# US 7,412,483 B2 · Automated email activity management

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 7,412,483 B2
- Document ID: US7412483B2
- Status: Granted
- Kind: B2
- Application number: 11/031,119
- Filed: 2005-01-07
- Published: 2006-07-27
- Granted: 2008-08-12
- Earliest claimed: 2005-01-07
- Assignees: International Business Machines Corporation
- Inventors: Nicholas Kushmerick; Tessa Ann Lau
- Web page: https://patentgrep.com/patent/US7412483B2

## CPC

- H04L 51/214: using selective forwarding
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- H04L 51/234: for tracking messages
- H04L 67/34: {involving the movement of software or configuration parameters (network booting or remote initial program loading [RIPL] G06F9/4416)}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system for organizing email comprising: (a) a modeler operable to infer a temporal sequential process from a corpus of unlabeled email messages; and (b) a categorizer operable to accept an incoming message and map the aforesaid incoming message to a transition in the aforesaid temporal sequential process.

## Claims

### Claim 1

A system for organizing email, comprising:
a modeler operable to infer a temporal sequential process from a corpus of unlabeled email messages,
wherein said temporal sequential process comprises a finite state machine;
a categorizer operable to accept an incoming message and map said incoming message to a transition in said temporal sequential process;
a first visualizer operable to display a representation of said temporal sequential process,
wherein said visualizer is operable to display a representation of a progression through said temporal sequential process, said progression comprising a change in said temporal sequential process;
a predictor operable to predict a future message based on a progression through said temporal sequential process; and
a second visualizer operable to display a representation of said future message,
wherein said modeler performs:
extracting a selected characteristic from each message;
creating at least one group containing at least one message which exhibits said selected characteristics; and
adding an ungrouped message into a group selected from said at least one group based on the temporal proximity of said ungrouped message and messages within said at least one group.