Lucheng Lyu

Lucheng Lyu


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 May 2024 in Information Processing & Management
Verified
Journal Article
Closed access
JYJinqing Yang
Jinqing Yang
LWLeyan Wu
Leyan Wu
LLLucheng Lyu
Lucheng Lyu

1 July 2017 in Public Health
Verified
Journal Article
Closed access
LWLiuan Wang
Liuan Wang
XGXitong Guo
Xitong Guo
TWTianshi Wu
Tianshi Wu
LLLucheng Lyu
Lucheng Lyu
ZZZhiwei Zhang
Zhiwei Zhang


11 July 2026 in Scientometrics
Verified
Journal Article
Open access
PDF file
LLLucheng Lyu
Lucheng Lyu
Robin HaunschildRobin Haunschild
Robin Haunschild
JZJian Zhou
Jian Zhou
JWJiaze Wang
Jiaze Wang
Technological convergence reflects emerging innovation trends, and monitoring its dynamics is crucial for innovation-related decision-making. However, quantitatively identifying and visualizing significant strengthening or weakening in technology convergence remains challenging. This study proposes a method based on EPO DOCDB IPC data to detect such patterns. A global technology base map is constructed, on which global convergence overlay maps are developed to enable multi-level comparative analyses and visualization of prominent convergences. A Large Language Model (LLM)-based validation confirms the proposed method’s effectiveness in capturing substantial convergence trends, achieving an average significance percentage of 90% for strengthening convergence and 87% for weakening convergence. Using artificial intelligence (AI) as a case study, our results show that the method effectively reveals prominent global convergence patterns in the AI field, as well as the similarities and differences in convergence trends across countries and organizations. Globally, AI core technology computing shows the strongest convergence strengthening with life sciences and measurement technologies, while its convergence with communication technologies weakens. Nationally, both China and the U.S. promote AI–based life sciences convergence, more pronounced in the U.S., whereas China shows a more diversified convergence profile. Organizationally, Google, Microsoft, Huawei, and Baidu center their convergence strategies around computing, but their convergence targets differ, reflecting distinct strategic priorities and innovation trajectories. This method offers a novel analytical framework and visualization tool for monitoring technological convergence, aiding innovation policy and R&D strategy formulation.


11 October 2026 in Systems
Verified
Journal Article
Open access
PDF file
JXJiayuan Xu
Jiayuan Xu
JZJian Zhou
Jian Zhou
ZZZhanyi Zhao
Zhanyi Zhao
LLLucheng Lyu
Lucheng Lyu
YZYajuan Zhao
Yajuan Zhao
Technology-transfer organizations need effective approaches for matching enterprise technological needs with potentially relevant patents. When a formal technology-demand statement is unavailable, however, enterprise technological demand is only partially observable from organizational records produced for different purposes. This study therefore focuses on enterprise patent, recruitment, and product information as three indirect and differently oriented sources of technological information, and examines their use in enterprise–patent matching without treating these records as verified technological demand. The main purpose of the study is to determine how source composition, matching methods, and review depth affect the retrospective recovery of observed patent assignment or licensing links. To address this purpose, source-specific enterprise profiles are constructed from the three information sources, combined for dense retrieval against a fixed patent corpus, and subsequently reviewed and reranked using a large language model (LLM). The results show that patent-derived profiles provide the strongest retrieval signal under the present representation, while jointly incorporating recruitment and product information provides only limited additional retrieval value. LLM-assisted review can change the ordering of retrieved candidates, particularly at shallower review depth, but the observed differences do not establish a statistically reliable performance advantage over embedding-only retrieval. Scientifically, these findings clarify the respective roles of heterogeneous enterprise information and LLM-assisted reranking in enterprise–patent matching, while also showing that retrieval performance based on organizational traces should not be interpreted directly as measurement of enterprise technological demand. Future research should further examine source-specific contributions, control for shared patent vocabulary, and evaluate the framework using time-aligned, external, and prospective data.