PROVIDING A VISUAL AND CONVERSATIONAL EXPERIENCE IN SUPPORT OF RECOMMENDATIONS

• US 20150370890A1
• Filed: 06/24/2014
• Published: 12/24/2015
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kandogan, Eser, Jain, Anshu N., Roth, Mary A., Schwarz, Peter M., Halan, Shivashankar, Hui, Joshua W., Kache, Holger, Lau, Tessa A.
• Granted Patent: US 9,594,824 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

The mapping system and method comprises receiving a query identifying a source entity, the source entity being of a first entity-type; generating a plurality of candidate entities from an analysis of an entity-relationship graph in response to the query based on the source entity; and computing feature values for each candidate entity of the plurality of candidate entities by passing the source entity and the plurality of candidate entities to a type-specific entity recommender particular to the first entity-type.

Claims

1. A method, comprising:

receiving, by a processor implemented recommender manager, a query identifying a source entity, the source entity being of a first entity-type;

generating, by the recommender manager, a plurality of candidate entities from an analysis of an entity-relationship graph in response to the query based on the source entity; and

computing, by the recommender manager, feature values for each candidate entity of the plurality of candidate entities by passing the source entity and the plurality of candidate entities to a type-specific entity recommender particular to the first entity-type.

2. The method of claim 1, further comprising:

computing an aggregated score for each candidate entity by combining all of the feature scores of associated with each candidate entity; and

generating a plurality of ranked candidate entities by ranking each candidate entity in accordance the computed aggregate score corresponding to that candidate entity.

4. The method of claim 1, wherein each entity recommender of the plurality of entity recommenders corresponds to one of a plurality of entity types.

5. The method of claim 1, wherein the entity-relationship graph is a set of points and edges, the set of points representing a plurality of entities and the edges representing relationships between the set of points.

6. The method of claim 1, further comprising:

identifying entity and relationship events that alter the entity-relationship graph by monitoring the entity-relationship graph.

7. The method of claim 6, further comprising:

extracting metadata associated with the entity and relationship events and providing the extracted metadata to a storage dataset in response to the identifying the entity and relationship events that alter the entity-relationship graph.

8. The method of claim 7, wherein when one of the entity and relationship events is a node event, processing the node event by a graph node indexer to index within a node content index metadata associated with the node event of the extracted metadata.

9. The method of claim 7, wherein when one of the entity and relationship events is a relation event, processing the relation event by a graph path indexer to index within a path index metadata associated with the relation event of the extracted metadata.

10. The method of claim 7, wherein when one of the entity and relationship events is a scheduled event, processing the scheduled event by a graph statistics collector to compute graph statistics from metadata associated with the scheduled event of the extracted metadata.

11. The method of claim 7, further comprising:

leveraging collaborative, semantic, and schematic metadata of the entity-relationship graph during the analysis of the entity-relationship graph.

3. The method of claim 3, further comprising:

presenting the plurality of ranked candidate entities in response to the query.

12. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause:

receiving, by a processor, a query identifying a source entity, the source entity being of a first entity-type;

generating, by the processor, a plurality of candidate entities from an analysis of an entity-relationship graph in response to the query based on the source entity; and

computing, by the processor, feature values for each candidate entity of the plurality of candidate entities by passing the source entity and the plurality of candidate entities to a type-specific entity recommender particular to the first entity-type.

13. The computer program product of claim 12, wherein the program instructions are further executable by the processor to cause:

computing an aggregated score for each candidate entity by combining all of the feature scores of associated with each candidate entity; and

generating a plurality of ranked candidate entities by ranking each candidate entity in accordance the computed aggregate score corresponding to that candidate entity.

14. The computer program product of claim 12, wherein the program instructions are further executable by the processor to cause:

presenting the plurality of ranked candidate entities in response to the query.

15. The computer program product of claim 12, wherein each entity recommender of the plurality of entity recommenders corresponds to one of a plurality of entity types.

16. The computer program product of claim 12, wherein the entity-relationship graph is a set of points and edges, the set of points representing a plurality of entities and the edges representing relationships between the set of points.

17. The computer program product of claim 12, wherein the program instructions are further executable by the processor to cause:

identifying entity and relationship events that alter the entity-relationship graph by monitoring the entity-relationship graph.

18. The computer program product of claim 17, wherein the program instructions are further executable by the processor to cause:

extracting metadata associated with the entity and relationship events and providing the extracted metadata to a storage dataset in response to the identifying the entity and relationship events that alter the entity-relationship graph.

19. A system, comprising a processor and a memory, the system configured to:

receive a query identifying a source entity, wherein the source entity is a first entity-type;

generate a plurality of candidate entities from an analysis of an entity-relationship graph in response to the query based on the source entity; and

compute feature values for each candidate entity of the plurality of candidate entities by passing the source entity and the plurality of candidate entities to a type-specific entity recommender particular to the first entity-type.

20. The system of claim 19, wherein the processing device is further configured to:

identify entity and relationship events that alter the entity-relationship graph by monitoring the entity-relationship graph.