GROUP RECOMMENDATION FOR SELECTION OF SERVICE ITEMS

摘要

The present disclosure provides enhanced group recommendation for selection of a service item with respect to a service class, and communicates the enhanced group recommendation to a sub-group of service users. Initial service scores for service items in the service class are generated by aggregating individual service preferences of sub-group members with respect to the service class. Group preferences for service items in the service class are then predicted using statistic data on previous service selections of sub-group members with respect to the service class. The initial service scores are aggregated with the predicted group preferences to generate of weighted service scores with respect to service items in the service class. One of the service items in the service class that has the highest weighted score is the group recommendation is communicated to the sub-group members.

主权项

1. A method by a network node of a wireless communication network for providing a group recommendation for selection of a service item with respect to a service class to a sub-group of service users, the method being performed by at least one processor in the network node to communicate the group recommendation to end users of the communication network and comprising the steps:
recording statistic data on previous service selections of sub-group members with respect to a plurality of service classes and a plurality of sub-groups of service users; training a prediction module with respect to the service classes by applying a machine learning algorithm to the statistic data, which has been recorded, to calculate probability that a new sub-group of service users will select service items in the service class as related group preferences; generating initial service scores for a specific sub-group of sub-group members and related service items in a corresponding service class by aggregating individual service preferences of the sub-group members with respect to the corresponding service class; predicting group preferences for the related service items in the corresponding service class on the basis of statistic data on previous service selections of sub-group members with respect to the service class; aggregating initial service scores with the predicted group preferences for generation of weighted service scores with respect to service items in the service class; and forwarding the service item in the service class with highest weighted score as group recommendation to the sub-group members.