System and method for using past or external information for future search results

• US 9,934,294 B2
• Filed: 09/26/2014
• Issued: 04/03/2018
• Est. Priority Date: 09/26/2014
• Status: Active Grant

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Wal-Mart Stores Texas LLC (WalMart Inc.)
• Inventors: Srivastava, Varun, Ruan, Yiye, Zheng, Yan
• Primary Examiner(s): Filipczyk, Marc
• Application Number:
  US14/498,538
• Publication Number:
  US 20160092520A1
• Time in Patent Office: 1,285 Days
• Field of Search: 707737
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A system and method for using past information for future search results is disclosed. A database system may comprise a first database cluster H and a second database cluster L. Social media mentions are mapped to products in the database system. Thereafter, each record in the database system is tracked to determine if mentions on social media platforms are increasing or decreasing, using a social media popularity trend signal. The social media popularity trend signal is created by comparing social media mentions during one time period to social media mentions in another time period. Other embodiments are also disclosed herein.

Claims

1. A method being implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at non-transitory computer-readable media, the method comprising:

storing a set of distinct records in a database system;

accessing a query log which comprises click-through information and item-view information for the set of distinct records, wherein (1) the click-through information comprises information about every record in the set of distinct records on which any user ever clicked, and (2) the item-view information comprises information about every record in the set of distinct records shown to any user as a result of a query;

calculating a total click-through for a record in the set of distinct records by determining how many times the record was clicked during a time period as recorded in the click-through information in the query log;

calculating a total item-view for the record by determining how many times the record received an item-view during the time period as recorded in the item-view information in the query log;

placing the record in either a first database cluster H in the database system or a second database cluster L in the database system based on the total click-through for the record and the total item-view for the record, wherein if the record is stored in the first database cluster H based on the total click-through for the record and the total item-view for the record, then the record has a higher likelihood of being accessed than if the record is stored in the second database cluster L based on the total click-through for the record and the total item-view for the record;

receiving a search request from a requester; and

presenting a search result containing one or more records in the set of distinct records to the requester;

wherein;

if the record was located at a predetermined ranking or higher on the first results list, calculating the total click-through further comprises, for each time the record was clicked by any user during the time period, determining a first position of the record on a first results list on which the record was located when the record was clicked;

if the record was located at the predetermined ranking or higher on the second results list, calculating the total item-view further comprises, for each time the record was clicked by any user during the time period, determining a second position of the record on a second results list on which the record was located when the record was displayed;

the predetermined ranking is a power of 2 or greater;

the first database cluster H is stored on a first database server;

the second database cluster L is stored on a second database server;

the first database server has greater processing capabilities than the second database server;

the method further comprises;

entering the total click-through for the record and the total item-view for the record in a feature vector that is used by a predictive model to determine a predicted likelihood of the record being accessed; and

determining the time period in real time on a dynamic basis; and

storing the record in either the first database cluster H or the second database cluster L based on the total click-through for the record and the total item-view for the record comprises storing the record in either the first database cluster H or the second database cluster L based on the predicted likelihood of the record being accessed.

2. A system comprising:

one or more processors; and

one or more non-transitory memory media storing computing instructions configured to run on the one or processors and perform acts of;

storing a set of distinct records in a database system;

accessing a query log which comprises click-through information and item-view information the set of distinct records, wherein (1) the click-through information comprises information about every record in the set of distinct records on which any user ever clicked, and (2) the item-view information comprises information about every record in the set of distinct records shown to any user as a result of a query;

calculating a total click-through for a record in the set of distinct records by determining how many times the record was clicked during a time period as recorded in the click-through information in the query log;

calculating a total item-view for the record by determining how many times the record received an item-view during the time period as recorded in the item-view information in the query log;

placing the record in either a first database cluster H in the database system or a second database cluster L in the database system based on the total click-through for the record and the total item-view for the record, wherein if the record is stored in the first database cluster H based on the total click-through for the record and the total item-view for the record, then the record has a higher likelihood of being accessed than if the record is stored in the second database cluster L based on the total click-through for the record and the total item-view for the record;

receiving a search request from a requester; and

presenting a search result containing one or more records in the set of distinct records to the requester;

wherein;

if the record was located at a predetermined ranking or higher on the first results list, calculating the total click-through further comprises, for each time the record was clicked by any user during the time period, determining a first position of the record on a first results list on which the record was located when the record was clicked;

if the record was located at the predetermined ranking or higher on the second results list, calculating the total item-view further comprises, for each time the record was clicked by any user during the time period, determining a second position of the record on a second results list on which the record was located when the record was displayed;

the predetermined ranking is a power of 2 or greater;

the first database cluster H is stored on a first database server;

the second database cluster L is stored on a second database server;

the first database server has greater processing capabilities than the second database server;

the one or more non-transitory memory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform acts of;

entering the total click-through for the record and the total item-view for the record in a feature vector that is used by a predictive model to determine a predicted likelihood of the record being accessed; and

determining the time period in real time on a dynamic basis; and

placing the record in either the first database cluster H in the database system or the second database cluster L in the database system based on the total click-through for the record and the total item-view for the record further comprises storing the record in either the first database cluster H in the database system or the second database cluster L in the database system based on the predicted likelihood of the record being accessed.