RSS

The Bulletin

New virtual assistant anticipates needs during conversation

Posting in Design

While Apple is trying to improve Siri -- the virtual personal assistant on the iPhone -- by making her more witty and "engaging," a startup is taking idea of the virtual assistant to a new level.

The product is called MindMeld. It's an iPad app from Expect Labs that, instead of answering a your question, anticipates what useful information you might need while listening to your conversations. Check out the video:

According to Technology Review, the company plans to release the product in a few weeks and license the "anticipatory computing engine" to businesses later this year. As Jessica Leber points out, it could be a benefit to businesses:

[T]his could give speech apps on tablets, phones, car dashboards, and elsewhere new capabilities. At a large workplace, for example, a business could build software that pulls up old meeting notes during conference calls by accessing document servers and calendars. A call center company could use it to bring up purchase histories as representatives talk to customers.

And the technology behind the app is quite impressive. When it hits the market it will be the first product with these capabilities. Here's how the company describes the three main components of the "anticipatory computing engine:"

1. Real-Time, Multi-Party Conversation Analysis: Our platform is designed to analyze and understand multiple concurrent streams of conversational dialogue in real-time. It continuously analyses audio signals and attempts to understand their underlying meaning. Based on this understanding, it not only attempts to identify key concepts and topics related to your conversation, but it also uses language structure and analysis to infer what types of information you may find most useful.

2. Continuous, Predictive Modeling: Our platform observes conversations over time and generates a model to represent the meaning of each conversation. This model changes from second-to-second as the conversation evolves. This model is then extrapolated to predict the topics, concepts and related information that may be relevant in the future. In essence, this platform analyzes and understands the past ten minutes of a conversation in order to predict what may be relevant in the next ten seconds.

3. Proactive Information Discovery: Our platform does not wait for a user to explicitly ask for information. Instead, it uses its underlying predictive model to identify information that is most likely to be relevant at every point in time. It then proactively finds and retrieves this information - from across the web or from a user’s social graph – and delivers this information to the user, in some cases before they even request it.

And while the technology relies on voice recognition technology (which can be frustratingly inaccurate), the company says that because the technology listens passively instead of trying to meet specific demands it can "tolerate occasional inaccuracies."

So, is this something you would use in your business meetings or conversations. Or would it just become distracting?

— By on January 18, 2013, 5:23 AM PST

Tyler Falk

Contributing Editor

Tyler Falk is a freelance journalist based in Washington, D.C. Previously, he was with Smart Growth America and Grist. He holds a degree from Goshen College. Follow him on Twitter. Disclosure