3 min
Level: Intermediate
Quality monitoring, or assessing the customer service we are providing at any given moment, can be automatedthanks to artificial intelligence for the contact centre.
This technology is capable of analysing millions of pieces of data, classifying them and presenting an assessment in a matter of seconds, which means we can evaluate every single conversation that has taken place with just one query.
The four steps we need to follow to get the best results are:
1. DEFINING GOALS AND METRICS
First, we need to decide which elements of the conversation we want the bot to consider; for example, politeness, problem-solving skills, protocol adherence, etc.
Once we know what we want to measure, we need to establish metrics for each aspect, such as using a 0-10 rating or qualitative analysis.
2. ACQUIRING A BOT
To achieve high quality monitoring, the bot must be able to generate summaries. This means we need generative AI with an NLP (Natural Language Processing) model to process the language and evaluate the content.
Important! If we want to monitor the calls in our contact centre, we also need to ensure that the bot is able to transcribe speech to text, which means it should include an ASR (automatic speech recognition) model.
3. ACQUIRING POWER BI
This tool, developed by Microsoft, allows us to have customised charts with the information that the AI extracts from all conversations, as well as tables that record the analysis and summary of each call.
4. DEVELOPING THE WORKFLOW
Once we’ve got the bot and Power BI in place, we need to create the workflow that the AI will follow to collect, analyse and send the information so that it’s synchronised within Power BI.
For example, if we want the bot to provide an assessment of a call that includes a summary, the agent’s courtesy rating, and the original audio of the call, we need to create the following workflow:
Step 1 – User request
The process begins when we ask: “Which agent and which call?
Step 2 – Call identification
The bot searches the database for the specific call using the information we have provided (agent name, date and time of the call, or any other unique identifier).
Step 3 – Audio transcription
Once it has found the audio file, it will transcribe the file and convert it to text.
Step 4 – Conversation analysis and summary
The bot will analyse the conversation to assess the aspects we defined in the first step.
If one of the aspects is ‘agent courtesy’, the model will look for indicators of courtesy in the conversation, such as the use of polite language, respectful tone, etc.
It will then assign ratings or tags to the specific aspects according to the metrics we have defined (for example, a score from 1 to 10).
To create a summary of the conversation, it will look for key points such as the reason for the call, the solution provided by the agent and any relevant issues.
Step 5 – Generating the full report IN POWER BI
The bot will compile the transcript, summary and scores and send them to Power BI, and the tool will sync the information every hour.
4. CONFIGURING THE APIs
Once the process is defined, there are two things to consider. Firstly, if we are using a third party tool for transcription and analysis, we need to ensure that the API works with the bot.
We also need to configure the API to ensure that the bot and Power BI are integrated and can automate report generation.
FINAL THOUGHTS
After following these steps, our bot will be ready to provide us with scores for every agent and every call in our contact centre.
All we need to do now is test and tune the model, deploy the system and, as always, monitor its performance.
Of course, we’ll also need to ensure internally that staff know how to use the bot, and technically that the AI meets privacy and security regulations to comply with GDPR.
If this process is too complex for your team or you don’t have someone with the skills to set up a bot, don’t hesitate to contact our technical team to help.
WANT TO OPTIMISE YOUR CONTACT CENTRE MONITORING?
Subscribe
Ask for a demo