Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Eric B Fox

Logan Luyet Dillard

Russell Dicker

Jason Matthew Cahill

Charlton E Lui

Marieke Watson Iwema

Alexander Hopmann

Dan W Altman

Emily K Rimas-Ribikauskas

Siddharth Sriram

Roshane Silva

Zach Rosenfield

Kfir Ami-ad

Steve Weil

Gokhan Uluderya

Tyler Furtwangler

Bijul Soni

Sanjay Rama

Scott Allen Mongrain

Patrick Simek

Balinder Malhi

Marc Keith Windle

Hyun-Suk Kim

Jared L Richardson

Leroy B Keely

Robert J Jarrett

Robert Andrew Little

Christopher M White

Jeffrey West Pettiross

Matthew Rubin Lerner

Richard Jennings Duncan

Arshish C Kapadia

Shawna Julie Davis

Zoltan C Szilagyi

Tarkan Sevilmis

Jeffrey E Larsson

David Charles LeBlanc

Kevin Joseph Fischer

David B Perry

Michael Ronn Marcelais

Brian T Hill

Eric A LeVine

Erick Raymundo Lerma

Benjamin J Bunker

Christopher Cushen White

Ernest L Pennington, Ii

Aaron E Erlandson

Kshamta Jerath

Ambrose Thomas Treacy

Tittu Jose

Maithili Dandige

Doron Bar-Caspi

Corinne S Sherry

Aaron Everett Erlandson

Marc Windle

Ricardo Prates De Oliveira

Syed Waqas Ahmed

Lachlan J Orr

Maithili V Dandige

David Leblanc

Technologies are described herein for extracting comments from customer reviews for a media item or a collection of media items in order to provide salient comments to promote the media item or the collection of media items. Comments contained in the customer reviews are associated with topics and individual comments are assigned to one or more of the topics. Sentiment indicators corresponding to the comments indicate a majority sentiment that is associated with the topics. Using the majority sentiment, quotes are extracted from the comments to be displayed with an offer to sell at the media item or the collection of media items.

Extracting quotes from customer reviews of collections of items

Increasing diversity of search results is described. In one embodiment, a computing device obtains initial search results based on a search query. From among non-indexed attributes of the initial search results, an attribute is selected by which to diversify the initial search results. A latent group of search results is determined from among the initial search results based on the attribute, and a relevance score of at least one search result in the latent group of search results is changed. Further, results are provided in response to the search query. In one embodiment, the results include at least a portion of the initial search results and at least a portion of the latent group of search results based on the changed relevance score of the search results in the latent group.

Diversity within search results

Technologies are described herein for extracting quotes from customer reviews for a collection of items in order to provide salient comments for a particular item and/or upsell the collection. Individual sentences contained the customer reviews regarding the collection of items are parsed into a collection of sentences. A list of topics is generated from the collection of sentences, and each sentence in is assigned to one or more of the topics. A number of the topics from the list of topics are identified as related to the particular item, and quotes are extracted from the sentences assigned to the identified topics to be displayed as customer reviews of the particular item. Similarly, a number of topics in the list of topics are identified as related to a customer satisfaction with the collection of items, and quotes are extracted from the sentences assigned to the identified topics to be displayed in conjunction with an offer to upsell the collection of items.

Disclosed are various embodiments for defining subcategories of items to be used in merchandising. The subcategories may be defined on the basis of item data and/or sales data for the items. Based on a distribution of the items in accordance with one or more of the item and/or sales data, implicit groups or subcategories can be identified and selected for merchandising purposes.

Automatic product groupings for merchandising

Disclosed are various embodiments for tracking user behavior relative to a network page and identifying user interest in various content items of the network page according to the user behavior. A network page that includes multiple content items is rendered for display in a client. A user action is obtained relative to the network page. A user behavior report is sent to one or more servers. The user behavior report indicates the user action, a timestamp associated with the user action, and one or more of the content items that are associated with the user action.

Tracking user behavior relative to a network page

Technologies are described herein for extracting quotes for an item from customer reviews. Individual sentences or phrases contained in customer reviews regarding an item or category of items are parsed into a collection of sentences. A list of topics is generated from the collection of sentences, and each sentence or phrases is assigned a topic from the list of topics. The most relevant topics from the list of topics are identified for a particular item, and one or more sentences or phrases from customer reviews for the particular item are selected for each of the most relevant topics that best represent the sentences associated with the item and assigned to that topic, according to content and sentiment.

Extracting quotes from customer reviews

Requests to a server farm are managed in an application intelligent manner based on server health and client information. A request management (RM) module is configured to make smart routing decisions, based on routing rules that relate the nature of requests to a dynamic topology of a server infrastructure. The RM may use its knowledge of server applications, servers, and clients to deny potentially harmful requests from entering the service, route good requests to the suitable machines, and maintain a history of the decisions and consequences automatic and/or manual optimization.

Application intelligent request management based on server health and client information

Server health and client information are exchanged through headers for request management. Headers in standardized or proprietary protocol communication between servers and a request management module and/or clients and the request management module may be used to exchange server health and client information. The exchanged server health and/or client information may be employed in throttling, routing, and/or load balancing the incoming requests. Rules specified by the client through the header exchange may also be used for throttling, routing, and/or load balancing decisions.

Exchange of server health and client information through headers for request management

An online service includes managed databases that include one or more tenants (e.g. customers, users). A multi-tenant database may be split between two or more databases while the database being split continues processing requests. For example, web servers continue to request operations on the database while content is being moved. After moving the content, tenant traffic is automatically redirected to the database that contains the tenant's content.

Dynamically splitting multi-tenant databases

Disclosed are various embodiments for increasing diversity of search results. A computing device performs a search of items in an electronic catalog to produce a plurality of search results. The electronic catalog is stored in a data store accessible to the computing device. A latent group is identified which includes a most relevant one of a plurality of search results. Each of the search results has a plurality of attributes. Membership in the latent group is determined by similarity of a non-indexed one of the attributes. A relevance score of those search results in the identified latent group other than the most relevant one of the search results is reduced.

Disclosed are various embodiments for defining subcategories of product items to be used in merchandising. The subcategories may be defined on the basis of product data and/or sales data for the product items. Based on a distribution of the product items in accordance with one or more of the product and/or sales data, implicit groups or subcategories can be identified and selected for merchandising purposes.

Technologies are described herein for extracting quotes from customer reviews regarding collections of items. An identifier of an individual item is received and customer reviews regarding a collection of items containing the individual item are retrieved. A collection of sentences is parsed from the retrieved customer reviews, and sentences that discuss the individual item are identified. A quote is extracted from the identified sentences and displayed to a customer in conjunction with information regarding the individual item. Similarly, individual items belonging to a collection of items are identified, and customer reviews regarding the individual items are retrieved. A collection of sentences are parsed from the retrieved customer reviews, and those sentences that discuss topics relevant to the collection of items are identified. A number of quotes are extracted from the identified sentences and displayed to a customer in conjunction with information regarding the collection of items.

Extracting quotes from customer reviews regarding collections of items

Technologies are described herein for classifying sentences or phrases as expressing positive or negative sentiment based on machine learning from training data comprising sentences manually labeled as to sentiment. A list of terms is generated from the manually labeled sentences and sentiment scores are determined for the terms in the list of terms based on the manually labeled sentences. A collection of sentences or phrases may then be classified as to sentiment utilizing one or more logistic regression classifiers trained on the sentiment scores determined for the terms in the list of terms. The classified collection of sentences may be further analyzed to determine an overall majority sentiment regarding a topic discussed in the sentences and/or to extract specific sentences or phrases expressing a particular sentiment for display to a customer.

Determining sentiment of sentences from customer reviews

Disclosed are various embodiments for selecting a subset of categories of product items to be used in merchandising. The subset of categories may be selected on a basis of a measured level of interest in the product items. Based on the subset of subcategories that have been selected, merchandising presentations may be automatically formulated and presented to a customer.

Automatic selection of product categories for merchandising

Growing community of inventors

Seattle, WA, United States of America

Eric B Fox