The world of Virtual Assistants – more SemTech …
Just finished viewing Tom Gruber’s SemTech 2009 presentation Siri, a Virtual Personal Assistant. See the video below:
An absolutely wonderful presentation! Tom Gruber is a really great speaker, and he had a powerful story to tell.
So what are the core capabilities of a Virtual Personal Assistant? Well, according to Gruber they are it:
- Does things for you – focus on Task completion
- Gets what you say – intent understanding via Conversation
- Gets to know you – learns and applies Personal Information
A few slides highlight some key points:
Task Flow Models provide Activity context
The virtual assistant models core task workflows to guide the decision logic when providing services to the user.
Application Architecture – the mother of all Mashups
The Virtual Assistant mashes up Services on the backend, and applies then to domain and task models in the core application tier.
Understanding the Context is key
Multiple contexts are considered when servicing a user’s request. If the context is ambiguous, the application will attempt to disambiguate the context by asking the user questions to resolve the ambiguity.
Here’s a link to the presentation slides from Tom’s talk.