In the construction industry, the professional evaluation of construction schemes represents a crucial link in ensuring the safety, quality and economic efficiency of the construction process. However, due to the large number and diversity of construction schemes, traditional expert review methods are limited in terms of timeliness and comprehensiveness. This leads to an increasingly urgent requirement for intelligent check of construction schemes. This paper proposes an intelligent compliance checking method for construction schemes that integrates knowledge graphs and large language model (LLM). Firstly, a method for constructing a multi-dimensional, multi-granular knowledge graph for construction standards is introduced, which serves as the foundation for domain-specific knowledge support to the LLM. Subsequently, a parsing module based on text classification and entity extraction models is proposed to automatically parse construction schemes and construct pathways for querying the knowledge graph of construction standards. Finally, an LLM is leveraged to achieve an intelligent compliance check. The experimental results demonstrate that the proposed method can effectively integrate domain knowledge to guide the LLM in checking construction schemes, with an accuracy rate of up to 72%. Concurrently, the well-designed prompt template and the comprehensiveness of the knowledge graph facilitate the stimulation of the LLM’s reasoning ability. This work contributes to exploring the application of LLMs and knowledge graphs in the vertical domain of text compliance checking. Future work will focus on optimizing the integration of LLMs and domain knowledge to further improve the accuracy and practicality of the intelligent checking system.

In the production scheduling of precast concrete components, decision makers often face the challenges of complex decision making and incomplete decision information due to the lack of real-time and comprehensive insights into subsequent production stages after the initial scheduling phase. To address these, this study proposes an action-oriented reinforcement learning (AO-DRL) method aimed at minimizing the maximum completion time. Firstly, the set of unscheduled components is defined as the action space, eliminating the need for designing extensive dispatching rules. Secondly, dynamic processing features that evolve with the production environment are extracted as action representations, providing the agent with comprehensive decision-making information. Thirdly, the Double Deep Q-Network (DDQN) algorithm is employed to train the AO-DRL model, enabling it to capture the dynamic relationship between the production environment and the unscheduled components for effective scheduling decisions. Finally, the proposed approach is validated using randomly generated samples across various problem scales. The experimental results demonstrate that AO-DRL outperforms traditional rule-based methods and heuristic algorithms while exhibiting strong generalization capabilities.