I am working on a task where I am required to automate the customer service request channel. The process is quite typical. A customer queries about a product via email, the person on the front channel checks emails, forwards it to the relevant department and then answer is provided.

The problem is that customer query can be about one of hundreds of devices listed. Each device has its own pdf documentation which is quite extensive. Finding the right pdf and then finding the right section where information could be listed is really a tedious process and wastes a lot of time. Sometimes the information is not even listed and answer has to be improvised by product specialist (the last part hints me about reinforcement learning, what do you guys think).

What I want to achieve is that this whole tedious and repetitive process is automated and may be if possible, the model learns over time as well. The task output is quite open ended as well. Different approaches and models can be tried out (like chatbots and etc). Rapid failure is highly appreciated here.

Below mentioned are some more details:


  • I have customers queries about devices in the form of emails.
  • PDF documentation of devices. The documentations are quite extensive.
  • I also happen to have some excel files where some sample queries and sample answers are listed. But since queries can be of very dynamic nature, it doesn't seem like a classification problem (to me at least).

I have googled quite a lot about the topic but mostly what I get are topics like 'How AI will transform the customer service' and then something more specific to NLP and a lot of company ads etc. So far what I have understood from online surfing is that possible approaches need to use NLP library (Nltk) in Python and do some topic modelling for documentation and for email. Still how I approach the whole task is not clear to me.

What I want from you guys is that maybe guide me how this task can be achieved step by step. I am not looking for any code! Just which methods can be used and how the problem can be approached. Right now, I don't know where to start and how to approach it.


At first, the problem has to be described from a business perspective. A lowcost customer service is a website without any kind of interaction. That means, the customer can download pdf documents and that is all the service he gets. A highcost customer service is based on a dialogue with the customer which can be done via e-mail, chat or voice. Here, the customer can interact with the company, asks complex questions and get detailed answers. What most companies are interested in, is to mix both types. That means, they want to provide an interactive service to the customer because this is what premium customers are asking for, but at the same time the company is trying to minimize their costs. So the idea is to automate the workflow and this is probably the motivation for the OP.

So what is available from a technology point of view which can be used in reality and contains some Artificial Intelligence magic? What most companies are using today is an e-mail client for example Outlook. In the e-mail client, some rules can be defined for sorting incoming e-mails automatically, but the improvement over “no sorting rules” is low. Other companies have discovered, that customer interaction can be outsourced to countries with a low salary. This works surprisingly efficient for the company but has nothing to do with AI, it is more a business decision.

It is correct, that in the area of natural language processing and workflow automation some research effort is going on. The problem is, that natural language understanding is much more difficult than other AI domains for example image recognition or game playing. The most advanced projects so far are IBM Watson and Cyc, both are not very well documented. In newer literature, there are examples given with neural networks which were trained by a dialogue corpus. After the training, the chatbot can answer requests by it's own. The research project is called “dialog system technology challenges (DSTC)”.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.