????在相關性搜索的應用上，旅行和在線零售行業(yè)走在最前列，不過其它行業(yè)也不甘落后。比如谷歌（Google）和必應（Bing）等搜索引擎也開始采用這一理念，開始根據(jù)用戶的搜索歷史和個人喜好，向不同人群顯示不同的搜索結果。另外近年來非常熱門的團購業(yè)也在努力整合相關性搜索，因為消費者越來越需要一個能夠提供折扣的購物平臺（而不是向吃素的人提供牛排餐廳的優(yōu)惠券）。圍繞著用戶意圖能夠構建起來的背景信息越多，顯示的搜索結果就會越精確。

????不過到目前為止，還是旅行業(yè)最能顯示相關性搜索的能力和價值。

????今天，人們在打算出行的時候，往往要登陸好幾十個網(wǎng)站，搜索符合要求的航班和酒店。每次都要頗費一番周折——尤其是每年的這個時候，機票和酒店更是貴得嚇人，以至于消費者無論花多大的力氣，也要貨比N家，找出其中最便宜的。

????擺在大多數(shù)旅行者面前的一個問題是：一般說來，如果在網(wǎng)絡上搜索一個航班的信息，會跑出來1,000多個難以區(qū)別的、混亂無序的搜索結果?，F(xiàn)在許多商業(yè)旅行平臺，甚至是有些消費者網(wǎng)站都開始使用語義數(shù)據(jù)、統(tǒng)計建模和機器學習等手段來解決這一問題。有些高級平臺可以迅速掃描用戶的相關數(shù)據(jù)——比如可能的航班時間、可接受的價格區(qū)間、用戶需要的機內(nèi)設施，以及用戶喜歡的航空公司等——然后為每名用戶重點展示最佳選擇。

????這些工具并不會把成千上萬個其它搜索結果排除掉，而是會把所有搜索結果組織起來，優(yōu)先顯示相關性最強的選項。這種組織方法意味著用戶可以輕易地對背景環(huán)境進行修改，比如今天可以想選擇“廉價旅行”，明天又變成“不計成本”。但不論采取哪種情況，相關性搜索引擎都能快速地分析人們的個人偏好，提供最好的選擇。

????消費者對相關性搜索能力的需求已經(jīng)存在了一段時間了。各大搜索引擎和企業(yè)早就在嘗試如何利用消費者對個性化信息的需求，現(xiàn)在相關性搜索終于開始走向成熟。在許多方面，相關性搜索都是對消費者行為變化方式的一種回應。以往消費者在購物或訂票時會先打開黃頁，但這已經(jīng)是老黃歷了。數(shù)字時代的消費者生活在網(wǎng)絡上，他們不能容忍收件箱里的垃圾廣告郵件，也不愿在吃飯時冷不防接到促銷電話。他們希望能夠控制自己收到的信息，以及何時收到這些信息。未來消費者在相關性和個性化問題上還會變得更加苛刻。

????Travel and online retailers are ahead of the curve, but others are embracing relevance-powered search. Search engines like Google and Bing are also beginning to adopt the concept -- serving up different results for different people, based on search history and personal preferences. And fast-growing daily deal businesses are working hard to incorporate relevance as consumers increasingly demand platforms that provide appropriate discounts (instead of offering steakhouse coupons to vegetarians). The more contexts that can be built around a user's intent, the more refined the result set can, and will, be.

????But travel is by far one of the best ways to showcase the power and value of relevance.

????Today, travelers spend hours searching dozens of websites for flights and hotels that meet their requirements. It's a major hassle every time they need to travel – especially this time of year, when air fare is so high that consumers will do everything in their power to get the best deal possible.

????The problem faced by most travelers is that a typical flight search will yield 1,000+ nearly indistinguishable and unorganized results. Many business travel platforms – and even some consumer websites – are starting to solve this problem through the use of semantic data, statistical modeling and machine learning. Advanced platforms can quickly scan available data on a user – like the times they can fly, their price range, the in-flight amenities they desire and their preferred airlines – and highlight the best options for each user.

????These tools won't eliminate the tens of thousands of results available to the user, but they will organize and structure them so the most relevant options are presented first. This structuring means that the context of a search can easily be modified whether the user is in a 'budget trip mood' today, or a 'no expense spared mood' tomorrow. Either way, relevance engines can quickly analyze your personal preferences to serve up the best options.

????The desire for relevance-powered search capabilities has been around for some time. Companies and search engines have long been trying to take advantage of the buyer's need for personalized information, and it's finally coming to fruition. In a lot of ways, it's a reaction to how consumer behavior is changing. While the old-school buyer might start the process in the yellow pages, today's digital-aged buyer lives online. They're far less tolerant of unwanted advertisements spamming their inboxes and cold calls during dinner time – and want control over the information they receive, and how they receive it. Tomorrow's buyer will be even more demanding when it comes to relevance and personalization.