Join us in person for the Deep Learning in Business Forum on October 6th at MIT

Register

Spotting trends in customer calls

Context

I work at a massive internet service provider that receives thousands of customer calls every day.

 

How can I take a bird's-eye view of all these conversations today, so that we can better plan for our customers' issues tomorrow?

  1. 01. Ingest

    I used an external application to convert our audio logs into text-based transcripts. Now, I'll upload this unlabeled data to Pienso Ingest.

  2. 02. Fingerprinting

    We already have an ontology for the most common customer support topics, but I'd like to reevaluate and expand it. So I'll create a Pienso Fingerprint model, which can detect themes that we haven't put a name to yet.

  3. 03. Deploy

    Next, I'll use Pienso Deploy to create a deployment that pits my Fingerprint model against a live stream of incoming call transcripts. Now, each new document that hits my deployment will receive a series of "soft" labels in the form of a fingerprint score.

  4. 04. Dashboard

    Finally, my operations team will use the Pienso Dashboard associated with my deployment to watch as these new documents get scored in real-time, monitoring for emerging trends and hunting for insights.

  5. 05. Outcomes

    Are customers experiencing an issue in a particular region? at a particular time of day? or around a specific event? Our analysts can now answer these questions as they arise, and then pass on their findings to our customer satisfaction and product development teams to inform future strategy.

01

Ingest

01 Ingest

Pienso Ingest lets you prepare your raw text for use as training data, whether it's structured or unstructured.

View

View

02

Explore

02 Explore

Pienso Explore lets you search a data set for documents that match your interest.

View

View

03

Annotate

03 Annotate

Pienso Annotate empowers you to convert your data sets from unstructured to structured — without manually labeling a single document.

View

View

04

Fingerprinting

04 Fingerprinting

Pienso Fingerprinting is an interactive semi-supervised approach to training generative models.

View

View

05

Deep Learning

05 Deep Learning

Pienso Deep Learning uses labeled training data to create a powerfully accurate topic model.

View

View

06

Analysis

06 Analysis

Pienso Analysis lets you use a finalized Fingerprint or Deep Learning model to investigate a data set through an array of granular views.

View

View

07

Dashboard

07 Dashboard

Pienso Dashboard lets you monitor the results of your Fingerprint or Deep Learning models in real-time as they score new documents as part of your Pienso API Deployment.

View

View

08

Deploy

08 Deploy

Pienso Deploy is a UI-driven API deployment manager. Use it to put your models on an API production slot that you can send your live data to for scoring.

View

View