Intelligent Retrieval and Comprehension of Entrepreneurship Education Resources Based on Semantic Summarization of Knowledge Graphs

Abstract

The latest technologies in natural language processing 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 aforementioned 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 article conducts answer prediction on single-choice exercises related to entrepreneurship education courses. This study employs 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.