Bots – Interpreting Customer Intention

At a Glance

Bots – Interpreting Customer Intention
Using built-in Natural Language Processing (NLP)
Bots – Interpreting Customer Intention
Mapping customer words to likely intentions
Bots – Interpreting Customer Intention
Mapping intentions to response actions

About Bots – Interpreting Customer Intention

Softdial Contact Center™ (SCC) provides a complete solution platform for building any kind of text bot – from a simple dialog with direct questions to the customer to a more sophisticated dialog that can interpret complex sentences used by customers – and act on those messages in many different ways.

Well-configured chatbots deliver an excellent customer experience that can save a customer time and can increase efficiency in the contact centre.

In order to provide the best service for customers, bots must understand the customer’s intention to some extent, no matter how it is expressed.

To support bots, SCC’s versatile flow design tool, Softdial Scripter™ provides :

  • a comprehensive toolset for text processing
  • text-based Natural Language Processing (NLP) facilities.

This page is split into two parts:

  1. Using NLP to Understand Customer Intention
  2. Building an Intentions Directory

 

Part 1 – Using NLP to understand customer intention

Figure 1 shows a very simple example using one of the possibilities that Softdial Scripter offers as a tool set to build bots. All these activities are supported by access to the customer’s data and the creation and use of special dictionaries, available within Scripter.

There is no right way or wrong way of developing such chatbot applications, with the process depending upon the nature of the activities covered by the chatbot and how the chatbot owner wants to engage with customers. In practice a number of scenarios might be developed by Scripter, before the one(s) with the best responses is/are chosen.

In this use case, an internal chatbot handles an upgrade of a TV package by employing Scripter’s text-based NLP engine.

 An example of a chatbot dialog flow using Softdial Scripter
Figure 1: Example of a chatbot dialog flow using Softdial Scripter

In this flow example:

  1. a conversation is initiated by either the chatbot, or the customer
  2. the chatbot asks questions of the customer and qualifies their customer’s ID
  3. if successful, the chatbot asks an open question – How can I help?
  4. the customer requests an upgrade.

At this point (i.e. the Answer step), Scripter can use NLP to interpret the customer’s intention.

Inside Natural Language Processing (NLP)

Scripter’s NLP engine splits the customer message into sentences and words, classifying the words as follows:

An example of an interpreted dialog flow using the Softdial Scripter Natural Language Processing Library
An example of an interpreted dialog flow using NLP

As a result of this process, we have a list of terms to cross reference with a knowledge base to determine which action should be taken e.g. upgrade the TV package.

In this case the customer wrote “I would like to upgrade my TV package”. Analysis of this sentence returns a group of terms – like, upgrade, TV package – as the likely interpretation of the intention of this customer. This can be used to search a multi-term dictionary available from the Scripter text processing library, to determine if there is a matching action.

Let’s say in our dictionary of actions we have the following relationship:
An example of an action definition using a multi-term dictionary search available from Scripter Text Processing Library
An example of an action definition using a multi-term dictionary search

Having interpreted the customer’s intention, the matching action is to present a choice of upgrade packages and ask which one is wanted.

The script flow will keep this loop until the final action, which might be to send a message to the relevant ERP to proceed with the chosen package upgrade.

Part 2 – Building an intentions directory

In order for a chatbot to generate a reasonable response to a customer query, an intentions dictionary is required to map the relationship between relevant terms and then define possible intentions to the chatbot.

In order to build this dictionary, the supervisor will utilise Scripter Designer to define the most relevant responses to any inbound text message.

In Figure 2 we can see how the Intentions Analyser is used to interpret intentions from words customers use.

Verbs such as ‘like’ or ‘want’ are identified and grouped as ‘Positive Intention’.

Nouns such as ‘TV’ or ‘package’ identify the items that the text is concerned with.

Building Intentions from groups of Intention Words

Figure 2: Building Intentions from groups of Intention Words

Having identified individual words in a phrase and flagged those individual words as having an intent, all of the words can be combined to identify the overall intent of the phrase.

Let’s say the NLP identifies words that are contained within the ‘PositiveIntentions’, ‘TVPackage’ and ‘Upgrade’ intents. The combination of these three groupings allows the NLP system to identify an overall intent to the phrase, in this case that the customer wishes to upgrade their TV package (as demonstrated in Figure 3).

List of intentions mapped to responses

Figure 3: List of intentions mapped to responses

List of intentions mapped to responses

There may be many combinations of intentions, each one having a different meaning and requiring a different response. To accommodate this, it is possible to build a library of intentions and to assign to each intention a response which can be sent back to the customer.

Additionally, SCC’s Scripter engine can be triggered to perform other tasks besides simply responding with text, for example:

  • transferring the session to a live agent with the skills needed to handle the session
  • performing a lookup against a database to get an account balance and returning the result to the customer.

 

What We Offer

Sytel Limited develops and supplies Softdial Contact Center® (SCC), offering multimedia, multichannel, fully blended cloud contact center solutions, for quick and easy deployment by partners offering CCaaS or enterprise users. All Sytel cloud components are secure, resilient and scale seamlessly from 10 agents to 10,000+, whether local, mobile or remote.

Flexible Contact Center Platform

Flexible Contact Center Platform

Softdial Contact Center™ - tightly integrated modules, designed to deliver at scale

Contact Center as a Service (CCaaS)

Contact Center as a Service (CCaaS)

Partners can run a functionally rich and flexible contact center stack in the cloud

Blended Media Desktop

Blended Media Desktop

Fully customisable, multi-channel, multi-session workspace

Work Anywhere

Work Anywhere

Browser-based tools, no software installation required

Cloud Or On-Premise, Multi-Tenant

Cloud Or On-Premise, Multi-Tenant

Scalable, resilient, secure, proven

Customise, Localise, White Label

Customise, Localise, White Label

Design all user interfaces to individual requirements

Integration Via APIs

Integration Via APIs

'Swap out' components and integrate with 3rd party apps

World Class Development

World Class Development

Continuous evolution pushing technical boundaries

Capabilities

Softdial Contact Center™ (SCC) is designed to be flexible, extensible and scalable, integrating with any legacy equipment, and meeting the most complex of requirements.

All Media Types

All Media Types

Voice, chat, email, social, etc - fully integrated and blended

Agent Multi-Tasking

Agent Multi-Tasking

Work with multiple live contact sessions of any media type

Dynamic Workforce Management

Dynamic Workforce Management

Automated, ‘best available’ decisions to manage agents and balance work load, across all media types

Predictive Dialing

Predictive Dialing

Best-of-breed performance under compliance

Optimised Inbound Routing

Optimised Inbound Routing

Smart rules and 'best-available' decisions to drive great customer service

Agent Scripts

Agent Scripts

Help agents achieve and maintain excellence

Voice and Screen Recording

Voice and Screen Recording

See and hear exactly how agents are interacting

Analytics and Data Feeds

Analytics and Data Feeds

Measure and evaluate performance at every level

IVR, Bots & Conversational AI

IVR, Bots & Conversational AI

Design effective automated flows or integrate with 3rd party providers

Customer Journey Tracking

Customer Journey Tracking

Stored customer contact history, to aid routing and add context to conversations

Modules

A complete suite of tools, with unique flexibility to extend and swap out modules to deliver a tailored contact center solution for any environment.

Softdial One™

Softdial One™

Highly flexible unified web UI for agents, supervisors and administrators

Softdial Scripter™

Softdial Scripter™

Create complex process flow scripts for agents, IVR, chatbots and other applications

Sytel AI Dialer™

Sytel AI Dialer™

Best-of-breed predictive dialing under any compliance rules

Softdial Pathfinder™

Softdial Pathfinder™

Precise routing rules for 'best available' connection

Softdial Media Server™

Softdial Media Server™

Core telephony functions to manage all inbound/ outbound SIP calls

Softdial Reporter™ 5

Softdial Reporter™ 5

Fully customisable performance stats, charts and reports, across all channels

Softdial Publisher™

Softdial Publisher™

Comprehensive data output to build your own reports

Softdial Recording Monitor™

Softdial Recording Monitor™

Audio and screen recording of agent activity to ensure the highest standards

Softdial Campaign Manager™

Softdial Campaign Manager™

Comprehensive configuration and control for outbound campaigns

Softdial Repository™

Softdial Repository™

Central storage and configuration of common resources

Sytel Global Compliance™

Sytel Global Compliance™

Flexible 'no contact' rules to protect contact center and consumer

Markets

Performance and efficiency for a wide range of business applications

Customer Service

Customer Service

Connect quickly to well equipped agents

Sales & Telemarketing

Sales & Telemarketing

Maximise agent productivity with best-of-breed predictive dialing

Healthcare

Healthcare

Secure, highly-configurable multichannel communications for excellence in patient care

Market Research

Market Research

Best-of-breed predictive dialing with CATI integration

Collections

Collections

Automated inbound/ outbound blending integrated with any debt management app