Keywords
Large language model
Digital human
Science popularization education
Local deployment
Intelligent interaction
Submitted : 2026-05-30
Accepted : 2026-06-14
Published : 2026-06-29
Abstract
With the continuous development of artificial intelligence technology, digital human technology offers extensive applications in science popularization education. This paper designs an AI popular science digital human system using local private large model technology, which integrates key technologies including speech recognition, natural language processing, speech synthesis, and digital human driving to enable intelligent interactive Q&A with users. The system adopts a locally deployed architecture, fine-tuned based on the Qwen large language model, and combines SenseVoice speech recognition, CosyVoice speech synthesis, and the LiveTalking digital human driving engine to build a complete popular science interaction process. The system has been put into practical use in scenarios such as science and technology festivals in primary and secondary schools and science and technology exhibition halls, which effectively improves the fun and interactivity of science popularization education and provides a new solution for cultivating scientific literacy among teenagers.
References
National Informatization Planning Working Group, 2021, 14th Five-Year National Informatization Plan.
Brown T, Mann B, Ryder N, et al., 2020, Language Models are Few-Shot Learners, Advances in Neural Information Processing Systems, 1877–1901.
Alibaba Cloud, 2023, Qwen Large Language Model Technical Report.
Alibaba Group, 2024, CosyVoice Speech Synthesis Technical Documentation.
Alibaba Group, 2024, SenseVoice Speech Recognition White Paper.
OpenAI, 2023, GPT-4 technical report, arXiv preprint arXiv:2303.08774.
Kwon W, Li Z, Zhuang S, et al., 2023, Efficient Memory Management for Large Language Model Serving with Pagedattention, SOSP, 611–626.
LiveTalking Open Source Community, 2024, LiveTalking Digital Human Driving Engine Documentation.
Prajwal K, Mukhopadhyay R, Namboodiri V, et al., 2020, A Lip Sync Expert is all you Need for Speech to Lip Generation in the Wild, ACM MM, 484–492.
Yang F, Zhang W, 2024, Research on Deep Learning-Based Voice-Driven Digital Human Technology. Journal of Computer Research and Development, 61(2): 312–325.
China Association for Science and Technology, 2021, National Scientific Literacy Action Plan (2021–2035).
Ministry of Education, 2018, Education Informatization 2.0 Action Plan.
Liu Y, Zhao W, 2023, Analysis on Development Status and Trends of Digital Human Technology. Journal of Computer-Aided Design & Computer Graphics, 35(8): 1156–1168.