Multi-stage text morphing

• US 20110184725A1
• Filed: 06/17/2010
• Published: 07/28/2011
• Est. Priority Date: 01/25/2010
• Status: Active Grant

• Current Assignee: HoloVisions LLC
• Original Assignee: HoloVisions LLC
• Inventors: Connor, Robert A.
• Granted Patent: US 8,386,239 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking

Abstract

This invention is a multi-stage method for “text morphing,” wherein text morphing involves integrating or blending together substantive content from two or more bodies of text into a single body of text based on locations of linguistic commonality among the two or more bodies of text. This method for multi-stage text morphing entails: substitution of phrase synonyms between two bodies of text; substitution, between two bodies of text, of text segments with synonymous starting phrases and synonymous ending phrases; and substitution, between two bodies of text, of phrases or segments using associations within a larger reference body of text. Text morphing as disclosed herein can be useful for creative ideation, product development, integrative search engines, and entertainment purposes.

Claims

1. A multi-stage method for morphing together bodies of text comprising:

stage-one text morphing comprising;

identifying pairs of phrases that each have a phrase (Phrase A) from a first body of text (Text A) and a phrase (Phrase B) from a second body of text (Text B);

wherein a phrase is a text string containing one or more words, abbreviations, numbers, or combinations thereof;

wherein Phrase A can be used as a phrase synonym for Phrase B; and

wherein a phrase synonym is one phrase that can be substituted for another phrase in text use without causing significant changes in the meaning of the text or creating grammatical errors; and

then substituting, within each pair of phrases, Phrase A for Phrase B, in Text B;

and stage-two text morphing comprising;

identifying pairs of text segments that each have a segment (Segment A) from Text A and a segment (Segment B) from Text B, wherein Segment A and Segment B start with phrases that are synonyms of each other and end with phrases that are synonyms of each other; and

then substituting, within each pair of text segments, all or part of Segment A for all or part of Segment B, in Text B.

2. The multi-stage method for text morphing in claim 1 wherein a database of phrase synonyms is created with sets of phrases that are:

bi-directionally substitutable, with any phrase in the set being substitutable for any other phrase in the set, without causing significant changes in meaning or grammatical errors;

or uni-directionally substitutable, with any phrase in the set being substitutable for at least one phrase in the set, without causing significant changes in meaning or grammatical errors, and only substitutions in the proper direction are made in the multi-stage method for text morphing in claim 1.

3. The multi-stage method for text morphing in claim 1:

wherein each phrase or segment substitution identified is performed only once in Text B;

wherein each substitution identified is done as often as the phrase or segment to be replaced appears throughout all of Text B;

or wherein each substitution identified is done selectively and non-uniformly, based on some ranking criteria, throughout Text B.

4. The multi-stage method for text morphing in claim 1 wherein multiple iterations of some or all morphing stages continue until process or outcomes criteria are met.

5. The multi-stage method for text morphing in claim 1 wherein the order in which two or more morphing stages are performed is changed.

6. The multi-stage method for text morphing in claim 1 wherein the result of the multi-stage text morphing process is evaluated for relevance to a query as part of an integrative information search process that evaluates the relevance of combinations of information sources to a query, instead of just evaluating the relevance of information sources individually.

7. A multi-stage method for morphing together bodies of text comprising:

stage-one text morphing comprising;

identifying pairs of phrases that each have a phrase (Phrase A) from a first body of text (Text A) and a phrase (Phrase B) from a second body of text (Text B);

wherein a phrase is a text string containing one or more words, abbreviations, numbers, or combinations thereof;

wherein Phrase A can be used as a phrase synonym for Phrase B; and

wherein a phrase synonym is one phrase that can be substituted for another phrase in text use without causing significant changes in the meaning of the text or creating grammatical errors; and

then substituting, within each pair of phrases, Phrase A for Phrase B, in Text B;

stage-two text morphing comprising;

identifying pairs of text segments that each have a segment (Segment A) from Text A and a segment (Segment B) from Text B, wherein Segment A and Segment B start with phrases that are synonyms of each other and end with phrases that are synonyms of each other; and

then substituting, within each pair of text segments, all or part of Segment A for all or part of Segment B, in Text B;

and stage-three text morphing comprising;

identifying triplets of text that each have a phrase (Phrase A) from Text A, a segment (Segment B) from Text B, and a segment (Segment C) from a large reference body of text (Text C), wherein Segment B and Segment C start with phrases that are synonyms of each other and end with phrases that are synonyms of each other;

wherein the segment portion between the starting and ending phrases of Segment B can be called Middle B and the segment portion between the starting and ending phrases of Segment C can be called Middle C, wherein Middle C is a synonym of, or identical to, Phrase A; and

substituting, for each triplet, Phrase A for Middle B, in Text B; and

/or

identifying triplets of text that each have a segment (Segment A) from Text A, a phrase (Phrase B) from Text B, and a segment (Segment C) from a large reference body of text (Text C), wherein Segment A and Segment C start with phrases that are synonyms of each other and end with phrases that are synonyms of each other;

wherein the segment portion between the starting and ending phrases of Segment A can be called Middle A and the segment portion between the starting and ending phrases of Segment C can be called Middle C, wherein Middle C is a synonym of, or identical to, Phrase B; and

substituting, for each triplet, Middle A for Phrase B, in Text B.

8. The multi-stage method for text morphing in claim 7 wherein a database of phrase synonyms is created with sets of phrases that are:

bi-directionally substitutable, with any phrase in the set being substitutable for any other phrase in the set, without causing significant changes in meaning or grammatical errors;

or uni-directionally substitutable, with any phrase in the set being substitutable for at least one phrase in the set, without causing significant changes in meaning or grammatical errors, and only substitutions in the proper direction are made in the multi-stage method for text morphing in claim 7.

9. The multi-stage method for text morphing in claim 7:

wherein each phrase or segment substitution identified is performed only once in Text B;

wherein each substitution identified is done as often as the phrase or segment to be replaced appears throughout all of Text B;

or wherein each substitution identified is done selectively and non-uniformly, based on some ranking criteria, throughout Text B.

10. The multi-stage method for text morphing in claim 7 wherein multiple iterations of some or all morphing stages continue until process or outcomes criteria are met.

11. The multi-stage method for text morphing in claim 7 wherein the order in which two or more morphing stages are performed is changed.

12. The multi-stage method for text morphing in claim 7 wherein the result of the multi-stage text morphing process is evaluated for relevance to a query as part of an integrative information search process that evaluates the relevance of combinations of information sources to a query, instead of just evaluating the relevance of information sources individually.

13. A multi-stage method for morphing together bodies of text comprising:

stage-one text morphing comprising;

identifying pairs of phrases that each have a phrase (Phrase A) from a first body of text (Text A) and a phrase (Phrase B) from a second body of text (Text B);

wherein a phrase is a text string containing one or more words, abbreviations, numbers, or combinations thereof;

wherein Phrase A can be used as a phrase synonym for Phrase B; and

wherein a phrase synonym is one phrase that can be substituted for another phrase in text use without causing significant changes in the meaning of the text or creating grammatical errors; and

then substituting, within each pair of phrases, Phrase A for Phrase B, in Text B;

stage-two text morphing comprising;

identifying pairs of text segments that each have a segment (Segment A) from Text A and a segment (Segment B) from Text B, wherein Segment A and Segment B start with phrases that are synonyms of each other and end with phrases that are synonyms of each other; and

then substituting, within each pair of text segments, all or part of Segment A for all or part of Segment B, in Text B;

stage-three text morphing comprising;

identifying triplets of text that each have a phrase (Phrase A) from Text A, a segment (Segment B) from Text B, and a segment (Segment C) from a large reference body of text (Text C), wherein Segment B and Segment C start with phrases that are synonyms of each other and end with phrases that are synonyms of each other;

wherein the segment portion between the starting and ending phrases of Segment B can be called Middle B and the segment portion between the starting and ending phrases of Segment C can be called Middle C, wherein Middle C is a synonym of, or identical to, Phrase A; and

substituting, for each triplet, Phrase A for Middle B, in Text B; and

/or

identifying triplets of text that each have a segment (Segment A) from Text A, a phrase (Phrase B) from Text B, and a segment (Segment C) from a large reference body of text (Text C), wherein Segment A and Segment C start with phrases that are synonyms of each other and end with phrases that are synonyms of each other;

wherein the segment portion between the starting and ending phrases of Segment A can be called Middle A and the segment portion between the starting and ending phrases of Segment C can be called Middle C, wherein Middle C is a synonym of, or identical to, Phrase B; and

substituting, for each triplet, Middle A for Phrase B, in Text B;

and stage-four text morphing comprising;

identifying quadruplets of text that each have a phrase (Phrase A) from Text A, a phrase (Phrase B) from Text B, and two segments (Segment C1 and Segment C2) from Text C, wherein Segment C1 and Segment C2 start with phrases that are synonyms of each other and end with phrases that are synonyms of each other;

wherein the segment portion between the starting and ending phrases of Segment C1 can be called Middle C1 and the segment portion between the starting and ending phrases of Segment C2 can be called Middle C2, wherein Middle C1 is a synonym of, or identical to, Phrase A and wherein Middle C2 is a synonym of, or identical to, Phrase B; and

substituting, for each quadruplet, Phrase A for Phrase B, in Text B.

14. The multi-stage method for text morphing in claim 13 wherein a database of phrase synonyms is created with sets of phrases that are:

bi-directionally substitutable, with any phrase in the set being substitutable for any other phrase in the set, without causing significant changes in meaning or grammatical errors;

or uni-directionally substitutable, with any phrase in the set being substitutable for at least one phrase in the set, without causing significant changes in meaning or grammatical errors, and only substitutions in the proper direction are made in the multi-stage method for text morphing in claim 13.

15. The multi-stage method for text morphing in claim 13:

wherein each phrase or segment substitution identified is performed only once in Text B;

wherein each substitution identified is done as often as the phrase or segment to be replaced appears throughout all of Text B;

or wherein each substitution identified is done selectively and non-uniformly, based on some ranking criteria, throughout Text B.

16. The multi-stage method for text morphing in claim 13 wherein multiple iterations of some or all morphing stages continue until process or outcomes criteria are met.

17. The multi-stage method for text morphing in claim 13 wherein the order in which two or more morphing stages are performed is changed.

18. The multi-stage method for text morphing in claim 13 wherein the result of the multi-stage text morphing process is evaluated for relevance to a query as part of an integrative information search process that evaluates the relevance of combinations of information sources to a query, instead of just evaluating the relevance of information sources individually.