Content Recommendation Based on Efficacy Models

• US 20150142789A1
• Filed: 11/20/2013
• Published: 05/21/2015
• Est. Priority Date: 11/20/2013
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Parundekar, Rahul, Oguchi, Kentaro, Melen, Roger, Hiroki, Daisuke
• Granted Patent: US 9,916,362 B2
• Time in Patent Office: Days
• US Class Current: 707/724
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The disclosure includes a system and method for providing recommendation items to users. The system includes a processor and a memory storing instructions that when executed cause the system to: receive identification input data associated with a user; identify the user using the identification input data; receive sensor data; determine a current situation associated with the user from one or more predefined situations described by predefined situation data and associated parameters; receive data describing a set of candidate items; generate a set of efficacy scores for the set of candidate items; eliminate one or more candidate items from the set of candidate items to obtain one or more remaining candidate items; rank the one or more remaining candidate items based on one or more associated efficacy scores; and provide one or more recommendation items to the user from the one or more ranked remaining candidate items.

Claims

1. A computer-implemented method comprising:

receiving identification input data associated with a user;

identifying the user using the identification input data;

receiving sensor data;

determining, based on the sensor data, a current situation associated with the user from one or more predefined situations described by predefined situation data and associated parameters;

receiving data describing a set of candidate items;

generating a set of efficacy scores for the set of candidate items based on the current situation and a user efficacy model associated with the user;

eliminating one or more candidate items from the set of candidate items to obtain one or more remaining candidate items;

ranking the one or more remaining candidate items based on one or more efficacy scores associated with the one or more remaining candidate items; and

providing one or more recommendation items to the user from the one or more ranked remaining candidate items.

2. The method of claim 1, further comprising:

receiving stakeholder efficacy data defined by a stakeholder;

generating the user efficacy model based on one or more of the current situation and the stakeholder efficacy data; and

generating the set of efficacy scores further based on the stakeholder efficacy data.

3. The method of claim 1, further comprising:

aggregating device data associated with a mobile computing device;

determining device bias data describing one or more scoring preferences configured for the mobile computing device; and

generating the set of efficacy scores further based on the device data and the device bias data.

4. The method of claim 1, further comprising:

determining, based on the current situation, a situational bias model that describes one or more situational constraints to be satisfied; and

generating the user efficacy model based on the current situation and the situational bias model.

5. The method of claim 1, further comprising:

determining that a historical user efficacy model associated with the user exists; and

generating the user efficacy model based on the current situation and the historical user efficacy model.

6. The method of claim 1, further comprising:

retrieving a group efficacy model associated with the user; and

generating the user efficacy model based on the current situation and the group efficacy model.

7. The method of claim 1, further comprising:

retrieving user profile data associated with the user;

retrieving user social data associated with the user;

generating user attribute data associated with the user based on the user profile data and the user social data;

generating the user efficacy model based on one or more of the user attribute data and the current situation; and

generating the set of efficacy scores further based on the user attribute data.

8. The method of claim 1, further comprising:

identifying one or more items consumed by the user;

identifying one or more affinity states for the one or more consumed items;

retrieving item social data associated with the one or more consumed items;

generating item attribute data associated with the one or more consumed items based on the one or more affinity states and the item social data;

classifying the one or more consumed items to one or more groups;

determining one or more group identifiers that identify the one or more groups; and

generating the user efficacy model based on one or more of the item attribute data, the current situation and the one or more group identifiers.

9. The method of claim 1, further comprising:

determining a trip start point, a trip stop-off point and a trip end point associated with a trip based on the sensor data;

retrieving data describing a trip history associated with the user;

determining a trip offset distance based on one or more of the trip history, the trip start point, the trip stop-off point and the trip end point;

aggregating device data associated with a mobile computing device;

generating travel mobility data associated with the mobile computing device, the travel mobility data including one or more of the trip start point, the trip end point, the trip stop-off point, the trip offset distance and the device data; and

generating the set of efficacy scores further based on the travel mobility data.

10. A computer program product comprising a computer usable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive identification input data associated with a user;

identify the user using the identification input data;

receive sensor data;

determine, based on the sensor data, a current situation associated with the user from one or more predefined situations described by predefined situation data and associated parameters;

receive data describing a set of candidate items;

generate a set of efficacy scores for the set of candidate items based on the current situation and a user efficacy model associated with the user;

eliminate one or more candidate items from the set of candidate items to obtain one or more remaining candidate items;

rank the one or more remaining candidate items based on one or more efficacy scores associated with the one or more remaining candidate items; and

provide one or more recommendation items to the user from the one or more ranked remaining candidate items.

11. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

receive stakeholder efficacy data defined by a stakeholder;

generate the user efficacy model based on one or more of the current situation and the stakeholder efficacy data; and

generate the set of efficacy scores further based on the stakeholder efficacy data.

12. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

aggregate device data associated with a mobile computing device;

determine device bias data describing one or more scoring preferences configured for the mobile computing device; and

generate the set of efficacy scores further based on the device data and the device bias data.

13. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

determine, based on the current situation, a situational bias model that describes one or more situational constraints to be satisfied; and

generate the user efficacy model based on the current situation and the situational bias model.

14. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

determine that a historical user efficacy model associated with the user exists; and

generate the user efficacy model based on the current situation and the historical user efficacy model.

15. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

retrieve a group efficacy model associated with the user; and

generate the user efficacy model based on the current situation and the group efficacy model.

16. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

retrieve user profile data associated with the user;

retrieve user social data associated with the user;

generate user attribute data associated with the user based on the user profile data and the user social data;

generate the user efficacy model based on one or more of the user attribute data and the current situation; and

generate the set of efficacy scores further based on the user attribute data.

17. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

identify one or more items consumed by the user;

identify one or more affinity states for the one or more consumed items;

retrieve item social data associated with the one or more consumed items;

generate item attribute data associated with the one or more consumed items based on the one or more affinity states and the item social data;

classify the one or more consumed items to one or more groups;

determine one or more group identifiers that identify the one or more groups; and

generate the user efficacy model based on one or more of the item attribute data, the current situation and the one or more group identifiers.

18. The computer program product of claim 10, wherein the computer readable program when executed on the computer causes the computer to also:

determine a trip start point, a trip stop-off point and a trip end point associated with a trip based on the sensor data;

retrieve data describing a trip history associated with the user;

determine a trip offset distance based on one or more of the trip history, the trip start point, the trip stop-off point and the trip end point;

aggregate device data associated with a mobile computing device;

generate travel mobility data associated with the mobile computing device, the travel mobility data including one or more of the trip start point, the trip end point, the trip stop-off point, the trip offset distance and the device data; and

generate the set of efficacy scores further based on the travel mobility data.

19. A system comprising:

a processor; and

a memory storing instructions that, when executed, cause the system to;

receive identification input data associated with a user;

identify the user using the identification input data;

receive sensor data;

determine, based on the sensor data, a current situation associated with the user from one or more predefined situations described by predefined situation data and associated parameters;

receive data describing a set of candidate items;

generate a set of efficacy scores for the set of candidate items based on the current situation and a user efficacy model associated with the user;

eliminate one or more candidate items from the set of candidate items to obtain one or more remaining candidate items;

rank the one or more remaining candidate items based on one or more efficacy scores associated with the one or more remaining candidate items; and

provide one or more recommendation items to the user from the one or more ranked remaining candidate items.

20. The system of claim 19, wherein the instructions when executed cause the system to also:

receive stakeholder efficacy data defined by a stakeholder;

generate the user efficacy model based on one or more of the current situation and the stakeholder efficacy data; and

generate the set of efficacy scores further based on the stakeholder efficacy data.

21. The system of claim 19, wherein the instructions when executed cause the system to also:

aggregate device data associated with a mobile computing device;

determine device bias data describing one or more scoring preferences configured for the mobile computing device; and

generate the set of efficacy scores further based on the device data and the device bias data.

22. The system of claim 19, wherein the instructions when executed cause the system to also:

determine, based on the current situation, a situational bias model that describes one or more situational constraints to be satisfied; and

generate the user efficacy model based on the current situation and the situational bias model.

23. The system of claim 19, wherein the instructions when executed cause the system to also:

determine that a historical user efficacy model associated with the user exists; and

generate the user efficacy model based on the current situation and the historical user efficacy model.

24. The system of claim 19, wherein the instructions when executed cause the system to also:

retrieve a group efficacy model associated with the user; and

generate the user efficacy model based on the current situation and the group efficacy model.

25. The system of claim 19, wherein the instructions when executed cause the system to also:

retrieve user profile data associated with the user;

retrieve user social data associated with the user;

generate user attribute data associated with the user based on the user profile data and the user social data;

generate the user efficacy model based on one or more of the user attribute data and the current situation; and

generate the set of efficacy scores further based on the user attribute data.

26. The system of claim 19, wherein the instructions when executed cause the system to also:

identify one or more items consumed by the user;

identify one or more affinity states for the one or more consumed items;

retrieve item social data associated with the one or more consumed items;

generate item attribute data associated with the one or more consumed items based on the one or more affinity states and the item social data;

classify the one or more consumed items to one or more groups;

determine one or more group identifiers that identify the one or more groups; and

generate the user efficacy model based on one or more of the item attribute data, the current situation and the one or more group identifiers.

27. The system of claim 19, wherein the instructions when executed cause the system to also:

determine a trip start point, a trip stop-off point and a trip end point associated with a trip based on the sensor data;

retrieve data describing a trip history associated with the user;

determine a trip offset distance based on one or more of the trip history, the trip start point, the trip stop-off point and the trip end point;

aggregate device data associated with a mobile computing device;

generate travel mobility data associated with the mobile computing device, the travel mobility data including one or more of the trip start point, the trip end point, the trip stop-off point, the trip offset distance and the device data; and

generate the set of efficacy scores further based on the travel mobility data.