In recent years, the number of web services grows explosively. With a large amount of information resources, it is difficult for users to quickly find the services they need. Thus, the design of an effective web service recommendation method has become the key factor to satisfy the requirements of users. However, traditional recommendation methods often tend to pay more attention to the accuracy of the results but ignore the diversity, which may lead to redundancy and overfitting, thus reducing the satisfaction of users. Considering these drawbacks, a novel method called DivMTID is proposed to improve the effectiveness by achieving accurate and diversified recommendations. First, we utilize users’ historical scores of web services to explore the users’ preferences. And we use the TF-IDF algorithm to calculate the weight vector of each web service. Second, we utilize cosine similarity to calculate the similarity between candidate web services and historical web services and we also forecast the ranking scores of candidate web services. At last, a diversification method is used to generate the top- recommended list for users. And through a case study, we show that DivMTID is an effective, accurate, and diversified web service recommendation method.

中文翻译：

---

高精度和多样化的服务建议

近年来，Web服务的数量呈爆炸性增长。拥有大量信息资源，用户很难快速找到所需的服务。因此，有效的Web服务推荐方法的设计已成为满足用户需求的关键因素。然而，传统的推荐方法往往倾向于更加关注结果的准确性，却忽略了多样性，这可能导致冗余和过度拟合，从而降低了用户的满意度。考虑到这些缺点，提出了一种称为DivMTID的新颖方法，通过实现准确和多样化的建议来提高有效性。首先，我们利用用户对网络服务的历史评分来探索用户的偏好。然后，我们使用TF-IDF算法来计算每个Web服务的权重向量。其次，我们利用余弦相似度来计算候选Web服务与历史Web服务之间的相似度，并预测候选Web服务的排名得分。最后，采用多样化的方法来产生最高推荐给用户的清单。并且通过案例研究，表明DivMTID是一种有效，准确和多样化的Web服务推荐方法。