Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

Systems, methods and computer program products that facilitate dynamic playlist priority in a vehicle based upon user preferences and context. According to an embodiment, a system comprises a processor that executes computer executable components stored in at least one memory, a compilation component that receives content in a vehicle, an assessment component that respectively classifies subsets of the content, a ranking component that ranks relevancy of the classified subsets of content based upon preferences and context of a user in the vehicle, a content playback component that plays the subsets of classified content based upon relevancy ranking, a prioritization component that dynamically prioritizes a first subset of the content based upon the context of the user or context of a sender of the first subset of content, wherein the first subset of content comprises extrinsic data, and an interrupt component that interrupts playback of the subsets of classified content based upon the dynamic prioritization.

Techniques for facilitating reservations between a first creative entity and a first venue. Digital audio data for a first creative entity is analyzed to determine acoustic attributes. A plurality of potential venues are determined. A machine learning model is used to calculate an estimated demand metric for the first creative entity for each of the plurality of potential venues, based on a venue profile for the respective venue and acoustic attributes for the first creative entity. Two or more venues are selected and a proposed itinerary is created. A digital order is generated based on the proposed itinerary. User profile data for the first creative entity is updated, upon successful completion of the digital order, and a digital transaction is generated to automatically charge a determined first amount to an account for the first venue and to transfer a determined second amount to an account for the first creative entity.

Various embodiments set forth systems and techniques for enabling audio personalization. The techniques include determining audio personalization settings for an audio category, determining one or more audio properties of an audio track, selecting, based on the one or more audio properties, a first portion of the audio track that is representative of the audio category, playing the first portion of the audio track for a user, and adjusting, based on input from the user, a personalization setting for the user when playing back the first portion of the audio track.

Example techniques involve playback of curated playlists based on media preferences. In an example implementation, a playback device receives data representing one or more instructions to play back a particular curated playlist of a streaming audio service and, in response, plays back audio tracks of the particular curated playlist. During playback, when a preference database includes a negative preference for a given audio track, the playback device skips that audio track.

Embodiments described herein involve providing media item preferences according to a user account of a user providing the preference, rather than a user account providing the media item. When a user indicates a preference for a media item, the preference are associated with that particular user, rather than with another user whose account the media item may have been accessed and played through when the particular user indicated the preference. As a result, a media preference history associated with the account providing the media item will not be disrupted by other users indicating preferences for the media item. Further, users may build on their respective media preference histories even when listening to music provided by someone else.

Aspects of the technology described herein use acoustic features of a music track to capture information for a recommendation system. The recommendation can work without analyzing label data (e.g., genre, artist) or usage data for a track. For each audio track, a descriptor is generated that can be used to compare the track to other tracks. The comparisons between track descriptors result in a similarity measure that can be used to make a recommendation. In this process, the audio descriptors are used directly to form a track-to-track similarity measure between tracks. By measuring the similarity between a track that a user is known to like and an unknown track, a decision can be made whether to recommend the unknown track to the user.

A system and its corresponding method are provided for recommending media based on emotion-related feedback from a user. In one example of the system and its corresponding method, songs are assigned to a queue according to objective criteria for achieving desired emotions with the user. Songs may also be assigned to the queue based on documented similarities between various user personality profiles.

Provided is a search system which is configured to search for a registered vector being similar to an input vector among a plurality of registered vectors, on the basis of a degree of similarity between an input vector and a registered vector. The search system includes a partial similarity calculation unit that calculates a degree of partial similarity which is the degree of similarity concerning some of one or more dimensions of the input vector and the registered vector, a limit calculation unit that calculates, on the basis of the degree of partial similarity, an upper limit of the degree of similarity that is expected when the degree of similarity is calculated, and a rejection decision unit that decides, on the basis of the upper limit of the degree of similarity, whether or not to reject the registered vector from a candidate for a search result.

A network server includes a communicator connected to a network; and at least one processor configured to communicate, through the communicator, with a user terminal connected to the network. The processor is configured to include or associate content IDs, determined according to one or more requests from the user terminal, in or with a playlist, the content IDs corresponding to content files, respectively, stored in a database; reflect actions of the user terminal, associated with one or more of the content files, on log data sets corresponding to the content IDs; and determine one or more of the content IDs as one or more target IDs to be selectively deleted or excluded from the playlist, on the basis of the log data sets.