商用洗碗设备故障知识库构建方法及系统
By integrating equipment component hierarchy maps and pre-trained language models into the construction of a fault knowledge base for commercial dishwashers, the problem of lacking domain knowledge understanding in existing technologies is solved, achieving high-precision fault information extraction and knowledge base construction, and supporting the development of intelligent diagnostic systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGSU XIAOGE INTELLIGENT TECH CO LTD
- Filing Date
- 2026-03-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies, when constructing a fault knowledge base for commercial dishwashers from unstructured maintenance texts, lack domain knowledge understanding and struggle to distinguish complex referential relationships across multiple fault scenarios, resulting in low accuracy in fault information extraction and a high likelihood of association errors.
An incremental approach is used to construct coreference chains. By combining the equipment component hierarchy map and a pre-trained language model, coreference scores and link decision scores are calculated to identify equipment components and fault code entities. Fault-related information is then aggregated based on the segmented subchains to form knowledge triples.
It improves the accuracy of identifying the referential relationships between professional terms and component alternatives, effectively prevents the incorrect association of different fault information, ensures the logical correctness and integrity of the knowledge base, and provides a clear data foundation for the intelligent diagnostic system.
Smart Images
Figure CN121808435B_ABST