A QoS-aware web service recommendation method based on user and service clustering

Abstract

The present invention provides a QoS-aware Web service recommendation method based on user and service clustering, based on the QoS records of users calling services, using cosine similarity calculation to cluster users with similar service preferences; and then describing the service itself The document WSDL file is used to extract and normalize feature words, and the K-means++ algorithm is used to cluster services with similar functional characteristics; finally, similar user sets and similar service sets are integrated into the collaborative filtering algorithm to solve the problem of the lack of service call matrix QoS values ​​are calculated and recommendations are generated. By using the data set provided by the WSDream open source project to carry out simulation experiments, the results show that this Web service recommendation method based on user and service clustering, compared with the existing technology, has two mainstream evaluation indicators of mean absolute error and root mean square error. has better results.

Description

technical field [0001] The invention relates to the field of service recommendation in data mining, in particular to a Web service recommendation method based on user and service clustering QoS perception. Background technique [0002] With the rapid development of the current Internet, the explosive growth of web services with various functions available on it, it is becoming more and more difficult for users to select an appropriate web service, so there is a great need for a related method to automatically and efficiently select an appropriate web service Recommended to users. Faced with massive service types and service information, how to efficiently and accurately recommend relevant services to users based on user specificity has increasingly become a research problem in the industry. Web service recommendation provides a research direction to solve this problem. [0003] Web service recommendation is to establish a recommendation model for service recommendation bas...

AI Technical Summary

Problems solved by technology

[0004] These studies have relatively good performance in predicting and recommending related services and variables based on QoS, but many of them ignore the significant impact of service functions and user similarity on the accuracy of recommendation results, and many recommendation models are deeply affected by the sparsity of QoS matrix data. These factors lead to the problem that the accuracy of the recommendation results is not high, which needs to be solved urgently

Images