In response to cybersecurity threats such as security breaches, data leakage, supply chain attacks, and ransomware viruses in digital network environments, more reliable cybersecurity architectures are needed to address these challenges. The article builds a zero-trust firewall applied to network security protection based on zero-trust architecture by integrating SPA single-packet authorisation technology and authentication scheme. Then SPA single packet authorisation technology with SM3 hash algorithm and SM4 algorithm for fully nominal encryption processing is constructed as a network security protection scheme, and the authentication protocol and trust evaluation algorithm are established by using hash and different-or function. In the simulation verification results, the communication volume of SDP client to complete one authentication is 981B, which reduces 27.17% compared to WaverleySDP overhead. The server in the SDP+SPA scenario still retains a certain amount of legitimate data after DDOS attacks and Web attacks, and receives only 53.47% of the traffic of the SDP scenario. The CPU usage of the client deployed with SPA is only 11.47 percentage points higher than that without SPA mechanism. The combination of SPA single-packet knocking technology and zero-trust architecture can achieve network security protection, and can also effectively deal with DDoS and Web attacks, and improve the performance of network security protection.

Consumer data is an important support for analysing and observing consumer behaviours in the era of digital marketing, and constructing models to predict consumer purchasing behaviours. In this paper, we select the Retailrocket consumer behaviour dataset based on real shopping websites, analyse the distribution of various types of consumer behaviour over time and other data characteristics, and gain insights into the behavioural habits of consumers when shopping. Based on the XGBoost algorithm in machine learning, a prediction model of consumer behaviour is constructed, and the genetic algorithm is used to optimize and improve the XGBoost algorithm.The XGBoost prediction model has a significantly better prediction performance than the LSTM prediction model and the LR prediction model when facing the data under the under-sampling data balancing method and the improved random under-sampling method based on the K-means algorithm. . The performance of the GA-XGBoost prediction model optimised by the genetic algorithm is significantly improved compared to the XGBoost prediction model, and substantially better than the LSTM prediction model and the LR prediction model. The accuracy and F1 value of the GA-XGBoost prediction model in the data under the improved stochastic undersampling method are 0.90865 and 0.92435, respectively, which are improved by 14.69% and 17.26% relative to the XGBoost prediction model. Meanwhile, the stability of GA-XGBoost prediction model is also significantly improved compared to XGBoost prediction model.

The digital era requires enterprises to pay attention to technological innovation and optimise ESG performance in the development process, so as to achieve high-quality development. Based on this, this paper proposes the hypotheses related to enterprise ESG, technological innovation and enterprise high-quality development. And construct the regression model of enterprise ESG performance and high-quality development. Basic statistics and correlation analysis are used to provide a preliminary description of enterprise ESG performance and high-quality development. Through the total effect test, the role of enterprise ESG performance on high-quality development is clarified. Through the mediation effect test, the role played by technological innovation between corporate ESG and highquality development is clarified, and the proposed hypotheses are verified, and the property rights, geographic and industry differences in the impact of corporate ESG performance on high-quality development are further explored by using robustness test and heterogeneity analysis. Finally, corresponding recommendations are made. Most of the enterprises selected in this paper have low levels of high-quality development, unsatisfactory ESG performance, and large overall gaps in technological innovation.The correlation coefficients of ESG performance (ESG) with corporate highquality development (LnTFP) and technological innovation are 0.402 and 0.335, respectively, and all of them are significantly and positively correlated at the 1 per cent level. Hypotheses H1, H2, and H3 are all valid.ESG performance and technological innovation have more significant effects on the highquality development of state-owned enterprises, eastern regions, and high-pollution enterprises.

Measurement and verification play a crucial role in flexible production, and with the development of technology, advanced measurement systems in flexible production systems gradually integrate fault diagnosis and prediction techniques to improve production efficiency. In this paper, a deep confidence neural network model, combined with the ISSA-VMD feature fusion model, is used to model fault diagnosis and prediction in flexible production of power systems. The training effect, prediction performance, feature extraction and fault diagnosis of this paper’s model in flexible production are evaluated and analysed through simulation experiments. The Loss value of this paper’s model converges to about 0.05 after 15 rounds of training, and has a good fitting effect on the training and test sets. The RMSE, MAE and R² of the model in this paper are 0.613, 0.371 and 0.988, respectively, which show good prediction performance. And the prediction results in the measurement system of power generation in flexible production are also more close to the real results. In addition, the DBN model incorporating ISSA-VMD feature fusion can completely separate the five fault signals, and the overall fault identification accuracy reaches 98.53% for the fault test set selected in this paper, which has strong diagnostic effect. This study provides more scientific and effective technical support for metrological verification in flexible production.

With the rise of major e-commerce, how to make more customer groups choose to buy items in their own websites is the goal that major e-commerce platforms have been relying on. Therefore, a set of personalised recommendation system that can intelligently explore customers’ needs comes into being. In this paper, a graph neural network model is used to sort out the multi-path fusion neighbourhood relationship among three objects: user, product and query. The utility matrix is established and the collaborative filtering algorithm is used to derive the user’s preference situation for commodities. Subtractive clustering is combined with fuzzy C-means to obtain the clustering centre of gravity and cluster e-commerce users. Graph neural network is introduced to ensure that the data sparsity of the user dataset is within a reasonable range. The practical application effect of the model is evaluated through simulation experiments and empirical analysis, respectively. In this paper, according to the age of the users, the users are clustered and analysed, and three clustering centres of gravity are obtained, which are (3.16, 32.73), (45.35, 40.25), and (14.03, 52.89), so the users are classified into three clusters, and the analysis of simulation experiments is carried out. The training effect of this paper’s model is fitted, and the adjusted R² = 0.8292, which shows that the accuracy of personalised recommendation is high. Meanwhile, comparing with other algorithms, this paper’s method reaches a recommendation satisfaction level of 100% when the number of learning times is 60, which is significantly better than other algorithms.

Supply chain finance innovation has a significant impact on regional economy. In this paper, blockchain technology is applied to supply chain finance business to improve the technology and security of traditional supply chain finance business. Drawing on relevant research results, we construct a blockchain-based supply chain financial innovation efficiency evaluation index system and measure the supply chain financial innovation efficiency using Malmquist index. A spatial econometric model is used to test the spillover effect and spatial synergy between supply chain financial innovation and regional economic growth, and to demonstrate the promotional effect of blockchain-based supply chain financial innovation on regional economic growth.The centres of the distribution curves of the kernel density function of the logarithmic value of GDP and supply chain financial innovation of the 30 provinces and regions are all shifted to the right, and the height of the main peak rises gradually.The 2013-2023 regional Moran’s index of economic growth and supply chain financial innovation are both significantly positive. The regression coefficients of supply chain financial innovation under the two spatial weights are significant at the 1% level, which provides strong data support for the view that supply chain financial innovation can promote regional economic growth in this paper.

The load of power supply has been increasing in recent years, and the scale of the power grid has been expanding. The impact of electromagnetic radiation on the lives of residents is also increasingly visible, and the electromagnetic environment around high-voltage AC transmission equipment has attracted great attention. Based on the principle of electromagnetic induction and Gauss theorem, this paper proposes the calculation method of electromagnetic radiation to evaluate the distribution law of spatial electromagnetic field around high-voltage AC transmission lines. Then the risk analysis of the electromagnetic environment around the high-voltage AC transmission line is carried out from the height from the ground and the presence of woods according to the measured data. Finally, according to the electromagnetic law of high-voltage transmission lines, the safety control technology to reduce the environmental impact of electromagnetic fields is proposed, mainly by raising the vertical height of the arc of the transmission line from the ground and reasonably designing the distribution of forest planting in the vicinity of the transmission line. When the vertical height of the conductor’s arc height from the ground was increased from 10m to 40m, the electric field strength and magnetic induction strength were reduced by 2.9kV/m and 2.35µT correspondingly, and at the same time, the electric field strength in the vicinity of the building was reduced by 71% at the most. The study proposes measures to effectively mitigate the electromagnetic impact by reasonably analysing the electromagnetic environment in the area where the UHV transmission line is located.

Aiming at the demand for scientific training of athletes in college sports education, this paper integrates data mining technology to propose athlete training and optimisation methods, and constructs an athlete training quality monitoring system and intelligent recovery assessment system. The traditional Apriori algorithm is improved by using multidimensional association rules, and multidimensional attribute mining is carried out on the collected data of athletes’ training data to search for frequent item sets and output strong association rules, so as to achieve the monitoring of training quality and adjustment of training programmes. Using the improved fuzzy decision-making method to filter out the optimal feature subset, and integrating the improved whale algorithm and random forest to achieve intelligent recovery effect evaluation. By carrying out the practice of training and recovery optimisation, it can be seen that the total score of physical fitness test of track and field athletes increased from 18.19 to 19.8 before the experiment, and the training quality was significantly improved. Various health indicators such as heart rate, blood lactate, serum creatine kinase, etc. gained significant improvement in adopting the recovery optimisation method of athletes in this paper. The mean values of training status, coaching factors, and personal situation satisfaction evaluation dimensions were 4.35, 4.425, and 4.38, respectively, and the training and recovery plan of this experiment was well received by the subject athletes.

Through the examination and calculation of each link of the dairy industry chain, we analyze the benefit distribution pattern of the dairy industry chain and highlight the necessity of optimizing the benefit distribution strategy of the dairy industry chain. The Shapley value method of the equilibrium of interests in game theory is chosen to study the benefit distribution strategy of each subject in the dairy industry chain under the cooperative game, and the model is revised by using the input factor, the risk factor and the correction factor, so as to further improve the rationality of the benefit distribution strategy. The research data were obtained by visiting the dairy industry chain in Xilingol League through field investigation, and the modified Shapley values of the herdsmen, middlemen, milk processors and retailers were finally obtained as 3976.43 yuan, 3839.31 yuan, 4175.53 yuan, and 3977.47 yuan after the modeling calculation, respectively. The comprehensive cost profit margin of each subject after correction is 2.17%, 1.82%, 7.43%, 7.68%, respectively, and herdsmen and milk processors are compensated in the benefit distribution strategy of this paper, and the amount of benefit distribution and the comprehensive profit margin of all the subjects in the dairy industry chain have been improved compared with that before the cooperation.

In this study, we construct an unmanned vehicle path optimization model based on fast extended random tree, and after kinematic modeling of unmanned vehicles, we introduce the artificial potential field method to improve the fast extended random tree algorithm, and apply it to the path optimization of unmanned vehicles. According to the swarm intelligence perception decision-making algorithm, the end-to-end unmanned vehicle decision-making model based on vehicle-circuit collaboration is constructed. The effectiveness of this paper’s driverless path optimization and decision-making model based on vehicle-circuit collaboration is examined. The waiting time for red light of this paper’s model is shorter than other path planning schemes, and the vehicle passing benefit at intersections is the highest. The passing benefit values of this paper’s model are 70.3% and 46.8% higher than Maxband scheme and Synchro scheme, respectively. In the right-turn simulation experiments, the main vehicle speed change shows a tendency to accelerate and the path is basically overlapped with the edge of the lane without offsetting the center of the lane. In the normal driving speeds of [14,38], the fuel consumption of the driverless vehicle shows an up and down trend, and the carbon dioxide emission varies with the fuel consumption. The total cost of traveling decreases with increasing speed.