Abstract: A device may receive building location information associated with a multi-unit building. The device may obtain an image that depicts the multi-unit building. The device may process, using a building analysis model, the image to identify exterior access features of the multi-unit building. The building analysis model may be trained based on a plurality of historical images of other exterior access features. The device may determine, using a scoring system and based on a configuration of exterior access features that are identified by the building analysis model, an exterior accessibility score of the unit. The device may perform, based on the exterior accessibility score, an action associated with qualifying the unit for installation of a service that involves access, from the unit, to an exterior of the multi-unit building.

Abstract: A system described herein, such as an Session Management Function (“SMF”) of a core network of a wireless network, may receive a request to associate a particular User Equipment (“UE”) with a plurality of Internet Protocol (“IP”) addresses. The UE may be associated with a communication session between the UE and the core network. The system may output an information request for IP address authorization information from a UE information repository associated with the wireless network, and may receive a response to the information request from the UE information repository. The system may identify a quantity of IP addresses based on the response to the information request, and may provide the identified quantity of IP addresses to the particular UE in response to the request to associate the particular UE with the plurality of IP addresses.

Abstract: A system described herein may receive, from a policy element of a core of a wireless network, a set of triggers associated with a plurality of radio frequency (“RF”) bands implemented by a radio access network (“RAN”). The system may identify that a User Equipment (“UE”) is connected to the RAN via a first RF band, and may identify a subsequent connection of the UE to the RAN via a second RF band. The system may identify that a particular trigger, of the set of triggers, is satisfied based on the subsequent connection of the UE to the RAN via the second RF band, and may indicate, to the policy element, that the particular trigger has been satisfied. The policy element may output a second set of UE policies for communications between the UE and the core of the wireless network based on the satisfaction of the particular trigger.

Abstract: In the present disclosure, systems and methods are disclosed for improving the quality and performance of communications between a User Equipment (UE) and a base station of an access network by inducing the base station to modify a configuration parameter corresponding to the connection with the UE. In some embodiments, during and/or after a connection has been established between the UE and the base station, the UE can determine an adjusted Channel Quality Indicator (CQI) value based on a signal parameter and an adjustment value, and report the adjusted CQI value to the base station.

Abstract: An illustrative UE locator system determines a time measurement indicative of a signal travel time between a UE device and an access point device. The signal travel time corresponds to an apparent distance, presuming a line-of-sight (LoS) signal travel path, between a location of the UE device and a location of the access point device. The UE locator system also accesses, from a bias suppression datastore, bias suppression data configured for use in suppressing an influence of a bias between the apparent distance and a true distance between the location of the UE device and the location of the access point device. The bias is associated with a non-line-of-sight (NLoS) signal travel path between the UE device and the access point device. Based on the time measurement and the bias suppression data, the UE locator system estimates the location of the UE device. Corresponding methods and systems are also disclosed.

Abstract: A system described herein may identify a set of radio frequency (“RF”) bands implemented by a particular base station of a RAN of a wireless network. The system may identify a first measure of hand-ins, associated with a particular time period, to the base station via a first RF band of the set of bands, and identify a second measure of hand-ins, associated with the particular time period, to the base station via a second RF band of the set of bands. The system may rank the first and second RF bands based on the respective associated first and second measures of hand-ins, select a particular RF band based on the ranking, and may cause the particular base station to implement, during the particular time period, a power saving technique with respect to the selected particular RF band.

Abstract: An improved discontinuous reception (DRX) mechanism is disclosed. In one embodiment, a method is disclosed comprising receiving a request to attach to a cellular network from user equipment (UE). The method then identifies a group identifier associated with the UE and determines a DRX parameter based on the group identifier. Finally, the method transmits the DRX parameter to the UE.

Abstract: A system described herein may record, to a distributed ledger, information associating a particular application with a particular set of Quality of Service (“QoS”) information. A particular Multi-Access/Mobile Edge Computing (“MEC”) device operator system may access the distributed ledger to identify the information associating the particular application with the particular set of QoS information. The system may read, from the distributed ledger, MEC configuration information indicating that the MEC device operator system has configured one or more MEC devices, of a plurality of MEC devices to provide the particular application in accordance with the particular set of QoS information. The system may select a particular MEC device, from the plurality of MEC devices, based on a request and further based on the MEC configuration information, and may output an indication of the selected particular MEC device in response to the request.

Abstract: A device sends, based on information indicating that a primary backhaul link of a private network is down, at least one message to a controller of the private network. The at least one message indicates that the controller is to activate at least one route condition policy, and the at least one message, when received by the controller, is to cause the controller to activate the at least one route condition policy. The device sends, based on the information, at least one additional message to a baseband unit (BBU) of the private network. The at least one additional message indicates that the BBU is to apply one or more spectrum sharing parameters for the private network, and the at least one additional message, when received by the BBU, is to cause the BBU to apply the one or more spectrum sharing parameters.

Abstract: A cleaning station may include an input nest that receives a device and transfers the device to a first rotation nest. The first rotation nest may position the device under a first nozzle and rotational nozzles. The first nozzle may clean a first face of the device with dry ice pellets, and the rotational nozzles may clean a first pair of sides of the device with dry ice pellets. The first rotation nest may rotate the device ninety degrees, and the rotational nozzles may clean a second pair of sides of the device with dry ice pellets. A second rotation nest may remove the device from the first rotation nest and may position the device over a second nozzle. The second nozzle may clean a second face of the device with dry ice pellets, and the second rotation nest may transfer the device to an output nest.

Abstract: A device may generate first scores for sentences of text based on a cumulative frequency of words in each sentence, may generate second scores for the sentences based on a cumulative frequency of domain entities in each sentence, and may generate third scores for the sentences based on a sentiment analysis of each sentence. The device may generate a summary of the text, may filter the sentences to extract a first set of sentences, may filter the sentences to extract a second set of sentences, and may filter the sentences to extract a third set of sentences. The device may identify and assign weights to a first group of sentences, a second group of sentences, and a third group of sentences, may generate a ranked list of sentences based on the weighted first group, second group, and third group, and may perform actions based on the final summary.

Abstract: A system described herein may identify a plurality of records recorded to a blockchain, and may identify a particular record of the plurality of records that includes a particular indicator that the particular record is associated with a particular event. The particular indicator may indicate a type of off-chain event. The system may perform, based on identifying the particular record that is associated with the particular event, one or more off-chain actions associated with the particular event. The performed off-chain event may be the indicated type, out of a plurality of possible types of events to perform. The system may record, to the blockchain, an indication that the one or more off-chain actions associated with the particular event have been performed. The event may include an identifier, which the system may also record to the indication that the one or more off-chain actions have been performed.

Abstract: Disclosed is a system comprised of different points-of-presence (“PoPs”) that provide software defined hybrid private and public networking for different entity sites. A system PoP may establish and/or maintain different network circuits for accessing different destinations or services. The system PoP may receive a tunnel creation request from a particular site, may obtain entity-defined policies that are specified for the particular site, and may establish a particular network tunnel to the particular site. The system PoP may then route egress traffic with a first classification through a first network circuit with a different quality of service (“QoS”) than egress traffic with a second classification according to the policies. Similarly, the system PoP may route ingress traffic arriving over the first network circuit through the particular network tunnel with a different QoS than ingress traffic arriving over the second network circuit according to the policies.

Abstract: A method, a device, and a non-transitory storage medium are described in which a network slice selection service is provided. The service may include using route selection policies that includes radio frequency criteria for selection of a network slice. The service may include establishing an application session based on the route selection policies. The service may further include determining that a radio frequency of the network slice cannot be sustained. The service may include executing an application session release procedure and an application session establishment procedure. The procedures may include using cause data and context data pertaining to the initial application session to re-establish the application session via a different network slice and a different radio frequency based on the route selection policies.

Abstract: A device may receive a simulation start command and status data indicating that network elements are ready to process data for multiple simulations. The device may align a time slot to zero, and may define a simulation start time, for the multiple simulations, based on the simulation start command and the status data. The device may define a verification start time, for the multiple simulations, based on the simulation start command, the status data, the time slot, and a system frame number being zero, and may define a network frame number that increments when the verification start time changes from zero to one. The device may cause the multiple simulations to be executed by the network elements, based on the time slot, the system frame number, and the network frame number, and may receive synchronized simulation results based on causing the multiple simulations to be executed by the network elements.

Abstract: Techniques for analyzing audiovisual content, such as streaming content are disclosed. In one embodiment, a method is disclosed comprising obtaining a frame of audiovisual content, using a video decoder to decode compressed model weights of at least one trained model, using the at least one trained model with the decoded weights to analyze the frame and extract content based on the analysis, using the extracted content to make a determination that the audiovisual content comprises a category of content, and causing actionable information to be transmitted to a client device of a user in response to the determination that the audiovisual content comprises the category of content.

Abstract: A system described herein may provide a technique for generating one or more predictive models of device availability, which may be used to predict whether a given device will be able to be reached via one or more networks to receive information, such as Over-the-Air (“OTA”) updates. The predictive models may be based on, for example, radio frequency (“RF”) metrics, device availability metrics, and timing offsets between times associated with such RF metrics and availability metrics. For a given device, based on RF metrics associated with the device and further based on a candidate time, the predictive model may be used to determine whether the device will be available at the candidate time.

Abstract: A system described herein may receive a request to associate a protocol data unit (“PDU”) session, between a particular User Equipment (“UE”) and a network, with multiple network slices. The system may provide the particular PDU session identifier to a first set of network devices that are associated with the first slice, and to a second set of network devices that are associated with the second slice. The network may route first traffic, received from the UE, to the first set of network devices based on the first traffic including the particular PDU session identifier and the identifier of the first network slice. The network may route second traffic, received from the UE, to the second set of network devices based on the second traffic including the particular PDU session identifier and the identifier of the second network slice.

Abstract: In some implementations, a network device may receive a set of key performance indicators (KPIs) associated with a network node. The network device may determine a KPI embedding associated with the set of KPIs. The network device may receive an image of a radio frequency (RF) environment associated with the network node. The network device may determine an RF environment embedding associated with the image of the RF environment. The network device may determine a joint embedding based on the KPI embedding and the RF environment embedding. The network device may determine at least one configuration parameter for the network node based on the joint embedding.

Abstract: In some aspects, the techniques described herein relate to a method including: retrieving properties associated with a plurality of machine learning (ML) models; building a graph data structure using the properties, the graph data structure including nodes corresponding to the properties and edges representing connections between the properties; training a multi-stack message-passing graph neural network (MSMPGNN) using the graph data structure; inputting a graph fragment into the MSMPGNN; generating a prediction based on the graph fragment using the MSMPGNN; and displaying the prediction to a user.