Personalizing search results

Patent metadata

Field	Value
Publication number	US-9852222-B2
Application number	US-201113048498-A
Country	US
Kind code	B2
Filing date	Mar 15, 2011
Priority date	Mar 15, 2011
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

Abstract

Some embodiments provide personalized search services. The personalized search services operate to contextualize what is being searched for and to provide at least some search results in that context that are specific to the user to whom the results are to be provided.

First claim

What is claimed is:

1. A method comprising:
determining, based on an analysis of an action history of a user a set of item properties that occur in patterns associated with a search category;
receiving, from a client device associated with the user, a text-based string representing a first search query;
determining, based on the text-based string, that the first search query relates to the search category;
generating, by a personalized search module, a second text-based string that includes at least one item property from the set of item properties that occur in patterns associated with the search category, the second text-based string representing a modified search query;
processing, through execution of instruction on processor a first search process based on the text-based string representing the first search query, yielding first search results, each of the first search results including a score indicative of a general relevance of the respective search result;
processing a second search process based on the second text-based string representing the modified search query, yielding second search results, each of the second search results including a score indicative of a likely relevance of the respective search result to the user;
combining the first and second search results to form combined search results, including identifying first and second search results that match and adding the relevancy scores of matching first and second search results to form a single relevancy score for a single search result in the combined search results; and
returning, to the client device, at least a portion of the combined search results in response to the search request, wherein the first search process and the second search process are distinct search process that are both performed in response to receiving the text-based string representing the search query.

2. The method of claim 1 , wherein determining the set of item properties that occur in patterns associated with the search category comprises identifying patterns of item properties associated with search categories.

3. The method of claim 2 , further comprising:
performing pattern identification for a plurality of item categories on a periodic basis.

4. The method of claim 1 , wherein the first search process and the second search process are performed against at least one database of items offered for sale via at least one network-based marketplace system.

5. The method of claim 1 , wherein the identifying of patterns of item properties associated with search categories includes identifying a pattern including at least two of a size, a color, a designer, a brand, a flavor, a retailer, and a manufacturer.

6. A system comprising:
one or more computer processors; and
one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause the system to perform operations comprising:
determining, based on an analysis of an action history of a user, a set of item properties that occur in patterns associated with a search category;
receiving, from a client device associated with the user, a text-based string repressing a first search query;
determining, based on the text-based string, that the first search query relates to the search category;
generating second text-based string that includes at least one item property from the set of item properties that occur in patterns associated with the search category, the second text-based string representing a modified search query;
processing, through execution of instruction on processor a first search process based on the text-based string representing the first search query, yielding first search results, each of the first search results including a score indicative of a general relevance of the respective search result;
processing a second search process based on the second text-based string representing the modified search query, yielding second search results, each of the second search results including a score indicative of a likely relevance of the respective search result to the user;
combining the first and second search results to form combined search results, including identifying first and second search results that match and adding the relevancy scores of matching first and second search results to form a single relevancy score for a single search result in the combined search results; and
returning, to the client device, at least a portion of the combined search results in response to the search request, wherein the first search process and the second search process are distinct search processes that are both performed in response to receiving the text-based string representing the search query.

7. The system of claim 6 , wherein determining the set of item properties that occur in patterns associated with the search category comprises identifying patterns of item properties associated with search categories.

8. The system of claim 7 , the operations further comprising:
performing pattern identification for a plurality of item categories on a periodic basis.

9. The system of claim 6 , wherein the first search process and the second search process are performed against at least one database of items offered for sale via at least one network-based marketplace system.

10. The system of claim 6 , wherein the identifying of patterns of item properties associated with search categories includes identifying a pattern including at least two of a size, a color, a designer, a brand, a flavor, a retailer, and a manufacturer.

11. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computing system, cause the computing system to perform operations comprising:
determining, based on an analysis of an action history of a user, a set of item properties that occur in patterns associated with a search category;
receiving, from a client device associated with the user, a text-based string representing a first search query;
determining, based on the text-based string, that the first search query relates to the search category;
generating a second text-based string that includes at least one item property from the set of item properties that occur in patterns associated with the search category, the second text-based string representing a modified search query;
processing, through execution of instructions on a processor, a first search process based on the text-based string representing the first search query, yielding first search results, each of the first search results including a score indicative of a general relevance of the respective search result;
processing a second search process based on the second text-based string representing the modified search query, yielding second search results, each of the second search results including a score indicative of a likely relevance of the respective search result to the user;
combining the first and second search results to form combined search results, including identifying first and second search results that match and adding the relevancy scores of matching first and second search results to form a single relevancy score for a single search result in the combined search results; and
returning, to the client device, at least a portion of the combined search results in response to the search request, wherein the first search process and the second search process are distinct search processes that are both performed in response to receiving the text-based string representing the search query.

12. The non-transitory computer-readable medium of claim 11 , wherein determining the set of item properties

Assignees

• Wu Xiaoyuan
• Mohan Sunil
• Ebay Inc

Inventors

• Wu Xiaoyuan
• Mohan Sunil

Classifications

• G06Q30/06

  Buying, selling or leasing transactions · CPC title

• G06Q30/08

  Auctions · CPC title

• G06F17/30867 Primary

  Physics · mapped topic

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title