Abstract: Detecting damaged packages is disclosed. Transport mechanisms, such as pallets, are equipped with sensors including inertial sensors. The inertial data, in conjunction with characteristics of the packages such as fragility values, can be used to determine whether a package may be damaged. If damage is suspected, the package can be inspected. The ability to detect damage may also use package geometries and the like. When damage is suspected, remedial actions can be performed.

Abstract: A microkernel device is disclosed. The microkernel device includes a microkernel configured to provide a desktop experience using cloud-based resources. The microkernel device includes enough hardware to interact with a user and operate with a network. Resources such as security, identify, processing, virtualization, and storage are provided in the cloud. Operations initiated at the device are performed in the cloud and the results are streamed to the microkernel device and displayed in the user interface.

Abstract: One example method includes generating sound information regarding sound sources in an environment. The sound information is generated by separating and localizing the sound sources. The sound information is then presented as guidance to a user. The guidance may be presented graphically in a user interface, haptically, or in another manner.

Abstract: One example method includes receiving a hybrid/classical algorithm, determining a runtime characteristic of the hybrid/classical algorithm, based on the runtime characteristic, checking a memory availability for execution of the hybrid/classical algorithm, when adequate memory is not available to support execution of the hybrid/classical algorithm, modifying a classical/quantum memory fabric to provide enough memory to support execution of the hybrid/classical algorithm, and orchestrating the hybrid classical/quantum algorithm to an execution environment that includes the classical/quantum memory fabric.

Abstract: One example method includes determining representation bias in a data set. A bias detection engine is trained using a data set that is sufficiently diversified and/or unbiased. Once trained, test data sets can be evaluated by the bias detection engine to determine an amount of representation bias in the test data sets. The representation bias can be visually conveyed to a user and suggestions on how to reduce the representation bias may be provided and/or implemented to reduce the representation bias in the test data set. Suggestions can be implemented by adding or removing data from the test data that will reduce the representation bias.

Abstract: A nanoservice architecture allows a service to include multiple functions or features along with a common skeleton code. Each of the nanoservices in a service may be configured using a common configuration file. The configuration file may include a portion that configures requirements or resources common to all nanoservices and other portions that are specific to associated nanoservices.

Abstract: Embodiments provide secure onboarding of an Information Handling System (IHS). A rendezvous service of an onboarding system is provided with an address of an onboarding service and a token that are both to be provided to the IHS. The IHS is powered for the first time upon a transfer of the IHS to an owner of the IHS. Upon the first powering of the IHS, the IHS initiates a connection with the rendezvous service of the onboarding system. The rendezvous service provides the IHS the token and the address of the onboarding service, where the onboarding service is operated on behalf of the owner. The IHS presents the token to a firewall protecting the onboarding service. In response to the presented token being recognized by the firewall, the firewall authorizes onboarding communications by the IHS with the onboarding service in order to configure the IHS for the owner.

Abstract: Techniques are provided that employ haptic feedback to influence an engagement level of a remote user. One method comprises obtaining sensor data associated with a remote user interacting with educational content items; applying the sensor data to an analytics engine to obtain an engagement status indicating an engagement level of the remote user with the educational content items; and automatically initiating a provision of a haptic feedback signal to the remote user based on the engagement status. The engagement status may comprise an engagement score, and the haptic feedback signal may be sent to the remote user based on an evaluation of the engagement score relative to one or more threshold-based criteria. A type and/or an intensity of the haptic feedback signal can be based on one or more user preferences of the remote user.

Abstract: Methods, apparatus, and processor-readable storage media for artificial intelligence-driven avatar-based personalized learning techniques are provided herein.

Abstract: One example method includes performing sound quality operations. Microphone arrays are used to cancel background noise and to enhance speech. With arrays at each environment of each user participating in a call, a first microphone array can cancel or suppress background noise and a second array can generate enhanced speech for transmission to other users. Thus, for user, the audio signal output by the user's device includes an anti-noise signal to cancel background noise present in the user's environment and enhanced speech from other users.

Abstract: One example method includes creating an image definition file, using the image definition file to create an image that is deployable to an edge device, copying an agent into the image, stripping any user passwords out of the image, and removing any unnecessary packages from the image, and after the stripping and the removing, the image becomes an immutable image. The immutable image may then be deployed to a group of edge devices, and one or more layers of the immutable image may be updated by the agent.

Abstract: One example method includes determining that local resources at an edge site are inadequate to support performance of a function needed by software running on the edge site, invoking a client agent, in response to invoking the client agent, receiving an execution manifest, determining, by the client agent, where to execute the function, wherein the determining comprises identifying a target execution environment for the function and the determining is based in part on information contained in the execution manifest, and transmitting, by the client agent, the execution manifest to a server agent of the target execution environment, and the execution manifest facilitates execution of the function in the target execution environment.

Abstract: Techniques are provided for machine learning-based educational content adaptation based on user personal characteristics. One method comprises obtaining personal characteristics of at least one user; applying the personal characteristics of the at least one user to at least one machine learning model to automatically adapt at least one educational content item for the at least one user using one or more of the applied personal characteristics of the at least one user; and initiating a provision of the at least one automatically adapted educational content item to the at least one user. Technology-related characteristics of the at least one user may also be applied to the at least one machine learning model to further adapt the at least one educational content item for the at least one user using the applied technology-related characteristics.

Abstract: Methods, apparatus, and processor-readable storage media for automatically generating context-based alternative text using artificial intelligence techniques are provided herein. An example computer-implemented method includes generating text captions for an image derived from a web page by processing the image using an artificial intelligence-based image captioning model; determining context information pertaining to the image by processing the image using an artificial intelligence-based context and emotion recognition library; generating context-based alternative text for at least a portion of the image by processing, using at least one artificial intelligence-based alternative text generation model, at least a portion of one or more of the generated text caption(s) for the image and the determined context information pertaining to at least a portion of the image; and performing one or more automated actions based on the generated context-based alternative text.

Abstract: Detecting damaged packages is disclosed. Transport mechanisms, such as pallets, are equipped with sensors including inertial sensors. The inertial data, in conjunction with characteristics of the packages such as fragility values, can be used to determine whether a package may be damaged. If damage is suspected, the package can be inspected. The ability to detect damage may also use package geometries and the like. When damage is suspected, remedial actions can be performed.

Abstract: A method comprises executing a workload acquiring algorithm at a first edge node of a plurality of edge nodes to pull at least one workload of a plurality of workloads from a workload queue corresponding to a second edge node of the plurality of edge nodes. In one example, the first edge node may be a component of a first edge location, and the method may further comprise providing the first edge node with access to one or more workloads from one or more workload queues corresponding to one or more edge nodes from a second edge location different from the first edge location.

Abstract: An edge compute network includes an endpoint device and an information handling system. The endpoint device includes a network interface configured to operate with no open inbound network ports and to provide an outbound request on a predetermined network port. The information handling system includes first and second reverse proxies and instantiates an endpoint orchestrator. The first reverse proxy receives the outbound request and provides the outbound request to the second reverse proxy. The second reverse proxy provides the outbound request to the endpoint orchestrator which authenticates the endpoint device based upon the outbound request and provides authentication information to the endpoint device. The endpoint device authenticates the information handling system based upon the authentication information, and opens the predetermined network port to the information handling system in response to authenticating the information handling system.

Abstract: One example method includes receiving datasets based on one or more instances of sensor data that are received from one or more sensors. The sensor data is associated with an aggregate fragility level that indicates how fragile one or more packages being transported by a movable edge node in an edge environment are. Features that are based on the datasets are extracted. Based on the extracted features, events that indicate anomalous driving patterns for the movable edge node are determined. In response to determining the events, an alarm based on a predetermined threshold that is based on the aggregate fragility level is generated.

Abstract: A method includes receiving inputs for respective users in an edge utility system comprising edge and core computing sites, with a first one of the inputs for a first user characterizing edge resources requested by that user for executing at least a portion of a workload of that user, and a second one of the inputs for a second user characterizing edge resources available from that user for executing at least a portion of a workload of another user. The method includes populating one or more data structures based at least in part on the received inputs, aggregating edge resources of multiple ones of the edge computing sites into an edge network based at least in part on the populated data structures, and utilizing at least a portion of the aggregated edge resources of the edge network to execute at least a portion of a workload of a particular user.

Abstract: One example method includes receiving datasets based on one or more instances of sensor data that are received from one or more sensors. The sensor data is associated with an aggregate fragility level that indicates how fragile one or more packages being transported by a movable edge node in an edge environment are. Features that are based on the datasets are extracted. Based on the extracted features, events that indicate anomalous driving patterns for the movable edge node are determined. In response to determining the events, an alarm based on a predetermined threshold that is based on the aggregate fragility level is generated.