Greetings, I am trying to develop a virtual voice assistant that understands the intention I want to make in a program. Example: photoshop. This part has already been done, the complicated thing I want to do, is to keep the actions that I have been doing sequentially, and I would like to predict after several interactions a possible action. The thing is that I have no idea how to start this problem that I'm having, or what kind of algorithm to use. How would you do? I appreciate your time reading this.