When the country vigorously advocates the goal of cultivating innovative and entrepreneurial engineering talents, the quality evaluation of innovation and entrepreneurship education has naturally become a part of the higher education system. However, there are few studies on the quality evaluation of innovation and entrepreneurship education in engineering majors in China. Firstly, through literature research, combined with the current development trend of quality evaluation of innovation and entrepreneurship education at home and abroad, BP neural network-based evaluation method was selected. Secondly, according to the three-element theory of education, namely, the three factors of educators, educators and education, and comprehensive research, the content of quality evaluation of innovation and entrepreneurship education in engineering majors in colleges and universities is determined, that is, from professional links, teaching links and students. Levels to build evaluation indicators. After establishing the evaluation index system, this paper uses Chengdu University of Technology as a research sample to issue questionnaires for engineering students in Chengdu University of Technology to obtain data for use, and to analyze and analyze the data by AHP, so as to obtain the weight of each indicator. Finally, based on the data collected by the questionnaire, the BP neural network data fitting and model training and optimization are carried out to determine the feasibility of the quality evaluation index of innovation and entrepreneurship education in engineering majors in colleges and universities, and to establish BP neural network evaluation model for engineering majors. The innovation and entrepreneurship education quality evaluation system provides new research methods and research ideas, enriches the connotation and breadth of the quality evaluation system of innovation and entrepreneurship education in engineering majors, and makes up for the shortcomings and vacancies in related fields.

Nuclear professional English course can help students of nuclear energy engineering major to understand the corresponding course content accurately and effectively while learning and researching frontier topics. This course has an important guiding role for their future development. This experiment obtained a series of data from students who had completed the course by questionnaire survey, and logistic regression algorithm was used to analyse the influencing factors of professional English test, then obtained the P value. The significant relationship between the independent variable and the dependent variable can be seen from the P value, thus reflecting the problems existing in the current course. The odds ratio (OR value) value of 0.030 is the biggest influence on the passing rate of the examination factor. In the questionnaire survey on the distribution of students’ intention, 96.25% of the students hope to have a new teaching mode, while 38.10% of the students do not take the initiative to read English books.

With the development of urban economy and the enhancement of competition among cities, urban marketing has attracted more and more attention. Emotional marketing is a people-oriented marketing strategy, which cannot be ignored under the current economic development and urban development level. Today, with abundant commodities and diversified shopping channels, how to attract new customers, maintain old customers and enhance customer loyalty through emotional marketing has become the focus of enterprises’ work. This paper studies from the perspective of clothing. Facing the fierce market competition, in the marketing era of domestic and foreign big enterprises seeking development by brands, if small and medium-sized enterprises want to survive and develop, they must set up the lofty goal of becoming big enterprises, implement brand marketing, and constantly grow and grow healthily in the process of building strong brands. It can be seen from the research in this paper that the recommendation success of this algorithm is 19% better than that of the traditional algorithm in the case of a certain number of partitions, and it is suitable for being put into extensive practice.

A ship's perception of risk is an important basis for collision avoidance. To improve such perception, several risk measurement parameters on the ship domain are determined, including the approach factor, the time to domain violation (TDV) and the possible collision domain. Then, a risk hierarchy prewarning (RHP) model based on the violation detection of a ship domain is proposed, in which a two-level alarm scheme is adopted accordingly. A low-intensity alarm will be activated by reaching the minimum approach factor and the TDV threshold, and a high-intensity alarm will be activated by the factor of the possible collision domain and the TDV threshold. Subsequently, a novel guard zone in ARPA radar utilising the RHP model has been developed to establish a ship's risk perception system for officers on watch at sea. The model proposed in this paper can not only enhance the veracity of risk assessment around our own ship, but also be used as a decision support system for collision avoidance.

In this paper, BP neural network model is used to study and analyse the teaching reform of signal and system course. Referring to the structure of BP neural network, the quality evaluation index system of signal and system course is established. On this basis, the factors influencing students’ examination results are predicted, and the questionnaire is designed and BP neural network is used for prediction. The mean square deviation of the result is 0.7788. Through the correlation coefficient analysis of the data obtained, we can get the major factors that affect students’ final scores. In view of this, the paper puts forward the direction and specific measures of teaching reform of this course.