The development of Internet of Things (IoT) technology has driven the widespread adoption of smart homes. Predicting indoor behavior patterns is of great significance for planning future life, guiding daily habits, and detecting abnormal behaviors. However, current indoor behavior prediction methods primarily focus on predicting individual-specific actions or activities, lacking a comprehensive approach to forecasting overall behavior patterns and exhibiting lower stability and accuracy in long-term prediction tasks. To achieve precise and long-term prediction of complex indoor human behaviors, this article proposes a novel method for behavior prediction with attention mechanism (BPAM), designed to predict users’ behavioral models while enabling timely detection of abnormal behaviors. Specifically, 1) we use passive infrared (PIR) sensors to capture the trajectory of a person moving indoors every day and model it as a directed graph; 2) we use graph convolutional networks (GCNs) to capture the features of a person’s daily behavior patterns and fuse the temporal information into the features; and 3) we develop an inference module that combines attention mechanism and long short-term memory (LSTM) networks to infer behavior patterns for the next days. Experimental results demonstrate that this method outperforms traditional approaches across multiple evaluation metrics, offering an effective solution for indoor behavior prediction.

Process models are frequently used in software engineering to describe business requirements, guide software testing and control system improvement. However, traditional process modeling methods often require the participation of numerous experts, which is expensive and time-consuming. Therefore, the exploration of a more efficient and cost-effective automated modeling method has emerged as a focal point in current research. This article explores a framework for automatically generating process models with multi-agent orchestration (MAO), aiming to enhance the efficiency of process modeling and offer valuable insights for domain experts. Our framework MAO leverages large language models as the cornerstone for multi-agent, employing an innovative prompt strategy to ensure efficient collaboration among multi-agent. Specifically, 1) Generation: The first phase of MAO is to generate a slightly rough process model from the text description; 2) Refinement: The agents would continuously refine the initial process model through multiple rounds of dialogue; 3) Reviewing: Large language models are prone to hallucination phenomena among multi-turn dialogues, so the agents need to review and repair semantic hallucinations in process models; 4) Modifying: The agents utilize external tools to test whether the generated process model contains format errors, and then adjust the process model to conform to the output paradigm. The experiments demonstrate that the process models generated by our framework outperform existing methods and surpass manual modeling by 89%, 61%, 52% and 75% on four different processes, respectively.