Abstract: Methods and systems are disclosed herein for accurately training a machine learning model with a reduced training data set. A large number of data records may be parsed. Each record may be reduced to a set of symbols representing the composition of each record. A user may assign a classification to each symbol within each record. Records with identical arrangements and classifications of symbols may be grouped together, and a representative sample of data records from each group may be fed into the model as the reduced training data set.

Abstract: Systems and methods are provided herein for providing recommendations to a user. A short-media viewing profile may be maintained for the user. The short-media viewing profile may be based on user's behavior while watching short-length media content. A long-media viewing profile may be maintained for the user. The long-media viewing profile may be based on user's behavior while watching long-length media content. In response to determining that the user is currently engaged in viewing short-length media content, a recommendation is provided to the user based on the short-media viewing profile. In response to determining that the user is currently engaged in viewing long-length media content, a recommendation is provided to the user based on the long-media viewing profile.

Abstract: Methods and systems are described herein to recommend media assets to a user based on user location. A media guidance application may identify, using control circuitry, a user location. The media guidance application may generate a list of a plurality of media assets that match a user profile. The media guidance application may determine whether subject matter of a first media asset of the plurality of media assets is inconsistent with the user location. The media guidance application may remove the first media asset from the list in response to determining that the subject matter of the first media asset is inconsistent with the user location.

Abstract: Systems and methods are provided herein for providing recommendations to a user. A short-media viewing profile may be maintained for the user. The short-media viewing profile may be based on user's behavior while watching short-length media content. A long-media viewing profile may be maintained for the user. The long-media viewing profile may be based on user's behavior while watching long-length media content. In response to determining that the user is currently engaged in viewing short-length media content, a recommendation is provided to the user based on the short-media viewing profile. In response to determining that the user is currently engaged in viewing long-length media content, a recommendation is provided to the user based on the long-media viewing profile.

Abstract: Methods and systems are described herein to recommend media assets to a user based on user location. A media guidance application may identify, using control circuitry, a user location. The media guidance application may generate a list of a plurality of media assets that match a user profile. The media guidance application may determine whether subject matter of a first media asset of the plurality of media assets is inconsistent with the user location. The media guidance application may remove the first media asset from the list in response to determining that the subject matter of the first media asset is inconsistent with the user location.

Abstract: In some aspects, control circuitry receives and stores a user-specified time duration to associate with a skip-forward command. When the user later issues a skip-forward command to advance playback of a media asset to a desired location, the control circuitry retrieves the stored time duration, and determines an expected overshoot value associated with the skip-forward command. The control circuitry then compensates for the expected overshoot by calculating a new location in the media asset based on both the retrieved time duration and expected overshoot value. Upon advancing to the new location, the media asset is played back in a fast-forward mode, e.g., at a speed higher than normal speed.

Abstract: Systems and methods are provided herein for providing recommendations to a user. A short-media viewing profile may be maintained for the user. The short-media viewing profile may be based on user's behavior while watching short-length media content. A long-media viewing profile may be maintained for the user. The long-media viewing profile may be based on user's behavior while watching long-length media content. In response to determining that the user is currently engaged in viewing short-length media content, a recommendation is provided to the user based on the short-media viewing profile. In response to determining that the user is currently engaged in viewing long-length media content, a recommendation is provided to the user based on the long-media viewing profile.

Abstract: Methods and systems are described for responding to natural language queries. Specifically a natural language query is received and a query template that corresponds to the natural language query is determined. One or more search results corresponding to the natural language query are retrieved. One or more attributes associated with the user equipment device are identified and based on those attributes a first response template associated with an audio-only response to the natural language query, a second response template associated with a visual-only response to the natural language query, or a third response template associated with an audio-visual response to the natural language query is selected. A response to the natural language query is generated based on the selected response template and the retrieved one or more search results.

Abstract: Systems and methods are provided for generating for presentation information about an event on a device that is in a mode of operation that prevents presentation of information about events. This may be accomplished by a media guidance application that receives a command, on a user device associated with a first user, to place the user device in a do not disturb mode. The media guidance application receives, while the user device is in the do not disturb mode, information about an event and determines whether the event is relevant to the user. The media guidance application then determines whether the event is trending among a plurality of users associated with the user and, if trending, displays, while the user device is in the do not disturb mode, a notification about the event to the user on the user device.

Abstract: In some aspects, control circuitry receives and stores a user-specified time duration to associate with a skip-forward command. When the user later issues a skip-forward command to advance playback of a media asset to a desired location, the control circuitry retrieves the stored time duration, and determines an expected overshoot value associated with the skip-forward command. The control circuitry then compensates for the expected overshoot by calculating a new location in the media asset based on both the retrieved time duration and expected overshoot value. Upon advancing to the new location, the media asset is played back in a fast-forward mode, e.g., at a speed higher than normal speed.

Abstract: Systems and methods are provided for generating for presentation information about an event on a device that is in a mode of operation that prevents presentation of information about events. This may be accomplished by a media guidance application that receives a command, on a user device associated with a first user, to place the user device in a do not disturb mode. The media guidance application receives, while the user device is in the do not disturb mode, information about an event and determines whether the event is relevant to the user. The media guidance application then determines whether the event is trending among a plurality of users associated with the user and, if trending, displays, while the user device is in the do not disturb mode, a notification about the event to the user on the user device.

Abstract: The systems and methods disclosed herein combine a plurality of interpretations of a voice-based input. The systems and methods may receive the voice-based input, process it using one or more automatic speech recognition modules to obtain a plurality of interpretations, and identify an entity set for each of the plurality of interpretations. The systems and methods may further generate a combined interpretation based on a first interpretation and second interpretation selected form the plurality of interpretations and assign a semantic score to the combined interpretation based on the entity sets of the first and second interpretation.

Abstract: Systems and methods are described herein for controlling playback of a media asset using a touch screen. In some embodiments, a media guidance application may control media playback based on touch screen input positions that are stored before the user removes his finger from the touch screen. In some embodiments, the media guidance application may distinguish between intended touch screen inputs and jitter by analyzing the time it takes to perform a touch screen input, the speed/acceleration of an input, or the orientation of an input.

Abstract: Systems and methods are provided herein for providing recommendations to a user. A short-media viewing profile may be maintained for the user. The short-media viewing profile may be based on user's behavior while watching short-length media content. A long-media viewing profile may be maintained for the user. The long-media viewing profile may be based on user's behavior while watching long-length media content. In response to determining that the user is currently engaged in viewing short-length media content, a recommendation is provided to the user based on the short-media viewing profile. In response to determining that the user is currently engaged in viewing long-length media content, a recommendation is provided to the user based on the long-media viewing profile.

Abstract: Systems and methods are provided for generating for presentation information about an event on a device that is in a mode of operation that prevents presentation of information about events. This may be accomplished by a media guidance application that receives a command, on a user device associated with a first user, to place the user device in a do not disturb mode. The media guidance application receives, while the user device is in the do not disturb mode, information about an event and determines whether the event is relevant to the user. The media guidance application then determines whether to display a notification based on applications in use by members of the user's social group and displays, while the user device is in the do not disturb mode, a notification about the event to the user on the user device.

Abstract: Systems and methods are provided herein for recommending a pause position during a binge-watching session. A series containing multiple sequential episodes is provided to a user device. Then it is determined whether the user is engaged in binge-watching the series. If the user is binge-watching the series, a binge compulsion score is determined for each episode of the plurality of sequential episodes, where the binge compulsion score is based on how many additional sequential episodes an average user has watched after watching that episode. Then, in response to determining that the binge compulsion score of the next episode corresponds to a threshold, a prompt is generated for display, where the prompt includes a recommendation to the user to pause the series before the next episode begins.

Abstract: Systems and methods are described for managing local and cloud storage space for a plurality of media assets. The media guidance application may detect that a command was received to delete a first media asset from storage. In response to detecting the command, the media guidance application may determine a viewing pattern for the first media asset associated with a subset of users in a plurality of users, where the subset of users consumed the first media asset. The media guidance application may retrieve viewing commands associated with a second media asset performed by the subset of users, where the second media asset is related to the first media asset. The media guidance application may determine whether the viewing commands satisfy the viewing pattern. And in response to determining that the commands satisfy the viewing pattern, the media guidance application may delete the second media asset from storage.

Abstract: Systems and methods are provided herein for providing recommendations to a user. A short-media viewing profile may be maintained for the user. The short-media viewing profile may be based on user's behavior while watching short-length media content. A long-media viewing profile may be maintained for the user. The long-media viewing profile may be based on user's behavior while watching long-length media content. In response to determining that the user is currently engaged in viewing short-length media content, a recommendation is provided to the user based on the short-media viewing profile. In response to determining that the user is currently engaged in viewing long-length media content, a recommendation is provided to the user based on the long-media viewing profile.

Abstract: Systems and methods are provided for generating for presentation information about an event on a device that is in a mode of operation that prevents presentation of information about events. This may be accomplished by a media guidance application that receives a command, on a user device associated with a first user, to place the user device in a do not disturb mode. The media guidance application receives, while the user device is in the do not disturb mode, information about an event and determines whether the event is relevant to the user. The media guidance application then determines whether to display a notification based on applications in use by members of the user's social group and displays, while the user device is in the do not disturb mode, a notification about the event to the user on the user device.

Abstract: Systems and methods are provided for generating for presentation information about an event on a device that is in a mode of operation that prevents presentation of information about events. This may be accomplished by a media guidance application that receives a command, on a user device associated with a first user, to place the user device in a do not disturb mode. The media guidance application receives, while the user device is in the do not disturb mode, information about an event and determines whether the event is relevant to the user. The media guidance application then determines whether the event is trending among a plurality of users associated with the user and, if trending, displays, while the user device is in the do not disturb mode, a notification about the event to the user on the user device.