top of page
  • Writer's pictureSharon Holland

What is Natural Language Understanding (NLU) and how can it help customer service?

Updated: Sep 30, 2023

Natural Language Understanding (NLU)  customer service?

Artificial Intelligence (AI) is increasingly becoming part of business operations, especially within the contact centre, where it is used to power chatbots, intelligent virtual assistants or automate existing processes to increase efficiency.

The field of AI encompasses a wide range of techniques and technologies, but this blog will look at how Natural Language Processing (NLP) and Natural Language Understanding (NLU) deliver benefits within customer service.

What is Natural Language Processing?

Natural Language Processing is a subfield of AI which is concerned with how computers process human language, covering areas such as:

  • Intent (why is the customer contacting the business?)

  • Theme detection (what is the conversation specifically about?)

  • Sentiment analysis (how is the speaker/writer feeling – positive, negative, neutral?)

  • Emotion detection (are they happy/angry?)

A set of rules and grammars is developed by linguistic experts that identifies and understands phrases and relationships among words.

AI, NLP and ML

Many are familiar with the AI technology of Machine Learning (ML), which some consider part of NLP, whilst others think the opposite. Both NLP and Machine Learning are fields of computer science that aim to deal with human language to extract insights from voice and text conversations.

Rather than following rules set by linguists in ML the machine learns patterns without being explicitly programmed. The experience that is gathered during the training phase is used by the machine learning algorithm to create the rules it needs to work to. This results in a more scalable system that does not need to rely on domain expertise.

NLP in action

To see NLP in action, let’s use this example:

“The staff in the branch were very helpful but the savings interest rate is too low, so I will go somewhere else.”

This is sentence is complex as it has both positive and negative comments, along with a termination risk.

If you use a tool that is based on words or a simplistic sentence-level scoring approach, it is likely that when it comes to a root-cause analysis, your tool will give the cause of termination as “staff experience and interest rates”. That’s why accuracy is so important. You need tool that offers a high level of precision and the ability to analyse each unique aspect of the sentence.

NLP enables you to go beyond the positive/negative comments. NLP means you can understand what the positive is helpful staff and that the negative is that interest rates are too low. These insights allow you to take meaningful action.

Natural Language in customer service

Natural Language Understanding provides a number of benefits to contact centres:

1. The Voice of The Customer

Many organisations collect feedback from their customers, either at regular intervals through scheduled surveys or after a interaction has been completed. However, these rarely provide the full picture of customer satisfaction levels. People that tend to fill in questionnaires are normally either very happy or very upset with the service they have received, which can often skew the results, and overall response rates are often very low.

By using NLU to analyse all the interactions that take place between the customer and the organisation you get a more complete view. Messages on digital channels (email, social media, webchat) and telephone (through voice to text transcription), can be analysed for deeper insight. This identifies improvements that can be made to the customer experience to increase satisfaction, reduce churn and enhance efficiency.

2. The Voice of The Agent

Companies want to deliver a consistent, high quality user experience for every single interaction. In practice, this usually involves managers manually checking interactions, either by listening to call recordings or reading digital conversations. This enables them to identify agent strengths and weaknesses, any script deviation, and areas for agent training/coaching.

However, this is very time-consuming – meaning supervisors can only evaluate a very small percentage of interactions, meaning most opportunities for improvement are missed which impacts the wider customer experience.

NLP can transform this process, by analysing 100% of interactions and assess them quickly, objectively and consistently, and flag any deemed high risk for a supervisor to follow up.

3. Automatic Customer Interaction Routing

Customers want their call to be dealt with first time by the most relevant agent. This also applies to digital transactions, which should automatically go to the best available agent.

NLP works across both digital and phone to ensure that interactions are routed to the right agent, first time. Instead of using a traditional IVR, customers can simply say what they are calling about, their message will be analysed, and they will be transferred to the right person. For digital interactions emails, chats or social media messages and scanned and sent to the most appropriate advisor. The enquiry can also be accompanied by a template that forms the basis of the answer. Customer service frustrations are reduced as they get to speak to the right person, first time.

4. Automated Call Categorisation

At the end of an interaction advisors categorise it by subject, which enables companies to measure which topics are driving the greatest volume of interactions. This information can be used to identify what changes or improvements are needed. However, manual categorisation requires human input which can result in discrepancies such as when advisors report the subject of an interaction differently, or where interactions might cover multiple topics.

Using NLU to automatically categorise interactions has a number of benefits. It offers greater consistency, deeper insights into what customers are enquiring about and improved efficiency by removing administration. As NLG technologies improve basic categorisation could evolve into summarising the entire call and adding it to the customer’s record. Moreover, this would give a more detailed picture of their wants and needs.

NLP offers customer service many benefits across the interaction lifecycle. From routing the call, understanding the conversation from the agent and customer point of view, to categorising and analysing on completion. All of this helps to improve customer satisfaction, increase efficiency, and deliver a competitive advantage across the contact centre.

If you want to find out how you can use NLP and NLP as part of customer service automation to improve your users’ experience contact us or call us on 0333 6000 360.

Source information provided by Enghouse Interactive:

11 views0 comments

Recent Posts

See All
bottom of page