System for identifying word patterns in text

• US 7,814,088 B2
• Filed: 05/12/2008
• Issued: 10/12/2010
• Est. Priority Date: 03/07/2001
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Simpson, Don M., Usey, Robert W. Jr.
• Primary Examiner(s): NGUYEN, CAM LINH T
• Application Number:
  US12/119,349
• Publication Number:
  US 20080208569A1
• Time in Patent Office: 883 Days
• Field of Search: 707 1- 6, 707705-708, 707/739, 707/771, 707/794, 706/55
• US Class Current: 707/708
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A system for identifying word patterns in text is conducted in real time and is highly suitable for network and Internet use. The system comprises a semantic network that may be compiled on a local computer or at a remote host and a software text analysis module for receiving the text to be analyzed, parsing the text, submitting the text to the semantic network, and receiving the results. Recognized, words are then examined, together with surrounding words in the text to determine whether the words are part of a word pattern. Word patterns are located at nodes in the semantic network in a hierarchical structure, and certain word patterns correspond to objects of the semantic network. When all word patterns involving a word are located, links are followed to objects corresponding to the word patterns. Several nodes may point to a single object, but each object is represented only once in the semantic network. Identified objects may thus be identified in real time, as the text streams through the text analysis module.

Claims

1. A system for identifying objects referenced in a stream of text, the system comprising:

an input pipeline configured to receive an incoming stream of text comprised of words;

a text analysis module configured to consult a semantic network to automatically identify one or more word patterns in the incoming stream of text, such that each word in the incoming stream is searched once in the semantic network, to break the stream of text into individual words, to analyze each word in an order of occurrence of the word in the stream of text by comparing the individual words to identified words in the semantic network, and to, upon finding a match between an individual word in the stream of text and an identified word in the semantic network, compare the individual word and an adjacent word of the stream of text to a word pattern in the semantic network; and

an object association module configured to reference a known object within the semantic network, the known object identified by a word pattern of the semantic network.

2. The system of claim 1, wherein the semantic network is configured to be loaded substantially entirely into a common RAM memory space of a processor, and wherein the text analysis module is configured to consult the semantic network within the RAM memory.

3. The system of claim 1, wherein the input pipeline is further configured to divide the stream of text into a plurality of threads such that the semantic network may be consulted concurrently for words in each of the plurality of threads.

4. The system of claim 1, further comprising a word pattern comparison module configured to consult the semantic network in a hierarchical order moving from identified nodes to related nodes linked with the identified nodes.

5. The system of claim 1, wherein the text analysis module is further configured to examine words in the stream of text in a sequential order as the words are received and format the stream of text to represent identified objects without persistently storing the stream of text.

6. The system of claim 1, wherein the text analysis module is configured to continually add words of the stream of text to recognized word patterns and compare the result to other word patterns in the semantic network until no more word patterns are located.

7. The system of claim 1, further comprising a compilation module configured to present the identified known objects to a user.

8. The system of claim 7, wherein the compilation module is configured to present the identified known objects to a user by providing links between identified word patterns in the stream of text and objects in a knowledge base to which the word patterns identify.