Artificial intelligence technology reconstructs the logic of knowledge production and application. Cross-domain knowledge fusion has become the core support for solving complex system problems and breaking through cutting-edge innovations. The knowledge boundary of a single domain restricts innovation efficiency. With the capabilities of data processing, semantic understanding and pattern mining, artificial intelligence weakens domain segmentation and promotes the cross-scenario circulation of knowledge elements. Current fusion practices suffer from problems such as isolated knowledge graphs, rigid mechanisms and lagging updates. Facing technological evolution and industrial demands, it is necessary to take the construction of interactive knowledge graphs, the design of human-machine collaboration mechanisms and the construction of dynamic update closed loops as paths to form a stable and efficient cross-domain knowledge allocation system. This study provides theoretical references and practical frameworks for the interdisciplinary field of artificial intelligence and knowledge management.

Xie Tengyue. Research on the Innovation Path of Cross-Domain Knowledge Fusion Driven by Artificial Intelligence. The Frontiers of Society, Science and Technology (2026), Vol. 8, Issue 2: 35-39. https://doi.org/10.25236/FSST.2026.080205.

[1] Fu Hansi, Ding Yajing. Research on Dynamic Update Strategy of Knowledge Base for Higher Vocational Art Design Major Driven by AIGC Technology[J]. Art Science and Technology, 2026, 39(4): 113-115, 118.

[2] Tang Peng, Xie Yueling, Jia Yingdan. Multi-Disciplinary Curriculum Reform Driven by Intelligent Manufacturing and Artificial Intelligence Under the Background of Emerging Engineering Education[J]. Electronic Edition of Science and Education Guide (First Ten Days), 2026(3): 7-9.

[3] Zhang Yue, Deng Junyi. Research on Interdisciplinary Integration Mechanism of College Mathematics and Professional Courses Driven by Metaverse[J]. Higher Education of Science, 2025(4): 46-53.

[4] Li Jing, Zhao Shuang, Ao Yuhan, et al. Construction of Artificial Intelligence Courses for Traditional Chinese Medicine From the Perspective of Interdisciplinary Integration[J]. Journal of Educational Observation, 2025, 14(10): 7-10.

[5] Yang Kaiyue. Transformation of Digital Think Tanks Driven by Artificial Intelligence: Core Characteristics, Architecture and Key Technologies[J]. Science and Technology Think Tank, 2026(2): 76-84.

[6] Wang L , Xu Y , Zhang M ,et al. Teaching innovation in a pharmacy course: integration of "Questioning-Training of Comprehensive Knowledge Application" and a "Teacher-AI-Student Interaction Model"[J].BMC Medical Education, 2025, 25(1).

[7] Vidal M E , Chudasama Y , Huang H ,et al. Integrating Knowledge Graphs with Symbolic AI: The Path to Interpretable Hybrid AI Systems in Medicine[J].Web Semantics: Science, Services and Agents on the World Wide Web, 2025, 84(3).

[8] Dash B M , Bouamama B O , Pekpe K M ,et al. Prior knowledge-infused Self-Supervised Learning and explainable AI for Fault Detection and Isolation in PEM electrolyzers[J]. Neurocomputing, 2024, 594(2):20.

[9] Dai D , Sun Y , Dong C ,et al. Effectively fusing clinical knowledge and AI knowledge for reliable lung nodule diagnosis[J].Expert Syst. Appl. 2023, 230:120634.

[10] Chakrabarti L , Zhang B , Tian H ,et al. Automated Skin Cancer Report Generation via a Knowledge-Distilled Vision-Language Model[J].IEEE Access, 2025, 13(13):136320-136335.

[11] Bi X , Xie H , Lyu Z ,et al. Research on explainable classification and model updating of maize kernels from different years based on multimodal data-driven approaches[J].Microchemical Journal, 2025, 215.

[12] Liu Guoqing, Chen Guoxiong. Geoscience Knowledge Extraction and Information Mining Integrating Knowledge Graphs and Large Language Models: A Case Study of Carlin-type Gold Deposits[J]. Earth Science, 2026, 51(03): 1009-1024.