Abstract: In some examples, a controller dynamically configures a property associated with monitoring performed by an agent. The controller stores, in a repository, metadata relating to the agent. The controller receives, from the agent, first sensor data that excludes the metadata, and uses indexing information in the first sensor data to retrieve the metadata from the repository.

Abstract: Systems, methods, and computer program products for configuring labelers, including machine learning labelers are provided. A declarative model describes a processing graph of labelers for a use case at logical level. The declarative model defines a configuration for each labeler in the processing graph of labelers in a declarative language. Each labeler in the processing graph of labelers can represent a wrapper on executable code. The declarative model is interpreted to implement the processing graph of labelers, which is executed to label a set of data records.

Abstract: Systems, methods, and computer program products for agnostic machine learning inference are provided. A computer system, such as a labeling platform, uses a machine learning (ML) model inference configuration to configure an inference environment to use an ML model to process labeling requests. The ML model inference configuration is agnostic to the particulars of the ML platform being used. An adapter maps the ML model inference configuration to an ML platform specific format to instantiate a running system on a given platform.

Abstract: A computer-implemented method for ML platform-agnostic machine learning (ML) training, the method comprising: providing a set of adapters to map an ML platform agnostic format to a plurality of ML platform specific formats; receiving, at a labeling platform, a use case associated with a use case type, the use case comprising configuration information for an ML model, the configuration information formatted according to the ML platform agnostic format; using an adapter, from the set of adapters, that corresponds to the selected ML platform, mapping the configuration information from the ML platform agnostic format to an ML platform specific format of the selected ML platform; and training the ML model using the selected ML platform and a set of training data.

Abstract: One embodiment includes a computer-implemented data labeling platform. The platform provides a confidence-driven workflow (CDW) executable to receive and process labeling requests to label data items. The CDW comprises a set of executable labelers, each labeler in having a dynamically modeled confidence range. The execution path for processing a labeling request to label a data item is dynamically determined.

Abstract: In some examples, a controller dynamically configures a property associated with monitoring performed by an agent. The controller stores, in a repository, metadata relating to the agent. The controller receives, from the agent, first sensor data that excludes the metadata, and uses indexing information in the first sensor data to retrieve the metadata from the repository.

Abstract: Systems, methods and products for optimization of a machine learning labeler. In one method, labeling requests are received and corresponding label inferences are generated using a champion model. A portion of the labeling requests and corresponding inferences is selected for use as training data, and labels are generated for the selected requests, thereby producing corresponding augmented results. A first portion of the augmented results are provided as training data to an experiment coordinator, which then trains one or more challenger models using these augmented results. A second portion of the augmented results is provided as evaluation data to a model evaluator, which evaluates the performance of the challenger models and the champion model. If one of the challenger models has higher performance than the champion model, the model evaluator promotes the challenger model to replace the champion model.

Abstract: One embodiment includes a computer-implemented data labeling platform. The platform provides a confidence-driven workflow (CDW) executable to receive and process labeling requests to label data items. The CDW comprises a set of executable labelers, each labeler in having a dynamically modeled confidence range. The execution path for processing a labeling request to label a data item is dynamically determined.

Abstract: Systems and methods for improving efficiency in performing service actions for one or more storage systems are described. In one embodiment, the systems and methods include detecting a service event on at least one of one or more storage systems based at least in part on monitoring events on the one or more storage systems, creating a service action based at least in part on detecting the service event, adding the service action to a list of pending service actions associated with the one or more storage systems, and assigning one or more service actions from the list of pending service actions to a service window. In some cases, each service event in the list of pending service events represents an adverse condition awaiting repair in relation to at least one of the one or more storage systems.

Abstract: Systems and methods for improving efficiency in performing service actions for one or more storage systems are described. In one embodiment, the systems and methods include detecting a service event on at least one of one or more storage systems based at least in part on monitoring events on the one or more storage systems, creating a service action based at least in part on detecting the service event, adding the service action to a list of pending service actions associated with the one or more storage systems, and assigning one or more service actions from the list of pending service actions to a service window. In some cases, each service event in the list of pending service events represents an adverse condition awaiting repair in relation to at least one of the one or more storage systems.

Abstract: Systems and methods for a self-learning event response engine of systems are described. In one embodiment, the systems and methods may include identifying two or more patterns of events among a plurality of detected events stored in a database, identifying an adverse condition of the storage system that occurs as a result of a particular pattern of events from the identified patterns of events, identifying a corrective action that resolves the adverse condition of the storage system, detecting an occurrence of one or more events from the particular pattern of events, and implementing the corrective action based at least in part on detecting the occurrence of the one or more events from the particular pattern of events.

Abstract: Systems and methods are disclosed for provisioning resources from a first user account to a second user and wearable device for use in a secure transaction. The system may include an electronic payment system having an account for a first user who may allocate funds to a second user's wearable device for utilization in an electronic payment transaction. The recipient and the recipient's device are authenticated to the electronic payment system. The first user may establish automated allocation rules for funding the second user's device and restrictions on the use of the funds. The wearable device may be a bracelet including a sensing element detecting when the recipient is wearing the device, a secure element storing authentication information and a transaction module facilitating the secure transaction and disabling the bracelet when the sensing element detects the bracelet is not properly secured to the recipient.

Abstract: A system or a method is provided that detects or establishes a connected network of personal or wearable devices of a user whereby the number and type of devices connected to that network are used to determine a security or confidence level for a particular transaction being attempted. The personal or wearable devices may include one or more of a smart watch, a mobile phone, a car, a smart belt buckle, smart key fob, or any other personal or wearable devices. Information indicating the number and composition on the various connected devices may be communicated from a user device requesting a payment transaction to a merchant or a payment service provider. The information indicating the number and composition of connected devices may be used for risk assessment to determine the confidence level or security level for the transaction requested by the user.

Abstract: A system and method includes a first device with one or more processors coupled to a memory and reads instructions from the memory to perform the step of receiving a first NFC communication from a master device and enabling payment capabilities of the first device based on the first NFC communications from the master device.

Abstract: Provided is a photocatalytic air purification vehicle wrap for at least partially covering an exterior surface of a vehicle. The vehicle wrap comprises a film or laminate material comprising a first surface area and a second surface area, the first surface area adapted to adhere to the exterior surface of the vehicle. The vehicle wrap further comprises a coating layer disposed on the second surface, the coating layer comprising a titanium dioxide solution cured onto the film or laminate material with ultraviolet radiation, wherein the coating layer is an outermost layer of the vehicle wrap such that the cured titanium dioxide solution is exposed to air surrounding the vehicle when the first surface area is adhered to the exterior surface of the vehicle.

Abstract: Embodiments of the present invention and provide a method for distributed virtual machine (VM) image management in a cloud computing management includes receiving in a hypervisor executing in memory of a host computer, a request for VM image data from a VM and determining whether or not the requested VM image data is present in a local cache of either the hypervisor of the host computer or in a cache of a hypervisor of a peer host. The method additionally includes retrieving the requested VM image data from a seed image in a remote data store in the cloud computing environment only when it is determined that the VM image data neither is present in the local cache of the hypervisor of the host computer nor is present in the cache of the hypervisor of the peer host.

Abstract: Provided is a photocatalytic air purification vehicle wrap for at least partially covering an exterior surface of a vehicle. The vehicle wrap comprises a film or laminate material comprising a first surface area and a second surface area, the first surface area adapted to adhere to the exterior surface of the vehicle. The vehicle wrap further comprises a coating layer disposed on the second surface, the coating layer comprising a titanium dioxide solution cured onto the film or laminate material with ultraviolet radiation, wherein the coating layer is an outermost layer of the vehicle wrap such that the cured titanium dioxide solution is exposed to air surrounding the vehicle when the first surface area is adhered to the exterior surface of the vehicle.

Abstract: Embodiments of the present invention and provide a method for distributed virtual machine (VM) image management in a cloud computing management includes receiving in a hypervisor executing in memory of a host computer, a request for VM image data from a VM and determining whether or not the requested VM image data is present in a local cache of either the hypervisor of the host computer or in a cache of a hypervisor of a peer host. The method additionally includes retrieving the requested VM image data from a seed image in a remote data store in the cloud computing environment only when it is determined that the VM image data neither is present in the local cache of the hypervisor of the host computer nor is present in the cache of the hypervisor of the peer host.