Model-Based Test Modeling and Automation Tool for Intelligent Mobile Apps

Functionalities of AI-powered mobile Apps or systems heavily depend on the given training dataset. The challenge in this case is that a learning system will change its behavior due to a slight change of dataset. While current alternative approaches for evaluating these apps either focus on individual performance measurement such as accuracy etc. Inspired by principles of the decision tree test method in software engineering, we introduce a 3D decision tree testing model for AI testing, a combined AI feature input tree, context tree, and output tree methodology for testing AI-powered applications. We report a newly developed AI test automation tool (known as AITest), which is built and implemented based on an innovative 3D AI Test model for AI-powered functions in intelligent mobile apps to support model-based AI function testing, test data generation, and auto test scripting and execution, and adequate test coverage analysis. Furthermore, the tool infrastructure, components, sample applications, and case study results are presented.