the generated images is quantitatively assessed through Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. Comparative analysis of the style transfer outcomes across three models reveals that the Generative Adversarial Network (GAN) model exhibits the lowest PSNR and SSIM values. Although the CycleGAN model achieves commendable style transfer, its visual impact remains less pronounced in comparison to the Wasserstein GAN (WGAN). Subjective evaluations of image quality and style fidelity between the generated images and the input stylized images indicate that the WGAN outperforms other models. It achieves an average content evaluation score of 4.11 and a style score of 4.2 across nine style transformations, surpassing the average scores obtained by competing models.

Integrating information technology with the curriculum has been closely watched by the educational community, and how well the two are integrated determines the effectiveness of mathematics education. This paper proposes an implementation scheme for mapping mathematical knowledge. Firstly, the Word2vec word vector model is used to acquire data from the original mathematical text, and then the Conditional Random Field model is used to extract the knowledge entities, and the Markov Logic Nets are used to extract the relationships between the knowledge entities. Then, the Path Ranking algorithm is utilized on the basis of entity alignment to realize the knowledge inference of the subject knowledge graph and mine the learning paths in the knowledge graph. Through the experimental and questionnaire methods, it was found that the math scores of the experimental class before the comparison experiment increased by 9.4337 points, which was significantly ahead of the control class. The average number of students who thought knowledge mapping teaching greatly improved their interest in math learning was 46.81%, while 31.29% believed that the new method had a relatively positive impact on their motivation to learn. It shows that knowledge mapping can be an effective method of teaching information technology.

In the context of the information era, the integration of industry and education, as a key direction for future educational reform, imposes higher standards on the quality of talent cultivation in colleges and universities. The study develops and investigates the hotel talent cultivation model and operation mechanism based on industry-education integration, starting from industry-education integration’s guiding ideology and principles. Then, in order to confirm the realistic feasibility of the hotel talent training model, the research object is selected, the relevant questionnaire is designed, and after the reliability test of the questionnaire, the questionnaire is distributed. The data are collected, and then the statistical analysis algorithm, including the difference test, correlation analysis, and regression analysis, is used to verify the examples. The data showed that corporate internship time, corporate internship environment, corporate internship management, corporate internship course planning, on-campus supervisors, and off-campus supervision were all significantly and positively correlated with satisfaction (Sig

The inheritance of intangible cultural heritage generally faces the situation of having no successors and difficulties in dissemination. The use of digital technology can overcome time and space limitations, expanding the dissemination effect of intangible heritage. A panoramic exhibition model of intangible cultural heritage is constructed using computer vision technology in this paper. In order to ensure that every pixel point in the image has a unique position, the perspective projection algorithm and the chi-square coordinate system are designed according to phase-forming geometry. Secondly, the optical information of each point is reproduced in the form of the image by using spherical projection, and the image alignment and image fusion smooth transition is carried out by improving the minimum deviation matching method of feature line segments based on chromatic aberration chunking. To convert the spherical panoramic image into a view that the user can explore, the inverse projection calculation is carried out. The performance of the model is tested after its construction is completed, and it is used to reproduce the panoramic view of the non-heritage contents of Xijiang Thousand Households Miaozhai in Guizhou. It is found that the matching error of this paper’s algorithm in the 20-frame scene test is close to or slightly higher than that of the SVD algorithm only in the 11th to 16th frame bits, and the rest of the frame errors are lower than that of the SVD algorithm by more than 0.04m. This paper’s algorithm is superior to OpenCV and Xiong methods by at least 0.1 points or more in all five scenes when testing the OG-IQA parameter. It can be concluded that the online exhibition content of non-heritage in Xijiang Miaozhai, Guizhou, produced using the model of this paper, has achieved a better communication effect and meets expectations. This paper provides innovative ideas and effective examples to demonstrate the use of computer vision technology in expanding the dissemination effect of intangible cultural heritage and promoting inheritance.

This paper explores the innovative integration of Augmented Reality (AR) technology into font design, emphasizing the user experience, visual performance, and spatial experientiality of AR interactive fonts. Central to this investigation is the deployment of AR-based calibration technology, which establishes a spatial coordinate system specifically for AR fonts. When synchronized with the camera model, these virtual fonts are seamlessly registered within real-world scenes. To enhance user engagement, gesture interaction design is incorporated, enabling interactive functionalities within the font system. The effectiveness of this design is evaluated through user testing, where the interactive performance is assessed based on audience experience post-implementation. The findings reveal that interactive fonts are highly effective in content display, achieving a user acceptance rate of 0.7659, and in content retrieval systems, with a rate of 0.7404. Audiences demonstrated a preference for conducting operations independently and showed a particular inclination towards font performance-based projects. The study concludes that the interactive font design project, which leverages augmented reality and gesture interaction technologies, holds substantial commercial potential.

This paper proposes state space modeling and Kalman filtering as the theoretical foundation to explore the impact of China’s monetary policy on the offshore RMB market and capital flows. In the state space model, the relationship between observable and unobservable variables is established, with the Hidden Markov Model representing the state vector as a first-order Markov process to estimate unobservable variables. Additionally, a variable parameter state space model is proposed to alter the relationship between explanatory variables and the dependent variable. Kalman filtering, as the core of the state space model solution algorithm, calculates the likelihood function through prediction error decomposition to estimate unknown parameters. The optimal lag of the model is determined to be 2 after constructing the VAR model in the empirical analysis, and the first-order autoregressive model is used to calculate variable parameters. The elasticity coefficient of the depth of development of the offshore RMB market on capital flows is the most significant variable, with a value of 0.96. Following this, the RMB exchange rate has an elasticity coefficient of 0.78.

Recently, the application and optimization research of intelligent algorithms in the monitoring and evaluation system of teaching mental health has been focused on. Many countries cannot avoid that with the rapid development of the urban economy, the mental health of Chinese people is ignored without knowing it. This phenomenon is more obvious in today’s campuses, especially in colleges and universities. Although the campus is equipped with a psychological counseling office, most students choose to give up because they can’t face themselves in a bad mood. Traditional random checks and individual conversations have no good effect. The intelligent algorithm developed in the new era is inevitably applied to the detection and evaluation of teaching psychological health. However, the intelligent algorithm at this stage cannot meet the requirements of teaching mental health monitoring and evaluation, because the data collection and processing are not completed through the matching intelligent algorithm, but directly through the algorithm DC method. The data collection will cause certain errors, and the data processing and output will inevitably be biased. This research is a kind of optimized intelligent algorithm system that can be applied to the monitoring and evaluation of teaching mental health. First, the research introduces and compares several modern intelligent algorithms used in teaching mental health monitoring and evaluation, and then analyzes the main influencing factors of monitoring and evaluation. These factors are integrated into the intelligent algorithm monitoring and evaluation system as key intelligent algorithm research objects, Finally, the optimized monitoring and evaluation system is applied in practice to obtain the corresponding imperfect information performance, and the final optimized result is obtained through further improvement. The results show that in most cases, a certain intelligent algorithm can not fully adapt to the detection and evaluation system, but the combination of different kinds of intelligent algorithms through influencing factors can give play to its advantages, and the final results can also be consistent with the actual. The proposed intelligent algorithm can not only be used in the monitoring and evaluation of teaching mental health but also reflect more monitoring and evaluation of teaching quality. The essence of the intelligent algorithm is to obtain complete data that can reflect reality by exploring the value of various information data. In the future, more joint intelligent algorithms will be proposed, which can adapt to more situations and achieve complete applications in teaching, security, medicine, and other fields.

This study integrates the microcourse concept into the realm of university music education, leveraging the benefits of microcourses tailored specifically for this discipline. It introduces a problem-solving-oriented teaching model for university music microcourses. The paper delves into the unique attributes of music education microcourse resources and addresses the need for sharing these resources across universities. To this end, it advocates the use of the PBFT consensus algorithm, supplemented by enhancements to the algorithm itself, in conjunction with data security storage technologies to bolster the protection of educational resources in university music micro-courses. Furthermore, the research evaluates the effectiveness of the microcourse model in university music education by examining the independent learning capabilities and problem-solving skills of the learners. The analysis focuses on the impact of learning behaviors on the outcomes under the microcourse framework. The dimensions of learners’ independent learning ability are assessed in terms of implementation and adjustment, goal-setting and planning, and application and reflection. The findings reveal mean values of 3.9865±0.68024, 3.7696±0.68595, and 3.6508±0.60124 for these dimensions, respectively. Notably, the dimension of implementation and adjustment scored the highest, indicating that learners are capable of timely adjustments to their learning status in alignment with their educational goals and plans. The study concludes that support from music education micro-courses significantly enhances learners’ independence in learning, and the synergistic effect of this model presents distinct advantages.

In recent years, the examination of literary creation through the lens of the natural geographic environment has emerged as a focal point in literary studies. This study designates China’s geographic environment as the independent variable and ancient Chinese literary creation as the dependent variable. We employ Pearson’s correlation coefficient to assess the appropriateness of the selected variables. Following this, a linear regression model is constructed using the least squares method to explore the relationship between geographic and environmental differences and ancient literary creation. The findings demonstrate significant positive correlations between the characteristics of topography, climate, and soil and the thematic content of ancient Chinese literature, with significance levels below 0.05. Specifically, the Pearson correlation coefficients are 0.509 for topographic features, 0.366 for climatic features, and 0.418 for soil features. Furthermore, the overall regression model exhibits an adjusted R² value of 0.235 and an F-value of 80.759. This research delineates the regional attributes that impact literary creation, thereby enhancing our understanding of the interplay between geography and literary output in ancient China.

Constructing a teaching model that meets the professional requirements and market demand has become an urgent task of teaching reform and innovation breakthrough. This paper proposes a PPCA teaching model for public relations based on the current and potential demand for public relations talent in the digital media era. Based on the proposed teaching model, the teaching practice is carried out at O University of H City. The research data was collected through questionnaires, and then the experimental data was statistically analyzed using two independent samples of t-tests and regression analysis to verify the effectiveness of the proposed model. The results show that the evaluation of the learning process based on the PPCA teaching model is between “good” and “excellent”, and the class that applies this model improves 3.64% more than the class that applies the traditional model in terms of the overall grade, learning attitude and interest, class participation, learning ability, and ability to acquire knowledge. Classes applying this model have higher scores in terms of overall achievement, learning attitude and interest, class participation, learning ability, and ability to acquire knowledge than classes in the traditional model by 3.646-17.856 points, which is superior to some extent. Meanwhile, the student’s active learning initiative (0.147) has the greatest influence on the teaching effectiveness of the PPCA teaching model in public relations. The study provides data that supports the innovation and practice of teaching public relations studies.

The development of student subjectivity constitutes a crucial dimension in achieving the comprehensive growth of students. This study examines the role of constructing model branches within higher education institutions and explores their influence on fostering student subjectivity. To this end, an enhanced K-means clustering algorithm, augmented by a particle swarm optimization technique, is employed to process the data of college students, thereby facilitating the development of model branches in these institutions. Additionally, the initial warning feature matrix within the collaborative filtering recommendation algorithm is applied to quantitatively assess student characteristic factors in the establishment of model branches, enabling the creation of an early warning system. The effect of model branch construction on the evolution of student subjectivity is subsequently analyzed through Gaussian process regression and partial least squares regression methods. The findings indicate that the extent of model branch development significantly impacts student subjectivity. Specifically, the average development level of student subjectivity in institutions with high-level model branches surpasses that in institutions lacking such structures by 17.255 points. Thus, the establishment of high-level model branches in colleges and universities emerges as a vital strategy to enhance student subjectivity and promote balanced and holistic student development.

In recent years, battery energy storage has garnered increasing attention in the frequency regulation field due to its rapid and precise output characteristics. The focus of this paper is on the control strategy for battery energy storage that is involved in primary frequency regulation and addresses the coordination control issues of different storage units when implemented on a large scale. A control method is proposed that considers the consistency of the State of Charge (SOC) in battery energy storage, which is involved in primary frequency regulation. The control of the battery energy storage system is divided into upper-level and lower-level control. The upper-level control uses model predictive control to obtain the total frequency regulation power of the energy storage station. The lower-level control allocates the corresponding power based on the capacity of each battery energy storage unit. It introduces a proportional integral adjustment term related to the average SOC to achieve SOC consistency control for each unit. Simulation results demonstrate that, regardless of whether the capacities of various storage units are identical, the proposed method achieves good frequency regulation performance, restores SOC to the ideal range, and ensures SOC consistency among different storage units. This approach aids the efficient and safe operation of battery energy storage systems.

This study seeks to enhance the integration of traditional Chinese cultural and artistic elements into contemporary architectural design, providing a rich source of inspiration. This paper investigates the connections between modern architectural symbols and traditional Chinese architectural and cultural elements. It identifies key characteristics of traditional architectural elements and proposes the integration of superficial structural features into contemporary designs, focusing on architectural space, form, and color. Utilizing Building Information Modeling (BIM) technology, this research designs a program that merges traditional Chinese elements with contemporary architectural practices. A specific test site was selected to implement this design. The study conducts a quantitative analysis of the space, form, and color characteristics extracted from the test site. The results indicate an overall symbolic value of the test building at 7.566. The analysis identifies the “stone lion” as an element with a high degree of alignment with traditional Chinese architectural elements, with nearly 50% of the participants rating its compatibility as 4 or above. Further quantitative analysis of the integration of color elements reveals that the color scale of the building’s main body predominantly ranges from 0 to 65, with a brightness level of 25 to 65, aligning with the aesthetic principles of traditional Chinese architecture.

In civil engineering management, under the background of carbon neutrality, there is a strong correlation and mutual constraints between cost, duration, and quality, and all civil engineering management must grasp cost control and multi-objective equilibrium. In this paper, the objective functions of duration, cost, and quality are constructed, the multi-objective equilibrium model of duration-cost-quality of civil engineering management is designed, and an improved non-dominant ranking genetic algorithm with elite strategy is constructed for solving the mathematical problem of multi-objective optimization. Finally, the model is used to analyze the case of a three-story mixed-structure office building, and it is found that the total cost of the model is 1089048 yuan, and the calculation is stopped when the programming cycle is 10096 times. Among them, scheme 1 has 146 working hours, a cost of 1.765 million yuan, and a quality of 0.95. Scheme 2 has 161 working hours, a cost of 1.693 million yuan, and a quality of 0.94. Scheme 3 has 176 working hours, a cost of 1.917 million yuan, and a quality of 0.99, and the specific plan can be selected according to the preference of the decision-maker. The model and algorithm’s effectiveness and matching are verified by analyzing actual data. This study enriches the theory of multi-objective optimization problems in engineering projects and provides a practical approach to managing project objectives.

Amidst the rapid advancement of artificial intelligence, computer vision algorithms have found extensive applications across various societal sectors. This paper presents the development of an automatic vehicle identification algorithm for crime-related scenarios, leveraging enhancements in computer vision technology. Initially, we refine the multi-scale feature fusion within the YOLOv4 architecture, subsequently substituting the standard convolution in the feature extraction network with depth-separable convolution to minimize parameter computation. Furthermore, we replace the conventional CIOU target localization loss function with EIOU to expedite model convergence. To address the issue of target vehicle detection failures, we incorporate the Kalman filter algorithm, ensuring precise tracking. Our experimental analysis, which utilizes both target detection and multi-target tracking evaluation indices, demonstrates that the modified YOLOv4 algorithm excels in recall, precision, and average IOU metrics compared to other algorithms, with a mean Average Precision (mAP) of 95.68% and an average detection speed of 0.039 seconds per image, satisfying real-time operational criteria. Vehicle tracking efficacy, compared using the YOLOv4-based detector before and after the modifications, shows significant improvements, indicated by a reduction in Identification Switches (IDS) across all video samples. This study introduces a robust method for the accurate identification and localization of vehicles involved in criminal activities, significantly enhancing case resolution efficiency.

This study pioneers the application of augmented reality (AR) in the realm of digital media, integrating AR technology with cultural education and artistic media concepts to forge a novel trajectory for digital media art creation. It delves into AR 3D scene construction technologies, employing calibration through the reconstruction of 2D image sequences, feature point extraction for spatial coordinate transformation, and 3D model development. Furthermore, it utilizes Level of Detail (LOD) models and texture mapping technologies to enhance visualization and interaction. The research culminates in a comparative analysis of traditional and AR-based media, evaluating differences in appeal and assessing functional capabilities. The findings indicate that AR-based media outperforms traditional media across several functions: media search (0.385), virtual design (0.424), immersive experience (0.466), real-time interaction (0.525), and user communication (0.396), with users expressing high satisfaction with these enhanced capabilities. This study not only diminishes the complexities associated with integrating digital media and AR technologies but also optimizes and innovates traditional methodologies.