Abstract: A processing machine (10) for building an object (11) from powder (12) includes a build platform (26A); a powder supply assembly (18) that deposits the powder (12) onto the build platform (26A) to form a powder layer (13); and an energy system (22) that directs an energy beam (22D) at a portion of the powder (12) on the build platform (26A) to form a portion of the object (11). The powder supply assembly (18) can include (i) a powder container (640A) that retains the powder (12); (ii) a supply outlet (639) positioned over the build platform (26A); and (ii) a flow control assembly (642) that selectively controls the flow of the powder (12) from the supply outlet (639).

Abstract: Techniques are described herein for providing data attribution based on spatial memory using a machine learning pipeline. The techniques include receiving, from a client device, an image of an object, wherein the image appended with object-specific data. The techniques further include extracting one or more features of the object from the object-specific data. The features may be included in a product catalog from one or more data sources. Based at least on one or more features associated with the object, a suggested category for the image is determined and associated with the image. The suggested category and the image may be used to train a machine learning model via a machine learning classification algorithm to predict a label for the image. The machine learning model is applied to assign the label to the image based at least on the suggested category.

Abstract: In methods and systems, a textual portion of an electronic message from a first user device to a second user device is received. One or more contextual tags to represent a context of the textual portion are recommended. The recommending the one or more contextual tags is based at least in part on the receiving the textual portion. One or more rich media elements are recommended to represent the context of the textual portion. The recommending the one or more rich media elements is based at least in part on the one or more contextual tags. The one or more rich media elements and the textual portion are integrated into a rich media message. The rich media message is provided to the second device.

Abstract: Monetization plug-ins in interactive multimedia applications. At least some of the illustrative embodiments are methods including: accepting an indication of flow of an interactive application configured to selectively implement an in-application purchase, the accepting by way of a graphical user interface (GUI); creating a representation of the flow of the interactive application, the representation at least partially in a declarative format; and executing the interactive application by a first runtime engine, the first runtime engine becomes executable code that implements the in-application purchase.

Abstract: Creation of interactive games. At least some embodiments involve creating an interactive application by way of a graphical user interface in a declarative format. The interactive application created is represented in a portable format, also at least partially in a declaration format. Execution of an interactive game involves reading the portable format by a runtime engine, and creating by the runtime engine executable routines consistent with the interactive application.