Lifelong Personal Context Recognition

Abstract

We focus on the development of AIs which live in lifelong symbiosis with a human. The key prerequisite for this task is that the AI understands -at any moment in time -the personal situational context that the human is in. We outline the key challenges that this task brings forth, namely (i) handling the humanlike and ego-centric nature of the the user's context, necessary for understanding and providing useful suggestions, (ii) performing lifelong context recognition using machine learning in a way that is robust to change, and (iii) maintaining alignment between the AI's and human's representations of the world through continual bidirectional interaction. In this short paper, we summarize our recent attempts at tackling these challenges, discuss the lessons learned, and highlight directions of future research. The main take-away message is that pursuing this project requires research which lies at the intersection of knowledge representation and machine learning. Neither technology can achieve this goal without the other.

A Context Model for Personal Data Streams

“…and are based on the HETUS (Harmonized European Time Use Surveys) standard. 2 Figures 2 and 3 provide a small, clean and anonymized subset of SU. In both figures, the first part (in white) provides the timestamps when this data were collected.…”

“…Our focus is on the exploitation of data, at run-time, while being collected, as the basis for supporting person-centric services, e.g., predicting human habits or better human-machine interaction. This type of services are in fact core for the development of human-in-the-loop Artificial Intelligence systems [2]. Towards this end, our proposed solution is to represent the input streams, no matter whether coming from sensors or from the user feedback, as sequences of personal situational contexts [7].…”