公开(公告)号：US20240419919A1

公开(公告)日：2024-12-19

申请号：US18238878

申请日：2023-08-28

Applicant: Google LLC

Inventor： Rongjing Xiang ,  Yue Liang ,  Yang Lu ,  Xu Liu ,  Keqian Yan ,  Jiawei Chen

IPC: G06F40/40 ,  G06F40/166 ,  G06F40/35 ,  G06N3/08 ,  G06T11/60

Abstract: The technology provides rewriting suggestions for communication styles in different pre-defined styles. Rewriting may convert text in different ways, including visually enhancing the message. A method provides input to a trained large language model, the input including curated examples associated with one or more writing style choices. The set of curated examples has a first size. The method also includes generating, using the model, a rewriting corpus according to one or more writing style choices. The rewriting corpus has a size two or more orders of magnitude larger than a size of curated examples. The writing style choices include at least one of tone, conversion, application context, or conversation type. A text rewriting model is trained using at least a subset of the rewriting corpus. The model is configured to generate vivid textual information in response to user input in an interactive domain, according to specific writing style choices.

公开(公告)号：US20240078374A1

公开(公告)日：2024-03-07

申请号：US17957489

申请日：2022-09-30

Applicant: GOOGLE LLC

Inventor： Ajay Gokhale ,  Jiawei Chen ,  Alvin Abdagic ,  Adrien Olczak ,  Alessandro Agostini ,  Alexander Robertson ,  Cristian Udrescu ,  Jackie Xiang ,  Jennifer Daniel ,  Keqian Yan ,  Mehek Sharma ,  Nicolo D'Ercole ,  Yang Lu ,  Dror Ayalon

IPC: G06F40/166 ,  G06F3/0482 ,  G06F3/0488 ,  G06F40/279 ,  G10L15/197 ,  G10L15/22 ,  G10L25/63

CPC classification number: G06F40/166 ,  G06F3/0482 ,  G06F3/0488 ,  G06F40/279 ,  G10L15/197 ,  G10L15/22 ,  G10L25/63 ,  G10L2015/223

Abstract: Implementations described herein relate to causing emoji(s) that are associated with a given emotion class expressed by a spoken utterance to be visually rendered for presentation to a user at a display of a client device of the user. Processor(s) of the client device may receive audio data that captures the spoken utterance, process the audio data to generate textual data that is predicted to correspond to the spoken utterance, and cause a transcription of the textual data to be visually rendered for presentation to the user via the display. Further, the processor(s) may determine, based on processing the textual data, whether the spoken utterance expresses a given emotion class. In response to determining that the spoken utterance expresses the given emotion class, the processor(s) may cause emoji(s) that are stored in association with the given emotion class to be visually rendered for presentation to the user via the display.