Patent classifications
H04M3/42144
METHOD AND SYSTEM TO SEAMLESSLY UPGRADE AUDIO SERVICES
A method and system to preserve group call audio during a cloud-based group call service upgrade are provided. Audio duplication requests are received and managed through a message broker and instances of an audio distribution service. When a determination is made that an audio distribution service needs to be upgraded, the group call is preserved by generating new instances of the audio distribution service. The new instances of the audio distribution service are added to a queue of the message broker, and old instance of the audio duplication service are gracefully shutdown. Each new instance of the audio distribution service is used to route an audio stream associated with each of the original audio duplication requests, while the olds instances of the audio duplication service are being gracefully shutdown.
Learning gamification and safety control application for mobile devices
An application for mobile devices that enables a server device to control multiple client devices with numerous features and capabilities relevant to both server and client devices, such as learning gamification and safety controls. Running on popular operating systems, this application is compatible with other mobile applications and provides a mechanism for the server device to override internal controls on one or more client devices with ability to configure access controls based on gamification features using parameters that include but not limited to applications, programs, goals, and rewards. This application includes safety and security control features that enables the server device to remotely monitor and control one or more client devices.
Artificial intelligence delivery edge network
Approaches, techniques, and mechanisms are disclosed for accessing AI services from one region to another region. An artificial intelligence (AI) service director is configured with mappings from domain names of AI cloud engines to IP addresses of edge nodes of an AI delivery edge network. The AI cloud engines are located in an AI source region. The AI delivery edge network is deployed in a non-AI-source region. An AI application, which accesses AI services using a domain name of an AI cloud engine in the AI cloud engines located in the AI source region, is redirected to an edge node in the edge nodes of the AI delivery edge network located in the non-AI-source region. The AI application is hosted in the non-AI-source region. The AI services is then provided, by way of the edge node located in the non-AI-source region, to the AI application.
Associating a user service with a telephony identifier
Associating a user service with a telephony identifier. The user service is accessible by a user of a telephony device via an application on the telephony device. The telephony device is operable in a radio telephony network (RTN) and is contactable via the telephony identifier when operating in the RTN. Network equipment: communicates, between the network equipment and the application on the telephony device, first data comprising a communicated token; receives, from the telephony device, second data comprising a received token, wherein the second data is received from the telephony device via an RTN-native service; receives, from a network node in the RTN, the telephony identifier in control signalling associated with the RTN-native service; and based at least on correlating the received token with the communicated token, associates the received telephony identifier with the user service.
Matrix completion and recommendation provision with deep learning
Matrix completion and recommendation provision with deep learning is described. A matrix manager system imputes unknown values of incomplete input matrices using deep learning. Unlike conventional techniques, the matrix manager system completes incomplete input matrices using deep learning regardless of whether an input matrix represents numerical, categorical, or a combination of numerical and categorical attributes. To enable a machine-learning model (e.g., an autoencoder) to complete a matrix, the matrix manager system initially encodes the matrix. This involves normalizing known values of numerical attributes and categorically encoding known values of categorical attributes. The matrix manager system performs categorical encoding by replacing information of a given categorical attribute (e.g., an attribute column) with replacement information for each possible value of the attribute (e.g., new columns for each possible value). The machine-learning model imputes the unknown values based on the encoded matrix and masks indicative of unknown values, numerical attributes, and categorical attributes.
ASSOCIATING A USER SERVICE WITH A TELEPHONY IDENTIFIER
Associating a user service with a telephony identifier. The user service is accessible by a user of a telephony device via an application on the telephony device. The telephony device is operable in a radio telephony network (RTN) and is contactable via the telephony identifier when operating in the RTN. Network equipment: communicates, between the network equipment and the application on the telephony device, first data comprising a communicated token; receives, from the telephony device, second data comprising a received token, wherein the second data is received from the telephony device via an RTN-native service; receives, from a network node in the RTN, the telephony identifier in control signalling associated with the RTN-native service; and based at least on correlating the received token with the communicated token, associates the received telephony identifier with the user service.
Learning gamification and safety control application for mobile devices
An application for mobile devices that enables a server device to control multiple client devices with numerous features and capabilities relevant to both server and client devices, such as learning gamification and safety controls. Running on popular operating systems, this application is compatible with other mobile applications and provides a mechanism for the server device to override internal controls on one or more client devices with ability to configure access controls based on gamification features using parameters that include but not limited to applications, programs, goals, and rewards. This application includes safety and security control features that enables the server device to remotely monitor and control one or more client devices.
Learning Gamification and Safety Control Application for Mobile Devices
An application for mobile devices that enables a server device to control multiple client devices with numerous features and capabilities relevant to both server and client devices, such as learning gamification and safety controls. Running on popular operating systems, this application is compatible with other mobile applications and provides a mechanism for the server device to override internal controls on one or more client devices with ability to configure access controls based on gamification features using parameters that include but not limited to applications, programs, goals, and rewards. This application includes safety and security control features that enables the server device to remotely monitor and control one or more client devices.
ARTIFICIAL INTELLIGENCE DELIVERY EDGE NETWORK
Approaches, techniques, and mechanisms are disclosed for accessing AI services from one region to another region. An artificial intelligence (AI) service director is configured with mappings from domain names of AI cloud engines to IP addresses of edge nodes of an AI delivery edge network. The AI cloud engines are located in an AI source region. The AI delivery edge network is deployed in a non-AI-source region. An AI application, which accesses AI services using a domain name of an AI cloud engine in the AI cloud engines located in the AI source region, is redirected to an edge node in the edge nodes of the AI delivery edge network located in the non-AI-source region. The AI application is hosted in the non-AI-source region. The AI services is then provided, by way of the edge node located in the non-AI-source region, to the AI application.
Multi-channel caller ID database updates
A call pattern associated with a telephone number of a subscriber of a wireless carrier network is monitored. The call pattern is then analyzed via a machine-learning algorithm to classify the subscriber into a subscriber classification category of multiple subscriber classification categories. A determination is made as to whether the subscriber classification category of the subscriber corresponds to a service plan type of a specific wireless service plan subscribed to by the subscriber for the telephone number. When the subscriber classification category fails to correspond to the plan type, an offer of an additional wireless service plan that corresponds to the subscriber classification category of the subscriber is sent to a user device of the subscriber. When the subscriber classification category corresponds to the service plan type, a caller category label is assigned to the subscriber that indicates the subscriber classification category of the subscriber.