Service quality prediction method and system based on deep neural network

Abstract

The invention discloses a service quality prediction method based on a deep neural network and a system thereof, and relates to the technical field of network services. The method includes the following steps: input request context variable information, and encode in the encoding module through entity expression matrix to obtain embedded request matrix; compress the encoded context variable information and perform feature extraction to obtain the described Request the embedded request vector according to the time sequence of the context variable information; according to the time sequence, input the embedded request vector to the LSTM network module to output the prediction data information of the deep neural network to the next input request context variable information; The predicted data information is sensed to obtain the decoded predicted data information, and the decoded predicted data information is restored to service quality data and output.

Description

technical field [0001] The invention relates to the technical field of network services, in particular to a service quality prediction method and system based on a deep neural network. Background technique [0002] The number of Web Services in the Internet has increased dramatically in the past ten years. With the increase in the number of public Web services, the application of SOA (Service Oriented Architecture, service-oriented architecture) architecture has also become very extensive. However, the complex network environment of the Internet makes the status of services ever-changing, so effective service quality prediction is very important at this time. [0003] Traditional service quality prediction methods are mostly based on CF model (Collaborative Filtering, collaborative filtering model) and MF model (Matrix factorization, matrix factorization model), which can use limited context data. At the same time, it is difficult for these two methods to be easily extended...

AI Technical Summary

Problems solved by technology

[0003] Traditional service quality prediction methods are mostly based on CF model (Collaborative Filtering, collaborative filtering model) and MF model (Matrix factorization, matrix factorization model), which can use limited context data

At the same time, it is difficult for these two methods to be easily extended to support the prediction of multi-type QoS (Quality of Service, service quality) data

It also lacks corresponding modeling methods for the hidden variables that affect the QoS response sequence

Images