Abstract:
Example user behavior prediction methods and apparatus are described. One example method includes obtaining a first contribution value of each piece of characteristic data for a specified behavior after obtaining behavior prediction information including a plurality of pieces of characteristic data. Every N pieces of characteristic data in the plurality of pieces of characteristic data may be processed by using one corresponding characteristic interaction model, to obtain a second contribution value of the every N pieces of characteristic data for the specified behavior. Finally, an execution probability of executing the specified behavior by a user may be determined based on the obtained first contribution value and the obtained second contribution value, to predict a user behavior. In the example method, interaction impact of the plurality of pieces of characteristic data on the specified behavior is considered during behavior prediction.
Abstract:
Embodiments of the present invention disclose a method, an apparatus, and a system for implementing an interactive near video on demand (NVOD) channel. The present invention relates to the field of NVOD channels and can implement an interactive NVOD channel at a low operation cost. The method includes: sending NVOD program metadata to a user equipment; receiving a request for playing an NVOD program, where the playing request is sent by the user equipment and includes the NVOD program that a user selects from the NVOD program metadata through the user equipment; determining, according to the playing request, a next NVOD program to be played, and sending a media stream of the determined NVOD program in multicast/broadcast mode. The present invention is mainly applied to NVOD channels and may be applied to IMS-based IPTV systems.
Abstract:
A neural network building method and apparatus are disclosed, and relate to the field of artificial intelligence. The method includes: initializing a search space and a plurality of building blocks, where the search space includes a plurality of operators, and the building block is a network structure obtained by connecting a plurality of nodes by using the operator; during training, in at least one training round, randomly discarding some operators, and updating the plurality of building blocks by using operators that are not discarded; and building a target neural network based on the plurality of updated building blocks. In the method, some operators are randomly discarded. This breaks association between operators, and overcomes a co-adaptation problem during training, to obtain a target neural network with better performance.