公开(公告)号：US20240362427A1

公开(公告)日：2024-10-31

申请号：US18308907

申请日：2023-04-28

Applicant: Adobe Inc.

Inventor： Mukul Gupta ,  Yaman Kumar ,  Rahul Gupta ,  Prerna Bothra ,  Mayur Hemani ,  Mayank Gupta ,  Gaurav Makkar

IPC: G06F40/56 ,  G06F40/106 ,  G06F40/169

CPC classification number: G06F40/56 ,  G06F40/106 ,  G06F40/169

Abstract: In implementations of systems for generating digital content, a computing device implements a generation system to receive a user input specifying a characteristic for digital content. The generation system generates input text based on the characteristic for processing by a first machine learning model. Output text generated by the first machine learning model based on processing the input text is received. The output text describes a digital content component. The generation system generates the digital content component by processing the output text using a second machine learning model. The generation system generates the digital content including the digital content component for display in a user interface based on the characteristic.

公开(公告)号：US11972201B2

公开(公告)日：2024-04-30

申请号：US16152947

申请日：2018-10-05

Applicant: Adobe Inc.

Inventor： Mayank Gupta ,  Mandeep Gandhi

IPC: G06F40/174 ,  G06F16/28 ,  G06F40/30

CPC classification number: G06F40/174 ,  G06F16/285 ,  G06F16/288 ,  G06F40/30

Abstract: In some embodiments, a computing system computes a hierarchical entity data model to facilitate autocompleting forms by generating an electronic schema extraction from an electronic form lacking data for one or more fields. The computing system generates an electronic schema including an input category and input field elements. The computing system accesses a hierarchical entity-data model including and entity category and entity-data elements. The computing system identifies associations between the entity category and input category based on semantic matching including text of an entity category label and an input field category label or matching a number of fields within an entity category to an input category. The computing system verifies the association by applying a natural language processing engine to the input field elements and the entity-data elements. The computing system autocompletes one or more input field elements with entity data from one or more of the entity-data elements.

公开(公告)号：US20190149546A1

公开(公告)日：2019-05-16

申请号：US15809306

申请日：2017-11-10

Applicant: Adobe Inc.

Inventor： Nitin Nizhawan ,  Mayank Gupta

IPC: H04L29/06

Abstract: Enhanced permission techniques are disclosed that ensures integrity of resources while the resources are provided for re-purposing by users that do not have conventional permissions, such as read or write permissions, to the resources. In some examples, a method to evaluate enhanced permissions for re-purposing a resource from a source path to a target path by a user may include evaluating source permissions and target permissions, and determining whether to allow the re-purposing the resource based on the evaluating. The source permissions are copy permissions or cut permissions specified for the source path and that apply to the user. The target permissions are paste permissions specified for the target path and that apply to the user.