In one embodiment, a service that monitors a network detects a plurality of anomalies in the network. The service uses data regarding the detected anomalies as input to one or more machine learning models. The service maps, using a conceptual space, outputs of the one or more machine learning models to symbols. The service applies a symbolic reasoning engine to the symbols, to rank the anomalies. The service sends an alert for a particular one of the detected anomalies to a user interface, based on its corresponding rank.

Example techniques for adaptive time window-based log message deduplication are described. In an example, message values are obtained from received log messages. Further, the number of log messages received in a time window having a message value is counted. A log message from which the message value is obtained and the counted number are transmitted upon expiry of the time window. A length of a time window in which a subsequent counting of log messages is to be performed is determined based on various parameters.

A method and apparatus are disclosed of providing a user application with a notification message. One example method may include receiving a script to setup a message queue, the script may include a database schema and the script may be executed by a processor to apply the database schema to a database that includes the message queue. The method may also include receiving one or more notifications messages having specific notification content that is applied to notification messages. The notifications may be received from a remote device. The message queue may include notification content used to generate notification messages destined for end user devices.

Systems, apparatuses, methods, and computer program products are disclosed for automating incident severity classification. An example method includes receiving, by communications circuitry, a historical incident dataset, the historical incident dataset including information regarding a set of historical incidents and an assigned severity classification for each historical incident in the set of historical incidents. The example method further includes training, by a model generator and using the historical incident dataset, a machine learning model to classify incident severity. The example method further includes receiving, by the communications circuitry, a new incident dataset, generating, by a prediction engine and using the trained machine learning model and the new incident dataset, a set of predicted severity classifications for the set of new incidents, and outputting, by the communications circuitry, the predicted set of severity classifications for the set of new incidents.

A wireless communication network manages a wireless access node. The wireless access node wirelessly exchanges user data with wireless User Equipment (UEs) and exchanges the user data with one or more network elements. The wireless access node generates status indicators that characterize wireless access node operation during the user data exchanges. An Element Management System (EMS) determines EMS load based on EMS operation and transfers load data that indicates the EMS load for delivery to the wireless access node. The wireless access node receives the load data transferred by the EMS. The wireless access node identifies individual priorities for individual ones of the status indicators. The wireless access node determines individual reporting times for the individual ones of the status indicators based on the load data and the individual priorities. The wireless access node transfers the individual ones of the status indicators to the EMS per the individual reporting times.

A system for troubleshooting network problems is disclosed. A model can use demographic information, network usage information, and network membership information to determine an importance of a problem. The importance of the problem for the user who reported the problem, a number of other users affected by the problem, and the importance of the problem to the other users can be used to determine a priority for resolving the problem. Before and after a work order is executed to resolve the problem, network metrics can be gathered, including aggregate network metrics, and automatically presented in various user interfaces. The analysis of the metrics can be used to update a database of which work orders are assigned in response to which problems.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a warning message comprising a first indication of a priority of the warning message and a second indication that identifies an event. The UE may transmit a repetition of the warning message based at least in part on the first indication. Numerous other aspects are described.

Example techniques for adaptive time window-based log message deduplication are described. In an example, message values are obtained from received log messages. Further, the number of log messages received in a time window having a message value is counted. A log message from which the message value is obtained and the counted number are transmitted upon expiry of the time window. A length of a time window in which a subsequent counting of log messages is to be performed is determined based on various parameters.

A method, including receiving, from multiple sources, respective sets of incidents, and respective suspiciousness labels for the incidents. A set of rules are applied so as to assign training labels to respective incidents in a subset of the incidents in the received sets. For each given incident in the subset, the respective training label is compared to the respective suspiciousness label so as to compute a respective quality score for each given source. Any sources having respective label quality scores meeting a predefined criterion are identified, and a model for computing predicted labels is fit to the incidents received from the identified sources and the respective suspiciousness labels of the incidents. The model is applied to an additional incident received from one of the sources to compute a predicted label for the additional incident, and a notification of the additional incident is prioritized in response to the predicted label.

A system, method, and computer program product are provided for a determining a network situation in a communication network. In use, at least one threshold value of at least one operational parameter of a communication network is obtained, the at least one operational parameter representing at least one operational status of at least one of a computational device or a communication device. Additionally, log data of the communication network is obtained, the log data containing at least one value of the at least one operational parameter reported by at least one network entity of the communication network. The at least one value of the at least one operational parameter of the log data is compared with a corresponding threshold value of the at least one threshold value to form a detection of a network situation. Further, the detection of the network situation is reported if the at least one value of the at least one operational parameter of the log data traverses the corresponding threshold value of the at least one threshold value.