App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 2

MMQA: reliable multimodal retrieval-augmented question answering framework for emergency power grid documents

Liang Hongchi1
Wu Jing1
Wang Yaxuan2
Xu Xin1
1. State Grid Fujian Electric Power Co, Ltd. Emergency Center, Fuzhou 350003, China
2. School of Computer Science, Sichuan University, Chengdu 610065, China
DOI: 10.19734/j.issn.1001-3695.2026.07.0167

Abstract

Power grid emergency question answering requires joint reasoning over textual and visual evidence from heterogeneous documents, including emergency plans, operation tickets, fault reports, and single-line diagrams. However, text-centered retrieval-augmented generation (RAG) methods struggle to capture fine-grained visual information and resolve conflicts across modalities. This paper proposes MMQA, a reliable multimodal retrieval-augmented question answering framework for power grid emergency documents. MMQA contains three core components. Branch retrieval and evidence organization separately retrieve and structure textual and visual evidence. State-sensitive visual alignment based on late interaction enables fine-grained retrieval of engineering drawing pages. Verifier-guided fusion extracts atomic claims, detects cross-modal conflicts, and generates answers only from verified evidence. This paper evaluates MMQA on Grid-EMQA-3K, a benchmark built from real power grid emergency documents and containing 3, 000 question-answer pairs. Experimental results show that MMQA outperforms strong baselines in answer generation quality, visual localization retrieval, and safety-oriented reliability, demonstrating the effectiveness of explicit evidence organization and cross-modal conflict resolution for reliable power grid emergency question answering.

Foundation Support

由国家电网有限公司科技项目(SGFJYJ00DJJS2500006):国网福建应急中心2025年面向异构数据智能体的电网应急高效处置关键技术研究与应用(521304XXXXXX)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.07.0167
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 2

Publish History

[2026-10-22] Accepted Paper

Cite This Article

梁宏池, 吴竞, 汪雅轩, 等. MMQA：面向电网应急文档的可靠多模态检索增强问答 [J]. 计算机应用研究, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.07.0167. (Liang Hongchi, Wu Jing, Wang Yaxuan, et al. MMQA: reliable multimodal retrieval-augmented question answering framework for emergency power grid documents [J]. Application Research of Computers, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.07.0167. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2025 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)