Construction of a Knowledge Graph for Computer Network Fault Diagnosis in Big Data Environments and Research on Users' Psychological and Emotional Health
Shiji Huang, Jingxuan LiuAbstract
Objective
This study aims to construct a knowledge graph for computer network fault diagnosis in big data environments and investigate its impact on the psychological and emotional health of technical operators. The research seeks to explore how intelligent diagnostic tools affect users' work-related stress, anxiety levels, and overall mental well-being in high-pressure IT environments.
Subjects and Methods
The study involved 150 network administrators and IT professionals. A comprehensive knowledge graph was developed by integrating multi-source data including network device logs, fault records, and expert knowledge. Participants performed diagnostic tasks using both the knowledge graph system and traditional methods. Psychological and emotional health was assessed using standardized instruments including the Perceived Stress Scale (PSS), Generalized Anxiety Disorder scale (GAD-7), and User Experience Questionnaire (UEQ), with pre- and post-intervention measurements.
Results
The knowledge graph achieved 88.5% accuracy in fault diagnosis with 15,231 entities and 42,567 relationships. System usage significantly reduced work-related stress by 35% (p < 0.01) and decreased anxiety symptoms by 28% (p < 0.05) compared to traditional methods. Regression analysis revealed that the system's reasoning capability positively influenced users' psychological adaptation (β = 0.68, p < 0.001), while reducing decision-making anxiety by 40%. User satisfaction increased by 45% with the knowledge graph approach.
Conclusions
The knowledge graph significantly enhances both network fault diagnosis efficiency and users' psychological well-being. This research demonstrates that intelligent diagnostic systems can reduce technical stress and anxiety while improving job performance, offering valuable insights for developing human-centered IT management tools that support both operational excellence and workplace mental health.
Corresponding Author
Jingxuan Liu, School of Information Engineering, Hunan Automotive Engineering Vocational University, Zhuzhou, 412001, China.