公开(公告)号：US20220415319A1

公开(公告)日：2022-12-29

申请号：US17360250

申请日：2021-06-28

Applicant: GOOGLE LLC

Inventor： Jeff J. Nainaparampil ,  Chih-Wei Chen ,  Umesh R. Patil

IPC: G10L15/22 ,  G06N20/00

Abstract: Implementations described herein relate to generating, locally at a client device, corresponding subset(s) of zero-prefix suggestions, for a user of the client device, and for suggestion state(s) associated with the client device, and subsequently causing the client device to utilize the corresponding subset(s) of zero-prefix suggestions. The suggestion state(s) and a superset of candidate zero-prefix suggestions can be processed, using machine learning model(s), to generate a corresponding score for each of the candidate zero-prefix suggestions and with respect to the suggestion state(s). Further, zero-prefix suggestions can be selected for inclusion in the corresponding subset(s) of zero-prefix suggestions, and for the suggestion state(s), based on the corresponding scores. Accordingly, when a given suggestion state is subsequently detected at the client device, a given corresponding subset of zero-prefix suggestions that is stored in association with the given suggestion state can be obtained and provided for presentation to the user.

公开(公告)号：US11269963B1

公开(公告)日：2022-03-08

申请号：US15870730

申请日：2018-01-12

Applicant: GOOGLE LLC

Inventor： Junbin Teng ,  Alessandra Mazzia ,  Chih-Wei Chen ,  Anja Hauth ,  Pascal Tom Getreuer

IPC: G06F16/9535 ,  G06F16/2457 ,  G06Q30/02 ,  G06F17/18 ,  G06F16/23 ,  G06F40/14

Abstract: Techniques for estimating social content interactions are provided. An example method includes determining counts of one or more user interactions with one or more content items created by an author, each user interaction of the one or more user interactions having an associated time, classifying, based on respective associated times of the user interactions, the determined counts of the user interactions with the content items into predetermined time intervals spanning a first duration, computing an engagement model for the author based on the classified counts corresponding to the predetermined time intervals and a number of the content items created by the author and estimating, at a particular time for a second duration, a number of interactions with a particular content item created by the author based on the engagement model and a determined actual number of interactions with the particular content item.