Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Abstract: 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.

Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: 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.

Abstract: The disclosure herein describes a recommendation system utilizing a specialized domain-specific language model for generating cold-start recommendations in an absence of user-specific data based on a user-selection of a seed item. A generalized language model is trained using a domain-specific corpus of training data, including title and description pairs associated with candidate items in a domain-specific catalog. The language model is trained to distinguish between real title-description pairs and fake title-description pairs. The trained language model analyzes the title and description of the seed item with the title and description of each candidate item in the catalog to create a hybrid set of scores. The set of scores includes similarity scores and classification scores for the seed item title with each candidate item description and title. The scores are utilized by the model to identify candidate items maximizing similarity with the seed item for cold-start recommendation to a user.

Abstract: A recommender system that represents items in a catalog by first feature vectors in a first vector space based on first characteristics of the items and second feature vectors in a second vector space based on second characteristics of the items different from the first characteristics and maps a feature vector defined in the first vector space for an item to a vector in the second vector space to provide recommendations based on the item.

Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Abstract: Computerized searching for an item based on a prior viewed item. A displayed item is identified as a query input item to be used in searching for a target item. That input item has an associated set of embedding vectors each representing a respective feature of the input item. Target features of the search are then identified based on the input item. For each feature in the target item that is desired to be the same as the input item, an embedding vector for the input item is accessed as the vector for that feature in the search. For each feature in the target item that is desired to be different than the input item, a special vector associated with that desired value and feature is accessed for that feature in the search. These accessed vectors are then compared against target items to find close matches.

Abstract: The disclosure herein describes a recommendation system utilizing a specialized domain-specific language model for generating cold-start recommendations in an absence of user-specific data based on a user-selection of a seed item. A generalized language model is trained using a domain-specific corpus of training data, including title and description pairs associated with candidate items in a domain-specific catalog. The language model is trained to distinguish between real title-description pairs and fake title-description pairs. The trained language model analyzes the title and description of the seed item with the title and description of each candidate item in the catalog to create a hybrid set of scores. The set of scores includes similarity scores and classification scores for the seed item title with each candidate item description and title. The scores are utilized by the model to identify candidate items maximizing similarity with the seed item for cold-start recommendation to a user.

Abstract: The disclosed distributed task coordination ensures task execution while minimizing both the risk of duplicate execution and resources consumed for coordination. Execution is guaranteed, while only best efforts are used to avoid duplication. Example solutions include requesting, by a node, a first lease from a first set of nodes; based at least on obtaining at least one first lease, requesting, by the node, a second lease from a second set of nodes; based at least on the node obtaining at least one second lease, determining a majority holder of second leases; and based at least on obtaining the majority of second leases, executing, by the node, a task associated with the at least one second lease. In some examples, the nodes comprise online processing units (NPUs). In some examples, if a first node begins executing the task and fails, another node automatically takes over to ensure completion.

Abstract: In one embodiment, an audio signal for an audio track is received and segmented into a plurality of segments of the audio signal. The plurality of segments of audio are input into a classification network that is configured to predict output values based on a plurality of genre and mood combinations formed from different combinations of a plurality of genres and a plurality of moods. The classification network predicts a set of output values for the plurality of segments, each of the set of output values corresponding to one or more the plurality of genre and mood combinations. One or more of the plurality of genre and mood combinations are assigned to the audio track based on the set of output values for one or more of the plurality of segments.

Abstract: Embodiments of the invention provide methods and apparatus for recommending items from a catalog of items to a user by parsing the catalog of items into a plurality of catalog clusters of related items and recommending catalog items to the user from catalog clusters to which items previously preferred by the user belong.

Abstract: A data set may be distributed over many data stores, and a query may be distributively evaluated by several data stores with the results combined to form a query result (e.g., utilizing a MapReduce framework). However, such architectures may violate security principles by performing sophisticated processing, including the execution of arbitrary code, on the same machines that store the data. Instead of processing queries, a data store may be configured only to receive requests specifying one or more filtering criteria, and to provide the data items satisfying the filtering criteria. A compute node may apply a query by generating a request including one o more filter criteria, providing the request to a data node, and applying the remainder of the query (including sophisticated processing, and potentially the execution of arbitrary code) to the data items provided by the data node, thereby improving the security and efficiency of query processing.

Abstract: Aspects of the subject matter described herein relate to a simplified login for mobile devices. In aspects, on a first logon, a mobile device asks a user to enter credentials and a PIN. The credentials and PIN are sent to a server which validates user credentials. If the user credentials are valid, the server encrypts data that includes at least the user credentials and the PIN and sends the encrypted data to the mobile device. In subsequent logons, the user may logon using only the PIN. During login, the mobile device sends the PIN in conjunction with the encrypted data. The server can then decrypt the data and compare the received PIN with the decrypted PIN. If the PINs are equal, the server may grant access to a resource according to the credentials.

Abstract: A data set may be distributed over many data stores, and a query may be distributively evaluated by several data stores with the results combined to form a query result (e.g., utilizing a MapReduce framework). However, such architectures may violate security principles by performing sophisticated processing, including the execution of arbitrary code, on the same machines that store the data. Instead of processing queries, a data store may be configured only to receive requests specifying one or more filtering criteria, and to provide the data items satisfying the filtering criteria. A compute node may apply a query by generating a request including one or more filter criteria, providing the request to a data node, and applying the remainder of the query (including sophisticated processing, and potentially the execution of arbitrary code) to the data items provided by the data node, thereby improving the security and efficiency of query processing.

Abstract: Embodiments of the present invention relate to systems, methods, and computer-storage media for maintaining privacy while delivering advertisements based on encrypted user profile identifiers. In embodiments, a Public key Encryption with Keyword Search (PEKS) is used to generate a public key and a private key. In embodiments, a public key and a private key are used to encrypt user profile identifiers and generate trapdoors associated with defined profile identifiers, respectively. A portion of the encrypted user profile identifiers are compared to a portion of the trapdoors. If a match is present between at least one encrypted user profile identifier and an associated trapdoor, a delivery engine is provided with an identification of content to be delivered to the user. The provided description is then used to determine an advertisement to present to a user. The advertisement is then presented to the user.

Abstract: A playlist generator that utilizes multiple data sources to rank each track within a set of candidate tracks to enable selection of candidate tracks according to the ranking. Candidate tracks are each scored according to one or more features, such as acoustic similarity and/or similar usage patterns of the candidate track or artist of the candidate track to a current or previously played track or artist. Each feature is weighted according to historical listening patterns surrounding a user-selected playlist seed artist. The weighting may also be further corrected according to historical listening patterns of the particular user. When historical usage data related to a particular seed artist is limited, more generalized historical usage data related to a higher level in a genre hierarchy may be used.

Abstract: In one embodiment, an audio signal for an audio track is received and segmented into a plurality of segments of the audio signal. The plurality of segments of audio are input into a classification network that is configured to predict output values based on a plurality of genre and mood combinations formed from different combinations of a plurality of genres and a plurality of moods. The classification network predicts a set of output values for the plurality of segments, each of the set of output values corresponding to one or more the plurality of genre and mood combinations. One or more of the plurality of genre and mood combinations are assigned to the audio track based on the set of output values for one or more of the plurality of segments.