Collaborative Optimization of Human–Computer Interaction Efficiency and Cognitive Load in Mobile Auditing

Abstract

Mobile auditing has been increasingly recognized as a critical direction in the digital transformation of auditing practices. However, field auditing scenarios are constrained by limited device resources, sensitive data privacy requirements, unstable network conditions, and elevated cognitive load among auditors, all of which substantially hinder human–computer interaction efficiency and audit quality. To address these challenges, a multi-module collaborative optimization framework for human–computer interaction was proposed. Four core technologies were integrated into the framework: non-intrusive cognitive load quantification, lightweight on-device cognitive inference, dynamic user interface information density reconfiguration, and adaptive computation offloading under weak network conditions. Through this integration, end-to-end coordination was achieved, encompassing cognitive state awareness, adaptive interface adjustment, and computational task optimization. To validate the effectiveness of the proposed framework, controlled dual-task experiments were conducted, simulating both static and dynamic interference conditions commonly encountered in realworld field auditing. Performance comparisons between the optimized system and a baseline system demonstrated that cognitive load was significantly reduced, while interaction efficiency and task accuracy were markedly improved. Furthermore, stable system performance was maintained under dynamic interference conditions, alongside lightweight deployment and enhanced privacy preservation capabilities. The proposed approach provides a practical technical pathway for optimizing human–computer interaction in mobile professional productivity tools, enriches interdisciplinary research at the intersection of mobile computing and cognitive engineering, and offers substantial academic and engineering value.