Method and system for text analysis based on the tagging, processing, and/or reformatting of the input text

• US 6,658,377 B1
• Filed: 06/13/2000
• Issued: 12/02/2003
• Est. Priority Date: 06/13/2000
• Status: Expired due to Term

• Current Assignee: BCS Software LLC (d/b/a Bluebonnet Consulting Services & Software)
• Original Assignee: Prospectus, Inc.
• Inventors: Samzelius, Jan, Jonsson, Marcus, Pang, Christianne, Anward, Jan
• Primary Examiner(s): Edouard, Patrick N.
• Application Number:
  US09/593,731
• Time in Patent Office: 1,267 Days
• Field of Search: 704/9, 704/10, 704/1, 707/530, 707/531, 707/532, 707/533
• US Class Current: 704/9
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking

Abstract

A method and system are provided for text analysis. A computer is used to analyze, parse, and manipulate natural language text according to a series of specific steps. Text is decomposed into small, homogenous segments that can be readily correlated to one another, to quantitative data, or to a knowledge database. The segments generated at the completion of the text analysis can then be further processed, for example, by a computer to derive statistical information, to generate a report, or to build a knowledge database.

Claims

1. An article of manufacture embodying a program of instructions executable by a computer, the program of instructions comprising:

tagging an input text;

processing the tagged input text, comprising;

(a) searching the tagged input text to identify at least one defined combination or condition, wherein each combination or condition is associated with at least one action, and

(b) performing at least one action, which is associated with each identified combination or condition, to the input text;

performing the text processing steps until the processed text matches a text template; and

generating at least one homogeneous text segment.

2. The article of manufacture of claim 1, further comprising instructions for deriving information from the at least one text segment.

3. The article of manufacture of claim 2 further comprising instructions for generating a report from the derived information.

4. A computer-implemented method for analyzing input text, comprising:

tagging the input text;

performing a text processing operation to reformat the tagged input text, comprising;

(a) searching the tagged input text to identify at least one defined combination or condition, wherein each combination or condition is associated with at least one action, and

(b) performing at least one action, which is associated with each identified combination or condition, to the input text;

performing the text processing steps until the processed text matches a template; and

generating at least one homogeneous text segment.

5. A computer-implemented method for generating a report from survey data, comprising:

analyzing the survey data using a computer;

generating, using a computer, at least one homogenous text segment that can be automatically processed, wherein the at least one text segment matches a template;

processing the at least one text segment using a computer; and

generating a report, using a computer, of survey data.

6. A computer for communication with an electronic network, the computer comprising:

means for tagging an input text;

means for processing the tagged input text, comprising;

(a) means for identifying at least one defined combination or condition in the tagged input text, wherein each combination or condition is associated with at least one action, and

(b) means for performing at least one action, which is associated with each identified combination or condition, to the input text;

means for performing the text processing steps until the processed text matches a text template; and

means for generating at least one homogenous text segment that can be automatically processed;

wherein the at least one homogenous text segment can be computer-processed to generate a report.

7. A system for text analysis, comprising:

a computer;

a tagging component accessible to the computer;

a text processing component accessible to the computer, the text processing component operable to reformat the text to generate at least one homogeneous text segment that can be automatically processed, wherein the at least one text segment matches a template; and

an information deriving component accessible to the computer.

8. The system of claim 7, further comprising at least one database accessible to the computer.

9. A method for computerized text analysis, comprising:

tagging a text;

searching the tagged text to identify at least one defined combination or condition, wherein each combination or condition is associated with at least one action;

performing a text processing operation on the tagged input text, the operation comprising one or more actions, associated with each identified combination or condition, selected from the group consisting of;

performing a first text splitting step,

reducing the number of words in the text,

processing an idiomatic expression in the text,

performing a first unnecessary word deletion step,

performing a first word re-tagging step,

splitting the text at a connective word,

performing a first word combining step,

marking prepositional phrases in the text,

performing a second text splitting step,

performing a second unnecessary word deletion step,

performing a second word combining step,

performing a second word re-tagging step, and

performing at least one simplification step; and

performing the searching and processing steps until the processed text matches a text template; and

generating a homogoneous text segment.

10. The method of claim 9 further comprising preparing the text before the text processing operation is performed.

11. The method of claim 10, wherein preparing the text comprises one or more actions selected from the group consisting of:

checking spelling,

adding punctuation marks,

replacing punctuation marks,

marking the ends of sentences and paragraphs, and

conforming the spacing between words, sentences and paragraphs.

12. A method for computerized text analysis, comprising:

tagging a text;

searching the tagged text to identify at least one defined combination or condition, wherein each combination or condition is associated with at least one action;

performing a text processing operation on the tagged input text, the operation comprising one or more actions, associated with each identified combination or condition, selected from the group consisting of;

performing a first text splitting step,

performing a first word re-tagging step,

splitting the text at a connective word,

performing a first word combining step,

marking prepositional phrases in the text,

performing a second text splitting step,

performing a second word combining step,

moving elements into tags,

rearranging word order; and

performing the searching and processing steps until the processed text matches a template; and

generating a homogeneous text segment.

13. The method of claim 12, wherein the group of actions further includes manipulating referencing words.

14. The method of claim 12, wherein the group of actions further includes processing an idiomatic expression in the text.

15. The method of claim 12, wherein the group of actions further includes:

reducing the number of words in the text, and

performing a first unnecessary word deletion step.

16. The method of claim 15, wherein the group of actions further includes performing a second unnecessary word deletion step.

17. The method of claim 12, wherein the group of actions further includes performing a second word re-tagging step.

18. The method of claim 12, further comprising preparing the text before the text processing operation is performed.