EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Context-Aware Semantic Retrieval for Ancient Texts: A Native Reasoning Approach Based on In-Memory Knowledge Graph

Tianrui Li, Hongyu Yuan

Electronics · 25.04.2026 · 15 (9) · 1827

DOI: 10.3390/electronics15091827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 25.04.2026. Verfasst von Tianrui Li und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Henan Province, Higher Education Key Scientific Research Program Funded of by Henan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a lightweight semantic retrieval framework driven by an in-memory knowledge graph (IMKG) to overcome the limitations of traditional keyword matching and the prohibitive hardware costs of deep learning models in digitizing ancient Chinese literature. By extracting structured metadata from canonical texts, we construct a dense, bidirectional graph schema. Diverging from resource-intensive neural architectures, our system abandons heavyweight vector embeddings in favor of a highly optimized, template-based heuristic matching engine natively implemented in Java. This purely symbolic approach ensures deterministic execution, zero-dependency deployment, and seamless operation on standard CPU-only servers. To handle complex historical inquiries, the framework integrates a context-aware dialogue manager for multi-turn anaphora and ellipsis resolution, alongside a synergistic tiered caching mechanism. Extensive evaluations on a benchmark of 13,652 annotated queries demonstrate that the system achieves an exceptional intent recognition accuracy of 97.14%, robust context retention, and ultra-low response latency (≤17 ms). Ultimately, this architecture provides a sustainable, highly reproducible, and cost-effective paradigm for the semantic exploration of classical textual heritage, exceptionally suited for small-to-medium cultural institutions.

Förderung

  • Natural Science Foundation of Henan Province
  • Higher Education Key Scientific Research Program Funded of by Henan Province

Zitieren

APA

Li, T., & Yuan, H. (2026). Context-Aware Semantic Retrieval for Ancient Texts: A Native Reasoning Approach Based on In-Memory Knowledge Graph. Electronics, 15(9), 1827. https://doi.org/10.3390/electronics15091827

Vancouver

Li T, Yuan H. Context-Aware Semantic Retrieval for Ancient Texts: A Native Reasoning Approach Based on In-Memory Knowledge Graph. Electronics. 2026;15(9):1827. doi:10.3390/electronics15091827

BibTeX
@article{Li2026,
  author = {Li, Tianrui and Yuan, Hongyu},
  title = {Context-Aware Semantic Retrieval for Ancient Texts: A Native Reasoning Approach Based on In-Memory Knowledge Graph},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1827},
  doi = {10.3390/electronics15091827}
}
Kostenlos starten →