T-mobile Usa, Inc.

Ruchir Sinha

Prem Kumar Bodiga

Rami Al-Kabra

Jonathan Patrick Morrow

Aaron Drake

Chuong Phan

Noah Dahlstrom

Aditi Saluja

Anandajothi Muttayane

Scott Toborg

Jeffery A Smith

Kameswaran Arunachalam

Tatiana Dashevskiy

Douglas Galagate

Eric Yatskowitz

Rajesh Gulati

Maheshkumar Nagarajan

Ijaz Ahamed Meeran Abdul Jabbar

Chabuk Savar Baquer Ali

Systems and methods for predicting throughput in a network are described herein. The systems and methods use, in some examples, impaired DNS lookup times to predict what a throughput measurement would have been at the time of the issue had a measurement been taken. Using impaired DNS lookup times rather than constantly measuring throughput can reduce the workload of the cellular network while also reducing the storage capacity needed to measure throughput values for all of the devices using the cellular network. Throughput prediction may be used in other ways, including, but not limited to, device testing and assessment.

Systems and methods for estimating throughput

Techniques for identifying certain types of network activity are disclosed, including parsing network traffic to automatically recognize anonymous identifiers. Such techniques may be used to identify and eliminate malicious and/or undesirable network traffic, and to identify topics relevant to a user of a particular network device so that communications to such a user are more likely to relate to a topic of interest to the user.

Ascertaining network devices used with anonymous identifiers

Techniques for identifying certain types of network activity are disclosed, including parsing of a Uniform Resource Locator (URL) to identify a plurality of key-value pairs in a query string of the URL. The plurality of key-value pairs may include one or more potential anonymous identifiers. In an example embodiment, a machine learning algorithm is trained on the URL to determine whether the one or more potential anonymous identifiers are actual anonymous identifiers (i.e., advertising identifiers) that provide advertisers a method to identify a user device without using, for example, a permanent device identifier. In this embodiment, a ranking threshold is used to verify the URL. A verified URL associate the one or more potential anonymous identifiers with the user device as actual anonymous identifiers. Such techniques may be used to identify and eliminate malicious and/or undesirable network traffic.

Using machine learning algorithm to ascertain network devices used with anonymous identifiers

A computing system may automatically infer one or more events that occur during an application session involving activity on a network, such as the Internet. Such an application session may be interactions with, for example, social networking websites, banking websites, news websites, and so on. Events are any of a number of activities or transactions that may occur during the application session. The computing system may automatically infer an event by gathering network transaction data for network transactions performed by one or more client devices of a wireless communication network. The computing system may generate a network activity signature based, at least in part, on the network transaction data and apply pattern recognition and/or machine learning to the network activity signature to infer events associated with the network activity signature.

Application session event inference from network activity

A first time that a Domain Name System (DNS) response message is sent by the gateway server of a network to a user device may be determined, the DNS response message being generated by a Local DNS server of the network in response to a DNS request message from the user device for routing via the gateway server to the user device. A second time that a client handshake message for an external server identified by a network address in the DNS response is received at the gateway server may be determined, in which the client handshake message is sent by the user device. A roundtrip time for the network that is a time difference between the first time and the second time is calculated. The roundtrip trip time is then halved to obtain a network latency time measurement for the network.

Network latency time measurement using DNS and web server messages

A geolocation of a mobile device determined during an event allows a communications network provider to associate geolocation data with QoS issues. The geolocation data may be ascertained by mapping call log data with a temporary subscriber identifier assigned by the communications network provider. Geolocation data may also be obtained from URL data. The geolocation data obtained from URL data may be verified by comparing the URL data with a geo-distance from a connected cell tower. The QoS issue can be associated with geolocation data and subsequently used to improve the network or strengthen the coverage at the geolocation.

Improving coverage in a cellular network using temporary subscriber indentifiers

Growing community of inventors

Newcastle, WA, United States of America

Ruchir Sinha