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：US20220222046A1

公开(公告)日：2022-07-14

申请号：US17354439

申请日：2021-06-22

Applicant: salesforce.com, inc.

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

IPC: G06F8/20 ,  G06N20/00 ,  G06F9/451 ,  G06F8/38

Abstract: Techniques are disclosed relating to automatically synthesizing user interface (UI) component instances. In disclosed techniques a computer system receives a set of existing UI elements and a set of design rules for the set of existing elements, where design rules in the set of design rules indicate one or more allowed states for respective UI elements in the set of existing UI elements. The one or more allowed states may correspond to one or more visual characteristics. Using the set of existing UI elements, the computer system may then automatically generate a plurality of UI component instances based on the set of design rules, where a respective UI component instance includes a first UI element in a first allowed state. The computer system may then train, using the plurality of UI component instances, a machine learning model operable to automatically generate UI designs.

公开(公告)号：US20210103969A1

公开(公告)日：2021-04-08

申请号：US16594241

申请日：2019-10-07

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Yang Zhang

IPC: G06Q30/06 ,  G06N3/04 ,  G06N3/08 ,  G06F16/535 ,  G06T7/90 ,  G06T7/194 ,  G06K9/62

Abstract: Systems and methods are provided for receiving at least a first query color, and searching an electronic catalog including a plurality of product images for the first query color to determine a similarity measure between the first query color and a product image of a plurality of product images. The similarity measure may be determined by determining a Euclidean distance between values in a three-dimensional color space for the first query color and a target color of the product image, and determining the similarity measure between the query color and the product image by determining a sum of the similarity measures from all target colors on the product image, weighted by the coverage of each target color. The search results may be transmitted based on the searching of the electronic catalog including the plurality of product images for the first query color.

公开(公告)号：US20230177250A1

公开(公告)日：2023-06-08

申请号：US17542844

申请日：2021-12-06

Applicant: salesforce.com, inc.

Inventor： Jessica Lundin ,  Sönke Rohde ,  Owen Winne Schoppe ,  Michael Sollami ,  David Woodward ,  Brian Lonsdorf ,  Alan Martin Ross

IPC: G06F40/103 ,  G06N5/04 ,  G06T11/60 ,  G06F40/247

CPC classification number: G06F40/103 ,  G06N5/04 ,  G06T11/60 ,  G06F40/247

Abstract: Systems, devices, and techniques are disclosed for visual text summary generation. An input text may be received. Keywords may be extracted from the input text. Representative keywords may be generated from the keywords. A graph representation of the representative keywords may be generated. Images associated with the representative keywords may be received. A visual-representation style may be selected based on the graph representation of the representative keywords. The mages associated with the representative keywords may be arranged according to the selected visual-representation style and the graph representation of the representative keywords.

公开(公告)号：US20230154082A1

公开(公告)日：2023-05-18

申请号：US17525916

申请日：2021-11-14

Applicant: salesforce.com, inc.

Inventor： Sönke Rohde ,  Brian Brechbuhl ,  Jessica Lundin ,  Douglas RG White ,  David Woodward ,  Chris Dalzell ,  Brian Lonsdorf ,  Alan Martin Ross ,  Owen Winne Schoppe ,  Michael Sollami

IPC: G06T11/60 ,  G06K9/20 ,  G06K9/32 ,  G06K9/62 ,  G06T7/11

CPC classification number: G06T11/60 ,  G06K9/2063 ,  G06K9/325 ,  G06K9/6256 ,  G06T7/11 ,  G06T2210/12 ,  G06T2207/20132

Abstract: Systems, devices, and techniques are disclosed for style-based dynamic content generation. A seed image, entity design data, entity style data, and text items may be received. Bounding boxes that identify areas of the seed image for the placement of the text items may be generated for the seed image. Variant images may be generated from the seed image, the entity design data, and the entity style data. The variant images may be generated by placing text items in the bounding boxes based on the entity design data and rendering text of the text items using the entity style data.

公开(公告)号：US20210103970A1

公开(公告)日：2021-04-08

申请号：US16594257

申请日：2019-10-07

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Yang Zhang

IPC: G06Q30/06 ,  G06T7/70 ,  G06T7/11

Abstract: Systems and methods are provided for receiving an image that includes a clothed person, determining a pose of the person in the image, and segmenting the image into one or more first fashion items. One or more second fashion items may be determined using a similarity search that searches at least one storage device communicatively coupled to the server based on the one or more first fashion items. At least one outfit proposal may be generated based on the one or more second fashion items. Image re-stylization of corresponding portions of the image may be performed, including the clothed person to generate recommended outfit images based on the at least one outfit proposal. The generated outfit images may be transmitted for display.

公开(公告)号：US20200097570A1

公开(公告)日：2020-03-26

申请号：US16168182

申请日：2018-10-23

Applicant: salesforce.com, Inc.

Inventor： Michael Sollami

IPC: G06F17/30 ,  G06N3/08

Abstract: A method of visual search of a data set includes receiving a request from a client digital data device comprising an image and utilizing a detection model to identify, in the image, apparent objects of interest, as well as bounding boxes within the image of those apparent objects. For each of one of more of the apparent objects of interest, the method extracts a sub-image defined by its respective bounding box. A feature retrieval model is used to identify features of apparent objects in each of those sub-images, and those features are applied (e.g., as text or otherwise) to a search engine to identify items in the digital data set. Results of the search can be presented on a digital data device of a requesting user.

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.

公开(公告)号：US11373343B2

公开(公告)日：2022-06-28

申请号：US17091259

申请日：2020-11-06

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Amir Hossein Raffiee ,  Owen Winne Schoppe

IPC: G06T7/90 ,  G06T11/00 ,  G06K9/62 ,  G06V10/75

Abstract: Generating, at a server of a generative adversarial network (GAN) for color selection, a training set of color palettes. A color palette generator of the server generates a first set of color palettes based on the training set of color palettes. The first set of color palettes may be compared with a reference set of color palettes to predict a curated set of color palettes. Colors from the curated set of color palettes may be removed that are within a predetermined distance from one another in a color space. The GAN may be validated by performing cluster analysis to determine outlier latent dimensions to be changed for the color selection by the GAN. Proposed color palettes may be generated based on the GAN to be displayed on a display device.

公开(公告)号：US20220148232A1

公开(公告)日：2022-05-12

申请号：US17091259

申请日：2020-11-06

Applicant: salesforce.com, inc.

Inventor： Michael Sollami ,  Amir Hossein Raffiee ,  Owen Winne Schoppe

IPC: G06T11/00 ,  G06K9/62 ,  G06T7/90

Abstract: Systems and method are provided for generating, at a server of a generative adversarial network (GAN) for color selection, a training set of color palettes. A color palette generator of the server generates a first set of color palettes based on the training set of color palettes. The first set of color palettes may be compared with a reference set of color palettes to predict a curated set of color palettes. Colors from the curated set of color palettes may be removed that are within a predetermined distance from one another in a color space. The GAN may be validated by performing cluster analysis to determine outlier latent dimensions to be changed for the color selection by the GAN. Proposed color palettes may be generated based on the GAN to be displayed on a display device.