US 10,503,832 B2Granted

Systems and methods for disambiguating a term based on static and temporal knowledge graphs

AssigneeRovi Guides, Inc.

InventorsManik Malhotra, Sashikumar Venkataraman, Ahmed Nizam Mohaideen P.

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods provided herein for a determining a meaning of an ambiguous term in a text segment based on a context term, a static knowledge graph and a temporal knowledge graph. These systems and methods access a first knowledge graph associated with the context term to determine a potential term that is the meaning of the unknown term. Upon determining that there are multiple potential terms in the first knowledge graph that could be the meaning of the unknown term, the systems and methods take into account the temporal dimension of relationships between entities for disambiguating the meaning of the unknown term. The systems and methods achieve this by determining a time stamp of the text segment and accessing a second knowledge graph associated with the first context term and related to the time stamp to determine the potential term that is the meaning of the first unknown term.

Claims20

Dependent claims

A method for selecting meanings for terms susceptible to multiple meanings in a text segment displayed in an interactive media guidance application, the method comprising:

receiving, through the media guidance application, a query comprising the text segment;
identifying first unknown text in the text segment;
analyzing the text segment for first context text;
determining a meaning of the first unknown text by accessing a first knowledge graph associated with the first context text to identify a potential entity that is the meaning of the first unknown text, wherein the first knowledge graph defines a first set of entities and associations between the first set of entities;
in response to determining that the first knowledge graph includes more than one potential entity that could be the meaning of the first unknown text:
determining a time stamp associated with the text segment;
and
determining the meaning of the first unknown text by accessing a second knowledge graph associated with the first context text and related to the time stamp to determine the potential entity that is the meaning of the first unknown text, wherein the second knowledge graph defines a second set of entities and associations between the second set of entities;
associating the first unknown text with the potential entity that is the meaning of the first unknown text;
determining a result of the query based on the meaning of the first unknown text;
and
transmitting the result for display in the media guidance application.

9 more elements

A system for selecting meanings for terms susceptible to multiple meanings in a text segment displayed in an interactive media guidance application, the system comprising:

control circuitry configured to:
receive, through the media guidance application, a query comprising the text segment;
identify first unknown text in the text segment;
analyze the text segment for first context text;
determine a meaning of the first unknown text by accessing a first knowledge graph associated with the first context text to identify a potential entity that is the meaning of the first unknown text, wherein the first knowledge graph defines a first set of entities and associations between the first set of entities;
in response to determining that the first knowledge graph includes more than one potential entity that could be the meaning of the first unknown text:
determine a time stamp associated with the text segment;
and
determine the meaning of the first unknown text by accessing a second knowledge graph associated with the first context text and related to the time stamp to determine the potential entity that is the meaning of the first unknown text, wherein the second knowledge graph defines a second set of entities and associations between the second set of entities;
associate the first unknown text with the potential entity that is the meaning of the first unknown text;
determine a result of the query based on the meaning of the first unknown text;
and
transmit the result for display in the media guidance application.

10 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/223,698Filed 29 Jul 2016
Published: US 2018/0032506 A11 Feb 2018
Granted: 10 Dec 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification9 codes

G06F 40/30
Handling natural language data: semantic analysis
G06F 16/3344
Query execution: using natural language analysis
G06F 16/36
Of unstructured textual data: creation of semantic tools, e.g. ontology or thesauri
G06F 16/367
Creation of semantic tools, e.g. ontology or thesauri: ontology

Family

US 2018/0032506 A1Pre-grant publication · published 1 Feb 2018
US 10,503,832 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key