Why Knowledge Graphs Are Foundational to Artificial Intelligence
AI is poised to drive the next wave of technological disruption across industries. Like previous technology revolutions in Web and mobile, however, there will be huge dividends for those organizations who can harness this technology for competitive advantage.
I spend a lot of time working with customers, many of whom are investing significant time and effort in building AI applications for this very reason. From the outside, these applications couldn’t be more diverse – fraud detection, retail recommendation engines, knowledge sharing – but I see a sweeping opportunity across the board: context.
Without context (who the user is, what they are searching for, what similar users have searched for in the past, and how all these connections play together) these AI applications may never reach their full potential. Context is data, and as a data geek, that is profoundly exciting.
We’re now looking at things, not strings
The best example of the value of context within data is the consumer Web. For example, most of us interact with Google every day. To understand the value of context in AI better, let’s look back to 2012, when Google fundamentally transformed search from “strings” to “things.”
Google is a clear leader in the field of AI through its own innovation and strategic acquisition, not least of which was its acquisition of AI firm DeepMind in 2014. But a smaller, lesser publicized move, I believe, deserves more attention: In 2012, Google introduced its “Knowledge Graph.”
Before the Knowledge Graph, searching via Google was a “string.” If I wanted to know when “Star Wars: The Last Jedi” was playing, I had to search for a movie theatre, then click through to find the right movie and then find and scroll through the showtimes. I had to hop across multiple links.
Today, if I type in “Star Wars: The Last Jedi” not only do I get a link to that movie’s page, but Google’s Knowledge Graph also knows what action I most likely want to take based on previous searches. Thanks to the Knowledge Graph, I am also offered multiple options like showtimes in my area, a way to buy tickets and the movie’s Rotten Tomatoes score.
Per Wikipedia, Google’s Knowledge Graph “uses a graph database to provide structured and detailed information about the topic in addition to a list of links to other sites.” This knowledge graph, built on top of a graph database, has allowed Google to focus its search on things – or concepts – and understand exactly what you’re looking for based on context.
What is a knowledge graph?
Knowledge graphs are a means of storing and using data, which allows people and machines to better tap into the connections in their datasets. By contrast typical NOSQL pattern is simple “store and retrieve.”
You store data and then you symmetrically retrieve it. That method does very little for the user in terms of context and connections. With knowledge graphs, every time you enter data you enrich the entire data ecosystem, because it’s connected to everything else. The more data, the more context. And this contextual value grows exponentially like Metcalfe’s law of the network, because networks are graphs.
Because of their structure, knowledge graphs capture facts related to people, processes, applications, data and things, and the relationships among them. They also capture evidence that can be used to attribute the strengths of these relationships. This is where the context is derived from.
An important question: what separates knowledge graphs from data lakes or data warehouses? The answer is operational convenience. Data warehousing is good for static BI projects, but knowledge graphs must be able to power insights in real time, otherwise they simply won’t work for applications like real-time recommendations, fraud detection or knowledge sharing.
When knowledge graphs are thought about this way, it becomes clear why a knowledge graph is so important for AI. Google isn’t the only company using a knowledge graph for AI. If you’ve interacted with a shopping or customer service “bot” lately, there is a good chance it was built on top of a knowledge graph as well.
“In the following query: “Can you show me brown leather Coach messenger bags under $100?” Shopping is identified as the user’s primary intent. eBay ShopBot then uses a hybrid approach leveraging deep learning and syntactic dependency parsing to extract relevant information related to the shopper’s intent. In the example above, NLU identifies the object of interest as a messenger bag and the target price range to be between $0 and $100. A named-entity recognition component, trained on eBay queries, is used to identify brown as the color, leather as the material, and Coach as the brand.
Once the intent, object and characteristics of the object are known, the data is mapped to eBay inventory using a Knowledge Graph (KG). The KG encapsulates shopping behavior patterns on eBay to bridge the gap between the structured query and behavior data. In other words, the KG helps figure out the best follow-up questions to ask in order to find the best results in the least amount of time.”
This is context for user-centered AI and why I believe knowledge graphs are going to be so fundamental to modern AI systems. The knowledge graph uses connected data to understand concepts and infer meaning so the system can better react to a user’s inquiry, and the user doesn’t have to stitch together multiple “strings” to reach their goals. Meanwhile, the graph accumulates contextual knowledge with each conversation.
Context requires connections, and graphs – as complex systems – offer the highest level of context. We’ve seen that these graphs are actually hungry for new connections and new data, which in turn creates the opportunity for data scientists to evolve and refine the algorithms that operate upon the graph. Customers like eBay have shown us that bigger, more connected graphs, driven by smarter contextualization algorithms are the foundation of valuable AI systems.
Knowledge graphs aren’t as new as you think
Knowledge graphs have actually existed in the enterprise for a while, with the two classic cases being for knowledge workers or traditional enterprise applications. As organizations accumulate historically high volumes of data, the need to synthesize that data to make strategic business decisions is more critical than ever before.
There is a name for businesses who glean insights from connected data (a system of data points working together as a single fabric) – a connected enterprise. Those enterprises are ripe for utilizing knowledge graphs to accelerate delivery of AI applications for their organization.
AI is going to drive the next wave of competitive advantage for companies, but the question will come down to execution and which companies can use AI successfully – whether it’s to connect with their customers, reduce the risk of fraud, increase employee productivity or make better investment decisions. That is the difference that makes a company a connected enterprise, and what will ultimately drive the next wave of competitive advantage through AI.
About the author: Jim Webber is Chief Scientist at Neo4j working on next-generation solutions for massively scaling graph data. Prior to joining Neo Technology, Jim was a Professional Services Director with ThoughtWorks where he worked on large-scale computing systems in finance and telecoms. Jim has a Ph.D. in Computing Science from the Newcastle University, UK.