Abstract: A content management computing device for managing voice-interactive online content includes a memory for storing data and a processor in communication with the memory. The processor is programmed to retrieve an online content item including content metadata, identify at least one voice interaction associated with the content metadata, serve the online content item to a user computing device, wherein serving the online content item further comprises instructing the user computing device to collect voice response data that is responsive to at least one voice interaction, receive the voice response data from the user computing device, identify a user request based on the voice response data, and transmit a response, based on the user request, to a user account.

Abstract: Methods and apparatus related to providing user-guided term suggestions. Some implementations may be directed to identifying user input that includes at least one term and identifying a user-initiated activity near the term. An edit term may be identified based on the user-initiated activity near the term, an edit position in the edit term may be identified, and one or more candidate terms may be identified based on the edit term. Similarity measures for the candidate terms may be determined. The similarity measure of a given candidate term of the candidate terms may be based on the edit position. One or more of the candidate terms may be selected as suggested terms based on the similarity measures and the selected suggested terms provided for potential replacement of the edit term.

Abstract: A content management computing device for managing voice-interactive online content includes a memory for storing data and a processor in communication with the memory. The processor is programmed to retrieve an online content item including content metadata, identify at least one voice interaction associated with the content metadata, serve the online content item to a user computing device, wherein serving the online content item further comprises instructing the user computing device to collect voice response data that is responsive to at least one voice interaction, receive the voice response data from the user computing device, identify a user request based on the voice response data, and transmit a response, based on the user request, to a user account.

Abstract: Techniques for summarizing media are described. A viewer-interaction analyzer receives a media file containing media, the media file including a plurality of segments. A segment of the media file is scored based on interactions of a set of raters. Viewer metrics on the segment of the media file are measured based on interactions with the segment of the media file by a set of viewers. A set of feature vectors are formed based on the measured viewer interactions, where feature vectors in the set of feature vectors are based on interactions of the set of viewers. A model is trained based on the set of feature vectors and the score assigned to the segment of the media file. The model is applied to segments of the media file to generate an interest rating for segments of the media file. An edited media file is generated based on segments of the media file having interest ratings that meet a criterion.

Abstract: In general, this disclosure is directed to techniques for generating, by a computing device, at approximately a time that a user is eating, at least one computer-generated indication. Based at least in part on the at least one computer-generated indication and pre-defined activity data that are indicative of a human consuming an ingestible substance, the computing device determines whether the user is currently consuming an ingestible substance. Responsive to determining that the user is currently consuming the ingestible substance, the computing device outputs a reminder to consume at least one particular ingestible substance, such as a medication.

Abstract: Methods and apparatus related to providing user-guided term suggestions. Some implementations may be directed to identifying user input that includes at least one term and identifying a user-initiated activity near the term. An edit term may be identified based on the user-initiated activity near the term, an edit position in the edit term may be identified, and one or more candidate terms may be identified based on the edit term. Similarity measures for the candidate terms may be determined. The similarity measure of a given candidate term of the candidate terms may be based on the edit position. One or more of the candidate terms may be selected as suggested terms based on the similarity measures and the selected suggested terms provided for potential replacement of the edit term.

Abstract: Techniques for summarizing media are described. A viewer-interaction analyzer receives a media file containing media, the media file including a plurality of segments. A segment of the media file is scored based on interactions of a set of raters. Viewer metrics on the segment of the media file are measured based on interactions with the segment of the media file by a set of viewers. A set of feature vectors are formed based on the measured viewer interactions, where feature vectors in the set of feature vectors are based on interactions of the set of viewers. A model is trained based on the set of feature vectors and the score assigned to the segment of the media file. The model is applied to segments of the media file to generate an interest rating for segments of the media file. An edited media file is generated based on segments of the media file having interest ratings that meet a criterion.

Abstract: Techniques for summarizing media are described. A viewer-interaction analyzer receives a media file containing media, the media file including a plurality of segments. A segment of the media file is scored based on interactions of a set of raters. Viewer metrics on the segment of the media file are measured based on interactions with the segment of the media file by a set of viewers. A set of feature vectors are formed based on the measured viewer interactions, where feature vectors in the set of feature vectors are based on interactions of the set of viewers. A model is trained based on the set of feature vectors and the score assigned to the segment of the media file. The model is applied to segments of the media file to generate an interest rating for segments of the media file. An edited media file is generated based on segments of the media file having interest ratings that meet a criterion.

Abstract: A content management computing device for managing voice-interactive online content includes a memory for storing data and a processor in communication with the memory. The processor is programmed to retrieve an online content item including content metadata, identify at least one voice interaction associated with the content metadata, serve the online content item to a user computing device, wherein serving the online content item further comprises instructing the user computing device to collect voice response data that is responsive to at least one voice interaction, receive the voice response data from the user computing device, identify a user request based on the voice response data, and transmit a response, based on the user request, to a user account.

Abstract: In general, this disclosure is directed to techniques for generating, by a computing device, at approximately a time that a user is eating, at least one computer-generated indication. Based at least in part on the at least one computer-generated indication and pre-defined activity data that are indicative of a human consuming an ingestible substance, the computing device determines whether the user is currently consuming an ingestible substance. Responsive to determining that the user is currently consuming the ingestible substance, the computing device outputs a reminder to consume at least one particular ingestible substance, such as a medication.

Abstract: A device is configured to receive a translation query that requests a translation of terms from a source language to a target language; determine translation features associated with the translation query; assign a feature value to each of the translation features to form feature values; apply a feature weight to each of the feature values to generate a final value; and determine whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the final value satisfies a threshold. The dialog translation user interface may facilitate translation of a conversation, the non-dialog translation user interface may provide translation search results, and the non-dialog translation user interface may be different than the dialog translation user interface. The device also configured to provide the dialog translation user interface for display when the final value satisfies the threshold.

Abstract: A method includes receiving, at an email service implemented by one or more server computers, an email message addressed to a user from a seller; and outputting, for display at a client computing device associated with the user, an email interface screen having a user operable interface element for ordering goods or services that are described in the email message. The method also includes receiving, at the email service, information indicating operation of the user operable interface element; and in response to receiving the information indicating operation of the user operable interface transmitting a purchase request relating to the goods or services.

Abstract: Systems and methods for recommending an outdoor activity geographic location are provided. In some aspects, multiple data items that are associated with a recurring time period and a destination geographic location are selected from one or more data repositories. That an outdoor activity for the user is available in the destination geographic location during the recurring time period is determined using information in the selected multiple data items and at least one characteristic of a user of a client computing device. An indication that the outdoor activity is available in the destination geographic location is provided to the client computing device.

Abstract: In one aspect, a method for automatically adjusting temporal creation data for a plurality of images is disclosed. The method may generally include receiving a plurality of image files associated with the plurality of images, wherein each of the plurality of image files includes an initial creation time. In addition, the method may include determining a baseline creation time by analyzing the plurality of image files based on their association with at least one of daytime hours or nighttime hours and adjusting the initial creation time for at least one of the plurality of image files based on the baseline creation time.

Abstract: A system and method for suggesting alternative travel destinations is disclosed. In one embodiment, the method may generally include receiving, at a computing device, a query from a client device associated with a requested travel destination. The requested travel destination may be at a first geographic location. The method may also include analyzing travel pattern data for at least one user that previously requested travel directions to the requested travel destination to identify at least one second geographic location that is associated with the requested travel destination. The travel pattern data may include information associated with a location of the at least one user after requesting the travel directions. In addition, the method may include transmitting to the client device a suggestion for at least one alternative travel destination based on the at least one second geographic location.

Abstract: A device is configured to receive a translation query that requests a translation of terms from a source language to a target language; determine translation features associated with the translation query; assign a feature value to each of the translation features to form feature values; apply a feature weight to each of the feature values to generate a final value; and determine whether to provide a dialog translation user interface or a non-dialog translation user interface based on whether the final value satisfies a threshold. The dialog translation user interface may facilitate translation of a conversation, the non-dialog translation user interface may provide translation search results, and the non-dialog translation user interface may be different than the dialog translation user interface. The device also configured to provide the dialog translation user interface for display when the final value satisfies the threshold.

Abstract: Systems and methods are described herein for comparing products in a marketplace. An image or video of the products may be captured using a camera associated with a mobile device. User input may be received to select two or more products within the image. Machine vision techniques may be applied to specifically identify the selected products. Product features associated with each of the identified products may be retrieved and formatted into a comparison of product features. The comparison may be presented to the user.

Abstract: Techniques for summarizing media are described. A viewer-interaction analyzer receives a media file containing media, the media file including a plurality of segments. A segment of the media file is scored based on interactions of a set of raters. Viewer metrics on the segment of the media file are measured based on interactions with the segment of the media file by a set of viewers. A set of feature vectors are formed based on the measured viewer interactions, where feature vectors in the set of feature vectors are based on interactions of the set of viewers. A model is trained based on the set of feature vectors and the score assigned to the segment of the media file. The model is applied to segments of the media file to generate an interest rating for segments of the media file. An edited media file is generated based on segments of the media file having interest ratings that meet a criterion.