REAL-TIME CONTEXT AWARE RECOMMENDATION ENGINE BASED ON A USER INTERNET OF THINGS ENVIRONMENT

• US 20150019342A1
• Filed: 07/07/2014
• Published: 01/15/2015
• Est. Priority Date: 07/09/2013
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: GUPTA, Binita
• Granted Patent: US 10,185,934 B2
• Time in Patent Office: Days
• US Class Current: 705/14.66
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G16Y 10/45 Commerce

Abstract

The disclosure relates to a recommendation engine that may monitor, aggregate, filter, and otherwise process relevant information associated with a user Internet of Things (IoT) environment to provide personal and context-aware recommendations based on relevant real-time knowledge about various IoT devices and other items in the IoT environment. For example, the recommendations may be generated based on ranked associations between the user and the various items in the IoT environment, which may be determined from profiles, states, usage patterns, proximities, and other contextually relevant information about the IoT environment. Furthermore, the recommendations may be uploaded to a recommendation data server, shared with friends, or otherwise used to provide similar recommendations to other users, and in a similar respect, the recommendations may be based on information stored on the recommendation data server and/or recommendations provided to friends or other users having similar profiles to the user.

Claims

1. A method for providing personalized recommendations, comprising:

collecting information from at least one personal space in a user environment that includes one or more Internet of Things (IoT) devices, wherein the collected information includes usage information associated with the one or more IoT devices;

constructing a profile associated with the user based at least in part on the usage information associated with the one or more IoT devices in the personal space;

assigning a theme to the personal space based at least in part on the profile associated with the user and the information collected from the personal space; and

recommending at least one item to the user based at least in part on the constructed profile associated with the user and the theme assigned to the personal space.

2. The method recited in claim 1, wherein assigning the theme to the personal space further comprises:

determining an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

assigning the theme to the personal space in response to determining that the inventory associated with the personal space satisfies one or more rules associated with the assigned theme.

3. The method recited in claim 1, wherein assigning the theme to the personal space further comprises:

determining an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

defining or augmenting the theme assigned to the personal space in response to determining that the inventory associated with the personal space does not satisfy one or more rules associated with any predefined themes.

4. The method recited in claim 1, wherein the personal space includes a room, the collected information indicates a dé

cor of the room, and the theme assigned to the personal space classifies the dé

cor as one of a plurality of given decors.

5. The method recited in claim 1, wherein the collected information includes one or more of a device profile, a device state, a user profile, a device usage pattern, a user proximity, a time, a location, or other information having contextual relevance to the user environment, and wherein the recommended item includes one or more of an activity, an event, a product, or a service.

6. The method recited in claim 1, wherein the collected information includes profile information associated with the one or more IoT devices and the method further comprises:

detecting frequent proximity between the user and one or more IoT devices among the IoT devices; and

associating at least one of the IoT devices with the user based at least in part on the profile information associated with the one or more IoT devices and the detected proximity.

7. The method recited in claim 1, further comprising:

ranking the one or more IoT devices based at least in part on the usage information, wherein the one or more IoT devices are ranked according to an importance to the user, and wherein the item is recommended to the user based further in part on the rankings associated with the one or more IoT devices.

8. The method recited in claim 7, wherein the user is a first user and ranking the one or more IoT devices further comprises:

ranking the one or more IoT devices based on functionality associated therewith and the usage information that corresponds to the first user;

ranking the one or more IoT devices based on functionality associated therewith and the usage information that corresponds to a second user;

ranking the one or more IoT devices based on similarities in the respective functionality associated therewith; and

generating a first ranking of the one or more IoT devices according to the importance to the first user and a second ranking of the one or more IoT devices according to an importance to the second user.

9. The method recited in claim 1, wherein recommending the item further comprises determining an association between the recommended item and an IoT device that has a high ranking among the ranked IoT devices.

10. The method recited in claim 1, further comprising:

making the collected information associated with the user environment available to a trusted set of users.

11. The method recited in claim 1, further comprising:

uploading the collected information associated with the user environment to a recommendation data server, wherein the uploaded information includes at least the usage information associated with the one or more IoT devices in the user environment; and

making the uploaded information available to a trusted set of users.

12. The method recited in claim 11, wherein recommending the item further comprises:

accessing, from the recommendation data server, recommendations provided to other users that have profiles similar to the constructed profile associated with the user;

acquiring recommendations provided to one or more users in the trusted set of users that have profiles similar to the constructed profile associated with the user; and

fetching data from one or more web sites having a context similar to the constructed profile associated with the user.

13. The method recited in claim 1, wherein recommending the item further comprises:

recommending the item to improve a state associated with a resource in the user environment or efficiently use the resource in the user environment.

14. The method recited in claim 1, wherein:

the user environment comprises a residence and the collected information comprises floor plan information and current dé

cor information associated with the residence,

the item is recommended to the user in response to a search for furnishing to purchase for the residence, and

the recommended item includes one or more furnishing items that are concurrently compatible with the floor plan information, the current dé

cor information, and a likely furnishing preference determined from the profile associated with the user.

15. The method recited in claim 1, further comprising:

providing a recommendation application to receive input from the user that specifies further information associated with the user environment not collected from the one or more IoT devices in the user environment.

16. A recommendation engine, comprising:

a memory configured to store information collected from at least one personal space in a user environment that includes one or more Internet of Things (IoT) devices, wherein the information collected from the at least one personal space includes usage information associated with the one or more IoT devices; and

one or more processors configured to;

construct a profile associated with the user based at least in part on the usage information associated with the one or more IoT devices in the personal space;

assign a theme to the personal space based at least in part on the profile associated with the user and the information collected from the personal space; and

recommend at least one item to the user based at least in part on the constructed profile associated with the user and the theme assigned to the personal space.

17. The recommendation engine recited in claim 16, wherein the one or more processors are further configured to:

determine an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

assign the theme to the personal space in response to the inventory associated with the personal space satisfying one or more rules associated with the assigned theme.

18. The recommendation engine recited in claim 16, wherein the one or more processors are further configured to:

determine an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

define or augment the theme assigned to the personal space in response to the inventory associated with the personal space failing to satisfy one or more rules associated with any predefined themes.

19. The recommendation engine recited in claim 16, wherein the one or more processors are further configured to make the collected information available to a trusted set of users.

20. The recommendation engine recited in claim 19, wherein the one or more processors are further configured to:

access, from a recommendation data server, recommendations provided to other users that have profiles similar to the constructed profile associated with the user;

acquire recommendations provided to one or more users in the trusted set of users that have profiles similar to the constructed profile associated with the user; and

fetch data from one or more web sites having a context similar to the constructed profile associated with the user.

21. An apparatus, comprising:

means for storing information collected from at least one personal space in a user environment that includes one or more Internet of Things (IoT) devices, wherein the information collected from the at least one personal space includes usage information associated with the one or more IoT devices;

means for constructing a profile associated with the user based at least in part on the usage information associated with the one or more IoT devices in the personal space;

means for assigning a theme to the personal space based at least in part on the profile associated with the user and the information collected from the personal space; and

means for recommending at least one item to the user based at least in part on the constructed profile associated with the user and the theme assigned to the personal space.

22. The apparatus recited in claim 21, further comprising:

means for determining an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

means for assigning the theme to the personal space in response to the inventory associated with the personal space satisfying one or more rules associated with the assigned theme.

23. The apparatus recited in claim 21, further comprising:

means for determining an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

means for defining or augmenting the theme assigned to the personal space in response to the inventory associated with the personal space failing to satisfy one or more rules associated with any predefined themes.

24. The apparatus recited in claim 21, further comprising means for making the collected information available to a trusted set of users.

25. The apparatus recited in claim 24, further comprising:

means for accessing, from a recommendation data server, recommendations provided to other users that have profiles similar to the constructed profile associated with the user;

means for acquiring recommendations provided to one or more users in the trusted set of users that have profiles similar to the constructed profile associated with the user; and

means for fetching data from one or more web sites having a context similar to the constructed profile associated with the user.

26. A computer-readable storage medium having computer-executable instructions recorded thereon, wherein executing the computer-executable instructions on a computer causes the computer to:

store information collected from at least one personal space in a user environment that includes one or more Internet of Things (IoT) devices, wherein the collected information includes usage information associated with the one or more IoT devices;

construct a profile associated with the user based at least in part on the usage information associated with the one or more IoT devices in the personal space;

assign a theme to the personal space based at least in part on the profile associated with the user and the information collected from the personal space; and

recommend at least one item to the user based at least in part on the constructed profile associated with the user and the theme assigned to the personal space.

27. The computer-readable storage medium recited in claim 26, wherein executing the computer-executable instructions on the computer further causes the computer to:

determine an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

assign the theme to the personal space in response to the inventory associated with the personal space satisfying one or more rules associated with the assigned theme.

28. The computer-readable storage medium recited in claim 26, wherein executing the computer-executable instructions on the computer further causes the computer to:

determine an inventory associated with the personal space based at least in part on the collected information associated with the one or more IoT devices in the personal space and any user input defining unconnected items in the personal space; and

define or augment the theme assigned to the personal space in response to the inventory associated with the personal space failing to satisfy one or more rules associated with any predefined themes.

29. The computer-readable storage medium recited in claim 26, wherein executing the computer-executable instructions on the computer further causes the computer to make the collected information available to a trusted set of users.

30. The computer-readable storage medium recited in claim 29, wherein executing the computer-executable instructions on the computer further causes the computer to:

access, from a recommendation data server, recommendations provided to other users that have profiles similar to the constructed profile associated with the user;

acquire recommendations provided to one or more users in the trusted set of users that have profiles similar to the constructed profile associated with the user; and

fetch data from one or more web sites having a context similar to the constructed profile associated with the user.