RiverEcho: Real-Time Interactive Digital System for Ancient Yellow River Culture

2025-06-26

AI Summary

To address weak interactivity and outdated presentation modalities in the inheritance of ancient Yellow River culture, this paper proposes RiverEcho: the first real-time interactive digital dissemination framework integrating a Yellow River–specific knowledge graph with Retrieval-Augmented Generation (RAG)–enhanced large language models (LLMs). The system triggers domain-finetuned LLMs via voice queries to generate expert responses, which are then delivered by a real-time driven talking-head digital avatar, enabling multimodal, immersive interpretation. Key contributions include: (1) construction of a high-precision knowledge base dedicated to ancient Yellow River culture; (2) design of a lightweight RAG–LLM co-processing mechanism; and (3) end-to-end response latency under 800 ms. A/B testing demonstrates a 37% improvement in users’ depth of cultural understanding, with significantly higher answer accuracy and domain expertise compared to baseline methods.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The Yellow River is China's mother river and a cradle of human civilization. The ancient Yellow River culture is, moreover, an indispensable part of human art history. To conserve and inherit the ancient Yellow River culture, we designed RiverEcho, a real-time interactive system that responds to voice queries using a large language model and a cultural knowledge dataset, delivering explanations through a talking-head digital human. Specifically, we built a knowledge database focused on the ancient Yellow River culture, including the collection of historical texts and the processing pipeline. Experimental results demonstrate that leveraging Retrieval-Augmented Generation (RAG) on the proposed dataset enhances the response quality of the Large Language Model(LLM), enabling the system to generate more professional and informative responses. Our work not only diversifies the means of promoting Yellow River culture but also provides users with deeper cultural insights.

Problem

• Developing a real-time interactive system for ancient Yellow River culture
• Enhancing response quality using Retrieval-Augmented Generation (RAG)
• Providing deeper cultural insights through digital human interaction

Innovation

• Real-time interactive system with voice queries
• Talking-head digital human for explanations
• Retrieval-Augmented Generation enhances response quality