{"id":686,"date":"2023-03-29T18:39:20","date_gmt":"2023-03-29T18:39:20","guid":{"rendered":"https:\/\/similari.com\/?p=686"},"modified":"2023-03-29T18:39:22","modified_gmt":"2023-03-29T18:39:22","slug":"the-anatomy-of-a-search-query-how-ai-knows-what-youre-thinking","status":"publish","type":"post","link":"https:\/\/similari.com\/the-anatomy-of-a-search-query-how-ai-knows-what-youre-thinking\/","title":{"rendered":"The Anatomy of a Search Query: How AI Knows What You\u2019re Thinking"},"content":{"rendered":"\n

<\/h3>\n\n\n\n

The word \u201cGoogle\u201d became a verb in 2006, when it found its way into the Merriam-Webster dictionary. But like all shifts in language, it had caught on long before official recognition caught up to everyday usage.<\/p>\n\n\n\n

That happened because search engines like Google had caused a seismic shift in the way humans access information. The algorithms read linking behavior between pages to enable information retrieval on an unprecedented scale. And it was all wrapped up in a streamlined, easy-to-use interface that gave users (even non-technical ones) what they wanted, fast: lists of websites semantically linked to their search query. <\/p>\n\n\n\n


Bad news for public libraries, but amazing for almost everything else. It\u2019s become so ubiquitous that most of us struggle to imagine the \u201cbefore time\u201d.  <\/p>\n\n\n\n

Why you might not be Googling<\/em> for much longer (or at least not in the same way)<\/h3>\n\n\n\n

None of this is news to anyone, so why am I talking about it? Simple: we\u2019re now at another inflection point, heralded by the arrival of powerful new technology. Generating lists of websites ranked according to relevance is useful, but it\u2019s just the starting point. The user still needs to sift, evaluate, analyze and synthesize that information.<\/p>\n\n\n\n

And as Google itself has acknowledged, there is now a pressing need to go further. Lists of websites are not enough: users want \u201cdeeper insights and understanding.\u201d<\/a> In this post, we\u2019re taking a look at how generative AI is changing how we search, paving the way to richer insights and better decision making. <\/p>\n\n\n\n

But first, a brief diversion on semantic analysis. <\/p>\n\n\n\n

Semantics: building search queries, word by word<\/h2>\n\n\n\n

Every word has what is known as a semantic domain, a range of other words that connect to a shared substrate. For example, the word \u201cvehicle\u201d is part of a semantic domain that includes words like car, plane, ship, and many more. \u201cVehicle\u201d can also signify a means of achieving something, particularly in medical and scientific applications. <\/p>\n\n\n\n

Search engines operate by identifying pages that contain keywords in the user\u2019s search query. But one of the conventional limitations of keyword-based search is that it lacks the human intuition to situate the right part of the semantic domain. So, \u201cvehicle\u201d, taken out of context, can recall the entire semantic domain of \u201cthings that travel\u201d, and<\/em> the entirely different domain of \u201cbiological component that delivers drugs\u201d. That\u2019s too broad to be useful.<\/p>\n\n\n\n

But there are many ways to refine a search query to get narrower and more relevant results:<\/p>\n\n\n\n