Information retrieval
AssigneeBritish Telecommunications public limited company
InventorGavin Churcher
Life of this patent
Estimating the term…
Abstract
An information retrieval system, and a method of operating an information retrieval system for retrieving information from a database in response to related queries submitted by a user, wherein information relating to possible interpretations of previous queries is stored and updated such that it may be used in order to disambiguate subsequent related queries and terms therein.
Claims16
A method of operating an information retrieval system for retrieving information from a database in response to queries submitted by a user, said method comprising the steps of:
- receiving a first user query;
- deriving a first lexical chain set from said first user query using a predetermined lexical chaining algorithm, said first lexical chain set comprising one or more lexical chains representing possible interpretations of said first user query;
- storing one or more lexical chains from said first lexical chain set in a lexical chain storage means;
- identifying a first subset of documents from said database using said first lexical chain set and a predetermined information retrieval algorithm;
- making information relating to said first subset of documents available to the user;
- receiving a subsequent user query, said subsequent user query being related to said first user query;
- deriving a subsequent lexical chain set from said subsequent user query using a predetermined lexical chaining algorithm in conjunction with one or more lexical chains stored in said lexical chain storage means;
- identifying a subsequent subset of documents from said database using said subsequent lexical chain set and a predetermined information retrieval algorithm;
- making information relating to said subsequent subset of documents available to the user.
An information retrieval system for retrieving information from a database in response to queries submitted by a user, said system comprising:
- means for receiving a first user query;
- means arranged to derive a first lexical chain set from a first user query using a predetermined lexical chaining algorithm, said first lexical chain set comprising one or more lexical chains representing possible interpretations of said first user query;
- means arranged to store one or more lexical chains from said first lexical chain set in a lexical chain storage means;
- means arranged to identify a first subset of documents from said database using said first lexical chain set and a predetermined information retrieval algorithm;
- means for making information relating to said first subset of documents available to the user;
- means for receiving a subsequent user query, said subsequent user query being related to said first user query;
- means arranged to derive a subsequent lexical chain set from said subsequent user query using a predetermined lexical chaining algorithm in conjunction with one or more lexical chains stored in said lexical chain storage means;
- means arranged to identify a subsequent subset of documents from said database using said subsequent lexical chain set and a predetermined information retrieval algorithm;
- means for making information relating to said subsequent subset of documents available to the user.
Dependencies are inferred from the claim text.