Automated Text-Based Messaging Interaction Using Natural Language Understanding Technologies

• US 20100151889A1
• Filed: 12/11/2009
• Published: 06/17/2010
• Est. Priority Date: 12/11/2008
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Nortel Networks Limited (Nortel Networks Corporation)
• Inventors: Passaretti, Christopher, Buckley, Stephen, Chen, Chun-Yang, Wu, Chingfa, Gulli, Russell
• Granted Patent: US 8,442,563 B2
• Time in Patent Office: Days
• US Class Current: 455/466
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

Automated text-based messaging interaction using natural language understanding technologies enables text-based messages to be received from users and interpreted by a self-service application platform so that the self-service application platform can respond to the text-based messages in an automated manner. The characters and strings of characters contained within the text message are interpreted to extract words, which are then processed using a natural language understanding engine to determine the content of the text-based message. The content is used to generate a response message from static and/or dynamic grammars to automate the process of interacting with a user via text-based messages. Multiple text-based message formats are supported, including text messages transmitted using Short Messaging Service (SMS), instant messaging, chat, and e-mail.

Claims

1. A method of automated text-based messaging interaction using natural language understanding technologies between a user and a self-service application platform, the method comprising the steps of:

receiving, by the self-service application platform, a text-based message from the user;

interpreting characters of the text-based message, by the self-service application platform, to determine words associated with the characters contained in the text-based message;

using natural language understanding, by the self-service application platform, to determine an understanding of a content of the text-based message from the words; and

selecting, by the self-service application platform, one or more grammars based on the understanding to formulate a text-based response message.

2. The method of claim 1, wherein the text-based message is an instant message, and wherein the step of receiving is implemented using an instant messaging client.

3. The method of claim 1, wherein the text-based message is a text message, and wherein the step of receiving is implemented using a Short Messaging Service (SMS) client.

4. The method of claim 1, wherein the text-based message is part of a chat session between the user and the self-service application platform, and wherein response messages from the self-service application platform within the chat session are automatically generated without the intervention of a human agent.

5. The method of claim 1, wherein the step of interpreting characters of the text-based message comprises expanding abbreviations and acronyms contained within the text-based message.

6. The method of claim 5, wherein the step of interpreting characters of the text-based message comprises using the characters to key into a database of abbreviations and acronyms commonly used in text-based messaging.

7. The method of claim 5, wherein the abbreviations and acronyms include sets of letters representing phrases of multiple words.

8. The method of claim 1, wherein the step of interpreting characters of the text-based message comprises fixing misspellings contained within the text-based message.

9. The method of claim 1, wherein the step of interpreting characters of the text-based message comprises the steps of recognizing emoticons and interpreting the emoticons to determine an emotional state of the user.

10. The method of claim 9, further comprising the step of using the determined emotional state when selecting the one or more grammars to formulate the text-based response message.

11. The method of claim 9, further comprising the step of initiating a voice-based session with the user based on the determined emotional state of the user.

12. The method of claim 1, wherein the step of using natural language understanding comprises parsing normal speech-based text patterns contained within the text-based message to discern information contained in the text-based message without requiring the text-based message to conform with a format specific to the self-service application platform.

13. The method of claim 1, wherein the self-service application platform is written using VoiceXML.

14. A method of automated text-based messaging interaction between computer platforms in a service oriented architecture, the method comprising the steps of:

receiving a text-based message by a first computer platform from a second computer platform;

using natural language understanding, by the first computer platform, to parse text patterns contained within the text-based message to discern information contained in the text-based message without requiring the text-based message to conform with a format specific to the first computer platform, to enable the first computer platform to obtain an understanding of a content of the text-based message; and

using the understanding to control an operation of the first computer platform to thereby enable computer-to-computer interaction with the first computer platform without specifying a format of how information should be organized within the text-based messages used to control operation of the first computer platform.

15. A text-based VoiceXML self-service application platform, comprising:

one or more processors; and

computer-readable memory containing data and instructions which, when loaded as control logic into the one or more processors of a computer system, causes the computer system to implement;

a VoiceXML automation engine configured to receive text-based messages;

a natural language speech and text recognition process to interpret characters of the text-based message to determine words associated with the characters contained in the text-based message; and

a natural language understanding process to determine an understanding of a content of the text-based message from the words;

wherein the VoiceXML automation engine uses the content of the text-based message determined using the natural language understanding process to select one or more grammars to formulate a text-based response message.

16. The text-based VoiceXML self-service application platform of claim 15, wherein the natural language understanding process parses normal speech-based text patterns contained within the text-based message to discern information contained in the text-based message without requiring the text-based message to conform with a format specific to the text-based VoiceXML self-service application platform.