Service quality prediction method and system based on deep neural network
A deep neural network and quality of service technology, applied in the field of service quality prediction method and system based on deep neural network, can solve the problems of limited context data, difficult expansion, and lack of modeling methods for QoS response sequence
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2021-12-14
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
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...
Examples
Embodiment Construction
[0029] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0030] The present invention will be further described below in conjunction with the accompanying drawings.
[0031] A service quality prediction method based on deep neural network, such as figure 1 shown, including the following steps:
[0032] Input the request context variable information and encode it in the encoding module through the entity expression matrix to obtain the embedded request matrix.
[0033] In a specific embodiment, the request context variable information includes numeric and non-numeric features, which need to be preprocessed before being input to the encoding module. For continuous data, it needs to be sampled to convert it into discretized data, so as to fuse the service quality data information with the request context information. For non-numerical variables, the first six dimensions (u1...