Virtual reality technology, as a trend of the development of the new era, has a profound impact and influence on traditional art design teaching. This paper combines virtual reality technology to construct a classroom teaching interactive analysis system to help art design teaching reform. All the objects required for the art design teaching scene are modeled in 3Ds Max, the mapping of each object in the scene is beautified using Photoshop, the FBX format file with animation effect is output, and Unity3D is used for the design and development of the VR part. Subsequently, a quantitative coding form for classroom observation, methods and rules for behavioral data collection, and a classroom migration matrix for analysis were designed to analyze the teaching interaction behaviors in the smart classroom classroom from the micro level. The characteristics of the teaching model in the art and design classroom were captured at the macro level based on the S-T analysis. A teaching experiment was conducted in a school’s art design program after the FIAS analysis. The improved art design classroom interaction increased for the blended teaching mode, and the average of the pre and posttest scores of the experimental class applying this model were 74.18 and 84.37 respectively, and there was a significant difference, which was a significant improvement over the control class. This study provides new ideas and methods for the teaching reform of art design majors in higher education institutions.

In this paper, information theory and information metrics are used to obtain an approximate estimation of linguistic information entropy. After that, the binary model of large-scale corpus and foreign language words is established, N-Gram model is constructed, and the information entropy of modern foreign language speech is estimated. Finally, the N-Gram model was utilized to statistically analyze the results of interpreting information loss, comparing the rate of information transfer in foreign language speeches and the subjects’ interpreting performance. The results showed that the phenomenon of information loss was prominent, with many types of loss, high frequency, and serious loss situations. T assertions had 8.61%-18.95% of propositional information loss, 3.0%-7.6% of constituent information loss, and 49.68% of overall loss. The data on the information loss of each language component showed that TPO and SPE presented the most and the least frequency among the 6 propositional information losses, which were 67 and 1 times, respectively. Among the 13 types of information component loss, TFLS presented the highest frequency and TLE and SFLO presented the lowest, with their losses of 55, 1, and 1 times, respectively. In the interpreted material of English speech, the rate of narration was 2.25 words per second and the average rate was 13.45 bits per second. Among the T assertions, numbers S7, S4, and S9 have the highest propositional untranslated rate (21.8%), propositional mistranslated rate (23.5%), and propositional information loss rate (44.5%), respectively; the corresponding lowest values are at S4 (2.7%), S5 (1.8%), and S4 (2.8%).

Target tracking is a fundamental task in the field of computer vision, which has a wide range of applications in real-life video image signal processing. This paper proposes target tracking optimization technique based on the principle of multi-scale convolutional neural network and multitarget tracking algorithm. The basic structure is designed using VGG16 network, the ROI align method is used to reduce the number of features for feature fusion, and the improved Hungarian algorithm is adopted to associate the fused features and obtain the target tracking results. In the tracking performance experiments, the target tracking optimization technique in this paper is more discriminative in terms of extracted features, and also has higher tracking results under challenging factors such as background clustering (BC), scale variation (SV), and out-of-view (OV). As for the target tracking experiments on mobile network video images, the average tracking accuracy and average tracking success rate of this paper’s method are 97.89% and 96.02%, which are better than DS_v2 and FFT16, and the average error between the target tracking results and the target’s actual motion trajectory is 4.12mm, while possessing the smallest error amplitude.

The traditional Japanese language teaching mode in colleges and universities has been unable to meet the requirements of Japanese language majors in various industries, and colleges and universities should use certain methods to carry out a reasonable reform of the teaching mode of Japanese language majors. Firstly, an error correction model based on UniLM model framework is proposed, using natural language processing technology to extract features, and fine-tuning training for the model after initialization. The model framework based on UniLM+CRF and the seq2seq model framework based on UniLM are built to realize the Japanese text grammar error annotation task and the Japanese text grammar error correction task respectively. Then a multi-task learning error correction method is proposed to integrate the grammar error labeling task and the grammar error correction task, so as to improve the accuracy of the error correction model. Finally, a specific Japanese grammar error correction system architecture is designed, a Japanese language knowledge base is established, and utterance synthesis rules are formulated to realize the innovative teaching of Japanese language in colleges and universities. The average grammatical error correction precision, recall, and F1 value of the model in this paper reached a good level in the students’ Japanese composition correction. The error between the average score of teacher correction and the average score of model correction is only 0.19 points, and the related experiments show that the innovative teaching model studied in this paper can effectively improve students’ mastery of Japanese syntactic ability. The above data illustrate that the Japanese error correction system based on UmiLM framework designed in this paper has certain application value and can realize the innovation of Japanese language teaching mode.

With the arrival of the aging society and the continuous improvement of human civilization, people pay more and more attention to the quality of existence, quality of life and happiness index, and the elderly service is becoming a hot issue of social concern. The article proposes a set of intelligent monitoring system for the elderly based on ROS service robot in the context of big health. The system is based on the machine vision following module to design the neural network-based fall detection module and the monitoring module of power consumption abnormality to realize the remote contact method between the elderly and the guardian. The article measures the quality of life and happiness index of 600 elderly people in old age through questionnaires, and systematically understands and comprehensively grasps the influence and effect of the monitoring system proposed in this paper on the quality of life and happiness index of the elderly from seven target levels and several index levels, including the quality of healthy life, economic quality of life, family quality of life, social quality of life, cultural quality of life, personal value realization and sense of identity and belongingness , with more than 97% of the elderly believing that the quality of cultural life has been improved by utilizing this AI intelligent machine.

With the access of multiple renewable resources to virtual power plants, hundreds of millions of power time series data are generated every day. A sparse learning-based power data compression and reconstruction processing method is designed in the study, which effectively solves the problems of low computational efficiency in the data processing centre of the virtual power plant and the waste of storage resources. According to the vector principal component analysis method, the power data are compressed. Then the data reconstruction network model is constructed based on sparse learning to achieve the reconstruction of power data. The experimental test results show that the median absolute errors of reconstruction of active and reactive power data are 4.05 MW and 0.885 Mvar, respectively, and the percentages of absolute errors are not more than 5%, which makes the reconstruction performance highly stable. The method achieves high-quality power data compression and highprecision reconstruction processing, which is of great significance for improving the computational efficiency of the virtual power plant data centre and accelerating the digital transformation of the power grid.

In this paper, the modelling and fault monitoring methods of virtual power plants are investigated. Aiming at the risks faced by the virtual power plant, a virtual power plant dynamic model based on BPNN is proposed, which uses neural networks to establish the relationship between the uncertainty factors and the technical parameters of the virtual power plant, and adjusts the technical parameters of the virtual power plant in real time according to the size of the uncertainty factors. The technical parameters of the virtual power plant are optimised to obtain the parameters that maintain the optimal performance of the virtual power plant. At the same time, in order to be able to comprehensively monitor the failure of the virtual power plant, play a role in early warning, starting from the real-time database of the equipment, the data from a variety of sources to the equipment as the centre of the fusion. Multiple state parameters of the equipment are tracked in real time and displayed in the form of trend graphs, which completes the analysis of the parameters of the fault characteristics in the database and achieves a nonlinear mapping from characteristics and signs to the cause of the fault and the type of fault. Based on the BPNN dynamic model, the SMAPE is 6.51%, and after using the model constructed in this paper to monitor the virtual power plant, the failure rate of the virtual power plant decreases month by month, and the failure rate is much smaller than that before the model is used. It verifies the good performance of the method of this paper, and also shows that the method of this paper has a broad application prospect in the field of fault monitoring and warning of virtual power plant.

This study aims to quantitatively analyze the impact of agricultural scientific and technological progress on rural economic growth. The contribution rate of agricultural scientific and technological progress in place A is measured through beyond logarithmic function model setting, data collection and processing. An agricultural carbon emission measurement model was built, in order to analyze the dynamic changes of total carbon emissions in place A. In addition, the gray correlation analysis algorithm was used to rank the correlation between agricultural science and technology indicators and economic growth in place A. Finally, a regression model is designed to analyze the impact of scientific and technological progress on rural economic growth. The coefficient of the t2 term of the contribution rate model of scientific and technological progress is 0.0013, which is greater than 0, indicating that there is scientific and technological progress in 2017-2023 in place A. The carbon emissions in place A decrease year by year with scientific and technological progress. All indicators in agricultural science and technology inputs can promote agricultural economic growth, and the gray correlation value in descending order is, T3>T9>T8>T1>T6>T4>T7>T2>T5. Scientific and technological progress has a different degree of promotion for the rural economic growth in place A.

In the development process of China’s power system, automatic monitoring mode has become an important development direction. In this context, how to achieve real-time monitoring of power data in the system has become an urgent problem. In this paper, considering the current range, the controller with input current is selected to collect voltage and current data signals and detect their circuits. Through metadata integration, the semantic integration of data expression is solved to achieve the management of electric power metadata. The collected data are sequentially accessed, handled and processed, the calibration of the voltage and current signals is agreed upon, the AD-converted values are read and the electrical parameters are calculated. Using the communication protocol IEC61850, the processed electric power data is uploaded into the server to complete the electric power data reading and monitoring tasks. The real-time management platform of intelligent maintenance power box constructed in this paper is used to monitor the abnormal power data. The abnormal power data appeared at different times, and the peak value of abnormal value 1 appeared at 14:00, and the peak data was 0.91 w. The evaluation value interval of the security threat in the transmission of power data is between 100-200 g, and the energy interval fluctuates around 1000 c. The results obtained are more reasonable, and the security of the data is guaranteed.

Based on digital simulation technology, this paper proposes a food packaging design model and a food production efficiency improvement model with food production as the research entry point. Establish the overall structure of the virtual reality design environment, the parameters of the packaging design process is converted into basic parameters to describe the problem, and the data is fed back to the CAD system to realize the design work. Design the hybrid optimization genetic algorithm based on annealing principle, adjust and optimize the production process and initialize the operation, simulate the annealing genetic algorithm process, and complete the production and processing scheduling sequence. Take A Food Co., Ltd. as the research object to carry out food packaging design and production efficiency improvement practice. The egg cake product packaging design scheme constructed by using the packaging design method in this paper obtains the total attention time of the subjects to be 149.3s, and the subjective score value reaches 85 points, which is better than the original packaging design. And in the real simulation of production using the production efficiency improvement method of this paper, the total production process operating time percentage is reduced from 73.8% to 35.1%, and the food production capacity is steadily increased by about 6%.