Amazon Technologies, Inc.

Uber Technologies, Inc.

Russell Dicker

Waqas Syed Ahmed

Jeremy Charles York

Joseph Spencer King

Logan Luyet Dillard

Ryan Justin Snodgrass

Jeffrey P Bezos

Eric B Fox

Scott Allen Mongrain

Joanna L Power

Matthew James Round

Florin V Manolache

Jennifer A Jacobi

Gregory D Linden

James G Robinson

Eric A Benson

Jeffrey T Brownell

Robert G Cottrell

Aaron D Wilson

Val Dan Dar Ion I Rosca

Corneliu Gabriel Alexandru Rudeanu

Brandon W Farrell

Marc Christopher Pottier

Vincent Yates

Valentin Radu Munteanu

Thomas Fallows

Chad E Desjardins

Qinming Fang

Michael Reckhow

Matthew W Amacker

Ethan Zane Evans

Ameesh Paleja

Alexander Clark Prater

Roy F Price

Cameron Janes

Andrew V Harbick

William D Carr

Maurice Codik Moscoso

Alexander J Cox

Brian Goldstein

Joseph A Frisbie, Iii

John Benjamin Compton

Matt Round

John B Compton

A network computer system can implement a hierarchical selection process to fulfill the scheduled transport request. The hierarchical selection process can include a first selection process and a second selection process. The first selection process can include assigning a transport provider to fulfill the scheduled transport request. Additionally, the first selection process can include disassociating the transport provider with the scheduled transport request upon determining that the transport provider is unable to fulfill the scheduled transport request at the scheduled time. The second selection process can be implemented at a specified time prior to the scheduled time and can include selecting a backup transport provider.

Hierarchical selection process

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

A network system can communicate with a user device and receive a set of request data for a scheduled request at a scheduled date and a scheduled time. The set of request data indicates a start location and a destination location for the scheduled request. The network system can record the scheduled request in a scheduling log, and implement a hierarchical selection process to fulfill the scheduled request.

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.

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

A subset of a set of components is selected for inclusion on a dynamically-generated page within a particular user context. The subset of components is selected based on scores associated with the components in the set. The score of a component is preferably determined based on measurements of user activity resulting from exposures of the components to users in the particular context.

Adaptive learning methods for selecting page components to include on dynamically generated pages

Tag merging enables a hosting entity such as a website to determine one or more tags that are logically-related to a particular tag and to present these tags to users to enable the users to vote whether to merge a logically-related tag with the particular tag. The hosting entity may determine these logically-related tags in multiple ways. For instance, the hosting entity may analyze keyword-to-keyword similarity data, item-overlap data, or may employ stemming logic. When the entity presents these tags to a user, the user may vote to merge the particular tag with one or more of the presented logically-related tags. When merged, items associated with the selected logically-related tag may become associated with the particular tag, or vice versa. Additionally, the selected tag may be removed from the items previously associated with the selected tag, or vice versa.

Tag merging

Tag scoring for elements associated with a common tag enables a user to conduct a tag search and view a listing of elements associated with the tag. The listing can be ordered by each element's tag score. To create such a tag score, users may associate an element with one or more tags that characterize the element. A tag score may then be assigned to this element for each assigned tag and may be based on a multitude of factors. These factors may include a number of times that the element has been tagged with the assigned tag and users' votes on the accuracy of the assigned tag to the element. Tag-scoring factors may include, among others, an age of a tag associated with the element, a click rate for the element, a customer review of the element, a sales rank for the element, or an availability of the element.

Tag scoring for elements associated with a common tag

A subset of a set of components is selected for inclusion on a dynamically-generated web page within a particular user context. Each component may, for example, contain content generated by a respective code module or service. The subset of components is selected based on scores associated with the components in the set. The score of a component is preferably determined based on measurements of user activity resulting from exposures of the components to users in the particular context.

Systems and methods are provided for providing an answer to a question left unanswered in an electronic discussion forum. In some embodiments, a question that has not been answered may be identified in a first discussion forum. A second discussion forum in which to present the question may be determined, where the second discussion forum is more likely than the first discussion forum to result in an answer to the question. The question may then be presented in the second discussion forum, and one or more responses to the question may be received in the second discussion forum. It may then be determined whether one of the one or more responses includes a good answer to the question, and when the determination is that one of the one or more responses includes a good answer, the good answer may be presented in the first discussion forum.

Providing an answer to a question left unanswered in an electronic forum

A subset of a set of components is selected for inclusion on a dynamically-generated web page within a particular user context. Each component may, for example, contain content generated by a respective code module or service. The subset of components is selected based on scores associated with the components in the set. The score of a component is preferably determined based on measurements of desired user activity resulting from exposures of the components to users in the particular context, and reflects a likelihood that other users within the same context will perform a desired action. The disclosed methods may also be used to select items, such as products, to suggest to users within specific contexts.

Adaptive learning methods for selecting web page components for inclusion in web pages

An interactive system enables users to generate and submit lists of items (e.g., products selected from an electronic catalog) for viewing by other users. The user-generated lists are selectively suggested to users of the system based (or based in part) on ratings of the user-generated lists. These ratings may, for example, be based on explicit ratings of the lists by users, and/or measures of how effective the respective lists are at driving purchases of items. In some contexts, the system may select one or more user-generated lists to present to a user based on a set of items purchased, viewed, or otherwise selected by the user, or based on the results of a search query submitted by the user.

Service for accepting and selectively exposing user-generated lists

Adding interactive objects to content having a timeline at user-identified positions in the timeline. During subsequent rendering of the content, the interactive objects are presented to a user at the identified positions. The interactive objects represent an opportunity for the user to render additional content or perform a transaction. In an embodiment, compensation is generated as a result of performance of the transaction.

Annotating content with interactive objects for transactions

Systems and methods are provided for identifying an answer to a question in an electronic discussion forum. In some embodiments, text from a discussion forum that includes a question may be retrieved. One or more responses to the question from the discussion forum may be determined. An answer to the question may then be determined from the one or more responses to the question. In some embodiments, an answer may be determined based, at least in part, on at least one of a context of the text from the discussion forum, a context of a location in which the answer to the question may be further presented, and user behavior related to the one or more responses to the question.

Identifying an answer to a question in an electronic forum

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.

Growing community of inventors

Seattle, WA, United States of America

Russell Dicker