One exemplary aspect describes systems and methods for determining normal SLE behavior, determining when a SLE exhibits abnormal deterioration, and determining whether to take an action to mitigate what appears to be an indication of an abnormal SLE.

There is a need for solutions that perform predictive natural language processing with improved efficiency and/or accuracy. This need can be addressed by, for example, by detecting an anomaly condition in the service provider system based on affected user activity data items associated with the service provider system; determining affected user profiles, wherein each affected user profile is predicted to experience the anomaly condition; determining, for each group of affected user profiles, affected user intentions based user activity data items associated with the group of affected user profiles; generating a support communication for each affected user profile in the group of affected user profiles based on the affected user intentions for the group; and causing a transmission of each support communication to each affected user profile in the group of affected user profiles.

Many services measure quality of service (QoS) according to abstract metrics based on general heuristics of QoS determinants (e.g., VoIP service providers may presume that QoS is predominantly determined by network performance). However, users' QoS perceptions are often based on their experiences with particular activities of the service, which may utilize different service paths having different QoS determinants. Therefore, QoS may be measured by identifying the activities of the service, and the dependencies among the components of such services; for respective activities and dependencies, identifying a service path from the source to the user, and the segments comprising the service path; measuring the quality of the segments of the service path; and calculating the QoS of the activity according to the QoS of the segments of the service path providing the activity. This approach may yield QoS information of greater relevance to the users' experience and with greater analytic value.

Embodiments determine failures of a network element (NE) in an outside plant utilizing a connectivity trail that indicates NEs starting at the headend and ending at a distribution tap that serves one or more customer premise devices associated to a customer account. Embodiments determine a failed NE that serves the highest number of customers for which a trouble is reported to a ticketing system. Embodiments avoid reporting downstream child NEs that may be performing poorly due to the upstream failed parent NE. Embodiments associate the one or more customer premise devices, and a customer account with respective NEs of the connectivity trail, perform operational metric tests to determine whether a customer premise device associated with a customer account has failed, determine when an NE of the connectivity trail has failed. Embodiments also include rebooting the failed NE and/or notifying a ticketing system accordingly.

Systems and methods for automation of a customer support sorting process are described. A probability that a call from a potential caller will be received by a call system may be determined based at least in part on historical status information and call history information. The historical status information may indicate one or more past operational states of a service network. The call history information may indicate one or more calls received by the call system, as well as a subject matter of each of the one or more calls. If the determined probability satisfies a threshold, a notification to the potential caller may be transmitted. The notification may inform the potential caller of a current operational state of the service network.

In an embodiment, a method is performed by a middleware computing platform and includes maintaining an active user pool comprising a plurality of servicing users. The method also includes exposing a service request interface to a plurality of user-to-user service platforms. The plurality of user-to-user platforms provide independent computing environments that separately execute user-to-user service workflows for requesting users. The method further includes receiving, via the service request interface, a plurality of service requests each from one of the plurality of user-to-user service platforms. In addition, the method includes automatically assigning one or more of the plurality of service requests to a target servicing user of the plurality of servicing users based at least in part on information associated with the service request and availability of the target servicing user. The method also includes exposing a service provider interface to the target servicing user. Furthermore, the method includes displaying, on the service provider interface, one or more service events respectively corresponding to the one or more assigned service requests.

In an embodiment, a method is performed by a middleware computing platform and includes maintaining an active user pool comprising a plurality of servicing users. The method also includes exposing a service request interface to a plurality of user-to-user service platforms. The plurality of user-to-user platforms provide independent computing environments that separately execute user-to-user service workflows for requesting users. The method further includes receiving, via the service request interface, a plurality of service requests each from one of the plurality of user-to-user service platforms. In addition, the method includes automatically assigning one or more of the plurality of service requests to a target servicing user of the plurality of servicing users based at least in part on information associated with the service request and availability of the target servicing user. The method also includes exposing a service provider interface to the target servicing user. Furthermore, the method includes displaying, on the service provider interface, one or more service events respectively corresponding to the one or more assigned service requests.

As disclosed herein an information technology service ticket characterization method includes receiving tickets from one or more client devices during a time period, determining focus windows within the time period where each focus window includes an event window, identifying tickets received within the focus windows, determining a proportion of identified tickets that are related to a service event, and based on the proportion of identified tickets that are related to the service event, assessing the quality of the service event. A corresponding system and computer program product are also disclosed herein.

An information handling system instantiates a hardware configuration generator to generate platform configurations. The hardware configuration generator provides a ranked list of the platform configurations, receives platform customer service request information, provides a ranked list of part numbers associated with the platform configurations based upon the customer service request information, and modifies the ranked list of platform configurations based upon the ranked list of part numbers.

An information handling system instantiates a hardware configuration generator to generate platform configurations. The hardware configuration generator provides a ranked list of the platform configurations, receives platform customer service request information, provides a ranked list of part numbers associated with the platform configurations based upon the customer service request information, and modifies the ranked list of platform configurations based upon the ranked list of part numbers.