IP Library › Granted Patent US 12,684,340
Granted Patent B2
US 12,684,340 · App. 18/858,606 · Granted Jul 14, 2026

Neural network processing management

Inventors: Yushu Zhang (Beijing, CN); Dawei Zhang (Saratoga, CA); Oghenekome Oteri (San Diego, CA); Huaning Niu (Los Gatos, CA); Wei Zeng (San Diego, CA); Weidong Yang (San Diego, CA); Hong He (Cupertino, CA)
Assignee: Apple Inc.
H04W8/24G06N3/063H04W72/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,684,340
App. No.
18/858,606
Granted
Jul 14, 2026
Kind
B2
Abstract

This disclosure relates to techniques for managing neural network processing resources in a wireless communication system. A wireless device and a cellular base station can establish a wireless link. The wireless device can determine its neural network processing capability. The wireless device can provide neural network processing capability information to the cellular base station. The cellular base station can determine whether and when to configure activities that use neural network processing for the wireless device based at least in part on the neural network processing capability information for the wireless device.

Claims (64)

1 . A method, comprising:

establishing a wireless link with a cellular base station;

determining neural network processing capability information for a wireless device, wherein the neural network processing capability information includes one or more indications of a number of supported neural network processing units (NPUs) for the wireless device for beam prediction in a spatial domain, beam prediction in a time domain, and positioning estimation; and

providing the neural network processing capability information for the wireless device to the cellular base station.

2 . The method of claim 1 ,

wherein the neural network processing capability information includes an other indication of a number of supported neural network processing units (NPUs) for the wireless device.

3 . The method of claim 1 ,

wherein the indication indicates the number of supported NPUs for the wireless device for:

channel state information measurement and reporting.

4 . The method of claim 1 ,

wherein the neural network processing capability information includes availability information for NPUs for the wireless device.

5 . The method of claim 4 , wherein the availability information for NPUs for the wireless device includes one or more of:

an other indication that one or more NPUs for the wireless device are always available for neural network processing tasks associated with the wireless link; or

an other indication of one or more of a preferred on duration, a preferred off duration, or a preferred periodicity of availability for one or more NPUs for the wireless device.

6 . The method of claim 1 ,

wherein the neural network processing capability information includes an other indication of a number of layers and a number of nodes per layer with which the wireless device is capable of performing neural network processing for one or more NPUs for the wireless device.

7 . The method of claim 1 , wherein the method further comprises:

receiving information from the cellular base station configuring the wireless device to perform a neural network processing activity;

determining a neural network processing unit occupancy duration for the neural network processing activity; and

performing the neural network processing activity.

8 . The method of claim 7 , wherein the neural network processing activity includes one or more of:

beam prediction and reporting;

channel state information measurement and reporting; or

wireless device positioning estimation.

9 . The method of claim 7 , wherein the method further comprises:

determining that neural network processing activity greater than neural network processing capability for the wireless device is configured by the cellular base station; and

determining one or more neural network processing activities to drop based at least in part on neural network processing activity configured by the cellular base station being greater than neural network processing capability for the wireless device.

10 . The method of claim 9 ,

wherein the one or more neural network processing activities to drop are determined based at least in part on priority indications for the one or more neural network processing activities, wherein neural network processing activities with lowest priority indications are dropped until a remaining number of neural network processing activities configured by the cellular base station is within the neural network processing capability for the wireless device.

11 . The method of claim 10 ,

wherein the priority indications for the one or more neural network processing activities are received by the wireless device via one or more of:

radio resource control (RRC) signaling;

media access control (MAC) control element (CE) signaling; or

downlink control information (DCI) signaling.

12 . A method, comprising:

establishing a wireless link with a wireless device;

receiving neural network processing capability information from the wireless device, wherein the neural network processing capability information includes one or more indications of a number of supported neural network processing units (NPUs) for the wireless device for beam prediction in a spatial domain, beam prediction in a time domain, and positioning estimation; and

configuring one or more neural network processing activities for the wireless device, wherein the one or more neural network processing activities are configured based at least in part on the neural network processing capability information.

13 . The method of claim 12 ,

wherein configuring one or more neural network processing activities for the wireless device based at least in part on the neural network processing capability information includes limiting number and type of neural network processing activities configured for the wireless device to be within neural network processing capability for the wireless device.

14 . The method of claim 13 , wherein the method further comprises:

determining neural network processing unit occupancy duration for the one or more neural network processing activities configured for the wireless device,

wherein limiting number and type of neural network processing activities configured for the wireless device to be within neural network processing capability for the wireless device is further based at least in part on the determined neural network processing unit occupancy duration for the one or more neural network processing activities configured for the wireless device.

15 . The method of claim 12 ,

wherein the neural network processing capability information includes availability information for NPUs for the wireless device, wherein the method further comprises:

determining an availability pattern for NPUs for the wireless device based at least in part on the availability information for NPUs for the wireless device; and

providing an other indication of the availability pattern for NPUs for the wireless device to the wireless device.

16 . The method of claim 12 ,

wherein the neural network processing capability information includes an other indication of a number of layers and a number of nodes per layer with which the wireless device is capable of performing neural network processing for one or more (NPUs) for the wireless device.

17 . The method of claim 12 , wherein the method further comprises:

providing priority information for the one or more neural network processing activities to the wireless device, wherein the priority information for the one or more neural network processing activities is provided via one or more of:

radio resource control (RRC) signaling;

media access control (MAC) control element (CE) signaling; or

downlink control information (DCI) signaling.

18 . An apparatus, comprising:

a processor configured to, when executing instructions stored in a memory, to perform operations comprising:

establishing a wireless link with a wireless device;

receiving neural network processing capability information from the wireless device wherein the neural network processing capability information includes one or more indications of a number of supported neural network processing units (NPUs) for the wireless device for beam prediction in a spatial domain, beam prediction in a time domain, and positioning estimation; and

configuring one or more neural network processing activities for the wireless device, wherein the one or more neural network processing activities are configured based at least in part on the neural network processing capability information.

19 . The apparatus of claim 18 ,

wherein configuring one or more neural network processing activities for the wireless device based at least in part on the neural network processing capability information includes limiting number and type of neural network processing activities configured for the wireless device to be within neural network processing capability for the wireless device.

20 . The apparatus of claim 19 , wherein the operations further comprise:

determining neural network processing unit occupancy duration for the one or more neural network processing activities configured for the wireless device,

wherein limiting number and type of neural network processing activities configured for the wireless device to be within neural network processing capability for the wireless device is further based at least in part on the determined neural network processing unit occupancy duration for the one or more neural network processing activities configured for the wireless device.