Abstract: For example, a method includes collecting orientation data from a mobile device as a user of the mobile device moves within an indoor space, generating orientation estimates for the mobile device from the orientation data, generating distance estimates representing distances of the mobile device to a wireless access point in the indoor space, storing the orientation estimates and the distance estimates together as a series of data blocks, constructing a plurality of trajectory segments from the orientation estimates, identifying identifiers for a last number of trajectory segments, using data blocks corresponding to the last number of trajectory segments, and identifying a predicted place within the indoor space to which the user is expected to go by using the identifiers to traverse a prediction tree, where branches of the prediction tree that are associated with the identifiers define a path that ends at a leaf node corresponding to the predicted place.

Abstract: The described technology is generally directed towards reducing unwanted cellular network activities, such as phantom 911 calls or other unwanted cellular network activities. Machine learning models described herein can be trained, using device level data and network level data, to identify devices that are likely to engage in an unwanted cellular network activity. A trained machine learning model can be deployed to identify devices, and devices identified by the trained machine learning model can be re-configured to prevent them from engaging in the unwanted cellular network activity. Devices likely to engage in the unwanted cellular network activity are thus identified and reconfigured to prevent future unwanted cellular network activity before it occurs.

Abstract: An artificial intelligence (AI) automation to improve network quality based on predicted locations is provided. A method can include training, by a first device comprising a processor and according to model configuration parameters received from a second device that is not the first device, a local machine learning model with training data derived from first location data collected by the first device; transmitting, by the first device to the second device, anonymized model features associated with the local machine learning model; in response to the transmitting of the anonymized model features, receiving, by the first device from the second device, an aggregated machine learning model; and estimating, by the first device, a future position of the first device by applying the aggregated machine learning model to second location data collected by the first device.

Abstract: The described technology is generally directed towards public service answering point (PSAP) call routing issue detection and resolution. A PSAP call routing issue detection tool is disclosed. The PSAP call routing issue detection tool can be configured to identify PSAP call routing problems in a cellular network. The PSAP call routing issue detection tool can present the PSAP call routing problems for further analysis and correction by cellular network engineers. The PSAP call routing issue detection tool can furthermore identify and suggest call routing corrections to address identified PSAP call routing problems. The PSAP call routing issue detection tool can optionally also automatically correct identified PSAP call routing problems according to suggested call routing corrections.

Abstract: Aspects of the subject disclosure may include, for example, a device comprising: a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising: obtaining a list of a plurality of known cell sites, the list comprising for each known cell site of the plurality of known cell sites a respective set of known geospatial coordinates; obtaining for each set of known geospatial coordinates, a corresponding aerial image; applying each corresponding aerial image to an automated process to generate a model, the model being usable to determine whether a particular test aerial image depicts a cell site; obtaining from a database an identification of an asserted cell site, the identification of the asserted cell site comprising a set of asserted geospatial coordinates; obtaining for the set of asserted geospatial coordinates, a test aerial image; applying the test aerial image to the mo

Abstract: The described technology is generally directed towards an adapting radio access network coverage for location-based alerts. A group of cells and/or cell sectors can be selected for sending an alert, according to selection techniques described herein. The selection techniques can provide a target level of cellular coverage for a geographic area, while avoiding over-inclusion of cells and consequent dissemination of alerts to subscribers outside the geographic area. The target level of coverage can comprise a desired amount of service overlap, to achieve a corresponding level of confidence that subscribers within the geographic area will receive an alert. The selection techniques can furthermore close identified coverage gaps within the geographic area.

Abstract: A system may allow for generic end user mobile devices to be operated using a virtualized personal device framework. The virtualized personal device framework may provide for a collective intelligence network platform that allows offloading of heavy computing processes onto virtual instance in a cloud network and enables crowd sourcing services for smart cities that may provide smart emergency services in which end-users collaborate.

Abstract: Aspects of the subject disclosure may include, for example, receiving network-related information associated with a first RAN that includes a first RIC, obtaining, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, determining, based on the data relating to the AI model and the network-related information associated with the first RAN, that the AI model can be leveraged by the first RAN to improve network performance of the first RAN, performing synchronization with the AI model synchronization system to obtain the AI model, responsive to the determining that the AI model can be leveraged by the first RAN to improve the network performance of the first RAN, and causing the first RIC to deploy the AI model in the first RAN after the performing the synchronization. Other embodiments are disclosed.

Abstract: A method may include a processing system having at least one processor for receiving a first machine learning model, the first machine learning model in a first format associated with a first development environment, adapting the first machine learning model to a containerized environment, validating the first machine learning model according to at least one validation criterion associated with a repository, and publishing the first machine learning model to the repository.

Abstract: Aspects of the subject disclosure may include, for example, receiving network-related information associated with a first RAN that includes a first RIC, obtaining, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, determining, based on the data relating to the AI model and the network-related information associated with the first RAN, that the AI model can be leveraged by the first RAN to improve network performance of the first RAN, performing synchronization with the AI model synchronization system to obtain the AI model, responsive to the determining that the AI model can be leveraged by the first RAN to improve the network performance of the first RAN, and causing the first RIC to deploy the AI model in the first RAN after the performing the synchronization. Other embodiments are disclosed.

Abstract: A method may include a processing system having at least one processor for receiving a first machine learning model, the first machine learning model in a first format associated with a first development environment, adapting the first machine learning model to a containerized environment, validating the first machine learning model according to at least one validation criterion associated with a repository, and publishing the first machine learning model to the repository.

Abstract: Aspects of the subject disclosure may include, for example, receiving network-related information associated with a first RAN that includes a first RIC, obtaining, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, determining, based on the data relating to the AI model and the network-related information associated with the first RAN, that the AI model can be leveraged by the first RAN to improve network performance of the first RAN, performing synchronization with the AI model synchronization system to obtain the AI model, responsive to the determining that the AI model can be leveraged by the first RAN to improve the network performance of the first RAN, and causing the first RIC to deploy the AI model in the first RAN after the performing the synchronization. Other embodiments are disclosed.

Abstract: A system may allow for generic end user mobile devices to be operated using a virtualized personal device framework. The virtualized personal device framework may provide for a collective intelligence network platform that allows offloading of heavy computing processes onto virtual instance in a cloud network and enables crowd sourcing services for smart cities that may provide smart emergency services in which end-users collaborate.

Abstract: Fast-aiding radio access network intelligent controllers (RICs) can assist other RICs that are experiencing performance issues. The system can take into account the availability of other RICs that can aid the RIC needing assistance. Therefore, multiple RICs cooperatively working together can generate synergies, and allow differentiated RICs to operate in both predefined and/or dynamically create RIC groups. Once a RIC that needs assistance is identified, other RICs can offload functionalities that are less important than the functionality of the RIC that is experiencing the performance issues. After the assisting RIC has offloaded its functionalities, it can then devote resources to the RIC that needs the assistance.

Abstract: A system may allow for generic end user mobile devices to be operated using a virtualized personal device framework. The virtualized personal device framework may provide for a collective intelligence network platform that allows offloading of heavy computing processes onto virtual instance in a cloud network and enables crowd sourcing services for smart cities that may provide smart emergency services in which end-users collaborate.

Abstract: Fast-aiding radio access network intelligent controllers (RICs) can assist other RICs that are experiencing performance issues. The system can take into account the availability of other RICs that can aid the RIC needing assistance. Therefore, multiple RICs cooperatively working together can generate synergies, and allow differentiated RICs to operate in both predefined and/or dynamically create RIC groups. Once a RIC that needs assistance is identified, other RICs can offload functionalities that are less important than the functionality of the RIC that is experiencing the performance issues. After the assisting RIC has offloaded its functionalities, it can then devote resources to the RIC that needs the assistance.

Abstract: A system may allow for generic end user mobile devices to be operated using a virtualized personal device framework. The virtualized personal device framework may provide for a collective intelligence network platform that allows offloading of heavy computing processes onto virtual instance in a cloud network and enables crowd sourcing services for smart cities that may provide smart emergency services in which end-users collaborate.

Abstract: A method may include a processing system having at least one processor for receiving a first machine learning model, the first machine learning model in a first format associated with a first development environment, adapting the first machine learning model to a containerized environment, validating the first machine learning model according to at least one validation criterion associated with a repository, and publishing the first machine learning model to the repository.