Summary of Workr: Occupation Inference For Intelligent Task Assistance, by Yonchanok Khaokaew et al.
WorkR: Occupation Inference for Intelligent Task Assistance
by Yonchanok Khaokaew, Hao Xue, Mohammad Saiedur Rahaman, Flora D. Salim
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces WorkR, a framework for digital assistants that leverages passive sensing to capture pervasive signals from various task activities, addressing the challenge of providing personalized support without continuous user input. The authors argue that signals from application usage, movements, social interactions, and environment can inform a user’s occupation. A Variational Autoencoder (VAE) is used to derive latent features for training models to infer occupations. Experimental results on an anonymized dataset demonstrate accurate inference of occupations with more than 91% accuracy across six ISO categories. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps digital assistants learn what people are doing and provide better support without asking them questions. Right now, users have to tell the assistant what they’re doing, but this can be hard when someone is switching between jobs or tasks quickly. The researchers created a new framework called WorkR that uses sensors to detect what people are doing and figure out their job based on patterns in how they use apps, move around, interact with others, and more. They tested it on a dataset and found that it could accurately guess occupations over 91% of the time. |
Keywords
* Artificial intelligence * Inference * Variational autoencoder
