IP Library Granted Patent US 11,388,099
Granted Patent B2
US 11,388,099 · App. 17/174,800 · Granted Jul 12, 2022

Methods and apparatus for facilitating real-time and/or predictive fault detection

Inventor: Ebrahim S. Safavi (Santa Clara, CA)
Assignee: Juniper Networks, Inc.
H04L47/2441G06N20/00H04W24/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,388,099
App. No.
17/174,800
Granted
Jul 12, 2022
Kind
B2
Abstract

Methods and apparatus for automatically identifying and correcting faults relating to poor communications service in a wireless system, e.g., in real time, are described. The methods are well suited for use in a system with a variety of access points, e.g., wireless and/or wired access points, which can be used to obtain access to the Internet or another network. Access points (APs), which have been configured to monitor in accordance with received monitoring configuration information, e.g. on a per access point interface basis, captures messages, store captured messages, and in collaboration with network monitoring apparatus which can be in an AP or external thereto, use message sequences to determine a remedial action to be automatically taken when poor service is likely as may be predicted based on the detected message sequence between a UE and one or more APs.

Claims (35)

1. A system, comprising:

hardware processing circuitry; and

one or more hardware memories storing instructions that when executed configure the hardware processing circuitry to perform operations comprising:

detecting a network communication associated with a first wireless device, the network communication including a first plurality of messages;

generating a plurality of message vectors, each corresponding to a different one of the first plurality of messages and indicating a type of the corresponding message, a relative position of the corresponding message in the first plurality of messages, and a number of messages in the first plurality of messages;

updating a first message sequence vector based on the plurality of message vectors, wherein the first message sequence vector includes a same number of dimensions as each of the plurality of message vectors;

determining, the first message sequence vector is within a predefined vector space volume;

identifying a corrective action associated with the vector space volume; and

automatically invoking the corrective action.

2. The system of claim 1 , the operations further comprising iteratively updating, as each message associated with the first wireless device is detected, the first message sequence vector based on the message, and determining whether each updated first message sequence vector is within a predefined vector space volume.

3. The system of claim 1 , wherein automatically invoking the corrective action comprises restarting a network component, changing an operating parameter of an access point (AP), adding a service set identifier (SSID) to an AP, or powering on a radio.

4. The system of claim 1 , the operations further comprising providing each of the message vectors to a recursive neural network (RNN), wherein the updating of the first message sequence vector based on the plurality of message vectors is based on output of the RNN.

5. The system of claim 1 , wherein detecting the network communication associated with the first wireless device detects messages exchanged between the wireless device and a second device, the operations further comprising detecting a second plurality of messages exchanged between the wireless device and a third device, and updating a second message sequence vector based on the second plurality of messages, determining a second vector space volume including the second message sequence vector, and determining whether the second vector space volume is associated with a corrective action.

6. The system of claim 5 , wherein the second device and the third device are both access points.

7. The system of claim 1 , wherein the determining that the first message sequence vector is within the predefined vector space volume comprises determining if a value of each dimension of the first message sequence vector is within a predefined range of values associated with the predefined vector space volume.

8. The system of claim 1 , the operations further comprising determining a message of the first plurality of messages is a new message, and training a machine learning model to generate a message vector corresponding to the new message.

9. A method performed by hardware processing circuitry, comprising:

detecting network communication associated with a first wireless device, the network communication including a first plurality of messages;

generating a plurality of message vectors, each corresponding to a different one of the first plurality of messages and indicating a type of the corresponding message, a relative position of the corresponding message in the first plurality of messages, and a number of messages in the first plurality of messages;

updating a first message sequence vector based on the plurality of message vectors, wherein the first message sequence vector includes a same number of dimensions as each of the plurality of message vectors;

determining the first message sequence vector is within a predefined vector space volume;

identifying a corrective action associated with the vector space volume; and

automatically invoking the corrective action.

10. The method of claim 9 , further comprising iteratively updating, as each message associated with the first wireless device is detected, the first message sequence vector based on the message, and determining whether each updated message sequence vector is within a predefined vector space volume.

11. The method of claim 9 , wherein automatically invoking the corrective action comprises restarting a network component, changing an operating parameter of an access point (AP), adding a service set identifier (SSID) to an AP, or powering on a radio.

12. The method of claim 9 , further comprising providing each of the message vectors to a recursive neural network (RNN), wherein the updating of the first message sequence vector based on the plurality of message vectors is based on output of the RNN.

13. The method of claim 9 , wherein detecting the network communication associated with the first wireless device detects messages exchanged between the wireless device and a second device, the method further comprising detecting a second plurality of messages exchanged between the wireless device and a third device, and updating a second message sequence vector based on the second plurality of messages, determining a second vector space volume including the second message sequence vector, and determining whether the second vector space volume is associated with a corrective action.

14. The method of claim 9 , wherein the determining that the first message sequence vector is within the predefined vector space volume comprises determining if a value of each dimension of the first message sequence vector is within a predefined range of values associated with the predefined vector space volume.

15. A non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations comprising:

detecting network communication associated with a first wireless device, the network communication including a first plurality of messages;

generating a plurality of message vectors, each corresponding to a different one of the first plurality of messages and indicating a type of the corresponding message, a relative position of the corresponding message in the first plurality of messages, and a number of messages in the first plurality of messages;

updating a first message sequence vector based on the plurality of message vectors, wherein the first message sequence vector includes a same number of dimensions as each of the plurality of message vectors;

determining the first message sequence vector is within a predefined vector space volume;

identifying a corrective action associated with the vector space volume; and

automatically invoking the corrective action.

Assignments (3)
CONFIRMATORY ASSIGNMENT Recorded Jan 25, 2024
From: SAFAVI, EBRAHIM
To: JUNIPER NETWORKS, INC.
Reel/Frame 066371/0851 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: SAFAVI, EBRAHIM
To: MIST SYSTEMS, INC.
Reel/Frame 055245/0215 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: MIST SYSTEMS, INC.
To: JUNIPER NETWORKS, INC.
Reel/Frame 055245/0237 →
Continuity (3)
Continuation 16237677 · Dec 31, 2018
Provisional Application 62787234 · Dec 31, 2018
Related Publication 20210168084A1 · Jun 3, 2021