公开(公告)号：US10963694B2

公开(公告)日：2021-03-30

申请号：US16177031

申请日：2018-10-31

Applicant: salesforce.com, inc.

Inventor： Sonke Rohde ,  Brian J. Lonsdorf

IPC: G06K9/00 ,  G06F16/9537 ,  G06F40/14

Abstract: Techniques are disclosed relating to identifying duplicate coding and/or design used in different parts of a user interface (e.g., a web application). In some embodiments, a plurality of visible elements of an interface are detected based on hierarchical user interface code. In some embodiments, a device groups sets of the plurality of visible elements based on determined coordinates and depth levels for the detected elements. In some embodiments, groups that meet a threshold similarity criterion are identified. In some embodiments the threshold similarity criterion is based on classification of detected elements and/or geospatial analysis.

公开(公告)号：US11138022B2

公开(公告)日：2021-10-05

申请号：US16176978

申请日：2018-10-31

Applicant: salesforce.com, inc.

Inventor： Sonke Rohde ,  Brian J. Lonsdorf

IPC: G06F3/16 ,  G06F9/451 ,  G06F16/2455 ,  G06F3/01

Abstract: Techniques are disclosed relating to predicting events based on automation parameters and initiating a procedure to request user input. In some embodiments, the system automatically selects one or more component types to display an interface to request the user input, e.g., based on user interface elements associated with the procedure. These component-based techniques may be used to imitate another interface while automatically formatting the input data without a known template.

公开(公告)号：US20200134388A1

公开(公告)日：2020-04-30

申请号：US16176760

申请日：2018-10-31

Applicant: salesforce.com, inc.

Inventor： Sonke Rohde

IPC: G06K9/62 ,  G06F8/38 ,  G06F17/22 ,  G06F15/18

Abstract: Techniques are disclosed relating to refining, based on user feedback, one or more machine learning engines for automatically generating component-based user interfaces. In various embodiments, a computer system stores template information that defines a plurality of component types and one or more display parameters identified for one or more user interfaces. The computer system may receive a request to generate a user interface, where the request specifies a data set to be displayed. Further, the computer system may automatically generate a user interface, where the generating is performed by one or more machine learning engines that use the template information and the data set as inputs. The computer system may then provide the user interface to one or more users, receive user feedback associated with the user interface, and train at least one of the one or more machine learning engines based on the user feedback.

公开(公告)号：US11694018B2

公开(公告)日：2023-07-04

申请号：US17163162

申请日：2021-01-29

Applicant: salesforce.com, inc.

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

IPC: G06F40/169 ,  G06F40/103 ,  G06N3/049 ,  G06T11/60 ,  G06F40/284

CPC classification number: G06F40/103 ,  G06F40/284 ,  G06N3/049 ,  G06T11/60

Abstract: An online system generates a set of content item variations for a reference content item that include different styles of text for the content item. The different styles of text are generated by applying machine-learned style transfer models, for example, neural network based models to reference text of the reference content item. The text variations retain the textual content of the reference text but are synthesized with different styles. The online system can provide the content item variations to users on an online experimental platform to collect user interaction information that may indicate how users respond to different styles of text. The online system or the content providers can effectively target users with content items that include the style of text the users respond to based on the collected information.

公开(公告)号：US10783405B2

公开(公告)日：2020-09-22

申请号：US16176760

申请日：2018-10-31

Applicant: salesforce.com, inc.

Inventor： Sonke Rohde ,  Brian J. Lonsdorf

IPC: G06F3/00 ,  G06K9/62 ,  G06N20/00 ,  G06F40/14 ,  G06F8/38

Abstract: Techniques are disclosed relating to refining, based on user feedback, one or more machine learning engines for automatically generating component-based user interfaces. In various embodiments, a computer system stores template information that defines a plurality of component types and one or more display parameters identified for one or more user interfaces. The computer system may receive a request to generate a user interface, where the request specifies a data set to be displayed. Further, the computer system may automatically generate a user interface, where the generating is performed by one or more machine learning engines that use the template information and the data set as inputs. The computer system may then provide the user interface to one or more users, receive user feedback associated with the user interface, and train at least one of the one or more machine learning engines based on the user feedback.

公开(公告)号：US11657511B2

公开(公告)日：2023-05-23

申请号：US17162245

申请日：2021-01-29

Applicant: salesforce.com, inc.

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

IPC: G06T7/00 ,  G06T7/11 ,  G06T5/00 ,  G06T7/194 ,  G06T7/13 ,  G06T5/20 ,  G06V20/40

CPC classification number: G06T7/11 ,  G06T5/002 ,  G06T5/20 ,  G06T7/13 ,  G06T7/194 ,  G06V20/46

Abstract: Disclosed herein are system, method and computer readable storage medium for detecting space suitable for overlaying media content onto an image. The system receives an image which may be an image or a video frame. The image is processed using a number of image processing techniques in order to automatically propose spaces for inserting media content onto the image. The proposed spaces may then be further analyzed using a heuristics-based approach to select bounding boxes for inserting media content. Subsequently, one or more media content items may be selected for insertion onto the bounding boxes on the image. The system may then cause a display of the image with the selected media content item overlaid onto the image within the selected bounding boxes.

公开(公告)号：US20220245820A1

公开(公告)日：2022-08-04

申请号：US17162245

申请日：2021-01-29

Applicant: salesforce.com, inc.

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

IPC: G06T7/11 ,  G06T5/00 ,  G06T5/20 ,  G06K9/00 ,  G06T7/13 ,  G06T7/194

Abstract: Disclosed herein are system, method and computer readable storage medium for detecting space suitable for overlaying media content onto an image. The system receives an image which may be an image or a video frame. The image is processed using a number of image processing techniques in order to automatically propose spaces for inserting media content onto the image. The proposed spaces may then be further analyzed using a heuristics-based approach to select bounding boxes for inserting media content. Subsequently, one or more media content items may be selected for insertion onto the bounding boxes on the image. The system may then cause a display of the image with the selected media content item overlaid onto the image within the selected bounding boxes.

公开(公告)号：US20220245322A1

公开(公告)日：2022-08-04

申请号：US17163162

申请日：2021-01-29

Applicant: salesforce.com, inc.

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

IPC: G06F40/103 ,  G06F40/284 ,  G06T11/60 ,  G06N3/04

Abstract: An online system generates a set of content item variations for a reference content item that include different styles of text for the content item. The different styles of text are generated by applying machine-learned style transfer models, for example, neural network based models to reference text of the reference content item. The text variations retain the textual content of the reference text but are synthesized with different styles. The online system can provide the content item variations to users on an online experimental platform to collect user interaction information that may indicate how users respond to different styles of text. The online system or the content providers can effectively target users with content items that include the style of text the users respond to based on the collected information.

公开(公告)号：US11210111B2

公开(公告)日：2021-12-28

申请号：US16176933

申请日：2018-10-31

Applicant: salesforce.com, inc.

Inventor： Sonke Rohde ,  Brian J. Lonsdorf

IPC: G06F9/451 ,  G06F8/38 ,  G06F40/186 ,  G06F8/36 ,  G06N20/00

Abstract: Techniques are disclosed relating to automatically generating user interfaces. In some embodiments, input data to be displayed is grouped into components (e.g., based on depth within hierarchical code, coordinates in a display space, etc.). These components may be based on template information that defines a set of known component types. In some embodiments, the system formats the selected components according to display parameters and causes display of a user interface that displays the components based on the formatting. In various embodiments, the disclosed techniques may allow automatic creation of effective user interfaces without information specifying layout and formatting for input data. This may provide flexible, quality interfaces without requiring design or coding expertise. Further, disclosed techniques may allow the automatic interface generator to generate interfaces similar to other existing interfaces.