Oracle bone inscriptions information processing: a comprehensive survey

Oracle bone inscriptions (OBI), the earliest known form of Chinese writing, have garnered widespread attention from historians since their excavation. This survey presents a comprehensive, task-centric synthesis that reframes the development of OBI information processing as a coevolution between methodologies and their underlying data substrate. We formulate a unified taxonomy of OBI data, emphasizing the quality, cross-modal, and domain-specific challenges that differentiate OBI corpora from general image processing datasets. We systematically review OBI processing paradigms from traditional expert-led foundations to current large multimodal model-based cross-modality perception and interpretation, alongside an extensive introduction of 36 OBI datasets. This survey also reviews over 100 articles, categorized by task-oriented contributions, to identify key advances, limitations, and application areas within OBI information processing. Critical challenges such as data accessibility, heterogeneity, and inapplicability of metrics are analyzed. Finally, we outline some potential research directions towards generative, multi-agent collaborative, high-dimensional reconstruction, providing a roadmap for building trustworthy, efficient OBI information processing systems that function as a true partner for frontline researchers to contribute to key debates on the social structure understanding and periodization of the pre-Qin period, one of the most important moments in Chinese history. Relevant papers and resources are continuously updated at https://github.com/OBI-Future/OBI-Survey .