Article: A system for generating tourism cultural symbols based on diffusion models and graph neural networks Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.95 pp.68 - 88 Abstract: The generation of tourism and cultural symbols often faces the problem of semantic drift - where patterns visually conform to the data distribution but deviate from their original cultural connotations. To address this, this paper integrates graph neural networks with diffusion models, utilising a graph attention network to encode semantic relationships between symbols and using these relationships to guide the diffusion process, thereby ensuring that the generated symbols balance visual realism with cultural fidelity. Tested on 15,327 symbolic images from seven world heritage sites in China, our method achieved area under the curve and accuracy scores of 0.912 and 0.894, respectively - representing improvements of 6.5% and 7.6% over the standard diffusion model and 4.3% and 4.9% over the current state-of-the-art diffusion adapter network. Experiments demonstrate that introducing structured constraints based on symbolic knowledge effectively suppresses semantic drift, providing a viable approach for the intelligent preservation of cultural heritage. Inderscience Publishers - linking academia, business and industry through research

Title: A system for generating tourism cultural symbols based on diffusion models and graph neural networks

Authors: Shanshan Hong; Manhua Yang

Addresses: Taizhou Vocational College of Science and Technology, Taizhou, 318020, China ' Taizhou Vocational College of Science and Technology, Taizhou, 318020, China

Abstract: The generation of tourism and cultural symbols often faces the problem of semantic drift - where patterns visually conform to the data distribution but deviate from their original cultural connotations. To address this, this paper integrates graph neural networks with diffusion models, utilising a graph attention network to encode semantic relationships between symbols and using these relationships to guide the diffusion process, thereby ensuring that the generated symbols balance visual realism with cultural fidelity. Tested on 15,327 symbolic images from seven world heritage sites in China, our method achieved area under the curve and accuracy scores of 0.912 and 0.894, respectively - representing improvements of 6.5% and 7.6% over the standard diffusion model and 4.3% and 4.9% over the current state-of-the-art diffusion adapter network. Experiments demonstrate that introducing structured constraints based on symbolic knowledge effectively suppresses semantic drift, providing a viable approach for the intelligent preservation of cultural heritage.

Keywords: diffusion models; graph neural networks; GNNs; tourism cultural symbols.

DOI: 10.1504/IJICT.2026.156132

International Journal of Information and Communication Technology, 2026 Vol.27 No.95, pp.68 - 88

Received: 25 Apr 2026
Accepted: 10 Jun 2026
Published online: 04 Sep 2026 *

Title: A system for generating tourism cultural symbols based on diffusion models and graph neural networks

Keep up-to-date