API recommendation method based on heterogeneous information network element path

Abstract

The invention relates to an API (Application Program Interface) recommendation method based on a heterogeneous information network element path, which comprises the following steps of: acquiring description information of an API and a Mashup application thereof, and constructing a heterogeneous information network surrounding the API; generating initial low-dimensional embedding of an API (Application Program Interface) and a Mashup; generating context meta-path embedding based on API and Mashup interaction; initial low-dimensional embedding of the API and the Mashup and context meta-path embedding based on interaction of the API and the Mashup are fused, a neural network model is trained, and API recommendation is achieved. According to the method and the device, a user can be helped to quickly find a proper API from a huge API library through accurate recommendation when developing a Mashup application, so that the development efficiency of the application is improved.

Description

technical field [0001] The present invention relates to the field of service computing and data analysis, in particular to an API (Application Programming Interface, application program interface) recommendation method of heterogeneous information network element paths. Background technique [0002] Web API is a web application program interface, which includes a wide range of functions. Through the API interface, web applications can realize storage services, message services, computing services, information services, search services and other capabilities. Using these capabilities, powerful web applications can be developed. . Although there are many excellent APIs on the Internet, in the face of the rapid development of the information society and the emergence of a large number of additional requirements, the functions of a single API have become increasingly unable to cope with complex business needs. Therefore, the development mode of creating new applications by mash...

AI Technical Summary

Problems solved by technology

However, it is still a challenging problem to quickly discover and select APIs suitable for mashup needs in a large-scale API database containing various functions

In addition, since most APIs are described using plain text or HTML rather than structured language, this further increases the difficulty of automatic API discovery

Traditional recommendation methods do not learn the explicit representation of meta-paths in recommendation methods that describe the relationship between APIs and Mashups, and describe auxiliary information as isolated features rather than complete semantic information, so the recommendation performance still needs to be further improved

Images