Web API recommendation method based on topic model clustering

A topic model and recommendation method technology, applied in the field of WebAPI service recommendation, can solve the problems of short Mashup service description documents, increase the workload of the recommendation system, and less information, so as to alleviate the sparsity problem, improve the recommendation accuracy, and improve the model accuracy. Effect

Active Publication Date: 2022-07-15
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, as the number of Web API services on the Internet continues to increase, the recommendation system needs to face two problems in Web API recommendation: First, Mashup service description documents are usually short, with sparse features and less information. The short description information extracts the potential information of the Mashup service description requirements. Second, the large number of Web API service sets greatly increases the workload of the recommendation system to search for related API services. How to quickly and effectively determine the Web API service candidate set

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Web API recommendation method based on topic model clustering
  • Web API recommendation method based on topic model clustering
  • Web API recommendation method based on topic model clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0128] The present invention will be further described below.

[0129] A Web API recommendation method based on topic model clustering, comprising the following steps:

[0130] Step 1: Calculate the semantic weight information of the word according to the context information to obtain the document-word semantic weight information matrix D. The steps are as follows:

[0131] 1.1 Count word frequency information and calculate TF-IDF information. The steps are as follows:

[0132] 1.1.1 Traverse each word in the Mashup service description document, count the number of occurrences of each word in the current document, and calculate the TF value of each word. The calculation formula is as follows:

[0133]

[0134] where TF i,j Represents the word frequency information of the jth word in the i-th Mashup service description document, NUM(j) represents the number of occurrences of the j-th word, and LEN(i) represents the length of the i-th Mashup text;

[0135] 1.1.2 Count the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A Web API recommendation method based on topic model clustering, calculates the semantic weight information of words according to context information to obtain document-word semantic weight information matrix D; counts word co-occurrence information to calculate SPPMI matrix information; obtains Mashup service based on The word frequency information matrix D of the document word, the context SPPMI matrix M of the word, the word embedding information matrix can be obtained by decomposing M, and the above two kinds of information can be further combined to calculate the topic information of the service; the obtained topic feature of the Mashup service is used as the spectrum The input of the clustering is clustered. By cutting the graph composed of all data points, the edge weights between different subgraphs after the graph are cut as low as possible, and the edge weights in the subgraphs are as high as possible. The purpose of clustering; combining GBDT and FM methods to make prediction recommendations for Web API services. The present invention effectively realizes Web API recommendation.

Description

technical field [0001] The invention relates to a Web API service recommendation method based on topic model clustering constructed for Mashup service. Background technique [0002] With the continuous maturity of Internet technology, the cost of Internet-based services continues to decrease. Driven by the idea of ​​"service-based" service computing, more and more companies publish data, resources or related services on the Internet to improve the utilization of information. rate and competitiveness. However, most of the traditional services follow the simple object access protocol, and usually provide a single-function service for the business needs of a specific field. In addition, there are problems such as complex technical system and poor scalability, which are difficult to adapt to complex and changeable applications in real life. Scenes. Therefore, for Web service providers, how to quickly reintegrate existing service resources according to actual users and specific...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9535G06F16/35G06F40/216G06F40/284G06K9/62
CPCG06F16/9535G06F16/355G06F40/216G06F40/284G06F18/22
Inventor 陆佳炜郑嘉弘赵伟马超治徐俊张元鸣肖刚
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products