System and method for dynamic inference collaboration

Patent metadata

Field	Value
Publication number	US-11782910-B2
Application number	US-202017031463-A
Country	US
Kind code	B2
Filing date	Sep 24, 2020
Priority date	Nov 15, 2019
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

An electronic device includes at least one memory and at least one processor coupled to the at least one memory. The at least one memory is configured to store a database. The at least one processor is configured to receive content metadata from a content provider based on a query from a first device. The at least one processor is also configured to identify a scenario and a keyword associated with the content metadata. The at least one processor is further configured to generate a recommendation based at least in part on content inferences associated with the first device stored in the database through relating the scenario to previously-identified scenarios and relating the keyword to previously-identified keywords. In addition, the at least one processor is configured to provide the recommendation.

First claim

What is claimed is:

1. An electronic device comprising:
at least one memory configured to store a graph database; and
at least one processor coupled to the at least one memory, the at least one processor configured to:
receive content metadata from a content provider based on a query from a first device;
identify a scenario and a keyword associated with the content metadata;
generate a recommendation based at least in part on content inferences associated with the first device stored in the graph database through relating the scenario to previously-identified scenarios and relating the keyword to previously-identified keywords; and
provide the recommendation;

wherein, to generate the recommendation, the at least one processor is configured to:
identify a domain based on the scenario and the keyword;
identify a provider associated with the domain based on historical data represented in the graph database, the provider representing one of a plurality of content providers;
identify content associated with the provider based on the historical data; and
generate the recommendation in a format that corresponds to the domain.

2. The electronic device of claim 1 , wherein:
the first device is one of a plurality of connected devices within a multi-device environment; and
the content inferences are also associated with the plurality of connected devices.

3. The electronic device of claim 2 , wherein the content inferences are based on (i) mapping of each of the plurality of connected devices to one or more domains and (ii) mapping of each of the one or more domains to one or more content providers and one or more scenarios.

4. The electronic device of claim 3 , wherein:
the at least one processor is further configured to update the graph database with additional information from any of the plurality of connected devices; and
the additional information includes:
additional keywords identified from additional content metadata and associated with the one or more domains;
device information indicating a type and identifying information of the first device that initiates an additional query; and
scenario data representing a time that the query occurred and a location of the first device at the time of the additional query.

5. The electronic device of claim 2 , wherein, to provide the recommendation, the at least one processor is configured to:
determine which of the plurality of connected devices will receive the recommendation;
in response to a determination to provide the recommendation to the first device, provide the recommendation to the first device;
in response to a determination to provide the recommendation to a second device of the plurality of connected devices, identify a user interface associated with the second device; and
modify the recommendation to correspond to the user interface associated with the second device.

6. The electronic device of claim 2 , wherein the at least one processor is configured to:
identify the domain based also on a type of the first device;
generate the recommendation for the first device; and
transmit the recommendation to the first device.

7. The electronic device of claim 1 , wherein:
to identify the scenario, the at least one processor is configured to identify a usage pattern based on at least one of a time that the query is received and a location of the first device at the time of the query; and
to identify the keyword, the at least one processor is configured to identify information associated with the query including a domain and details of the content provider.

8. A method comprising:
receiving content metadata from a content provider based on a query from a first device;
identifying a scenario and a keyword associated with the content metadata;
generating a recommendation based at least in part on content inferences associated with the first device stored in a graph database through relating the scenario to previously-identified scenarios and relating the keyword to previously-identified keywords; and
providing the recommendation;
wherein generating the recommendation comprises:
identifying a domain based on the scenario and the keyword;
identifying a provider associated with the domain based on historical data represented in the graph database, the provider representing one of a plurality of content providers;
identifying content associated with the provider based on the historical data; and
generating the recommendation in a format that corresponds to the domain.

9. The method of claim 8 , wherein:
the first device is one of a plurality of connected devices within a multi-device environment; and
the content inferences are also associated with the plurality of connected devices.

10. The method of claim 9 , wherein the content inferences are based on (i) mapping of each of the plurality of connected devices to one or more domains and (ii) mapping of each of the one or more domains to one or more content providers and one or more scenarios.

11. The method of claim 10 , further comprising:
updating the graph database with additional information from any of the plurality of connected devices;
the additional information includes:
additional keywords identified from additional content metadata and associated with the one or more domains;
device information indicating a type and identifying information of the first device that initiates an additional query; and
scenario data representing a time that the query occurred and a location of the first device at the time of the additional query.

12. The method of claim 9 , wherein providing the recommendation comprises:
determining which of the plurality of connected devices will receive the recommendation;
in response to a determination to provide the recommendation to the first device, providing the recommendation to the first device;
in response to a determination to provide the recommendation to a second device of the plurality of connected devices, identifying a user interface associated with the second device; and
modifying the recommendation to correspond to the user interface associated with the second device.

13. The method of claim 9 , wherein;
the domain is identified based also on a type of the first device;
the recommendation is generated for the first device; and
providing the recommendation comprises transmitting the recommendation to the first device.

14. The method of claim 8 , wherein:
identifying the scenario comprises identifying a usage pattern based on at least one of a time that the query is received and a location of the first device at the time of the query; and
identifying the keyword comprises identifying information associated with the query including a domain and details of the content provider.

15. A non-transitory computer readable medium receive content metadata from a content provider based on a query from a first device;
identify a scenario and a keyword associated with the content metadata;
containing instructions that when executed cause at least one processor to:
generate a recommendation based at least in part on content inferences associated with the first device stored in a graph database through relating the scenario to previously-identified scenarios and relating the keyword to previously-identified keywords; and
provide the recommendation;
wherein the instructions that when executed cause the at least one processor to generate the recommendation comprise instructions that when executed cause the at least one processor to:
identify a domain based on the scenario and the keyword;
identify a provider ass

Assignees

• Samsung Electronics Co Ltd

Inventors

• Sehgal Akshat
• Venkatesan Shankar Narayan
• Razallian Sojan Ponthanplavi
• Boykov Artem

Classifications

• G06F16/2425 Primary

  Iterative querying; Query formulation based on the results of a preceding query · CPC title

• G06F16/908

  using metadata automatically derived from the content · CPC title

• G06F16/909

  using geographical or spatial information, e.g. location (spatiotemporally dependent retrieval from the web G06F16/9537) · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06N5/04

  Inference or reasoning models · CPC title