Browse Prior Art Database

Dynamic insertion of related media content based on active group conversations Disclosure Number: IPCOM000187930D
Original Publication Date: 2009-Sep-18
Included in the Prior Art Database: 2009-Sep-18
Document File: 3 page(s) / 26K

Publishing Venue



Proposed is a system for introducing dynamic and interactive secondary media hooks into real time media conversations to provide relevant material and targeted advertisements to a group.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 44% of the total text.

Page 1 of 3

Dynamic insertion of related media content based on active group conversations

It is quite common for people to communicate via voice over a computer or Internet capable device in order to have a conversation with multiple participants. These systems often support an interactive display device (i.e. monitor with mouse, touch screen display, etc.) that can provide a secondary form of user interaction in the context of a active communication (such as displaying the length of call, current caller, current caller location, etc.).

Voice over Internet Protocol (VoIP) providers, modern cell phone devices, and online gaming communities are all examples of internet capable devices that transmit audio content to one or more participants in a system that is capable of displaying secondary visual information to the current user. These systems are often subsidized via traditional advertising models, or require an active subscription in order to leverage the service provided. Advertising models are often based on a user profile filled in upon use, and can be augmented via previous user's click through behavior.

In this publication, proposed is a system for introducing interactive secondary visual hooks into real time audio-based conversation systems in order to provide relevant related content for interaction on a interactive display device about the current discussion in order to provide a superior system for communication, or a relevant model for inserting or augmenting current voice communication networks to provide targeted advertisements. This system would differentiate current service providers in its ability to provide deeper context to the current conversation, or support a more optimal ad delivery system to provide a more compelling service to both the end user and advertiser.

The system provides hooks into collaborative audio applications to identify keywords in the context of the active conversation via real-time speech to text translation systems in order to surface relevant related media or advertising to one or more conversation participants via an interactive medium (such as a touch screen display).

During an active audio conversation, an end-users voice is translated via computer from audio to text format and searched for relevant keywords. Real-time speech to text translation is provided by multiple products today. These systems vary in their sophistication and ability to determine the subject of a particular conversation. They are often used in compliance systems in order to ensure data is not leaked out of the enterprise, or they are used in real time language translation systems in order to convert the input from one language to another (i.e. English to French).

Actual translation of the conversation may occur on the end-user client device, at an intermediary service provider, or at any of the devices that are active participants in the audio conversation. The ability to enable speech...