Abstract: Systems and techniques are generally described for attribute-based content selection and search. In some examples, a graphical user interface (GUI) may display an image of a first product comprising a plurality of visual attributes. In some further examples, the GUI may display at least a first control button with data identifying a first visual attribute of the plurality of visual attributes. In some cases, a first selection of the first control button may be received. In some examples, a first plurality of products may be determined based at least in part on the first selection of the first control button. The first plurality of products may be determined based on a visual similarity to the first product, and a visual dissimilarity to the first product with respect to the first visual attribute. In some examples, the first plurality of products may be displayed on the GUI.

Abstract: Provided is a sensor network capable of acquiring, from a data center, learning data composed of a pair of sensor data (input) and a classification label (output) necessary for adding/changing a classification label for updating a classifier while reducing the volume of communication between a sensor and the center. One aspect of the present invention relates to a sensor network, including one or more sensor nodes and a data center. The sensor node includes: an encoding unit for encoding sensor data by an encoder part of an autoencoder; and a transmission unit for transmitting the encoded data. The data center includes: a reception unit for receiving data encoded from sensor data by the encoder part of the autoencoder; a decoding unit for decoding the encoded data by a decoder part of the autoencoder; and a storage unit for storing the decoded data therein.

Abstract: A unified graph query system provides an abstraction layer that increases the interoperability of different graph technologies by exposing graphs stored in graph databases using a unified query language. The abstraction layer generates graph models for each of the available graph databases and extracts a graph component and other source data used to identify the source of the data requested by a query. The unified graph query system executes the query across the multiple graphs included in different graph databases by using the graph models to locate the graph component in each of the multiple graphs and extract the feature data associated with the graph component. The feature data is used to generate features that are used by a machine learning service to train machine learning models and is also used to make predictions in real time.

Abstract: An improved analytics system dynamically generates, integrates, and deploys multiple models for use related to a particular user and/or user segment. The integrated model analytics system can deploy a set of models specifically identified for a user from a group of models related to the service. This set of models can be used to provide recommendations for the user related to content of the service. As the user continues to interact with the service, the integrated model analytics system can dynamically update multiple models from the set of models based on real-time user interactions. These updated models can be used to generate updated recommendations for the user that can be used to dynamically update content presented to the user. In addition, this updated model can be used when providing recommendations for users in other user segments.

Abstract: The invention relates to database abstraction and data linkage. According to an embodiment of the present invention, the invention takes a variety of attributes (e.g., names, IP address, device identifiers, addresses, phone numbers, account numbers, etc.) and returns the online activity, demographic data, account data and/or other activity, events and data associated with that attribute. The tool may then iterate over each attribute and return a network of connections having multiple degrees of association. The innovative tool may be linked to known bad actor data, and perform automated searches on this data to proactively alert potentially fraudulent activity. The tool may also be developed to add attributes and apply machine learning to the associations to more intelligently describe the returned network. Further, the tool may be developed to describe larger networks having multiple degrees of connections.

Abstract: Methods, systems, and computer-readable media for schema-based spatial partitioning in a time-series database are disclosed. A time-series database divides elements of time-series data of a plurality of time series into partitions according to a clustering scheme. The time series are associated with respective schemas. The schemas comprise dimension names and measure names. The clustering scheme is determined based (at least in part) on the schemas and dimension values, and the schemas are determined based (at least in part) on the elements of time-series data. The time-series database stores the elements of time-series data from the plurality of partitions into one or more storage tiers. The time-series database performs a query of the time-series data in one or more of the storage tiers. The query is performed based (at least in part) on the clustering scheme.

Abstract: Certain aspects of the present disclosure provide techniques for operation of a feature management platform. A feature management platform is an end-to-end platform developed to manage the full lifecycle of data features. For example, to create a stateful feature, the feature management platform can receive a processing artifact from a computing device. The processing artifact defines the stateful feature, including the data source to retrieve event data from, when to retrieve the event data, the type of transform to apply, etc. Based on the processing artifact, the feature management system generates a processing job (e.g., the API defines a pipeline), which when initiated generates a vector that encapsulates the stateful feature. The vector is transmitted to the computing device that locally hosts a model, which generates a prediction that is transmitted to the feature management platform. Subsequently, the predication and stateful feature can be transmitted to other computing devices.

Abstract: Methods, systems and devices for determining optimized tillage of a soil area are provided. Operations include transmitting, using at least one sensor, a data set regarding a physical, chemical and/or biological aspect of the soil area. Operations include receiving, using at least one computing device, the data set regarding the physical, chemical and/or biological aspect of the soil area. The at least one computing device removes a set of redundant data and the at least one computing device enhances a set of data that is not the set of redundant data. Operations include generating a visualization of the set of data that is not redundant data. The data that is not redundant data provides a data set reflecting a soil compaction measurement within the soil area and the soil area is not deeper than 36 inches from a surface of the soil area.

Abstract: A system and method for collecting data to obtain the data from a user, obtaining metadata for each word of the data from the user, and/or obtaining a searchable transcript of the data and a device to store the searchable transcript. The metadata may be date, time, name or location metadata and the data collection device may include a speech recognition engine to translate speech into searchable words. The speech recognition engine may provide a confidence level corresponding to the translation of the speech into searchable words, and the speech recognition engine may distinguish a first user and a second user in order to provide a first searchable transcript for the first user and a second searchable transcript for the second user. An ad transcript may be added to the searchable transcript, and the searchable transcript may be placed in a centralized community search database.

Abstract: The disclosure is directed to various ways of improving the functioning of computer systems, information networks, data stores, search engine systems and methods, and other advantages. Among other things, provided herein are methods, systems, components, processes, modules, blocks, circuits, sub-systems, articles, and other elements (collectively referred to in some cases as the “platform” or the “system”) that collectively enable, in one or more datastores (e.g., where each datastore may include one or more databases) and systems, the creation, development, maintenance, and use of a set of custom objects for use in a wide range of activities, including sales activities, marketing activities, service activities, content development activities, and others, as well as improved methods and systems for sales, marketing and services that make use of such entity resolution systems and methods as well as custom objects.

Abstract: Techniques are described herein to improve onboarding of third party entity data with existing knowledge graphs. In various implementation s, a computing system associated with an existing knowledge graph may receive a request from a third party to onboard, with the existing knowledge graph, a plurality of entities. Each entity may have associated identifier(s) and relationship(s) with other entities of the plurality of entities. First third party entity data that describes the plurality of entities and associated identifiers/relationships may be received from the third party. The first third entity party data may be analyzed to identify semantic fingerprint(s) matching respective subsets of the entities. Results related to the analyzing may be determined. The results may include a statistic representing success or failure of applying rule(s) to a respective subset of entities that match a given semantic fingerprint. Remedial action(s) may be triggered based on the failure statistic.

Abstract: A method, apparatus, system, and computer program code for classifying data. A number of virtual datasets is generated at multiple granularities across a number of data dimensions. Data records that correspond to a combination of data dimensions are identified in a virtual dataset. A number of defined rules are applied to: determine a set of granularities for each of the number data dimensions for comparing the data records that were identified; and determine a model for comparing the data records that were identified. The data records are classified according to the model and the set of granularities that were determined for the number data dimensions.

Abstract: A data-driven nonuniform subsampling approach for computation-free on-sensor data dimensionality is provided, referred to herein as selective sensing. Designing an on-sensor data dimensionality reduction scheme for efficient signal sensing has long been a challenging task. Compressive sensing is a generic solution for sensing signals in a compressed format. Although compressive sensing can be directly implemented in the analog domain for specific types of signals, many application scenarios require implementation of data compression in the digital domain. However, the computational complexity involved in digital-domain compressive sensing limits its practical application, especially in resource-constrained sensor devices or high-data-rate sensor devices. Embodiments described herein provide a selective sensing framework that adopts a novel concept of data-driven nonuniform subsampling to reduce the dimensionality of acquired signals while retaining the information of interest in a computation-free fashion.

Abstract: Various embodiments provide methods, systems, apparatus, computer program products, and/or the like for managing, ingesting, monitoring, updating, and/or extracting/retrieving information/data associated with an electronic record (ER) stored in an ER data store and/or accessing information/data from the ER data store, wherein the ERs are generated, updated/modified, and/or accessed via a graph-based domain ontology.

Abstract: Methods, systems, and media for presenting content based on a generic rating are provided.

Abstract: A versioned file system comprises a set of structured data representations. At a first time, an interface creates and exports to a cloud data store a first structured data representation corresponding to a first version of the local file system. The first structured data representation is an XML tree having a root element, one or more directory elements associated with the root element, and one or more file elements associated with a given directory element. Upon a change within the file system, the interface creates and exports a second structured data representation corresponding to a second version of the file system. The second structured data representation differs from the first structured data representation up to and including the root element of the second structured data representation. The interface continues to generate and export the structured data representations to the data store.

Abstract: Provided is a method for managing source identifiers of clustered records, which may include receiving a plurality of records, each having identification data associated with a source thereof. The records may be sorted into a first plurality of clusters. A first source identifier may be generated for each cluster. Update data associated with an update to the records may be received. At least some of the records may be sorted into a second plurality of clusters. A first cluster of the second plurality of clusters may have first identification data different from at least one cluster of the first plurality of clusters, and a second cluster of the second plurality of clusters may have identification data that substantially matches the at least one cluster. Whether to assign the first source identifier to the first or second cluster may be determined. A system and computer program product are also disclosed.

Abstract: Systems and methods for structuring unstructured data according to a data object structure that enables fast query look-ups across a variety of space and time dimensions. Furthermore, many embodiments optimize the storage of the data objects using a set of compression techniques that configure the data types used for the data objects based on properties of the stored data. Furthermore, many embodiments provide are able to service query look-up requests without having to deserialize data within the byte stream format as stored in memory by encoding information that provide memory locations for requested data, thereby allowing for the immediate retrieval of the data as it is stored in the persistent memory.

Abstract: Various embodiments provide methods, systems, apparatus, computer program products, and/or the like for managing, ingesting, monitoring, updating, and/or extracting/retrieving information/data associated with an electronic record (ER) stored in an ER data store and/or accessing information/data from the ER data store, wherein the ERs are generated, updated/modified, and/or accessed via a graph-based domain ontology.

Abstract: A compiler receives a description of a machine learning network and generates a computer program that implements the machine learning network. The compiler allocates instructions of the computer program to different groups of processing elements (Tiles) for execution such that different groups of Tiles implement different layers of the machine learning network. The compiler may determine the size of the different groups based on a partial computation metric associated with the computations performed to implement the corresponding layer. Furthermore, the compiler may assign specific Tiles to each group based on a set of predefined layout constraints. The compiler may statically schedule at least a portion of the instructions into one or more deterministic phases for execution by the groups of Tiles.