Relationship management system and method using asynchronous electronic messaging

• US 6,668,281 B1
• Filed: 06/10/1999
• Issued: 12/23/2003
• Est. Priority Date: 06/10/1999
• Status: Expired due to Term

• Current Assignee: General Interactive Incorporated
• Original Assignee: General Interactive Incorporated
• Inventors: Ayyadurai, V. A. Shiva
• Primary Examiner(s): Jean, Frantz B.
• Application Number:
  US09/329,500
• Time in Patent Office: 1,657 Days
• Field of Search: 709/223, 709/203, 709/206, 709/201, 709/200, 709/207, 709/227, 709/226, 709/217, 709/238, 709/246, 379/93.24, 379/88.13, 379/88.22, 379/88.05, 379/100.01, 707/1, 707/500, 455/412, 382/100, 382/137
• US Class Current: 709/223
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

A system and method for automating workflow related to the reception, review, distribution, and disposition of client contact through electronic communications. All types of received contact messages are converted to e-mail messages and automatically processed using natural language processing to generate one or more replies. The original message and the reply(ies) are distributed to one or more workflow automation databases, such as customer care databases, direct mail campaign databases, and sales lead databases, for transmission of the reply(ies) to the originator. The method can be realized in a single database or across multiple databases, located on a single computer platform or distributed across multiple networked computer platforms.

Claims

1. A computer-implemented method for performing workflow comprising the steps of:

(1) receiving a first message from an originator via an electronic reception means;

(2) storing said first message in a first database subsystem;

(3) processing said first message to generate a proposed reply message by performing unsupervised classification, said processing including assignment of properties of said message using natural language processing, said properties including an author attitude, issues presented, requests presented, an author type, and an author education level;

(4) storing said reply message in said first database subsystem;

(5) selecting and extracting said first message and said reply message from said first database subsystem;

(6) transferring said extracted first message and extracted reply message to one or more workflow database subsystems; and

(7) transmitting said reply message to said originator via an electronic transmission means.

2. The computer-implemented method for performing workflow of claim 1, wherein said electronic reception means comprises an e-mail reception means.

3. The computer-implemented method for performing workflow of claim 2, wherein said e-mail reception means further comprises a network and an e-mail transfer protocol.

4. The computer-implemented method for performing workflow of claim 3, wherein said e-mail transfer protocol further comprises the Simple Mail Transfer Protocol.

5. The computer-implemented method for performing workflow of claim 1, wherein said electronic transmission means comprises an e-mail transmission means.

6. The computer-implemented method for performing workflow of claim 5, wherein said e-mail transmission means further comprises a network and an e-mail transfer protocol.

7. The computer-implemented method for performing workflow of claim 6, wherein said e-mail transfer protocol further comprises the Simple Mail Transfer Protocol.

8. The computer-implemented method for performing workflow of claim 1, wherein said step of receiving a first message further comprises the step of converting a written document to an electronic text-based message.

9. The computer-implemented method for performing workflow of claim 8, wherein said step of converting a written document further comprises the step of Optical Character Recognition.

10. The computer-implemented method for performing workflow of claim 9, wherein said step of converting a written document further comprises the step of facsimile document transmission.

11. The computer-implemented method for performing workflow of claim 8, wherein said step of receiving a first message further comprises the step of converting an e-commerce transaction to an e-mail message.

12. The computer-implemented method for performing workflow of claim 8, wherein said step of receiving a first message further comprises the step of converting an Internet web form to an e-mail message.

13. The computer-implemented method for performing workflow of claim 8, wherein said step of receiving a first message furtherer comprises the step of converting data from a card reader to an e-mail message.

14. The computer-implemented method for performing workflow of claim 8, wherein said step of receiving a first message further comprises the step of converting barcode scanner data to an e-mail message.

15. The method of claim 1, said processing further including performing feature extraction to derive one or more output signals, said feature extraction being based on one or more of pattern recognition procedures selected from the group consisting essentially of keyword analysis, morphology, natural language processing, thesauri, co-occurrence statistics, syllabic analysis and word analysis.

16. The method of claim 15, wherein the one or more output signals are selected from the group consisting essentially of keyword frequencies, co-occurrence statistics, a dimensionally-reduced representation of the keyword frequencies, phoneme frequencies, structural pattern statistics for sentences, paragraphs, and pages, estimated education level of the author based on word choices and complexity of sentence structure, and customer type.