Google explains usage of AI to make search results better

Google relies on Artificial Intelligence (AI) a lot to improve its search engine. In a recent blog post, the company detailed how AI improvements to its Search systems mean that they are constantly getting better at understanding what users are looking for.

 

Google says that it has developed hundreds of algorithms over the years, like its early spelling system, to help deliver relevant search results. As new AI systems are developed, Google doesn’t do away with older algorithms.

 

Google explains, “AI plays a major role in showing you helpful results, even at the outermost edges of your imagination. In fact, Search runs on hundreds of algorithms and machine learning models, and we’re able to improve it when our systems — new and old — can play well together”. Algorithms have specialized roles and are triggered at different times to deliver the most helpful results.

 

Launched in 2015, RankBrain was the first AI system Google deployed in Search. As the name suggests, what it does is that it helps Google to decide the best order for top search results. RankBrain (as its name suggests) is used to help rank — or decide the best order for — top search results. What it does is that it helps Google understand better how words in a search relate to real-life concepts.

 

With an example it has been explained, “If you search for “what’s the title of the consumer at the highest level of a food chain, our systems learn from seeing those words on various pages that the concept of a food chain may have to do with animals, and not human consumers. By understanding and matching these words to their related concepts, RankBrain understands that you’re looking.” This AI system is helpful in ranking the best possible search results.

 

A lot of times people don’t type coherent sentences in Google Search while looking for something. To understand this better, Google launched an AI system called BERT in 2019. “BERT understands words in a sequence and how they relate to each other, so it ensures we don’t drop important words from your query — no matter how small they are,” explained Google.

 

Citing an example, the company says that “if you search for can you get medicine for someone's pharmacy,” BERT understands that you’re trying to figure out if you can pick up medicine for someone else. With BERT, Google can “understand that even small words can have big meanings.” Based on its complex language understanding, BERT can very quickly rank documents for relevance.