Method and apparatus for information management using fuzzy typing

• US 6,721,734 B1
• Filed: 04/18/2000
• Issued: 04/13/2004
• Est. Priority Date: 04/18/2000
• Status: Expired due to Fees

• Current Assignee: Justsystems Evans Research Incorporated
• Original Assignee: Claritech Corporation
• Inventors: Subasic, Pero, Huettner, Alison
• Primary Examiner(s): Vu, Kim
• Assistant Examiner(s): LY, ANH
• Application Number:
  US09/551,013
• Time in Patent Office: 1,456 Days
• Field of Search: 707/1-10, 704/9, 704/10, 715/530, 715/531, 715/532, 706/1, 706/3, 706/48, 706/55
• US Class Current: 1/1
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A technique for analyzing affect in which ambiguity in both emotion and natural language is explicitly represented and processed through fuzzy logic. In particular, textual information is processed to i) isolate a vocabulary of words belonging to an emotion, ii) represent the meaning of each word belonging to that emotion using multiple categories and scalar metrics, iii) compute profiles for text documents based on the categories and scores of their component words, and iv) manipulate the profiles to visualize the texts. The representation vehicle in the system is a set of fuzzy semantic categories (affect categories) followed by their respective centralities (degrees of relatedness between lexicon entries and their various categories) and intensities (representative of the strength of the affect level described by that word) called an affect set. A graphical representation of the affect set can also be used as a tool for decision making.

Claims

1. A method for retrieving information from a data source, comprising the steps of:

selecting at least one document;

parsing said document into a plurality of words;

creating an initial affect set for said document by comparing said words to an affect lexicon and assigning an affect category, a centrality and an intensity to each of said words found in said affect lexicon; and

using said affect set to retrieve information from said data source.

2. A method, as in claim 1, further comprising:

combining a plurality of different centralities and intensities associated with different words corresponding to an affect category of a document; and

using said combined centralities and intensities to retrieve information from said data source.

3. A method, as in claim 2, further comprising:

combining a plurality of centralities by computing the fuzzy union of all centralities corresponding to an affect category and combining a plurality of intensities by computing the average of all intensities corresponding to an affect category.

4. A method, as in claim 3, further comprising:

determining the number of words corresponding to each affect category and its average of all intensities to compute the overall affect intensity for a document.

5. A method of retrieving information from a data source, comprising the steps of:

receiving a request for information from a communications network;

selecting a data source based on said request;

selecting at least one document from said data source;

parsing said document into a plurality of words;

creating an initial affect set for said document by comparing said words to an affect lexicon and assigning an affect category, a centrality and an intensity to each of said words; and

using said affect set to retrieve information from said data source.

6. A method, as in claim 5, further comprising:

combining a plurality of different centralities and intensities associated with different words corresponding to an affect category of a document; and

using said combined centralities and intensities to retrieve information from said data source.

7. A method, as in claim 6, further comprising:

combining a plurality of centralities by computing the fuzzy union of all centralities corresponding to an affect category and combining a plurality of intensities by computing the average of all intensities corresponding to an affect category.

8. A method, as in claim 7, further comprising:

determining the number of words corresponding to each affect category and its average of all intensities to compute the overall affect intensity for a document.

9. A method of retrieving information from a data source, comprising the steps of:

receiving a request for information from a communications network;

parsing said request into a plurality of words;

creating an initial affect set for said document by comparing said words to an affect lexicon and assigning an affect category, a centrality and an intensity to each of said words; and

using said affect set to retrieve information from said data source.

10. A method, as in claim 9, further comprising:

combining a plurality of different centralities and intensities associated with different words corresponding to an affect category of a request; and

using said combined centralities and intensities to retrieve information from said data source.

11. A method, as in claim 9, further comprising:

combining a plurality of centralities by computing the fuzzy union of all centralities corresponding to an affect category and combining a plurality of intensities by computing the average of all intensities corresponding to an affect category.

12. A method, as in claim 11, further comprising:

determining the number of words corresponding to each affect category and its average of all intensities to compute the overall affect intensity for a request.

13. A method of retrieving information from a data source, comprising the steps of:

receiving a request for information;

parsing said request into a plurality of words;

creating an initial affect set for said document by comparing said words to an affect lexicon and assigning an affect category, a centrality and an intensity to each of said words; and

using said affect set to retrieve information from said data source.

14. A method, as in claim 13, further comprising:

combining a plurality of different centralities and intensities associated with different words corresponding to an affect category of a request; and

using said combined centralities and intensities to retrieve information from said data source.

15. A method, as in claim 14, further comprising:

combining a plurality of centralities by computing the fuzzy union of all centralities corresponding to an affect category and combining a plurality of intensities by computing the average of all intensities corresponding to an affect category.

16. A method, as in claim 15, further comprising:

determining the number of words corresponding to each affect category and its average of all intensities to compute the overall affect intensity for a request.

17. A method of determining affect associated with a text passage, comprising the steps of:

selecting a text passage;

parsing said text passage into a plurality of words;

creating an initial affect set by comparing said words to an affect lexicon and assigning an affect category, a centrality and an intensity to each of said parsed words;

creating an modified affect set by combining a plurality of different centralities and intensities associated with different words corresponding to an affect category of said text passage; and

using said modified affect set to determine said affect of said text passage.

18. A method, as in claim 17, wherein:

said text passage consists of a sentence.

19. A method, as in claim 17, wherein:

said text passage consists of a paragraph.

20. A method, as in claim 17, wherein:

said text passage consists of a document.

21. A method, as in claim 17, wherein:

said text passage consists of a plurality of documents.