Inventor

Savalle Pierre-André

FR89 patents

Patents

50 patents

US10346277B2Jul 9, 2019

Adaptive sampling to build accurate application throughput models

CISCO TECH INC21 citations94

US10440577B1Oct 8, 2019

Hard/soft finite state machine (FSM) resetting approach for capturing network telemetry to improve device classification

CISCO TECH INC16 citations86

US10218726B2Feb 26, 2019

Dynamic device clustering using device profile information

CISCO TECH INC18 citations86

US11018943B1May 25, 2021

Learning packet capture policies to enrich context for device classification systems

CISCO TECH INC8 citations84

US10728775B2Jul 28, 2020

Roaming and transition patterns coding in wireless networks for cognitive visibility

CISCO TECH INC5 citations84

US10212044B2Feb 19, 2019

Learning when to reuse existing rules in active labeling for device classification

CISCO TECH INC8 citations81

US12407581B1Sep 2, 2025

Multi-agent coordination for network anomaly detection, troubleshooting, and remediation using language models

CISCO TECH INC4 citations75

US12199847B2Jan 14, 2025

Anomaly detection of model performance in an MLOps platform

CISCO TECH INC3 citations75

US11729071B1Aug 15, 2023

Selection of SaaS endpoint instances based on local service provider connectivity statistics

CISCO TECH INC4 citations75

US11456926B1Sep 27, 2022

Assessing the true impact of predictive application-driven routing on end user experience

CISCO TECH INC6 citations75

US12074789B1Aug 27, 2024

Gathering labels from proprietary applications for QoE predictions

CISCO TECH INC3 citations74

US11706130B2Jul 18, 2023

Root-causing user experience anomalies to coordinate reactive policies in application-aware routing

CISCO TECH INC2 citations73

US11677819B2Jun 13, 2023

Peer-to-peer feature exchange for edge inference of forecasting models

CISCO TECH INC2 citations73

US11632327B2Apr 18, 2023

Estimating the efficacy of predictive routing for prospective deployments

CISCO TECH INC2 citations73

US11582093B2Feb 14, 2023

Using stability metrics for live evaluation of device classification systems and hard examples collection

CISCO TECH INC3 citations73

US11528218B2Dec 13, 2022

Probe fusion for application-driven routing

CISCO TECH INC4 citations73

US11528231B2Dec 13, 2022

Active labeling of unknown devices in a network

CISCO TECH INC5 citations73

US11514084B2Nov 29, 2022

Extraction of prototypical trajectories for automatic classification of network KPI predictions

CISCO TECH INC4 citations73

US11477112B2Oct 18, 2022

On-the-fly SD-WAN tunnel creation for application-driven routing

CISCO TECH INC2 citations73

US11399023B2Jul 26, 2022

Revisiting device classification rules upon observation of new endpoint attributes

CISCO TECH INC5 citations73

US11283830B2Mar 22, 2022

Protecting device classification systems from adversarial endpoints

CISCO TECH INC3 citations73

US11151476B2Oct 19, 2021

Learning criticality of misclassifications used as input to classification to reduce the probability of critical misclassification

CISCO TECH INC2 citations73

US10965556B2Mar 30, 2021

Sampling traffic telemetry for device classification with distributed probabilistic data structures

CISCO TECH INC2 citations73

US10917803B2Feb 9, 2021

Automatic characterization of AP behaviors

CISCO TECH INC4 citations73

US10701095B2Jun 30, 2020

Hierarchical models using self organizing learning topologies

CISCO TECH INC3 citations73

US10700984B2Jun 30, 2020

Differentiating devices with similar network footprints using active techniques

CISCO TECH INC4 citations73

US10616251B2Apr 7, 2020

Anomaly selection using distance metric-based diversity and relevance

CISCO TECH INC4 citations73

US10220167B2Mar 5, 2019

Mechanisms to prevent anomaly detectors from learning anomalous patterns

CISCO TECH INC5 citations73

US10659333B2May 19, 2020

Detection and analysis of seasonal network patterns for anomaly detection

CISCO TECH INC6 citations72

US10404728B2Sep 3, 2019

Learning internal ranges from network traffic data to augment anomaly detection systems

CISCO TECH INC4 citations72

US10243980B2Mar 26, 2019

Edge-based machine learning for encoding legitimate scanning

CISCO TECH INC5 citations72

US12506653B2Dec 23, 2025

LLM-based network troubleshooting using expert-curated recipes

CISCO TECH INC1 citations64

US12587564B2Mar 24, 2026

Adversarial training of language models to prevent hijacking of conversational agents

CISCO TECH INC0 citations63

US12058010B2Aug 6, 2024

Adaptive stress testing of SD-WAN tunnels for what-if scenario model training

CISCO TECH INC0 citations63

US11736364B2Aug 22, 2023

Cascade-based classification of network devices using multi-scale bags of network words

CISCO TECH INC0 citations63

US11729097B2Aug 15, 2023

QOS configuration update based on behavioral application correlation

CISCO TECH INC0 citations63

US11711291B2Jul 25, 2023

Progressive automation with predictive application network analytics

CISCO TECH INC0 citations63

US11625241B2Apr 11, 2023

Predicting the impact of network software upgrades on machine learning model performance

CISCO TECH INC0 citations63

US11507887B2Nov 22, 2022

Model interpretability using proxy features

CISCO TECH INC1 citations63

US11483234B2Oct 25, 2022

Predictive routing-based policy adjustments in software-defined networks

CISCO TECH INC0 citations63

US11405802B2Aug 2, 2022

Roaming and transition patterns coding in wireless networks for cognitive visibility

CISCO TECH INC0 citations63

US11381640B2Jul 5, 2022

Detection of isolated changes in network metrics using smart-peering

CISCO TECH INC1 citations63

US11232372B2Jan 25, 2022

Merging and optimizing heterogeneous rulesets for device classification

CISCO TECH INC0 citations63

US11025486B2Jun 1, 2021

Cascade-based classification of network devices using multi-scale bags of network words

CISCO TECH INC1 citations63

US10601676B2Mar 24, 2020

Cross-organizational network diagnostics with privacy awareness

CISCO TECH INC1 citations63

US10193912B2Jan 29, 2019

Warm-start with knowledge and data based grace period for live anomaly detection systems

CISCO TECH INC1 citations63

US12587448B2Mar 24, 2026

AI-based network troubleshooting with expert feedback

CISCO TECH INC0 citations62

Showing the top 50 of 89 patents by PatentIndex Score.

Savalle Pierre-André

Patents

Adaptive sampling to build accurate application throughput models

Hard/soft finite state machine (FSM) resetting approach for capturing network telemetry to improve device classification

Dynamic device clustering using device profile information

Learning packet capture policies to enrich context for device classification systems

Roaming and transition patterns coding in wireless networks for cognitive visibility

Sparse coding of hidden states for explanatory purposes

Hierarchical models using self organizing learning topologies

Self organizing learning topologies

Learning when to reuse existing rules in active labeling for device classification

Multi-agent coordination for network anomaly detection, troubleshooting, and remediation using language models

Anomaly detection of model performance in an MLOps platform

Selection of SaaS endpoint instances based on local service provider connectivity statistics

Assessing the true impact of predictive application-driven routing on end user experience

Gathering labels from proprietary applications for QoE predictions

Root-causing user experience anomalies to coordinate reactive policies in application-aware routing

Peer-to-peer feature exchange for edge inference of forecasting models

Estimating the efficacy of predictive routing for prospective deployments

Using stability metrics for live evaluation of device classification systems and hard examples collection

Probe fusion for application-driven routing

Active labeling of unknown devices in a network

Extraction of prototypical trajectories for automatic classification of network KPI predictions

On-the-fly SD-WAN tunnel creation for application-driven routing

Revisiting device classification rules upon observation of new endpoint attributes

Protecting device classification systems from adversarial endpoints

Learning criticality of misclassifications used as input to classification to reduce the probability of critical misclassification

Sampling traffic telemetry for device classification with distributed probabilistic data structures

Automatic characterization of AP behaviors

Hierarchical models using self organizing learning topologies

Differentiating devices with similar network footprints using active techniques

Anomaly selection using distance metric-based diversity and relevance

Mechanisms to prevent anomaly detectors from learning anomalous patterns

Detection and analysis of seasonal network patterns for anomaly detection

Learning internal ranges from network traffic data to augment anomaly detection systems

Edge-based machine learning for encoding legitimate scanning

LLM-based network troubleshooting using expert-curated recipes

Adversarial training of language models to prevent hijacking of conversational agents

Adaptive stress testing of SD-WAN tunnels for what-if scenario model training

Cascade-based classification of network devices using multi-scale bags of network words

QOS configuration update based on behavioral application correlation

Progressive automation with predictive application network analytics

Predicting the impact of network software upgrades on machine learning model performance

Model interpretability using proxy features

Predictive routing-based policy adjustments in software-defined networks

Roaming and transition patterns coding in wireless networks for cognitive visibility

Detection of isolated changes in network metrics using smart-peering

Merging and optimizing heterogeneous rulesets for device classification

Cascade-based classification of network devices using multi-scale bags of network words

Cross-organizational network diagnostics with privacy awareness

Warm-start with knowledge and data based grace period for live anomaly detection systems

AI-based network troubleshooting with expert feedback