A radio tuning method for a vehicle includes sensing that the vehicle is traveling out of a terrestrial broadcast range of a radio station that a radio of the vehicle is currently tuned to. The radio station broadcasts first content. An internet location streaming second content that is substantially similar to the first content broadcasted by the radio station is identified. An estimated period of time remaining until the vehicle exits the terrestrial broadcast range of the first radio station is indicated to the user. A user of the vehicle is provided with an option to switch tuning of the radio from the radio station to the internet location that is streaming the second content.

A radio tuning method for a vehicle includes sensing that the vehicle is traveling out of a terrestrial broadcast range of a radio station that a radio of the vehicle is currently tuned to. The radio station broadcasts first content. An internet location streaming second content that is substantially similar to the first content broadcasted by the radio station is identified. An estimated period of time remaining until the vehicle exits the terrestrial broadcast range of the first radio station is indicated to the user. A user of the vehicle is provided with an option to switch tuning of the radio from the radio station to the internet location that is streaming the second content.

Provided are an artificial intelligence (AI) system that simulates functions of a human brain such as recognition and judgment by utilizing a machine learning algorithm such as deep learning, etc. and an application of the AI system. A computing apparatus is disclosed. A computing apparatus comprises a memory storing instructions and a processor executing the instructions in the memory to obtain a keyword corresponding to a broadcast channel from a speech signal included in a broadcast signal received through the broadcast channel, determine a relation between genre information of the broadcast channel obtained from metadata about the broadcast channel and the obtained keyword and determine a genre of the broadcast channel based on the genre information obtained from the metadata or by analyzing an image signal included in the broadcast signal, according to the determined relation.

A display device for providing a speech recognition service according to an embodiment of the present disclosure can include a storage unit configured to store a user's viewing history, a display unit, and a control unit configured to acquire a plurality of recommended utterance words based on the stored viewing history information, receive a command for requesting the speech recognition service, and display the plurality of acquired recommended utterance words on the display unit according to the received command.

A system and method for determining a similarity measure between a first network broadcast time segment and a second network broadcast time segment. The method includes generating first training data comprising groupings of similar broadcast networks and groupings of dissimilar broadcast networks, extracting second training data comprising audience data and genre data for time segments of network broadcasts, and training an encoder neural network based on the first and second training data. The method includes executing the trained neural network with input data comprising the first network broadcast time segment and determining a similarity measure relative to the second network broadcast time segment.

A customized programming content creation system is disclosed. According to one embodiment, a media content search engine locates and retrieves media segments, and a storage component stores a user location indicator. A processor accesses scheduling information data structures for the media segments, and filters the media segments to generate a set of current local media segments. The filtering is based on a comparison of a user-associated location value with a geography value from the scheduling information data structure, and a comparison of a current time value with an expiration value from the scheduling information data structure. The set of current local media segments includes at least one local weather segment. The media segments are also filtered to identify at least one current news media segment. An integrated video stream is assembled. The stream is then transmitted for presentation on a user device of the user.

A method for use in an automated media scheduling system includes generating a shots representing potential playlists of media items. Each of the shots includes multiple shot positions. A shot-position-dependent score of a current content item being considered for insertion into a particular shot position of a particular shot is generated, and indicates how closely the current content item conforms to a predetermined set of factors associated with the particular shot position of the particular shot. The current content item is inserted into the particular shot position of the particular shot based, at least in part on a comparison of the shot-position-dependent score of the current content item with shot-position-dependent scores of other content items, and the shot positions of each of the shots are populated with eligible content items. One of the shots is selected for scheduling based on aggregate scores of eligible content associated with each individual shot.

A consumption probability metric may be generated for a media asset. An aggregated forecast predicting user consumption of a media asset is received. A plurality of probabilities, each corresponding to a user of a plurality of users, is received, each indicating how likely a respective user is to consume the media asset. A weight for the plurality of users is calculated representing a ratio of the total number of users to a number of users in the plurality of users. A disaggregated forecast predicting user consumption of a media asset is determined based on the weight for the plurality of users and the plurality of probabilities. A modification factor is computed based on the aggregated forecast and the disaggregated forecast. A metric is generated that includes a plurality of user identifiers associated with the plurality of users and a plurality of modified probabilities each modified by the modification factor.

A consumption probability metric may be generated for a media asset. An aggregated forecast predicting user consumption of a media asset is received. A plurality of probabilities, each corresponding to a user of a plurality of users, is received, each indicating how likely a respective user is to consume the media asset. A weight for the plurality of users is calculated representing a ratio of the total number of users to a number of users in the plurality of users. A disaggregated forecast predicting user consumption of a media asset is determined based on the weight for the plurality of users and the plurality of probabilities. A modification factor is computed based on the aggregated forecast and the disaggregated forecast. A metric is generated that includes a plurality of user identifiers associated with the plurality of users and a plurality of modified probabilities each modified by the modification factor.

Implementing and applying a database with radio station information that is gathered from client devices as stations become available to a plurality of users (i.e., “crowd sourced” radio station information) and allowing for a client device to download only the radio station information that is pertinent to the travel route of the user and/or radio station selection criteria associated with the client device or the user. Radio station information can be rendered via a graphical interface of a client device to allow the user to informatively select a new radio station, either before or as a current radio signal degrades to the point of being unusable. Radio station information may be rendered to cause the user's terrestrial radio to tune to a new station.