Abstract: A Network Repository Function (NRF) obtains status data from network functions in a geographic region. The NRF obtains additional status data for other network functions from another NRF in another geographic region. The NRF receives a request and identifies some of the network functions based on the request. The NRF prioritizes the identified network functions based on the status data. The NRF transfers a response that indicates the prioritized network functions.

Abstract: A plurality of tickets can be received. A pattern pertaining to an issue with an application can be determined by at least one artificial neural network. The pattern can be indicated among at least a portion of the plurality of tickets. The portion of the plurality of tickets can be grouped into a group comprising a primary ticket and at least one secondary ticket. Automation steps can be accessed from a database. The automation steps can be implemented to resolve the issue for the primary ticket. Responsive to the resolving the issue by implementing the automation steps from the database for the primary ticket, the secondary ticket can be closed.

Abstract: The technology described herein improves management of core network connectivity in order to limit network connectivity issues from spreading to other areas in the wireless network. A determination that a predetermined threshold of service requests and/or service request failures associated with one or more core network entities in a first geographic area has been exceeded during a first time period serves as the basis for preventing the one or more core network entities from receiving services from a backup UDR during a second period of time, the second time period subsequent to the first time period.

Abstract: A plurality of tickets can be received. A pattern pertaining to an issue with an application can be determined by at least one artificial neural network. The pattern can be indicated among at least a portion of the plurality of tickets. The portion of the plurality of tickets can be grouped into a group comprising a primary ticket and at least one secondary ticket. Automation steps can be accessed from a database. The automation steps can be implemented to resolve the issue for the primary ticket. Responsive to the resolving the issue by implementing the automation steps from the database for the primary ticket, the secondary ticket can be closed.

Abstract: An encoder is trained together with a perception component based on a training set comprising unannotated sensor data sets and annotated sensor data sets in a sequence of multiple training steps.

Abstract: A solution for route selection includes receiving, by a network repository, from a first network function (NF), a query related to a target NF; querying, by the network repository, a route selection node for a shortest path to the target NF; receiving, by the network repository, from the route selection node, an indication of the shortest path to the target NF; and based on at least receiving the indication of the shortest path to the target NF, transmitting, by the network repository, to the first NF, a route to the target NF. In some examples, the shortest path has at least one of: a minimum number of hops, a minimum latency, a minimum jitter, and a minimum weighted transport score. In some examples, the route selection node is co-located with the network repository, which may be a network repository function (NRF).

Abstract: Performing hybrid synchronization of databases in a telecommunication network is described herein. Management and replication of different types of data stored in the databases can be performed differently. Provisioning data stored in the databases can be managed differently from session data stored in the databases. The provisioning data can be managed utilizing synchronous synchronization. The session data can be managed utilizing asynchronous synchronization. The provisioning data can be stored in the databases separately from the session data.

Abstract: A data communication system authenticates a wireless communication device, and in response, determines status information for the wireless communication device. The data communication system receives a telephony request for the wireless communication device. The data communication system delivers a telephony service to the wireless communication device in response to the telephony request and based on the status information.

Abstract: Systems, methods, and computer-readable media are described herein to which dynamically provide indications within a database that a monitored communication protocol is congested or otherwise unavailable. Key performance indicators are monitored on a first wireless communication protocol to determine if it is congested. Once the congestion is determined, the database is updated, and a terminating call application server may then receive an indication that the first wireless communication protocol is congested and may suggest to another communication protocol.

Abstract: A wireless communication network provides a text-messaging service and a voice-calling service to wireless communication devices. The wireless communication network monitors performance of text-messaging functions and voice-calling functions. The wireless communication network prioritizes the text-messaging functions and the voice-calling functions based on their performance. The wireless communication network transfers function lists that prioritize the text-messaging functions and the voice-calling functions by their performance. The wireless communication network wirelessly exchanges text-messaging signaling and voice-calling signaling between the wireless communication devices and the text-messaging functions and the voice-calling functions. Individual ones of the wireless communication devices exchange the text-messaging signaling with selected ones of the text-messaging functions based on the function list that prioritizes the text-messaging functions by their performance.

Abstract: A wireless communication device wirelessly downloads a user application, and in response, wirelessly receives signaling that indicates a wireless network slice for the user application. The wireless communication device wirelessly downloads another user application, and in response, wirelessly receives other signaling that indicates another wireless network slice for the other user application. The wireless communication device executes the user application, and in response, wirelessly transfers a request for the wireless network slice and wirelessly exchanges application data for the user application over the wireless network slice for the user application. The wireless communication device executes the other user application, and in response, wirelessly transfers another request for the other wireless network slice and wirelessly exchanges other application data for the other user application over the other wireless network slice for the other user application.

Abstract: A wireless communication network delivers status information for User Equipment (UE) upon request. A network controller exchanges registration signaling with the UE and exchanges authentication signaling for the UE with a Unified Data Management (UDM). The UDM exchanges the authentication signaling with the network controller and responsively transfers a UDM request for the UE status information to the network controller. The network controller determines the UE status information and transfers the UE status information to the UDM in response to the UDM request. The UDM receive the UE status information from the network controller and transfers the UE status information to a Unified Data Repository (UDR). The UDR receives the UE status information from the UDM and receives a status request for the UE from a network element. The UDR responsively transfers the UE status information for the UE to the network element.

Abstract: A wireless communication network deregisters network functions. In the wireless communication, a network data system receives a deregistration command that indicates a wireless User Equipment (UE) and forwards the deregistration command to a Unified Data Management (UDM). The UDM receives the indication and determines a Data Network Name (DNN) for the wireless UE. The UDM identifies a network controller and a session controller for the wireless UE based on the DNN. The UDM transfers deregistration notifications to the network controller and session controller. The UDM receives a deregistration acknowledgement from the network controller. The UDM directs the network data system to remove stored session data for the session controller. The network data system receives the direction from the UDM and responsively removes stored session data for the session controller.

Abstract: A computer implemented method of training an encoder to extract features from sensor data comprises generating a plurality of training examples, each training example comprising at least two data representations of a set of sensor data, the at least two data representations related by a transformation parameterized by at least one numerical transformation value; and training the encoder based on a self-supervised regression loss function applied to the training examples. The encoder extracts respective features from the at least two data representations of each training example, and at least one numerical output value is computed from the extracted features. The self-supervised regression loss function encourages the at least one numerical output value to match the at least one numerical transformation value parameterizing the transformation.

Abstract: A wireless communication system serves a wireless User Equipment (UE) over a wireless network slice. A serving wireless communication network selects a Uniform Data Repository (UDR) in a target wireless communication network based on the wireless network slice. The serving wireless communication network transfers an information request for the wireless UE across a wireless communication network boundary to the selected UDR in the target wireless communication network. In response to the information request, the selected UDR in the target wireless communication network transfers UE information for the wireless UE across the wireless communication network boundary to the serving wireless communication network. The wireless network slice in the serving wireless communication network serves the wireless UE based on the UE information.

Abstract: It A computer implemented method of training an encoder to extract features from sensor data comprises training a machine learning (ML) system based on a self-supervised loss function applied to a training set, the ML system comprising the encoder. The training set comprises first data representations and corresponding second data representations, wherein the encoder extracts features from each first and second data representation, and wherein the self-supervised loss function encourages the ML system to associate each first data representation with its corresponding second data representation based on their respective features.

Abstract: A computer implemented method of training an encoder to extract features from sensor data comprises training a machine learning (ML) system based on a self-supervised loss function applied to a training set, the ML system comprising the encoder. The training set comprises sets of real sensor data and corresponding sets of synthetic sensor data. The encoder extracts features from each set of real and synthetic sensor data, and the self-supervised loss function encourages the ML system to associate each set of real sensor data with its corresponding set of synthetic sensor data based on their respective features.

Abstract: Embodiments of the present disclosure are directed to systems and methods for improving wireless network services by carrying out various procedures to identify and filter suspect user devices. A network function may monitor a plurality of network service requests from a particular user device and determine, based on the plurality of network services requests, that the requesting user device is engaged in suspicious activity. Upon such a determination, the network function may initiate one or more enforcement actions by communicating an instruction to an equipment identity register to add the requesting user device to a suspect device list stored on a unified data repository.

Abstract: A wireless communication network receives a current message that relates to a user device for delivery to a network function. The network writes the current message to a queue. The network determines if the queue stores one or more prior messages that relate to the user device. The network transfers the current message from the queue for delivery to the network function when the queue does not store the one or more prior messages for the user device. When the queue for the user device does store the one or more prior messages for the user device, the network prioritizes the current message and the one or more prior messages by network function type and transfers the current message and the one or more prior messages that relate to the user device from the queue for delivery to the network function based on the prioritization.

Abstract: A carrier network may detect and prevent completion of SIM swap frauds. For example, a carrier network may, based at least in part on a SIM swap request to replace a first SIM associated with a subscriber with a second SIM, store first information associated with the first SIM. Subsequent to the execution of a SIM swap to replace the first SIM with the second SIM, the carrier network may perform fraud detection on the SIM swap based at least in part on the first information associated with the first SIM stored based at least in part on the SIM swap request and based at least in part on second information associated with the second SIM and based at least in part on the SIM swap being detected as fraudulent by the fraud detection, cause the second SIM to be prohibited from operating with respect to the subscriber.