Abstract College students’ employability is a compound and developmental concept, and employability enhancement is affected by various factors, among which college management reform is an important influence factor of college students’ employability. This paper first constructs the influence factor model of students’ employability enhancement based on the method of multiple linear regression analysis. Then, based on the results of the multiple regression analysis, the design of the path of college management reform oriented to the improvement of students’ employability is carried out. Finally, the feasibility of the path is verified by using independent sample t-test and paired sample t-test. The correlations between the influencing factors of employability and the specific dimensions of employability all reach a significant level and show a weak correlation (Pearson’s correlation coefficient in the range of 0.111~0.346), which indicates that the refined influencing factors of college students’ employability have a greater effect on the level of employability. Among them, major setting, career planning, evaluation and motivation, campus culture, and teaching ability are the core influencing factors for the improvement of college students’ employability. After the experiment, there is a significant difference between the experimental group that adopts the corresponding teaching management mode under the college reform path designed in this paper and the homogeneous control group in terms of students’ employability (p<0.05), indicating that the college management reform path designed in this paper is able to effectively enhance students’ employability.

Abstract With the development of the times and the progress of science and technology, stage design has also gained more development, and at the same time, it also promotes the stage design more and more tends to be intelligent and creative, intelligent accompanied by creativity almost at the same time existence and development, the two are complementary. This paper applies Stable Diffusion technology to generate the tone and style of choreography design, and adjusts the parameters of the generated image through LoRA model to realize the style fine-tuning. Attention mechanism is introduced on the basis of SD model to enhance the representation of object embedding vectors. Use the scene layout network based on region convolutional network to improve the accuracy and stability of target detection. Introducing the three concepts of Query, Key and Value, a CLIP text encoder is designed so that the sublayer network generates clearer images. The stage performers are detected and recognized by YOLO algorithm, and the Nearest Neighbor Rule Classification and Matching algorithm is applied to calculate the distance between each sample, extract the human body key point features, and realize the stage light tracking. The physiological characteristic signals of the audience were collected by using eye-tracking instrument, and the spatial elements of the choreography that were paid more attention by the subjects were the spatial interface elements and the set elements, which were more eye-catching and attractive than the other four types of spatial elements, and the total duration of the gaze was 104.624 s and 63.552 s. The correct rate of the direction of the rotational tracking of the luminaires controlled by the KNN and RANSAC algorithms used in this paper reaches 97%, and the rotation degree error is between [-18.72%,22.3%]. It meets the stage lighting tracking performance requirements.

Abstract Residents’ consumption level is increasing, e-commerce vocational education has become an increasingly important field of education, how to realize customer value-added has become the focus of attention of e-commerce platforms. In this paper, we use the improved dynamic RFM customer segmentation model based on K-Means clustering to segment e-commerce consumers, to accurately portray the changes of e-commerce consumers’ loyalty and the transfer characteristics between e-commerce consumers’ groups, to achieve the identification of consumers’ online behavioral patterns. The RFM model classifies users into four categories: important value, general value, focus on development, and focus on retention. The important value users of Product B have high activity and contribution, but very low loyalty, which indicates that there may be group purchasing behaviors in this group, and the e-commerce operator of Product B can focus on serving this type of customers. After implementing the technique in teaching, the six dimensions of the experimental class C about teaching effectiveness are better than the other two classes, which shows that the technique provides a new perspective for the improvement of teaching effectiveness in e-commerce education.

Abstract With the help of virtual reality technology, the study first conducted a preliminary discussion on language learning, and found that virtual reality technology is an important tool to promote new language learning. The study constructs a model of English language teaching with virtual reality technology, on the basis of which a moderated mediator model is constructed with virtual reality technology as the independent variable, students’ cognitive load as the mediator variable, spatial ability as the moderating variable, and language learning effect as the dependent variable and puts forward relevant hypotheses to explore the effect of virtual reality technology on the effect of immersive language learning. The experimental design was carried out with 122 students from University H as subjects, divided into an experimental group and a general group. The results of the study showed a significant main effect of virtual reality environment (F(1,31)=4.01,p=0.05), indicating that the use of virtual reality technology has a significant impact on immersive language learning. Among learners with different spatial abilities, learners with high spatial abilities learn better compared to learners with low spatial abilities, and the experimentation of virtual reality technology has an enhancing effect on language learning compared to traditional teaching methods. According to the results of the mediation effect test, students’ cognitive load mediates the effect of the use of virtual reality technology on language learning outcomes.

Abstract With the rapid development of artificial intelligence technology, the field of education, especially journalism communication teaching in colleges and universities, is facing unprecedented opportunities for change. Artificial intelligence not only promotes the innovation of teaching methods, but also provides a new path for improving teaching effects. This paper takes the teaching of journalism and communication major in colleges and universities as the research object, and discusses how to effectively improve the teaching effect under the background of artificial intelligence. Through the investigation and data analysis of journalism and communication disciplines in 30 universities across the country, the introduction of artificial intelligence technology has shown significant advantages in improving students’ learning efficiency, enhancing curriculum interactivity, and improving teachers’ teaching quality. The artificial intelligence-assisted personalized learning system can customize course content according to students’ learning progress and interests, while the teaching evaluation system provides real-time feedback on students’ performance through data analysis, helping teachers adjust teaching strategies more accurately. In colleges and universities using artificial intelligence technology, students’ average grades have increased by 15%, classroom participation has increased by 20%, and teaching satisfaction has increased by 25%.

Abstract At present, the auxiliary teaching system for Civics and Politics courses has problems such as low accuracy of knowledge state prediction and insignificant effect of personalized learning, which affects the actual learning effect. In this paper, we analyze the demand for teaching college students Civics and Politics using deep learning, and discuss the overall design of the system. Based on the open-source online teaching system CAT-SOOP, a set of augmented learning algorithm-based Civics course assisted teaching system is designed and implemented, which is based on the student practice data, training student knowledge tracking model and augmented learning recommendation engine for assisting the personalized recommendation of student’s Civics exercises. The results show that compared with the random recommendation method, the relevance of the recommended exercises of this system is improved from 0.03 to 0.238, the reward value is more stable, and the maximum value is improved by 0.2. The assisted teaching system for the Civics course designed in this paper for college students achieves the expected goals and meets the diverse needs of the audience seeking intelligent Civics education.

Abstract The application of speech recognition technology in the power industry can improve the collaborative efficiency of power grids at all levels and reduce the work intensity of dispatchers, which is one of the indispensable key technologies in the process of intelligent development of power grids. In this study, a power speech recognition model is designed based on the combination of Transformer-based out-of-set word model and n-gram language error checking based model. For model application, a training set is used for model training to test the input features of the model in this paper. Subsequently, a power speech dataset was created, which was used for model comparison to validate the effectiveness of the algorithms in the paper. System design using the algorithms proposed in the paper is carried out to process real-time speech, speech files, and speech information from telephone terminals. The results show that the Spectrogram feature of the speech signal is more suitable as the input feature of the model in this paper, which can reduce the word error rate of the speech recognition model. The model in this paper performs best in all four metrics: Accurary, Precision, Recall, and F1. The parameter count of the proposed method in this paper is 25, the word error rate WER is 8.21%, and the real-time rate RTF is 0.017, which indicates that the algorithm has a good generalization performance on power speech dataset.

Abstract Although automation technology has a good application prospect in the field of power system, the current research on the role of automation technology on power system protection and control is relatively small. Accordingly, a research program on power system protection and control based on automation technology is developed. The main simulation and analysis software for this research is first determined, and the CNN-based power system fault identification algorithm and protection scheme are designed by combining the line multi-channel characteristics of the power system. It is found that the security and stability of the power system cannot be maintained for a long time only by relying on the protection scheme, and in response to this dilemma, the PLC-based fuzzy PID voltage controller is used to realize the intelligent control of the power system and monitoring of the equipment in the scope of automation technology. Finally, with the help of the above analysis tools, the scheme of this paper is verified and analyzed. The CNN-based power system fault identification algorithm performs well, with the values of 99.29%, 97.53%, and 98.39% for each performance index, and the protection scheme is able to quickly complete the repair within 20ms of the fault occurrence. In addition, the introduction of fuzzy PID controller power system control strategy, the quality of voltage output and equipment speed has a significant role in improving the power system to promote the development of power system in the direction of more efficient, safer and smarter.

Abstract Aiming at the problem that the fault samples of UHV converter equipment are few and cannot effectively support the intelligent operation and inspection of the equipment, this paper proposes a brain-like learning sample spatio-temporal correlation generation technique for the operation and inspection of UHV converter equipment. In this technique, GPNN fuses the temporal evolution law and similarity of nearby samples to intercept typical fault samples and then combines the SNNs model of brain-like computing to construct an intelligent diagnosis model for UHV converter equipment. The improved K-SVD dictionary learning algorithm is used to extract the time-domain features of the UHV converter faults, combined with the empirical wavelet singular entropy to obtain the frequency-domain features, and the KPCA algorithm is used to fuse the multiscale time-frequency features to obtain the multiscale spatial and temporal features of the faults of UHV converter equipment. The GPNN model for generating multi-scale spatio-temporal sequence fault samples is constructed by combining GAN with the nearest neighbor interpolation algorithm. The fault samples generated by the GPNN model are used as inputs and combined with the SNNs model for intelligent diagnosis of UHV converter equipment faults. The consistency between the fault samples generated by the GPNN model and the actual samples reaches more than 90.57%, the accuracy of the brain-like intelligent fault recognition model reaches up to 98.06%, and its training time is only 37.14 seconds. Learning the multi-scale features of the samples through the GPNN model, combined with brain-like computing technology, can support the training of brain-like models for health assessment, fault diagnosis, and trend prediction of UHV converter equipment.

Abstract Open education is a form of education based on multiple media resources. The optimization of teaching resource allocation on this form can be achieved through resource sharing and personalized resource recommendations. The study proposes an open education teaching resource sharing method based on blockchain technology, which builds a model from three levels: application layer, contract layer, and data layer, specifies the resource transmission efficiency and channel, and realizes the sharing of teaching resources. It also establishes a personalized recommendation process based on K-Means clustering algorithm to achieve recommendations for open education resources. The sharing model constructed in this paper has high resource uploading efficiency and fast updating speed, and is well received by teachers and students. The recommendation accuracy of the personalized recommendation model is higher than 93.6%, and the recommendation time consumed is lower than 21.8s, which is better than the comparison method, and the application effect is better. After using the resource allocation optimization method above to carry out educational reform, students’ performance has significantly improved, and the teaching reform under this method has been highly evaluated.