Method for providing information and electronic device supporting the same

Patent metadata

Field	Value
Publication number	US-2018285752-A1
Application number	US-201815941230-A
Country	US
Kind code	A1
Filing date	Mar 30, 2018
Priority date	Mar 31, 2017
Publication date	Oct 4, 2018
Grant date	—

Abstract

An electronic device and method are disclosed herein. The electronic device includes a microphone, a camera, an output device, a memory, and a processor. The processor implements the method, including receiving a voice input and/or capturing an image, and analyze the first voice input or the image to determine at least one of a user's intent, emotion, and situation based on predefined keywords and expressions, identifying a category based on the input, selecting first information based on the category, selecting and outputting a first query prompting confirmation of output of the first information, detect a first responsive input to the first query, and when a condition to output the first information is satisfied, output a second query, detecting a second input responsive to the second query, and selectively outputting the first information based on the second input.

First claim

What is claimed is:

1 . An electronic device comprising:
a microphone; a camera; an output device; a memory storing:
first data storing a plurality of pre-defined user states including at least one of a user intent, a user emotion and a user environment,
second data storing a plurality of user reactions including pre-defined user responses and information indicating user facial expressions,
a plurality of output information, classified according to conversational categories, and
a plurality of pre-defined queries, classified according to the conversational categories,
a processor operatively coupled to the microphone, the camera, the output device, and the memory, the processor configured to:
receive an input including at least one of voice input through the microphone and an image of a user captured through the camera,
analyze the received input to select one of the user reactions from among the stored plurality of user reactions of the second data,
retrieve at least one pre-defined user state from the first data, based on mapping of the plurality of pre-defined user states to the plurality of user reactions,
identify a conversational category from the at least one pre-defined user state, based on mapping of the pre-defined user states and the conversational categories, and
select a first information from among the plurality of output information classified to the identified conversational category and outputting the selected first information through the output device.

2 . The electronic device of claim 1 , wherein when the input includes the voice input, the processor is further configured to:
analyze the voice input using at least one of voice recognition and voice print recognition; and compare at least one word extracted from the voice input by the voice recognition and the voice print recognition at least one of the pre-defined user responses to identify the at least one pre-defined user state from among the first data.

3 . The electronic device of claim 1 , wherein when the input includes the image of the user, the processor is further configured to:
extract at least one object from the image different from the user; identify the extracted at least one object by comparison of a feature of the extracted at least one extracted object to known features stored in the memory; and compare the at least one identified object with a pre-stored mapping of known objects with known user environments to identify a matching user environment from among the first data.

4 . The electronic device of claim 1 , wherein selection of the first information from among the plurality of output information is further based on
at least one of an age of the user, a gender of the user, a physical characteristic of the user, a brand historically preferred by the user, and a history indicating information output to the user previously from among the plurality of output information.

5 . The electronic device of claim 1 , wherein the processor is further configured to:
select a first query from among the plurality of pre-defined queries based on the identified conversational category, output the first query through the output device requesting a confirmation of whether to output the first information, and receive a second input including at least one of the voice input and the image of the user and generate a numerical score based on the second input, wherein the first information is output through the output device when the numerical score is greater than or equal to a first magnitude.

6 . The electronic device of claim 5 , wherein generating the numerical score further comprises:
identifying whether the second input responsive to the first query is classified into one of the categories of affirmative, negative or undecided; increase the numerical score by a first predetermined magnitude when the second input is classified as affirmative; decrease the numerical score by a second predetermined magnitude when the second input is classified as negative; and maintain the numerical score without change when the second input is classified as undecided.

7 . The electronic device of claim 6 , wherein when the second input includes the voice input, the processor is further configured to:
perform at least one of voice recognition and voice print recognition on the second input to extract a word from the second input; classifying the extracted word as affirmative, negative, or undecided, based on classification criterion stored in advance in the memory; when the word is classified as affirmative, increase the numerical score by the first predetermined magnitude; when the word is classified as negative, decrease the numerical score by the second predetermined magnitude; and when the word is classified as undecided, maintain the numerical score without change.

8 . The electronic device of claim 5 , wherein when the numerical score is less than a second magnitude, a second query is selected and output, the second query not relevant to the selected first information.

9 . The electronic device of claim 8 , wherein
when the numerical score is greater than or equal to the second magnitude and less than the first magnitude, a third query is selected and output from among the plurality or pre-defined queries matching the identified conversational category prompting final confirmation of whether to display the selected first information.

10 . The electronic device of claim 1 , wherein the selected first information is output through the output device when receiving a second input confirming requested output of the first information.

11 . A method in an electronic device, the method comprising:
storing in a memory:
first data of a plurality of pre-defined user states including at least one of a user intent, a user emotion and a user environment,
second data of a plurality of user reactions including pre-defined user responses and information indicating user facial expressions,
a plurality of output information classified according to conversational categories, and
a plurality of pre-defined queries classified according to the conversational categories,
receiving an input including at least one of voice input through a microphone and an image of a user captured through a camera; analyzing by a processor the received input to select one of the user reactions from among the stored plurality of user reactions of the second data; retrieving at least one pre-defined user state from the first data, based on mapping of the plurality of pre-defined user states to the plurality of user reactions; identifying a conversational category from the at least one pre-defined user state, based on mapping of the pre-defined user states and the conversational categories; and selecting a first information from among the plurality of output information classified to the identified conversational category and outputting the selected first information through an output device.

12 . The method of claim 11 , wherein when the input includes the voice input, the method further comprises
analyzing the voice input using at least one of voice recognition and voice print recognition; and comparing at least one word extracted from the voice input by the voice recognition and the voice print recognition at least one of the pre-defined user responses to identify the at least one pre-defined user state from among the first data.

13 . The method of claim 11 , wherein when the input includes the image of the user, the method further comprises:
extracting at least one object from the image different from the user; identifying the extracted at

Assignees

• Samsung Electronics Co Ltd

Inventors

• Yu Yong Ju
• Goo Ja Min
• You Seong Hoon
• Kwon Ki Young
• Kim Ki Won
• Kim Eun Young
• Kim Ji Min
• Kim Chul Kwi
• Kim Hyung Woo
• Namkung Joo
• Park Ji Hyun
• Oh Sae Gee
• Lee Dong Kyu
• Lee Im Sung
• Lee Chan Won
• Jang Si Hak

Classifications

• G06F16/903 Primary

  Querying (for retrieval from the web G06F16/953) · CPC title

• G06Q30/0256 Primary

  User search · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L25/27

  characterised by the analysis technique · CPC title