Artificial intelligence technology has brought new breakthroughs to the field of machine translation.
Through the introduction of cloud computing data aggregation algorithms, this paper proposes two
translation methods, namely rules and corpus. At the same time, the translation system is studied
with English as the research object. Based on the statistical translation method, the basic framework
of the English translation system (ETS) is designed, including a preprocessing module, a source
language matching module, a statistical decoding module, and a target translation generation module.
And by introducing the k-means algorithm and the optimized k-means++ algorithm, ETS was studied.
Combined with cloud computing technology, the ETS had a powerful data storage platform. Finally, a
simulation experiment was carried out to test the performance of the system from three aspects: the
average number and type of translation results, the success rate of translation in different languages,
and the speed of online translation. First, the comparison method of the two algorithms was used to
test them separately. The data showed that with the increase of vocabulary, the average number and
types of translation results in the ETS have also increased. The system developed by k-means++
algorithm was 5.03 items higher than the average number of translation results of the system
developed by k-means algorithm, and 1.93 items higher than the average number of categories.
When testing the success rate of translation in six languages, the data showed that the average
success rate of English translation in different languages remained at 94.34%. It was concluded that
the success rate of using k-means++ was higher than that of k-means algorithm, and the k-means++
algorithm could make the translation system produce better results when running. Finally, the online
translation speed of the common ETS and the ETS based on cloud computing technology were tested.
The average online translation speed of the system under cloud computing technology was 40.46b/s
under different translated text volumes, while the average online translation speed of the common
system was 26.47b/s. It indicates that the efficiency of the ETS on the basis of cloud computing
technology is high and the data processing capability is strong, which makes the system far more
efficient than the ordinary translation system in operation and has obvious superiority.

The continuous development of power market puts forward new requirements for power grid operation and power supply quality. Under this background, if electric power enterprises want to achieve sustainable development, they must strengthen management and technological innovation to improve their competitiveness. Currently, the distribution network construction is still dominated by the traditional cable transmission method, which has many drawbacks and can hardly meet the requirements of modern power production for communication capability. Digital twin technology is an advanced intelligent control method, which can effectively integrate information in complex systems. It can use data-driven to achieve real-time monitoring, fault detection and analysis functions, which can better help users improve the efficiency and security of power use. The intelligent communication network has the characteristics of good real-time, strong scalability and can quickly adapt to different environments, different devices and application scenarios. By building a complete set of distributed automatic control system, the goal of stable, reliable, efficient and energy-saving power system can be achieved. This paper presented the relevant calculation formulas of energy consumption and time delay in smart grid, and the effectiveness of the formula was verified through simulation. By combining the principle of heterogeneous sensors, a new intelligent integrated management system for remote monitoring of distribution lines was designed to realize a series of functions such as centralized meter reading, load forecasting, inspector positioning, online diagnosis, etc. of the intelligent dispatching center, which provided a theoretical basis for the optimal dispatching of the smart grid. This paper compared the traditional distribution network monitoring system with the distribution network digital twin monitoring system based on intelligent communication network. The results showed that the time delay and bit error rate of the optimized detection system had been significantly reduced, and the success rate of packet reception had increased by 10.4%; in addition, it could achieve higher accuracy and security and reduce operation

The combination of the content of Civics and professional courses in colleges and universities is one of the important contents of general education in colleges and universities in recent years. The article introduces machine learning algorithms into this field to explore the optimization path of western economics course civics in colleges and universities. After developing the resources of western economics course civics, the content generation model of western economics course civics is constructed by using the content generation algorithm based on pre-training model and keywordawareness, respectively. Then the text generation performance of the proposed content generation model is examined. The results of the teaching experiments of the experimental group and the control group are compared to explore the effectiveness of this paper’s machine-learning-based content optimization and practice path of western economics course civics on improving students’ performance. The F1 values of this paper’s content generation model on the ROUGE-1, ROUGE-2, and ROUGE-L indicators are 39.06%, 24.79%, and 36.65%, respectively, which is the optimal performance among all models. The students in the experimental group and the control group had the same level of Civics in Western Economics course before the experiment. After the experiment, the two groups produced a score difference of about 5 points on the 8 content dimensions, and the p-values were all less than 0.05. The experimental group’s postexperimental performance in course civics were all significantly improved (p0.05). The content optimization and practice path of western economics course Civics based on machine learning can significantly improve the learning effect of students.

Curriculum Civics reform in physical education should keep pace with the times and actively explore modern technical means. This study addresses the problem of regulating the elements of Civic and political education in physical education, and establishes a mathematical model of multi-objective optimization and regulation by comprehensively considering the various factors and constraints involved in the problem. In order to further optimize the regulation results, an improved two-population genetic algorithm is used to solve the model. Taking the physical education course of a university as an example to analyze, the design algorithm of this paper is compared with the experiments, and the improved two-population genetic algorithm completes the convergence in 300 iterations, and the degree of adaptability is improved by 2.04%, which has the characteristics of strong global search ability and fast convergence speed, which proves that the improved two-population genetic algorithm has a certain degree of superiority and validity. The utilization rate of the elements of ideology and politics education in the experimental solution results reaches 0.87, and other factors meet the actual needs of sports teaching, and the method of this paper can realize the intelligent regulation of the elements of ideology and politics education in sports teaching.

In the process of increasing the service capacity of digital infrastructure, the complex data generated by data terminals grows rapidly, which puts forward higher requirements for complex data task scheduling preprocessing. In this paper, based on particle swarm algorithm and improved artificial fish swarm algorithm, a hybrid particle swarm multi-objective optimization scheduling algorithm applicable to task scheduling and processing of complex data sets is designed. Then we design a reasonable expression method for the particle position and adaptation value algorithm in the multiobjective optimization algorithm, and put forward the pre-search strategy of the particle swarm algorithm to improve the search performance of the particles in the algorithm. Finally, the algorithm is equipped to construct a task scheduling and processing model for complex data sets. The results show that the hybrid particle swarm optimization algorithm established in this paper outperforms the comparison model in terms of load balancing and processing time, and is able to keep the system CPU utilization between 0.350-0.491 in the simulation experimental environment. It is also found that the application of the task scheduling and processing model in this paper can increase the power of photovoltaic and wind power generation in the grid system and reduce the operating cost of the grid system. This study provides an effective reference method for the processing of data and task scheduling in various types of complex systems, and brings new ideas and directions for research in related fields.

This project defines and generalizes the groundwater flow and soil deformation in geotechnical engineering by combining the hydrogeological conceptual model. Based on the fluid-solid coupling theory, a coupled model of groundwater flow and soil deformation is constructed, and the SUB program package in MODFLOW simulation software is selected to numerically simulate and analyze the relationship between groundwater flow and soil deformation in the study area. In layer2 and layer3, the trend of groundwater level decline and soil compression is shown, and the other layers4~layer9 also show the same situation, due to the over-exploitation of groundwater, resulting in serious decline of the soil in the study area, which reveals the causal relationship between groundwater flow and soil deformation at present.

Random forest algorithm is a kind of integrated learning algorithm with strong universality, high prediction accuracy and not easy to overfitting, and strong stability in stock index prediction application. This study constructs a stock index prediction model based on the random forest algorithm, and predicts the stock index futures price state according to the iteration of the decision tree in the random forest algorithm. Then we propose to use the regular term and ARMA-GARCH time series forecasting model to optimize the overfitting and large forecasting errors in the Random Forest model to achieve the construction of stock index forecasting optimization model. It is verified that the average absolute error of the random forest optimization model proposed in this paper is only 0.0316 in stock index forecasting, and the robustness in stock index forecasting is excellent. The empirical application results of stock index forecasting show that the accuracy of this paper’s model for CSI 300 and CSI 500 indexes is above 90%, and the total return of the strategy during the backtesting period is relatively high. The practical application of the stock index forecasting model proposed in this study has the value of further research, which can provide reference and guidance for investors.

Financial risk has a greater impact on the operation and development of enterprises, and accurate prediction of financial risk has become an industry demand, so as to better help enterprises avoid possible financial risk. The article establishes an enterprise financial risk prediction model based on the random forest algorithm, and fills in the oversampling of financial data through the SMOTENC algorithm, and realizes the downsizing of financial data by combining with the KPCA algorithm. Based on the enterprise financial risk characterization index system, the financial data of 358 listed enterprises were selected to carry out model validation and application analysis. The accuracy of corporate financial risk prediction based on Random Forest can reach up to 94.17%, and the average value of the overall time efficiency of the model is 0.68%, which is faster than the comparison algorithm in terms of financial data processing capability. Based on the results of financial risk prediction, the changes in corporate profitability, operating ability, solvency and development ability can be analyzed in depth, providing data support for enterprises to formulate preventive measures for corporate financial risk.

The article uses web crawling to obtain public opinion data after the Sichuan Luding MS6.8 earthquake and preprocesses this data. Aiming at the limitations of the traditional LDA topic model, an improved topic model based on LDA, TT-LDA, is proposed. the BERT model is used to encode the public opinion data, and on the basis of the BERT embedding, the BiLSTM model is used for contextualized word representation for deep feature extraction to complete the modeling of public opinion sentiment evolution. Combining the crawled data and the model, we analyze the public opinion after the Sichuan Luding MS6.8 earthquake. Three days after the earthquake, positive sentiment, neutral sentiment, and negative sentiment increase to 488498, 466832, and 516560, respectively, a total of 1471890 sentiment data, and after time evolution, the sentiment polarity intensity increases from -0.178 to – 0.886, indicating that when the official announcement of the number of casualties of the accident is made, the netizens’ negative sentiment fully erupts to show the post-earthquake public opinion sentiment evolution process.

E-commerce classroom teaching is an important means to improve the quality and teaching effect of e-commerce teaching, and effective interaction in teaching is an important carrier of e-commerce teaching classroom activities. This study combines pan-reinforcement learning and reinforcement Q learning algorithms to recognize and analyze speech data in e-commerce teaching classroom, and uses head posture estimation algorithm to recognize interactive behaviors in e-commerce teaching classroom video, and combines the video and speech interaction data to get the e-commerce teaching interactive behavior recognition model. The model is then equipped with web application technology to design a visual analysis system for e-commerce teaching interaction, and the optimization strategy of e-commerce teaching interaction is realized with the assistance of this system. The results of the study show that the interactive behavior recognition model proposed in this paper can accurately identify the interactive behavior of teachers and students in each course of e-commerce teaching. It is also found that after the implementation of interaction optimization strategy in college e-commerce teaching classroom, the frequency of effective interaction behaviors of teachers and students increases from 351 to 391 times, and the meaningless classroom silence time is reduced. And the learners’ cognition of knowledge is also improved under the influence of the improvement of the effect of interactive behavior. The visual analysis system of teaching interaction proposed in this paper based on reinforcement learning algorithm is of great significance for optimizing the effective interactive behaviors of teachers and students in e-commerce teaching and improving the degree of students’ knowledge cognition.