SYSTEMS AND METHODS FOR TREND AWARE SELF-CORRECTING ENTITY RELATIONSHIP EXTRACTION

• US 20110238615A1
• Filed: 03/23/2011
• Published: 09/29/2011
• Est. Priority Date: 03/23/2010
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Sinha, Ayon
• Granted Patent: US 8,515,889 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• 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;

determining, based on a relationship score associated with each entity, a plurality of entities related to the selected entity, the relationship score representing navigation transition, aggregated over time, between the selected entity and each of the plurality of entities;

determining, based on probabilities, a plurality of most probable entities from the plurality of entities related to the selected entity;

calculating a relevance score for each of the plurality of most probable entities; and

displaying a subset of the plurality of most probable entities, the subset of the plurality of most probable entities determined according to the relevance score for each of the plurality of most probable entities.

2. The method of claim 1, wherein the determining the plurality of entities comprises using relationship scores wherein more recent navigation transitions are weighted more than older navigation transitions when aggregating navigation transition data.

3. The method of claim 1, wherein the determining the plurality of most probable entities comprises calculating a probability for each entity, wherein the probability is calculated by normalizing the navigation transitions between the selected entity and each entity of the plurality of entities using all navigation transitions associated with the selected entity.

4. The method of claim 1, wherein the calculating the relevance score of each of the plurality of most probable entities comprises determining an entity velocity for each of the plurality of most probable entities.

5. The method of claim 4, wherein the determining the entity velocity comprises calculating a change over time in popularity of the entity.

6. The method of claim 5, wherein the calculating the change over time in popularity of the entity comprises determining the change in sales volume associated with the entity between a current time period and a past time period.

7. The method of claim 5, wherein the calculating the change over time in popularity of the entity comprises determining the change in page views associated with the entity between a current time period and a past time period.

8. The method of claim 4, wherein the calculating the relevance score of each of the plurality of most probable entities comprises a mathematical operation including a probability calculated for an entity and the entity velocity for the entity.

9. A system comprising:

an activity tracking module configured to receive a selected entity;

a relationship module configured to,

determine, based on a relationship score associated with each entity, a plurality of entities related to the selected entity, the relationship score representing navigation transitions, aggregated over time, between the selected entity and each of the plurality of entities,

determine, based on probabilities, a plurality of most probable entities from the plurality of entities related to the selected entity, and

calculating a relevance score for each of the plurality of most probable entities; and

a recommendation engine configured to provide a subset of the plurality of most probable entities, the subset of the plurality of most probable entities determined according to the relevance score for each of the plurality of most probable entities.

10. The system of claim 9, wherein the relationship module is configured to determine the plurality of entities using relationship scores wherein more recent navigation transitions are weighted more than older navigation transitions when aggregating navigation transition data.

11. The system of claim 9, wherein the relationship module is configured to determine the plurality of most probable entities using a probability for each entity, wherein the probability is calculated by normalizing the navigation transitions between the selected entity and each entity of the plurality of entities using all navigation transitions associated with the selected entity.

12. The system of claim 9, wherein the relationship module is configured to calculate the relevance score of each of the plurality of most probable entities using an entity velocity for each of the plurality of most probable entities.

13. The system of claim 12, wherein the relationship module is configured to determine the entity velocity using a change over time in popularity of the entity.

14. The system of claim 13, wherein the relationship module is configured to calculate the change over time in popularity of the entity using the change in sales volume associated with the entity between a current time period and a past time period.

15. The system of claim 13, wherein the relationship module is configured to calculate the change over time in popularity of the entity using the change in page views associated with the entity between a current time period and a past time period.

16. The system of claim 12, wherein the relationship module is configured to calculate the relevance score of each of the plurality of most probable entities using a mathematical operation including a probability calculated for an entity and the entity velocity for the entity.

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

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

determine, based on a relationship score associated with each entity, a plurality of entities related to the selected entity, the relationship score representing navigation transitions, aggregated over time, between the selected entity and each of the plurality of entities;

determine, based on probabilities, a plurality of most probable entities from the plurality of entities related to the selected entity;

calculate a relevance score for each of the plurality of most probable entities; and

recommend a subset of the plurality of most probable entities, the subset of the plurality of most probable entities determined according to the relevance score for each of the plurality of most probable entities.

18. The non-transitory machine-readable medium of claim 17, wherein the instructions to determine a plurality of entities related to the selected entity further comprise instructions that cause the machine to weight recent navigation transitions higher when aggregating over time.

19. The non-transitory machine-readable medium of claim 17, wherein the instructions to calculate the relevance score for each of the plurality of most probable entities further comprise instructions that cause the machine to using a mathematical operation including a probability calculated for each the plurality of most probable entities and the entity velocity for each the plurality of most probable entities

20. The non-transitory machine-readable medium of claim 19, wherein the instructions to calculate the relevance score for each of the plurality of most probable entities further comprise instructions that cause the machine to:

calculate probably using a mathematical operation to normalize the navigation transitions between the selected entity and each entity of the plurality of entities using all navigation transitions associated with the selected entity; and

determine the entity velocity using a change over time in popularity of the entity.