USER FEEDBACK MECHANISM FOR SOFTWARE APPLICATIONS

    公开(公告)号:US20230333962A1

    公开(公告)日:2023-10-19

    申请号:US17969555

    申请日:2022-10-19

    申请人: AUTODESK, INC.

    IPC分类号: G06F11/36 G06F11/34

    CPC分类号: G06F11/3604 G06F11/3476

    摘要: A feedback mechanism that reports software issues between users of software applications and the developers of the software applications. The feedback mechanism generates feedback logs that capture moments of user frustration at the moment a user encounters issues with using a particular software application executing on a client device. The feedback mechanism is triggered to generate a feedback log by the user via a predetermined set of user inputs. Once generated, the feedback log captures an associated importance level, a user description, and/or context information (such as application and command activity information) for the particular software application and one or more other software applications that interacted with the particular software application executing on the client device. The feedback log can also capture multimedia content such as audio, images, and videos. The feedback log is then transmitted to a server of a developer of the particular software application.

    TRAINING MACHINE LEARNING MODELS TO PERFORM NEURAL STYLE TRANSFER IN THREE-DIMENSIONAL SHAPES

    公开(公告)号:US20230326158A1

    公开(公告)日:2023-10-12

    申请号:US18149605

    申请日:2023-01-03

    申请人: AUTODESK, INC.

    摘要: One embodiment of the present invention sets forth a technique for training a machine learning model to perform style transfer. The technique includes applying one or more augmentations to a first input three-dimensional (3D) shape to generate a second input 3D shape. The technique also includes generating, via a first set of neural network layers, a style code based on a first latent representation of the first input 3D shape and a second latent representation of the second input 3D shape. The technique further includes generating, via a second set of neural network layers, a first output 3D shape based on the style code and the second latent representation, and performing one or more operations on the first and second sets of neural network layers based on a first loss associated with the first output 3D shape to generate a trained machine learning model.

    SEMANTIC SCRIPT LANGUAGE PROCESSING
    24.
    发明公开

    公开(公告)号:US20230315986A1

    公开(公告)日:2023-10-05

    申请号:US17710663

    申请日:2022-03-31

    申请人: Autodesk, Inc.

    发明人: Clayton P. Hotson

    IPC分类号: G06F40/279 G06F40/253

    CPC分类号: G06F40/279 G06F40/253

    摘要: A method and system provide the ability to process source computer instructions. The source computer instructions are obtained and include input statements that consist of two functions and one or more arguments. The two functions are competing with each other for consumption of the one or more arguments. For an input statement, an inherent numeric precedence weight is determined for each function and argument. All possible legal configurations of the functions and arguments are determined and consist of different groupings of the functions and arguments. A score is assigned to each grouping and consists of a sum of the weights within each different grouping. The grouping and legal configuration having the highest score is selected. The input statements are compiled into executable code using the selected different grouping.

    VOXEL-BASED APPROACH FOR DESIGN MODELS
    26.
    发明公开

    公开(公告)号:US20230297734A1

    公开(公告)日:2023-09-21

    申请号:US17832123

    申请日:2022-06-03

    申请人: AUTODESK, INC.

    IPC分类号: G06F30/20 G06F30/12

    摘要: A voxel-based design approach enables the creating and modifying of a design model comprising a 3D grid of discrete voxels that is represented by a voxel data structure. The voxel data structure comprises voxel-level entries, each entry corresponding to a voxel based on the 3D location within the 3D grid. The voxel data structure includes a design-level entry for storing design-level performance metrics. The system updates the voxel data structure to reflect user modifications to the design model and renders a visualization of the updated design model. The system displays a per-voxel heat map for the design model for a selected performance metric based on the voxel data structure. The design system displays multiple optimized design solutions based on corresponding optimized voxel data structures. The system generates the multiple optimized design solutions based on a voxel-based optimization technique. The system also performs a voxel-based recommendation visualization technique.

    MULTI-USER COLLABORATION SYSTEM FOR GENERATIVE DESIGNS

    公开(公告)号:US20230297728A1

    公开(公告)日:2023-09-21

    申请号:US17696340

    申请日:2022-03-16

    申请人: AUTODESK, INC.

    IPC分类号: G06F30/10

    CPC分类号: G06F30/10 G06F2111/02

    摘要: In various embodiments, a computer-implemented method comprises receiving, during a real-time collaboration session including a plurality of participants, a first input associated with a first selectable component from a set of pre-defined selectable components associated with a shared design model, where the first selectable component is associated with a first participant in the plurality of participants, in response to receiving a confirmation of the first input, modifying the shared design model to generate an updated shared design model, wherein the first selectable component in the updated shared design model includes the modified first selectable component, and causing the updated shared design model to be synchronized with at least one other participant in a plurality of participants included in the real-time collaboration session.

    DEFECT REMOVAL FROM MANUFACTURED OBJECTS HAVING MORPHED SURFACES

    公开(公告)号:US20230289596A1

    公开(公告)日:2023-09-14

    申请号:US18141262

    申请日:2023-04-28

    申请人: Autodesk, Inc.

    摘要: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided repair of physical structures include: generating a two dimensional difference image from a first three dimensional model of at least one actual three dimensional surface of a manufactured object, and a second three dimensional model of at least one source three dimensional surface used as input to a manufacturing process that generated the manufactured object; obtaining from an image-to-image translation based machine learning algorithm, trained using pairs of input images representing deformed and deformed plus surface defected added versions of a nominal three dimensional surface, a translated version of the two dimensional image; generating from the translated version of the two dimensional image a third three dimensional model of at least one morphed three dimensional surface corresponding to the at least one source three dimensional surface. Further, defects can be removed based on the third three dimensional model.

    TECHNIQUES FOR TRIAL-AND-ERROR LEARNING IN COMPLEX APPLICATION ENVIRONMENTS

    公开(公告)号:US20230289220A1

    公开(公告)日:2023-09-14

    申请号:US17965715

    申请日:2022-10-13

    申请人: AUTODESK, INC.

    IPC分类号: G06F9/48 G06F9/38

    CPC分类号: G06F9/4881 G06F9/3836

    摘要: One embodiment of a computer-implemented method for automatically tracking how extensively software application commands have been investigated comprises identifying an interaction with a first command occurring within a graphical user interface, wherein the first command is associated with one or more command parameters; updating a command history associated with the first command based on the interaction with the first command; computing a progress level associated with the first command based on the command history, wherein the progress level indicates how many command parameters included in the one or more command parameters have been modified; determining a coverage level associated with the first command based on the command history; and outputting at least one of the use level or the progress level for display in the graphical user interface.