Amazon Technologies, Inc.

Eugene Kalenkovich

Tom Killalea

Richendra Khanna

Janna Hamaker

Peter Thomas Killalea

Joshua M Goodspeed

Ronald M Whitman

Rajiv Chopra

Preetha Chatterjee

Thomas F Dimson

Zaur Kambarov

Gregory Gridin

Segment signatures for road segments may be generated to enable, among other things, conflation of map data. To generate a segment signature, map data is analyzed to determine road segments represented by the map data. A road segment may be converted into a segment signature to enable comparing road segments between different maps and/or for other reasons. The segment signature may be generated for a road segment and may include truncated geohashes or geohashes including fewer significant digits than more precise geohashes for points along the road segment, thereby designating a small area of land for comparison purposes. The segment signature may include alphanumeric digits representing a start angle and an end angle of the road segment.

Identification of road segments

Highlights from a community of users highlighting portions of an electronic digital content are analyzed and popular highlights determined. The popular highlights are then distributed to the users.

Selection of popular portions of content

Character identity recognition is applied to identify text strings corresponding to character identities in a written work. The textual strings are grouped according to character identity and, from each group, a primary name is selected. A significance value may be calculated for each of the character identities. The character identities including the primary names are presented in a catalog based on the calculated significance values.

Recognition of characters and their significance within written works

A method is provided for presenting a written work. A character identity is recognized within a written work. Presentation information for the written work, such as a graphical scheme or an electronic voice, is determined based on the character identity. The presentation information is provided to a user computing device. The user computing device renders the written work or a portion thereof using the presentation information.

Presentation of written works based on character identities and attributes

Selection of popular highlights

Highlights from a community of users highlighting portions of an electronic digital work may produce aggregated highlights. Users may have access to public and purchase versions of the aggregated highlights. Reconciliation of highlights across multiple versions of the same digital work may also take place, with the reconciled highlights incorporated into the aggregated highlights.

Aggregation of highlights

Techniques for ranking electronic content items include analyzing annotations made in the content items. Specifically, the number of annotations and the number of people making the annotations can be analyzed to produce a popularity ranking of different content items.

Annotation-based content rankings

In some implementations, a user may select a category, attribute or term related to content item. During presentation of the content item, an electronic device may visually distinguish (or, alternatively, hide) at least one portion of content associated with the selected category, attribute or term. In some examples, a user interface may be displayed to enable the user to select one or more categories, attributes, or terms related to the content item. The user interface may further enable the user to select a graphics scheme to be used for visually distinguishing at least one portion of content corresponding to the selection. Selection information identifying a portion of content to be visually distinguished or hidden may be sent to a content provider, such as for synchronization with other instances of the content item on other devices of a user, or for aggregation of the selection information by the content provider.

Visually distinguishing portions of content

Named entity recognition is applied to identify text strings corresponding to character identities in a written work. The textual strings are grouped according to character identity and, from each group, a primary name is selected. A significance is calculated for each of the character identities. The character identities including the primary names are presented in a catalog based on the calculated significance. In some embodiments, character identity identification results are refined by allowing users to vote regarding the significance of the character identities and by granting more weight to the votes of users with a close relationship to the written work.

Similarities are discovered among different users with respect to their media experiences and other behaviors, such as taste in media items (e.g., books, music, movies, magazines, art, etc.), browsing behavior, purchase decisions, and online shopping habits, and usage history. The similarities are determined in part by substantially real-time comparison of individual users with a set of predetermined user-based clusters formed from the experiences and behaviors of sample users. Users from a population may then be identified based on similarity metrics. Recommendations for new media items, or other goods/services, may also be made based on choices being made by similar users.

Growing community of inventors

Sammamish, WA, United States of America

Eugene Kalenkovich