Abstract: Implementations include receiving image data representative of images of items within a physical environment and depicting defects in at least one item, providing one or more of a set of augmented images using image augmentation based on the image data and a set of synthetic images using ML-based image synthesis based on the image data, processing one of the set of augmented images and the set of synthetic images using an ML model to provide a set of defect characteristics representative of defects in the at least one item, providing one or more root causes of each of the one or more defects by processing the set of defect characteristics and ancillary data, the ancillary data representative of the physical environment, and generating one or more alerts based on the one or more root causes for remediation of at least one root cause of the one or more defects.

Abstract: A system creates an abstraction layer surrounding a diverse data system including multiple different databases. Data is received from data sources and ingested into the various databases according to a core model. New instances of the core model are created and added to a larger linked data model (LDM) when new data sources are added to the system. The LDM captures the linkages between different linked data objects and links across different databases. Accordingly, applications are able to access or explore the linked data stored in different databases without prior knowledge of the linking relationships.

Abstract: A device may receive form analysis information to be used to analyze a form for an organization. The form analysis information may include an industry profile associated with the organization, a government regulation that governs the organization, and a form field justification that indicates a justification for including a particular field in the form. The device may analyze the form based on the form analysis information and based on one or more fields included in the form. The device may generate one or more scores for the one or more fields based on analyzing the form. The one or more scores may be generated based on the industry profile, the government regulation, and the form field justification. The device may perform one or more automated actions in association with the form based on the one or more scores.

Abstract: Event correlation may include identifying a feature set for each log file of a plurality of log files, and extracting the feature set for each event of a plurality of events in each log file of the plurality of log files. Event correlation may further include determining a plurality of trace event pairs linkage strength values for an event from a first log file of the plurality of log files and a plurality of events from a second log file of the plurality of log files. The trace event pairs linkage strength values may represent an overlap of the feature set for the event from the first log file and the feature set for each of the plurality of events from the second log file.

Abstract: A machine learning (ML) based intermittent data processing system accesses a collection of intermittent data points, determines a data distribution associated with the collection and generates one or more calculated values based on the data distribution. A simulation can be employed to determine the accuracy of the calculated values based on which, the calculated values can be employed for further processing. The collection of intermittent data points is initially processed to determine if one or more of the data distribution identification, bootstrapping or variability capping techniques are to be applied in order to obtain the calculated values. The calculated values are used to generate visualizations and recommendations.

Abstract: A system provides feedback driven end-to-end state control of a data model. A data model may be used to model the behavior of a petrochemical refinery to predict future events. The system may be used to ensure proper operation of the data model. Contingency data models may be executed when a failure is detected. Further, when the system detects accuracy that is out of tolerance, the system may initiate retraining of the data model being currently used.

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: Implementations of the present disclosure are directed to dispensing beverages from a beverage dispensing machine and include determining, from computer-readable media, pour parameters for a beverage of a plurality of beverages, the pour parameters being specific to the beverage, at least one pour parameter including a tilt value, and automatically, by the beverage dispensing machine: rotating a drum that holds a vessel to achieve the tilt value, initiating dispensing of the beverage into the vessel from a tap, automatically rotating the drum to reduce the tilt value of the vessel during dispensing of the beverage, and ceasing dispensing of the beverage into the vessel from the tap, the tilt value being substantially zero upon ceasing.

Abstract: The systems and methods described herein may generate multi-modal embeddings with sub-symbolic features and symbolic features. The sub-symbolic embeddings may be generated with computer vision processing. The symbolic features may include mathematical representations of image content, which are enriched with information from background knowledge sources. The system may aggregate the sub-symbolic and symbolic features using aggregation techniques such as concatenation, averaging, summing, and/or maxing. The multi-modal embeddings may be included in a multi-modal embedding model and trained via supervised learning. Once the multi-modal embeddings are trained, the system may generate inferences based on linear algebra operations involving the multi-modal embeddings that are relevant to an inference response to the natural language question and input image.

Abstract: A device may receive a first sample. The device may identify a plurality of second samples that are similar to the first sample. The plurality of second samples may correspond to service tickets that have previously been processed. The device may obtain or determine log information identifying a plurality of events associated with the first sample. The device may determine respective probabilities of occurrence corresponding to the plurality of second samples. A probability of occurrence, for a particular second sample, may identify a likelihood of receiving a corresponding service ticket within a particular time period of occurrence of the plurality of events. The device may assign ranks to the plurality of second samples based on the respective probabilities of occurrence. The device may provide information identifying the ranks and the plurality of second samples.

Abstract: Techniques are described for unified identity and access management (IAM) across multiple applications in a distributed (e.g., cloud) computing environment. Implementations provide for IAM across multiple applications through use of a single, unified IAM tool including an IAM interface. The IAM tool can manage user identity and user access rights for multiple applications in the platform environment. The IAM tool can also employ a unified IAM database, which stores user profiles that each describes user access rights for a user in one or more applications. Through use of the unified IAM tool, an operator can access a single interface to manage user identity and access privileges across multiple applications which may have their own identity management interfaces, with user roles in different applications mapped through use of an equivalency matrix in some cases. The IAM tool can be used to add, remove, or edit user access privileges for multiple applications.

Abstract: A distributed ledger technology (DLT) network may include a plurality of participant nodes. The participant nodes may respectively validate a distributed ledger based on a consensus protocol. A blockchain export system may send, to a data receiver not included in the DLT network, a participant public key for a participant node of the DLT network. The blockchain export system may receive, from the data receiver, a request to share token data stored in a blockchain of the distributed ledger. The blockchain export system may generate a certification that the token data is stored on the blockchain. The certification may include a digital signature based on a participant private key paired to the participant public key. The blockchain system may transmit the certification to the data receiver. The data receiver may verify the certification based on the participant public key.

Abstract: An aerial monitoring system and method for identification and location of object features is disclosed. The aerial monitoring system and method includes training an image processing engine to identify predefined object features in images. Training involves the image processing engine generating a model for identifying predefined object features in images. Identifying the predefined object features includes using a drone outfitted with a drone camera to capture and geotag monitoring images of target objects. The monitoring images are both infrared and non-infrared. The image processing engine applies the model to the monitoring images to determine whether the monitoring images include object features that fit within one of multiple categories. The image processing engine uses a fuzzy clustering process to group objects into cluster locations. The image processing system outputs the identification and location of the object features. The output is used for maintenance planning related to the objects.

Abstract: A device may process configuration data to identify category data that identifies possible categories of data included in the configuration data. The device may process the category data, after identifying the category data, using a natural language processing technique to generate a set of terms to be processed using an artificial intelligence module. The device may utilize the artificial intelligence module to process the set of terms to predict a set of configuration actions to be performed with respect to the configuration data and to determine an order in which to perform the set of configuration actions. The artificial intelligence module may be associated with translating the configuration data into a computer-readable form. The device may generate an execution script based on the set of configuration actions or the order in which to perform the set of configuration actions. The device may perform the set of configuration actions.

Abstract: In some examples, immersive and artificial intelligence based retail may include ascertaining attributes associated with a user, identifying a device to display an augmented reality display, a virtual reality display, and/or a mixed reality display, and generating, based on the ascertained attributes and for display on the identified device, a virtual store including a plurality of clothing articles. A clothing article may be selected from the plurality of clothing articles, and based on the selection of the clothing article, a design, a color combination, a texture, and/or a print pattern may be generated based on the clothing article. Further, immersive and artificial intelligence based retail may include generating a display of a plurality of three-dimensional hologram images of the user wearing the clothing article, and determining personalized clothing articles for the user based on selection of a clothing article from the displayed plurality of three-dimensional hologram images.

Abstract: The system and method generally include identifying whether an utterance spoken by a user (e.g., customer) is a complete or incomplete sentence. For example, the system may include a partial utterance detection module that determines whether an utterance spoken by a user is a partial utterance. The detection process may include providing a detection advice code that gives a recommendation for handling the utterance of interest. If it is determined that the utterance is an incomplete sentence, then the system and method can identify the type of utterance. For example, the system may include a partial utterance classification module that predicts the class of a partial utterance. The classification process may include providing a classification advice code that gives a recommendation for handling the utterance of interest.

Abstract: Implementations of the present disclosure include receiving a content image depicting a first set of objects and a style image depicting a second set of objects and a collective style, processing, by the design generation assistant, the content image using one or more ML models to determine a first sub-set of objects, to which a style is to be transferred from the style image, the first sub-set of objects including fewer objects than the first set of objects, processing, by the design generation assistant, the style image using the ML models to determine a second sub-set of objects, from which the style is to be transferred, and generating, by the design generation assistant, an output image with stylized objects, each stylized object including an object in the first sub-set of objects having the style of the one or more objects in the second sub-set of objects.

Abstract: A device may receive, from a user device, a request to access a virtual reality (VR) learning environment that includes an identifier associated with a program that supports the VR learning environment. The device may identify a set of objects to use within the VR learning environment by searching a data structure using the identifier associated with the program that supports the VR learning environment. The device may provide the VR learning environment to the user device. The device may receive, from the user device, information associated with interactions within the VR learning environment. The device may identify one or more additional objects to use within the VR learning environment by using one or more natural language processing techniques to analyze the information associated with the interactions within the VR learning environment. The device may provide the one or more additional objects to the user device.

Abstract: A device may receive historical software data associated with a software development platform, and may train a neural network model, with the historical software data, to generate a trained neural network model. The device may receive, from the software development platform, historical test configuration data, and may train an execution model, with the historical test configuration data, to generate a trained execution model. The device may receive software data identifying software to be tested, and may process the software data, with the trained neural network model, to predict a set of test cases to execute for testing the software. The device may process the set of test cases, with the trained execution model, to identify configurations, scripts, and test targets for executing the set of test cases, and may perform one or more actions based on the set of test cases, the configurations, the scripts, and the test targets.

Abstract: Cloud service based on container technology provides a lightweight, portable, but robust architecture for deploying service applications. Service volume and resource requirement for a typical modern-day application may fluctuate dramatically in time. A dynamic resource allocation scheme based on machine learning algorithms and executed by the cloud for applications deployed as independent containers allows for efficient resource usage and improvement of quality of service for the applications.