Abstract: A computer-implemented method that includes a computing system receiving a plurality of data items that include content data. The system then generates a first inference model based on the received content data. The system also receives metadata associated with respective data items and then generates a second inference model based on the received metadata data. The system further determines, based on the first inference model, a first weight parameter associated with the content data, and determines, based on the second inference model, a second weight parameter associated with the metadata. The system then generates a classification model for determining a classification of at least one data item of the plurality of data items. The classification model is generated based on at least one of the first weight parameter or the second weight parameter.

Abstract: According to examples, intelligent visualization munging may include transforming and enriching data that is to be visualized, determining features of the transformed and enriched data, determining a user role of a user associated with the transformed and enriched data, and a user interaction of the user. Intelligent visualization munging may further include learning a behavior of the user, and analyzing the features, the user role, the user interaction, and a learned behavior model to generate a recommendation that includes a predetermined number of visualizations from a plurality of available visualizations to display the transformed and enriched data. The predetermined number of visualizations is less than the plurality of available visualizations.

Abstract: A device may receive a first command, included in a set of commands, to set a configuration parameter associated with performing feature extraction. The device may receive a second command, included in the set of commands, to set a corresponding value for the configuration parameter. The configuration parameter and the corresponding value may correspond to a particular feature metric that is to be extracted. The device may configure, based on the configuration parameter and the corresponding value, feature extraction for a corpus of documents. The device may perform, based on configuring feature extraction for the corpus, feature extraction on the corpus to determine the particular feature metric. The device may generate a feature vector based on performing the feature extraction. The feature vector may include the particular feature metric. The feature vector may include a feature identifier identifying the particular feature metric. The device may provide the feature vector.

Abstract: A device may receive information associated with an application to be tested. The device may identify test data associated with the application to be tested based on the received information. The device may associate the test data with a plurality of test cases. The device may associate the plurality of test cases with a test set. The device may associate the test set with a release. The device may provide the plurality of test cases and the test data, associated with the release, to the application to be tested. The device may receive a plurality of first results, and may compare the plurality of first results and a plurality of second results. The device may provide information for display based on comparing the plurality of first results and the plurality of second results.

Abstract: A device receives images of a video stream, models for objects in the images, and physical property data for the objects, and maps the models and the physical property data to the objects in the images to generate augmented data sequences. The device applies different physical properties to the objects in the augmented data sequences to generate augmented data sequences with different applied physical properties, and trains a machine learning (ML) model based on the images to generate a first trained ML model. The device trains the ML model, based on the augmented data sequences with the different applied physical properties, to generate a second trained ML model, and compares the first trained ML model and the second trained ML model. The device determines whether the second trained ML model is optimized based on the comparison, and provides the second trained ML model when optimized.

Abstract: Knowledge graph systems are disclosed for implementing multiple approaches, including stand alone or combined approaches, for knowledge graph pruning. The approaches are based on graph sampling work such as, for example, information gain theory. The approaches are applied by a knowledge graph system to perform schema pruning, automatic graph pruning, and query correlation for improving query performance.

Abstract: Knowledge graph systems are disclosed for implementing multiple approaches, including stand alone or combined approaches, for knowledge graph pruning. The approaches are based on graph sampling work such as, for example, information gain theory. The approaches are applied by a knowledge graph system to perform schema pruning, automatic graph pruning, and query correlation for improving query performance.

Abstract: According to an example of the present disclosure, a system is disclosed. The system comprises at least one sensing unit and a robotics engine in communication with the at least one sensing unit. The at least one sensing unit detects stock information associated with an item. The robotics engine performs a trend analysis based on the stock information collected over a predefined duration of time, and determines a threshold value based on the trend analysis. Furthermore, the robotics engine generates an alert when the stock information is below the threshold value, and selects a vendor based on one or more predefined parameters. The robotics engine also generates an instruction to obtain the replacement item from the selected vendor for replenishing the item in an inventory.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for incident response are disclosed. In one aspect, a computer-implemented method includes receiving data identifying two or more groups of actions performed to remediate a computer security threat. The method includes determining first unique paths from a first action of each of the two or more groups of actions to a second action of each of the two or more groups of actions, and determining second unique paths from the second action of each of the two or more groups of actions to a third action of each of the two or more groups of actions. The method also includes combining common paths among the first unique paths and the second unique paths, identifying one of the common paths that appears most frequently, and determining a core path that includes a subset of the actions of the two or more groups of actions based on the one of the common paths that appears most frequently.

Abstract: A device may receive first data that identifies operations of an organization. The operations may be associated with a first manner in which the organization stores second data or a second manner in which the organization generates a contract. The device may process the first data to identify the operations of the organization. The device may perform a first analysis of the first data to determine whether the operations of the organization satisfy a set of rules. The set of rules may indicate the first manner in which the organization is to store the second data. The device may perform a second analysis of the second data to identify an error associated with the second data. The device may perform an action to modify the operations of the organization or to facilitate fixing of the error based on a result of the first analysis or the second analysis.

Abstract: A method for anonymously communicating data that defines a token from a source system to a destination system via a block-chain distributed database includes receiving, at a token distribution system, request information from a source system. The request information specifies source identifying information and an address for receiving one or more tokens. The token distribution system determines one or more tokens for allocation to the source system and communicates the allocated tokens to the address defined in the request information via a zero-knowledge transaction. The source system moves the tokens to a different address for communicating a block-chain transaction and communicates the tokens at the different address to a destination address associated with the destination system via a block-chain transaction.

Abstract: A device may receive first information associated with an emergence area. The first information may include imagery data of the emergence area. The device may determine an expected commodity quantity value based on the first information. The device may determine an actual commodity quantity value based on the imagery data. The device may determine an emergence value, associated with the emergence area, based on the expected commodity quantity value and the actual commodity quantity value. The device may receive second information associated with a commodity, and may determine one or more conditions based on the second information and the emergence value. The device may determine a recommendation based on the one or more conditions, and may provide the recommendation to permit and/or cause an action to be performed in association with the emergence area.

Abstract: A task transformation architecture meets the technical challenges of geographically distributed task assignment and completion, e.g., by crowd-sourced workers who are external to any given enterprise that needs the task completed. The architecture delivers task information to the workers while maintaining confidentiality. In one aspect, the architecture determines when task descriptions include confidential information, transforms the task to remove the confidential information, and delivers the transformed task to the worker. When the worker responds with a completed project, e.g., source code for executing the transformed task, the architecture transforms the completed project into a form that restores the confidential information.

Abstract: Examples of an intelligent persona generation system are provided. In an example, the system receives an image and an identity creation requirement from a user. The system implements an artificial intelligence component to sort the sort the image into a plurality of objects. The system may identify a principal object from evaluation of the plurality of objects. The system may identify at least one parameter associated with the identity creation requirement and receive associated parameter data from a pre-existing library coupled to the processor. The system may determine a parameter set from the parameter data, associated with the principal object by performing a first cognitive learning operation. The system may implement a second cognitive learning operation on the principal object and the parameter set associated with the principal object to determine an identity model indicative of an identity creation relevant for processing the identity creation requirement.

Abstract: A system for elastic volume type selection and optimization is provided. The system may detect that a block storage volume was provisioned by a public cloud computing platform based on a first volume type identifier of a first volume type. The system may determine, based on a normalization model, a baseline operation rate and a baseline throughput rate for the provisioned block storage volume. The system may determine, based on a selected transition mode and historical performance measurements, a simulated operation rate and a simulated throughput rate. The system may communicate, in response to the simulated throughput being greater than the baseline throughput rate or the simulated operation rate being greater than the baseline operation rate, a provisioning instruction to re-provision the provisioned block storage volume on the cloud computing platform.

Abstract: A system for categorizing words into clusters includes a receiver to receive a set of sentences formed by a plurality of words. The set of sentences is indicative of interaction of a user with a virtual assistant. A categorizer categorizes the plurality of words into a first set of clusters by using a first clustering technique, and categorizes the plurality of words into a second set of clusters by using a second clustering technique. A detector detects words that appear in similar clusters after categorization by the first clustering technique and the second clustering technique. Similarity of clusters is based on a nature of words forming the clusters. A generator generates a confidence score for each of the plurality of words based on the detection. The confidence score of a word is indicative of accuracy of the categorization of the word.

Abstract: According to an example, customized visualization based intelligence augmentation may include accessing, based on a user request, a domain model, and mapping the user request to the domain model. Based on the mapping, a guided query that includes a relevant refinement question may be generated. A response may be received to the refinement question. Based on the received response, a refined user request may be generated, and classified into an intelligence augmentation category. Based on the classification, an intelligence augmentation analyzer may be accessed to analyze the refined user request to generate an insight output that is classified to a visualization. Based on the classification of the insight output to the visualization, responsive to the user request, a display of the visualization may be generated.

Abstract: A system for predicting a non-fraud dispute using an artificial intelligence (AI) based communications system is disclosed. The system may comprise a data access interface to receive instructions historical transaction and disputes data from at least one data source associated with an account issuer. The data access interface may also receive incoming transaction data associated with a transaction from at least one data source associated with an account holder.

Abstract: A knowledge graph virtualization system (KGVS) implements data virtualization techniques using semantic knowledge when parsing a knowledge graph to return results to a query. The data virtualization using semantic knowledge enable end users and applications to describe desired output without detailed knowledge of underlying data storage, schema, and relationships.

Abstract: A device receives, from a tag reader device of a plurality of tag readers, information associated with a scan of a tag, where each of the plurality of tag readers is configured to read a different type of tag. The device determines, based on the information associated with the scan, a tag reader type associated with the tag reader device, where the plurality of tag readers is associated with a corresponding plurality of tag reader types. The device includes a plurality of parsers associated with the plurality of tag reader types, and identifies a parser, included in the device, associated with the tag reader type associated with the tag reader device. The device determines, using the parser, a tag identifier based on the information associated with the scan. Based on determining that the tag identifier is valid, the device transmits the information associated with the scan to a server.