Abstract: Systems and methods are described for a three-tiered artificial intelligence architecture that synchronizes processing statement deployment across diverse computer networks. The system may receive, at a user interface, a first request for a first recommendation. The first recommendation includes a set of standardized processing statements for implementing on a function. The system may input the first request into a first network component. The first network component includes first, second, and third models. The first model is trained to generate a library of standardized processing statements. The second model is trained to generate a plurality of standardized processing characteristic values for each standardized processing statement in the library. The third model is trained to generate recommendations of sets of standardized processing statements to functions. The system receives an output from the first network component and generates for display the first recommendation based on the output.

Abstract: Embodiments described herein include receiving an application flow defining logic for triggering automated actions for a candidate post on one or more web-based communication channels. An artificial intelligence (AI) powered web crawler may crawl a set of websites for target content. Responsive to identifying target content, machine learning may be leveraged to identify an entity name for an entity that is a subject of the target content and associate the entity with one or more event categories. Based on the event categories, a segment may be generated at runtime for the application flow where segment membership was not known at the time the application flow was defined or before application runtime.

Abstract: Techniques for propagation of deletion operations among a plurality of related datasets are described herein.

Abstract: Methods and systems for distributed cognition of digital content include receiving submissions from community members regarding a knowledge object. Each community member has a reputation value and each submission includes an evaluation value representing an evaluation of the knowledge object by the community member. A consensus evaluation is determined based on a calculated combination of the evaluation values in the submissions received and the reputation values of the respective community members who submitted the submissions. While submissions are being received, the consensus evaluation of the knowledge object is iteratively updated based on submissions received, being a calculated combination of the evaluation values in the submissions received and the reputation values of the respective community members who submitted the submissions.

Abstract: Various of the disclosed embodiments concern systems and methods for applying legal analytics. In some embodiments, a legal analytics platform retrieves legal data from an electronic database, analyzes some or all of the legal data, and identifies interesting patterns and results of statistical analyses. In order to permit searching of the legal data, metadata elements or tags can be generated for legal entities and legal events. In some embodiments, the legal analytics platform identifies timestamps in the legal data and performs time-based statistical analysis. Results of the statistical analyses can be presented to a user via a graphical user interface (GUI), which may also allow the user to interact with the legal analytics platform and search one or more databases of legal data.

Abstract: Methods and systems for condensing a sequential data set on a computer system. A sequential data set is received by the computer system and analyzed to identify a number of occurrences in the sequential data set of each of a plurality of unique data value pairs. A condensed data set is generated including a data element for each of the unique data value pairs. Each data element in the condensed data set includes an identification of the first data value and the second data value of the unique data value pair as well as a count indicative of the number of occurrences in the sequential data set of the first data value immediately followed by the second data value. A graphical signature is generated including a plurality of vectors each extending between two nodes corresponding to the data values of a different data element.

Abstract: Methods and systems of training and using a neural network model include training a time series embedding model and a text embedding model with unsupervised clustering to translate time series and text, respectively, to a shared latent space. The time series embedding model and the text embedding model are further trained using semi-supervised clustering that samples training data pairs of time series information and associated text for annotation.

Abstract: A system for determining relevant information based on user interactions may include a processor configured to receive data and associated relevance information from a data source and a set of signals describing a current environment of a user or historical user behavior information in which the data source being local to a computing device. The processor may be further configured to provide, using a machine learning model, a relevance score for each of multiple data items based at least in part on the received relevance information and the set of signals. The processor may be further configured to sort the data items based on a ranking of each relevance score for each data item. The processor may be further configured to provide, as output, the multiple data items based at least in part on the ranking.

Abstract: According to one embodiment, an information processing device includes: an encoder including a first layer and a second layer which are coupled in series; and a decoder. The encoder is configured to: generate, based on first data, a first key and a first value in the first layer, and a second key and a second value in the second layer; and generate, based on second data different from the first data, a first query in the first layer, and a second query in the second layer. The decoder is configured to: generate third data which is included in the first data and is not included in the second data, based on the first key, the first value, the first query, the second key, the second value, and the second query.

Abstract: Embodiments include a search and match computing system configured to: access, from a third party computing system, a query regarding at least one entity; determine if the query is a structured query or an unstructured query; process the query with at least one of an application programming interface configured to receive structured queries or a second application programming interface receive unstructured queries; initiate a search and match application configured to execute queries on at least one of: a relational data scheme or a non-relational data scheme; receive search results from the at least one of: the relational data scheme or the non-relational data scheme; and process the received search results to generate an output data packet for access by the third party computing system.

Abstract: A modular and distributed architecture for data stream processing and analysis is described to incorporate data stream analytics capabilities, called Data Stream Analytics Service (DSAS) in the IoT/M2M service layer. Each service layer node hosting DSAS can be split into two independent modules, Stream Forwarder and Stream Analytics Engine. Stream Forwarder is a light weight processing modules that can be responsible for data preprocessing and routing. Stream Analytics Engine is responsible for performing actual analytics on the data stream. Separating the two functionalities enables the service layer nodes to efficiently distribute stream analytics tasks across multiple nodes.

Abstract: A controller, for use in a storage device of a data processing system, includes a host interface, a memory interface and one or more processors. The host interface is configured to communicate over a computer network with one or more remote hosts of a data processing system. The memory interface is configured to communicate locally with a non-volatile memory of the storage device. The one or more processors are configured to manage local storage or retrieval of media objects at the non-volatile memory, and to perform additional tasks that are not associated with management of storage or retrieval of the objects.

Abstract: Methods and systems for optimizing a data structure are disclosed. An example method can comprise categorizing, based on travel information associated with a vehicle, locations according to at least one of a first category and a second category. An example method can comprise generating search criteria configured to select first data for locations categorized with the first category and second data for locations categorized with the second category. The first data can be more detailed than the second data. An example method can comprise receiving information based on the search criteria and providing the information to the vehicle.

Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of: providing a search engine that includes, or communicates with, a recall personalization model configured to generate personalized recall sets of search results for users; receiving, at the search engine, a search query submitted by a user; generating, using the recall personalization module, a feature vector for the user that includes contextual features associated with the user; generating, using the recall personalization model, a simulated narrowing query that includes the search query submitted by the user and the feature vector; generating, using the search engine, a recall set of search results based, at least in part, on the simulated narrowing query. Other embodiments are disclosed herein.

Abstract: A method includes receiving interaction data that indicates, for each given interaction among multiple interactions that occurred at a client device, (i) an event type an (ii) a delay period specifying an amount of time between the given event and a previous event that occurred prior to the given event, encoding each given interaction into an encoded interaction having a standardized format that is a combination of (i) the event type and (ii) the delay period, generating an interaction signature that includes sequence of encoded interactions, processing the sequence of encoded interactions using a model trained to label sequences of user interactions as valid or invalid, including labelling, using the model, a sequence of encoded interactions as invalid, and preventing distribution of a set of content to an entity that performed the sequence of encoded interactions in response to a subsequently identified request to provide content to the entity.

Abstract: Systems and methods are disclosed herein for identifying a media asset in response to an ambiguous input. The media guidance application may detect a portion of music provided by a user, e.g., a melody from user humming. The media guidance application may retrieve information about the user's location for a predetermined time period prior to detecting the portion of music. The media guidance application may then determine content accessible by the user at the location, e.g., a commercial played at a display screen at a train station when the user was waiting for the train, to identify the media asset corresponding to the user humming.

Abstract: The disclosure below describes a knowledge pattern machine that goes beyond and is distinct from a traditional search engine as simple information aggregator. Rather than acting as a search engine of the data itself, the knowledge pattern machine use variously layers of artificial intelligence to discover correlations within the queries and historical data, and to derive and recognize data patterns based on user queries for predictively generating new knowledge items or reports that are of interest to the user. Previous patterns and knowledge items or reports are accumulated and incorporated in identification of new data patterns and new predictive knowledge items or reports in response to future user queries, thus providing a stateful machine. The predictive knowledge items are updated in real-time without user interference as the underlying data sources evolve overtime. The data patterns and knowledge items are organized hierarchically and may be shared among different users at various levels.

Abstract: A computer implemented method of reducing data elements in a data file includes: receiving a data file including one or more primary data elements; storing the data file in a memory coupled to the processor; generating, from at least one of the one or more primary data elements, a plurality of supplemental data elements; determining whether any of the plurality of supplemental data elements and any of the primary data elements offset each other; and upon determining that at least one of the plurality of supplemental data elements and at least one of the primary data elements offset each other, deleting, from the data file, at least one of the offset supplemental data elements or primary data elements.

Abstract: A method for performing a path finding operation in graph data stored in a database is provided. The method may include receiving, from a client, a request to perform a weighted path operation on at least portion of the graph data. The portion of the graph data may correspond to a graph. The request may specify attributes associated with vertices and/or edges included in the graph. In response to the request, the weighted path operation may be performed by at least identifying a shortest path between two endpoints in the graph. The shortest path may minimize the one or more attributes of vertices and/or edges included in the shortest path. Related systems and articles of manufacture, including computer program products, are also provided.

Abstract: Deduplication of files or other data or objects in a manner that is aware of a format of the file and the application. A file may be chunked based on the format. The chunks are more consistent and lead to higher deduplication ratios. The file may be presented as a single file. However, the file is stored in chunks or subfiles and deduplication is performed with respect to the chunks. When the file is read, the file is rebuilt from its respective chunks. The files may also be compressed using differential compression, which leverages the content of similar files to compress a current file.