Ranking of query feedback terms in an information retrieval system

• US 6,363,378 B1
• Filed: 10/13/1998
• Issued: 03/26/2002
• Est. Priority Date: 10/13/1998
• Status: Expired due to Term

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle Corporation
• Inventors: Faisal, Mohammad, Conklin, James
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): RONES, CHARLES
• Application Number:
  US09/170,894
• Time in Patent Office: 1,260 Days
• Field of Search: 707/3, 707/5, 707/10, 707/531, 707/60, 706/45, 704/9
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

An information retrieval system processes user input queries, and identifies query feedback, including ranking the query feedback, to facilitate the user in re-formatting a new query. A knowledge base, which comprises a plurality of nodes depicting terminological concepts, is arranged to reflect conceptual proximity among the nodes. The information retrieval system processes the queries, identifies topics related to the query as well as query feedback terms, and then links both the topics and feedback terms to nodes of the knowledge base with corresponding terminological concepts. At least one focal node is selected from the knowledge base based on the topics to determine a conceptual proximity between the focal node and the query feedback nodes. The query feedback terms are ranked based on conceptual proximity to the focal node. A content processing system that identifies themes from a corpus of documents for use in query feedback processing is also disclosed.

Claims

1. A computer system comprising:

storage medium for storing a knowledge base, comprising a plurality of nodes that represent concepts, to define conceptual relationships among said nodes;

a user input device for receiving user queries;

processor unit for processing said user queries to identify a plurality of query topics related to said query, to identify nodes in said knowledge base with concepts that correspond to said query topics, to select at least one focal node from said knowledge base, wherein a focal node represents a concept, as defined by said relationships in said knowledge base, conceptually most representative of said query topics, to determine conceptual proximity between said focal node and said nodes identifying said query topics, and to rank said query topics from a first topic closest in conceptual proximity to said focal node to a last topic furthest in conceptual proximity to said focal node; and

an output display for displaying said topics, as query feedback, in said information retrieval system ranging from said first topic to said last topic.

2. A method for ranking query feedback terms in an information retrieval system, said method comprising the step of:

storing a knowledge base that comprises a plurality of nodes, depicting terminological concepts, arranged to reflect semantic relationships among said nodes;

processing a query to identify a plurality of documents related to said query;

processing a query to identify query feedback terms;

identifying a plurality of themes from said documents;

identifying a plurality of theme nodes in said knowledge base by lining said themes to a set of nodes with corresponding terminological concepts;

identifying at least one cluster of theme nodes;

selecting a focal node from said knowledge base for said at least one cluster of said theme nodes, wherein said focal node represents a terminological center, as defined by said relationships of nodes in said knowledge base, in a cluster of said theme nodes;

identifying a plurality of query feedback term nodes in said knowledge base by linking said query feedback terms with corresponding terminological concepts;

determining conceptual proximity, as depicted by relationships among said nodes of said knowledge base, between said focal node and said query feedback term nodes;

ranking said query feedback terms according to conceptual proximity, ranging from a first term with the closest conceptual proximity to said focal node to a last term with the furthest conceptual proximity to said focal node; and

displaying said query feedback terms in said information retrieval system ranging from said first term to said last term.

3. A method for ranking query feedback terms in an information retrieval system, said method comprising the step of:

storing a knowledge base, comprising a plurality of nodes that represent concepts, to define conceptual relationships among said nodes;

processing a query to identify a plurality of topics related to said query;

processing said query to identify a plurality of query feedback terms, identifying topic nodes in said knowledge base with concepts that correspond to said topics identified;

selecting at least one focal node from said knowledge base based on said topic nodes, wherein a focal node represents a concept, as defined by said relationships in said knowledge base, conceptually most representative of said query topics;

identifying query feedback term nodes in said knowledge base with concepts that correspond to said query feedback terms;

determining conceptual proximity between said focal node and said query feedback term nodes;

ranking said query feedback terms starting from a first term closest in conceptual proximity to said focal nodes; and

displaying said query feedback terms in said information retrieval system starting from said first term.

4. The method as set forth in claim 3, wherein the step of processing a query to identify a plurality of topics comprises the steps of:

selecting a plurality of documents relevant to said query; and

selecting said topics from said documents.

5. The method as set forth in claim 4, wherein the step of selecting said topics from said documents comprises the step of determining one or more themes from said documents, wherein said themes define at least a portion of the thematic content of said documents.

6. The method as set forth in claim 3, wherein the step of storing a knowledge base comprises the step of storing a knowledge base comprising a directed graph that associates terminology having a lexical, semantic or usage association through parent, child and cross-reference links.

7. The method as set forth in claim 3, wherein:

the step of selecting at least one focal topic from said knowledge base comprises the steps of;

selecting nodes from said knowledge base for terminology that corresponds to said topics identified;

determining focal nodes from said nodes selected, wherein said focal nodes generally reflect a center of a cluster formed by selection of said nodes selected; and

the step of ranking said query feedback terms comprises the steps of;

determining a distance between said focal node and said query feedback nodes in said knowledge base; and

ranking said query feedback terms, corresponding to said query feedback nodes, based on their respective distances.

8. A computer readable medium comprising a plurality of instructions, which when executed, causes a computer to perform the steps of:

storing a knowledge base, comprising a plurality of nodes that represent concepts, to define conceptual relationships among said nodes;

processing a query to identify a plurality of topics related to said query;

processing said query to identify a plurality of query feedback terms,

identifying topic nodes in said knowledge base with concepts that correspond to said topics identified;

selecting at least one focal node from said knowledge base based on said topic nodes, wherein a focal node represents a concept, as defined by said relationships in said knowledge base, conceptually most representative of said query topics;

identifying query feedback term nodes in said knowledge base with concepts that correspond to said query feedback terms;

determining conceptual proximity between said focal node and said query feedback term nodes;

ranking said query feedback terms starting from a first term closest in conceptual proximity to said focal node; and

displaying said query feedback terms in said information retrieval system starting from said first term.

9. The computer readable medium as set forth in claim 8, wherein the step of processing a query to identify a plurality of query topics comprises the steps of:

selecting a plurality of documents relevant to said query; and

selecting said topics from said documents.

10. The computer readable medium as set forth in claim 9, wherein the step of selecting said topics from said documents comprises the step of determining one or more themes from said documents, wherein said themes define at least a portion of the thematic content of said documents.

11. The computer readable medium as set forth in claim 9, wherein the step of storing a knowledge base comprises the step of storing a knowledge base comprising a directed graph that associates terminology having a lexical, semantic or usage association through parent, child and cross-reference links.

12. The computer readable medium as set forth in claim 8, wherein:

the step of selecting at least one focal topic from said knowledge base comprises the steps of;

selecting nodes from said knowledge base for terminology that corresponds to said topics identified;

determining a focal node from said nodes selected, wherein said focal node generally reflects a center of a cluster formed by selection of said nodes selected; and

the step of ranking said query feedback terms comprises the steps of;

determining a distance between said focal node and said query feedback nodes in said knowledge base; and

ranking said query feedback terms, corresponding to said query feedback nodes, based on their respective distances.