Table of Contents
Artificially intelligent agents (or AI agents) need to understand what customers actually want in order to provide excellent customer service. Our human understanding of the broad variance in natural language is easy to take for granted. But, for AI agents, extracting the meaning (or, in this case, customer intent) from sentences is a complex process still being explored by the world’s best dialogue teams.
Most of the chatbots you’ve seen on the market have been built on decision-tree-style conversational flows, where the chatbot developer has already pre-scripted the conversation. Think about the number of different paths non-linear conversations can take; how can developers possibly account for them all? These chatbots don’t truly understand the semantics of the user’s query or the consumer intent behind them. Their understanding is nothing more than deciding which step to move forward with down the previously scripted set of paths.
In this post, we’ll take a high-level look at how AI agents process queries and derive the customer intent behind the conversations.
What is customer intent?
Customer intent is the purpose or goal a customer sets out to achieve when interacting with a brand. Essentially, it’s the “why” behind a conversation, or what a customer is trying to accomplish.
For an AI agent to be truly effective, it’s really important to understand that intent. That’s because, with the right context, AI agents can offer more relevant responses, anticipate customer needs, offer proactive solutions, and even streamline the conversation to reduce friction in the customer journey.
Similar to search queries, there are three broad categories of customer intent:
- Informational, where the customer is looking for answers or trying to learn something specific
- Transactional, where they want to complete an action, like making a purchase or modifying a reservation
- Navigational, where they’re trying to find a particular product, page, or website
Typically, AI agents rely on natural language processing (NLP) and machine learning to analyze the potential customer’s input and understand the intent behind the query in real-time, also known as intent classification.
Understanding what customers want
Have a listen to this demo of a customer speaking to an AI agent we made for a travel booking use case.
Rather than saying, “I want to speak to your bookings department,” this caller jumps straight into sharing the reference number. Good AI agents need to be able to understand what customers are saying, regardless of the wording they use to express themselves.
We use a process called user intent detection,which is when AI agents process speech and match queries to certain customer or buyer intents. We’ve trained our model on billions of general conversations, so it has a strong baseline for understanding the intent behind a vast number of sentences. We fine-tune the model with small amounts of domain-specific data to suit each AI agent and the intents it attends to.
Our solutions are designed to understand the intent of your target audience better, handle customer interactions seamlessly, and ultimately improve the overall customer experience.
Getting the right information based on customer intent
Once the AI agent has identified the intent behind a query, it may need to extract certain information, like the customer’s expectations or pain points, that will allow it to complete the task, i.e., solve the issue at hand. The AI agent will have a predefined set of information to obtain and will need to guide the flow of conversation to ensure it gets everything it needs. Here’s an example of conversational AI in hospitality where an AI agent is trying to capture customer’s information to point them in the right direction:
Value extraction is the process by which AI agents extract the relevant information from customer queries and store them against the relevant “slots.” While it sounds straightforward, it’s really difficult to get AI agents to understand which information goes in which slot.
For example, you might say, “I want to book a table for 2 at 4.” For an AI agent to understand that one number is a time and the other is the number of people, it must have been trained on customer intent data that demonstrates that “for 2” means for 2 people, and “at 4,” means at 4 o’clock, and that if the restaurant is open from 12 pm to 12 am, then “4” is probably 4 pm.
This is a problem we’ve been able to solve through our restaurant booking platform, according to real customer feedback. If you want to learn more about why it’s so difficult for AI agents to extract values, check out our blog post on the neural language understanding of people’s names.
At PolyAI, we build high-quality AI agents with great memory as default. This means they can take down information as it’s given rather than asking end users to repeat themselves when the machine decides it’s time to record something.
What if the machine isn’t sure?
Where a human agent will naturally be aware of how comfortable they feel understanding a query, an AI agent needs to calculate its confidence based on the customer’s behavior at every step of the way.
Typically, the AI agent will have a confidence threshold for each intent that decides whether to move forward with the query, ask for further clarification, or hand off to a human agent, usually in line with call deflection protocols.
Some intent signals are less weighty than others, so we might program the AI agent to move forward past relatively low confidence thresholds. For example, if someone is asking to reserve a high chair in a restaurant that we know has an abundance of high chairs, we may allow the AI agent to move forward at a lower confidence threshold than we would for someone giving more sensitive information like card details.
Based on the confidence levels, the AI agent has to be smart enough to understand when to proceed with the conversation and when to hand it off to a human agent. In other words, the AI agent must be able to understand that it won’t be able to understand, which is a complex problem in its own right!
How PolyAI brings it all together
At PolyAI, we build AI agents on top of our Encoder model. The model is trained on hundreds of millions of conversations, and the model can understand a wide variety of conversational contexts, and is able to handle any number of typos and figures of speech, in a large number of languages.
We use our model and clients’ knowledge bases to develop intent classifiers that are able to extract niche, domain-specific intents from complicated queries. We then employ the slot-filling process to collect the data required to resolve the query. Confidence measurement means our clients can constantly monitor the accuracy of their AI agents, and make educated decisions about when conversations should be handed off to human agents.
Intent alone is not enough
Understanding what the other person is saying is only one half of the conversation. Thanks to conversational AI technology, our AI agents can craft responses, trigger actions to solve customer queries, and even make customer service automation possible.
Customer intent FAQs
AI agents analyze customer behavior, context, and language patterns to interpret actions and provide relevant responses or suggestions.
Yes, using AI for ecommerce customer service can improve the experience as it can understand purchase intent, streamline interactions, and offer faster, more personalized support.
