Dynamic adaptation of non standard service tasks through reinforcement learning driven task technology fit and service interaction

通过强化学习驱动的任务技术匹配和服务交互,实现非标准服务任务的动态适应

阅读:3

Abstract

Non-standard service-oriented microenterprises face significant challenges in digital transformation due to heterogeneous tasks and the absence of standardized workflows. This study proposes a lightweight, embedded platform construction methodology-the Task-Service-HCI (TSH) method-which integrates Task-Technology Fit (TTF), Service Process Customization (SPC), and Human-Computer Interaction (HCI) into a closed-loop mechanism for task recognition, workflow configuration, and interactive feedback. Based on this method, a Reinforcement Learning-driven Task-Technology Fit Optimization (RL-TTFO) system architecture is designed to enable semantic task parsing and adaptive workflow generation.A prototype platform was deployed in the professional organizing industry, collecting behavioral logs and survey data from 300 users. Structural equation modeling results show that task-technology fit has a significant positive effect on user satisfaction (β = 0.62, p < 0.001), with configuration participation playing a mediating role in perceived control (p < 0.01). Regression analysis further indicates that the RL-TTFO mechanism increases usage frequency by 35.4% and improves perceived system intelligence by 27.1% compared with static workflow configurations (p < 0.001). These findings demonstrate that the proposed approach provides a sustainable, low-barrier digital transformation solution for resource-constrained microenterprises operating in highly customized service environments.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。