Systems and methods for trend aware self-correcting entity relationship extraction

• US 9,342,791 B2
• Filed: 08/20/2015
• Issued: 05/17/2016
• Est. Priority Date: 03/23/2010
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Sinha, Ayon
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US14/831,069
• Publication Number:
  US 20150356194A1
• Time in Patent Office: 271 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Methods and systems for trend aware self-correcting entity relationship extraction are disclosed. For example, a method can include receiving a selected entity, determining a plurality of entities related to the selected entity, determining a plurality of most probable entities, calculating relevance scores, and displaying a subset of the plurality of most probable entities. The selected entity can be received on a network-based transaction system. The plurality of entities related to the selected entity can be determined based on a relationship score. The relationship score can represent navigation transitions, aggregated over time, between the selected entity and each of the plurality of entities. The plurality of most probable entities can be determined based on probabilities. Relevance scores can be calculated for each of the plurality of most probable entities. Finally, the subset of the plurality of most probable entities to be displayed can be determined according to the relevance scores.

Claims

1. A method comprising:

receiving a selected entity on a network-based transaction system;

accessing a database to retrieve one or more entity relationships based on the selected entity;

determining a set of related entities based on the one or more entity relationships, the determining includes calculating edge strengths between the selected entity and the set of related entities based on community behavior tracked by the network based transaction system;

generating a set of recommended entities from among the set of related entities based on at least a velocity score of each of the related entities, the velocity comprising a measure of directional change in popularity; and

displaying the set of recommended entities.

2. The method of claim 1, wherein generating the set of recommended entities further includes calculating a relevance score for each related entity in the sub-set of related entities.

3. The method of claim 2, wherein calculating the relevance score includes determining a category associated with the selected entity and filtering the sub-set of related entities in accordance with the category.

4. The method of claim 1, wherein the community behavior tracked by the network-based transaction system includes navigation between entities, and wherein calculating the edge strengths includes determining an amount of navigation between entities.

5. The method of claim 4, wherein determining the amount of navigation between entities can include determining user session boundaries for determining related navigation history.

6. The method of claim 5, wherein determining user session boundaries includes imposing artificial session boundaries based on at least one of idle time or browsing behavior.

7. A hardware implemented system comprising:

a hardware implemented activity tracking module to receive a selected entity on a network-based transaction system;

a hardware implemented relationship module to;

access a database to retrieve one or more entity relationships based on the selected entity,

determine a set of related entities based on the one or more entity relationships, and

calculate edge strengths between the selected entity and the set of related entities based on community behavior tracked by the network based transaction system; and

a hardware implemented recommendation engine to generate a set of recommended entities from among the set of related entities based on at least a velocity score of each of the related entities, the velocity comprising a measure of directional change in popularity, and cause display of the set of recommended entities.

8. The hardware implemented system of claim 7, wherein the relationship module is configured to weight more recent navigation transitions more heavily than older navigation transitions when aggregating the navigation transitions between entities.

9. The hardware implemented system of claim 7, wherein each probability of the probabilities calculated from edge strengths is calculated by normalizing navigation transitions between the selected entity and each entity of the plurality of entities using a plurality of navigation transitions associated with the selected entity.

10. The hardware implemented system of claim 7, wherein the relationship module is configured to calculate the directional change in popularity of the entity using a change in sales volume associated with the entity between a current time period and a past time period.

11. The hardware implemented system of claim 7, wherein the relationship module is configured to calculate the directional change in popularity of the entity using a change in page views associated with the entity between a current time period and a past time period.

12. A non-transitory machine-readable storage medium containing instructions that, when executed on a machine, cause the machine to perform operations comprising:

receiving a selected entity on a network-based transaction system;

accessing a database to retrieve one or more entity relationships based on the selected entity;

determining a set of related entities based on the one or more entity relationships, the determining the set of related entities includes calculating edge strengths between the selected entity and the set of related entities based on community behavior tracked by the network-based transaction system;

generating a set of recommended entities from among the set of related entities based on at least a velocity score of each of the related entities, the velocity comprising a measure of directional change in popularity; and

displaying the set of recommended entities.

13. The non-transitory machine-readable storage medium of claim 12, wherein generating the set of recommended entities further includes calculating a relevance score for each related entity in the sub-set of related entities.

14. The non-transitory machine-readable storage medium of claim 13, wherein calculating the relevance score includes determining a category associated with the selected entity and filtering the sub-set of related entities in accordance with the category.

15. The non-transitory machine-readable storage medium of claim 12, wherein the community behavior tracked by the network-based transaction system includes navigation between entities;

and wherein calculating the edge strengths includes determining an amount of navigation between entities.

16. The non-transitory machine-readable storage medium of claim 15, wherein determining the amount of navigation between entities can include determining user session boundaries for determining related navigation history.

17. The non-transitory machine-readable storage medium of claim 16, wherein determining user session boundaries includes imposing artificial session boundaries based on at least one of idle time or browsing behavior.