Windows 10: Introducing Locations in Microsoft Search in Bing

Brink · Nov 27, 2018

Maps and directions are a common intent for many enterprise searches. Many companies have more than one building and it's critical for businesses to provide a correct answer when employees search for a building location or directions within their organization.

As one of the more requested scenarios from our customers, today we are pleased to announce a new feature called, Locations. This feature enables enterprises to surface relevant buildings and places, pertinent to an individual enterprise, based on simple keywords you choose.

To get started, have your Microsoft Search in Bing admin to visit the admin portal and manage the locations for your O365 tenant. Below are the help documents if you'd like to learn more on how this works.

Add a Location

Manage Locations

Bulk modify using import/export features

User instructions for using location feature

We have a few pointers while creating or using the locations features:

When a new location is created, it will be available for search after 2 hours.

Location is searchable using the Location name, Keywords and Reserved keywords.

We welcome your feedback and questions. Please reply to this article or ask your questions in Tech Communities or using the Feedback link from the business results.
Click to expand...

Source: Introducing Locations in Microsoft Search in Bing - Microsoft Tech Community - 291894

:)

Brink · Nov 27, 2018

Introducing Bing Visual Search

Over the years people have come to expect search engines to automatically detect intent and provide great search results for text queries typed into a single search box. Now Bing takes the first step to achieve the same for images. The Bing Team sets out to connect your camera to a deep search experience.

We started several years ago by introducing ‘Search By’ Image capability. This allowed a user to specify an entire image to be used as a search query. But what if you only want to search for a certain object you saw in an internet image – or one you photographed? So far you'd have to jump through hoops to accomplish this - but not anymore. In this post we will share some recent work we’ve done to solve this challenge and some of the technical wizardry that made it possible.

Introducing Bing Visual Search

Let's say you are looking for kitchen decoration inspiration, and an image attracted your attention. You click on a thumbnail result to get to the ‘Detail View’. You really like the overall décor, but you are particularly interested in that nice-looking chandelier. Would it be possible to see where you can get one just like that? With Bing Visual Search, now you can!

In the Detail View, you will now see a magnifying glass symbol in the top left of the image. It is called the visual search button.

Clicking the visual search button displays a visual search box on the image. You can click and drag this box to adjust it to cover just the object of your interest. You can also simply draw a box around the chandelier if that’s more convenient.

Every time you adjust the visual search box, Bing instantly runs a visual search using the selected portion of the image as the query.

We realize that many Bing image search users may be shopping for items they see in the image or a similar product. We automatically detect the shopping intent and, in addition to regular image search, we also run a product search to find matching products:

Now you can simply click on the chandelier that is right for you, pick the best merchant on the detail page and finalize your purchase!

If you're not in a shopping mood after all, you can still click on “Related Images” to continue exploration of similar images. We are continuously working to detect more intents and bring the best information to the results to satisfy your search needs.

After you’ve found the perfect chandelier options for your project, it’s easy to conduct a visual search for other items. For example, in our example image you can select that beautiful bowl and find a similar one for your kitchen. You can search for any object you see in the image.

Visual search is in its infancy, and we are aware of cases where there is still room for improvement. For example, you may need to tweak your visual search box to fully capture the object of interest to get the best results.

All this goodness is available on your PC or mobile device by visiting Bing.com or in the Bing mobile app. Developers can build visual search into their app using Bing APIs as described here.

Please try out our visual search - just be careful as it can get quite addictive! Let us know what you think using Bing Listens or the Feedback button on Bing.

Under the hood

So how does it all work?

In text based search, the first step is query understanding. Similarly, in visual search, we first need to understand the query image. The major difference is that now instead of query terms we need another way to represent the query-image. Once the query understanding phase is complete, the subsequent steps in the execution of the query are similar:

As a first step in the query-image understanding process, we run Image Processing Service to perform object detection, extraction of various image features including DNN features, recognition features, and additional features used for duplicate detection.

Next comes text query inference step. Here we try to generate the best text query to represent the input image. This is based on a pipeline widely used in Bing image search to identify so called BRQs (for 'best representative query'). You can learn more about how this process works in our earlier post at: The Image Graph - Powering the Next Generation of Bing Image Search).

Subsequently we run a triggering model to identify different scenarios for search by image. Here we leverage the expertise already used in Bing answers triggering. For instance, if we detect that the query-image has the shopping intent, then we show rich segment specific experience.

Once the image understanding phase is complete, we enter the next step: matching. In order to implement search by image inside of existing Bing index serve stack, designed mostly for text search, we need to get text-like representation for the image feature vector. To accomplish this we employ a technique known in vision area as Visual Words. This technique allows us to quantize a dense feature vector into a set of discrete visual words, which are essentially a clustering of similar feature vectors into clusters, using the joint k-means algorithm. The visual words are then used to narrow down a set of candidates from billions to several millions.

After the matching step, we enter the stage of multilevel ranking. We need to rank millions of image candidates, and we’ll do that based on feature vector distances. To speed up the calculations, we use an innovative algorithm developed by Microsoft Research in collaboration with University of Science and Technology of China called Optimized Product Quantization (for more information see the paper: Optimized Product Quantization for Approximate Nearest Neighbor Search). The main idea is to decompose the original high-dimensional vector into many low-dimensional sub-vectors that are then quantized separately as pictured below.

After quantization is complete we need to calculate distances between the query-image and result-image vectors. Instead of using the usual Euclidean distance calculation, we perform a table lookup against a set of pre-calculated values to speed things up even further.

As a result of Optimized Product Quantization, we have reduced candidate set from millions to thousands. At this point we can perform a more expensive operation to rank the images more accurately. After multiple levels of ranking the de-duplication step is executed to remove any duplicate images from the results. The set of images we end up with after this step is the final result set that will be returned to the user.

What’s Next?

We’re constantly working to make the experience better. For example, you may soon notice that we will automatically help you pick objects without needing to draw a box, and provide other tools to help refine your search. We’re also continually focused on bringing the most comprehensive and highest quality visual search results.

Let us know what you think and stay tuned for more improvements!

- The Bing Team
Click to expand...

Source: Beyond text queries: Searching with Bing Visual Search | Search Quality Insights

Brink · Nov 27, 2018

Introducing Microsoft Search for Windows 10, Office, Bing, and more

At Ignite last year, we introduced personalized search across Office 365, a way to bring intelligent search and discovery experiences directly to you. Today, we’re delighted to announce that we are expanding that vision to encompass search both inside and outside of Microsoft 365. By applying artificial intelligence (AI) technology from Bing to the deep personalized insights surfaced by the Microsoft Graph, we are able to make search in your organization even more effective.

With Microsoft Search, we’re introducing new organizational search experiences into the apps you use every day, including Bing.com and Windows, and our vision to connect across your organization’s network of data.

mtjJdltMoWU

We’re also evolving the notion of what search means. Getting pages of results with hyperlinks to other information is simply not enough. Faced with ever decreasing attention spans, and an explosion of data, we recognize that the challenge is to find and deliver answers to your questions, suggest insights, and enable you to take action on your tasks. This makes search a powerful capability that stretches across your work to make you more productive and take advantage of the collective knowledge from your organization.

Our vision is a cohesive and coherent search capability, prominent in every experience, providing the way to search across all your organization’s data—both inside and outside of Microsoft 365.
Over the next few months, you’ll experience these first steps:

Search will move to a prominent, consistent place across the apps you work with every day. From Outlook to PowerPoint, Excel to Sway, OneNote to Microsoft Teams, Office.com to SharePoint, the search bar will be in the same place—across desktop, mobile, and web.

Personalized results as soon as you click in the search box, such as people you share with the most and documents you were working on recently. No query is required to get suggestions.

The search box itself will also command the application where you are working. For example, begin typing “acc” in Word to get list of suggested actions such as Accept Revision or Accessibility Checker. You no longer need to hunt through toolbars to look for a command.

Search results will include results from across your organization. For example, within Word, you can find not only other Word documents, but also a presentation you were working on. You can navigate straight to that presentation or you can choose to incorporate slides from that file directly into your document.

Extending that same organizational search experience wherever you are working—in Bing.com (when signed in with your Office 365 account), Edge or Windows. Search wherever you want to and get the same experience.

Unified administration of your organizational search results, including admin-curated results such as bookmarks.

Experience Microsoft Search today

Key to delivering the Microsoft Search capability is the ability to have consistent scope of results anywhere you are searching. Even if the interface looks different, the goal is to have the same experience, personalized and contextualized for that specific interaction point.

Microsoft Search in Bing.com

Over the last year, 180 companies participated in our private preview, with files, sites, people, locations, and groups based on Microsoft Graph data. Based on the private preview feedback, we’re announcing the ability to search across conversations in both Teams and Yammer simultaneously.

Searching in Bing returns both your organizational results and web results, making it an easy destination for broad searches to get the best of your work world and secure your web searches. Public preview begins rolling out today. Tenant admins must opt in to the experience for their organization. Visit bing.com/business/explore for details.

Microsoft Search in Office.com

Get back to your work faster with Office.com, surfacing the same search scope across Microsoft 365. Find documents you were recently working on, as well as recommended documents that your colleagues have mentioned you in, and keep up to date with what has been worked on since you last looked at it. Microsoft Search in Office.com goes into targeted release today.

Microsoft Search in SharePoint mobile app

The new version of the SharePoint mobile app includes search as the default experience when you enter the app. It lists common questions, personalized results, and frequent searches that organizations can curate. The new SharePoint mobile app is available for download today.

Microsoft Search in the Outlook mobile app

The Outlook mobile app also highlights search as an important element of the user experience, providing access to commands, content, and people. With “zero query search,” simply placing your cursor in the search box will bring up recommendations powered by AI and the Microsoft Graph. The Outlook mobile app for iOS and Android are available for download today.

Outlook will also bring zero query, fuzzy search, and top results based on intelligent technology to other endpoints as we drive towards coherence. Enhancements to search in Outlook for Windows, Mac, and on the web started to roll out to targeted release mid-September.

Connect and curate data across your organization’s systems

Boundary-less search is only as good as the sources it has access to. We recognize that organizations have a wealth of data in other third-party services and applications. In 2019, we will build native connectors for popular third-party applications that will surface search results inline with Microsoft data into all the search experiences you have, including Office, Windows, Edge, and Bing.com. Administrators will be able to select which connectors they wish to use for their organizations based on which investments they’ve already made in third-party applications. Further extensibility with APIs will also be possible. Organizations will be able customize the search sources and the display of search results with custom refiners and verticals, and control the display of how sources of information look in result pages.

Coming in the first half of 2019

Microsoft Search in Office

Our new suite-wide search in the ribbon offers the same consistent experience and results across your favorite Office apps—across desktop, mobile, and web. Find, command, navigate, and discover directly from the same search box.

Microsoft Search in Windows

Right from your taskbar, perform searches that include local and organizational search results; whether that is people, the location of an office, or your files, you can find it all in Windows.

What’s coming next?

The Microsoft Graph gleans insight from the people, sites, devices, and documents you work with and is the basis for consistent learning across your organization, wherever you and your colleagues work. Microsoft Graph ranks search results relevant to your needs. You can see all the results that satisfy your query, but personalized search prioritizes the results that are most likely to achieve your objective.

Supercharging the Microsoft Graph with advanced AI technology from Bing and its knowledge of the world, we can extend our vision for insightful technology to make it simple to ask natural language questions and get real answers, without manual intervention. For example, a question such as “Can my brother work for me at my company?” means that not only syntactic parsing of the question is necessary but semantic understanding. Your organization’s HR policy probably specifies “close family relationships,” so we use Bing’s knowledge of the world to expand and match “brother” and couple that with searching your organization’s intranet to derive the answer.

Using this machine reading comprehension technology is just one of the many ways we’ll be continuously improving Microsoft Search in the future.
Click to expand...

Source: Microsoft Search - cohesive search that intelligently helps you find, discover, command, and navigate - Microsoft 365 Blog

JDanielWebb777 · Nov 27, 2018

In Windows 10 , can I change Cortana search engine from Bing to Google?

The Windows 10 Cortana application is Microsoft Bing proprietary and cannot be adjusted.

Microsoft Windows 10 has introduced the intended replacement for Internet Explorer called Microsoft Edge which also defaults to searching using Bing. If there are no listed alternate search engines when attempting to add a new one then, assuming the search
provider supports the "OpenSearch" standard they can be added using the steps listed below.

1. In Microsoft Edge - Open a tab to your desired "http://www.google.com" and leave the tab open to the default google website.

2. Select More actions (...) > Settings and then scroll down to select View
advanced settings. In the list under Search in the address bar with, choose Add new.

3. Select the website and then select Add as default

Windows 10: Introducing Locations in Microsoft Search in Bing

Introducing Locations in Microsoft Search in Bing

Introducing Locations in Microsoft Search in Bing

Introducing Locations in Microsoft Search in Bing

Introducing Locations in Microsoft Search in Bing - Similar Threads - Introducing Locations Microsoft

Bing search location setting

Introducing the new Microsoft Edge and Bing

Improvements to Microsoft Search in Bing

Microsoft Build 2019: Introducing Microsoft Search

Microsoft Search Webcast: Get started with Microsoft Search in Bing

Introducing Microsoft Search for Windows 10, Office, Bing, and more

Introducing Bing AMP viewer and Bing AMP cache

Bing search

Introducing Bing Visual Search