SYSTEMS AND METHODS FOR NAVIGATING ELECTRONIC TEXTS

• US 20120078612A1
• Filed: 09/21/2011
• Published: 03/29/2012
• Est. Priority Date: 09/29/2010
• Status: Active Grant

• Current Assignee: Concert Technology Corporation, Nimbus Apollo, Inc. (Gilead Sciences Inc.)
• Original Assignee: Rhonda Enterprises, LLC (Concert Technology Corporation)
• Inventors: Kandekar, Kunal, Curtis, Scott, Svendsen, Hugh
• Granted Patent: US 9,087,043 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/258 Heading extraction; Automatic titling; Numbering

Abstract

Disclosed herein are systems and methods for navigating electronic texts. According to an aspect, a method may include determining text subgroups within an electronic text. The method may also include selecting a text seed within one of the text subgroups. Further, the method may include determining a similarity relationship between the text seed and one or more adjacent text subgroups that do not include the selected text seed. The method may also include associating the text seed with the one or more adjacent text subgroups based on the similarity relationship to create a text cluster.

Claims

1. A method comprising:

determining text subgroups within an electronic text;

selecting a text seed within one of the text subgroups;

determining a similarity relationship between the text seed and one or more adjacent text subgroups that do not include the selected text seed; and

associating the text seed with the one or more adjacent text subgroups based on the similarity relationship to create a text cluster.

2. The method of claim 1, wherein determining the text subgroups comprises defining the text subgroups according to one of chapters, paragraphs, and sentences of the electronic text.

3. The method of claim 1, wherein the text seed comprises one or more words.

4. The method of claim 3, wherein selecting the text seed comprises:

determining a relevance score for each of the one or more words based on a frequency of the words; and

using the relevance score for each of the one or more words to select the text seed from among the text subgroups.

5. The method of claim 4, comprising selecting a plurality of text seeds, each text seed being a minimum word distance from any other text seed.

6. The method of claim 1, wherein selecting the text seed comprises selecting the text seed based on user input.

7. The method of claim 1, further comprising linking the text cluster to another one of the text subgroups within the electronic text based on a similarity relationship between the text cluster and the other one of the text subgroups.

8. The method of claim 7, further comprising presenting at least one navigational link that links the text cluster to the other one of the text subgroups.

9. The method of claim 8, wherein linking the text cluster to the other one of the text subgroups comprises:

determining a first similarity score between the cluster and a first text subgroup within the electronic text; and

determining a second similarity score between the cluster and a second text subgroup within the electronic text,

wherein the method further comprises determining a highest similarity score among the first and second similarity scores, and

wherein presenting the at least one navigational link comprises presenting a navigational link for the cluster and one of the first and second text subgroups having the highest similarity score.

10. The method of claim 1, further comprising:

selecting one or more other text seeds within the one of the text subgroups; and

for each of the other text seeds;

determining a similarity relationship between the text seed and the text subgroups that do not include the other text seed; and

associating the other text seed with at least one of the text subgroups based on the similarity relationship.

11. The method of claim 1, wherein determining the similarity relationship comprises one of performing semantic analysis, performing natural language processing, identifying causal relationships between the text seed and the text subgroups, determining semantic similarity based on ontology, using a semantic index to compare semantic similarities, and determining a statistic similarity.

12. The method of claim 1, wherein determining the similarity relationship comprises:

using a semantic graph representing relations between words to compare the text seed to one or more words in each of the one or more adjacent text subgroups; and

using the comparison to associate the text seed with the one or more adjacent text subgroups.

13. The method of claim 12, further comprising generating the semantic graph using at least one of pre-generated summarization of the electronic text, metadata of the electronic text, semantic analysis of the electronic text, semantic indexing, natural language processing (NLP), and statistical techniques.

14. The method of claim 1, further comprising storing a navigational aid in metadata of the electronic text that indicates linkage of the text cluster with the other one of the text subgroups.

15. The method of claim 1, further comprising:

linking the text cluster to another one of the text subgroups within the electronic text based on a similarity relationship between the text cluster and the other one of the text subgroups; and

presenting a navigational link that links the text cluster to the other one of the text subgroups.

16. The method of claim 15, further comprising:

receiving user input for selecting the navigational link; and

in response to receiving the user input, controlling a user interface to present content of the other one of the text subgroups.

17. The method of claim 1, further comprising:

linking the text cluster to another one of the text subgroups within the electronic text based on a similarity relationship between the text cluster and the other one of the text subgroups;

receiving user input for selecting the text cluster; and

in response to receiving the user input, controlling a user interface to present content of the other one of the text subgroups.

18. The method of claim 1, further comprising linking the text cluster to another one of the text subgroups within the electronic text based on a similarity relationship between the text cluster and the other one of the text subgroups,

wherein the text seed and the one or more adjacent text subgroups each comprise a sentence,

wherein determining the similarity relationship comprises determining similarity scores between the text seed and sentences within the one or more adjacent text subgroups, and

wherein the method further comprises applying predefined criteria for penalizing the similarity scores.

19. The method of claim 18, wherein applying predefined criteria comprises:

determining whether the text seed and the sentences within the one or more adjacent text subgroups are interrupted by a break in the electronic text; and

in response to determining that the text seed and the sentences within the one or more adjacent text subgroups are interrupted by a break in the electronic text, reducing the similarity score associated with the text seed and the one or more adjacent text subgroups.

20. The method of claim 19, wherein the break includes one of a sentence break, a paragraph break, a chapter break, and a volume break.

21. The method of claim 1, further comprising linking the text cluster to another one of the text subgroups within the electronic text based on a similarity relationship between the text cluster and the other one of the text subgroups,

wherein the text seed and the one or more adjacent text subgroups each comprise a sentence,

wherein determining the similarity relationship comprises determining similarity scores between the sentence of the text seed and the sentences of the one or more adjacent text subgroups, and

wherein associating the text seed with the one or more adjacent text subgroups comprises merging the text seed and the adjacent text subgroup that includes the sentence having the highest similarity score to create the text cluster.

22. The method of claim 21, wherein the text cluster is a current text cluster, and

wherein the method further comprises:

determining similarity scores between the current text cluster and the sentences immediately before and immediately after the current text cluster; and

merging the current text cluster and the sentence immediately before or immediately after the current text cluster that has the highest similarity relationship to generate an updated current text cluster comprising the current text cluster and the sentence having the highest similarity score.

23. The method of claim 22, further comprising repeatedly implementing the steps of determining similarity scores and merging the current cluster and the sentence until all sentences in the electronic text have been merged with at least one text cluster.

24. The method of claim 22, further comprising:

determining a portion of the electronic text having a highest similarity relationship with the current text cluster; and

presenting at least one navigational link that links the current text cluster to the portion of the electronic text having the highest similarity relationship.

25. An electronic device comprising:

an electronic document manager configured to;

determine text subgroups within an electronic text;

select a text seed within one of the text subgroups;

determine a similarity relationship between the text seed and one or more adjacent text subgroups that do not include the selected text seed; and

associate the text seed with the one or more adjacent text subgroups based on the similarity relationship to create a text cluster.

26. A non-transitory computer-readable storage medium having stored thereon computer executable instructions for performing the following steps:

determining text subgroups within an electronic text;

selecting a text seed within one of the text subgroups;

determining a similarity relationship between the text seed and one or more adjacent text subgroups that do not include the selected text seed; and

associating the text seed with the one or more adjacent text subgroups based on the similarity relationship to create a text cluster.