Scylla logo
Book a demo
Video analytics trends Part 1:
Combining structured and unstructured data

Video analytics trends Part 1: Combining structured and unstructured data

Posted by Graeme Woods

Graeme Woods

Global Business Analyst

Part of my work as a Scylla analyst is to identify and extrapolate trends in business and AI.

One trend I have noticed is the extension of analytics from numeric data to unstructured data such as freeform text and especially video.

Structured data is data that conforms to a data model, follows a consistent format and can be easily accessed. Unstructured data does not have a predefined data model. Studies have shown that unstructured data comprises up to 80% of an organisation’s data.

Traditionally data warehouses use structured data from accounting and production functions. However, the 80% of all organisational data that is unstructured is unavailable for analysis. For example, video data may be siloed away in the security department.

By unlocking meaning in this unstructured data, organisations can potentially extend the amount and types of data available to support decisions. Useful information can be sourced from across the entire organisation, not just from ERP solutions, giving a broader perspective.

The real value from introducing this unstructured data is not from simply storing data, or even detecting events in video, but from being able to extract useful insights. This is an AI problem, and I anticipate AI will be used to automatically extract the insights by combining unstructured and structured data.

Proprietary AI reporting tools will analyse real time unstructured data (such as video), draw on other available structured data (such as real time sales statistics) and history to identify causal relationships and provide insights to help guide operational decisions.

Structured vs unstructured data

For example, an AI may analyse the number of people entering a store and how they move through the store to identify whether a promotional campaign is delivering results, or whether it needs to be refined. At the same time, it may be identifying potential shoplifting behaviour and recommending rostering changes to cut down queuing times and identifying how much the reduced queues increase sales revenue.

This use case illustrates the potential benefits of combining different sources of data and touches on AI assisted reporting. I’ll write more about this next time.

More Video Analytics Trends:

Part 1: Combining Structured and Unstructured Data

Part 2: AI Assisted Reporting

Part 3: Composite Detections

Part 4: Cloud and Edge Processing

Stay up to date with all of new stories

Scylla Technologies Inc needs the contact information you provide to us to contact you about our products and services. You may unsubscribe from these communications at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, please review our Privacy Policy.

Related materials

Scylla is AICPA certified
Scylla is ISO certified

Copyright© 2022 - SCYLLA TECHNOLOGIES INC. | All rights reserved