Keyword-based conversational searching using voice commands

• US 9,305,064 B1
• Filed: 05/24/2013
• Issued: 04/05/2016
• Est. Priority Date: 05/24/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: LeBeau, Michael J., Venkatachary, Srinivasan
• Primary Examiner(s): Pham, Tuan A
• Application Number:
  US13/902,317
• Time in Patent Office: 1,047 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2458 Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
• CPC Class Codes: G06F 16/632 Query formulation

Abstract

Methods, apparatus, and computer-readable media are described herein related to keyword-based conversational searching using voice commands. A computing device can receive an audio command for performing a search query. The computing device may receive a plurality of keywords associated with a subject matter of the search query, and computing device may configure the plurality of keywords as a plurality of audio instructions receivable by the computing device to cause the computing device to perform a subsequent search query. The computing device can then provide the plurality of keywords for display, along with search results associated with the search query.

Claims

1. A method, comprising:

receiving, at a head-mountable computing device (HMD), an audio command corresponding to a search query;

in response to receiving the audio command, using semantic mapping data to determine a first set of keywords corresponding to the search query, wherein the semantic mapping data specifies relationships between search queries and keywords;

providing, on a display of the HMD, a first menu comprising the first set of keywords, along with search results associated with the search query;

configuring a speech recognition system of the HMD to recognize, for each keyword in the first menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform a subsequent search query of the keyword of the first menu;

receiving, at the HMD, a particular audio instruction to perform a subsequent search query of a particular keyword of the first menu of keywords provided on the display of the HMD;

in response to receiving the particular audio instruction, using the semantic mapping data to determine a second set of keywords corresponding to the subsequent search query of the particular keyword;

providing, on the display of the HMD, a second menu comprising the second set of keywords, along with search results associated with the subsequent search query of the particular keyword; and

configuring the speech recognition system of the HMD (i) to recognize, for each keyword in the second menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform another subsequent search query of the keyword of the second menu, and (ii) to no longer recognize at least one keyword of the first menu.

2. The method of claim 1, wherein determining the first set of keywords comprises selecting a given keyword to be in the first set of keywords based on a determination that a frequency of submission of one or more prior search queries of the given keyword exceeds a threshold.

3. The method of claim 1, wherein the corresponding audio instruction for causing the HMD to perform the subsequent search query of the keyword of the first menu includes a spoken utterance of the keyword of the first menu.

4. A head-mountable computing device (HMD), comprising:

a display;

at least one audio sensor;

a speech recognition system;

at least one processor; and

data storage comprising instructions that, when executed by the at least one processor, cause the HMD to perform functions comprising;

receiving, via the at least one audio sensor of the HMD, an audio command corresponding to a search query;

in response to receiving the audio command, using semantic mapping data to determine a first set of keywords corresponding to the search query, wherein the semantic mapping data specifies relationships between search queries and keywords;

providing, on the display of the HMD, a first menu comprising the first set of keywords, along with search results associated with the search query;

configuring the speech recognition system of the HMD to recognize, for each keyword in the first menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform a subsequent search query of the keyword of the first menu;

receiving, via the at least one audio sensor of the HMD, a particular audio instruction to perform a subsequent search query of a particular keyword of the first menu of keywords provided on the display of the HMD;

in response to receiving the particular audio instruction, using the semantic mapping data to determine a second set of keywords corresponding to the subsequent search query of the particular keyword;

providing, on the display of the HMD, a second menu comprising the second set of keywords, along with search results associated with the subsequent search query of the particular keyword; and

configuring the speech recognition system of the HMD (i) to recognize, for each keyword in the second menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform another subsequent search query of the keyword of the second menu, and (ii) to no longer recognize at least one keyword of the first menu.

5. The HMD of claim 4, wherein determining the first set of keywords comprises selecting a given keyword to be in the first set of keywords based on a determination that a frequency of submission of one or more prior search queries of the given keyword exceeds a threshold.

6. The HMD of claim 4, wherein the corresponding audio instruction for causing the HMD to perform the subsequent search query of the keyword of the first menu includes a spoken utterance of the keyword of the first menu.

7. A non-transitory computer readable medium having stored thereon instructions that, upon execution by a head-mountable computing device (HMD), cause the HMD to perform functions comprising:

receiving an audio command corresponding to a search query;

in response to receiving the audio command, using semantic mapping data to determine a first set of keywords corresponding to the search query, wherein the semantic mapping data specifies relationships between search queries and keywords;

providing, on a display of the HMD, a first menu comprising the first set of keywords, along with search results associated with the search query; and

configuring a speech recognition system of the HMD to recognize, for each keyword in the first menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform a subsequent search query of the keyword of the first menu;

receiving a particular audio instruction to perform a subsequent search query of a particular keyword of the first menu of keywords provided on the display of the HMD;

in response to receiving the particular audio instruction, using the semantic mapping data to determine a second set of keywords corresponding to the subsequent search query of the particular keyword;

providing, on the display of the HMD, a second menu comprising the second set of keywords, along with search results associated with the subsequent search query of the particular keyword; and

configuring the speech recognition system of the HMD (i) to recognize, for each keyword in the second menu provided on the display of the HMD, a corresponding audio instruction for causing the HMD to perform another subsequent search query of the keyword of the second menu, and (ii) to no longer recognize at least one keyword of the first menu.

8. The non-transitory computer readable medium of claim 7, wherein determining the first set of keywords comprises selecting a given first keyword to be in the first set of keywords based on a determination that a frequency of submission of one or more prior search queries of the given first keyword exceeds a threshold, and wherein determining the second set of keywords comprises selecting a given second keyword to be in the second set of keywords based on a determination that a frequency of submission of one or more prior search queries of the given second keyword exceeds a threshold.

9. The non-transitory computer readable medium of claim 7, wherein the corresponding audio instruction for causing the HMD to perform the subsequent search query of the keyword of the first menu includes a spoken utterance of the keyword of the first menu, and wherein the corresponding audio instruction for causing the HMD to perform another subsequent search query of the keyword of the second menu includes a spoken utterance of the keyword of the second menu.