Granted Patent B2

US 12,326,868 · App. 18/298,714 · Granted Jun 10, 2025

Inventors: Vignesh Kumar Krishnamurthy (Bengaluru, IN); Sumit Agarwal (Bengaluru, IN); Prathyusha Maligireddy (Bengaluru, IN); Shruthi Hariharan (Bengaluru, IN)

Assignee: Samsung Electronics Co., Ltd.

G06F16/24578G06F16/9535

Abstract

Claims (58)

1. A method for providing a response to a query in an Internet of Things (IoT) environment, the method comprising:

receiving, by an electronic device, the query;

generating, by the electronic device, the response for the query;

determining, by the electronic device, at least one intent in relation to each of a plurality of portions of the response;

ranking, by the electronic device, the at least one intent corresponding to each of the plurality of portions based on at least one of user preferences or a usage history of at least one user device present in the IoT environment;

based on the ranking of each of the at least one intent, associate, by the electronic device, each of the ranked at least one intent with the corresponding portion of the plurality of portions;

distinguishing, by the electronic device, the plurality of portions of the response from remaining portions of the response; and

displaying, by the electronic device, the response,

wherein the response is one of a natural language sentence or a natural language combination of sentences, and

wherein the distinguished plurality of portions of the response are displayed differently than the remaining portions of the response.

2. The method of claim 1 ,

wherein the determining of the at least one intent comprises:

identifying, by the electronic device, the plurality of portions of the response; and

determining, by the electronic device, the at least one intent for each of the plurality of portions of the response based on at least one of information derived from the query, a relationship between the query and the response, contextual inputs, the user preferences, or the usage history of the at least one user device, and

wherein the at least one user device includes the electronic device.

3. The method of claim 2 , wherein the contextual inputs include at least one of partial phrases associated with the response, recognizable named entities from the response, a context derived from the response, a current application executing on the electronic device, at least one action being performed by the electronic device at a current instance of time, or the at least one action being performed by the at least one user device at the current instance of time.

4. The method of claim 2 , wherein the usage history of the at least one user device includes individual usage history of metric data associated with the at least one user device.

5. The method of claim 2 ,

wherein the usage history of the at least one user device includes global usage history of metric data associated with the at least one user device, and

wherein the global usage history of the metric data indicates a collection of individual usage history of the metric data maintained for a plurality of users associated with the at least one user device.

6. The method of claim 4 , wherein the metric data includes at least one of a location or a status of the at least one user device.

7. The method of claim 1 , wherein the ranking of each of the at least one intent comprises:

identifying, by the electronic device, at least one domain and at least one action device for each of the at least one intent, the at least one domain and the at least one action device identified for an intent are configured to execute the intent, the at least one action device belonging to the at least one user device; and

ranking, by the electronic device, each intent by analyzing at least one of the at least one domain and the at least one action device identified for each of the at least one intent or the user preferences using at least one learning method.

8. The method of claim 7 , wherein the identifying of the at least one domain and the at least one action device comprises:

analyzing, by the electronic device, at least one of individual user preferences, individual usage history of metric data, or global usage history of the metric data to identify the at least one domain and the at least one action device.

9. The method of claim 7 , wherein the at least one learning method includes at least one of at least one machine learning method or at least one non-machine learning method.

10. The method of claim 1 , wherein the distinguishing of the plurality of portions of the response comprises:

generating, by the electronic device, actionable information for each of the plurality of portions of the response by analyzing at least one of the ranking of each of the at least one intent, at least one domain, and at least one action device associated with each of the at least one intent, the user preferences, and the usage history of the at least one user device;

linking, by the electronic device, the actionable information with each of the plurality of portions of the response; and

based on the linking of the actionable information with each of the plurality of portions of the response, distinguishing, by the electronic device, the plurality of portions of the response.

11. The method of claim 10 , wherein the actionable information includes at least one of a natural language utterance (NLU), sentences in a natural language, or media.

12. The method of claim 10 , wherein the distinguishing of the plurality of portions of the response further comprises at least one of hyperlinking the plurality of portions of the response or creating at least one object for each of the plurality of portions of the response.

13. The method of claim 10 , further comprising:

categorizing the actionable information based on at least one of at least one action associated with the actionable information or a category of at least one application associated with the at least one action associated with the actionable information.

14. The method of claim 1 , further comprising:

generating, by the electronic device, actionable information for each of the plurality of portions of the response based on the corresponding intent from among the at least one intent; and

hyperlinking each of the plurality of portions to the corresponding generated actionable information,

wherein the distinguishing of the plurality of portions of the response further comprises identifying the plurality of portions of the response as including a hyperlink to the corresponding generated actionable information.

15. A method for providing a response to a query in an Internet of Things (IoT) environment, the method comprising:

receiving, by an electronic device, the query;

generating, by the electronic device, a first response to the query, the first response comprising a plurality of portions;

obtaining, by the electronic device, one or more pieces of actionable information from at least one of applications or connected devices related to the plurality of portions of the first response; and

generating, by the electronic device, a second response including the one or more pieces of actionable information in a form of a user selectable interface for selection a portion of the plurality of portions,

wherein the second response is one of a natural language sentence or a natural language combination of sentences.

16. An electronic device in an Internet of Things (IoT) environment, the electronic device comprising:

memory storing one or more computer programs; and

at least one processor communicatively coupled to the memory,

wherein the one or more computer programs include computer-executable instructions which, when executed by the at least one processor, cause the electronic device to:

receive a query,

generate a response for the query,

determine at least one intent in relation to each of a plurality of portions of the response,

rank the at least one intent corresponding to each of the plurality of portions based on at least one of user preferences or a usage history of at least one user device present in the IoT environment,

based on the rank of each of the at least one intent, associate, by the electronic device, each of the ranked at least one intent with the corresponding portion of the plurality of portions,

distinguish the plurality of portions of the response from remaining portions of the response, and

display the response,

wherein the distinguished plurality of portions of the response are displayed differently than the remaining portions of the response, and

wherein the response is one of a natural language sentence or a natural language combination of sentences.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (35)