View source for 17876156. NON-WAKE WORD INVOCATION OF AN AUTOMATED ASSISTANT FROM CERTAIN UTTERANCES RELATED TO DISPLAY CONTENT simplified abstract (GOOGLE LLC)

=NON-WAKE WORD INVOCATION OF AN AUTOMATED ASSISTANT FROM CERTAIN UTTERANCES RELATED TO DISPLAY CONTENT=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Pu-sen Chao of Los Altos CA (US)|Pu-sen Chao of Los Altos CA (US)]][[Category:Pu-sen Chao of Los Altos CA (US)]]

[[:Category:Alex Fandrianto of Los Gatos CA (US)|Alex Fandrianto of Los Gatos CA (US)]][[Category:Alex Fandrianto of Los Gatos CA (US)]]

[[:Category:Muhammad Umair of San Jose CA (US)|Muhammad Umair of San Jose CA (US)]][[Category:Muhammad Umair of San Jose CA (US)]]

==NON-WAKE WORD INVOCATION OF AN AUTOMATED ASSISTANT FROM CERTAIN UTTERANCES RELATED TO DISPLAY CONTENT - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17876156 titled 'NON-WAKE WORD INVOCATION OF AN AUTOMATED ASSISTANT FROM CERTAIN UTTERANCES RELATED TO DISPLAY CONTENT

==Simplified Explanation==

Implementations relate to an automated assistant that can respond to certain spoken utterances without requiring an invocation phrase or other input. The assistant can analyze display content being accessed by a user to identify relevant inputs, intents, and parameters associated with assistant operations. It then determines if any spoken utterances from the user correspond to these identified inputs. If a match is found, the assistant initiates the relevant operation without the need for a preceding invocation phrase or input.

* The automated assistant can respond to spoken utterances without the need for an invocation phrase or input.
* It analyzes display content to identify relevant inputs, intents, and parameters associated with assistant operations.
* The assistant determines if any spoken utterances from the user correspond to the identified inputs.
* If a match is found, the assistant performs the relevant operation without requiring a preceding invocation phrase or input.
* This process can be repeated for other inputs and operations when different display content is being accessed.

Potential applications of this technology:

* Hands-free operation of devices: Users can interact with their devices using voice commands without the need to manually trigger the assistant.
* Improved accessibility: Individuals with physical disabilities or impairments can easily access and control devices using voice commands.
* Enhanced user experience: Users can seamlessly interact with their devices without the need for explicit invocation phrases, making the interaction more natural and intuitive.

Problems solved by this technology:

* Eliminates the need for users to remember and use specific invocation phrases or inputs to interact with the automated assistant.
* Reduces the cognitive load on users by allowing them to directly speak their commands without any additional steps.
* Enables a more fluid and efficient interaction with devices, as users can quickly initiate assistant operations without any manual input.

Benefits of this technology:

* Improved user convenience and efficiency by eliminating the need for explicit invocation phrases or inputs.
* Enhanced accessibility for individuals with physical disabilities or impairments.
* More natural and intuitive interaction with devices, leading to a better user experience.


==Original Abstract Submitted==

Implementations relate to an automated assistant that is responsive, without requiring an invocation phrase or other invocation input(s), to certain spoken utterances when certain display content is being accessed by a user. The display content can be processed to identify certain inputs and/or other intents and parameters that are associated with assistant operations and are relevant to the display content. Thereafter, the automated assistant can determine whether any spoken utterances from the user correspond to those certain inputs, intents, and/or parameters. In response to receiving such a spoken utterance, the automated assistant can initialize performance of the relevant operation without necessitating that the user provides a preceding invocation phrase or other invocation input(s). When other display content is being accessed, the automated assistant can repeat the process for other inputs and operations.



[[Category:G10L17/22]]
[[Category:G06F3/16]]
[[Category:G06F3/0481]]
[[Category:G10L17/06]]
[[Category:G10L13/02]]