# US 10,455,438 B2 · Telecom monitoring and analysis system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,455,438 B2
- Document ID: US10455438B2
- Status: Granted
- Kind: B2
- Application number: 15/474,888
- Filed: 2017-03-30
- Published: 2018-10-04
- Granted: 2019-10-22
- Earliest claimed: 2017-03-30
- Assignees: T-Mobile USA, Inc.
- Applicants: T-Mobile USA, Inc.
- Inventors: Emad Tawfik Bisada
- Web page: https://patentgrep.com/patent/US10455438B2

## CPC

- H04W 24/08: Testing, {supervising or monitoring} using real traffic
- H04L 41/0631: using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L 41/069: using logs of notifications; Post-processing of notifications
- H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports}
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A Telecom Monitoring and Analysis System (TMAS) can be utilized to automatically collect and analyze session logs for troubleshooting a session degradation and/or a session failure within a telecommunications network. The TMAS may receive an access request from an authorized user for purposes of troubleshooting a session degradation/failure associated with a particular subscription with an operator of the telecommunications network. The authorized user may provide an identifier associated with the subscription, and the TMAS can then query one or multiple dedicated monitoring systems for past session logs associated with the identifier. Upon receipt of the past session logs, the TMAS may generate, without user intervention, a report, based at least in part on the past session logs, the report including session degradation and/or failure information. The past session logs and/or the generated report may be sent to a user device of the authorized user.

## Claims

### Claim 1

A method comprising:
receiving a request from a user computing device to access a system for monitoring at least one of a session degradation or a session failure of a communication session between subscribers in a telecommunications network;
causing, by the system, a user interface to be displayed on a display of the user computing device, the user interface being configured to receive, via user input to the user computing device:
an identifier associated with a subscription to services provided by an operator of the telecommunications network;
a time window within which to collect past session logs associated with the identifier; and
a selection of at least two dedicated monitoring systems among a plurality of dedicated monitoring systems available for selection via the user interface, the plurality of dedicated monitoring systems monitoring the communication session within respective portions of the telecommunications network, individual dedicated monitoring systems of the plurality of dedicated monitoring systems being configured to obtain session logs comprising information relating to data packets of the communication session captured by a corresponding dedicated monitoring probe within the respective portion of the telecommunications network for the individual dedicated monitoring systems;
receiving, via the user interface, the identifier, the time window, and the selection of the at least two dedicated monitoring systems;
querying, by the system, the at least two dedicated monitoring systems for the past session logs associated with the identifier;
receiving the past session logs from the at least two dedicated monitoring systems;
sending the past session logs to the user computing device; and
generating, using a trained machine learning model, a root cause within the telecommunications network of the at least one of the session degradation or the session failure of the communication session by processing the past session logs as input to the trained machine learning model and by performing deep packet inspection before the at least one of the session degradation or the session failure, wherein the trained machine learning model uses training data including additional past session logs and data regarding root causes of session degradations or session failures exhibited in the additional past session logs.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
receiving the selection of the at least two dedicated monitoring systems comprises receiving, via the user interface, a selection of multiple dedicated monitoring systems comprising a first dedicated monitoring system and a second dedicated monitoring system;
querying the at least two dedicated monitoring systems comprises:
querying the first dedicated monitoring system for first past session logs associated with (i) the identifier and (ii) a first portion of the telecommunications network; and
querying the second dedicated monitoring system for second past session logs associated with (i) the identifier and (ii) a second portion of the telecommunications network; and
receiving the past session logs comprises:
receiving the first past session logs from the first dedicated monitoring system; and
receiving the second past session logs from the second dedicated monitoring system.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
generating, by the system, without user intervention, and based at least in part on the past session logs, a report that includes session degradation information or session failure information; and
sending the report to the user computing device.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
querying one or more data sources for contextual data associated with the past session logs; and
receiving the contextual data associated with the past session logs,
wherein generating the report is further based on the contextual data.

### Claim 5 (depends on 3)

The method of claim 3, wherein:
the past session logs include past call logs associated with a call; and
the report includes the session failure information comprising at least one of:
a drop time of the call that was dropped;
a drop cause code of the call that was dropped; or
one or more radio frequency characteristics at a geographical location where the call was dropped.

### Claim 6 (depends on 3)

The method of claim 3, further comprising:
receiving, based on feedback from one or more users that analyzed additional past session logs, the data regarding root causes, within the telecommunications network, of the session degradations or the session failures exhibited in the additional past session logs; and
training the machine learning model using the training data to obtain the trained machine learning model, the training data including the additional past session logs and the data regarding the root causes,
wherein generating the report further comprises:
including the root cause in the session degradation information or the session failure information.

### Claim 7

A method comprising:
receiving a request from a user computing device to access a system for monitoring at least one of a session degradation or a session failure of a communication session between subscribers in a telecommunications network;
requesting, by the system, a user of the user computing device to specify an identifier associated with a subscription to services provided by an operator of the telecommunications network;
receiving the identifier from the user computing device;
querying, by the system, multiple dedicated monitoring systems for past session logs associated with the identifier, the multiple dedicated monitoring systems monitoring respective portions of the telecommunications network, individual dedicated monitoring systems of the multiple dedicated monitoring systems being configured to obtain session logs comprising information relating to data packets of the communication session captured by a corresponding dedicated monitoring probe within the respective portion of the telecommunications network for the individual dedicated monitoring systems;
receiving first past session logs from a first dedicated monitoring system of the multiple dedicated monitoring systems;
receiving second past session logs from a second dedicated monitoring system of the multiple dedicated monitoring systems;
sending the first past session logs and the second past session logs to the user computing device; and
generating, using a trained machine learning model, a root cause within the telecommunications network of the at least one of the session degradation or the session failure of the communication session by processing the first past session logs and the second past session logs as input to the trained machine learning model and by performing deep packet inspection before the at least one of the session degradation or the session failure, wherein the trained machine learning model uses training data including additional past session logs and data regarding root causes of session degradations or session failures exhibited in the additional past session logs.

### Claim 8 (depends on 7)

The method of claim 7, wherein:
requesting the user of the user computing device to specify the identifier further comprises requesting the user to specify an automation script that includes the identifier; and
querying the multiple dedicated monitoring systems is based at least in part on executing the automation script.

### Claim 9 (depends on 7)

The method of claim 7, wherein requesting the user of the user computing device to specify the identifier further comprises causing a user interface to be displayed on a display of the user computing device, the user interface being configured to receive, via user input to the user computing device:
the identifier in the form of a subscription identifier;
a time window within which to collect the past session logs associated with the subscription identifier; and
a selection of multiple dedicated monitoring systems among a plurality of dedicated monitoring systems available for selection via the user interface,
the method further comprising receiving, via the user interface, the subscription identifier, the time window, and a selection of the multiple dedicated monitoring systems among the plurality of dedicated monitoring systems available for selection,
wherein querying the multiple dedicated monitoring systems is based at least in part on the subscription identifier, the time window, and the selection of the multiple dedicated monitoring systems.

### Claim 10 (depends on 7)

The method of claim 7, further comprising:
generating, by the system, without user intervention, and based at least in part on the first past session logs and the second past session logs, a report that includes session degradation information or session failure information; and
sending the report to the user computing device.

### Claim 11 (depends on 10)

The method of claim 10, wherein sending the first past session logs, the second past session logs, and the report to the user computing device comprises downloading the first past session logs, the second past session logs, and the report to a folder location on the user computing device specified by the user.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
querying one or more data sources for contextual data associated with the past session logs; and
receiving the contextual data associated with the past session logs,
wherein generating the report is further based on the contextual data.

### Claim 13 (depends on 10)

The method of claim 10, wherein:
the past session logs include past call logs associated with a call; and
the report includes the session failure information comprising at least one of:
a drop time of the call that was dropped;
a drop cause code of the call that was dropped; or
one or more radio frequency characteristics at a geographical location where the call was dropped.

### Claim 14 (depends on 10)

The method of claim 10, further comprising:
receiving, based on feedback from one or more users that analyzed additional past session logs, the data regarding root causes, within the telecommunications network, of the session degradations or the session failures exhibited in the additional past session logs; and
training the machine learning model using the training data to obtain the trained machine learning model, the training data including the additional past session logs and the data regarding the root causes,
wherein generating the report further comprises:
including the root cause in the session degradation information or the session failure information.

### Claim 15 (depends on 7)

The method of claim 7, further comprising:
determining that a subset of past session logs among the first past session logs and the second past session logs have a same format; and
arranging the subset of past session logs having the same format in chronological order based at least in part on respective timestamps identified in the subset of past session logs.

### Claim 16

A system comprising:
one or more processors; and
memory storing computer-executable instructions that, when executed by the one or more processors, cause the system to:
receive a request from a user computing device to access the system for monitoring at least one of a session degradation or a session failure of a communication session between subscribers in a telecommunications network;
request, via a user interface of the user computing device, an identifier associated with a subscription to services provided by an operator of the telecommunications network;
receive the identifier from the user computing device;
query multiple dedicated monitoring systems for past session logs associated with the identifier, the multiple dedicated monitoring systems monitoring respective portions of the telecommunications network, individual dedicated monitoring systems of the multiple dedicated monitoring systems being configured to obtain session logs comprising information relating to data packets of the communication session captured by a corresponding dedicated monitoring probe within the respective portion of the telecommunications network for the individual dedicated monitoring systems;
receive first past session logs from a first dedicated monitoring system of the multiple dedicated monitoring systems, the first past session logs being associated with a first portion of the telecommunications network;
receive second past session logs from a second dedicated monitoring system of the multiple dedicated monitoring systems, the second past session logs being associated with a second portion of the telecommunications network;
send the first past session logs and the second past session logs to the user computing device; and
generate, using a trained machine learning model, a root cause within the telecommunications network of the session degradation or the session failure of the communication session by processing the first past session logs and the second past session logs as input to the trained machine learning model and by performing deep packet inspection before the at least one of the session degradation or the session failure, wherein the trained machine learning model uses training data including additional past session logs and data regarding root causes of session degradations or session failures exhibited in the additional past session logs.

### Claim 17 (depends on 16)

The system of claim 16, wherein:
requesting, via the user interface of the user computing device, the identifier further comprises causing the user interface to be displayed on a display of the user computing device, the user interface being configured to receive, via user input to the user computing device:
the identifier as a subscription identifier;
a time window within which to collect the past session logs associated with the subscription identifier; and
a selection of at least one dedicated monitoring systems among a plurality of dedicated monitoring systems available for selection via the user interface, the computer-executable instructions, when executed by the one or more processors, further cause the system to receive, via the user interface, the subscription identifier, the time window, and a selection of the multiple dedicated monitoring systems among the plurality of dedicated monitoring systems available for selection; and
querying the multiple dedicated monitoring systems is based at least in part on the subscription identifier, the time window, and the selection of the multiple dedicated monitoring systems.

### Claim 18 (depends on 16)

The system of claim 16, wherein the computer-executable instructions, when executed by the one or more processors, further cause the system to:
generate, without user intervention, and based at least in part on the first past session logs and the second past session logs, a report that includes session degradation information or session failure information; and
send the report to the user computing device.

### Claim 19 (depends on 18)

The system of claim 18, wherein the computer-executable instructions, when executed by the one or more processors, further cause the system to:
query one or more data sources for contextual data associated with the past session logs; and
receive the contextual data associated with the past session logs,
wherein generating the report is further based on the contextual data.

### Claim 20 (depends on 18)

The system of claim 18, wherein:
the past session logs include past call logs associated with a call
the report includes the session failure information comprising at least one of:
a drop time of the call that was dropped;
a drop cause code of the call that was dropped; or
one or more radio frequency characteristics at a geographical location where the call was dropped.