RPA vs. Conversational AI: What’s the difference?
Many people wonder how Robotic Process Automation (RPA) differs from Conversational AI and Natural Language Processing (NLP). The short answer is that Conversational AI and NLP use a combination of rules and probability, whereas RPA uses structured inputs and defined logic.
RPA uses structured inputs and defined logic
RPA is a generic term to describe any type of process automation where a piece of software mimics the repetitive actions of a human user. It’s most commonly used to mimic the clicks of a human user to perform actions such as data entry on a user interface, complete forms, trigger actions on a screen, upload files to an Enterprise Resource Planning (ERP) system and more. RPA is preprogrammed, meaning these systems have no inherent ability to learn from their actions or environment.
An example of a great candidate for RPA is expense processing. Though mostly handled by one department, each expense report is processed with multiple steps. A typical expensing process is as follows: retrieving an attachment from an email or information from an app, categorizing the expenses, routing the invoice to the right person for approval, and finally, uploading the information to a finance system for payout. All of these steps can be handled by RBA software.
Conversational AI and NLP uses a combination of rules and probability
Artificial intelligence is primarily software that has the ability to learn from the data it processes. Machine learning is a key component of modern AI systems, giving AI entities the ability to extract and learn patterns from data. Based on the type, the machine learning algorithm could learn from experience in controlled environments where rules are well defined, for example, playing chess, learn from explicitly defined labels that are usually set by a human, such as fraud detection, or simply identify and delineate patterns, for example finding similarities in data.
Natural language processing is a sub-field of machine learning that deals with performing language-related tasks such as translation, comprehension, summarization or understanding pieces of text. A wide field in itself, the most commonly deployed language models perform understanding tasks and are used primarily in chatbots.
Natural Language Understanding (NLU), takes a piece of text, typically a sentence, and maps it to an “intent”. An intent is a summary of what that sentence of phrase means. For example, “I need to pay my bill” may be summarized as “pay bill” intent.
A NLU model is explicitly trained by humans who decide what intents should be learned by the model. This is known as supervised learning. Intents are training by showing the model sample utterances, which are sample phrases for an intent. A few examples of utterances are “I need to pay my bill”, “Bill payment”, and “How do I pay my bill”. All of the aforementioned utterances would be trained for the intent “pay bill”.
The model then summarizes these examples into a machine representation that renders meaning to these sentences. This representation is known as vector space.
When a new phrase that is similar in meaning comes along, for example “How much is my invoice, I want to pay it”, the model finds the closest match in vector space and then assigns a probability for how well the input phrase matches the intent. The phrase mentioned may match the “pay bill” intent with a probability of 0.92, meaning it is a 92% match.
If the value is above a set threshold, the chatbot will trigger the action or response associated with the chosen intent. If multiple matches are found, the one with the highest probability is chosen. If the match is below the threshold, then the chatbot may decline to answer. All the responses and actions for each intent are preassigned by human conversation designers.
The combination of RPA and NLP allows an enterprise to expand the variety and complexity of the transactional journeys they expose their customers to through conversational channels.