Abstract: A method of performing joint analysis of customer device and network numeric data and customer care call language data using graph data modeling, the method comprising receiving live language data associated with a live customer care call from a particular subscriber device, wherein the live language data comprises an indication of a communication issue associated with the particular subscriber device; receiving live numeric data associated with communications of the particular subscriber device; analyzing the live language data, the live numeric data, historical language data associated with customer care calls from a first plurality of subscriber devices, historical numeric data associated with communications of a second plurality of subscriber devices to generate a graph database and identify a candidate cause associated with the communication issue of the particular subscriber device; and initiating, based on the identified candidate cause, an action at the particular subscriber device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting a quality score for transcoded data are disclosed. In one aspect, a method includes the actions of receiving, from an originating device, a request to initiate an audio communication with a terminating device. The actions further include providing, for output, an indication that the originating device is configured to process the given audio data using a first codec and a second codec. The actions further include receiving data indicating a selection of the first codec. The actions further include determining that audio data received or to be received is transcoded from the second codec or another codec. The actions further include determining a likely MOS of audio output by the originating device from processing the transcoded audio data. The actions further include determining an action that is configured to increase the MOS of the audio.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for utilizing an on-device machine learning model are disclosed. In one aspect, a method includes the actions of receiving a model that is trained using machine learning and that is configured to determine a given cause of a given event associated with a computing device that is executing the application. The actions further include accessing device data. The actions further include accessing network data. The actions further include providing the device data, the network data, and data identifying an event associated with the computing device as an input to the model. The actions further include receiving, from the model, data indicating a cause of the event. The actions further include determining an action that remediates the cause of the event. The actions further include performing the action that remediates the cause of the event.

Abstract: Techniques are described herein for locally (e.g., on a user device) assigning a tag to untagged network traffic in order to allocate the network traffic to an appropriate network slice. In embodiments, the techniques may involve receiving network traffic that is untagged, determining information about the network traffic, identifying, based on the information about the network traffic, a set of attribute values associated with the network traffic, and assigning, based on the set of attribute values and based on configuration data, a tag to the network traffic. In embodiments, the network traffic is then allocated to a network slice associated with the assigned tag to be transmitted over a local network connection.

Abstract: Methods and systems for secure caller identification are described herein. In one implementation, when a phone call from a caller is received, a home network may mark a caller ID as trustable in a trusted flag if the caller ID can be verified. The home network may further forward the caller ID and a replica of the flag to a next hop entity until the next hop is the callee. The network on each hop may further verify the caller ID based on a trust relationship between the network and a prior network. In another implementation, the home network of the caller may send a caller ID token (CIT) associated with the caller and send a replica of CIT to a serving network of the callee through one or more networks. The serving network may verify the replica of CIT to determine whether the caller ID is trustable.

Abstract: Aspects of the present disclosure relate to implementing on-device latency detection into operating system (OS)-level functionality of a client device in client-server and/or network communications. An example method includes extracting packet headers from data-connection packets transmitted between a local application client and a remote application server. Data records including packet headers and timestamps are stored. Data records for related data-connection packets (e.g., queries and responses, handshakes) are identified via the packet headers, and timestamps of the identified data records are compared to determine latency measurements. Latency measurements are then distributed to relevant application clients locally residing on an upper layer. The latency measurements are presented in dashboard display to an end user and used for server-side dynamic load balancing.

Abstract: Methods and systems for improving the detection and alert logic by cloud data for a potential harmful or dislike number are described herein. According to an implementation, a computer server, e.g., a telephony application server (TAS), may receive a voice call associated with a phone number to a user. The TAS may determine that the phone number is associated with a category of a potential harmful number or a potential dislike number. The TAS may generate a string indicative of the category and present the string on a user interface of the user device. The TAS may apply a machine learning model to classify an incoming call. The machine learning model may be trained based on one or more voice data metrics such as call duration, call rejection rate, etc. The training may be further supplemented by personal data on the user device to provide accurate classification.

Abstract: Aspects of the present disclosure relate to implementing on-device latency detection into operating system (OS)-level functionality of a client device in client-server and/or network communications. An example method includes extracting packet headers from data-connection packets transmitted between a local application client and a remote application server. Data records including packet headers and timestamps are stored. Data records for related data-connection packets (e.g., queries and responses, handshakes) are identified via the packet headers, and timestamps of the identified data records are compared to determine latency measurements. Latency measurements are then distributed to relevant application clients locally residing on an upper layer. The latency measurements are presented in dashboard display to an end user and used for server-side dynamic load balancing.

Abstract: Aspects of the present disclosure relate to implementing on-device latency detection into operating system (OS)-level functionality of a client device in client-server and/or network communications. An example method includes extracting packet headers from data-connection packets transmitted between a local application client and a remote application server. Data records including packet headers and timestamps are stored. Data records for related data-connection packets (e.g., queries and responses, handshakes) are identified via the packet headers, and timestamps of the identified data records are compared to determine latency measurements. Latency measurements are then distributed to relevant application clients locally residing on an upper layer. The latency measurements are presented in dashboard display to an end user and used for server-side dynamic load balancing.

Abstract: A mobile communication device that replenishes and manages ads to display on an active application. The mobile communication device comprises a radio transceiver, a processor, a memory, a plurality of applications, stored in the memory, wherein each application comprises an ad client, and an ad manager, stored in the memory. The ad manager, when executed by the processor, requests a plurality of ads from an ad gateway associated with the network associated with the mobile communication device. The ad manager then receives a plurality of ads from the ad gateway. The ad manager then stores these ads into an ad cache, embedded within the memory of the mobile communication device. The ad manager receives a request from an ad client of one of the applications for an ad to display. The ad manager sends an ad selected from the ad cache to the ad client in the active application.

Abstract: In a wireless communication device, an operating system directs a first wireless transceiver to support a user application. The first wireless transceiver exchanges user data for the user application. In the wireless communication device, an internet browser identifies when the first wireless transceiver supports the user application and when a second wireless transceiver has wireless connectivity but does not support the user application. The internet browser generates a user prompt to use of the second wireless transceiver to support the user application. The internet browser receives a positive user response to the user prompt and responsively directs the operating system to use the second wireless transceiver to support the user application. The operating system directs the second wireless transceiver to support the user application. In the wireless communication device, the second wireless transceiver exchanges additional user data for the user application.

Abstract: A wireless communication device may be operated to facilitate directing user applications to use WLAN data connections. One of the user applications generates an application request for a URI, and a browser application requests a translation of the URI into an IP address. An LTE transceiver exchanges wireless data with an LTE network to translate the URI into the IP address. A WLAN transceiver detects a WLAN data connection. The browser application identifies that the LTE transceiver is exchanging wireless data with the LTE network and that the WLAN data connection is detected, and responsively processes a WLAN identifier for the WLAN data connection and an application identifier for the user application to determine if a user WLAN notice should be presented. If the WLAN notice should be presented, the browser application generates the user WLAN notice. The user WLAN notice is displayed to the user on a graphical display.

Abstract: A mobile communication device that replenishes and manages ads to display on an active application. The mobile communication device comprises a radio transceiver, a processor, a memory, a plurality of applications, stored in the memory, wherein each application comprises an ad client, and an ad manager, stored in the memory. The ad manager, when executed by the processor, requests a plurality of ads from an ad gateway associated with the network associated with the mobile communication device. The ad manager then receives a plurality of ads from the ad gateway. The ad manager then stores these ads into an ad cache, embedded within the memory of the mobile communication device. The ad manager receives a request from an ad client of one of the applications for an ad to display. The ad manager sends an ad selected from the ad cache to the ad client in the active application.

Abstract: A mobile device comprising a long-range radio transceiver, a first short-range radio transceiver, a processor, a memory, and an application stored in the memory. The application, when executed by the processor, detects an event and in response to detecting the event, selects a reference to a second communication device stored in the memory based on a current location of the mobile communication device, wherein the second communication device comprises a second short-range radio transceiver configured for communication with the first short-range radio transceiver. The application further transmits a redirect message via the long-range radio transceiver to a redirect server application executing on a computer system, wherein the redirect message comprises the reference to the second communication device, whereby voice calls directed to the long-range radio transceiver are redirected to the first short-range radio transceiver via the second short-range radio transceiver of the second communication device.

Abstract: Embodiments of the disclosure are directed to methods and systems for customizing advertising content for use on a mobile communication device. A user may be allowed to customize the advertisement content that is presented on their device. This may be accomplished by monitoring the advertisement activity on the mobile device and then allowing the user to customize advertisements from that monitored activity. The functionality may be provided by a customization application executed by the device, individual communication applications executed by the device, and/or an ad gateway in communication with the device.