App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

MLE-KPE: multi-stage llm-enhanced method for Chinese patent keyword extraction

Teng Shangzhi1
Deng Minhui1
You Xindong2
Lyu Xueqiang1
1. Beijing Key Laboratory of Cyber Culture and Digital Communication, Beijing Information Science and Technology University, Beijing 100101, China
2. School of Information Engineering, Beijing Institute Of Graphic Communication, Beijing 102600, China
DOI: 10.19734/j.issn.1001-3695.2025.10.0466

Abstract

This study aims to improve the accuracy and diversity of keyword extraction from Chinese patent texts, addressing limitations of existing methods in semantic representation, feature extraction, and long-text processing. This study propose a Multi-Stage LLM-Enhanced Patent Keyword Extraction (MLE-KPE) method, which consists of three stages. First, this study performs sentence-level topic modeling using Sentence-BERT embeddings and a Gaussian Mixture Model (GMM) , and incorporates IPC classification numbers as prior information to select topic-representative sentences for each document. Second, a large language model (LLM) semantically aggregates the selected topic sentences to generate a rich set of candidate keywords. Finally, this study scores, deduplicates, and ranks candidate keywords according to semantic similarity and phrase centrality, producing a high-quality final keyword list. Experiments on a self-constructed patent dataset and a Chinese scientific literature dataset show that the proposed method outperforms baseline models on F1@5, F1@10, and F1@15, demonstrating its effectiveness and generalization ability. The MLE-KPE model effectively enhances keyword extraction for patent texts and offers a new multi-level fusion solution for patent keyword extraction.

Foundation Support

国家自然科学基金资助项目(62171043,62202061)
北京市自然科学基金资助项目(4232025)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.10.0466
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-23] Accepted Paper

Cite This Article

滕尚志, 邓敏慧, 游新冬, 等. MLE-KPE:一种融合大模型的多阶段中文专利关键词提取方法 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0466. (Teng Shangzhi, Deng Minhui, You Xindong, et al. MLE-KPE: multi-stage llm-enhanced method for Chinese patent keyword extraction [J]. Application Research of Computers, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0466. )

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
  • 2020-2022 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)