A Service Recommendation Algorithm Based on Knowledge Graph and Collaborative Filtering

Abstract

With the rapid development of the Internet, the number of Web APIs is increasing. How to recommend accurate and appropriate Web APIs to mashups has become a focus and difficulty in the field of service computing. The existing methods are mainly based on collaborative filtering technology, but these methods have problems such as the data sparsity and cold start, which leads to poor recommendation effects. This paper proposes a service recommendation model based on knowledge graph and collaborative filtering. In this model, the knowledge graph connects the APIs and mashups related information to mine the potential relations between mashups and APIs, hence reducing the impact of data sparsity. All the API entities in the service knowledge graph are embedded into the low-dimensional space through the representation learning algorithm, then the distances between the API vectors are calculated to recommend the related APIs. In addition, in order to solve the cold-start problem of recommending APIs to target mashups that have no APIs usage, the similarities of functional sets extracted from mashups are calculated to recommend APIs for target mashups. At the same time, the model obtains the Mashup-API usage record, using the technology of collaborative filtering to recommend appropriate APIs to target mashups. Finally, the similarities of the above recommended APIs are normalized and sorted to form the final recommendation result. The experimental results show that our proposed model significantly improves the accuracy of service recommendation.

Core Technology Optimization of Intelligent Financial Technology Based on Collaborative Filtering Algorithm in Big Data Environment

“…Combined with the actual situation of the financial industry, collaborative filtering algorithms mostly use collaborative filtering algorithms based on user needs. It is mainly divided into two steps: establishing the similarity model and then establishing the interest model [17]. The similarity model mainly views the set of customers' interests, and the degree of interest is to recommend new financial products based on the financial products purchased by users [18].…”

Group Recommendation Based on Heterogeneous Graph Algorithm for EBSNs

“…He et al proposed the use of neural networks to improve collaborative filtering [43]. Although collaborative filtering has been shown to be effective when users expressed enough ratings to share common ratings with other users, it has tended to perform poorly for so-called cold-start users [44]- [46].…”

SSIKG: A framework for spatial‐semantic integrated indoor knowledge graph construction

“…KGs express data by focusing on relationships between objects, and have been built for various purposes, such as recommendation or question and answer systems. In particular, many studies have been conducted to build KGs for service recommendations (Hu et al, 2019; Jiang et al, 2021; Mezni, 2021; Mezni et al, 2021; Wang, Wang, et al, 2019). For example, Wang, Wang, et al (2019) developed a domain‐oriented user and service interaction KG that expresses data by focusing on the user–service relationship.…”