MODEL-BASED COLLABORATIVE FILTERING METHOD FOR COLLABORATIVE WEB QUALITY-OF-SERVICE PREDICTION FOR PRIVACY PROTECTION

摘要

Disclosed is a model-based collaborative filtering method for collaborative Web quality-of-service prediction for privacy protection. The method comprises the following steps: step one, data collection, involving: each user locally collecting a quality-of-service value, i.e. a QoS value; step two, data disguising, involving: disguising the quality-of-service value; step three, carrying out model-based collaborative filtering on the disguised quality-of-service value; and step four, result prediction, involving: predicting a result according to the quality-of-service value subjected to collaborative filtering. The present invention introduces differential privacy to a collaborative Web service QoS prediction framework for the first time, and a user can obtain the maximum privacy protection by means of ensuring the availability of data. An experiment result indicates that the method of the present invention provides secure and accurate collaborative Web service QoS prediction, and the model-based collaborative filtering method has advantages in terms of capturing a latent structure of QoS data.