Telematics-based network device troubleshooting and repair

Patent metadata

Field	Value
Publication number	US-10963333-B1
Application number	US-201816106195-A
Country	US
Kind code	B1
Filing date	Aug 21, 2018
Priority date	Aug 21, 2018
Publication date	Mar 30, 2021
Grant date	Mar 30, 2021

Abstract

Telematics-based device troubleshooting, self-repair, and optimization are provided. A system, method, and computer readable storage device collect telemetry data associated with the health of networked CPE devices, service provider data, and service and repair data associated with CPE devices, analyze the collected information, and detect and predict issues that can affect the functioning and operation of CPE devices. Analysis of collected data can be based on self-check rules. In some implementations, troubleshooting steps or rules can be executed by a server device or communicated to a CPE device for enabling self-troubleshooting and self-correction of an issue. Self-check and troubleshooting rules can be configured according to insights derived from machine learning techniques applied to collected data (e.g., telemetry data, service provider data, and service and repair data (troubleshooting and repair feedback data collected in association with customer calls, field technician visits, and self-healing checks and actions performed on/by CPE devices)).

First claim

We claim:

1. A system for providing telematics-based device troubleshooting, self-repair, and optimization, the system comprising:
at least one processor; and
a memory storage including instructions that, when executed by the at least one processor, cause the system to:
receive telemetry data from a plurality of network-connected customer premises equipment (CPE) devices;
evaluate the telemetry data for identifying an issue associated with at least one CPE device of the plurality of CPE devices;
generate a troubleshooting plan comprising a plurality of troubleshooting steps for diagnosing and resolving the issue, wherein generation of the troubleshooting plan is based on machine-learned insights;
transmit one or more of the plurality of troubleshooting steps to the at least one CPE device to cause the at least one CPE device to execute the one or more troubleshooting steps to diagnose and resolve the issue;
receive troubleshooting and repair feedback from the at least one CPE device, the feedback includes information associated with whether the one or more troubleshooting steps resolved the issue;
store data, including the telemetry data and the troubleshooting and repair feedback, in a database system;
analyze the data stored in the database system; and
based on the analysis:
predict an occurrence of the issue in association with one or more other CPE devices of the plurality of CPE devices prior to the issue occurring; and
proactively generate and transmit a modified troubleshooting plan based on the analysis to the one or more other CPE devices for execution to prevent the issue from occurring.

2. The system of claim 1 , wherein in generating the troubleshooting plan, the instructions further cause the system to customize the troubleshooting plan based at least in part on the particular at least one CPE device and the issue.

3. The system of claim 1 , wherein the data stored in the database system further includes service provider data from a service provider system and associated metadata, and in analyzing the data stored in the database system, the instructions further cause the system to:
use machine-learning techniques to analyze the data for identifying a data pattern associated with attributes of the issue;
configure one or more self-check rules based on the identified data pattern; and
store the one or more self-check rules for use in identifying the issue.

4. The system of claim 3 , wherein the service provider data includes one or a combination of:
information about signal levels of transmissions from a headend of the server provider system;
bandwidth levels;
software update-related information;
available services;
customer subscription information; and
business rules.

5. The system of claim 3 , wherein the identified data pattern is associated with at least one of:
particular telemetry data values;
a type of CPE device;
a particular service;
a particular network;
a location;
a node;
a particular software version;
a particular hardware component;
an application; and
a particular device configuration.

6. The system of claim 3 , wherein the instructions further cause the system to:
use the machine-learning techniques to analyze the troubleshooting and repair feedback for deriving insights;
adjust one or more troubleshooting steps based on the derived insights; and
modify the troubleshooting plan for diagnosing and resolving the issue based on the derived insights to generate the modified troubleshooting plan.

7. The system of claim 6 , wherein the troubleshooting and repair feedback includes information associated with troubleshooting or correcting the issue and includes one or a combination of:
information associated with the attributes of the issue;
information about the at least one CPE device;
troubleshooting steps performed;
actions taken to correct the issue; and
results of the troubleshooting steps.

8. The system of claim 3 , wherein in predicting the occurrence of the issue in association with the one or more other CPE devices, the instructions further cause the system to predict the occurrence based on an identification of corresponding attributes of the issue and the one or more other CPE devices.

9. The system of claim 3 , wherein the instructions further cause the system to:
store the one or more self-check rules for access by the at least one CPE device; and
receive an alert indicating the issue and the telemetry data from the at least one CPE device responsive to a local identification of the issue by the at least one CPE device based on an evaluation of the one or more self-check rules.

10. The system of claim 1 , wherein the instructions further cause the system to execute one or more of the plurality of troubleshooting steps of the troubleshooting plan to diagnose and resolve the issue.

11. A customer premises equipment (CPE) device comprising:
at least one processor; and
a memory storage including instructions that, when executed by the at least one processor, cause the CPE device to:
collect telemetry data associated with the CPE device;
apply one or more self-check rules to the collected telemetry data for identifying an issue associated with the CPE device, wherein one of the one or more self-check rules includes determining a status of one or more other CPE devices communicatively coupled to the CPE device, the status indicating whether the issue has been identified in association with the one or more other CPE devices;
responsive to identifying the issue associated with the CPE device, generate and transmit an alert to a telematics device repair (TDR) server, wherein the alert includes information about the issue and about the CPE device;
receive, from the TDR server, a troubleshooting plan comprising one or more troubleshooting steps for diagnosing and resolving the issue, wherein generation of the troubleshooting plan is based on machine-learned insights;
execute the one or more troubleshooting steps to diagnose and resolve the issue; and
provide, to the TDR server, troubleshooting and repair feedback, the feedback including information associated with whether the one or more troubleshooting steps resolved the issue.

12. The CPE device of claim 11 , wherein the telemetry data associated with the CPE device includes information about the CPE device's connectivity to a network, signal levels, information about the functioning of hardware components, information about the functioning of software components, and application signaling information.

13. The CPE device of claim 12 , wherein in determining the status of the one or more other CPE devices communicatively coupled to the CPE device, the instructions cause the CPE device to:
request the status of the one or more other CPE devices association with the issue;
receive an acknowledgement response from the one or more other CPE devices indicating whether the one or more other CPE devices are experiencing the same issue; and
based on the acknowledgement response, determine whether the issue is confined to the CPE device or if the CPE device and the one or more other CPE devices are experiencing the same issue.

14. The CPE device of claim 13 , wherein the one or more other CPE devices are located at a same premises as the CPE device or on a same node as the CPE device.

15. The CPE device of claim 11 , wherein the one or more self-check rules are configured based on machine-learned insights learned from an analysis of telemetry data collected from a plurality of CPE devices, service provider data, troubleshooting and repair feedback, and associated meta

Assignees

• Cox Communications Inc

Inventors

• Nijim Yousef Wasef
• Strothmann James Alan

Classifications

• G06N5/041

  Abduction · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F11/3089

  Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents (software debugging using additional hardware using a specific debug interface G06F11/3656; performance evaluation by tracing or monitoring G06F11/3466) · CPC title

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/0787

  Storage of error reports, e.g. persistent data storage, storage using memory protection · CPC title