Abstract: In accordance with an embodiment, described herein is a system and method for capture of change data from a distributed data source system, for example a distributed database or a distributed data stream, and preparation of a canonical format output, for use with one or more heterogeneous targets, for example a database or message queue. The change data capture system can include support for features such as distributed source topology-awareness, initial load, deduplication, and recovery. A technical purpose of the systems and methods described herein includes determination and communication of changes performed to data at a distributed data source that includes a large amount of data across a plurality of nodes, to one or more target computer systems.

Abstract: Creating a summary of a plurality of texts includes tokenizing each of a plurality of texts to obtain tokens; generating a vector space using a first set of vectors having one or more obtained feature scores equal to or larger than a predefined value; executing non-hierarchical clustering using the vector space to generate a first plurality of clusters; choosing a first representative text in each of the plurality of clusters; generating a second set of vectors from each of the arrays generated based on a number of characters included in tokens of the representative texts; executing hierarchical clustering using the second set of vectors to generate a second plurality of clusters; and in response to a determining a number of clusters included in the second plurality of clusters, determining a second representative text for each of the clusters included in the second plurality of clusters.

Abstract: The invention, which discloses a method and a system for identifying a core product term, relates to the technical field of computers.

Abstract: Systems, methods, and techniques to efficiently analyze and navigate through decision logic using an execution graph are provided. The method includes executing decision logic in response to receiving a data file. The method further includes generating, in response to the executing, an execution graph. The execution graph includes a plurality of nodes corresponding to a plurality of decision entities of the decision logic. The method further includes displaying the execution graph on a user interface. The method further includes displaying, in response to receiving a selection of a node of the plurality of nodes, information associated with the selected node.

Abstract: A search request for content can be initiated by a user, and the content that is relevant to the search request can be identified and presented in a manner that indicates the content's trustworthiness or relevancy. The identified content can be ranked based on the number of times the content has been referenced as well as by source that referenced the content. The relevant identified content can then be displayed in an ordered list that is ordered based on the number of times the content has been referenced. In some cases, the order may be modified by the authority of the source.

Abstract: An electronic device generates a score for each objective in a hierarchy of objectives. Generating the score comprises using a representation of the media content item and a user as inputs to a first machine learning algorithm, to generate a score for a first objective corresponding to a first level in the hierarchy of the objectives and using an output of the first machine learning algorithm, distinct from the score for the first objective, as an input to a second machine learning algorithm to generate a score for a second objective corresponding to a second level in the hierarchy of objectives. The electronic device generates a respective score between the user and the media content item using the score for the first objective and the score for the second objective and provides media content to the user based on the respective scores.

Abstract: An example apparatus for visual question answering includes a receiver to receive an input image and a question. The apparatus also includes an encoder to encode the input image and the question into a query representation including visual attention features. The apparatus includes a knowledge spotter to retrieve a knowledge entry from a visual knowledge base pre-built on a set of question-answer pairs. The apparatus further includes a joint embedder to jointly embed the visual attention features and the knowledge entry to generate visual-knowledge features. The apparatus also further includes an answer generator to generate an answer based on the query representation and the visual-knowledge features.

Abstract: A method for sharing access to data from a cloud-based analytics engine may include receiving, at a first client, a message from a second client. The message may include an image of a data presentation and metadata associated with the data presentation. The first client may respond to a selection of the image of the data presentation by accessing the cloud-based analytics engine to retrieve, based on the metadata associated with the data presentation, data associated with the data presentation. The data presentation may generated for display at the first client based on the data retrieved from the cloud-based analytics engine. The data presentation displayed at the first client may be interactive to enable an application of one or more modifications to the data presentation displayed at the first client. Related systems and articles of manufacture are also provided.

Abstract: 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.

Abstract: Methods, systems, and computing platforms for data communication are disclosed. The processor(s) may be configured to electronically receive a SQL query request for a relational computer readable database having plurality of computer readable records. The processor(s) may be configured to electronically process the SQL query request with a machine learning controller based on a set of machine learning training data so as to output at least one probable smart execution plan for executing the SQL query request. The processor(s) may be configured to electronically output the at least one probable smart execution plan for executing the SQL query request to a relational database management processing module.

Abstract: Disclosed is a system and method for defining data structures for client-server system. In one embodiment, the present invention provides a compiler-enforced data model across distributed systems for providing system stability and the ability to identify and fix violations of the data model contract in a more efficient manner.

Abstract: Disclosed herein are embodiments for compressing data. A first encoding, a decoding, and an error prediction index are received from one or more artificial neural networks. The first encoding corresponds to a lossy compression of the data. The decoding corresponds to a decompression of the first encoding. The error prediction index indicates one or more locations of predicted error in the decoding. Based on the data and the error prediction index, a first set of bits is generated to include one or more bit values of the data at the one or more locations of predicted error. Based on the error prediction index and the decoding, a second set of bits is generated to indicate one or more locations of unpredicted error in the decoding. The first encoding, the first set of bits, and the second set of bits are stored as a losslessly compressed version of the data.

Abstract: A system is provided to predict requested playbacks of media files by users from a media storage system. The system includes a processor and a computer readable medium operably coupled thereto, to perform predictive playback operations which include accessing an AI model and a media file comprising metadata associated with generating the media file, generating a predictive score for a playback of the media file based on the AI model and the metadata, comparing the predictive score to a threshold required to transcode the media file into a playback format prior to the playback, predicting the playback based on the comparing, determining a predicted playback time of the media file based on the metadata for the media file, and transcoding the media file into the playback format prior to the predicted playback time.

Abstract: An apparatus includes a processing device configured to obtain data records associated with an enterprise system comprising strings associated with an attribute. The processing device is also configured to generate a similarity matrix with entries comprising values characterizing similarity between respective pairs of the strings. The processing device is further configured to apply a thresholding filter to values in the entries of the similarity matrix to create an adjacency matrix, and to construct a graph network of the data records based at least in part on the adjacency matrix, wherein the graph network comprises edges connecting pairs of the data records. The processing device is further configured to perform a clustering operation on the graph network to identify clusters of the data records for the attribute, and to initiate remedial action in the enterprise system responsive to identifying a given cluster comprising a given subset of the data records.

Abstract: Predictive queue flushing for real-time synchronization of data sets between two data stores, comprising a data synchronization software module that interfaces with each data store, and uses a queue monitor to record and store changes to data on each data store and calculate velocity and acceleration of event arrivals, and a policy manager to manage synchronization, and a query generator to incorporate policies from the policy manager and measurements from the queue monitor to direct the data synchronization software module, flushing the change queue in accordance with the established synchronization policy, yielding synchronized shared data sets.

Abstract: Embodiments are directed to data ingestion over a network. Raw data and integrated data associated with a plurality of separate data sources may be provided such that the raw data includes content associated with a plurality of subjects. Categorization models may be employed to categorize the raw data based on various features, such as, format, structure, data source, variability, volume, or associated entities. Matching models may be determined based on the categorization of the of the raw data, the integrated data and the content associated with the plurality of subjects. Matching models may generate a plurality of unified facts based on the raw data and the integrated data such that each unified fact is associated with a score associated with a quality of its match with a unified schema.

Abstract: The present disclosure relates to a method for searching an audio, pertaining to the technical field of electronics. The method includes: detecting a predetermined trigger event in response to receiving a trigger instruction for searching an audio; recording a time point when a detected trigger event occurs each time upon detecting the predetermined trigger event once until a predetermined end event is detected, and acquiring recorded time points to obtain a time point sequence; selecting a target reference time sequence matching the time point sequence from pre-stored reference time sequences; and determining target audio data corresponding to the target reference time sequence based on a pre-stored corresponding relationship between audio data and the reference time sequence.

Abstract: A method includes receiving a user query and performing, using at least one processor, multiple rounds of an answer generation process. Each round of the answer generation process includes selecting one of multiple functions to be performed based on an input state. The input state for each round includes an embedding of the user query in a feature space. The input state for at least one round also includes an embedding of information to be used to identify an answer to the user query in the feature space. Each round of the answer generation process also includes performing the selected function. The multiple functions include (i) an answer generation function that produces the answer to the user query and (ii) at least one additional function that updates the input state for a current round for use during a subsequent round. In addition, the method includes providing the answer to the user.

Abstract: A method includes defining a set of context types; defining a set of source types, each comprising context types; defining, for each source type, and for each context type included in the events from data sources having the source type, a context definition comprising a set of fields, in events from the data sources, that are associated with the context type; receiving a query comprising a first field value and a time period; retrieving a plurality of events that include the first field value and the time period; for each retrieved event, and for each context definition defined for a source type and a context type of a data source from which the retrieved event originated, determining field values of fields in the set of fields of the context definition; aggregating, for each context type, determined field values from the events; and generating an output.

Abstract: Described are techniques for automated anomaly detection including a technique comprising training an ensemble of deep learning models using clustered time series training data from numerous components in an Information Technology (IT) infrastructure. The technique further comprises inputting aggregated time series data to the ensemble of deep learning models and identifying anomalies in the aggregated time series data based on respective portions of the aggregated time series data that are indicated as anomalous by a majority of deep learning models in the ensemble of deep learning models. The technique further comprises grouping the anomalies according to relationships between the anomalies and performing a mitigation action in response to grouping the anomalies.