# US 2026/0195642 A1 · Predicting user traffic metrics in computer networks

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

- Number: US 2026/0195642 A1
- Document ID: US20260195642A1
- Status: Published application
- Kind: A1
- Application number: 19/129,670
- Filed: 2023-04-27
- Published: 2026-07-09
- Earliest claimed: 2022-12-13
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget LM Ericsson (publ)
- Inventors: Paulo Antonio MOREIRA MIJARES; José María RUIZ AVILÉS; Juan RAMIRO MORENO; Jose OUTES CARNERO; Adriano MENDO MATEO; Yak NG MOLINA; Rakibul Islam RONY
- Web page: https://patentgrep.com/patent/US20260195642A1

## CPC

- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- H04M 3/2236: {Quality of speech transmission monitoring}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A computing system (600) collects input data associated with a network and generates one or more features (210) from the input data. The computing system (600) trains a plurality of metrics models (230) to predict respective metrics and predicts the respective metrics using the plurality of metrics models (230).

## Claims

### Claim 1

A method, implemented by a computing system, the method comprising:
collecting input data associated with a network;
generating one or more features from the input data;
training a plurality of metrics models to predict respective metrics; and
predicting the respective metrics using the plurality of metrics models.

### Claim 2 (depends on 1)

The method of claim 1, wherein training the plurality of metrics models comprises training the plurality of metrics models using a plurality of independent training stages executed in parallel.

### Claim 3 (depends on 1)

The method of claim 1, wherein predicting the respective metrics comprises:
predicting a first set of metrics using a first set of the metrics models; and
predicting a second set of metrics using the first set of metrics as input to a second set of the metrics models.

### Claim 4 (depends on 3)

The method of claim 3, wherein predicting the respective metrics further comprises predicting a third set of metrics using the second set of metrics as input to a third set of the metrics models.

### Claim 5 (depends on 4)

The method of claim 4, wherein the first set of metrics comprises Reference Signal Received Quality, Channel Quality Indicator, or Reference Signal Signal-to-Noise Ratio.

### Claim 6 (depends on 4)

The method of claim 4, wherein the second set of metrics comprises Signal-to-Interference Ratio (SINR).

### Claim 7 (depends on 4)

The method of claim 4, wherein the third set of metrics comprises uplink user throughput, downlink user throughput, or latency.

### Claim 8 (depends on 1)

The method of claim 1, wherein:
the collected input data comprises measured data obtained from a plurality of different locations spanning a geographic area;
the collected input data is missing metrics from one or more of the different locations; and
predicting the respective metrics using the plurality of metrics models comprises predicting the missing metrics for each of the one or more of the different locations.

### Claim 9

A computing system, comprising:
processing circuitry and memory circuitry, the memory circuitry storing instructions executable by the processing circuitry whereby the computing system is configured to:
collect input data associated with a network;
generate one or more features from the input data;
train a plurality of metrics models to predict respective metrics; and
predict the respective metrics using the plurality of metrics models.

### Claim 10

(canceled)

### Claim 11 (depends on 1)

A non-transitory computer-readable medium storing thereon a computer program comprising instructions that, when executed on processing circuitry of a computing system, cause the computing system to carry out the method of claim 1.

### Claim 12

(canceled)

### Claim 13 (depends on 4)

The method of claim 4, wherein the first set of metrics comprises Reference Signal Received Quality.

### Claim 14 (depends on 4)

The method of claim 4, wherein the first set of metrics comprises Channel Quality Indicator.

### Claim 15 (depends on 4)

The method of claim 4, wherein the first set of metrics comprises Reference Signal Signal-to-Noise Ratio.

### Claim 16 (depends on 4)

The method of claim 4, wherein the third set of metrics comprises uplink user throughput.

### Claim 17 (depends on 4)

The method of claim 4, wherein the third set of metrics comprises downlink user throughput.

### Claim 18 (depends on 4)

The method of claim 4, wherein the third set of metrics comprises latency.
