Chatbots in the contact centre

Share this content

The introduction of chatbots has the potential to revolutionise both the contact centre and the customer experience market. It has potential rather than certainty – as success depends upon the right selection of chatbot for your organisation. Done well, a chatbot can both ease pressure on the contact centre – research indicates a saving of 2.5 billion customer service hours by 2023 – and enhance that all important customer experience, by giving customers quicker access to information and resources.

From a finance perspective, the role of chatbots also holds significant merit.  A recent report from Analyst house Juniper Research found that the adoption of this technology within the retail, banking and healthcare sectors could see businesses realise cost savings of $11 billion annually by 2023. 

With this in mind, it’s worthwhile doing the process well. So, how do you implement the ‘right’ chatbot for your brand?

Start by establishing your organisation’s needs

First things first. Before you delve into the world of chatbots, it’s important to define your goals so that your search is focused on the features your organisation needs, and less influenced by the features that vendors are promoting. Customer service is one such use case and often the most preferred use for chatbots.

Next you need to work with your teams to plan how a chatbot will fit into your contact centre. Which systems does your chatbot need to integrate with? Which categories of queries do you want the chatbot to handle? What should happen when customers don’t want to use the chatbot? And how can customers exit the chatbot process – or transfer to a human agent?

Consider how you want the chatbot to interact

Natural language processing is the technology that voice assistants like Alexa and Siri use to understand what we’re asking, and turn those words into actions. In a chatbot, NLP allows users to type any sequence of words into the chat window. The chatbot can understand the user’s meaning and their intent (i.e. are they asking a question or making a statement).

Chatbots without NLP usually resort to giving users canned responses to choose from. Instead of typing a question, the chatbot asks users to click a button that best represents their query. A chatbot without NLP is likely to be less capable of dealing with a wide array of customer queries, unless you use a complex menu system to gradually refine the customer’s needs.

If you are building a custom chatbot you may also need to consider which data to load into your solution. The dialogue dataset is essentially a database of conversations that form the basis of the chatbot’s ‘brain’. Datasets include lists of questions and answers, customer support conversations, chatroom discussions, and even dialogue from films.

In addition, considerations should be given to the dialogue flow design – how the customer will communicate with the chatbot and how that conversation is programmed to be structured. Also, how will your chatbot handle exceptions – so when the customer does something unusual or when the chatbot doesn’t understand.

Enhancing the chatbot

Chatbots will only learn if you teach them. Your chatbot can only provide the information it has been given, in ways it has been taught. So, if a chatbot is giving customers their bank balance, it is only because it has been programmed to do so, and connected to the data sources it needs.

This sounds obvious, but it is important if you want to develop a chatbot that ‘learns’ from interactions – and doesn’t rely solely on manual input to develop its knowledge and skills.

If you want to create a smarter chatbot that gradually learns from interactions, you must create feedback loops (or other processes) so that evidence from experiences is fed back into the chatbot’s code. For example, chatbots can recognise popular customer choices, and then learn to prioritise those most popular selections.

The ‘right’ chatbot

Rather like any enterprise software, you can choose chatbots that include an immense range of functionality, and can be adapted to suit your changing needs, or you can choose a simpler package that is easier to deploy, but limits what you can achieve. Ultimately, you need to consider which chatbot platform provides the greatest value, while offering the simplest integration for the most manageable cost.  Whichever path you choose, make sure the fit is right for your organisation, reflects your brand values, and ultimately fulfils your objectives. 

 

About ValurSvansson

Replies

Please login or register to join the discussion.

There are currently no replies, be the first to post a reply.