公开(公告)号：US12032607B2

公开(公告)日：2024-07-09

申请号：US16876624

申请日：2020-05-18

Applicant: Adobe Inc.

Inventor： Sudhir Tubegere Shankaranarayana ,  Sreenivas Ramaswamy ,  Sachin Tripathi ,  Reetesh Mukul ,  Mayuri Jain ,  Bhakti Ramnani

IPC: G06F16/33 ,  G06F16/332 ,  G06F40/284 ,  G06N20/00

CPC classification number: G06F16/3322 ,  G06F16/3334 ,  G06F40/284 ,  G06N20/00

Abstract: A context-based recommendation system for feature search automatically identifies features of a feature-rich system (e.g., an application) based on the program code of the feature-rich system and additional data corresponding to the feature-rich system. A code workflow graph describing workflows in the program code is generated. Various data corresponding to the feature-rich system, such as help data, analytics data, social media data, and so forth is obtained. The code workflow graph and the data are analyzed to identify sentences in the workflow. These sentences are used to a train machine learning system to generate one or more recommendations. In response to a user query, the machine learning system generates and outputs as recommendations workflows identified based on the user query.

公开(公告)号：US20210357440A1

公开(公告)日：2021-11-18

申请号：US16876624

申请日：2020-05-18

Applicant: Adobe Inc.

Inventor： Sudhir Tubegere Shankaranarayana ,  Sreenivas Ramaswamy ,  Sachin Tripathi ,  Reetesh Mukul ,  Mayuri Jain ,  Bhakti Ramnani

IPC: G06F16/332 ,  G06N20/00 ,  G06F16/33 ,  G06F40/284

Abstract: A context-based recommendation system for feature search automatically identifies features of a feature-rich system (e.g., an application) based on the program code of the feature-rich system and additional data corresponding to the feature-rich system. A code workflow graph describing workflows in the program code is generated. Various data corresponding to the feature-rich system, such as help data, analytics data, social media data, and so forth is obtained. The code workflow graph and the data are analyzed to identify sentences in the workflow. These sentences are used to a train machine learning system to generate one or more recommendations. In response to a user query, the machine learning system generates and outputs as recommendations workflows identified based on the user query.

公开(公告)号：US11119727B1

公开(公告)日：2021-09-14

申请号：US16912190

申请日：2020-06-25

Applicant: Adobe Inc.

Inventor： Subham Gupta ,  Sudhir Tubegere Shankaranarayana ,  Jaideep Jeyakar ,  Ashutosh Dwivedi

IPC: G06F3/16 ,  G10L25/48 ,  G06F3/0488 ,  G06F3/0482

Abstract: Digital tutorial generation techniques and systems are described in which a digital tutorial is generated automatically and without user intervention. History data is generated describing a sequence of user inputs provided as part of user interaction with an application and audio data is received capturing user utterances, e.g., speech, from a microphone of the computing device. A step-identification module of the tutorial generation system identifies a plurality of tutorial steps based on a sequence of user inputs described by the history data. A segmentation module of the tutorial generation system then generates a plurality of audio segments from the audio data corresponding to respective ones of the plurality of tutorial steps. The digital tutorial is then generated by a synchronization module of the tutorial generation system by synchronizing the plurality of audio segments as part of the plurality of tutorial steps, which is then output.

公开(公告)号：US10818058B1

公开(公告)日：2020-10-27

申请号：US16513257

申请日：2019-07-16

Applicant: Adobe Inc.

Inventor： Subham Gupta ,  Ashutosh Dwivedi ,  Sudhir Tubegere Shankaranarayana ,  Jaideep Jeyakar

IPC: G06T11/60 ,  G06T13/80 ,  G06F3/0482 ,  G09B5/06 ,  G06T7/20 ,  G09B19/00

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating and providing an animated tutorial based on determining modifications made to a digital image. For example, the disclosed systems can determine modifications made to a digital image based on comparing an initial state of a digital image with a modified state of the digital image and/or based on analyzing an action history within a digital image editing application. The disclosed systems can generate an animated tutorial based on the determined modifications and can further generate a deep link that references the animated tutorial. In addition, the disclosed systems can provide the animated tutorial to a social networking system together with the deep link to cause devices to execute a digital image editing application and present the animated tutorial upon selection of the deep link.