A Closer Look at the Artificial Intelligence Behind Haiku Deck Zuru
You may have heard that Haiku Deck Zuru is the world’s first presentation creation tool powered by artificial intelligence. It is so unique and powerful that we have submitted a patent for the transformation of structured content into a presentation.
Haiku Deck Zuru from Haiku Deck on Vimeo.
So…what exactly does that mean?
Here’s a step-by-step walk-through of Zuru with our co-founder and CTO Kevin, who shows that artificial intelligence isn’t just a buzzword. In fact, Haiku Deck Zuru uses a number of different kinds of artificial intelligence (as well as massive amounts of proprietary data) in thoughtful ways to transform presentations from boring to brilliant.
Step 1: Parsing and Data Structuring
Types of artificial intelligence used: natural language processing
The presentation transformation process begins with an uploaded PowerPoint or Keynote file, or with an outline created in Evernote. (Our goal is to be able to input more file types soon.)
First, Haiku Deck Zuru’s parsing engine extracts the text, converting it from a binary file into structured data that can be analyzed (and, ultimately, transformed).
Zuru looks for and extracts any custom images, analyzing where the images are placed on each slide and assessing importance by calculating how much of the slide area each image takes up. If an important custom image is identified, Zuru centers and aligns it to make it fit well with the visual style of Haiku Deck.
At this stage, Zuru also uses natural language processing to strip words down to their most meaningful roots, remove duplicates, standardize text, and identify meaningful compound words (for example, “Space Needle” instead of “space” and “needle”). This processing stage is critical for identifying appropriate images later on.
Next, Zuru looks at how the text is laid out, noting patterns such as list items, titles and subtitles, headers and sub headers, and so on. It analyzes the size and placement of text to intelligently identify footer text, and to zero in on which text is important and which is not.
Zuru also analyzes the text to evaluate at a high level how well it follows presentation best practices, and to identify presentations that will require more manual intervention. For example, are there too many bullets, or too many words in general?
Step 2: Keyword Analysis
Types of artificial intelligence used: machine learning
This is where the artificial intelligence behind Zuru gets really interesting, as Zuru uses the (anonymous) data it has gathered from the millions of presentations created by Haiku Deck users to suggest a beautiful, relevant image for each slide.
Using this giant data set (which had to be crunched for 36 hours using a linear regression model), Zuru looks at how frequently each possible keyword on a slide appears in presentations, vs. how frequently it has been used as an image search term and actually selected as an image result.
- “Love” appears very frequently in presentations, but it’s not frequently used as the image search term. So when Zuru sees “love” on a slide, it is less likely to select that word for the image search.
- “Dog” appears frequently, and is frequently chosen. So when Zuru sees “dog” on a slide, it is more likely to select that word for the image search.
- “Space Needle” does not appear frequently, but is frequently chosen. So when Zuru sees “Space Needle” on a slide, it is very likely to select that phrase for the image search (and, if you remember from step 1, it’s smart enough to look for the iconic structure instead of pictures of stars or sewing).
Zuru also takes into consideration where a given keyword appears in the slide (for example, a word appearing in the header is likely more important than a word appearing in the 5th bullet), how frequently it appears on the slide, and how frequently a given word has appeared in other slides. All these calculations help determine the best term or terms to use for an image search.
Step 3: Image Selection
Next, Zuru does an image search for the most highly ranked keywords, returning hundreds of extremely high-quality, Creative Commons licensed images in a matter of milliseconds. Kevin has carefully designed this step to be able to handle massive amounts of image searches very quickly, in parallel, so that it feels instantaneous to the user.
Because of all the natural language process and normalization we’ve done already (see step 1), as well as our robust proprietary data set (see step 2), more than 90% of image search terms appear in our list of the 70,000 most popular image search terms, which allows Zuru to suggest standout images incredibly quickly and accurately.
The Data Behind Haiku Deck Zuru – Created with Haiku Deck, presentation software that inspires
Images that have been hand-curated by our team, or that have been selected frequently by Haiku Deck users, rise to the top — and, of course, Zuru will continue to get smarter with every new presentation created.
Step 4: Image Optimization
Types of artificial intelligence used: computer vision, K-means clustering
Once Zuru has identified the perfect image for a slide background, it converts the image into a Lab color space, a format closely mapped to the way that humans perceive light. Zuru uses a process called K-means clustering to analyze the color palette, removing the grayscales and zeroing in on the colors that appear most frequently in the image. Zuru pulls out the most prominent colors in the image and performs brightness analysis on them, comparing them against hundreds of professionally designed color palettes to select the ideal colors for the slide foreground and background.
Next, Zuru performs brightness analysis to determine the best placement of the text (top, middle, or bottom), and whether a text screen is needed for optimal readability and contrast.
Finally, Zuru adjusts the zoom and placement of the image so that the slide background is perfectly centered.
Step 5: Finishing Touches
At this stage, Zuru analyzes the presentation content to determine the high-level category (for example, real estate, marketing, education) and select an appropriate font from our full library of themes.
Kevin’s goal with Zuru is to use data and artificial intelligence to get presentations 90% of the way there in a matter of minutes, and to make it very easy for the presentation creator to review and fine-tune the results.
In this final stage, Zuru will point out areas where trimming down text could improve the presentation, and also identify slides where it needs more input to select the correct keyword or image. The user can either make edits right in Zuru, or export back to .pptx format to edit directly in PowerPoint (which we didn’t even think was possible until very recently).
Sound complicated? Well, it is — which is one of the many reasons we love Kevin and his team. The good news is that although Zuru is complex behind the scenes, it’s incredibly important to all of us that the user experience is simple.
Want to give Zuru a try? Send us a PowerPoint or an outline at firstname.lastname@example.org. We’ll run it through Zuru and send it back to you to see what you think.
And if you’re already convinced (as I am), you can become a charter member and be one of the very first to try it.