System and method for processing multi-modal communication within a workgroup
First Claim
Patent Images
1. A method of processing multi-modal communications, comprising the steps of:
- intercepting each incoming message of a plurality of messages, wherein said plurality of messages are characterized by at least two different modes, one of said modes being a non-text mode;
converting each intercepted message into a single text format shared by each message;
parsing each message in the shared text format into a list of keywords;
analyzing the list of keyword for each message to generate a respective vector of at least one keyword for each message, wherein said vector is based on a path distance in a semantic hierarchical tree of a dictionary;
calculating a similarity distance between the messages based on their respective vectors of keywords; and
clustering the messages into a plurality of message clusters based upon the calculated similarity distances.
1 Assignment
0 Petitions
Accused Products
Abstract
There is disclosed a system and method for processing multi-modal collaboration. In an embodiment communication received from multiple modes are converted into a common format. Using various conversion modules, the communication may be converted into a common electronic text format (e.g. ASCII text) that contains keywords. Once the communication is converted into a common format, the information contained in the communication may be analyzed and consolidated into related areas or topics. The consolidated information may then be searched for common references in order to augment the information context.
-
Citations
14 Claims
-
1. A method of processing multi-modal communications, comprising the steps of:
-
intercepting each incoming message of a plurality of messages, wherein said plurality of messages are characterized by at least two different modes, one of said modes being a non-text mode; converting each intercepted message into a single text format shared by each message; parsing each message in the shared text format into a list of keywords; analyzing the list of keyword for each message to generate a respective vector of at least one keyword for each message, wherein said vector is based on a path distance in a semantic hierarchical tree of a dictionary; calculating a similarity distance between the messages based on their respective vectors of keywords; and clustering the messages into a plurality of message clusters based upon the calculated similarity distances. - View Dependent Claims (2, 3, 4)
-
-
5. A computer-based system for processing multi-modal communications, comprising:
-
a central processing unit; a real time message monitor component for intercepting each incoming message of a plurality of messages, wherein said plurality of messages are characterized by at least two different modes, one of said modes being a non-text mode; a conversion module for converting each intercepted message into a single shared text format shared by each message; a natural language parsing engine comprising a processor and configured to parse each message in the shared text format into a list of keywords; a digital hierarchical dictionary for calculating a similarity distance between the list of keywords for each message; and a member similarity based clustering algorithm module for clustering the messages into context threads based upon the calculated similarity distances. - View Dependent Claims (6, 7, 8)
-
-
9. A non-transitory data processor readable medium storing data processor code that, when loaded into a data processing device, adapts the device to perform a method of processing multi-modal communications, the data processor readable medium comprising:
-
code for intercepting a plurality of incoming text based messages; code for converting each incoming text based message into a single text format shared by each of said plurality of incoming text based messages; code for intercepting a plurality of incoming audio based messages; code for converting each incoming audio based message into said single text format; code for parsing each of the converted plurality of incoming text based messages and each of the converted incoming audio based messages into a list of keywords; code for analyzing the list of keywords for each message to generate a respective vector of at least one keyword for each message, wherein said vector is based on a path distance in a semantic hierarchical tree of a dictionary; code for calculating a similarity distance between the messages based on their respective vectors of keywords; and code for clustering into topical message clusters based upon the calculated similarity distances. - View Dependent Claims (10, 11, 12, 13, 14)
-
Specification