October 14, 2019 News Magazine

Microsoft open-sources a crucial algorithm behind its Bing Search services

Microsoft today announced that it has open-sourced a key piece of what makes its Bing search services able to quickly return search results to its users. By making this technology open, the company hopes that developers will be able to build similar experiences for their users in other domains where users search through vast data troves, including in retail, though in this age of abundant data, chances are developers will find plenty of other enterprise and consumer use cases, too.

The piece of software the company open-sourced today is a library Microsoft developed to make better use of all the data it collected and AI models it built for Bing .

“Only a few years ago, web search was simple. Users typed a few words and waded through pages of results,” the company notes in today’s announcement. “Today, those same users may instead snap a picture on a phone and drop it into a search box or use an intelligent assistant to ask a question without physically touching a device at all. They may also type a question and expect an actual reply, not a list of pages with likely answers.”

With the Space Partition Tree and Graph (SPTAG) algorithm that is at the core of the open-sourced Python library, Microsoft is able to search through billions of pieces of information in milliseconds.

Vector search itself isn’t a new idea, of course. What Microsoft has done, though, is apply this concept to working with deep learning models. First, the team takes a pre-trained model and encodes that data into vectors, where every vector represents a word or pixel. Using the new SPTAG library, it then generates a vector index. As queries come in, the deep learning model translates that text or image into a vector and the library finds the most related vectors in that index.

“With Bing search, the vectorizing effort has extended to over 150 billion pieces of data indexed by the search engine to bring improvement over traditional keyword matching,” Microsoft says. “These include single words, characters, web page snippets, full queries and other media. Once a user searches, Bing can scan the indexed vectors and deliver the best match.”

The library is now available under the MIT license and provides all of the tools to build and search these distributed vector indexes. You can find more details about how to get started with using this library — as well as application samples — here.


Source: TechCrunch

Tags: in Uncategorized
Banner
Related Posts

Flutterwave and Alipay partner on payments between Africa and China

July 29, 2019

July 29, 2019

San Francisco and Lagos based fintech startup Flutterwave has partnered with Chinese e-commerce company Alibaba to offer digital payments between...

Is your product’s AI annoying people?

June 17, 2019

June 17, 2019

James Glasnapp Contributor James Glasnapp is a senior UX researcher at PARC. Artificial intelligence (AI) is allowing us all to...

Ninja is leaving Twitch for Microsoft’s Mixer

August 1, 2019

August 1, 2019

Tyler “Ninja” Blevins, the biggest streamer ever, has today announced his intention to leave the Twitch platform in favor of...

Audi proves two little screens are better than one big screen

June 7, 2019

June 7, 2019

I’m spending some time in the new Audi Q8, and the car company equipped the crossover with its latest infotainment...

Uber CTO says competing with Didi is ‘very healthy’ despite their complicated relationship

July 9, 2019

July 9, 2019

Competing with a company that counts you as an investor is hardly conventional — some might call it strange —...

Alibaba returns to growth with revenue up 51% to $13.9 billion

May 15, 2019

May 15, 2019

It’s business as usual for Alibaba after the Chinese e-commerce giant bounced back from a lackluster Q3 — which saw...

Disney shares are up after the big reveal of its streaming service

April 12, 2019

April 12, 2019

Investors seem to think that Disney is on the right track with its plans for the new streaming service, Disney+....

500 Startups Japan becomes Coral Capital with a new $45M fund

March 5, 2019

March 5, 2019

The 500 Startups Japan crew is going independent. The VC firm announced a $30 million fund in 2015, and now...

Startups Weekly: Spotify gets acquisitive and Instacart screws up

February 9, 2019

February 9, 2019

Did anyone else listen to season one of StartUp, Alex Blumberg’s OG Gimlet podcast? I did, and I felt like...

Porsche Taycan configurator: The 11 details that stood out

September 5, 2019

September 5, 2019

The Porsche Taycan is here — actually two flavors, the Turbo S and the Turbo — in case you haven’t...

Android Q devices will get over-the-air security updates — but there’s a catch

May 7, 2019

May 7, 2019

Devices shipping with Android Q will receive over-the-air security patches without having to go through device manufacturers. A lack of...

This is Samsung’s Galaxy Note 10 and 10+

August 7, 2019

August 7, 2019

Eight years later, the Galaxy Note is undeniable. The original device, unveiled at IFA 2011, seemed unfathomably massive for a...

Rocket Lab adds satellite manufacturing to its offerings

April 9, 2019

April 9, 2019

Rocket Lab, one of the biggest startups in the NewSpace category of companies providing launch and satellite services, has added...

Kurly, a grocery e-commerce startup in Korea, closes upsized $113M Series B round

May 30, 2019

May 30, 2019

Kurly, a startup that operates a grocery delivery service in Korea, said today that it has closed an upsized Series...

Comments
Leave a Reply

Your email address will not be published. Required fields are marked *