The Visual Data Exploration Concept Explained

Today most businesses are awakening to the age of data overload. Cloud processing facilitates more sources of information and more delivery platforms, while social media, IoT (Internet of Things) devices and smart phones bring challenges of their own.

Applying the rapid recent advances in AI is one way to help tame this tsunami. In a future post, we will see how Zegami’s use of Machine Learning does precisely this in augmenting, categorising and otherwise bringing structure where there is none. However, at Zegami, we also accept that AI alone is not equipped to make critical decisions on our behalf. Human judgement will always be needed.

Rather than attempting to replace human intelligence, Zegami recognises that there are key activities which will always require human input. Zegami instead puts human cognitive faculties at the centre of the process, making it more efficient by providing it with information in a format more amenable to rapid scrutiny and analysis.

Traditionally, exploration and discovery of data have been facilitated by search. Until now, the way we search for items of data has revolved around one user experience: a single text box where a word or a phrase can be typed. Results are displayed to the user in the same rudimentary format, i.e. 10 to 50 links in a series of pages. There has been limited innovation on the way we consume search for the last 20 years and even companies like google have little incentive to change the overall search experience.

Zegami is consciously very different

A new approach, originally pioneered by Microsoft back in 2009, makes big data immediately comprehensible to the human eye, through a dynamic interactive visualisation. Unfortunately, it was ahead of its time. Today Zegami has taken the concept of Microsoft Pivot and the HTML5 Pivot viewer and turned it into a next generation search and data exploration platform.

Zegami provides a fundamentally different approach. By presenting the entire collection of information within a single field of view, it allows the full scope of the of the data to be taken in at once. Paged interfaces become a thing of the past, as users can now instantly see the overall scope at once. The innate ability of our subconscious mind can then be applied to the big picture, identifying patterns and apprehending the shape of the data as a whole.

Zegami provides a fundamentally different approach. By presenting the entire collection of information within a single field of view, it allows the full scope of the of the data to be taken in at once. Paged interfaces become a thing of the past, as users can now instantly see the overall scope at once. The innate ability of our subconscious mind can then be applied to the big picture, identifying patterns and apprehending the shape of the data as a whole.

Making all data visual

For inherently visual data, such as that based around media assets and their metadata, it’s easy to see how this is an extremely powerful tool. One can begin by view tens of thousands of images at once. With a few clicks, they are instantly filtered and rearranged based on inferences made by our Machine Learning algorithms. Potentially salient specimens begin to stand out. Users can then zoom right in to examine the full resolution asset without interruption, before pulling back out again for another look at the bigger picture.

But Zegami isn’t only for images. In Zegami, any dataset can be displayed as a visual summary, through Zegami’s Zeg engine. Zegs are visual representations of the most relevant facts for an item of data. Zegs can be thought of as miniature dashboards geared towards allowing maximum information to be absorbed at a glance; through images, colour coding, charts, and the prominent display of key numbers and labels. In this way, all data can be searched and explored visually.

Visual Data Exploration search is a new approach to dealing with the task of finding and analysing the information in large datasets. One of the keys to the success of the Zegami platform is its unique ability to engage both machine learning and human intuition, to empower people to make smarter and faster decisions. This is why, in the age of information overload, smart businesses are awakening to Zegami.

Zegami is an Oxford University spinout company founded on the 1st February 2016 by Samuel Conway CEO, Roger Noble CTO and Stephen Taylor (Chief computational Biologist, Weatherall Institute of Molecular Medicine, Oxford). As a company we are focussed building the next generation search platform utilising the concept of Visual Data Exploration and Augmented Intelligence.