Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: A computer-implemented method includes receiving an indication that an order scheduled for later pickup is to be picked up earlier than scheduled. A plurality of robots that are holding items that form at least part of the order are then identified and instructed to move immediately to a pickup location and to make the items of the order held by the plurality of robots available for retrieval from the plurality of robots.

Abstract: A computer-implemented method includes identifying which retail items in a set of retail items have erroneous on-hands values stored in a database and removing the identified retail items from the set of retail items to form a sub-set of retail items. A nominal sales floor capacity stored in the database for the retail items in the sub-set of retail items are evaluated without evaluating the nominal sales floor capacity of the identified retail items. The nominal sales floor capacity stored in the database for at least one retail item is corrected based on evaluating the nominal sales floor capacity stored in the database.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: A computer-implemented method includes receiving an indication that an order scheduled for later pickup is to be picked up earlier than scheduled. A plurality of robots that are holding items that form at least part of the order are then identified and instructed to move immediately to a pickup location and to make the items of the order held by the plurality of robots available for retrieval from the plurality of robots.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: A computer-implemented method includes identifying which retail items in a set of retail items have erroneous on-hands values stored in a database and removing the identified retail items from the set of retail items to form a sub-set of retail items. A nominal sales floor capacity stored in the database for the retail items in the sub-set of retail items are evaluated without evaluating the nominal sales floor capacity of the identified retail items. The nominal sales floor capacity stored in the database for at least one retail item is corrected based on evaluating the nominal sales floor capacity stored in the database.

Abstract: Digital graphic novel content is received and features of the graphic novel content are identified. At least one of the identified features includes text. Contextual information corresponding to the feature or features that include text is generated based on the identified features. The contextual information is used to aid translation of the text included in the feature or features that include text.

Abstract: Digital graphic novel content is received and features of the graphic novel content are identified. At least one of the identified features includes text. Contextual information corresponding to the feature or features that include text is generated based on the identified features. The contextual information is used to aid translation of the text included in the feature or features that include text.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: Locations and presentation orders of objects of interest (e.g., speech bubbles) in digital graphic novel content are identified such that expanded versions of the objects of interest can be presented to a reader. Specifically, digital graphic novel content is received and locations of interest regions (e.g., rectangular text regions of speech bubbles) in the content are identified by applying a machine-learned model to the content. Locations and presentation orders of objects of interest in the digital graphic novel content are identified based on the identified locations of the interest regions. The digital graphic novel content and presentation metadata including the locations and presentation orders of the objects of interest are provided to a reading device such that expanded versions of the objects of interest are presented to the user in accordance with the presentation metadata.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: Digital graphic novel content is received and a machine-learning model applied to predict features of the digital graphic novel content. The predicted features include locations of a plurality of panels and a reading order of the plurality of panels. A packaged digital graphic novel is created that includes the digital graphic novel content and presentation metadata. The presentation metadata indicates a manner in which the digital graphic novel content should be presented based on the locations and reading order of the plurality of panels. The packaged digital graphic novel is provided to a reading device to be presented in accordance with the manner indicated in the presentation metadata.

Abstract: Digital graphic novel content is received and features of the graphic novel content are identified. At least one of the identified features includes text. Contextual information corresponding to the feature or features that include text is generated based on the identified features. The contextual information is used to aid translation of the text included in the feature or features that include text.

Abstract: A first method includes, at a server, receiving a new message in a message thread, identifying quoted text (e.g., text from a previous message in the message thread) in the new message, replacing the quoted text with a token that includes information uniquely associated with the previous message to produce a modified incoming message, and sending the modified incoming message to a client. Optionally, the token includes information identifying the previous message in the message thread. Optionally, the token identifies a range of text in the previous message, and the text replaced by the token corresponds to the range of text in the previous message identified by the token. Optionally, the token comprises a tag having text to be displayed by the client. In some embodiments, the method includes sending to the client all messages in the message thread, including the modified incoming message.

Abstract: Methods and systems for automatically downloading and storing media on a mobile device are provided. A method at a mobile device includes an auto-storing process, which includes receiving, at a first time within a predefined time range, a first set of media items. The first set of media items may be based on a user media preference. Next, at a second time within the predefined time range, it may be determined that at least a portion of the first set of media items has been activated. Based on the activated media items, at least one user media activation characteristic may be determined. In response to determining that at least a portion of the first set of media items has been activated, a second set of media items based on the user media activation characteristic may be received.

Abstract: Systems and methods for priority inbox notifications and synchronization are disclosed. In some embodiments, a method includes, at a computer system, obtaining message information from a server system. The message information represents a set of messages and an importance score associated with each message in the set of messages. The importance score is generated based at least in part on a global importance prediction model and a user importance prediction model. A new mail notification is presented when a determination is made that the set of messages include one or more unread priority messages. The priority messages comprise messages with which the associated importance score satisfy one or more predefined message importance criteria: Optionally, presentation of a new mail notification is foregone when there is a determination that the set of messages do not include any unread priority messages.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving geographical information derived from a non-verbal user action associated with a first computing device. The non-verbal user action implies an interest of a user in a geographic location. The method also includes identifying a grammar associated with the geographic location using the derived geographical information and outputting a grammar indicator for use in selecting the identified grammar for voice recognition processing of vocal input from the user.