US 2016/0253333 A1Published application

Content inversion for user searches and product recommendations systems and methods

AssigneePaypal, Inc.

InventorBoris A. Galitsky

Life of this patent

Estimating the term…

Loading patent…

Abstract

There is provided systems and method for content inversion for use in user searches and product recommendations. The methods include receiving a first content, wherein the first content includes a first sentence having at least one first sentiment expression, creating a syntactic parse tree of the first sentence, identifying a first sentiment in the at least one first sentiment expression, wherein the first sentiment corresponds to a first polarity, determining a first needs expression corresponding to the first sentiment, wherein the first needs expression includes a first subject. The method may further include creating a sub-tree corresponding to the first needs expression, and grouping the content with other content having similar sub-trees.

Claims20

Dependent claims

A method comprising:

receiving a search query;
determining, using sentence structure processing, a first subject and a first sentiment for the first subject in the search query;
executing, using a search engine, an online search of using at least the first subject and the first sentiment of the search query;
receiving content resulting from the online search using the search engine;
determining, using the sentence structure processing, at least one sentence from the content for at least one second subject and at least one second sentiment;
matching the first subject to the at least one second subject and the first sentiment to the at least one second sentiment;
aligning phrases between the search query and the at least one sentence based on the matching the first subject to the at least one second subject and the first sentiment to the at least one second sentiment;
determining a generalization score between the search query and the at least one sentence using the phrases aligned between the search query and the at least one sentence;
and
providing search results based on the generalization score and the content.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/150,292Filed 9 May 2016
Priority: 2 Aug 2012
Published: 1 Sep 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06F 16/24578
With adaptation to user needs: using ranking
G06F 16/248
Querying: presentation of query results
G06F 16/33
Of unstructured textual data: querying
G06F 16/3344
Query execution: using natural language analysis

Family

Application61/678,893Us provisional application · filed 2 Aug 2012
Application13/957,830Continuation · filed 2 Aug 2013
Application15/150,292Continuation
US 10,402,411 B2Related patent
US 2014/0040288 A1Published application
US 9,336,297 B2Related patent
US 2016/0253333 A1This 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