公开(公告)号：US11868790B2

公开(公告)日：2024-01-09

申请号：US17649016

申请日：2022-01-26

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Sönke Rohde ,  Alan Martin Ross ,  David James Woodward ,  Jessica Lundin ,  Owen Winne Schoppe ,  Brian J. Lonsdorf ,  Aashish Jain

IPC: G06F9/451 ,  G06N3/08 ,  G06F9/54 ,  G06N3/045 ,  G06V10/762 ,  G06V10/771 ,  G06V10/82 ,  G06F3/04845 ,  G06N3/088 ,  G06F8/38 ,  G06N3/047 ,  G06N3/044 ,  G06N7/01 ,  G06V30/19 ,  G06F17/00

CPC classification number: G06F9/451 ,  G06F3/04845 ,  G06F9/547 ,  G06N3/045 ,  G06N3/08 ,  G06V10/763 ,  G06V10/771 ,  G06V10/82 ,  G06F8/38 ,  G06N3/044 ,  G06N3/047 ,  G06N3/088 ,  G06N7/01 ,  G06V30/19173

Abstract: Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

公开(公告)号：US20220114349A1

公开(公告)日：2022-04-14

申请号：US17067000

申请日：2020-10-09

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Aashish Jain

IPC: G06F40/56 ,  G06F40/51 ,  G06F16/35 ,  G06F40/284

Abstract: Systems and method are provided for selecting product corpus data. Natural language processing may be used to cluster and filter the dataset for valid descriptions of the product having a predetermined sentence length and normal natural language structure. A transformer based a multi-modal conditioned natural language generator may be instantiated based on the clustered and filtered dataset. The instantiated multi-modal conditioned natural language generator may be trained. An evaluation of an output of the multi-modal conditioned natural language generator may be performed. A product description may be generated based on the trained multi-modal conditioned natural language generator, and the product description may be output for an electronic product catalog.

公开(公告)号：US20230129431A1

公开(公告)日：2023-04-27

申请号：US17649016

申请日：2022-01-26

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Sönke Rohde ,  Alan Martin Ross ,  David James Woodward ,  Jessica Lundin ,  Owen Winne Schoppe ,  Brian J. Lonsdorf ,  Aashish Jain

IPC: G06F3/04845 ,  G06N3/04 ,  G06V10/771 ,  G06V10/762 ,  G06V10/82

Abstract: Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

公开(公告)号：US20230129240A1

公开(公告)日：2023-04-27

申请号：US17649045

申请日：2022-01-26

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Sönke Rohde ,  Alan Martin Ross ,  David James Woodward ,  Jessica Lundin ,  Owen Winne Schoppe ,  Brian J. Lonsdorf ,  Aashish Jain

IPC: G06F9/451 ,  G06F9/54 ,  G06N3/08 ,  G06N3/04

Abstract: Techniques are disclosed for automatically converting a layout image to a text-based representation. In the disclosed techniques, a server computer system receives a layout image that includes a plurality of portions representing a plurality of user interface (UI) elements included in a UI design. The server computer system transforms, via executed of a trained residual neural network (ResNet), the layout image to a text-based representation of the layout image that specifies coordinates of bounding regions of the plurality of UI elements included in the UI design, where the text-based representation is usable to generate program code executable to render the UI design. The disclosed techniques may advantageously automate one or more portions of a UI design process and, as a result save time and computing resources via the execution of an image to text-based conversion ResNet machine learning model.