Machine learning based electronic messaging system

Electrical computers and digital processing systems: multicomput – Computer conferencing – Demand based messaging

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C709S201000, C709S220000

Reexamination Certificate

active

06424997

ABSTRACT:

BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention generally relates to an electronic message classification system and, more particularly, to an electronic messaging system that assigns an incoming message a set of classification outputs in order to automatically effect an appropriate action on the incoming message.
2. Background Description
Businesses and institutions receive and generate many electronic messages in the course of their commerce and activities. These electronic messages are typically electronic mail (e-mail) messages routed, via a mail system (e.g., server), to a specific individual or individuals. Once the specific individual or individuals receive the message, it is opened, read, and an appropriate action is taken, such as, for example, forwarding the message to another individual, responding to the message or performing countless other actions.
In typical electronic mail systems, the message is routed to a server and is stored on the server until the individual requests the message. At that time, the server simply finds the appropriate message by searching the headers of messages residing on the server, and forwarding the appropriate message to the requesting individual. The server typically does not perform any other activities, especially those activities requested by the message itself. This is because only the header information associated with the requesting individual is read, and not any other information within the message.
To further complicate matters, in large institutions, such as banks, electronic messages are routed to the institution generally, and not to any specific individual. In these instances, several individuals may have the sole function of opening and reading the incoming messages, and to properly route the messages so that, for example, an appropriate action by a qualified specialist can be performed on the message. As can be imagined, this is very time consuming and inefficient, especially when messages need expert attention in several divergent fields.
It is desirable, however, to have an electronic mail system that effectively and efficiently performs activities on the incoming messages. These activities may include prioritizing a message or, for example, automatically generating a report or response to the incoming message. This would be preferably performed without assistance from a qualified specialist or other individual first having to open, read and route the incoming message.
In order to perform these activities, certain information must be extracted from the electronic messages, such as a desired activity to be taken by a qualified specialist. To this end, considerable effort is now being made to develop software for the extraction of information from electronic messages. Such software is generally in the field of knowledge based or expert systems and uses such techniques a s parsing and classifying. The general applications, in addition to information extraction, include classification and categorization of natural language documents and automated electronic data transmission processing and including e-mail and facsimile.
SUMMARY OF THE INVENTION
It is therefore an object of the present invention to provide an electronic messaging system that assigns an incoming message a set of classification outputs in order to automatically effect an appropriate action on the incoming message.
The present invention describes a machine learning based electronic mail system. The system and method of the present invention receives incoming messages and classifies the information within the message. The classification is then used to automatically effect an appropriate action on the incoming message. These actions include, amongst other actions, (i) routing a message, (ii) prioritizing a message, (iii) automatically generating a response to the message, (iv) providing input to a report generator, or (v) initiating or continuing a dialog between the sender and the messaging system.
In preferred embodiments, a classifier and action selection module analyzes the incoming message and classifies the messages with associated confidence levels, which may include analyzing the electronic message by tokenization of the text, morphological analysis of the text, and other well known processes. According to the method and system of the present invention, the classifier and action selection module then determines the appropriate action to effect on the message.


REFERENCES:
patent: 5283856 (1994-02-01), Gross et al.
patent: 5369570 (1994-11-01), Parad
patent: 5377354 (1994-12-01), Scannell et al.
patent: 5608874 (1997-03-01), Ogawa et al.
patent: 6094649 (2000-07-01), Bowen et al.
patent: 6256773 (2001-07-01), Bowman-Amuah
patent: 6275850 (2001-08-01), Beyda et al.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Machine learning based electronic messaging system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Machine learning based electronic messaging system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Machine learning based electronic messaging system will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2905759

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.