US 12,379,821 B2
Smart assist for repeated actions
Victor Carbune, Zurich (CH); Daniel Keysers, Stallikon (CH); and Thomas Deselaers, Zurich (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Nov. 15, 2023, as Appl. No. 18/509,766.
Application 18/509,766 is a continuation of application No. 17/581,390, filed on Jan. 21, 2022, granted, now 11,860,668.
Application 17/581,390 is a continuation of application No. 15/383,966, filed on Dec. 19, 2016, granted, now 11,237,696, issued on Feb. 1, 2022.
Prior Publication US 2024/0152249 A1, May 9, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/04817 (2022.01); G06F 3/0481 (2022.01); G06F 3/0482 (2013.01); G06F 9/451 (2018.01); G06Q 30/0601 (2023.01); G06Q 50/12 (2012.01); G06V 40/10 (2022.01)
CPC G06F 3/04817 (2013.01) [G06F 3/0481 (2013.01); G06F 3/0482 (2013.01); G06F 9/451 (2018.02); G06Q 30/0601 (2013.01); G06Q 50/12 (2013.01); G06V 40/10 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors comprising:
identifying a current sequence of user actions of a user with a mobile application executing at least in part at a computing device of the user;
identifying, based on the current sequence of user actions, a previous sequence of user actions of the user with the mobile application executing at least in part at the computing device of the user;
determining a confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions;
in response to determining that the confidence score fails to satisfy a first confidence threshold and a second confidence threshold:
classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as low; and
based on classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as low:
refraining from storing the current sequence of actions; and
refraining from prompting the user to utilize the previous sequence of user actions to complete the current sequence of user actions;
in response to determining that the confidence score fails to satisfy the first confidence threshold but satisfies the second confidence threshold:
classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as medium; and
based on classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as medium:
storing the current sequence of user actions in association with the previous sequence of user actions; and
refraining from prompting the user to utilize the previous sequence of user actions to complete the current sequence of user actions; and
in response to determining that the confidence score satisfies the first confidence threshold:
classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as high; and
based on classifying the confidence score indicative of whether the previous sequence of user actions can be utilized to complete the current sequence of user actions as high:
prompting, via the computing device of the user, the user to utilize the previous sequence of user actions to complete the current sequence of user actions.