Abstract: Provided are an electronic device for deriving a domain connected to the IP address based on Open Source INTelligence (OSINT) information and for deriving the domain connected to the IP address based on an artificial intelligence (AI) model, and a method for the same.

Abstract: Techniques for secure multi-model hosting and experimentation in a cloud provider network are described. A request to perform an action involving one of multiple machine learning (ML) models is received at a cloud provider network. A user associated with the request can be consistently mapped to a particular experience from multiple experiences of an experiment. Based on this experience, a request to use a ML model can be sent by a data plane component that includes a path value associated with the experience. The request can be sent from the data plane component to a private connectivity endpoint, which securely provides the request into another virtual private cloud including the ML models without the request transiting the public internet. The request can be routed via path-based routing and the included path value to a ML model providing the experience.

Abstract: Embodiments relate to a delay control system for improving network coding of bidirectional traffic, and more particularly to a delay control system for improving network coding of bidirectional traffic that sets a path with a constraint on time in an IIoT network and controls new network coding-aware routing capable of efficiently utilizing opportunities for network coding, and the delay control system for improving network coding of bidirectional traffic includes an intermediate node request collector configured to receive a route request (RREQ) packet transmitted from a source node, an intermediate node calculator configured to calculate a deadline between the source node and a destination node based on the RREQ packet received by the intermediate node request collector, and an intermediate node request transmitter configured to transmit the RREQ packet through an optimal path between the source node and the destination node based on the deadline.

Abstract: Systems, methods, and computer program products for adaptively splitting electronic chats are provided. An e-discovery system comprises a computer processor and a non-transitory, computer-readable medium embodying thereon a set of computer instructions executable by the computer processor. The set of computer instructions includes instructions for: sending a chat query to a remote electronic chat service; receiving an electronic chat responsive to the chat query, the electronic chat embodying a set of electronic chat messages; adaptively splitting the set of electronic chat messages into a set of conversations, each conversation in the set of conversations comprising a subset of electronic chat messages from the set of electronic chat messages; and storing each conversation from the set of conversations as a separate document.

Abstract: Recently, there has been a dramatic increase in the development and use of machine learning and artificial intelligence (ML/AI) applications. The exponentially growing complexity of ML/AI models and their voracious data needs have created needs for large but well-designed data centers—even the network topology needs to be critically considered. Presented herein are embodiments of topologies for data center system that comprise both a high bandwidth scale-up fabric and a scale-out fabric. In one or more embodiments, the scale-out fabric may comprise as many rails as allowed by the radix of the switch (i.e., 36 rails for 64-port switches and 72 rails for 128-port switches), and in one or more embodiments, the rails preferably span a minimum number of tiers as possible and reserve the upper tier for the rail crossing function. If the last tier is used for the rail crossing function, it may be oversubscribed.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first network node may receive assistance information indicating an occurrence of at least one dynamic network change, wherein the at least one dynamic network change corresponds to a change from a first network state to a second network state, wherein a first machine learning scheme is associated with the first network state, and wherein the first machine learning scheme includes a machine learning model for generating a prediction associated with a first serving cell and/or a machine tearning parameter associated with the machine tearning model. The first network node may identify, based at least in part on the assistance information, a second machine learning scheme associated with the second network state, and may perform a wireless communication based at least in part on the second machine learning scheme. Numerous other aspects are described.

Abstract: Cost aware routing in a network topology to reduce costs within an egress-based pricing model. A method includes receiving telemetry data from one or more of a network device or a compute device within a cloud computing network, wherein the telemetry data is associated with a customer of the cloud computing network. The method includes retrieving an egress-based pricing scheme associated with a provider of the cloud computing network and provisioning one or more of the network device or the compute device to optimize routing decisions for the customer to reduce a predicted data egress charge for the customer. A route may be selected to traverse multiple clouds and/or colocation providers according to ingress, egress, and transfer charges. Segment routing and VRFs may be used to implement routes selected based on criteria such as cost, latency, throughput, and jitter.

Abstract: Some embodiments provide a method of executing a distributed application with multiple endpoint processing units (EPUs) that perform computations for the distributed application. The EPUs are connected through a network having multiple network elements. The method iteratively provides instructions to the EPUs to perform computations associated with the distributed application. The method stores a result of each EPU computation at the EPU until the result has been forwarded to a destination in the network and a confirmation has been received that the result has successfully been received at its destination in the network.

Abstract: Apparatuses, systems, and techniques to improve federated learning for neural networks. In at least one embodiment, a federated server dynamically selects neural network weights according to one or more learnable aggregation weights indicating a contribution from each of one or more edge devices or clients during federated training according to various characteristics of each edge device or client model and training data.

Abstract: A method for unjoining and rejoining clusters of computing nodes in edge site computing networks to reduce the impact of interruption to connectivity between computing nodes is presented. The method includes accessing a cluster of computing nodes executing on an edge site computing network. The cluster of computing nodes includes a plurality of follower computing nodes and a leader computing node. The method further includes detecting an interruption to connectivity established between the leader computing node and one or more of the plurality of follower computing nodes. In response to detecting the interruption to connectivity, the method includes bifurcating the cluster of computing nodes into a first subcluster of computing nodes and a second subcluster of computing nodes. In response to detecting a restoration of connectivity, the method includes recombining the first subcluster of computing nodes and the second subcluster of computing nodes.

Abstract: Proposed is a method of providing a digital twin service based on reality verification. The method includes receiving, by a first server, workplace information including a workplace location from a first application running on a mobile terminal of a first user who manages a workplace existing in the real world, and registering the workplace information newly, and forwarding, by the first server, the workplace information newly registered in a database to a second server that online services a metaverse obtained by digitizing the real world so that a virtual workplace for the workplace is implemented at the same location in the metaverse.

Abstract: A video stream acquisition method, apparatus and system, a device and a medium are provided. The video stream acquisition method is applied to a user terminal and includes: sending a stream pulling information acquisition request to a media server, to make the media server determine target stream pulling information based on a generated domain name; acquiring the target stream pulling information, performing a domain name resolution on the target stream pulling information based on a preset domain name resolution method, and obtaining the IP address of the target intranet edge server; and based on the IP address of the target intranet edge server, sending a target stream pulling request to the target intranet edge server, and acquiring a target video stream returned by the target intranet edge server based on the target stream pulling request.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for executing generative models for private conversations within protected inference environments. In particular, in some embodiments, the disclosed systems receive an encrypted chat message marked with a private status. In addition, in some embodiments, the disclosed systems generate a decrypted chat message by decrypting the encrypted chat message using a shared session key based on a hardware-backed attestation indicating server-side processing by a trusted execution environment. Moreover, in some embodiments, the disclosed systems generate a re-encrypted chat message by re-encrypting the decrypted chat message with an additional session key established for a private engine instance.

Abstract: According to an example aspect of the present disclosure, there is provided a method comprising receiving by a control apparatus, from a client apparatus, a request for a resource allocation of one or more connected devices on one or more time ranges, receiving by the control apparatus, from an orchestrator apparatus, a work plan for a group of connected devices, wherein the work plan comprises planned positions of the group of connected devices and the group of connected devices comprises said one or more connected devices, computing by the control apparatus, based at least on the work plan, a resource allocation for each of multiple connection points on said one or more time ranges, wherein the resource allocation comprises an assignation of said one or more connected devices to the connected points and transmitting, by the control apparatus, the resource allocation to the client apparatus.

Abstract: An adapter module executing on a computing device of a computing environment is to be used to transmit packets from a network interface card of the computing environment to a control program executing within the computing environment. The adapter module obtains packet information of a packet received at the network interface card. Based on obtaining the packet information, a packet completion queue entry is generated in a packet completion queue and the packet information is stored in the packet completion queue entry. The packet information is to be used to locate a data buffer into which the packet is stored. The packet completion queue entry is provided to the control program to be used by the control program to retrieve the packet from the data buffer.

Abstract: Systems, methods, and devices for managing multiple service flows through a single Customer Premises Equipment (CPE) device to provide differentiated services to multiple customers, which may be at the same or different locations. A CPE device may be configured to create one or more Virtual Local Area Networks (VLAN) tags within the CPE device, each associated with a specific Service Set Identifier (SSID), which segregates service flows based on customer needs and service types. The CPE device may also generate multiple tunnels from a network gateway to the Wi-Fi routers, with each tunnel corresponding to one of the SSIDs. The tunnels facilitate the segregation of service flows to maintain distinct and independent service streams for different customer segments.

Abstract: A system as discussed herein includes communication management hardware. The communication management hardware: receives a first data packet including a first data payload, the first data packet encoded in accordance with a wireless communication protocol for conveyance to a destination network address; maps a first quality of service associated with the first data packet to a first service flow amongst multiple service flows supported by a backhaul network; and forwards the first data packet over the first service flow of the backhaul network for delivery of the first data packet to the destination network address.

Abstract: A method performed by a processing system including at least one processor includes calculating a first set of key performance indicators for a communications network based on data acquired from at least one source that is accessible to an operator of the communications network and publishing at least the first set of key performance indicators via an application programming interface that enables the operator of the communications network to share data with an external client of the communications network.

Abstract: In a method and system for sharing a vehicle location through mobile text message parsing, the method of sharing a vehicle location through mobile text message parsing includes extracting a text message and a mobile phone number of a user from a mobile device of the user, receiving shared data for real-time location sharing with a vehicle of another user from a server based on a parsing result for the text message and the mobile phone number of the user, and providing a real-time location sharing service with respect to the vehicle of the other user according to input by the user for a sharing selection message for selecting whether to share a real-time location with the vehicle of the other user displayed in response to the shared data.

Abstract: There is provided techniques for tracing operations in a network. A method is performed by a wireless device operatively connected to the network. The method comprises performing an operation with respect to a piece of data. The piece of data is associated with an application run in the network. The method comprises tracing the operation in a trace instance. The trace instance comprises an identifier of a span of the trace instance, an initial timestamp from when the span was originally created, and a reference to another span of the trace instance. The method comprises transmitting a CoAP message to an application server of the application. The CoAP message has a header part and a payload part. The payload part comprises the trace instance.