# US 2026/0095805 A1 · System for monitoring quality of service and latency of a cellular network and related methods

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

- Number: US 2026/0095805 A1
- Document ID: US20260095805A1
- Status: Published application
- Kind: A1
- Application number: 19/112,008
- Filed: 2023-12-27
- Published: 2026-04-02
- Earliest claimed: 2022-12-28
- Assignees: Latence Technologies Inc.
- Applicants: Latence Technologies Inc.
- Inventors: Benoit GENDRON; Nicolas GORSE
- Web page: https://patentgrep.com/patent/US20260095805A1

## CPC

- H04L 12/12: Arrangements for remote connection or disconnection of substations or of equipment thereof
- H04W 28/0236: {radio quality, e.g. interference, losses or delay}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
- H04L 43/0852: Delays
- H04W 24/02: Arrangements for optimising operational condition
- H04L 41/142: using statistical or mathematical methods
- H04L 41/147: for predicting network behaviour
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A method and a system for monitoring a quality of service (QoS) of a cellular network are provided. The method includes generating, using a monitoring module, test data based on latency parameters, the test data comprising initial test packets, and transmitting the initial test packets of the test data to a target module. The method includes transmitting, using the target module, redirected test packets back to the monitoring module, the redirected test packets associated with the initial test packets. The method further includes processing, using the monitoring module, the redirected test packets to calculate latency measurements between transmission of the initial test packets and reception of the redirected test packets. The method also includes transmitting the latency measurements to a processing module comprising a QoS neural network; and producing at least one of a current latency state and a future latency state using the QoS neural network.

## Claims

### Claim 1

A method for monitoring a quality of service (QoS) of a cellular network, comprising steps of:
generating, using a monitoring module, test data based on latency parameters, the test data comprising initial test packets;
transmitting the initial test packets of the test data to a target module;
upon reception of the initial test packets, transmitting, using the target module, redirected test packets back to the monitoring module, the redirected test packets associated with the initial test packets;
upon reception of the redirected test packets at the monitoring module, processing, using the monitoring module, the redirected test packets to calculate latency measurements between transmission of the initial test packets and reception of the redirected test packets;
transmitting the latency measurements to a processing module comprising a QoS neural network; and
producing at least one of a current latency state and a future latency state using the QoS neural network, the current and future latency states indicative of a current and future QoS of the cellular network, respectively.

### Claim 2 (depends on 1)

The method of claim 1, wherein transmitting the redirected test packets back to the monitoring module comprises one of:
transmitting test packets generated by the target module and associated with respective initial test packets; and
redirecting the initial test packets to the monitoring module.

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more latency parameters include a class of measurements and a frequency of measurements.

### Claim 4 (depends on 3)

The method of claim 3, wherein the class of measurements includes a communication protocol for generating the test data, the communication protocol being selected from a group including an Internet Control Message Protocol (ICMP), a Transmission Control Protocol (TCP), a User Datagram Protocol (UDP), a secure Hypertext Transfer Protocol (HTTP/S/3) and a Two-Way Active Management Protocol (TWAMP).

### Claim 5 (depends on 3)

The method of claim 3, wherein the frequency of measurements comprises a measurement cycle, and wherein test data is periodically generated based on the measurement cycle.

### Claim 6 (depends on 1)

The method of claim 1, wherein the QoS neural network is trained with the latency measurements and past latency measurements.

### Claim 7 (depends on 6)

The method of claim 6, further comprising labelling the latency measurements using epoch timestamps, and wherein the QoS neural network is trained using labelled latency measurements.

### Claim 8 (depends on 1)

The method of claim 1, wherein the QoS neural network is one of an evolutive statistical extrapolation model, and a machine learning model adapted to operate continuously.

### Claim 9 (depends on 1)

The method of claim 1, wherein the QoS neural network comprises an anomaly detection model, and wherein the method further comprises steps of:
detecting, using the QoS neural network, abnormal variations in response times based on the latency measurements; and
generating an alert when an anomaly is detected, indicative that one or more abnormal variations have been detected.

### Claim 10 (depends on 1)

The method of claim 1, wherein the QoS neural network comprises a future prediction model, and wherein the method further comprises steps of:
predicting, using the QoS neural network, future network problems; and
generating an alert when a future network problem is predicted.

### Claim 11 (depends on 1)

The method of claim 1, wherein the QoS neural network comprises a sub-components decomposition model, and wherein the method further comprises a step of calculating sub-components of latency including transmission time, propagation time, routing time, queuing time, and jitter.

### Claim 12 (depends on 1)

The method of claim 1, wherein generating the test data comprises continuously generating new test data, each new test data comprising a plurality of the initial test packets.

### Claim 13 (depends on 1)

The method of claim 1, wherein the steps are performed in real-time.

### Claim 14 (depends on 1)

The method of claim 1, wherein producing the at least one of the current latency state and the future latency state comprises calculating, using a network stability estimation model, a network stability score defined as
network
⁢
stability
⁢
score
=
(
1
-
σ
x
_
)
×
(
1
-
∑
i
=
1
π
ε
i
κ
i
n
)
×
(
1
-
∑
i
=
1
π
δ
i
κ
i
n
)
where: σ is the standard deviation of the latency measurements, x is the average of the latency measurements, n is the number of protocols, i (κ i) is the number of samples collected for a given protocol, i (ε i) is the number of events observed for the protocol and i (δ i) is the number of samples collected.

### Claim 15 (depends on 1)

The method of claim 1, wherein generating the test data comprises one of:
generating synthetically generated data used for testing purposes; and
collecting organically generated data transmitted through the network and using the organically generated data as the test data.

### Claim 16 (depends on 1)

The method of claim 1, wherein calculating the latency measurements further comprises calculating network bandwidth.

### Claim 17 (depends on 1)

The method of claim 1, further comprising a step of determining a location of one or more nodes traversed by the data packets, and wherein the latency measurements include complementary contextual data based on the one or more nodes traversed.

### Claim 18 (depends on 17)

The method of claim 17, wherein the complementary contextual data includes one of weather data and geolocation data.

### Claim 19

A system for monitoring a quality of service (QoS) of a cellular network, the system comprising:
a monitoring module configured:
to generate test data based on latency parameters to be measured, the test data comprising initial test packets;
transmit the initial test packets to a target device;
receive redirected test packets from the target device, the redirected test packets associated with the initial test packets; and
process the redirected test packets to calculate latency measurements between transmission of the initial test packets and reception of the redirected test packets; and
a processing module operatively connected with the monitoring module and comprising a QoS neural network, the processing module being configured to receive the latency measurements from the monitoring module and to produce at least one of a current latency state and a future latency state.

### Claim 20

A system for monitoring a quality of service (QoS) of a cellular network, the system comprising:
a monitoring module configured to generate test data based on latency parameters to be measured, the test data comprising initial test packets;
a target module operatively connected to the monitoring module, the target module being configured to:
receive, from the monitoring module, the initial test packets; and
transmit redirected test packets back to the monitoring module;
the monitoring module being further configured to process the redirected test packets to calculate latency measurements between transmission of the initial test packets and reception of the redirected test packets;
a processing module operatively connected with the monitoring module and comprising a QoS neural network, the processing module being configured to receive the latency measurements from the monitoring module and to produce at least one of a current latency state and a future latency state.

### Claim 21 (depends on 20)

The system of claim 20, further comprising an application programming interface adapted to transmit the at least one of a current latency state and a future latency state to a user device.

### Claim 22 (depends on 1)

A computer-readable medium comprising computer-readable instructions stored thereon that, when executed by a computer, perform the steps of claim 1.
