Entrepreneurship education is critical in encouraging students' innovation, creativity, and entrepreneurial spirit. It provides essential skills and knowledge, enabling them to open their creative potential and apply innovative thinking across diverse professional fields. With the widespread application of large language models in education, intelligent-assisted teaching in entrepreneurship education is stepping into a new learning phase anytime and anywhere. Entrepreneurship education extends across interdisciplinary knowledge fields, incorporating subjects like finance and risk management, which require advanced mathematical computational skills. This complexity presents new challenges for artificial intelligence-assisted question-and-answer models. The study explores how students can maximize the knowledge repository of current large language models to improve learning efficiency. Experimentally validates the performance differences between large language models and graph convolutional reasoning models regarding the complex semantic reasoning and mathematical computational demands in entrepreneurship education questions. Based on case studies, it is found that despite the broad prospects of large language models in entrepreneurship education, they still need to improve in practical applications. Especially in tasks within entrepreneurship education that demand precision, such as mathematical computations and risk assessment, the accuracy and efficiency of existing models still need improvement. Therefore, further exploration into algorithm optimization, model fusion, and other technical enhancements can improve the processing capabilities of intelligent question-and-answer systems for specific domain issues, aiming to meet the practical needs of entrepreneurship education.

Glycation is a nonenzymatic process in which proteins react with reducing sugar molecules. The identification of glycation sites in protein may provide guidelines to understand the biological function of protein glycation. In this study, we developed a computational method to predict protein glycation sites by using the support vector machine classifier. The experimental results showed that the prediction accuracy was 85.51% and an overall MCC was 0.70. Feature analysis indicated that the composition ofk-spaced amino acid pairs feature contributed the most for glycation sites prediction.

The latest technologies in natural language processing (NLP) provide creative, knowledge retrieval and question-answering technologies in the design of intelligent education, which can provide learners with personalized feedback and expert guidance. Entrepreneurship education aims to cultivate and develop the innovative thinking and entrepreneurial skills of students, making it a practical form of education. However, a knowledge retrieval and question-answering teaching assistant system for entrepreneurship education has not been proposed. This observation motivated us to develop a reading comprehension framework to address the challenges of domain-specific knowledge gaps and the weak comprehension of complex texts encountered by Intelligent education models in practical applications. The proposed framework mainly includes: question understanding, relevant knowledge retrieval, mathematical calculation and answer prediction. The techniques involved in the above modules mainly include text embedding, similarity retrieval, graph convolution and long-short term memory network. By integrating this model into entrepreneurship courses, learners can participate in real-time discussions and receive immediate feedback, creating a more dynamic and interactive learning environment. To assess the effectiveness of the proposed model, this paper conducts answer prediction on single-choice exercises related to entrepreneurship education courses. This study employing the potential of using a question-and-answer format to enhance intelligent entrepreneurship education, paving the way for a more effective and engaging online learning experience.

Given an undirected, connected and edge-weighted graph, the dominating tree problem consists of finding a tree with minimum total edge weight such that for each vertex is either in the tree or adjacent to a vertex in the tree. In this paper, we propose a hybrid framework combining genetic algorithm with iterated local search (GAITLS) for solving the dominating tree problem. The main components of our framework are as follows: (1) the score functions $Dscore$ and $Wscore$ applied in the initialization and local search phase; (2) the initialization procedure with restricted candidate list (RCL) by controlling the parameter to balance the greediness and randomness; (3) the iterated local search with three phases, which is used to intensify the individuals; (4) the mutation with high diversity proposed to perturb the population. The experimental results on the classical instances show that our method performs much better than the-state-of-art algorithms.

With the abundance of learning resources available on massive open online courses (MOOCs) platforms, the issue of interactive data sparsity has emerged as a significant challenge.This paper introduces MRMLREC, an efficient MOOC video recommendation which consists of two main stages: multi-relational representation and multi-level recommendation, aiming to solve the problem of data sparsity. In the multi-relational representation stage, MRMLREC adopts a tripartite approach, constructing relational graphs based on temporal sequences, courses-videos relation, and knowledge concepts-video relation. These graphs are processed by a Graph Convolution Network (GCN) and two variant Graph Attention Networks (GAT) to derive representations. A variant of the Long Short-Term Memory Network (LSTM) then integrates these multi-dimensional data to enhance the overall representation. The multi-level recommendation stage introduces three prediction tasks at varying levels—courses, knowledge concepts, and videos—to mitigate data sparsity and improve the interpretability of video recommendations. Beam search (BS) is employed to identify top-β items at each level, refining the subsequent level's search space and enhancing recommendation efficiency. Additionally, an optional layer offers both personalization and diversification modes, ensuring variety in recommended videos and maintaining learner engagement. Comprehensive experiments demonstrate the effectiveness of MRMLREC on two real-world instances from Xuetang X.