In complex assembly industry settings, fault localization involves rapidly and accurately identifying the source of a fault and obtaining a troubleshooting solution based on fault symptoms. This study proposes a knowledge-enhanced joint model that incorporates aviation assembly knowledge graph (KG) embedding into large language models (LLMs). This model utilizes graph-structured Big Data within KGs to conduct prefix-tuning of the LLMs. The KGs for prefix-tuning enable an online reconfiguration of the LLMs, which avoids a massive computational load. Through the subgraph embedding learning process, the specialized knowledge of the joint model within the aviation assembly domain, especially in fault localization, is strengthened. In the context of aviation assembly functional testing, the joint model can generate knowledge subgraphs, fuse knowledge through retrieval augmentation, and ultimately provide knowledge-based reasoning responses. In practical industrial scenario experiments, the joint enhancement model demonstrates an accuracy of 98.5% for fault diagnosis and troubleshooting schemes.

The aviation assembly domain, which is a complex system, involves the multi-dimensional information of parts, processes, tools, plants and operation projects. In order to assist the knowledge management from natural language text in the aircraft manufacturing process, this paper proposes the corresponding ontology scheme and the joint knowledge extraction model, which is necessary for construct the knowledge graph in the aviation assembly domain. The model is able to automated end-to-end construct knowledge graph. The proposed model, which is based on reinforcement learning approach and a novel labeling scheme, takes the constraint relationships between entities and relations as an important identification basis. The model does not rely on manual feature setting, while it greatly reduces the training cost. The proposed joint knowledge extraction model was testified from the practical scenarios of the general assembly and component assembly. The experimental results showed that the proposed model showed an excellent performance in the aviation assembly domain, with the F1-score of 89.71% for entities, the F1-score of 91.27% for relations, and the overall average F1-score of 82.41%. Based on the superior performance of the model, the knowledge graph of the general assembly and component assembly, which included 1, 308 pairs of triples composed of five kinds of entities and three kinds of relations, was further constructed in the aviation assembly domain.

Legal knowledge involves multidimensional heterogeneous knowledge such as legal provisions, judicial interpretations, judicial cases, and defenses, which requires extremely high relevance and accuracy of knowledge. Meanwhile, the construction of a legal knowledge reasoning system also faces challenges in obtaining, processing, and sharing multisource heterogeneous knowledge. The knowledge graph technology, which is a knowledge organization form with triples as the basic unit, is able to efficiently transform multisource heterogeneous information into a knowledge representation form close to human cognition. Taking the automated construction of the Chinese legal knowledge graph (CLKG) as a case scenario, this paper presents a joint knowledge enhancement model (JKEM), where prior knowledge is embedded into a large language model (LLM), and the LLM is fine-tuned through the prefix of the prior knowledge data. Under the condition of freezing most parameters of the LLM, this fine-tuning scheme adds continuous deep prompts as prefix tokens to the input sequences of different layers, which can significantly improve the accuracy of knowledge extraction. The results show that the knowledge extraction accuracy of the JKEM in this paper reaches $90.92\%$. Based on the superior performance of this model, the CLKG is further constructed, which contains 3480 knowledge triples composed of 9 entities and 2 relationships, providing strong support for an in-depth understanding of the complex relationships in the legal field.

Dynamic scheduling systems often rely on structured domain knowledge for real-time optimization and decision making. However, much of this knowledge originates from unstructured text, such as operational manuals, maintenance logs, and expert records. Extracting machine readable decision categories from such raw corpora without manual intervention remains a significant challenge. To address this issue, we propose a framework using large language models (LLMs) that automatically discovers latent semantic dimensions from unstructured text without any predefined schema. The LLM performs unsupervised semantic clustering via hierarchical prompts, autonomously inducing concept categories. We validate our method on Traditional Chinese Medicine (TCM), a domain characterized by highly nested, multi-dimensional knowledge structures. This makes it a challenging and representative benchmark for testing the generalizability of knowledge discovery methods. From 12,163 TCM herb records (64,107 independent short sentences), the DeepSeek-V3.2 model with batch-wise clustering generates 458 raw labels. These labels are further merged into 22 broad semantic categories. The resulting groups can be interpreted as potential decision dimensions or state abstractions for knowledge driven optimization systems. For evaluation, we adopt a dual approach: (1) semantic cosine similarity computed by Qwen3-Embedding-8B shows that 19 concepts achieve an average internal coherence above 60%; (2) domain experts rate the reasonableness of sampled concepts on a 1 to 5 scale, yielding an average score of 4.64. Experimental results demonstrate that our method autonomously induces high quality, interpretable concept taxonomies from large-scale unstructured text. We further validate the transferability of the method on an aircraft assembly manual, where it induces 12 semantically coherent concepts (average example coherence 59.6%) that align well with a domain ontology. This work offers a transferable paradigm for integrating unstructured domain knowledge into intelligent scheduling and optimization frameworks, with potential implications for dynamic scheduling systems.