Abstract: Methods, systems, and computer programs encoded on a computer storage medium, for training and using machine learning models are disclosed. Methods include creating a model that represents relationships between user attributes, content exposures, and performance levels for a target action using organic exposure data specifying one or more organic exposures experienced by a particular user over a specified time prior to performance of a target action by the particular user and third party exposure data specifying third party exposures of a specified type of digital component to the particular user over the specified time period. Using the model, an incremental performance level attributable to each of the third party exposures at an action time when the target action was performed by the particular user is determined. Transmission criteria for at least some digital components to which the particular user was exposed are modified based on the incremental performance.

Abstract: This application provides a controller software architecture, a controller software upgrade method, a controller, and an apparatus. The controller software architecture includes: a driver layer, an interface layer, an application layer, and a global buffer. The interface layer is configured to exchange data with the application layer through the global buffer, and the interface layer is further configured to exchange data with the driver layer through the global buffer. In this way, data exchange between the interface layer and the application layer and data exchange between the interface layer and the driver layer can be implemented through the global buffer, thereby developing a controller.

Abstract: An application scaling management method and apparatus are disclosed, so as to perform, in a case in which an application requires capacity expansion and remaining resources of a data center in which the application runs are insufficient, capacity expansion of the application by utilizing remaining resources of another data center, thereby improving resource utilization and capacity expansion efficiency.

Abstract: The present disclosure discloses a networking method and apparatus for a home network with a universal wired medium networking technology. The method includes: receiving, by a G.hn network device, a key-press operation; broadcasting a notice of open registration of a current domain and receiving joining application information of applying for joining in the current domain from an extra-domain node in a first preset time window, by the G.hn network device; determining, by the G.hn network device, whether a signal intensity of the extra-domain node transmitting the joining application information is not less than a first preset threshold; and allowing, by the G.hn network device, the extra-domain node to join in the current domain if the signal intensity of the extra-domain node transmitting the joining application information is not less than the first preset threshold.

Abstract: An application scaling management method and apparatus are disclosed, so as to perform, in a case in which an application requires capacity expansion and remaining resources of a data center in which the application runs are insufficient, capacity expansion of the application by utilizing remaining resources of another data center, thereby improving resource utilization and capacity expansion efficiency.