The terms "accounting process automation" and "robotic process automation" and "machine intelligence" and "artificial intelligence" seem to have very different meanings to different people.
Here is a list of vendors that seem to provide process automation:
This video showsa really good example of what most people seem to be calling "RPA" or robotic process automation. What RPA seems to be is a "bot" performing specific detailed tasks by "scraping" or "reading" information from a web page and then "copying and pasting" fields from a web site or application to another. It is like "recording" a macro of a routine task which is then repeated over and over by the robot/macro rather than performed by a human.
So, what RPA seems to be is similar to what a business rules management system does plus some sort of user interface to "scrap" or "read" information from one system and put it into another. Neither business rules management systems nor RPA seem to have an over-arching conceptual model which can be leveaged.
These seem software vendors seem to provide similar capabilities, but they take a different approach. Each of these uses the semantic web approach and does provide the ability to create a conceptual model which can be leveraged by business rules:
Basically, RPA is a computer performing a specific set of routine tasks in order, replacing a human that performed these mundane routine tasks.
So, I can see the benefit of RPA. I have a different vision for automation. I am taking the expert systems approach. I would not consider RPA an expert system, it is just stringing tasks together. And I am not using "deep learning" or "machine learning" commonly associated with artificial intelligence.
These different approaches each have different capabilities. The pros and cons of each approach are not currently clear to me. What is clear is that different companies are trying to figue out the best way to make automation work.
##########