Herein are machine learning (ML) techniques for unsupervised training with a corpus of signaling system 7 (SS7) messages having a diversity of called and calling parties, operation codes (opcodes) and transaction types, numbering plans and nature of address indicators, and mobile country codes and network codes. In an embodiment, a computer stores SS7 messages that are not labeled as anomalous or non-anomalous. Each SS7 message contains an opcode and other fields. For each SS7 message, the opcode of the SS7 message is stored into a respective feature vector (FV) of many FVs that are based on respective unlabeled SS7 messages. The FVs contain many distinct opcodes. Based on the FVs that contain many distinct opcodes and that are based on respective unlabeled SS7 messages, an ML model such as a reconstructive model such as an autoencoder is unsupervised trained to detect an anomalous SS7 message.

Systems, methods, and apparatus to monitor mobile Internet activity are disclosed. An example apparatus includes at least one memory, and processor circuitry to execute instructions to at least assign (i) a first port of a proxy server to a first mobile device associated with a first panelist and (ii) a second port of the proxy server to a second mobile device associated with a second panelist, in response to receiving an un-authenticated request for media from at least one of the first, second, or third mobile devices, service the un-authenticated request in response to determining that the un-authenticated request is from an Internet Protocol (IP) address associated with an IP address range representative of devices on a cellular network, and, in response to servicing the un-authenticated request via the first port, store an association between the media and first panelist demographic information associated with the first mobile device.

One disclosed system includes dialer device with a dialer identifier that initiates a call with a receiver device with a receiver identifier over a voice channel. A database stores: interaction data in association with both the receiver identifier and the dialer identifier; a content quality metric in association with the interaction data; and a network topology in which the receiver identifier and the dialer identifier are associated with nodes and are connected by an edge. A server is programmed to: update, based on the content quality metric and the network topology, a rankings associated with the receiver identifier and the dialer identifier; and one of: surface the ranking associated with the dialer identifier and the ranking associated with the receiver identifier to an external searching agent using an external data channel and without using any voice channel; or rank the dialer identifier for an internal searching agent using the ranking.

One example method of operation may include identifying a call from a calling device destined for a mobile device, responsive to identifying a calling device number assigned to the calling device, accessing a call content application programming interface (API), operated by a content delivery device, configured to deliver to the mobile device a first caller identification name (CNAM) or a second CNAM, assigned to the calling device number, determining a context assigned to a mobile device number assigned to the mobile device, selecting one of the first CNAM and the second CNAM based on the context, and assigning the selected CNAM to the call.

One example method of operation may include identifying a call from a calling device destined for a mobile device, identifying a calling device number associated with the calling device and a mobile device number associated with the mobile device, determining whether a stored calling relationship exists between the calling device number and the mobile device number, and appending one of a plurality of caller identification names (CNAM) to the call based on the determination as to whether there is a stored calling relationship.

Systems, methods, and apparatus to monitor mobile Internet activity are disclosed. An example apparatus includes at least one memory, machine-readable instructions, programmable circuitry to execute the machine-readable instructions to at least assign a first port of a proxy server to a mobile device associated with a panelist, cause transmission of configuration data to the mobile device to instruct the mobile device to transmit future requests the first port of the proxy server, obtain a first request for media on the first port originating from the mobile device, and after a determination that the first request originated from an Internet Protocol (IP) address associated with an IP address range representative of devices on a cellular network, service the first request, generate a data association, request the media from an Internet media provider identified in the first request, and cause transmission of the media to the mobile device.

Systems, methods, and apparatus to monitor mobile Internet activity are disclosed. An example system includes at least one processor, and memory including instructions, when executed, cause the at least one processor to in response to obtaining first panelist demographic information associated with a first panelist and second panelist demographic information associated with a second panelist, assign a first port of a proxy server to a first mobile device associated with the first panelist and a second port of the proxy server to a second mobile device associated with the second panelist, the first port different from the second port, transmit configuration information to the first mobile device to instruct the first mobile device to transmit requests for media including a first request to the first port, and in response to obtaining the first request at the first port, store an association between the first panelist demographic information and the media.

One example method of operation may include identifying a call from a calling device destined for a mobile device, responsive to identifying a calling device number assigned to the calling device, accessing a call content application programming interface (API), operated by a content delivery device, configured to deliver to the mobile device a first caller identification name (CNAM) or a second CNAM, assigned to the calling device number, determining a context assigned to a mobile device number assigned to the mobile device, selecting one of the first CNAM and the second CNAM based on the context, and assigning the selected CNAM to the call.

One example method of operation may include identifying a call from a calling device destined for a mobile device, identifying a calling device number associated with the calling device and a mobile device number associated with the mobile device, determining whether a stored calling relationship exists between the calling device number and the mobile device number, and appending one of a plurality of caller identification names (CNAM) to the call based on the determination as to whether there is a stored calling relationship.

In various embodiments, the techniques and supporting systems implement a recursive routing mechanism in hierarchical topological addressed environments to analyze and determine the presence of packet-forwarding errors within an IP network comprising a plurality of network-connected devices. This includes receiving, at a software defined network device, an indication of a potential packet-forwarding error between a first and second device of the plurality of network-connected devices and injecting, by the software defined network device, a test packet at an ingress to the first device. The test packet includes an initial ingress interface location identifying the first device, an alternate ingress interface location identifying the software defined network device and an egress interface location identifying the second device. A determination may then be made as to whether the test packet is received at the second device, thus indicating the existence or lack of routing errors.