Evolutionary Multi-Objective Optimization Algorithms (EMOAs) are extensively utilised to address issues involving conflicting objectives. Recent studies suggest that decision-makers (DMs) are typically only concerned with a portion of the Pareto frontier. The Interactive Evolutionary Multi-Objective Optimization Algorithm (iEMOA) has been developed to address this issue by integrating the preference of DM into the optimization process through multiple interactions. However, extant approaches often treat these preferences as static, neglecting the dynamic nature of DM. This paper proposes a preference-based reinforcement learning (PbRL) method that utilises list-wise preferences to dynamically align shifting preference of DM in a multi-objective optimization problem (MOP). First, a Markov decision process (MDP) model for list-wise preference is developed. Second, modifications are made to the reward and resampling mechanisms in the basic deep deterministic policy gradient (DDPG) algorithm. Third, the machine decision-maker (MDM) model is enhanced to account for preference shift. The efficacy of the proposed approach is demonstrated through comparative experiments with state-of-the-art methods, highlighting its superior performance in handling the complex preference behaviours exhibited by real-world DM.

Aiming at problems such as incomplete, inconsistent, and inaccurate requirements that often occur in the process of obtaining high-end equipment functional requirements, this paper presents a requirement quality improvement method. Referring to the agile development theory of requirements engineering, the quality improvement method constructs a functional requirement model based on user stories, defines the concept of functional requirement quality, designs functional requirement quality evaluation criteria, and constructs a functional requirement quality evaluation process. A case study and sensitivity analysis of new energy vehicle requirement development are conducted to confirm the feasibility and effectiveness of the method, and the experimental results show the superiority of the proposed method in improving the quality of high-end equipment functional requirements.