The application of big data technology in each link of the supply chain can reduce the cost of each link, optimize the allocation of resources, and increase the benefits of enterprises. This paper builds a supply chain cost control program based on big data at three levels: pre-prediction, mid-control and post analysis. It analyzes the feasibility of inventory management program based on CPFR, combines inventory optimization elements based on supply chain coordination, and proposes sales inventory optimization program for supply chain coordination to optimize inventory resources. Combine the time series model and multiple regression model, unite the CPFR concept, synthesize the CPFR sales combination forecasting model, and design and form the resource optimization scheme for real-time adjustment of supply chain inventory based on sales forecast. Analyze and validate the forecasting effect of the combination forecasting model, forecast product sales on a weekly basis, and calculate product safety inventory and remaining inventory. Analyze the effect of enterprise supply chain cost control based on big data sales forecast. The proportion of procurement cost in the enterprise’s supply chain cost to revenue shows a decreasing trend, falling to 0.5107 in 2023, and the gross profit margin shows an increasing trend, growing to 0.5366 in 2023, which controls its cost and improves its gross profit. It shows that the enterprise uses big data technology to optimize the supply chain resources in the process of supply chain cost control, and the cost control effect is better.

This paper is based on the digital image processing technology, using the undamaged image information to restore and protect the frescoes. The discrete binary wavelet change is used to decompose and denoise the image signal. And decompose and filter the high-frequency component and low-frequency component of the image, choose different components, respectively, carry out coefficient transformation, and solve the OMP least-paradigm for different random matrices. The color space is selected, and the mural color space is channel decomposed according to the grayscale mode and restored separately. Establish an assumed datum for each independent face of the mural, establish a spatial coordinate system for it, realize the transformation of spatial coordinates, and realize the super-resolution three-dimensional reconstruction of the mural based on the generative adversarial network and the self-attention mechanism. Objective evaluation indexes and subjective evaluation indexes are established to compare the protection effect of different algorithms on murals. Compared with the traditional algorithm CDD, this paper’s algorithm improves the restoration time by 9.545~15.625 s, and the peak signal-to-noise ratio index improves by 1.35~4.769 db. In the results of the image extraction and processing, the calculated values of discrete curvature of the mural segments AB, CD, and EF ranges from -0.00945 to -0.00478, and the difference of standard deviation of the curvature from the target curvature is 6.477%. The approximate target curvature is obtained, and the algorithm has strong adaptive ability.

This paper takes the rural areas of Chongqing Municipality, a national integrated urban-rural comprehensive experimental area, as an example, and uses geospatial and spatial big data and information geography as a means to identify urban areas and rural areas of Chongqing Municipality in a refined way. GIS spatial analysis methods such as kernel density, hotspot analysis, and spatial autocorrelation are utilized to quantify features such as spatial agglomeration and diffusion characteristics and spatial distribution direction of compulsory education resources in rural areas. The Gini coefficient is used to conduct a comparative study of the imbalance of the amount of per-pupil educational facility resources within Chongqing Municipality, and to measure the development gap in the construction of compulsory educational facilities between regions. The study shows that between 2013 and 2023, the imbalance coefficient of compulsory education in Chongqing rural areas decreased from 0.3637 in 2013 to 0.0243 in 2023 for the secondary school stage, and from 0.3582 to 0.1952 for the elementary school stage, indicating that the imbalance coefficient of the layout of compulsory education resources in Chongqing Municipality decreases year by year, and the spatial equilibrium of the resources increases with it. This study provides effective ideas and methods to promote the structural adjustment of the spatial layout of compulsory education resources in Chongqing Municipality, and provides scientific decision-making basis for the relevant planning departments to calibrate the current planning and formulate the future planning.

Electricity theft management is closely related to the economy of electric power enterprises. This paper proposes a power theft estimation method based on semi-supervised learning and time series analysis prediction. The electricity consumption data of power theft users are extracted as time series data, and in order to achieve multi-step prediction, MMD is utilized to improve the LSSVR semi-supervised learning algorithm. In addition, a perturbation term is introduced to optimize the convergence effect of the artificial bee colony algorithm, and a time series prediction algorithm based on improved artificial bee colony is established. Bringing in the power theft monitoring process to identify whether the user has power theft behavior, using the real power consumption dataset as the experimental validation data, comparing the identification accuracy of the prediction model. Predict the potential power theft of each user, solve the optimization model with the goal of optimal economic efficiency, and determine the actual ranking order of power theft users. The improved time series prediction algorithm proposed in this paper has a global error of 0.0003 and 0.0027 in dataset 1 and dataset 2, respectively, with the lowest global error and the highest overall accuracy of PSE prediction. And the algorithm predicts the list of users to be scheduled is basically the same as the list of users determined by the real PSE, which can achieve the maximum economic benefits.

Teaching evaluation is the feedback on the teaching effect of teachers and the learning effect of students. It has become a critical link in colleges and universities teaching management and teaching inspection. This paper proposes and applies an improved BT-SVM multi-classification algorithm to the education evaluation model. By calculating the relative distance between classes, the error accumulation phenomenon existing in the traditional SVM when dealing with multi-classification problems is solved. A classifier structure based on an incomplete binary tree is constructed to automatically classify teaching data by gradually dividing the data set and training the SVM classifier. By calculating the decision function value of the test sample in the binary tree, the category to which it belongs can be quickly determined. The education evaluation model follows the principle of legal compliance to improve the quality and efficiency of model evaluation and ensure the rule of law construction in colleges and universities. The research results show that the error rate of the BT-SVM algorithm in machine learning is below 0.1%, the fairness index is between 0.1-2, and the prediction accuracy is 96%. It shows that the machine learning algorithm can effectively improve the efficiency of education evaluation work and has the principle of fair legal compliance.

The body language of dancers is an important tool for conveying emotions in the art of dance. In this study, the body movements of dancers are detected and tracked by Kinect, and the dance movement recognition model based on skeleton information and the dance movement emotion recognition model based on Attention-ConvLSTM are constructed respectively. After extracting and recognizing the dance actions, the emotion conveyed by each action is then recognized and measured. The action recognition accuracy of the dance action recognition model in this paper is 88.34%, which exceeds that of other action recognition models, and reaches the best result after only 40 iterations, and the recognition efficiency is also higher than that of other models. The emotion recognition model of the dance action emotion recognition model in this paper has the best emotion recognition effect, and the recognition rate is 98.95%. In the eigenvalue speed, the similarity between Excited and Pleased is the lowest (0.531). In Skeleton Pair Distance, the highest similarity between Excited and Pleased (8.439). For Skeleton Pair Inclination, the shortest distance between Excited and Relaxed is 0.503. For Speed, Emotional Relaxed, Sad and Miserable are easily confused with each other. For Skeleton Pair Distance, the emotions Pleased, Relaxed and Happy are easily confused with each other. For Skeletal Pair Angle, the emotions Mixed can easily be confused with the Happy category of emotions. Skeletal points of the legs have a greater influence on emotion expression. Finally, the construction of dance emotion expression mechanism is realized with the movement changes of head, hand, leg, waist and torso.

More and more problems are revealed in the process of popularization of higher education, especially the imperfection of the quality assurance system of higher education, which restricts and hinders the development of colleges and universities to a certain extent. This paper uses structural equation modeling to analyze the influencing factors of higher education quality. And consequently, it combines digital technology to build a higher education quality assurance system. Take a university as an example to practice, through the higher education quality assurance system evaluation index selection and empowerment, combined with the fuzzy comprehensive evaluation method to establish an evaluation model, to assess the effectiveness of the practice of the educational quality assurance system of the sample university. The management level (0.4380) and faculty (0.1472) of the university have the most significant influence on the quality of higher education. Under the constructed higher education quality assurance system, the comprehensive scoring result of the sample colleges and universities is at a good level (8.227), with the highest quality level in the dimensions of teaching effectiveness (8.7341) and student development (8.7000), which indicates that the digitization-based higher education assurance system is able to effectively ensure and promote the quality of education in colleges and universities.

Accompanied by the increasing consumer quality and the exploration of enterprises centered on user experience, the new retail model has emerged, and the emerging retail model also plays an important role in enhancing customer loyalty. This paper establishes an experiential sensory marketing model by combining perceptual theory and emerging technology from the basic features of the new retail model. Multiple linear regression model is used to study the influence of experiential sensory marketing mode on customer loyalty, and the correlation coefficient is used to analyze the correlation between the two. The correlation coefficients between the experiential sensory marketing model and customer loyalty range from 0.457 to 0.669, which is a moderate correlation. For every 1 percentage point increase in experiential sensory marketing mode, there is a significant increase of 0.647 percentage points in customer loyalty, and the average score value of customer attention under experiential sensory marketing strategy is 4.31 points. The sensory marketing strategy in experiential retail environment needs to improve the marketing standardization system, relying on professional service platform to improve the customer’s emotional experience, and then enhance customer loyalty.

Most areas in Hunan Province are rich in shale gas blocks, and their shale gas reservoir physical properties, geological characteristics, and enrichment rules need to be further studied. The article chooses the five # logging data of the Xiaoyanxi Formation in Anhua, Hunan Province, as the research object, preprocesses the logging data by curve environmental influence correction, curve reconstruction, and normalization, calculates the total organic carbon content and mineral composition change of shale gas by multiple linear regression, and uses the multi-mineral content calculated by optimization algorithm combined with the volumetric model to realize the matrix porosity of the variable skeleton. Then, the differential equivalent medium, self-compatible approximation, and K-T models were used to calculate the shale rock skeleton modulus. Then the shale gas reservoir petrophysical model was constructed. The adsorbed gas and free gas of the shale gas reservoir were solved separately to obtain the total gas content of the shale gas reservoir. The average TOC content solved by the model is 1.79%, which is only 2.23% higher than the absolute error of the actual data. When the volume fraction of the organic matter mixture increased from 0 to 0.25, the relative change of the longitudinal and transverse wave velocity ratio was only 0.87%. The shale gas content in Anhua Xiaoyanxi Formation 5# in Hunan Province ranges from 0.87 to 8.41 cm³/g, significantly higher than the lower limit value for shale gas industrial development. Recorded well data can clarify the reservoir’s physical characteristics of shale gas in Hunan Province and provide data support for exploring shale gas.

Supply chain optimization configuration contributes to the improvement and development of enterprise business application system. This paper takes the supply chain of manufacturing enterprises as the research object and analyzes the economic benefits of supply chain optimization of manufacturing enterprises. Aiming at the current development environment of enterprises, it puts forward the necessity of the development of enterprise supply chain flexibility, and establishes the overall supply chain flexibility model that contains the supply flexibility of the supply chain, the manufacturing flexibility and the distribution flexibility of the distributors. Simplify the total cost model of supply chain and establish the demand-driven supply chain optimization model. Analyze and validate the parameter settings of the improved particle swarm algorithm, and obtain the operating efficiency of the improved particle swarm algorithm with the changes of ordering cycle and inventory capacity. Combined with the sample enterprises, analyze the financial savings of each link after supply chain optimization. Further measurements show that after supply chain optimization of Company R, the saving percentage is 10.24%, and the annual saving amount is 562,807 yuan, with obvious economic benefits.