Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a machine learning model to determine predicted client intent classifications and generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client intent classifications and corresponding intent classification probabilities. The disclosed systems utilize the predicted client disposition classifications and the disposition classification probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to determine predicted client intent classifications and/or client-agent escalation classes to generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client-agent escalation classes and corresponding probabilities. The disclosed systems utilize the predicted client-agent escalation classifications and the escalation class probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a machine learning model to determine predicted client intent classifications and generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client intent classifications and corresponding intent classification probabilities. The disclosed systems utilize the predicted client disposition classifications and the disposition classification probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.

Abstract: A cooling system may include a tank filled with a first cooling fluid. The cooling system may include a container including a chamber, the chamber receiving a heat-generating component, the container being sealed, the container being at least partially submerged in the first cooling fluid in the tank, the container including a second cooling fluid.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to determine predicted client intent classifications and/or client-agent escalation classes to generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client-agent escalation classes and corresponding probabilities. The disclosed systems utilize the predicted client-agent escalation classifications and the escalation class probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a machine learning model to determine predicted client intent classifications and generate personalized digital text reply options within an automated interactive digital text thread. For example, disclosed systems utilize the machine learning model to generate predicted client intent classifications and corresponding intent classification probabilities. The disclosed systems utilize the predicted client disposition classifications and the disposition classification probabilities to generate personalized digital text reply options. Moreover, the disclosed systems can provide personalized digital text reply options to a client device within an automated interactive digital text thread, bypassing the inefficiency of menu options or protocols utilized to guide clients to terminal information.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN includes one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWc). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWc techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN includes one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWc). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWc techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN includes one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWc). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWc techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN includes one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWc). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWc techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN is configured with one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWC). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWC. Techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described which apply a method for including a routing stack to provide a timely way to dynamically learn about route changes for an end to end system in the context of an adaptive private network (APN). By allowing learned routes to be assigned different services based on filtering rules, the APN can efficiently manage traffic through the WAN. Techniques for learning routes and to advertise the learned routes in different networks are also described. Upon an APN route change being detected in the APN, a route table is updated with the APN route change, wherein the route table contains routes in a local area network (LAN) and routes in a wide area network (WAN). The APN route change is selected from the route table and configured to a protocol for the LAN. The selected APN route change is advertised in the protocol to local routers in the LAN.

Abstract: Techniques are described to automatically activate and deactivate standby backup paths in response to changing bandwidth requirements in an adaptive private network (APN). The APN is configured with one or more regular active wide area network (WAN) links in an active mode and an on-demand WAN link in a standby mode. The on-demand WAN link is activated to supplement the conduit bandwidth when an available bandwidth of the conduit falls below a pre-specified trigger bandwidth threshold and the conduit bandwidth usage exceeds a usage threshold of a bandwidth of the conduit that is being supplied by the active paths (BWC). The on-demand WAN link is deactivated to standby mode when an available bandwidth of the conduit is above the pre-specified trigger bandwidth threshold and the conduit bandwidth usage drops below the usage threshold of BWC. Techniques for adaptive and active bandwidth testing of WAN links in an APN are also described.

Abstract: Techniques are described which apply a method for including a routing stack to provide a timely way to dynamically learn about route changes for an end to end system in the context of an adaptive private network (APN). By allowing learned routes to be assigned different services based on filtering rules, the APN can efficiently manage traffic through the WAN. Techniques for learning routes and to advertise the learned routes in different networks are also described. Upon an APN route change being detected in the APN, a route table is updated with the APN route change, wherein the route table contains routes in a local area network (LAN) and routes in a wide area network (WAN). The APN route change is selected from the route table and configured to a protocol for the LAN. The selected APN route change is advertised in the protocol to local routers in the LAN.

Abstract: A method, non-transitory computer readable medium, and apparatus that quantitatively assesses the impact of a project change request to software quality including determining at least one initial project request defect value based on an initial project request effort value and a defect insertion rate, determining at least one project change request defect value based on a project change request effort value and the defect insertion rate, comparing at least one project change request defect value to at least one initial project request defect value, and providing a quality impact value based on the result of the comparison.

Abstract: A method, non-transitory computer readable medium, and apparatus that quantitatively assesses the impact of a project change request to software quality including determining at least one initial project request defect value based on an initial project request effort value and a defect insertion rate, determining at least one project change request defect value based on a project change request effort value and the defect insertion rate, comparing at least one project change request defect value to at least one initial project request defect value, and providing a quality impact value based on the result of the comparison.