Reference model of next-generation digital personal assistant: integrating proactive behavior

ABSTRACT

Digital personal assistants such as Apple's Siri or Google Assistant emerge and penetrate our everyday lives, acting as digital helper for searching information or executing simple tasks. However, with their primarily reactive behavior through conversational input current assistants are rather limited in their support. This paper proposes a novel reference model of next-generation digital personal assistants which integrates the user's goals and a proactive behavior of support to achieve these goals. We report the findings of our focus group discussion with 11 researchers to develop and substantiate our model as well as identify common areas of human-centered assistance, namely mental, physical, activity, environment, social, and technology support. We further show and discuss important research challenges of next-generation assistants. Using our proposed reference model, researchers in the community can now design and classify their future personal assistants.

References

1. Caceres, R., and Friday, A. Ubicomp Systems at 20: Progress, Opportunities, and Challenges. IEEE Pervasive Computing, 1 (2011), 14--21.
2. Isbell, C. L., and Pierce, J. S. An IP Continuum for Adaptive Interface Design. In HCII'05 (2005).
3. Lane, N. D., Miluzzo, E., Lu, H., Peebles, D., Choudhury, T., and Campbell, A. T. A Survey of Mobile Phone Sensing. Communications Magazine 48, 9 (2010), 140--150.
4. Lim, B. Y., and Dey, A. K. Investigating Intelligibility for Uncertain Context-aware Applications. In UbiComp'11, ACM (2011), 415--424.
5. Luger, E., and Sellen, A. Like Having a Really Bad PA: The Gulf between User Expectation and Experience of Conversational Agents. In CHI'16, ACM (2016), 5286--5297.
6. Meurisch, C. Intelligent Personal Guidance of Human Behavior Utilizing Anticipatory Models. In UbiComp'16: Adjunct, ACM (2016), 441--445.
7. Meurisch, C., Jeutter, B., Schmidt, W., Gündling, N., Schmidt, B., Herrlich, F., and Mühlhäuser, M. An Extensible Pervasive Platform for Large-scale Anticipatory Mobile Computing. In COMPSAC'17, IEEE (2017).
8. Pejovic, V., and Musolesi, M. Anticipatory Mobile Computing for Behaviour Change Interventions. In UbiComp'14: Adjunct, ACM (2014), 1025--1034.
9. Pejovic, V., and Musolesi, M. Anticipatory Mobile Computing: A Survey of the State of the Art and Research Challenges. ACM Computing Surveys 47, 3 (2015), 47.
10. Sun, Y., Yuan, N. J., Wang, Y., Xie, X., McDonald, K., and Zhang, R. Contextual Intent Tracking for Personal Assistants. In KDD'16, ACM (2016), 273--282.
11. Sutton, R. S., and Barto, A. G. Reinforcement learning: An introduction, vol. 1. MIT press Cambridge, 1998.
12. Weiser, M. The Computer for the 21st Century. Scientific American 265, 3 (1991), 94--104.

Index Terms

• Applied computing

  • Law, social and behavioral sciences

• Information systems

  • Information systems applications