Abstract: Techniques for optimizing a system to improve an overall user satisfaction in a speech controlled system are described. A user speaks an utterance and the system compares an expected sum of user satisfaction values for each action to make a decision as to how best to process the utterance. As a result, the system may make a decision that decreases user satisfaction in the short term but increases user satisfaction in the long term. The system may estimate a user satisfaction value and associate the estimated user satisfaction value with a current dialog state. By tracking user satisfaction values over time, the system may train machine learning models to optimize the expected sum of user satisfaction values. This improves how the system selects an action or application to which to dispatch the dialog state and how a specific application selects an action or intent corresponding to the command.

Abstract: Techniques for optimizing a system to improve an overall user satisfaction in a speech controlled system are described. A user speaks an utterance and the system compares an expected sum of user satisfaction values for each action to make a decision as to how best to process the utterance. As a result, the system may make a decision that decreases user satisfaction in the short term but increases user satisfaction in the long term. The system may estimate a user satisfaction value and associate the estimated user satisfaction value with a current dialog state. By tracking user satisfaction values over time, the system may train machine learning models to optimize the expected sum of user satisfaction values. This improves how the system selects an action or application to which to dispatch the dialog state and how a specific application selects an action or intent corresponding to the command.

Abstract: Provided are systems and methods for receiving a plurality of item submissions from a plurality of mobile user devices (each item submission of the plurality of item submissions including: item identifier data indicative of an item; and item location data indicative of a location of the item), determining a determined location for the item (using the respective item location data for each of the plurality of item submissions), and storing the determined location for the item in an item location database. The determined location for the item is stored in association with an item identifier corresponding to the item, and the item location database stores determined locations for a plurality of items.

Abstract: Techniques for optimizing a system to improve an overall user satisfaction in a speech controlled system are described. A user speaks an utterance and the system compares an expected sum of user satisfaction values for each action to make a decision as to how best to process the utterance. As a result, the system may make a decision that decreases user satisfaction in the short term but increases user satisfaction in the long term. The system may estimate a user satisfaction value and associate the estimated user satisfaction value with a current dialog state. By tracking user satisfaction values over time, the system may train machine learning models to optimize the expected sum of user satisfaction values. This improves how the system selects an action or application to which to dispatch the dialog state and how a specific application selects an action or intent corresponding to the command.

Abstract: Features are disclosed for processing user queries into a form that can produce relevant results. Spoken user queries can be transcribed into textual queries. Textual queries can be processed using a statistical model to identify entities within the queries. Running searches using the entities rather than the original search query can produce relevant results even when no result would have been obtained by running the original search query. In some embodiments, attributes may be identified and used during the search to narrow the results and potentially produce results that are more relevant.

Abstract: A system that configures a device's operation based on the device's environment. The system may receive scene data describing a scene in which the device will operate. The scene data may include image data, audio data, or other data. A feature vector comprising the scene data may be processed to identify one or more categories to be associated with the scene. Various processing techniques, such as using Bayesian nonparametric models, may be used to categorize the scene data. The device may then adjust its operation based on the one or more selected categories.

Abstract: A content delivery system, such as an on-demand movie catalog, is configured to customize previews of content based on previously determined user preferences and metadata associated with the content. A user may select a particular item of content, such as a movie, and the system will dynamically create a short preview of the movie including portions of the movie that are likely to appeal to the user, such as scenes featuring certain actors, themes, locales, etc. The selection of scenes is compiled by cross-referencing the user preferences with metadata and other information associated with the movie and the content of specific scenes. The preview may also be compiled using components and methods configured to create a preview that both includes content desirable to the viewing user, but also content that can be combined to create a logical preview.