Browse Prior Art Database

Seamless Virtual Assistant Information Feed

IP.com Disclosure Number: IPCOM000235580D
Publication Date: 2014-Mar-10
Document File: 3 page(s) / 34K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed are a system and method for integrating a virtual assistant into a smart phone-based conversation, in which the system continuously and seamlessly processes the speeches by all participants, determines in real time information useful to the speaker associated with this phone, and produces a live stream on a display associated with the smart phone. Additionally, the system alerts the speaker in a non-intrusive manner when new information is added to the feed.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 37% of the total text.

Page 01 of 3

Seamless Virtual Assistant Information Feed

Most smart phones have a standard virtual assistant that is able to provide information on demand. However, the feature lacks the capability for a user to engage with the virtual assistant in a seamless and unobtrusive way as part of natural conversation (i.e., occurring either while the user is using the phone independently or on a live phone call with another party). Existing virtual assistant technology requires that the user take a deliberate action to engage the assistant (e.g., holding down a button, speaking a keyword, etc.). Because the existing technology requires deliberate action to be engaged, many opportunities are missed in which the virtual assistant could provide helpful information to the user.

The novel contribution is a system and method for integrating a virtual assistant into a smart phone-based conversation, in which the system continuously and seamlessly processes the speeches by all participants, determines in real time information useful to the speaker associated with this phone, and produces a live stream on a display associated with the smart phone. Additionally, the system alerts the speaker in a non-intrusive manner when new information is added to the feed. The user can set prioritization criteria for information sorting and display. The system also allows the user to cleanse older and less relevant information.

The system and method also includes a means to directly engage the virtual assistant. The user can simultaneously mute the second party on a phone call and activate the virtual assistant via a physical or logical switch. In addition, the user can use the system in conjunction with continuously listening to all speeches mode and switch exclusive engagement with virtual assistant mode. This allows the user to directly interact with the virtual assistant in response to a live-feed item.

The system and method can immediately notify the user of relevant information relating to a specific contact when the user begins a conversation with that contact. This is done by receiving a contact number when a call is initiated either by the user of the phone, or received from second party. The system retrieves items from the feed that were relevant to the user of this phone during past conversations with the contact, and then automatically displays these items to the user.

The framework is integrated with a smart phone's existing virtual assistant. When enabled, the system continuously listens and processes all words that are spoken

without any direct user action. It can function when the user is using the phone independently or on a live phone call with another party. The user does not need to engage the assistant with a keyword or a physical button, resulting in a seamless interaction. The framework processes all speech on the fly and determines what information it can provide to help the user. It generates useful results based on referencing information for that...