IP Library › Granted Patent US 12,748,652
Granted Patent B2
US 12,748,652 · App. 18/710,781 · Granted Sep 29, 2026

Network attribute analysis

Inventors: Zhongwen Zhu (Saint-Laurent, CA); Abdelwahab Hamou-Lhadj (Dollard-des-Ormeaux, CA); Salman Memon (Montreal, CA); Alka Isac (Montreal, CA)
Assignee: Telefonaktiebolaget LM Ericsson (Publ)
G06F11/079G06F11/0709G06N3/08G06N5/04G06N20/00
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 12,748,652
App. No.
18/710,781
Granted
Sep 29, 2026
Kind
B2
Abstract

There is provided a computer-implemented method for analysing one or more network attributes of a network. One or more first network attributes of the network are analysed using a first machine learning model to generate a first output comprising information about an event in the network. If an estimated confidence level for the first output is less than a confidence level threshold, the one or more first network attributes are analysed using a second machine learning model to generate a second output. The second output is indicative of one or more second network attributes of the network to analyse using the first machine learning model.

Claims (69)

1 . A method performed by processing circuitry of a first entity for processing one or more network attributes of a network, the method comprising:

processing one or more first network attributes of the network using a first machine learning model to generate a first output comprising information about an event in the network;

if an estimated confidence level for the first output is less than a confidence level threshold, processing the one or more first network attributes using a second machine learning model to generate a second output, the second output being indicative of one or more second network attributes of the network to process using the first machine learning model;

repeating the method for one or more iterations, for each iteration of the one or more iterations, if a second output is generated, the one or more second network attributes from the iteration are processed using the first machine learning model in the subsequent iteration; and

initiating a reconfiguration in the network for the one or more second network attributes to be acquired.

2 . The method as claimed in claim 1 , wherein:

the method is repeated until the confidence level for the first output is equal to or greater than the confidence level threshold.

3 . The method as claimed in claim 1 , the method comprising:

if the estimated confidence level for the first output is equal to or greater than the confidence level threshold, generating a report on the first output; and

if the estimated confidence level for the first output is less than the confidence level threshold, generating a report on the second output.

4 . The method as claimed in claim 3 , wherein:

the report on the first output comprises information indicative of the one or more first network attributes.

5 . The method as claimed in claim 1 , wherein:

the one or more first network attributes and the first output are processed using the second machine learning model to generate the second output.

6 . The method as claimed in claim 1 , wherein:

the information about the event in the network comprises any one or more of:

information indicative of a time of the event in the network;

information indicative of a level within the network at which the event occurs; and

information indicative of a cause of the event in the network.

7 . The method as claimed in claim 6 , wherein:

the level within the network is any one or more of:

a level at which one or more network nodes are deployed in the network;

a level at which one or more computing platforms are deployed in the network;

a level at which virtualization or containerization occurs in the network; and

a level at which one or more services are hosted or executed in the network.

8 . The method as claimed in claim 6 , wherein:

the information about the event in the network comprises, for one or more levels within the network, a percentage value indicative of a likelihood that the event in the network occurs at that level within the network; and

the highest percentage value is the information indicative of the level within the network at which the event occurs.

9 . The method as claimed in claim 1 , wherein:

all of the one or more second network attributes are different from the one or more first network attributes; or

the one or more second network attributes comprise at least one of the one or more first network attributes and at least one other network attribute of the network.

10 . The method as claimed in claim 1 , wherein:

the one or more first network attributes comprise two or more first network attributes that are acquired from different locations in the network; and

the one or more second network attributes comprise two or more second network attributes that are acquired from different locations in the network.

11 . The method as claimed in claim 1 , wherein:

the one or more first network attributes are acquired from any one or more of a log file, a trace file, and a performance management counter; and

the one or more second network attributes are acquired from any one or more of a log file, a trace file, and a performance management counter.

12 . The method as claimed in claim 1 , wherein:

the one or more first network attributes comprise at least two first network attributes and the at least two first network attributes are in a time series; and

the one or more second network attributes comprise at least two second network attributes and the at least two second network attributes are in a time series.

13 . The method as claimed in claim 1 , wherein:

the one or more first network attributes comprise at least two first network attributes and each of the at least two first network attributes have the same time stamp; and

the one or more second network attributes comprise at least two second network attributes and each of the at least two second network attributes have the same time stamp.

14 . The method as claimed in claim 1 , wherein:

the one or more first network attributes comprise at least two first network attributes that are in different formats;

the method comprises converting the at least two first network attributes into the same format;

the one or more second network attributes comprise at least two second network attributes that are in different formats; and

the method comprises converting the at least two second network attributes into the same format.

15 . The method as claimed in claim 1 , wherein:

processing the one or more first network attributes using the second machine learning model to generate the second output comprises:

using the second machine learning model to:

compare the one or more first network attributes to one or more second outputs previously generated using the second machine learning model, wherein each previously generated second output is indicative of one or more second network attributes of the network previously processed using the first machine learning model; and

generate the second output based on a result of the comparison.

16 . A computer-implemented method performed by processing circuitry of a second entity for processing for training a machine learning model to process one or more network attributes of a network, the method comprising:

training a first machine learning model to process one or more first network attributes of the network to generate a first output comprising information about an event in the network;

training a second machine learning model to process the one or more first network attributes to generate a second output if an estimated confidence level for the first output is less than a confidence level threshold, the second output being indicative of one or more second network attributes of the network to process using the first machine learning model, if a second output is generated, the one or more second network attributes from an iteration are processed using the first machine learning model in a subsequent iteration; and

initiating a reconfiguration in the network for the one or more second network attributes to be acquired.

17 . The method as claimed in claim 16 , wherein:

the first machine learning model is trained using a first training dataset, wherein the first training dataset comprises information indicative of a past occurrence of the event in the network and one or more first network attributes of the network corresponding to the past occurrence of the event; and

the second machine learning model is trained using a second training dataset, wherein the second training dataset comprises the one or more first network attributes of the network corresponding to the past occurrence of the event and one or more second network attributes of the network corresponding to the past occurrence of the event.

18 . The method as claimed in claim 17 , wherein:

the information indicative of the past occurrence of the event has a time stamp indicative of a time of the past occurrence of the event;

each first network attribute of the one or more first network attributes has a time stamp indicative of a time at which the first network attribute was recorded; and

for each first network attribute of the one or more first network attributes, the time at which the first network attribute was recorded is a time that falls within a predefined time interval that precedes the time of the past occurrence of the event.

19 . A computer program comprising instructions stored in a non-transitory medium which, when executed by processing circuitry, cause the processing circuitry to perform a method according to for processing one or more network attributes of a network, the method comprising:

processing one or more first network attributes of the network using a first machine learning model to generate a first output comprising information about an event in the network;

if an estimated confidence level for the first output is less than a confidence level threshold, processing the one or more first network attributes using a second machine learning model to generate a second output, the second output being indicative of one or more second network attributes of the network to process using the first machine learning model;

repeating the method for one or more iterations, for each iteration of the one or more iterations, if a second output is generated, the one or more second network attributes from the iteration are processed using the first machine learning model in the subsequent iteration; and

initiating a reconfiguration in the network for the one or more second network attributes to be acquired.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 17, 2024
From: ZHU, ZHONGWEN; HAMOU-LHADJ, ABDELWAHAB; MEMON, SALMAN; ISAC, ALKA
To: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
Reel/Frame 067446/0385 →
Continuity (1)
Related Publication 20250021423A1 · Jan 16, 2025
References Cited (30)
US 10158653B1 · Magcale · 2018 [cited by examiner]
US 11025502B2 · Qaadri · 2021 [cited by examiner]
US 11201801B2 · Dinh · 2021 [cited by examiner]
US 11415425B1 · Merchant · 2022 [cited by examiner]
US 11438228B1 · Belton, Jr. · 2022 [cited by examiner]
US 11442803B2 · Cherbakov · 2022 [cited by examiner]
US 11507887B2 · Kolar · 2022 [cited by examiner]
US 11658407B2 · Tran · 2023 [cited by examiner]
US 11698878B1 · Douglis · 2023 [cited by examiner]
US 11838172B2 · Cheng · 2023 [cited by examiner]
US 12008403B2 · Banerjee · 2024 [cited by examiner]
US 20210027205A1 · Sevakula · 2021 [cited by examiner]
US 20210156700A1 · Davis et al. · 2021 [cited by applicant]
US 20210165708A1 · Vijayaraghavan · 2021 [cited by examiner]
US 20210287109A1 · Cmielowski · 2021 [cited by examiner]
US 20210303378A1 · Sethi · 2021 [cited by examiner]
US 20220007199A1 · Mahalingam · 2022 [cited by examiner]
US 20220329328A1 · Paulraj · 2022 [cited by examiner]
US 20230069434A1 · Cheng · 2023 [cited by examiner]
US 20240298193A1 · Nie · 2024 [cited by examiner]
US 20250021423A1 · Zhu · 2025 [cited by examiner]
EP 3614313A1 · 2020 [cited by applicant]
WO 2020121084A1 · 2020 [cited by applicant]
WO 2020246973A1 · 2020 [cited by applicant]
WO 2021121585A1 · 2021 [cited by applicant]
International Search Report and Written Opinion dated Jul. 18, 2022 for International Application No. PCT/IB2021/060645 filed Nov. 17, 2021, consisting of 16 pages. [cited by applicant]
N. Marzo; Natural Language Processing Model for Log Analysis to Retrieve Solutions for Troubleshooting Processes; Degree Project in Computer Science and Engineering; KTH Royal Institute of Technology; Jun. 16, 2021, con… [cited by applicant]
Architecture Working Group; View on 5G Architecture, 5G PPP; Version 3.0; Jun. 19, 2019, consisting of 166 pages. [cited by applicant]
J. Devlin et al.; BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding; arXiv; May 24, 2019, consisting of 16 pages. [cited by applicant]
R. Nogueira et al.; Multi-Stage Document Ranking with BERT; arXiv; Oct. 31, 2019, consisting of 13 pages. [cited by applicant]