System and method for quote-based search summaries
AssigneeNorthern Light Group, LLC
InventorsC David Seuss, Anton Voskresenskiy
Life of this patent
Estimating the term…
Abstract
A computer-implemented method for generating quote-based search summaries from a plurality of documents includes receiving information identifying a meaning taxonomy, the meaning taxonomy including a normalized term and at least one syntactic structure that identifies an entity; locating, within at least one document of the plurality of documents, a statement attributable to the entity; receiving a search query comprising the normalized term; and displaying a summary of the at least one document, the summary including the statement.
Claims16
A computer-implemented method for generating quote-based search summaries from a plurality of documents, the method comprising:
- receiving, by a search system, information identifying a meaning taxonomy, the meaning taxonomy including a normalized term corresponding to a named entity and at least one syntactic structure that is different from the normalized term and identifies the named entity, the named entity being one of an individual or an organization;
- locating, by the search system within at least one document in a second plurality of documents of the plurality of documents, an attributable statement made by or on behalf of the named entity, at least by:
- locating, within a textual content of the at least one document, a first syntactic structure from the at least one syntactic structure that identifies the named entity, wherein the named entity is other than an author of the at least one document,
- locating, proximal to the first syntactic structure within the textual content of the at least one document, a second syntactic structure indicative of a statement, and
- determining whether the statement is about the named entity, determining whether the statement is by the named entity, and determining whether the statement is both by and about the named entity;
- updating, by the search system, a search index to associate the at least one document with the named entity and the attributable statement;
- receiving, by the search system via a graphical user interface (GUI), a search query comprising the normalized term corresponding to the named entity;
- and
- responsive to receiving the search query:
- determining, by the search system using the search index, that the at least one document is responsive to the search query, and
- displaying, by the search system in the GUI, a summary of the at least one document, the summary including the attributable statement;
- and
- displaying a plurality of summaries, wherein each summary in the plurality of summaries is for one of the second plurality of documents,
- wherein the plurality of summaries is displayed in an ordered list having an ordering of the plurality summaries according to a degree to which a statement in each summary is attributable to the named entity.
A system for generating quote-based search summaries from a plurality of documents, the system comprising:
- at least one processor;
- a taxonomy component, executed by the at least one processor, configured to receive information identifying a meaning taxonomy, the meaning taxonomy including a normalized term corresponding to a named entity and at least one syntactic structure that is different from the normalized term and identifies the named entity, the named entity being one of an individual or an organization;
- a search component, executed by the at least one processor, configured to locate, within at least one document in a second plurality of documents of the plurality of documents, an attributable statement made by or on behalf of the named entity, at least by:
- locating, within a textual content of the at least one document, a first syntactic structure from the at least one syntactic structure that identifies the named entity, wherein the named entity is other than an author of the at least one document,
- locating, proximal to the first syntactic structure within the textual content of the at least one document, a second syntactic structure indicative of a statement, and
- determining whether the statement is about the named entity, determining whether the statement is by the named entity, and determining whether the statement is both by and about the named entity;
- a search index component, executed by the at least one processor, configured to update a search index to associate the at least one document with the named entity and the attributable statement;
- a query input component, executed by the at least one processor, configured to receive a search query via a graphical user interface (GUI), the search query comprising the normalized term corresponding to the named entity;
- a query server component configured to use the search index to determine, responsive to the search query, that the at least one document is responsive to the search query;
- and
- a display component, executed by the at least one processor, configured to display a summary of the at least one document in the GUI, the summary including the attributable statement and display a plurality of summaries, wherein each summary in the plurality of summaries is for one of the second plurality of documents, wherein the plurality of summaries is displayed in an ordered list having an ordering of the plurality summaries according to a degree to which a statement in each summary is attributable to the named entity.
One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause:
- receiving, by a search system, information identifying a meaning taxonomy, the meaning taxonomy including a normalized term corresponding to a named entity and at least one syntactic structure that is different from the normalized term and identifies the named entity, the named entity being one of an individual or an organization;
- locating, by the search system within at least one document in a second plurality of documents of the plurality of documents, an attributable statement made by or on behalf of the named entity, at least by:
- locating, within a textual content of the at least one document, a first syntactic structure from the at least one syntactic structure that identifies the named entity, wherein the named entity is other than an author of the at least one document,
- locating, proximal to the first syntactic structure within the textual content of the at least one document, a second syntactic structure indicative of a statement, and
- determining whether the statement is about the named entity, determining whether the statement is by the named entity, and determining whether the statement is both by and about the named entity;
- updating, by the search system, a search index to associate the at least one document with the named entity and the attributable statement;
- receiving, by the search system via a graphical user interface (GUI), a search query comprising the normalized term corresponding to the named entity;
- and
- responsive to receiving the search query:
- determining, by the search system using the search index, that the at least one document is responsive to the search query, and
- displaying, by the search system in the GUI, a summary of the at least one document, the summary including the attributable statement;
- and
- displaying a plurality of summaries, wherein each summary in the plurality of summaries is for one of the second plurality of documents,
- wherein the plurality of summaries is displayed in an ordered list having an ordering of the plurality summaries according to a degree to which a statement in each summary is attributable to the named entity.
Dependencies are inferred from the claim text.