# US 11,909,521 B2 · Method for reducing false detection of successful decoding of cyclic redundancy check codes

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

- Number: US 11,909,521 B2
- Document ID: US11909521B2
- Status: Granted
- Kind: B2
- Application number: 17/930,873
- Filed: 2022-09-09
- Published: 2023-01-05
- Granted: 2024-02-20
- Earliest claimed: 2020-05-05
- Assignees: Viavi Solutions Inc.
- Applicants: VIAVI Solutions Inc.
- Inventors: Saman Rajaei; Hongyuan Huang
- Web page: https://patentgrep.com/patent/US11909521B2

## CPC

- H04L 1/004: {by using forward error control (H04L1/0618 takes precedence; coding, decoding or code conversion, for error detection or correction H03M13/00)}
- H04L 1/0054: {Maximum-likelihood or sequential decoding, e.g. Viterbi, Fano, ZJ algorithms}
- G06N 3/00: Computing arrangements based on biological models
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- H03M 13/13: Linear codes
- H04L 1/0057: {Block codes (H04L1/0061, H04L1/0064 take precedence)}
- H03M 13/09: Error detection only, e.g. using cyclic redundancy check [CRC] codes or single parity bit
- H04L 1/0061: {Error detection codes}
- H04L 1/0072: {Error control for data other than payload data, e.g. control data}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)

## Abstract

A network testing device may receive, from a base station, an encoded physical downlink control channel (PDCCH) payload and decode the encoded PDCCH payload to obtain candidate PDCCH payloads and to generate path metrics (PMs), wherein each PM of the PMs corresponds to one candidate PDCCH payload of the candidate PDCCH payloads. The network testing device may perform a cyclic redundancy check on each of the candidate PDCCH payloads to determine, from the PMs, a passing PM, and may determine, based on the PMs, a confidence value associated with the passing PM. The network testing device may discard, based on determining that the confidence value does not satisfy a threshold, the passing PM, or may output, based on determining that the confidence value satisfies the threshold, a candidate PDCCH payload corresponding to the passing PM. The network testing device may transmit, based on the candidate PDCCH payload, data to the base station.

## Claims

### Claim 1

A method, comprising:
determining, by a device, a confidence value associated with a passing path metric (PM) based on processing the passing PM using a machine learning model trained on historical PM values;
determining, by the device, whether the confidence value satisfies a threshold;
discarding, by the device and based on determining that the confidence value does not satisfy the threshold, the passing PM; or
outputting, by the device and based on determining that the confidence value does satisfy the threshold, a candidate physical downlink control channel (PDCCH) payload corresponding to the passing PM; and
transmitting, by the device and based on the candidate PDCCH payload, data to a base station.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the confidence value comprises:
determining the confidence value based on an average normalized PM value.

### Claim 3 (depends on 1)

The method of claim 1, wherein the machine learning model is trained based on historical confidence values.

### Claim 4 (depends on 1)

The method of claim 1, wherein the threshold is determined based on an additional machine learning model.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining another confidence value associated with another passing PM;
determining whether the other confidence value satisfies the threshold; and
discarding the other confidence value based on determining that the other confidence value does not satisfy the threshold.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
retraining the machine learning model based on the passing PM or the confidence value.

### Claim 7 (depends on 1)

The method of claim 1, wherein the passing PM is identified as the passing PM based on a cyclic redundancy check.

### Claim 8

A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
determine a confidence value associated with a passing path metric (PM) based on processing the passing PM using a machine learning model trained on historical PM values;
determine whether the confidence value satisfies a threshold;
discard, based on determining that the confidence value does not satisfy the threshold, the passing PM; or
output, based on determining that the confidence value does satisfy the threshold, a candidate physical downlink control channel (PDCCH) payload corresponding to the passing PM; and
transmit, based on the candidate PDCCH payload, data to a base station.

### Claim 9 (depends on 8)

The device of claim 8, wherein the one or more processors, to determine the confidence value, are configured to:
determine the confidence value based on an average normalized PM value.

### Claim 10 (depends on 8)

The device of claim 8, wherein the machine learning model is trained based on historical confidence values.

### Claim 11 (depends on 8)

The device of claim 8, wherein the threshold is determined based on an additional machine learning model.

### Claim 12 (depends on 8)

The device of claim 8, wherein the one or more processors are further configured to:
determine another confidence value associated with another passing PM;
determine whether the other confidence value satisfies the threshold; and
discard the other confidence value based on determining that the other confidence value does not satisfy the threshold.

### Claim 13 (depends on 8)

The device of claim 8, wherein the one or more processors are further configured to:
retrain the machine learning model based on the passing PM or the confidence value.

### Claim 14 (depends on 8)

The device of claim 8, wherein the passing PM is identified as the passing PM based on a cyclic redundancy check.

### Claim 15

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
determine a confidence value associated with a passing path metric (PM) based on processing the passing PM using a machine learning model trained on historical PM values;
determine whether the confidence value satisfies a threshold;
discard, based on determining that the confidence value does not satisfy the threshold, the passing PM; or
output, based on determining that the confidence value does satisfy the threshold, a candidate physical downlink control channel (PDCCH) payload corresponding to the passing PM; and
transmit, based on the candidate PDCCH payload, data to a base station.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the device to determine the confidence value, cause the device to:
determine the confidence value based on an average normalized PM value.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the machine learning model is trained based on historical confidence values.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the threshold is determined based on an additional machine learning model.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to:
determine another confidence value associated with another passing PM;
determine whether the other confidence value satisfies the threshold; and
discard the other confidence value based on determining that the other confidence value does not satisfy the threshold.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to:
retrain the machine learning model based on the passing PM or the confidence value.