US 10,896,232 B2Granted

Generating recommendations based on human-curated lists

AssigneeFujitsu Limited

InventorsJun Wang, Kanji Uchino

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method of generating a recommendation for an item is provided. A method may include receiving search results based on a query for an item. The method may also include identifying a plurality of human-curated lists from the search results, wherein each human-curated list of the plurality of human-curated lists includes a plurality of human-recommended items. Further, the method may include determining, via the at least one processor, one or more scores associated with at least one of the plurality of human-curated lists and the plurality of human-recommended items. The method may further include generating, via the at least one processor, a recommendation including at least one recommended item based on the determined one or more scores. Furthermore, the method may include displaying the recommendation for the item.

Claims16

Dependent claims

A method of generating a recommendation for an item, the method comprising:

receiving, via at least one processor, search results based on a query for an item;
identifying, via the at least one processor, a plurality of human-curated lists from the search results, each human-curated list of the plurality of human-curated lists including a plurality of human-recommended items by:
selecting, via the at least one processor, a webpage of the search results;
detecting, via the at least one processor, a main block of the selected webpage;
determining, via the at least one processor, if the main block of the selected webpage includes a plurality of items in response to the query for the item;
and
in response to the selected webpage including a plurality of items in response to the query for the item, identifying, via the at least one processor, the webpage as a human-curated list;
determining, via the at least one processor, one or more scores associated with at least one of the plurality of human-curated lists and the plurality of human-recommended items;
generating, via the at least one processor, a recommendation including at least one recommended item based on the determined one or more scores;
and
displaying, via the at least one processor, the recommended item,
wherein determining if the main block of the selected webpage includes a plurality of items in response to the query for the item comprises:
detecting, via the at least one processor, a plurality of items in response to the query for the item based on at least one of an anchor pattern and known item names;
segmenting, via the at least one processor, the plurality of detected items;
extracting, via the at least one processor, item information for each of the plurality of detected items;
comparing, via the at least one processor, item information for two or more detected items of the plurality of detected items;
and
in response to a match between item information for the two or more detected items, identifying, via the at least one processor, the two or more detected items as a single item.

15 more elements

One or more non-transitory computer-readable media that include instructions that, when executed by one or more processing systems, are configured to cause the processing system to perform operations, the operations comprising:

receiving search results based on a query for an item;
identifying a plurality of human-curated lists from the search results, each human-curated list of the plurality of human-curated lists including a plurality of human-recommended items by:
selecting a webpage of the search results;
detecting a main block of the selected webpage;
determining if the main block of the selected webpage includes a plurality of items in response to the query for the item;
and
in response to the selected webpage including a plurality of items in response to the query for the item, identifying the webpage as a human-curated list;
determining one or more scores associated with the human-curated lists and the human-recommended items of the human-curated lists;
generating a recommendation including at least one recommended item based on the determined one or more scores;
and
displaying the recommendation for the recommended item,
wherein determining if the main block of the selected webpage includes a plurality of items in response to the query for the item comprises:
detecting a plurality of items in response to the query for the item based on at least one of an anchor pattern and known item names;
segmenting the plurality of detected items;
extracting item information for each of the plurality of detected items;
comparing item information for two or more detected items of the plurality of detected items;
and
in response to a match between item information for the two or more detected items, identifying the two or more detected items as a single item.

15 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/904,154Filed 23 Feb 2018
Published: US 2019/0266285 A129 Aug 2019
Granted: 19 Jan 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 16/9535
Querying, e.g. by the use of web search engines: search customisation based on user profiles and personalisation
G06F 16/9536
Querying, e.g. by the use of web search engines: search customisation based on social or collaborative filtering
G06F 16/24578
With adaptation to user needs: using ranking
G06F 16/958
Retrieval from the web: organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking