System for automatically generating queries

• US 8,219,557 B2
• Filed: 06/10/2010
• Issued: 07/10/2012
• Est. Priority Date: 08/13/2001
• Status: Active Grant

• Current Assignee: III Holdings 6, LLC
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Shanahan, James G., Grefenstette, Gregory T.
• Primary Examiner(s): NGUYEN, CAM LINH T
• Application Number:
  US12/813,354
• Publication Number:
  US 20100250547A1
• Time in Patent Office: 761 Days
• Field of Search: 707/735, 707/713, 707/737, 707/740, 707/749, 707/772, 707/778, 707/795, 707/803
• US Class Current: 707/736
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method, system and article of manufacture therefor, are disclosed for automatically generating a query from document content.

Claims

1. A computer implemented method, comprising:

accessing selected-document content that is selected from a document;

accessing a database of entities, each entity having associated therewith one or more entity-types, each entity type pertaining to one or more themes;

automatically identifying in the selected-document content at least one entity in the database of entities;

accessing a categorization system for categorizing document content having a classification profile defined using an organization of categories that corresponds to categories of document content available through an information retrieval system;

the classification profile allowing document content to be assigned to an existing category;

automatically categorizing the selected-document content using the categorization system to assign a subset of one or more categories from the categories of document content available through the information retrieval system;

automatically formulating a query for document content by providing a first element of the query representative of at least one entity identified in the selected-document content, and by providing a second element of the query focusing the query to the subset of categories of document content assigned to the selected-document content;

automatically, after formulating the query, acquiring search results by using the query for querying document content available through the information retrieval system;

wherein at least said identifying, categorizing, formulating and acquiring are performed using one or more processors.

2. The method according to claim 1, further comprising:

automatically filtering the search results;

wherein said filtering is performed using the one or more processors.

3. The method according to claim 2, further comprising:

automatically using the search results acquired through the information retrieval system for annotating the selected-document content;

wherein said using is performed using the one or more processors.

4. The method according to claim 3, further comprising:

making available the selected-document content annotated using the search results;

wherein the selected-document content annotated using the search results is characterized by the theme of at least one entity-type associated with at least one entity identified in the selected-document content.

5. The method according to claim 1, wherein said identifying identifies in the selected-document content the at least one entity from proper names, times, locations, amounts, citations, and addresses.

6. The method according to claim 1, wherein said identifying identifies in the selected-document content the at least one entity as a proper name.

7. The method according to claim 1, wherein said identifying identifies in the selected-document content the at least one entity as a location.

8. The method according to claim 1, wherein said identifying identifies in the selected-document content the at least one entity using one or a combination of regular expressions, lexicons, keywords, and rules.

9. The method according to claim 1, wherein entities in the database of entities further comprise lexicons that have associated therewith an entity and an entity-type.

10. The method according to claim 9, wherein the lexicons in the database of entities have further associated therewith an entity-string.

11. The method according to claim 10, wherein the lexicons in the database of entities have further associated therewith a part-of-speech tag.

12. The method according to claim 1, wherein said identifying further comprises tagging the at least one entity in the selected-document content with a part-of-speech tag that identifies grammatical usage of the at least one entity.

13. The method according to claim 1, wherein said categorizing the selected-document content further comprises assigning the selected-document content a category vocabulary associated with each category in the set of one or more categories.

14. The method according to claim 13, wherein said formulating further formulates the query for document content by providing a third element specified using the category vocabulary associated with each category in the set of one or more categories.

15. The method according to claim 14, wherein said formulating further formulates the query for document content by providing a fourth element specified using one or more aspects to augment the at least one entity identified in the selected-document content.

16. The method according to claim 1, wherein the organization of categories is organized as a hierarchy.

17. The method according to claim 1, wherein said categorizing further comprises computing a similarity measure between the selected-document content and class profiles of categories in the categorization system.

18. The method according to claim 1, wherein said formulating further formulates the query for document content by providing a third element specified using one or more aspects to augment the at least one entity identified in the selected-document content.