System and method for embedded information retrieval in a distributed free-text application environment
First Claim
1. An embedded distributed information retrieval system, comprising:
- an embedding module for embedding a distributed information retrieval system in a computer application program, the embedding module being operative to enable a user to select at least one information source and at least one knowledge base;
a free-text parser coupled to the application program, the free-text parser operative to receive scheduled reads of textual information from the application program, parse the textual information into sentences, and rank the sentences on the basis of words and phrases in the sentences;
a query engine coupled to receive the ranked sentences, and operative to generate structured queries, the query engine coupled to the at least one knowledge base and including a semantic network processor program;
a metasearch engine coupled to receive and submit the structured queries to the at least one information source; and
a retrieval manager coupled to the metasearch engine, the retrieval manager operative to receive retrieved links associated with the structured queries, and to rank and filter the retrieved links based upon predefined criteria.
4 Assignments
0 Petitions
Accused Products
Abstract
An embedded information retrieval system is provided including a free-text parser, a knowledge-based query generator, a distributed query dispatcher, and a persistent feedback retrieval manager. When the system is embedded in a text application, the free-text parser takes samples of the text supplied by the user and segments the samples into sentences. The sentences are ranked by their content. The top content-bearing sentences are supplied to the query generator to be converted into queries for the query dispatcher. For each query, the query dispatcher identifies the relevant distributed information sources, submits the query to them, and waits for retrievals. The retrievals are passed to the retrieval manager and saved locally. User feedback is used by the retrieval manager persistently and incrementally to improve retrieval accuracy.
71 Citations
17 Claims
-
1. An embedded distributed information retrieval system, comprising:
-
an embedding module for embedding a distributed information retrieval system in a computer application program, the embedding module being operative to enable a user to select at least one information source and at least one knowledge base;
a free-text parser coupled to the application program, the free-text parser operative to receive scheduled reads of textual information from the application program, parse the textual information into sentences, and rank the sentences on the basis of words and phrases in the sentences;
a query engine coupled to receive the ranked sentences, and operative to generate structured queries, the query engine coupled to the at least one knowledge base and including a semantic network processor program;
a metasearch engine coupled to receive and submit the structured queries to the at least one information source; and
a retrieval manager coupled to the metasearch engine, the retrieval manager operative to receive retrieved links associated with the structured queries, and to rank and filter the retrieved links based upon predefined criteria. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An embedded distributed information retrieval method for generating structured queries, comprising:
-
(a) receiving an input from a user that indicates the user'"'"'s selection of at least one information source;
(b) receiving scheduled reads of textual information;
(c) parsing the textual information into sentences;
(d) parsing the sentences into words and phrases;
(e) ranking sentences by their content-bearing capacities based on their weighted words and phrases;
(f) generating structured queries from the ranked sentences using a semantic network processor program;
(g) submitting the structured queries to the at least one information source;
(h) receiving retrieved links associated with the structured queries; and
(i) ranking and filtering the retrieved links based upon predefined criteria. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17)
-
Specification