Semantic sparse Web service discovery method based on Gaussian ATM and word embedding

Abstract

The invention provides a semantic sparse web service discovery method based on Gaussian ATM and word embedding, which is performed in the following order: collecting a Web service description document, parsing the collected Web service description document, obtaining a feature vocabulary in the Web service description document, preprocessing the vocabulary in the Web service description document to obtain a set of prototype words; using a word embedding training model Word2Vec to train the set of the prototype words to obtain a continuous vector representation of each word in the set of the prototype words; using the set of the prototype words obtained via the Gaussian ATM model to train, and obtaining each Web service hierarchical structure; using the set of continuous vectors obtained bytraining to enrich user query, and obtaining an extended user query; using the obtained service hierarchical structure and using the probability ranking method to obtain query output corresponding tothe extended user query. The method provided by the invention can realize accurate and efficient Web service discovery.

Description

technical field [0001] The invention relates to the technical field of service computing, in particular to a semantic sparse Web service discovery method based on Gaussian ATM and word embedding. Background technique [0002] Today, with the increasing popularity of informatization, the software architecture of the Internet and its computing environment have undergone drastic changes, which has contributed to the development and popularization of software service development based on the Internet system. In the ever-changing software service environment, the development of software systems will face new challenges due to the fundamental characteristics of highly distributed and autonomous computing resources. This kind of dynamic, changeable and complex difficult problem can be solved by using the Web architecture based on the service-oriented thought. Therefore, with the rapid development of the service technology that uses the architecture designed by the service-oriented ...

AI Technical Summary

Problems solved by technology

For this reason, the scale of Web services continues to increase rapidly, making it difficult for mass users to accurately and efficiently discover Web services.

At the same time, whether the Web services published on the Internet are described by using XML or natural language, there are fewer description feature words (for example, the service description words in PWeb are less than 100, accounting for more than 70%) , and there is a problem of insufficient feature vocabulary statistics after conversion

This phenomenon of semantic sparseness makes the similarity calculation ineffective, and this problem brings new difficulties to the keyword-based search method.

Images