A method, system and computer program product for analyzing multidimensional data are disclosed. In embodiments, the method comprises obtaining an original set of data having a sequential order and multiple original dimensions; selecting a topic-based summarization scheme to summarize the original set of data; and applying the selected topic-based summarization scheme to the original set of data to transform the original set of data into a new set of data having fewer dimensions than the original set of data, while preserving, within a defined measure, the sequential order of the original set of data. In embodiments, the selecting a topic-based summarization scheme includes selecting a plurality of topics, each of the topic representing a set of the original dimensions. In embodiments, the applying the topic-based summarization scheme includes performing dimensionality reduction on the original set of data to transform the original dimensions to the topics.

Systems and methods are provided for performing operations including: retrieving, by one or more processors, a first content item; obtaining a first view count for the first content item; determining that the first view count corresponds to trending content; and presenting the first content item to a user in a presentation arrangement of a graphical user interface with a first indication of the first view count, the first indication having a first visual attribute representing trending content.

In some implementations, a user device (e.g., a computing device) can perform client-side personalization of search results. For example, a computing device can obtain search results matching user specified search parameters from a server device and/or from various services on the user device. The user device can score the search results based on various search result item attributes. After scoring, the user device can promote or demote search results items based on whether the search results item is relevant to recent user behavior. The promotion and/or demotion of search results items can cause search results items scores to be adjusted to generate a personalized score for each search result. The search results can then be ordered and/or presented based on the personalized score for each search results item. When presenting search results items, the user device can present information indicative of the source of the search results items.

One embodiment included a non-transitory machine-readable medium containing instructions that when executed carry out a method of searching for a search term. The method uses, instead of an index database of search terms, an index database section of only search terms that have the prefix of the search term, such that execution can occur on an improved processing system that is relatively small. The index database section is arranged as a prefix database of terms that start with the prefix, e.g., a trie, a radix trie, or a ternary search tree of the terms. The method may be implemented as a serverless function triggered by a user entering a search term or part thereof.

An electronic device obtains a plurality of collections of media content items, each collection of media content items being associated with text generated by one or more users of the media-providing service. Based on how frequently a first media content item co-occurs with a first descriptor in text for respective collections of media items that include the first media content item, the electronic device generates, without user input, a new collection of media content items for a first user. The new collection of media content items corresponds to the first descriptor and includes the first media content item. The electronic device presents the new collection of media content items to the first user as a recommendation.

Technologies for performing stochastic similarity searches in an online clustering space include a device having a column addressable memory and circuitry. The circuitry is configured to determine a Hamming distance from a binary dimensionally expanded vector to each cluster of a set of clusters of binary dimensionally expanded vectors in the memory, identify the cluster having the smallest Hamming distance from the binary dimensionally expanded vector, determine whether the identified cluster satisfies a target size, and add or delete, in response to a determination that the identified cluster does not satisfy the target size, the binary dimensionally expanded vector to or from the identified cluster.

Described herein is a computer implemented method, a computer processing system, and a non-transitory computer-readable storage medium. The method includes displaying a first set of media item representations in a media item order in an initial media selection interface. While the initial media selection interface is displayed, the method further comprises detecting a display complete media set at reference input and, in response: determining a reference media item representation and displaying a complete media selection interface in a first initial display state which is based on the reference media item representation.

An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.

A method for enabling event consumption is described. Upon receipt of a request for events associated with a first initial topic, a determination that the request includes a request for historical events is performed. Responsive to determining that one or more rules apply to the request for historical events, a determination of a first path from the first initial topic to a first aggregate topic is performed based on the one or more rules. The first path is different from a second path from the first initial topic to a second aggregate topic that is defined according to a current multiplexed framework definition. The current multiplexed framework definition is used for storing new events associated with the first initial topic in a second multiplexed event recordation system at a time that follows the time of receipt of the request. A first set of historical events is retrieved based on the first path.

The present disclosure relates to a new method for cross-modal retrieval via deep binary hashing and quantization. In a training phase, the system simultaneously learns to generate feature vectors, binary codes, and quantization codes for data across two or more modalities that preserves the semantic similarity correlations in the original data. In a prediction phase, the system retrieve a data item in a database that is semantically similar to a query item of a different modality. To identify the database item closest in semantic meaning to the query item, the system first narrows the database search space based on binary hash code distances between each of the database items and the query item. The system then measures the quantization distances between the query items and the database items in the smaller search space. The system identifies database item have the closest quantization distance to the query item as the closest semantic match to the query item.