Academic Journal of Computing & Information Science, 2026, 9(6); doi: 10.25236/AJCIS.2026.090607.
Qiuting Zhao, Min Wang, Zitong Hui, Yuxuan Wang, Meng Li, Shihao Zhang
Information School, Beijing City University, Beijing, China
To address the limitations of current sci-tech intelligence analysis, such as insufficient depth, limited coverage and low automation, this paper designs and implements an artificial intelligence-based scientific and technological intelligence analysis and evaluation system. It deeply integrates NLP, LLMs, and knowledge graph technologies to build an AI-domain knowledge graph and an advanced technology evaluation module, realizing a fully automated workflow from data acquisition to one-click report generation. The backend uses Spring Boot, and the frontend uses Vue. A Bert-CRF model is employed for named entity recognition, while LDA topic modeling and Leiden community detection enable frontier technology evaluation. This paper presents the system architecture, module design, and testing results, verifying the system's effectiveness.
Science and technology intelligence; Artificial intelligence; Knowledge graphs; Large language models
Qiuting Zhao, Min Wang, Zitong Hui, Yuxuan Wang, Meng Li, Shihao Zhang. Design and Implementation of an Artificial Intelligence-Based Scientific and Technological Intelligence Analysis and Evaluation System. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 6: 47-54. https://doi.org/10.25236/AJCIS.2026.090607.
[1] Li Guangjian, Pan Jiali. The Process and Current Reflections on Empowering Intelligence Work with Artificial Intelligence Technology[J]. Journal of Information Resources Management, 2024, 14(2): 4-20. DOI:10.13365/j.jirm.2024.02.004.
[2] Zhang Yuchen, Xuan Jia. Operation Mode of Sci-Tech Intelligence Work under the Influence of Generative Artificial Intelligence Technology[J]. National Defense Technology, 2025, 46(5): 106-114. DOI:10.13943/j.issn1671-4547.2025.05.13.
[3] Zhao Yutong, Yang Jianlin. Research on Disruptive Technology Identification Based on Cross-Domain Patents: A Case Study in the Field of Artificial Intelligence[J]. Information Theory and Practice, 2023, 46(3): 174-182. DOI:10.16353/j.cnki.1000-7490.2023.03.023.
[4] Liu Junwan, Pang Bo, Xu Shuo. Early Identification of Disruptive Technologies Based on Weak Signals[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(12): 1395-1411.
[5] Zheng X, Wu Q, Luo X, et al. Analyzing the evolutionary trajectory of technological themes based on the BERTopic model: A case study in the field of artificial intelligence[J]. PloS one, 2025, 20(6): e0324933. DOI:10.1371/JOURNAL.PONE.0324933.
[6] Wang Yong, Qin Jiajun, Huang Yourui, et al. Design of University Research Management Question-Answering System Integrating Knowledge Graph and Large Language Model[J]. Journal of Computer Science and Exploration, 2025, 19(1): 107-117.
[7] Zhan C, Zhou Y, Huang Y. Research on Emerging Technology Identification Methods Based on a Knowledge Graph of High-Value Patents[J]. Big Data and Cognitive Computing, 2026, 10(2): 40. DOI:10.3390/BDCC10020040.
[8] Wang Ping, Xu Jian, Wang Xiaodong. Construction and Optimization Method of Intelligent Knowledge Base Integrating Knowledge Graph and Large Language Model[J]. Information Recording Materials, 2026, 27(10): 119-121+148. DOI:10.16009/j.issn.1009-5624.2026.10.039.
[9] Lin Y, Xu C, Xu K, et al. Research on the Knowledge Structure and Sustainable Development Pathways of Artificial Intelligence from the Perspective of Technological Science[J]. Sustainability, 2024, 16(20): 9019. DOI:10.3390/SU16209019.
[10] Chunyi S, Jun W, Yongming Z. The Evolution of Artificial Intelligence in the Digital Economy: An Application of the Potential Dirichlet Allocation Model[J]. Sustainability, 2023, 15(2): 1360.
[11] Entering a New Stage of "AI+" and Sharing New Achievements in Digital Development: The 56th Statistical Report on China's Internet Development Released[J]. Information Construction, 2025, (8): 49-51.