The present disclosure relates to a method of providing media to a user based on analysis of an image. The method comprises analysing the image to obtain image information about what is depicted therein. The method also comprises, based on said obtained image information, selecting a first plurality of media items comprising audio, from a media database, said media items of the first plurality being associated with that which is depicted in the image according to the image information. The method also comprises filtering the first plurality of media items based on metadata associated with the user to obtain a plurality of seed media items. The method also comprises providing at least one media item from the media database to the user based on the obtained seed media items.

Systems and methods for responding to a subscriber's text-based request for content items are presented. In response to a request from a subscriber, word pieces are generated from the text-based terms of the request. A request embedding vector of the word pieces is obtained from a trained machine learning model. Using the request embedding vector, a set of content items, from a corpus of content items, is identified. At least some content items of the set of content items are returned to the subscriber in response to the text-based request for content items.

Systems and methods for responding to a subscriber's text-based request for content items are presented. In response to a request from a subscriber, word pieces are generated from the text-based terms of the request. A request embedding vector of the word pieces is obtained from a trained machine learning model. Using the request embedding vector, a set of content items, from a corpus of content items, is identified. At least some content items of the set of content items are returned to the subscriber in response to the text-based request for content items.

The described technology is directed towards data-driven navigation, in which a next navigation location depends on variable data associated with an interactive user interface element (rather than a fixed link). The data may be in a hierarchy of data models. A menu contains interactive navigation elements, each bound to a data model. A selected interactive navigation element results in locating a data model associated with the selected element. The data model is used to determine the next navigation location. Also described is hierarchical navigation to one item of a level as well as lateral and peer navigation.

A client electronic device to provide custom functionality for video content playback. The client electronic device includes one or more processors and a non-transitory computer-readable medium having stored therein instructions, which when executed by the one or more processors, causes the client electronic device to receive a streaming manifest file and a first auxiliary manifest file, where the streaming manifest file includes references to video segments of a video content, where the first auxiliary manifest file includes timed metadata associated with the video content, where the streaming manifest file and the first auxiliary manifest file refer to a same timeline, provide the streaming manifest file to a core playback module to play the video content according to the streaming manifest file, and provide custom functionality using the timed metadata included in the first auxiliary manifest file that replaces or augments functionality provided by the core playback module.

A client electronic device to provide custom functionality for video content playback. The client electronic device includes one or more processors and a non-transitory computer-readable medium having stored therein instructions, which when executed by the one or more processors, causes the client electronic device to receive a streaming manifest file and a first auxiliary manifest file, where the streaming manifest file includes references to video segments of a video content, where the first auxiliary manifest file includes timed metadata associated with the video content, where the streaming manifest file and the first auxiliary manifest file refer to a same timeline, provide the streaming manifest file to a core playback module to play the video content according to the streaming manifest file, and provide custom functionality using the timed metadata included in the first auxiliary manifest file that replaces or augments functionality provided by the core playback module.

A method includes receiving media content comprising audio data for distribution through content distribution platform that requires the media content to include video content, transforming the audio data into textual content, determining, based on a search of a searchable database, that the textual content of the audio data matches characteristics of visual data in the searchable database, integrating the visual data having the matched characteristics with the media content to create an augmented content stream in response to the determination that the textual content of the audio data matches the characteristics of the visual data, and distributing the augmented content stream through the content distribution platform that requires the media content to include video content.

A method includes receiving media content comprising audio data for distribution through content distribution platform that requires the media content to include video content, transforming the audio data into textual content, determining, based on a search of a searchable database, that the textual content of the audio data matches characteristics of visual data in the searchable database, integrating the visual data having the matched characteristics with the media content to create an augmented content stream in response to the determination that the textual content of the audio data matches the characteristics of the visual data, and distributing the augmented content stream through the content distribution platform that requires the media content to include video content.

The present disclosure relates to generating a complex entity index based on a combination of atomic and deep learned attributes associated with instances of a complex entity. For example, systems described herein generate a multi-dimensional representation of entity instances based on evaluation of digital content associated with the respective entity instances. Systems described herein further generate an index representation in which similarity of entity instances are illustrated and presented via an interactive presentation that enables a user to traverse instances of an entity to observe similarities and differences between instances of an entity that have similar embeddings to one another within a multi-dimensional index space.

The present disclosure relates to generating a complex entity index based on a combination of atomic and deep learned attributes associated with instances of a complex entity. For example, systems described herein generate a multi-dimensional representation of entity instances based on evaluation of digital content associated with the respective entity instances. Systems described herein further generate an index representation in which similarity of entity instances are illustrated and presented via an interactive presentation that enables a user to traverse instances of an entity to observe similarities and differences between instances of an entity that have similar embeddings to one another within a multi-dimensional index space.