A web service is a technology that allows data to be exchanged between applications using open protocols and standards. Web services generally offer basic functions that solve specific problems. The composition of services occurs when more complex problems need to be solved using successive invocations to other services. The automatic composition of web services is a current problem. Due to the continuous creation and updating of services, the manual composition of new services becomes impractical. Planning algorithms are an alternative to automate the process of web services composition. In particular, the planning algorithms with preferences allow users to guide the algorithm to find a solution in line with their requirements (e.g. prioritizing the use of services according to properties such as availability, cost, response time, etc.). This paper introduces a Planning approach with preferences to compose and run complex services from a set of web services given as input. To evaluate the approach, different preferences about the input services were used to obtain composition of services. As a result, we measured the feasibility of the proposed approach and the impact of the use of preferences on the composition result.

中文翻译：

---

基于偏好的 Web 服务组合 AI 规划


Web 服务是一种允许使用开放协议和标准在应用程序之间交换数据的技术。 Web 服务通常提供解决特定问题的基本功能。当需要使用对其他服务的连续调用来解决更复杂的问题时，就会出现服务组合。 Web服务的自动组合是当前的一个问题。由于服务的不断创建和更新，手动组合新服务变得不切实际。规划算法是自动化 Web 服务组合过程的替代方案。特别是，具有偏好的规划算法允许用户指导算法找到符合其需求的解决方案（例如，根据可用性、成本、响应时间等属性对服务的使用进行优先级排序）。本文介绍了一种规划方法，该方法具有从作为输入给出的一组 Web 服务组合和运行复杂服务的偏好。为了评估该方法，使用输入服务的不同偏好来获取服务组合。因此，我们测量了所提出方法的可行性以及偏好的使用对合成结果的影响。