Search

Visual Performance Evaluation Model Construction and Generative AI Prompt Template Design for OA Form Interfaces in Smart Office Scenarios

Author(s)

Ying Liu, Zhigang Hu

Affiliation(s)

Shaanxi University of Science and Technology, Xi'an, Shaanxi, China

Abstract

OA form interfaces serve as critical nodes for human-computer interaction in smart office scenarios, and their visual design quality directly affects user operational efficiency and cognitive experience. Addressing the gaps in existing evaluation research—namely the lack of systematic weight derivation and operational scoring criteria tailored to the B-end scenario of OA forms, and the absence of executable visual design standards for generative AI tools—this study integrates literature review, vendor case analysis, questionnaire survey (n=386), and user interviews (n=12) to construct a visual performance evaluation system for OA form interfaces comprising 5 dimensions and 15 indicators. The Analytic Hierarchy Process (AHP) is employed to derive indicator weights: Information Architecture (0.309) > Layout Rationality (0.234) > Visual Clarity (0.215) > Interaction Usability (0.168) > Aesthetic Consistency (0.074). Pairwise comparison weights exhibit significant ranking differences relative to direct scoring, revealing that information architecture and layout constitute the structural priority dimensions of visual performance. Furthermore, graded checklist scoring criteria are developed for the 15 secondary indicators, and a Visual Performance Evaluation (VPE) linear weighted model is constructed (inter-rater reliability ICC = 0.87). The checklist criteria are transformed into 22 prompt parameters through direct mapping, combinatorial mapping, and constraint mapping, forming a standardized AI prompt template. A controlled experiment (n=54) demonstrates that using the template increases the mean VPE score of AI-generated interfaces by 27.8% (p < 0.001), with more pronounced improvements in visual dimensions whose parameters exhibit higher executability. This study provides an operational quantitative evaluation tool for OA system interface design optimization and offers a methodological reference for translating design evaluation knowledge into generative AI prompts.

Keywords

Smart Office; OA Form Interface; Visual Performance; Analytic Hierarchy Process; Checklist Scoring Criteria; AI-Assisted Design

References

[1]iResearch. 2024 China Collaborative Office Platform Industry Research Report. Shanghai: Shanghai iResearch Market Consulting Co., Ltd., 2024. [2]Saaty T L. The Analytic Hierarchy Process: Planning, Priority Setting, Resource Allocation. New York: McGraw-Hill, 1980. [3]Sanders M S, McCormick E J. Human Factors in Engineering and Design. 7th ed. New York: McGraw-Hill, 1993. [4]Chen X Q, Huang L Q, Li M Z. Visual Search Performance Research on Intercity Logistics APP Interface Navigation Design. Packaging Engineering, 2021, 42(8): 198-204. [5]Yang M H, Yang J M, Qian X S. Research on Visual Saliency Evaluation in Decision Support System Interface Design. Packaging Engineering, 2021, 42(20): 77-84. [6]Wu X L, Xue C Q, Gedeon T, et al. Visual Search Experiment of Information Features in Digital Monitoring Task Interfaces. Journal of Southeast University (Natural Science Edition), 2018, 48(5): 807-814. [7]Wu X L, Gedeon T, Xue C Q, et al. Comparison of Consistency Effects Between Fixation/Saccade Indicators and Pupil Dilation Amplitude in Information Feature Search. Journal of Computer-Aided Design & Computer Graphics, 2019, 31(9): 1636-1644. [8]Wu X L, Xu P P, Jiang X M. Research on Color Hierarchy Coding of Industrial Monitoring Interfaces Based on Attentional Capture. Industrial Engineering and Management, 2022, 27(4): 32-38. [9]Nielsen J. Usability Engineering. San Francisco: Morgan Kaufmann, 1993. [10]Nielsen J. 10 Usability Heuristics for User Interface Design. (1994-04-24)[2024-12-15]. https://www.nngroup.com/articles/ten-usability-heuristics/. [11]ISO 9241-11:2018. Ergonomics of human-system interaction — Part 11: Usability: Definitions and concepts. Geneva: ISO, 2018. [12]Saaty T L. Decision Making with Dependence and Feedback: The Analytic Network Process. 2nd ed. Pittsburgh: RWS Publications, 2001. [13]Ou Yang Y P, Shieh H M, Leu J D, et al. A novel hybrid MCDM model combined with DEMATEL and ANP with applications. International Journal of Operations Research, 2008, 5(3): 160-168. [14]Tzeng G H, Chiang C H, Li C W. Evaluating Intertwined Effects in E-learning Programs: A Novel Hybrid MCDM Model Based on Factor Analysis and DEMATEL. Expert Systems with Applications, 2007, 32(4): 1028-1044. [15]Tzeng G H, Huang J J. Multiple Attribute Decision Making: Methods and Applications. Boca Raton: CRC Press, 2011. [16]Shao Q G, Liou J J H, Weng S S, et al. Improving the Green Building Evaluation System in China Based on the DANP Method. Sustainability, 2018, 10(4): 1173. [17]Yu N, Huang Y T. Important Factors Affecting User Experience Design and Satisfaction of a Mobile Health App—A Case Study of Daily Yoga App. International Journal of Environmental Research and Public Health, 2020, 17(19): 6967. [18]Ji Y D, Zhao M, Zhao W. Evaluation of Ecological Dominance of Industrial Chain Leader Enterprises Based on Grounded Theory: A Scale Development. Science & Technology Progress and Policy, 2024, 41(6): 86-96. [19]Benaida M. Developing and Extending Usability Heuristics Evaluation for User Interface Design via AHP. Soft Computing, 2023, 27(14): 9693-9707. [20]Ouyang W M, Du H M, Jiang J J, et al. Research on Aesthetic Design of In-Vehicle Infotainment System Interfaces. Packaging Engineering, 2025, 46(12): 274-285. [21]Ayağ Z, Samanlioglu F. A hesitant fuzzy linguistic terms set-based AHP-TOPSIS approach to evaluate ERP software packages. International Journal of Intelligent Computing and Cybernetics, 2021, 14(1): 54-77. [22]Zhu D, Xu Y, Ma H, et al. Building a Three-Level User Experience (UX) Measurement Framework for Mobile Banking Applications in a Chinese Context: An Analytic Hierarchy Process (AHP) Analysis. Multimodal Technologies and Interaction, 2022, 6(9): 83. [23]Zhang N, Wang J M, Yang Y P. Evaluation Method for Aesthetic Image of Human-Machine Interface Morphological Element Layout Design. Mechanical Science and Technology for Aerospace Engineering, 2015. [24]Zhang R J, Wang M X, Guo Y P, et al. Human-Machine Interface Design Evaluation for Oilfield Water Injection System Platforms. Journal of Machine Design, 2021, 41(7): 118-125. [25]Xu F H, Zhang L. Research on Human-Factor Suitability Evaluation System for Smartphone APP Interaction Interfaces. Chinese Journal of Ergonomics, 2018, 24(3). [26]Wu J W, Sun J L, Li M. Research on Usability Evaluation of WeChat Mini-Program Interface Design Based on Entropy Weight Method. Packaging Engineering, 2021, 42(12): 191-196. [27]Liu V, Chilton L B. Design Guidelines for Prompt Engineering Text-to-Image Generative Models//Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'22). New Orleans: ACM, 2022: Article 384. [28]Goloujeh A M, Sullivan A, Magerko B. Is It AI or Is It Me? Understanding Users' Prompt Journey with Text-to-Image Generative AI Tools//Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'24). Honolulu: ACM, 2024. [29]Wang Z, Huang Y, Ma L, et al. PROMPTCHARM: Text-to-Image Generation through Multi-modal Prompting and Refinement//Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'24). Honolulu: ACM, 2024.