# US 2022/0046577 A1 · Neural network functions for positioning measurement data processing at a user equipment

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

- Number: US 2022/0046577 A1
- Document ID: US20220046577A1
- Status: Published application
- Kind: A1
- Application number: 17/391,373
- Filed: 2021-08-02
- Published: 2022-02-10
- Earliest claimed: 2020-08-04
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Jay Kumar SUNDARARAJAN; Taesang YOO; Naga BHUSHAN; Pavan Kumar VITTHALADEVUNI; June NAMGOONG; Krishna Kiran MUKKAVILLI; Tingfang JI
- Web page: https://patentgrep.com/patent/US20220046577A1

## CPC

- G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)}
- H04W 64/00: Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management
- G01S 5/0036: {of measured values, i.e. measurement on mobile and position calculation on base station}
- G01S 5/0236: {Assistance data, e.g. base station almanac}
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- H04L 5/0048: {Allocation of pilot signals, i.e. of signals known to the receiver (allocation of control signalling H04L5/0053; use of control signalling H04L5/0091)}
- G01S 5/0205: {Details}
- G06N 3/045: Combinations of networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- H04L 5/001: {the frequencies being arranged in component carriers}
- H04L 5/005: {of common pilots, i.e. pilots destined for multiple users or terminals}
- H04L 5/0057: {Physical resource allocation for CQI}
- H04L 25/0224: {using sounding signals}
- H04L 27/0006: {Assessment of spectral gaps suitable for allocating digitally modulated signals, e.g. for carrier allocation in cognitive radio (for spectrum sharing between different networks H04W16/14)}
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In an aspect, a network component transmits, to a UE, at least one neural network function configured to facilitate processing of positioning measurement data into one or more positioning measurement features at the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures. The UE may obtain positioning measurement data associated with the UE, and may process the positioning measurement data into a respective set of positioning measurement features based on the at least one neural network function. The UE may report the processed set of positioning measurement features to a network component, such as the BS or LMF.

## Claims

### Claim 1

A method of operating a user equipment (UE), comprising:
obtaining at least one neural network function configured to facilitate positioning measurement data processing at the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures;
obtaining positioning measurement data associated with the UE;
processing the positioning measurement data into a respective set of positioning measurement features based on the at least one neural network function; and
reporting the processed set of positioning measurement features to a network component.

### Claim 2 (depends on 1)

The method of claim 1, wherein the obtaining obtains the positioning measurement data by performing a set of positioning measurements on a reference signal for positioning.

### Claim 3 (depends on 1)

The method of claim 1, wherein the obtaining obtains the positioning measurement data by capturing sensor data via one or more sensors communicatively coupled to the UE.

### Claim 4 (depends on 1)

The method of claim 1,
wherein the at least one neural network function comprises a first neural network function configured to process the positioning measurement data into a first respective set of positioning measurement features, and
wherein the at least one neural network function comprises a second neural network function configured to process the positioning measurement data into a second respective set of respective set of positioning measurement features.

### Claim 5 (depends on 4)

The method of claim 4,
wherein the first respective set of positioning measurement features is associated with less positioning precision relative to the second respective set of positioning measurement features, and
wherein the reporting reports the first respective set of positioning measurement features before the second respective set of positioning measurement features.

### Claim 6 (depends on 1)

The method of claim 1,
wherein the positioning measurement data comprises an uncompressed representation of raw samples of a reference signal for positioning, and
wherein the processed set of positioning measurement features comprises a compressed representation of the reference signal for positioning.

### Claim 7 (depends on 1)

The method of claim 1,
wherein the at least one neural network function comprises a plurality of neural network functions that are each configured to facilitate positioning measurement data processing at the UE of a single positioning measurement type or a group of positioning measurement types, or
wherein the at least one neural network function comprises a single neural network function configured to facilitate positioning measurement data processing at the UE of a plurality of positioning measurement types.

### Claim 8 (depends on 1)

The method of claim 1, wherein the positioning measurement data comprises an estimate of a channel response associated with a reference signal.

### Claim 9 (depends on 1)

The method of claim 1,
wherein the processing processes the positioning measurement data into a probability distribution associated with the set of positioning measurement features based on the at least one neural network function, and
wherein the reporting reports the probability distribution or metrics based on the probability distribution.

### Claim 10

A method of operating a base station (BS), comprising:
transmitting, to a user equipment (UE), at least one neural network function configured to facilitate processing of positioning measurement data into one or more positioning measurement features at the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; and
receiving, from the UE, a set of positioning measurement features that is processed based on the at least one neural network function.

### Claim 11 (depends on 10)

The method of claim 10, wherein the at least one neural network function is generated dynamically at the BS or another network component.

### Claim 12 (depends on 10)

The method of claim 10, wherein the positioning measurement data comprises a set of positioning measurements on a reference signal for positioning.

### Claim 13 (depends on 10)

The method of claim 10, wherein the positioning measurement data comprises sensor data captured via one or more sensors communicatively coupled to the UE.

### Claim 14 (depends on 10)

The method of claim 10, wherein the set of positioning measurement features comprises a compressed representation of an initial set of positioning measurements measured at the UE with respect to a reference signal for positioning.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
recovering the initial set of positioning measurements measured at the UE by uncompressing the processed set of positioning measurements into an uncompressed set of positioning measurements; and
determining a positioning estimate for the UE based on the uncompressed set of positioning measurements.

### Claim 16 (depends on 10)

The method of claim 10, further comprising:
determining a positioning estimate for the UE based on the received set of positioning measurements.

### Claim 17 (depends on 10)

The method of claim 10, wherein the receiving comprises:
receiving, from the UE, a first respective set of respective set of positioning measurement features associated with a first neural network function; and
receiving, from the UE after the first respective set of respective set of positioning measurement features is received, a second respective set of respective set of positioning measurement features based on a second neural network function.

### Claim 18 (depends on 17)

The method of claim 17,
wherein the first respective set of positioning measurement features is associated with less positioning precision relative to the second respective set of positioning measurement features.

### Claim 19 (depends on 10)

The method of claim 10, wherein the positioning measurement data comprises an estimate of a channel response associated with a reference signal.

### Claim 20 (depends on 10)

The method of claim 10,
wherein the at least one neural network function configured to facilitate processing of the positioning measurement data into a probability distribution associated with the set of positioning measurement features based on the at least one neural network function, and
wherein the receiving receives the probability distribution or metrics based on the probability distribution.

### Claim 21

A user equipment (UE), comprising:
a memory;
at least one transceiver; and
at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to:
obtain at least one neural network function configured to facilitate positioning measurement data processing at the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures;
obtain positioning measurement data associated with the UE;
process the positioning measurement data into a respective set of positioning measurement features based on the at least one neural network function; and
report the processed set of positioning measurement features to a network component.

### Claim 22 (depends on 21)

The UE of claim 21,
wherein the obtaining obtains the positioning measurement data by performing a set of positioning measurements on a reference signal for positioning, or
wherein the obtaining obtains the positioning measurement data by capturing sensor data via one or more sensors communicatively coupled to the UE.

### Claim 23 (depends on 21)

The UE of claim 21,
wherein the at least one neural network function comprises a first neural network function configured to process the positioning measurement data into a first respective set of positioning measurement features, and
wherein the at least one neural network function comprises a second neural network function configured to process the positioning measurement data into a second respective set of respective set of positioning measurement features.

### Claim 24 (depends on 21)

The UE of claim 21, wherein the positioning measurement data comprises an estimate of a channel response associated with a reference signal.

### Claim 25

A base station (BS), comprising:
a memory;
at least one transceiver; and
at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to:
transmit, via the at least one transceiver, to a user equipment (UE), at least one neural network function configured to facilitate processing of positioning measurement data into one or more positioning measurement features at the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; and
receive, via the at least one transceiver, from the UE, a set of positioning measurement features that is processed based on the at least one neural network function.

### Claim 26 (depends on 25)

The BS of claim 25, wherein the at least one neural network function is generated dynamically at the BS or another network component.

### Claim 27 (depends on 25)

The BS of claim 25, wherein the positioning measurement data comprises a set of positioning measurements on a reference signal for positioning.

### Claim 28 (depends on 25)

The BS of claim 25, wherein the positioning measurement data comprises sensor data captured via one or more sensors communicatively coupled to the UE.

### Claim 29 (depends on 25)

The BS of claim 25, wherein the set of positioning measurement features comprises a compressed representation of an initial set of positioning measurements measured at the UE with respect to a reference signal for positioning.

### Claim 30 (depends on 25)

The BS of claim 25, wherein the positioning measurement data comprises an estimate of a channel response associated with a reference signal.
