# US 2023/0422175 A1 · Machine learning (ml)-based dynamic demodulator parameter selection

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

- Number: US 2023/0422175 A1
- Document ID: US20230422175A1
- Status: Published application
- Kind: A1
- Application number: 17/848,295
- Filed: 2022-06-23
- Published: 2023-12-28
- Earliest claimed: 2022-06-23
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Jacob PICK; Assaf TOUBOUL; Shay LANDIS; Alexei Yurievitch GOROKHOV; Hari SANKAR; Peer BERGER
- Web page: https://patentgrep.com/patent/US20230422175A1

## CPC

- H04L 25/03165: {using neural networks}
- H04W 52/0261: {managing power supply demand, e.g. depending on battery level}
- G06N 3/02: Neural networks
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of wireless communication by a receiver, includes predicting, with an artificial neural network, at each data block of a set of data blocks, a least complex set of demodulator parameters that will achieve a goal, based on features of a data block expected to be received. The method also includes dynamically selecting the least complex set of demodulator parameters, from multiple sets of demodulator parameters, based on the features of the data block expected to be received. The selecting occurring to prevent degradation of demodulation performance for each data block with the selected set of demodulator parameters for the data block, with respect to a more complex set of demodulator parameters.

## Claims

### Claim 1

A method of wireless communication by a receiving device, comprising:
predicting, with an artificial neural network, at each data block of a set of data blocks, a least complex set of demodulator parameters that will achieve a goal, based on features of a data block expected to be received; and
dynamically selecting the least complex set of demodulator parameters, from a plurality of sets of demodulator parameters, based on the features of the data block expected to be received, the selecting occurring to prevent degradation of demodulation performance for each data block with the selected set of demodulator parameters for the data block, with respect to a more complex set of demodulator parameters.

### Claim 2 (depends on 1)

The method of claim 1, in which the data block is one of a resource element (RE), a sub-code block (CB), a CB, or a transport block.

### Claim 3 (depends on 1)

The method of claim 1, in which the plurality of sets of demodulation parameters define a search space, and/or a quantity of layers to be processed with higher complexity.

### Claim 4 (depends on 1)

The method of claim 1, in which the receiving device is a user equipment (UE).

### Claim 5 (depends on 1)

The method of claim 1, in which the receiving device is a base station.

### Claim 6 (depends on 1)

The method of claim 1, in which the goal comprises maintaining performance relative to the more complex set of demodulator parameters.

### Claim 7 (depends on 1)

The method of claim 1, in which the goal comprises maintaining performance within a first threshold amount relative to performance with the more complex set of demodulator parameters when a second threshold amount of power savings is achieved relative to power consumed with the more complex set of demodulator parameters.

### Claim 8

An apparatus for wireless communication by a receiving device, comprising:
a memory; and
at least one processor coupled to the memory, the at least one processor configured:
to predict with an artificial neural network, at each data block of a set of data blocks, a least complex set of demodulator parameters that will achieve a goal, based on features of a data block expected to be received; and
to dynamically select the least complex set of demodulator parameters, from a plurality of sets of demodulator parameters, based on the features of the data block expected to be received, the processor configured to dynamically select to prevent degradation of demodulation performance for each data block with the selected set of demodulator parameters for the data block, with respect to a more complex set of demodulator parameters.

### Claim 9 (depends on 8)

The apparatus of claim 8, in which the data block is one of a resource element (RE), a sub-code block (CB), a CB, or a transport block.

### Claim 10 (depends on 8)

The apparatus of claim 8, in which the plurality of sets of demodulation parameters define a search space, and/or a quantity of layers to be processed with higher complexity.

### Claim 11 (depends on 8)

The apparatus of claim 8, in which the receiving device is a user equipment (UE).

### Claim 12 (depends on 8)

The apparatus of claim 8, in which the receiving device is a base station.

### Claim 13 (depends on 8)

The apparatus of claim 8, in which the goal comprises maintaining performance relative to the more complex set of demodulator parameters.

### Claim 14 (depends on 8)

The apparatus of claim 8, in which the goal comprises maintaining performance within a first threshold amount relative to performance with the more complex set of demodulator parameters when a second threshold amount of power savings is achieved relative to power consumed with the more complex set of demodulator parameters.

### Claim 15

An apparatus for wireless communication by a receiving device, comprising:
means for predicting, with an artificial neural network, at each data block of a set of data blocks, a least complex set of demodulator parameters that will achieve a goal, based on features of a data block expected to be received; and
means for dynamically selecting the least complex set of demodulator parameters, from a plurality of sets of demodulator parameters, based on the features of the data block expected to be received, the means for dynamically selecting preventing degradation of demodulation performance for each data block with the selected set of demodulator parameters for the data block, with respect to a more complex set of demodulator parameters.

### Claim 16 (depends on 15)

The apparatus of claim 15, in which the data block is one of a resource element (RE), a sub-code block (CB), a CB, or a transport block.

### Claim 17 (depends on 15)

The apparatus of claim 15, in which the plurality of sets of demodulation parameters define a search space, and/or a quantity of layers to be processed with higher complexity.

### Claim 18 (depends on 15)

The apparatus of claim 15, in which the receiving device is a user equipment (UE).

### Claim 19 (depends on 15)

The apparatus of claim 15, in which the receiving device is a base station.

### Claim 20 (depends on 15)

The apparatus of claim 15, in which the goal comprises maintaining performance relative to the more complex set of demodulator parameters.

### Claim 21 (depends on 15)

The apparatus of claim 15, in which the goal comprises maintaining performance within a first threshold amount relative to performance with the more complex set of demodulator parameters when a second threshold amount of power savings is achieved relative to power consumed with the more complex set of demodulator parameters.

### Claim 22

A non-transitory computer-readable medium having program code recorded thereon, the program code executed by a processor of a receiving device and comprising:
program code to predict, with an artificial neural network, at each data block of a set of data blocks, a least complex set of demodulator parameters that will achieve a goal, based on features of a data block expected to be received; and
program code to dynamically select the least complex set of demodulator parameters, from a plurality of sets of demodulator parameters, based on the features of the data block expected to be received, the program code to dynamically select preventing degradation of demodulation performance for each data block with the selected set of demodulator parameters for the data block, with respect to a more complex set of demodulator parameters.

### Claim 23 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the data block is one of a resource element (RE), a sub-code block (CB), a CB, or a transport block.

### Claim 24 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the plurality of sets of demodulation parameters define a search space, and/or a quantity of layers to be processed with higher complexity.

### Claim 25 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the receiving device is a user equipment (UE).

### Claim 26 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the receiving device is a base station.

### Claim 27 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the goal comprises maintaining performance relative to the more complex set of demodulator parameters.

### Claim 28 (depends on 22)

The non-transitory computer-readable medium of claim 22, in which the goal comprises maintaining performance within a first threshold amount relative to performance with the more complex set of demodulator parameters when a second threshold amount of power savings is achieved relative to power consumed with the more complex set of demodulator parameters.
