• Home
  • Product
    • Smart Meeting Rooms
    • Easy Meeting Scheduling
    • Open AI Superpower for Sales Teams
  • Case Studies
  • Pricing
  • Blogs
  • Signup/Signin
  • Home
  • Product
    • Smart Meeting Rooms
    • Easy Meeting Scheduling
    • Open AI Superpower for Sales Teams
  • Case Studies
  • Pricing
  • Blogs
  • Signup/Signin
  • Home
  • Product
    • Smart Meeting Rooms
    • Easy Meeting Scheduling
    • Open AI Superpower for Sales Teams
  • Case Studies
  • Pricing
  • Blogs
  • Signup/Signin
Conversational Intelligence

The Approach to Conversational AI for Early-Stage Teams

Rida
December 6, 2022

Transforming Sales Enablement with Conversational AI

Conversational AI and Sales Enablement as a problem statement is what we are tackling at Zipteams. Getting started in the sphere of conversational intelligence poses some crucial roadblocks. The primary one, in our experience, was the sheer variety of data that flows into our systems.

Initially, we approached every use case from a perfectionist’s point of view. We started applying state-of-the-art algorithms and models to the entire bulk of calls taking place in our digital meeting rooms. We imagined that this would ensure that we let nothing slip through the cracks.

This posed 3 major issues:

1. Risk of a very high spend when using some off-the-shelf models for various downstream inference tasks

2. Handling noise and edge cases was difficult in situations where we had to build models from scratch because a significantly larger training dataset (with negative sampling) was required

3. Long Inference time in certain use cases

We realized that most of the insights or information worth indexing came from a tiny subset of a conversation when compared to the entire duration of the call. Therefore, we adopted a different processing style to combat the issues we faced above.

1. We built a lightweight monitoring engine that focuses on quickly (read: VERY quickly) identifying “interesting” moments from a call in real-time. We do this with a combination of age-old techniques (E.g. Regex, NER, tokenization, POS tagging, etc.) as well as some low-latency inference models deployed at the nodes through which the call session is being managed i.e. the audio-video bridges.

2. Once an “interesting” moment is captured, we asynchronously push it to our secondary inference layer that hosts some larger use-case-specific high-latency models, which weed out the false positives.

This approach has now put us in a position to tackle some complex use cases in real-time and have the analysis ready without any post-processing requirements.

Although this AI engineering paradigm has existed for a while, we’re seeing the vast potential for its use in the conversational AI space, especially in some high-cost processing stages, such as speech-to-text engines.


Rida

Product & Community Manager, Zipteams

Leave A Reply Cancel reply

Your email address will not be published. Required fields are marked *

*

*

Keyword Tagging for Sales Team Enhancement
Previous Article
How Conversational Intelligence Can Boost Your Sales
Next Article

logo (2)
© Copyright 2023
Twitter Linkedin Instagram Youtube Medium
Terms of Use
Privacy Policy

Company

Contact Us
Pricing
Cancellation & Refunds
Beta Program

Product

Smart Meeting Rooms
Easy Meeting Scheduling
Open AI Superpower for Sales Teams
Integrations

Resources

Case Studies
Blogs