Techniques for demonstrating signal processing procedures for network-deployed neural network models

Abstract

Methods, systems, and devices for wireless communications are described. In some examples, a device (e.g., a user equipment (UE)) may obtain a configuration message from a base station indicating one or more neural network models. The UE may then obtain an indication of a sequence of operations for a signal processing procedure for one of the one or more neural network models. In some examples, the signal processing procedure includes an input pre-processing procedure or an output pre-processing procedure. Upon obtaining the signal from the base station, the UE may perform a signal processing procedure on a received signal for the neural network model according to the sequence of operations.

Description

Claim of Priority

[0001] Cross Reference

[0001] This patent application claims the benefit of Indian Provisional Patent Application No. 202121018558, filed on April 22, 2021, entitled "TECHNIQUES FOR INDICATING SIGNAL PROCESSING PROCEDURES FOR NETWORK DEPLOYED NEURAL NETWORK MODELS" by YERRAM(registered trademark) ALLI et al., which is assigned to the assignee of the present application.

Technical Field

[0002]

[0002] The following relates to wireless communications, and more specifically to methods and systems for indicating information related to signal processing procedures for neural network models.

Background Art

[0003]

[0003] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, and broadcast. These systems may be able to support communication with multiple users by sharing available system resources (e.g., time, frequency, and power). Examples of such multiple access systems include fourth-generation (4G) systems such as Long-Term Evolution (LTE®) systems, LTE Advanced (LTE-A) systems, or LTE-A Pro systems, and fifth-generation (5G) systems, sometimes called New Radio (NR) systems. These systems may employ techniques such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations or one or more network access nodes, each simultaneously supporting communication for multiple communication devices, which may sometimes be known as user equipment (UEs). [Overview of the project]

[0004]

[0004] A method for wireless communication in a device in a wireless network is described. The method may include: obtaining a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device; and obtaining an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The method may further include performing the signal processing procedure for at least one neural network model using signals obtained in the device according to the sequence of operations.

[0005]

[0005] An apparatus for wireless communication in a device in a wireless network is described. The apparatus may include a processor and memory coupled to the processor. The processor may be configured to: obtain a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device; and obtain an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The processor may be further configured to perform the signal processing procedure for at least one neural network model using signals obtained in the device according to the sequence of operations.

[0006]

[0006] Another apparatus for wireless communication in a device in a wireless network is described. The apparatus may include means for obtaining a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device, and means for obtaining an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The apparatus may further include means for performing the signal processing procedure for at least one neural network model using signals obtained in the device according to the sequence of operations.

[0007]

[0007] A non-temporary computer-readable medium for storing code for wireless communication in a device in a wireless network is described. The code may include instructions that can be executed by a processor to perform: obtain a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device; and obtain an indication of a sequence of operations for a signal processing procedure for at least one of the neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The code may further include instructions that can be executed by a processor to perform the signal processing procedure for at least one neural network model using signals obtained in the device according to the sequence of operations.

[0008]

[0008] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for obtaining signaling that constitutes a device with a set of actions including one or more actions from a sequence of actions for at least one neural network model.

[0009]

[0009] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, obtaining an indication of a sequence of actions may include actions, features, means, or instructions for obtaining an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message includes a set of actions that include all actions of a sequence of actions for at least one neural network model.

[0010]

[0010] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, obtaining an indication of a sequence of actions may include an action, feature, means, or instruction for obtaining a second configuration message for a device, where the second configuration message indicates a set of actions comprising all actions of at least one neural network model, an indication of a sequence of actions, and a sequence of actions for at least one neural network model.

[0011]

[0011] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, obtaining an indication of a sequence of actions may include actions, features, means, or instructions for obtaining a set of input parameters, a set of output parameters, or both for one or more actions of a sequence of actions for at least one neural network model.

[0012]

[0012] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include operations, features, means, or instructions for obtaining indications of mappings between one or more neural network models and sets of operating states, wherein a signal processing procedure for at least one neural network model may be performed using signals obtained in the device according to a sequence of operations based on mappings between one or more neural network models and sets of operating states.

[0013]

[0013] In some examples of the methods, apparatus, and non-transient computer-readable media described herein, the set of operating states includes a signal-to-noise ratio (SNR) range, bandwidth range, signal scaling range, channel delay profile, signal peak range, or any combination thereof, relating to the signal acquired in the device.

[0014]

[0014] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for outputting messages indicating the device's ability to support one or more actions for one or more signal processing procedures, wherein indication of a sequence of actions for a signal processing procedure for at least one neural network model may be obtained based on the device's capabilities.

[0015]

[0015] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a sequence of operations includes one or more operations supported by the device.

[0016]

[0016] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a message indicating the device's ability to support one or more operations for one or more signal processing procedures includes an indication of a threshold input dimension for each of the one or more operations for one or more signal processing procedures, or a threshold runtime for each of the one or more operations for one or more signal processing procedures.

[0017]

[0017] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, obtaining an indication of a sequence of actions may include actions, features, means, or instructions for obtaining radio resource control (RRC) signaling or media access control (MAC) control elements (MAC-CE) that include an indication of a sequence of actions.

[0018]

[0018] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for obtaining indications of one or more data formats relating to one or more actions in a sequence of actions, wherein one or more data formats include Extensible Markup Language (XML) data formats, Java Script Object Notation (JSON) data formats, or any combination thereof.

[0019]

[0019] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, the devices include UEs, base stations, network entities, relay devices, sidelink devices, or integrated access and backhaul (IAB) nodes.

[0020]

[0020] A method for wireless communication in a network entity is described. The method may include outputting a configuration message to a device, wherein the configuration message indicates one or more neural network models for the device, and outputting an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The method may further include outputting a signal to the device based on the indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0021]

[0021] An apparatus for wireless communication in a network entity is described. The apparatus may include a processor and memory coupled to the processor. The processor may be configured to output a configuration message to a device, wherein the configuration message indicates one or more neural network models for the device, and to output an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The processor may be further configured to output a signal to the device based on the indication of the sequence of operations for the signal processing procedure for at least one neural network model.

[0022]

[0022] Another apparatus for wireless communication in a network entity is described. The apparatus may include means for outputting a configuration message to a device, wherein the configuration message indicates one or more neural network models for the device, and means for outputting an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The apparatus may further include means for outputting a signal to the device based on the indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0023]

[0023] A non-temporary computer-readable medium for storing code for wireless communication in a network entity is described. The code may include instructions that can be executed by a processor to output a configuration message to a device, wherein the configuration message indicates one or more neural network models for the device, and an indication of a sequence of actions for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure includes one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model. The code may further include instructions that can be executed by a processor to output a signal to the device based on the indication of the sequence of actions for a signal processing procedure for at least one neural network model.

[0024]

[0024] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for outputting signaling that configures a device with a set of operations including one or more operations from a sequence of operations for at least one neural network model.

[0025]

[0025] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for obtaining a second sequence of operations for a second signaling procedure implemented at a network entity.

[0026]

[0026] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, outputting an indication of a sequence of operations may include operations, features, means, or instructions for outputting an indication of a sequence of operations for a signal processing procedure in a configuration message, where the configuration message includes a set of operations including all operations in the sequence of operations for at least one neural network model.

[0027]

[0027] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, outputting an indication of a sequence of operations may include operations, features, means, or instructions for outputting a second configuration message to a device, where the second configuration message indicates the at least one neural network model, the indication of the sequence of operations, and the set of operations including all operations in the sequence of operations for the at least one neural network model.

[0028]

[0028] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, outputting an indication of a sequence of actions may include actions, features, means, or instructions for outputting a set of input parameters, a set of output parameters, or both for one or more actions of a sequence of actions for at least one neural network model.

[0029]

[0029] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for outputting indications of mappings between one or more neural network models and sets of operating states.

[0030]

[0030] In some examples of the methods, apparatus, and non-transient computer-readable media described herein, the set of operating states includes an SNR range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to the signal transmitted to the device.

[0031]

[0031] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for obtaining a message indicating the device's ability to support one or more actions for one or more signal processing procedures, wherein obtaining an indication of a sequence of actions for a signal processing procedure for at least one neural network model may be based on the device's ability.

[0032]

[0032] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a sequence of operations includes one or more operations supported by the device.

[0033]

[0033] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a message indicating the device's ability to support one or more operations for one or more signal processing procedures includes an indication of a threshold input dimension for each of the one or more operations for one or more signal processing procedures, or a threshold runtime for each of the one or more operations for one or more signal processing procedures.

[0034]

[0034] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, outputting an indication of a sequence of actions may include actions, features, means, or instructions for outputting RRC signaling or MAC-CE containing an indication of a sequence of actions.

[0035]

[0035] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for outputting indications of one or more data formats relating to one or more actions in a sequence of actions, wherein one or more data formats include XML data formats, JSON data formats, or any combination thereof.

[0036]

[0036] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, the device includes a UE, base station, network entity, relay device, sidelink device, or IAB node.

[0037]

[0037] A method for wireless communication in a device in a wireless network is described. The method may include receiving a configuration message for the device, the configuration message indicating one or more neural network models for the device, receiving an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model, and performing the signal processing procedure for at least one neural network model using signals received in the device in accordance with the sequence of operations.

[0038]

[0038] An apparatus for wireless communication in a device in a wireless network is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions may be executable by the processor to cause the apparatus to: receive a configuration message for the device, the configuration message indicating one or more neural network models for the device; receive an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model; and perform the signal processing procedure for at least one neural network model using signals received in the device according to the sequence of operations.

[0039]

[0039] Another apparatus for wireless communication in a device in a wireless network is described. The apparatus may include means for receiving a configuration message for a device, the configuration message indicating one or more neural network models for the device; means for receiving an indication of a sequence of operations for a signal processing procedure for at least one of the neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model; and means for performing the signal processing procedure for at least one neural network model using signals received in the device in accordance with the sequence of operations.

[0040]

[0040] A non-temporary computer-readable medium for storing code for wireless communication in a device in a wireless network is described. The code may include instructions that can be executed by a processor to: receive a configuration message for the device, the configuration message indicating one or more neural network models for the device; receive an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model; and perform the signal processing procedure for at least one neural network model using signals received in the device in accordance with the sequence of operations.

[0041]

[0041] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for receiving signaling that constitute a device in a set of actions including one or more actions from a sequence of actions for at least one neural network model.

[0042]

[0042] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for receiving an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message includes a set of actions that include all of a sequence of actions for at least one neural network model.

[0043]

[0043] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include operations, features, means, or instructions for receiving a second configuration message for a device, the second configuration message indicating a set of operations comprising at least one neural network model, an indication of a sequence of operations, and all operations of a sequence of operations for at least one neural network model.

[0044]

[0044] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for receiving a set of input parameters, a set of output parameters, or both for one or more actions of a sequence of actions for at least one neural network model.

[0045]

[0045] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include operations, features, means, or instructions for receiving indications of mappings between one or more neural network models and sets of operating states, wherein performing a signal processing procedure for at least one neural network model using signals received in the device in accordance with a sequence of operations may be based on mappings between one or more neural network models and sets of operating states.

[0046]

[0046] In some examples of the methods, apparatus, and non-transient computer-readable media described herein, the set of operating states includes an SNR range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to the signal received in the device.

[0047]

[0047] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for sending messages indicating the device's ability to support one or more actions for one or more signal processing procedures, wherein receiving an indication of a sequence of actions for a signal processing procedure for at least one neural network model may be based on the device's ability.

[0048]

[0048] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a sequence of operations includes one or more operations supported by the device.

[0049]

[0049] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a message indicating the device's ability to support one or more operations for one or more signal processing procedures includes an indication of a threshold input dimension for each of the one or more operations for one or more signal processing procedures, or a threshold runtime for each of the one or more operations for one or more signal processing procedures.

[0050]

[0050] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include operations, features, means, or instructions for receiving RRC signaling or MAC-CE, including indication of a sequence of operations.

[0051]

[0051] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for receiving indications of one or more data formats relating to one or more actions in a sequence of actions, the one or more data formats including XML data format, JSON data format, or any combination thereof.

[0052]

[0052] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, the device includes a UE, base station, network entity, relay device, sidelink device, or IAB node.

[0053]

[0053] A method for wireless communication at a base station is described. The method may include: sending a configuration message to a device, the configuration message indicating one or more neural network models for the device; sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models; the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model; and sending a signal to the device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0054]

[0054] An apparatus for wireless communication at a base station is described. The apparatus may include a processor, a memory coupled to the processor, and instructions stored in the memory. Instructions may be executable by the processor to cause the apparatus to send a configuration message to a device, the configuration message indicating one or more neural network models for the device, and an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model, and to send a signal to the device based on the indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0055]

[0055] Another apparatus for wireless communication at a base station is described. The apparatus may include means for sending a configuration message to a device, the configuration message indicating one or more neural network models for the device, and means for sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model, and means for sending a signal to the device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0056]

[0056] A non-temporary computer-readable medium for storing code for wireless communication at a base station is described. The code may include instructions that can be executed by a processor to send a configuration message to a device, the configuration message indicating one or more neural network models for the device, and an indication of a sequence of actions for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model, and to send a signal to the device based on having sent the indication of a sequence of actions for a signal processing procedure for at least one neural network model.

[0057]

[0057] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting signaling that constitutes a device in a set of actions including one or more actions from a sequence of actions for at least one neural network model.

[0058]

[0058] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include operations, features, means, or instructions for receiving a second sequence of operations for a second signaling procedure performed at a base station.

[0059]

[0059] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message includes a set of actions comprising all actions of a sequence of actions for at least one neural network model.

[0060]

[0060] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for sending a second configuration message to a device, the second configuration message indicating a set of actions comprising at least one neural network model, an indication of a sequence of actions, and all actions of a sequence of actions for at least one neural network model.

[0061]

[0061] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting a set of input parameters, a set of output parameters, or both for one or more actions of a sequence of actions for at least one neural network model.

[0062]

[0062] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting indications of mappings between one or more neural network models and sets of operating states.

[0063]

[0063] In some examples of the methods, apparatus, and non-transient computer-readable media described herein, the set of operating states includes an SNR range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to the signal transmitted to the device.

[0064]

[0064] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for receiving messages indicating the device's ability to support one or more actions for one or more signal processing procedures, wherein receiving an indication of a sequence of actions for a signal processing procedure for at least one neural network model may be based on the device's ability.

[0065]

[0065] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a sequence of operations includes one or more operations supported by the device.

[0066]

[0066] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, a message indicating the device's ability to support one or more operations for one or more signal processing procedures includes an indication of a threshold input dimension for each of the one or more operations for one or more signal processing procedures, or a threshold runtime for each of the one or more operations for one or more signal processing procedures.

[0067]

[0067] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting RRC signaling or MAC-CE, including indication of a sequence of actions.

[0068]

[0068] Some examples of methods, apparatus, and non-temporary computer-readable media described herein may further include actions, features, means, or instructions for transmitting indications of one or more data formats relating to one or more actions in a sequence of actions, the one or more data formats including XML data format, JSON data format, or any combination thereof.

[0069]

[0069] In some examples of the methods, apparatus, and non-temporary computer-readable media described herein, the device includes a UE, base station, network entity, relay device, sidelink device, or IAB node. [Brief explanation of the drawing]

[0070] [Figure 1]

[0070] A figure illustrating an example of a wireless communication system that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 2] A figure illustrating an example of a wireless communication system that supports a technique for demonstrating signal processing procedures for network-deployed neural network models, according to one or more aspects of the present disclosure. [Figure 3]

[0071] A diagram illustrating an example of a flowchart supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 4]

[0072] A figure illustrating an example of a machine learning process that supports techniques for demonstrating signal processing procedures for network-deployed neural network models, according to one or more aspects of the present disclosure. [Figure 5]

[0073] A diagram illustrating an example of a process flow supporting a technique for demonstrating signal processing procedures for network-deployed neural network models, according to one or more aspects of the present disclosure. [Figure 6]

[0074] A block diagram of a device supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 7] A block diagram of a device supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 8]

[0075] A block diagram of a communications manager supporting a technique for illustrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 9]

[0076] A diagram of a system including a device that supports a technique for demonstrating signal processing procedures for network-deployed neural network models, according to one or more aspects of the present disclosure. [Figure 10]

[0077] A block diagram of a device supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 11] A block diagram of a device supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 12]

[0078] A block diagram of a communications manager supporting a technique for illustrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 13]

[0079] A diagram of a system including a device that supports a technique for demonstrating signal processing procedures for network-deployed neural network models, according to one or more aspects of the present disclosure. [Figure 14]

[0080] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 15] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 16] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 17] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 18] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Figure 19] A flowchart illustrating a method for supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. [Modes for carrying out the invention]

[0071]

[0081] Some wireless communication systems may support machine learning or neural network models (also called machine learning models) which can be used to optimize the wireless communication process, such as decoding, encoding, analog-to-digital conversion, and generating information for reporting to higher layers or transmitting in response to received signals. To utilize a neural network model, a device (e.g., an UE) may perform preprocessing on the received signal before inputting it into the neural network model, which may convert the received signal into a format compatible with the neural network model (e.g., a format that can be received and processed by the neural network model). As used herein, the term “preprocessing” may be used to refer to any action, procedure, algorithm, or mathematical calculation that may be performed to convert a signal into a format that can be received and processed by a neural network model.

[0072]

[0082] Similarly, a device may perform post-processing on the output of a neural network model, which may convert the output into a format suitable for reporting the output to the device's network or higher layers (e.g., a format of the output that can be received and / or processed by the network or higher layers). The output of a neural network model may include a modified version of the signals input to the neural network model, decisions or calculations performed by the neural network model based on the input, etc. However, methods for providing wireless devices (e.g., UEs) with information and instructions to perform signal processing (e.g., pre-processing and post-processing) for neural network models implemented within wireless communication systems have not yet been considered. That is, some wireless communication systems do not define or intend signaling and configurations that can be used to provide UEs and other wireless devices with information (e.g., actions, instructions) that enable each UE and wireless device to implement a neural network model within their respective wireless communication systems.

[0073]

[0083] As described herein, a device may receive (e.g., acquire) signaling indicating pre-processing, post-processing, and signal processing (e.g., pre-processing or post-processing) operations for each pre-processing, post-processing, and neural network model, and the order in which those operations should be performed. Neural network models may include the same signal processing operations (e.g., basic functions or non-trainable layers), such as signal scaling operations, cyclic shift operations, and inverse fast Fourier transform (IFFT) operations. While signal processing operations may be common across neural network models, the sequence in which the operations are performed, as well as the input and output parameters of the operations, may differ for each neural network model. Accordingly, aspects of this disclosure concern signaling and techniques that enable a wireless device (e.g., a UE) to consist of pre-processing and post-processing operations related to signal processing and neural network models. In this regard, aspects of this disclosure enable the UE to implement the signal processing and neural network model-related operations in the correct order (e.g., the appropriate chronological order of operations), thereby enabling the wireless device to perform the signal processing operations related to the neural network model more efficiently and effectively.

[0074]

[0084] In this disclosure, the terms “signal processing procedure,” “signal processing operation,” and similar terms may be used to refer to any procedure or operation for processing a physical layer signal covering time, frequency, space, and / or code domains observed in one or more time instances. Accordingly, the terms “signal processing procedure” and “signal processing operation” may be used to process various types of signals, including radio frequency signals, audio / video (A / V) signals, time-series data, images, and the like.

[0075]

[0085] In one example, a network (e.g., an entity in a wireless communication system, such as a network entity or base station) may constitute a device with a set of signal processing operations (e.g., which may be defined in a standard) and may indicate a signal sequence of operations for each neural network model (e.g., the order in which the set of operations should be performed) as well as input and output parameters for the operations (e.g., via RRC signaling or MAC-CE). The sequence of operations may indicate a sequence of subsets of operations contained within the set of operations (e.g., the set of operations includes a first subset of operations, then a second subset of operations, etc.), and / or a sequence of operations within a given subset of operations (e.g., the subset of operations includes a first operation, then a second operation). Upon acquiring or receiving a signal (e.g., from a network entity), the device may perform signal processing according to the sequence of operations. In another example, a network (e.g., a network entity) may signal to a device, as part of a complete package, the signal processing operations for the neural network models, the sequence of operations, and the input and output parameters, along with the neural network models.

[0076]

[0086] In some examples, a device may also acquire or receive signaling indicating a relationship between a neural network model and an operating range (e.g., SNR range or bandwidth range) that the device can use to dynamically select which neural network model to apply to a received signal. Furthermore, a device may output or transmit signaling to a network indicating its ability to perform signal processing operations, and the network may use this capability signaling to determine which neural network model to provide to the device. Using the methods described herein, a device may acquire (e.g., receive) information related to signal processing and perform signaling processing according to information about a neural network model deployed by a wireless device (e.g., a UE) within a wireless communication system. Thus, the techniques described herein may enable UEs and other wireless devices to perform signal processing operations that facilitate neural network models more efficiently and effectively, thereby enabling more complex and reliable processing within a wireless communication system.

[0077]

[0087] Aspects of this disclosure are first described in the context of wireless communication systems. Additional aspects of this disclosure are described in the context of flowcharts, machine learning processes, and process flows. Aspects of this disclosure are further illustrated and described with reference to apparatus diagrams, system diagrams, and flowcharts relating to techniques for illustrating signal processing procedures for network-deployed neural network models.

[0078]

[0088] Figure 1 shows an example of a wireless communication system 100 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. The wireless communication system 100 may include one or more network entities 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a Long-Term Evolution (LTE) network, an LTE Advanced (LTE-A) network, an LTE-A Pro network, or a New Radio (NR) network. In some examples, the wireless communication system 100 may support extended broadband communication, ultra-high reliability (e.g., mission-critical) communication, low-latency communication, communication using low-cost and low-complexity devices, or any combination thereof.

[0079]

[0089] Network entities 105 may be distributed across a geographical area to form a wireless communication system 100 and may be devices of different forms or with different capabilities. Network entities 105 and UE 115 may communicate wirelessly via one or more communication links 125. Each base station 105 may provide a coverage area 110 from which UE 115 and base station 105 can establish one or more communication links 125. Coverage area 110 may be an example of a geographical area from which base station 105 and UE 115 can support signal communication according to one or more radio access technologies.

[0080]

[0090] The UE115 may be distributed throughout the coverage area 110 of the wireless communication system 100, and each UE115 may be stationary, mobile, or both at different times. The UE115 may be devices of different forms or with different capabilities. Several exemplary UE115 are shown in Figure 1. The UE115 described herein may be capable of communicating with various types of devices, such as other UE115, network entities 105, or network equipment (e.g., core network nodes, relay devices, IAB nodes, or other network equipment), as shown in Figure 1.

[0081]

[0091] Network entities 105 may communicate with the core network 130, communicate with each other, or both. For example, network entities 105 may interface with the core network 130 through one or more backhaul links 120 (e.g., via S1, N2, N3, or other interfaces). Network entities 105 may communicate with each other over the backhaul links 120 (e.g., via X2, Xn, or other interfaces) either directly (e.g., directly between network entities 105) or indirectly (e.g., via the core network 130), or both. In some examples, the backhaul links 120 may be one or more wireless links, or include them.

[0082]

[0092] One or more of the network entities 105 described herein may include, or be referred to as, a base transceiver station, a radio base station, an access point, a radio transceiver, a node B, an enode B (eNB), a next-generation node B or giganode B (any of which may be called a gNB), a home node B, a home enode B, or other preferred terms.

[0083]

[0093] As described herein, a node, sometimes referred to as a network node, network entity, or wireless node, may be a base station (e.g., any base station as described herein), a UE (e.g., any UE as described herein), a network controller, equipment, device, computing system, one or more components, and / or another preferred processing entity, configured to implement any of the techniques described herein. For example, a network node may be a UE. As another example, a network node may be a base station. As yet another example, a first network node may be configured to communicate with a second or third network node. In one aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a UE. In another aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a base station. In yet another aspect of this example, the first, second, and third network nodes may differ from those examples. Similarly, references to UEs, base stations, equipment, devices, computing systems, etc., may include disclosures that UEs, base stations, equipment, devices, computing systems, etc., are network nodes. For example, a disclosure that a UE is configured to acquire or receive information from a base station also discloses that a first network node is configured to receive information from a second network node. If, in accordance with this disclosure, a particular example is broadened in accordance with this disclosure (for example, a UE being configured to receive information from a base station also discloses that a first network node is configured to receive information from a second network node), then a broader example of a narrower example may be interpreted in the reverse, but broad, open-ended manner.In the above example, where configuring a UE to receive information from a base station also discloses that a first network node is configured to receive information from a second network node, the first network node may refer to a first UE, a first base station, a first apparatus, a first device, a first computing system, one or more first components, a first processing entity, etc., configured to receive information, and the second network node may refer to a second UE, a base station, a second apparatus, a second device, a second computing system, one or more first components, a first processing entity, etc.

[0084]

[0094] As described herein, the communication of information (e.g., arbitrary information, signals, etc.) may be described in various ways using different terminology. Disclosure of one communication term includes disclosure of other communication terms. For example, a first network node may be described as being configured to output or transmit information to a second network node. In this example, in accordance with the present disclosure, the disclosure that a first network node is configured to transmit information to a second network node includes the disclosure that a first network node is configured to provide, send, output, communicate, or transmit information to a second network node. Similarly, in this example, in accordance with the present disclosure, the disclosure that a first network node is configured to transmit information to a second network node includes the disclosure that a second network node is configured to receive, retrieve, or decode information provided, sent, output, communicated, or transmitted by a first network node.

[0085]

[0095] UE115 may include, or may be referred to as, a mobile device, wireless device, remote device, handheld device, or subscriber device, or any other preferred term, where “device” may also be referred to as a unit, station, terminal, or client, in the examples. UE115 may also include, or may be referred to as, a personal electronic device, such as a cellular phone, personal digital assistant (PDA), tablet computer, laptop computer, or personal computer. In some examples, UE115 may include, or may be referred to as, a wireless local loop (WLL) station, an Internet of Things (IoT) device, any Internet of Things (IoE) device, or a machine-type communications (MTC) device, in the examples, which may be implemented in various objects, such as appliances, vehicles, meters, etc.

[0086]

[0096] The UE115 described herein may be capable of communicating with other UE115s that may sometimes act as relays, as shown in Figure 1, as well as with various types of devices, including, in some examples, macro eNBs or gNBs, small cell eNBs or gNBs, or network entities 105 and network equipment, including relay base stations. In some examples, the UE115 may communicate with the core network 130 through a communication link 155.

[0087]

[0097] UE115 and network entity 105 may communicate wirelessly with each other via one or more communication links 125 over one or more carriers. The term "carrier" may refer to a set of radio frequency spectrum resources having a defined physical layer structure for supporting communication links 125. For example, a carrier used for communication link 125 may include a portion of a radio frequency spectrum band (e.g., a bandwidth portion) operating according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling to coordinate the operation for the carrier, user data, or other signaling. The wireless communication system 100 may support communication with UE115 using carrier aggregation or multi-carrier operation. UE115 may consist of multiple downlink component carriers and one or more uplink component carriers according to a carrier aggregation configuration. Carrier aggregation can be used with both frequency-division duplex (FDD) component carriers and time-division duplex (TDD) component carriers.

[0088]

[0098] As described herein, the communication of information (e.g., arbitrary information, signals, etc.) may be described in various ways using different terminology. Disclosure of one communication term includes disclosure of other communication terms. For example, a first network node may be described as configured to transmit information to a second network node. In this example, the disclosure that a first network node is configured to transmit information to a second network node includes the disclosure that a first network node is configured to provide, send, output, communicate, or transmit information to a second network node. Similarly, in this example, the disclosure that a first network node is configured to transmit information to a second network node includes the disclosure that a second network node is configured to receive, retrieve, or decode information provided, sent, output, communicated, or transmitted by a first network node.

[0089]

[0099] The signal waveform transmitted on a carrier can consist of multiple subcarriers (for example, using multicarrier modulation (MCM) techniques such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM). In systems employing MCM techniques, a resource element may include one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, where the symbol period and subcarrier spacing are inversely related. The number of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both). Therefore, the more resource elements the UE115 receives, and the higher the order of the modulation scheme, the higher the data rate for the UE115 can be. Wireless communication resources can refer to a combination of radio frequency spectral resources, temporal resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial layers can further increase the data rate or data integrity for communication with the UE115.

[0090]

[0100] The time interval for network entity 105 or UE115 is, for example, T s = 1 / (Δf max ·N f It can refer to a sampling period of ) seconds, which can be expressed in multiples of basic time units, where Δf max This can represent the maximum supported subcarrier interval, N f This may represent the maximum supported Discrete Fourier Transform (DFT) size. The time intervals of communication resources may be organized according to radio frames, each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0091]

[0101] Each frame may contain multiple sequentially numbered subframes or slots, each subframe or slot may have the same duration. In some examples, a frame may be divided into subframes (e.g., in the time domain), and each subframe may be further divided into several slots. Alternatively, each frame may contain a variable number of slots, the number of slots may depend on the subcarrier interval. Each slot may contain several symbol periods (e.g., depending on the length of the cyclic prefix prepared for each symbol period). In some wireless communication systems 100, a slot may be further divided into several minislots, each containing one or more symbols. Except for the cyclic prefix, each symbol period may contain one or more (e.g., N) symbols. f This may include the sampling period. The duration of the symbol period may depend on the subcarrier interval or frequency operating bandwidth.

[0092]

[0102] A subframe, slot, minislot, or symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communication system 100 and may be called a transmit time interval (TTI). In some examples, the TTI duration (e.g., the number of symbol periods in the TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of shortened TTIs (sTTIs)).

[0093]

[0103] Physical channels can be multiplexed on a carrier according to various techniques. Physical control channels and physical data channels can be multiplexed on a downlink carrier using, for example, one or more of the following techniques: time-division multiplexing (TDM), frequency-division multiplexing (FDM), or hybrid TDM-FDM. The control region of a physical control channel (e.g., a control resource set (CORESET)) may be defined by several symbolic periods and may extend across the carrier's system bandwidth or a subset of the system bandwidth. One or more control regions (e.g., a CORESET) may be configured for a set of UE115s. For example, one or more of the UE115s may monitor or search for control regions for control information according to one or more search space sets, each search space set may contain one or more control channel candidates in one or more cascaded aggregation levels. The aggregation levels of control channel candidates may refer to several control channel resources (e.g., control channel elements (CCEs)) related to encoded information for a control information format having a given payload size. The search space set may include a common search space set configured to send control information to multiple UE115s, and a UE-specific search space set for sending control information to a specific UE115.

[0094]

[0104] In some examples, base station 105 is mobile and therefore can provide communication coverage to a moving geographic coverage area 110. In some examples, different geographic coverage areas 110 associated with different technologies may overlap, but different geographic coverage areas 110 may be supported by the same base station 105. In other examples, overlapping geographic coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include heterogeneous networks, for example, in which different types of network entities 105 provide coverage to various geographic coverage areas 110 using the same or different radio access technologies.

[0095]

[0105] Some UE115s, such as MTC devices or IoT devices, may be low-cost or low-complexity devices that can provide automated communication between machines (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC may refer to data communication technology that enables devices to communicate with each other or with base stations 105 without human intervention. In some examples, M2M communication or MTC may include communication from devices that incorporate sensors or meters to measure or capture information, relay such information to a central server or application program that utilizes the information, or present the information to a human interacting with the application program. Some UE115s may be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security detection, physical access control, and billing for transaction-based businesses.

[0096]

[0106] The wireless communication system 100 may be configured to support ultra-high reliability communication, low latency communication, or various combinations thereof. For example, the wireless communication system 100 may be configured to support ultra-high reliability low latency communication (URLLC) or mission-critical communication. The UE 115 may be designed to support ultra-high reliability features, low latency features, or critical features (e.g., mission-critical features). Ultra-high reliability communication may include private or group communications and may be supported by one or more mission-critical services, such as mission-critical push-to-talk (MCPTT), mission-critical video (MCVideo), or mission-critical data (MCData). Support for mission-critical features may include service prioritization, and mission-critical services may be used for public safety or general commercial applications. The terms ultra-high reliability, low latency, mission-critical, and ultra-high reliability low latency may be used interchangeably herein.

[0097]

[0107] In some examples, a UE115 may also be able to communicate directly with other UE115s over a device-to-device (D2D) communication link 135 (for example, using peer-to-peer (P2P) or D2D protocols). One or more UE115s utilizing D2D communication may be within the geographical coverage area 110 of base station 105. Other UE115s in such a group may be outside the geographical coverage area 110 of base station 105, or otherwise unable to receive transmissions from base station 105. In some examples, a group of UE115s communicating via D2D communication may utilize a one-to-many (1:M) system where each UE115 transmits to any other UE115 in the group. In some examples, base station 105 facilitates the scheduling of resources for D2D communication. In other cases, D2D communication takes place between UE115s without the involvement of base station 105.

[0098]

[0108] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an advanced packet core (EPC) or 5G core (5GC) that includes at least one control plane entity that manages access and mobility (e.g., a Mobility Management Entity (MME), an Access and Mobility Management Function (AMF)) and at least one user plane entity that routes packets or interconnections to the external network (e.g., a Serving Gateway (S-GW), a Packet Data Network (PDN) Gateway (P-GW), or a User Plane Function (UPF)). The control plane entity may manage non-access layer (NAS) functions, such as mobility, authentication, and bearer management, for UE 115 serviced by network entity 105 associated with the core network 130. User IP packets may be forwarded through user plane entities that may provide IP address allocation and other functions. A user plane entity may be connected to an IP service 150 for one or more network operators. The IP service 150 may include access to the Internet, an intranet, an IP multimedia subsystem (IMS), or a packet-switched streaming service.

[0099]

[0109] Some of the network devices, such as the base station 105, may include sub-components such as access network entities 140, which may be an example of an access node controller (ANC). Each access network entity 140 may communicate with the UE 115 through one or more other access network transmitting entities 145, which may be called radio heads, smart radio heads, or transmit / receive points (TRPs). Each access network transmitting entity 145 may include one or more antenna panels. In some configurations, the various functions of each access network entity 140 or base station 105 may be distributed across various network devices (e.g., radio heads and ANCs) or integrated into a single network device (e.g., base station 105).

[0100]

[0110] The wireless communication system 100 may operate using one or more frequency bands, for example, in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). In some examples, the region from 300 MHz to 3 GHz is known as the ultra-high frequency (UHF) region or decimeter band, as the wavelengths range from approximately 1 decimeter to 1 meter in length. While UHF waves may be blocked or redirected by buildings and environmental features, the waves may penetrate structures well enough for a macrocell to serve a UE 115 located indoors. Transmitting UHF waves may be associated with smaller antennas and shorter distances (e.g., less than 100 kilometers) compared to transmissions using lower frequencies and longer waves in the high frequency (HF) or very high frequency (VHF) portion of the spectrum below 300 MHz.

[0101]

[0111] The electromagnetic spectrum is often subdivided into various classes, bands, channels, etc., based on frequency / wavelength. In 5G NR, two initial operating bands are identified as frequency range designations FR1 (410 MHz to 7.125 GHz) and FR2 (24.25 GHz to 52.6 GHz). It should be understood that although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the “sub-6 GHz” band in various documents and papers. A similar naming issue sometimes occurs with FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and papers, even though FR2 is different from the extremely high frequency (EHF) band (30 GHz to 300 GHz) which is identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0102]

[0112] The frequencies between FR1 and FR2 are often referred to as midband frequencies. Recent 5G NR research identifies these midband frequency operating bands as frequency range designation FR3 (7.125 GHz to 24.25 GHz). Frequency bands falling within FR3 may inherit FR1 or FR2 characteristics, and thus effectively extend the features of FR1 or FR2 to the midband frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as frequency range designations FR4a or FR4-1 (52.6 GHz to 71 GHz), FR4 (52.6 GHz to 114.25 GHz), and FR5 (114.25 GHz to 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0103]

[0113] With the above aspects in mind, unless otherwise specified, terms such as "sub-6GHz" can broadly refer to frequencies that may be below 6GHz, within FR1, or include midband frequencies, as used herein. Furthermore, unless otherwise specified, terms such as "millimeter wave" can broadly refer to frequencies that may include midband frequencies, within FR2, FR4, FR4-a or FR4-1, or FR5, or within the EHF band, as used herein.

[0114] The wireless communication system 100 may utilize both licensed and unlicensed radio frequency spectrum bands. For example, the wireless communication system 100 may employ Licensed Auxiliary Access (LAA), Unlicensed LTE (LTE-U) radio access technology, or NR technology in unlicensed bands such as the 5 GHz Industrial Scientific and Medical (ISM) band. When operating in unlicensed radio frequency spectrum bands, devices such as network entities 105 and UE 115 may employ carrier detection for collision detection and avoidance. In some examples, operation in unlicensed bands may be based on a carrier aggregation configuration, along with component carriers operating in licensed bands (e.g., LAA). Operation in unlicensed spectrums may include, among other examples, downlink transmission, uplink transmission, P2P transmission, or D2D transmission.

[0104]

[0115] Base station 105 or UE115 may be equipped with multiple antennas that can be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communication, or beamforming. The antennas of base station 105 or UE115 may be located within one or more antenna arrays or antenna panels that can support MIMO operation or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be collated in an antenna assembly, such as an antenna tower. In some examples, the antennas or antenna arrays associated with base station 105 may be located in a variety of geographical locations. Base station 105 may have an antenna array with several rows and columns of antenna ports that base station 105 can use to support beamforming of communication with UE115. Similarly, UE115 may have one or more antenna arrays that can support various MIMO or beamforming operations. As an addition or alternative, an antenna panel may support radio frequency beamforming for signals transmitted through antenna ports.

[0105]

[0116] Sometimes called spatial filtering, directional transmission, or directional reception, beamforming is a signal processing technique that can be used in a transmitting or receiving device (e.g., base station 105, UE115) to shape or steer an antenna beam (e.g., transmit beam, receive beam) along a spatial path between the transmitting and receiving devices. Beamforming can be achieved by combining signals communicated through the antenna elements of an antenna array such that several signals propagating in a particular orientation relative to the antenna array experience constructive interference and others experience destructive interference. Coordination of signals communicated through antenna elements may include the transmitting or receiving device applying amplitude offset, phase offset, or both to the signals carried through the antenna elements associated with the device. Coordination associated with each antenna element may be defined by a beamforming weight set associated with a particular orientation (e.g., relative to the antenna array of the transmitting or receiving device, or to some other orientation).

[0106]

[0117] The wireless communication system 100 may be a packet-based network operating according to a layered protocol stack. In the user plane, communication at the bearer or Packet Data Convergence Protocol (PDCP) layer may be IP-based. The Radio Link Control (RLC) layer may perform packet segmentation and reassembly for communication over logical channels. The MAC layer may perform priority processing and multiplexing of logical channels to transport channels. The MAC layer may also use error detection techniques, error correction techniques, or both to support retransmission at the MAC layer to improve link efficiency. In the control plane, the RRC protocol layer may establish, configure, and maintain RRC connections between the UE 115 and the base station 105 or core network 130, supporting radio bearers for user plane data. At the physical layer, transport channels may be mapped to physical channels.

[0107]

[0118] The techniques described herein may be implemented via additional or alternative wireless devices, including IAB nodes 104, distributed units (DUs) 165, central units (CUs) 160, and radio units (RUs) 170, as an addition to or alternative to what is performed between the UE 115 and the network entity 105. For example, in some implementations, the embodiments described herein may be implemented in the context of a disaggregated radio access network (RAN) architecture (e.g., an open RAN architecture). In a disaggregated architecture, the RAN may be split into three areas of function corresponding to the CU 160, DU 165, and RU 170. The split of function between the CU 160, DU 165, and RU 175 is flexible and therefore results in a number of different function substitutions depending on which functions (e.g., MAC functions, baseband functions, radio frequency functions, and any combination thereof) are performed in the CU 160, DU 165, and RU 175. For example, a functional split of the protocol stack may be employed between the DU165 and the RU170, such that the DU165 may support one or more layers of the protocol stack, and the RU170 may support one or more different layers of the protocol stack.

[0108]

[0119] Several wireless communication systems (e.g., wireless communication system 100), infrastructure, and spectral resources for NR access may further support wireless backhaul link capabilities as a complement to wireline backhaul connections, providing an IAB network architecture. One or more network entities 105 may include CU160, DU165, and RU170, and may be referred to as a donor network entity 105 or IAB donor. One or more DU165 (e.g., and / or RU170) associated with the donor base station 105 may be partially controlled by the CU160 associated with the donor base station 105. One or more donor network entities 105 (e.g., IAB donor) may communicate with one or more additional network entities 105 (e.g., IAB node 104) via supported access and backhaul links. The IAB node 104 may support mobile terminal (MT) functionality controlled and / or scheduled by the DU165 of the combined IAB donor. In addition, the IAB node 104 may include a DU 165 that supports communication links with the relay chain or additional entities in the configuration of the access network (e.g., downstream) (e.g., IAB node 104, UE 115, etc.). In such cases, one or more components of the disaggregated RAN architecture (e.g., one or more IAB nodes 104 or components of IAB node 104) may be configured to operate in accordance with the techniques described herein.

[0109]

[0120] In some examples, the wireless communication system 100 may include a core network 130 (e.g., a next-generation core network (NGC)), one or more IAB donors, IAB nodes 104, and UE 115, where the IAB nodes 104 may be partially controlled by each other and / or by the IAB donors. The IAB donors and IAB nodes 104 may be examples of a form of network entity 105. The IAB donors and one or more IAB nodes 104 may be configured as some kind of relay chain (e.g., or communicating accordingly).

[0110]

[0121] For example, an access network (AN) or RAN may refer to communication between an access node (e.g., an IAB donor), an IAB node 104, and one or more UEs 115. The IAB donor may facilitate the connection between the core network 130 and the AN (e.g., via a wireline or wireless connection to the core network 130). That is, the IAB donor may refer to a RAN node with a wireline or wireless connection to the core network 130. The IAB donor may include a CU 160 and at least one DU 165 (e.g., a RU 170), where the CU 160 may communicate with the core network 130 via an NG interface (e.g., some backhaul link). The CU 160 may host Layer 3 (L3) functions and signaling (e.g., RRC, Service Data Adaptive Protocol (SDAP), PDCP, etc.). At least one DU165 and / or RU170 may host lower layers, such as Layer 1 (L1) and Layer 2 (L2) (e.g., RLC, MAC, physical (PHY)) functions and signaling, and may be controlled at least partially by a CU160, respectively. A DU165 may support one or more different cells. The IAB donor and IAB node 104 may communicate via the F1 interface according to some protocol (e.g., the F1 AP protocol) that defines signaling messages. Furthermore, a CU160 may communicate with the core network via the NG interface (which may be an example of a backhaul link) and with other CU160s (e.g., CU160s associated with alternative IAB donors) via the Xn-C interface (which may be an example of a backhaul link).

[0111]

[0122] IAB node 104 may refer to a RAN node that provides IAB functionality (e.g., access for UE 115, wireless self-backhauling capability, etc.). IAB node 104 may include DU 165 and MT. DU 165 may act as a distributed scheduling node directed toward child nodes associated with IAB node 104, and MT may act as a scheduled node directed toward a parent node associated with IAB node 104. That is, an IAB donor may be called a parent node communicating with one or more child nodes (e.g., an IAB donor may relay transmissions for UEs through one or more other IAB nodes 104). Furthermore, depending on the relay chain or configuration of the AN, IAB node 104 may also be called a parent or child node to other IAB nodes 104. Therefore, an MT entity of IAB node 104 (e.g., MT) may provide a Uu interface to its child nodes for receiving signaling from the parent IAB node 104, and a DU interface (e.g., DU165) may provide a Uu interface to its parent node for signaling to the child IAB node 104 or UE115.

[0112]

[0123] For example, IAB node 104 may be referred to in relation to parent nodes associated with IAB nodes and child nodes associated with IAB donors. An IAB donor may include a CU 160 with a wireline (e.g., fiber optic) or wireless connection to the core network and may act as a parent node to IAB node 104. For example, the DU 165 of the IAB donor may relay transmissions to UE 115 through IAB node 104, or may directly signal transmissions to UE 115. The CU 160 of the IAB donor may signal the establishment of a communication link via the F1 interface to IAB node 104, and IAB node 104 may schedule transmissions (e.g., transmissions to UE 115 relayed from the IAB donor) via the DU 165. That is, data may be relayed to and from IAB node 104 via signaling on the NR Uu interface to MT of IAB node 104. Communication with IAB node 104 may be scheduled by DU165 of the IAB donor, and communication with IAB node 104 may be scheduled by DU165 of IAB node 104.

[0113]

[0124] For the techniques described herein applied in the context of a disaggregated RAN architecture, one or more components of the disaggregated RAN architecture (e.g., one or more IAB nodes 104 or components of IAB node 104) may be configured to support techniques for large round-trip times in random access channel procedures as described herein. For example, some operations described as being performed by UE 115 or base station 105 may, in addition or alternatively, be performed by components of the disaggregated RAN architecture (e.g., IAB nodes, DUs, CUs, etc.).

[0114]

[0125] In some examples, the wireless communication system 100 may support neural network modeling, and a communication manager 101 may be included in the device to support signal processing when implementing the neural network model. In some embodiments, the base station 105 may include a communication manager 101-a, and the UE 115 may include a communication manager 101-b. The communication manager 101-a may transmit one or more neural network models, an indication of a sequence of actions, and signals to the UE 115. The sequence of actions may inform the UE 115 of the order in which the signaling operations for each neural network model should be performed. In response, the communication manager 101-b may select a neural network model based on the received signal and perform the signaling operation according to the sequence of actions for the selected model. In some examples, the communication manager 101-b may transmit a signaling that constitutes a set of actions for the UE 115 before transmitting a sequence of actions, where the sequence of actions includes one or more of the set of actions. In another example, the communication manager 101-b may transmit a set of actions, a sequence of actions, and one or more neural network models together as a single package. In either case, the UE 115 may obtain information related to signal processing for one or more neural network models.

[0115]

[0126] Figure 2 shows an example of a wireless communication system 200 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. In some examples, the wireless communication system 200 may implement or be implemented by aspects of the wireless communication system 100. For example, the wireless communication system 200 may include a base station 105-a and a UE 115-a, which may be an example of the base station 105 and UE 115 described with reference to Figure 1. In some examples, the base station 105-a and the UE 115-a may be located in a coverage area 110-a and may communicate via a downlink communication link 205.

[0116]

[0127] In some examples, the wireless communication system 200 may support machine learning or neural network models. A neural network model could be an example of a program trained to recognize patterns, and the wireless communication system may utilize a neural network model to optimize the wireless communication process. For example, among other examples, the wireless communication system may utilize a neural network model to detect delays related to line-of-sight (LOS) signals.

[0117]

[0128] In some cases, a network such as base station 105-a may configure wireless devices with neural network models so that wireless devices such as UE115-a can implement the neural network models. For example, base station 105-a may encode one or more neural network models and use a format (e.g., Open Neural Network Switching (ONNX) format) to output (e.g., provide, transmit) them to UE115-a via downlink communication link 205. UE115-a may use a decoder to interpret one or more neural network models and implement one or more neural network models. In some examples, the network may determine which neural network models to provide to wireless devices based on the current operating scenario (e.g., number of antennas, operating SNR, operating bandwidth part, modulation, or radio frequency model). Each of the neural network models provided to wireless devices may be valid under some operating range. For example, each neural network model may be effective under a given SNR range, a given bandwidth range, a given channel power delay profile, a given signal scaling range, a given signal peak range, etc. A wireless device may implement a neural network model whose operating range includes the characteristics (e.g., signal SNR or signal bandwidth) of an acquired (e.g., received) signal.

[0118]

[0129] To implement a neural network model or to report the output of a neural network model, a wireless device may perform signal processing. Signal processing may include at least one of pre-processing or post-processing. The wireless device (e.g., UE115-a) may perform pre-processing to convert a received signal into a format suitable for input to a neural network model. Similarly, the wireless device (e.g., UE115-a) may perform post-processing to convert the output of a neural network model into a format that can be mapped to suit reporting, where the report may be sent to a higher layer (internal or external layer) in the wireless device or transmitted as a signal to another device (e.g., base station 105-a).

[0119]

[0130] Using other techniques, a wireless device (e.g., UE115-a) may be pre-configured with information on how signal processing should be performed for all neural network models designed by the network, which could include hundreds or thousands of neural network models designed for different operating scenarios. However, the network may provide the wireless device with a relatively small subset of these neural network models, and therefore, pre-configuring the wireless device with information on how signaling processing should be performed for all neural network models may not be feasible or efficient. In addition, neural network architectures can continue to evolve, which may be more suitable for various processing operations.

[0120]

[0131] As described herein, wireless devices may acquire or receive signaling that provides information for performing signal processing (e.g., pre-processing or post-processing) for a network-deployed neural network model. In some examples, the operations for signal processing (e.g., basic functions or non-trainable layers) may be common across different neural network models, but the sequence in which the operations are performed, as well as the input and output parameters, may differ. In one example, a UE115-a or base station 105-a may be pre-configured with a set of operations, where each operation in the set may include several inputs and outputs (optional for inputs and outputs).

[0121]

[0132] Some examples of operations that UE115-a can perform include channel feedback reporting (CFR) operations, zero-padding operations, IFFT operations (e.g., converting a signal from the frequency domain to the time domain), signal scaling operations (e.g., scaling the magnitude or amplitude of a signal), peak search operations (e.g., identifying the peak or maximum magnitude / amplitude of a signal), cyclic shift operations (e.g., bit rotation or shifting bits of a signal), truncation operations, concatenation operations, complex-to-real number operations, arbitrary linear algebra operations (e.g., singular value decomposition (SVD), QR decomposition, Cholesky decomposition, determinants, rank, condition numbers, or eigenvalues), or arbitrary matrix and vector equations. In some examples, matrix and vector operations can be obtained through mathematical or scientific computing libraries such as NumPy, SciPy, and LinAlg. That is, UE115-a can utilize arbitrary vector, matrix, or tensor operations or arbitrary linear algebra methods as part of signal processing (e.g., pre-processing or post-processing).

[0122]

[0133] While communicating with base station 105-a, UE115-a may acquire or receive one or more neural network models from the network. For example, UE115-a may receive a configuration message 210 from base station 105-a indicating a first neural network model. Upon receiving one or more neural network models, UE115-a may receive an execution sequence indication 215. The execution sequence indication 215 may indicate a sequence or order of operations to perform at least a subset of a set of operations for one or more signal processing procedures for each neural network model provided to UE115-a. For example, the execution sequence indication 215 for a LOS delay detection neural network model may indicate that operations for signal processing should be performed in the order of channel feedback reporting operation, zero padding operation, IFFT operation, signal scaling operation, peak search operation, cyclic shift operation, truncation operation, concatenation operation, and complex-to-real number operation. In addition, the execution sequence indication 215 may include indications of input and output parameters for each step of each neural network model (for example, for each operation in the sequence). For example, the execution sequence indication 215 may indicate that for a LOS delay detection neural network model, a left peak shift of a cyclic shift operation should be input and the peak index should be output. In some examples, the execution sequence indication 215 may be included in RRC signaling or MAC-CE. In some examples, signaling formats such as XML and JSON may be used to signal the execution sequence indication 215, or to indicate format support for pre-processing, post-processing, or machine learning models. Exemplary code for an execution sequence indication for a LOS delay detection neural network model is shown below in Table 1.

[0123] [Table 1-1]

[0124] [Table 1-2]

[0125] [Table 1-3]

[0126]

[0134] The wireless device may perform signal processing on the received signal based on the execution sequence indication 215. For example, UE115-a may acquire a signal 220 from base station 105-a and determine the characteristics of the signal 220 (e.g., signal SNR or signal bandwidth). Based on the determined signal characteristics, UE115-a may select a neural network model (e.g., a first neural network model) and perform preprocessing on the acquired signal 220 according to the sequence of operations shown in the execution sequence indication 215 of the selected neural network model. After the signal 220 has been preprocessed, UE115-a may implement the selected neural network model. After implementing the neural network model, UE115-a may, in some examples, perform postprocessing on the received signal 220 according to the sequence of operations shown in the execution sequence indication 215 of the selected neural network model and report the output of the neural network model to a higher layer or for transmission to base station 105-a.

[0127]

[0135] Alternatively, the network may augment the neural network model with information for performing signal processing for the neural network model. In such an example, the configuration message 210 may include the neural network model and the signal processing functions for the neural network model (e.g., a set of actions, a sequence for executing the set of actions, and input and output parameters for each action). The base station 105-a may utilize a format (e.g., ONNX format) to encode and output (e.g., provide, transmit) the neural network model and signal processing functions, and the UE 115-a may acquire (e.g., receive) and decode the neural network model and signaling processing functions according to the format. In such a case, the UE 115-a may not be pre-configured with a set of actions for signal processing and may not receive the execution sequence indication 215, but instead may receive a configuration message 210 for some neural network model and perform signal processing for the neural network model based on the configuration message 210. In some examples, the UE115-a may receive multiple configuration messages 210 to obtain information about the signal processing of multiple neural network models.

[0128]

[0136] In some examples, base station 105-a may receive signaling that indicates information related to signal processing for a neural network model. For example, base station 105-a may receive execution sequence indications from machine learning blocks (e.g., real-time and non-real-time radio access network (RAN) intelligent controllers) for one or more neural network models. The execution sequence indications may indicate the order in which a set of pre-configured operations should be performed at base station 105-a for signal processing of one or more neural network models. When base station 105-a receives a signal, it may perform signal processing on the signal based on the execution sequence indications.

[0129]

[0137] In another example, UE115-a may acquire or receive multiple neural network models, where each neural network model may be valid under different operating ranges. In such an example, the set of operations pre-configured in UE115-a may include one or more operations for determining one or more characteristics of the received signal. For example, UE115-a may be pre-configured with an operation for calculating the SNR. The execution sequence indication 215 may perform one or more operations as part of signal processing to determine one or more characteristics of the received signal and indicate that a neural network model should be selected based on the output of one or more operations. For example, the execution sequence indication 215 may specify that a first neural network model should be selected if the SNR of signal 220 is below a threshold, and a second neural network model should be selected if the SNR is above a threshold. One or more operations may be an example of a table or function that takes some input (e.g., the SNR of signal 220) and generates a model identifier (ID) as an output.

[0130]

[0138] In some examples, UE115-a may indicate its ability to support a set of pre-configured operations in UE115-a. For example, UE115-a may output or transmit a signal to base station 105-a indicating that it supports basic mathematics but not complex operations (e.g., singular value decomposition (SVD) or QR decomposition). In another example, UE115-a may indicate a threshold input dimension for one or more operations from the set of pre-configured operations in UE115-a. For example, UE115-a may output or transmit a signal to base station 105-a indicating that it supports 4×4SVD but not 8×8SVD or 16×8SVD. Furthermore, UE115-a may indicate a threshold runtime for one or more operations from the set of pre-configured operations in UE115-a. If UE115-a indicates that it cannot support one or more operations from the set of operations, base station 105-a may output or transmit an additional network model to UE115-a.

[0131]

[0139] Figure 3 shows an example of a flowchart 300 that supports a technique for illustrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. In some examples, the flowchart 300 may implement embodiments of wireless communication system 100 and wireless communication system 200. For example, the flowchart 300 may be implemented by UE 115 or base station 105 as described with reference to Figures 1 and 2.

[0132]

[0140] In some examples, a wireless device may acquire / receive signaling that, for each neural network model provided to the wireless device, is pre-configured with a set of actions, and indicates a sequence of actions for input processing (e.g., sequence 330 of actions) or a sequence of actions for output processing (e.g., sequence 335 of actions). Furthermore, the signaling may indicate input and output parameters for each action within the sequence of actions.

[0133]

[0141] In some examples, the wireless device may acquire or receive a signal at 305 via one or more antennas 301-a (for example, from a base station). In some examples, the wireless device may determine the characteristics of the signal and select a neural network model based on the characteristics of the signal. For example, the wireless device may determine that the signal is associated with an SNR above a threshold and select a first neural network. Alternatively, the wireless device may determine that the signal is associated with an SNR below a threshold and select a second neural network. Once the wireless device has identified which neural network model to implement, it may perform input processing on the received signal at 310. In some examples, the wireless device may perform input processing according to a sequence of operations 330. In one example, the wireless device may implement a neural network model for LOS delay detection. In such a case, the sequence of operations 330 may be as follows: CFR operation, zero-padding operation, IFFT operation, signal scaling operation, peak search operation, cyclic shift operation, truncation operation, concatenation operation, complex-to-real operation, each operation may have specified output and input parameters. The input processing can convert the received signal into a format compatible with the selected neural network model, and therefore the wireless device can implement the neural network model selected in 315.

[0134]

[0142] At 320, the wireless device may perform output processing. In some examples, the wireless device may perform output processing according to the sequence of operations 335. In one example, the wireless device may implement a neural network model for LOS delay detection. In such an example, the sequence of operations 335 may indicate that the output should be shifted and scaled only as a result of the cyclic shift operation performed at 310. In some examples, the sequences of operations 335 and 330 may include different operations or one or more of the same operations. After performing output processing, the wireless device may map the output of the neural network model to one or more reports at 325, and the wireless device may send the reports to the upper layer 340 or output / transmit the reports to the network or base station via one or more antennas 301-b.

[0135]

[0143] Figure 4 shows an example of a machine learning process 400 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. The machine learning process 400 may be implemented in a wireless device, such as the UE 115 described with reference to Figures 1 to 3. The machine learning process 400 may include a machine learning algorithm 410. In some examples, the wireless device may receive a neural network model from a base station 105 and implement one or more machine learning algorithms 410 as part of the neural network model to optimize the communication process.

[0136]

[0144] As shown in the figure, the machine learning algorithm 410 could be an example of a neural network, such as a feedforward (FF) or deep feedforward (DFF) neural network, a recurrent neural network (RNN), a long-term / short-term memory (LSTM) neural network, or any other type of neural network. However, any other machine learning algorithm may be supported by UE115. For example, the machine learning algorithm 410 could implement a nearest neighbor algorithm, a linear regression algorithm, a Naive Bayes algorithm, a random forest algorithm, or any other machine learning algorithm. Furthermore, the machine learning process 400 may involve supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or any combination thereof. Machine learning may be performed before the deployment of UE115, while UE115 is deployed, during periods of low usage of UE115 while UE115 is deployed, or any combination thereof.

[0137]

[0145] The machine learning algorithm 410 may include an input layer 415, one or more hidden layers 420, and an output layer 425. In a neural network fully connected to one hidden layer 420, each hidden layer node 435 may receive values ​​as input from each input layer node 430, where each input is weighted. These neural network weights may be based on a cost function that is modified during training of the machine learning algorithm 410. Similarly, each output layer node 440 may receive values ​​as input from each hidden layer node 435, where the inputs are weighted. If post-deployment training (e.g., online training) is supported in UE115, UE115 may allocate memory to store errors and / or gradients for inverse matrix multiplication. These errors and / or gradients may support updating the machine learning algorithm 410 based on the outputted feedback. Training the machine learning algorithm 410 can support the calculation of weights for mapping input patterns to desired output results (for example, connecting input layer nodes 430 to hidden layer nodes 435, and hidden layer nodes 435 to output layer nodes 440). This training may result in a UE-specific machine learning algorithm 410 based on the historical application data and data transfers of a particular UE115.

[0138]

[0146] UE115 can send the input value 405 to the machine learning algorithm 410 for processing. In some examples, UE115 may preprocess the input value 405 according to a sequence of operations received from the base station so that the input value 405 is in a format compatible with the machine learning algorithm 410. The input value 405 can be converted into a set of k input layer nodes 430 in the input layer 415. In some cases, different measurements may be input to different input layer nodes 430 in the input layer 415. If the number of input layer nodes 430 exceeds the number of inputs corresponding to the input value 405, some input layer nodes 430 may be assigned a default value (e.g., a value of 0). As shown in the figure, the input layer 415 may contain three input layer nodes 430-a, 430-b, and 430-c. However, it should be understood that the input layer 415 may contain any number of input layer nodes 430 (e.g., 20 input nodes).

[0139]

[0147] The machine learning algorithm 410 can convert the input layer 415 into a hidden layer 420 based on the number of input-hidden weights between the k input layer nodes 430 and the n hidden layer nodes 435. The machine learning algorithm 410 may include any number of hidden layers 420 as intermediate steps between the input layer 415 and the output layer 425. In addition, each hidden layer 420 may contain any number of nodes. For example, as shown in the figure, the hidden layer 420 may contain four hidden layer nodes 435-a, 435-b, 435-c, and 435-d. However, it should be understood that the hidden layer 420 may contain any number of hidden layer nodes 435 (for example, 10 input nodes). In a fully connected neural network, each node in a layer may be based on each node in the previous layer. For example, the value of hidden layer node 435-a can be obtained based on the values ​​of input layer nodes 430-a, 430-b, and 430-c (for example, with different weights applied to each node value).

[0140]

[0148] The machine learning algorithm 410 can determine a value for an output layer node 440 of an output layer 425 that follows one or more hidden layers 420. For example, the machine learning algorithm 410 can convert a hidden layer 420 to an output layer 425 based on the number of hidden-output weights between n hidden layer nodes 435 and m output layer nodes 440. In some cases, n=m. Each output layer node 440 may correspond to a different output value 445 of the machine learning algorithm 410. As shown in the figure, the machine learning algorithm 410 may include three output layer nodes 440-a, 440-b, and 440-c that support three different thresholds. However, it should be understood that the output layer 425 may include any number of output layer nodes 440. In some examples, the UE 115 may perform post-processing on the output value 445 according to a sequence of operations received from the base station, such that the input value 405 can be in a format compatible with reporting the output value 445 to the upper layer or to the base station 105.

[0141]

[0149] Figure 5 shows an example of a process flow 500 that supports a technique for demonstrating a signal processing procedure for a network-deployed neural network model, according to one or more embodiments of the present disclosure. In some examples, the process flow 500 may implement, or be implemented by, an embodiment of a wireless communication system 100, a wireless communication system 200, and a flowchart 300. The process flow 500 may involve UE115-b receiving a signaling indicating information relating to signaling processing for one or more neural network models. Alternative examples of the following may be implemented, where some steps are performed in a different order than described, or not performed at all. In some cases, the steps may include additional features not described below, or further steps may be added.

[0142]

[0150] In 505, UE115-b may potentially output or transmit capability messages to base station 105-b. Capability messages may indicate UE115-b's ability to support one or more operations for signaling processing. In some examples, capability messages may include indications of threshold input dimensions for one or more operations for signaling processing, or threshold runtimes for each of one or more operations for signaling processing.

[0143]

[0151] In 510, UE115-b may obtain or receive a configuration message from base station 105-b. The configuration message may include an indication of one or more neural network models. In some examples, base station 105-b may determine one or more neural network models to output / transmit to UE115-b based on its current operating state (e.g., number of antennas, operating SNR, operating bandwidth part, modulation, or radio frequency model) or based on a capability message received in 505.

[0144]

[0152] At 515, UE115-b may obtain or receive an indication from base station 105-b of a sequence of operations for each of the one or more neural network models provided to UE115-b at 510. In one example, UE115-b may consist of a set of operations related to signal processing (e.g., basic functions or non-trainable layers), and the sequence of operations may specify the order in which at least a subset of the set of operations for signal processing (pre-processing or post-processing) should be performed. The sequence of operations may also include input and output parameters for each operation in the subset. In another example, the set of operations and the sequence of operations for the neural networks of one or more neural network models may be included in a configuration message received at 510. In such a case, UE115-b may not receive an indication of the sequence of operations at 515.

[0145]

[0153] In 520, UE115-b may acquire or receive signals from base station 105-b. In some examples, UE115-b may determine the characteristics of the signal (e.g., SNR, bandwidth, or signal scale) and select a neural network model to implement based on the signal characteristics. In some cases, UE115-b may be pre-configured with a table or function showing the relationship between the neural network model and the operating range (e.g., SNR range, bandwidth range, or signal scale range), and UE115-b may select a neural network model based on the table or function as part of signal processing (e.g., preprocessing).

[0146]

[0154] At 525, UE115-b may perform input processing on the signal received at 520. In some examples, UE115-b may perform input processing according to a sequence of operations shown at 515 or a sequence of operations contained in a configuration message received at 510.

[0147]

[0155] In 530, the UE115-b can be configured to apply a neural network model.

[0148]

[0156] In 535, UE115-b may perform output processing on the neural network model output. In some examples, UE115-b may perform output processing according to a sequence of actions shown in 515 or a sequence of actions contained in a configuration message received in 510. After performing output processing, UE115-b may map the output to one or more reports and potentially output or transmit one or more reports to base station 105-b.

[0149]

[0157] Figure 6 shows a block diagram 600 of device 605 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Device 605 may be an example of an embodiment of UE115 described herein. Device 605 may include a receiver 610, a transmitter 615, and a communications manager 620. Device 605 may also include a processor. Each of these components may communicate with one another (for example, via one or more buses).

[0150]

[0158] The receiver 610 may provide means for acquiring (e.g., receiving) information such as packets, user data, control information, or any combination thereof, related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models). The information may be passed to other components of device 605. The receiver 610 may utilize a single antenna or a set of multiple antennas.

[0151]

[0159] Transmitter 615 may provide means for outputting (e.g., providing, transmitting) signals generated by other components of device 605. For example, transmitter 615 may transmit information such as packets related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models), user data, control information, or any combination thereof. In some examples, transmitter 615 may be collated with receiver 610 in a transceiver module. Transmitter 615 may utilize a single antenna or a set of multiple antennas.

[0152]

[0160] The communication manager 620, receiver 610, transmitter 615, or various combinations thereof or various components thereof may be examples of means for implementing various aspects of the techniques for demonstrating signal processing procedures for the network-deployed neural network models described herein. For example, the communication manager 620, receiver 610, transmitter 615, or various combinations thereof or components thereof may support methods for implementing one or more of the functions described herein.

[0153]

[0161] In some examples, the communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in hardware (for example, in communications management circuits). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, which are configured as means for performing the functions described herein or otherwise support such means. In some examples, a processor and memory coupled to the processor may be configured to perform one or more of the functions described herein (for example, by the processor executing instructions stored in the memory).

[0154]

[0162] As an addition or alternative, in some examples, the communications manager 620, receiver 610, transmitter 615, or various combinations or components thereof may be implemented in code executed by a processor (for example, as communications management software or firmware). When implemented in code executed by a processor, the functions of the communications manager 620, receiver 610, transmitter 615, or various combinations or components thereof may be implemented by a general-purpose processor, DSP, central processing unit (CPU), ASIC, FPGA, or any combination thereof or other programmable logic device (for example, configured as a means for performing the functions described in this disclosure or otherwise supporting such means).

[0155]

[0163] In some examples, the communications manager 620 may be configured to use or otherwise cooperate with the receiver 610, the transmitter 615, or both to perform various operations (e.g., acquire / receive, monitor, output / transmit). For example, the communications manager 620 may be incorporated in combination with the receiver 610, the transmitter 615, or both to receive information from the receiver 610, send information to the transmitter 615, or receive information, transmit information, or perform various other operations as described herein.

[0156]

[0164] The communication manager 620 may support wireless communication in a device in a wireless network in accordance with the examples disclosed herein. For example, the communication manager 620 may be configured or otherwise supported as a means for receiving a configuration message for a device, the configuration message indicating one or more neural network models for the device. The communication manager 620 may be configured or otherwise supported as a means for receiving an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The communication manager 620 may be configured or otherwise supported as a means for performing a signal processing procedure for at least one neural network model using signals received in the device in accordance with the sequence of operations.

[0157]

[0165] By including or configuring a communications manager 620 as described herein, device 605 (for example, a processor controlling a receiver 610, a transmitter 615, a communications manager 620, or a combination thereof, or otherwise coupled thereto) can support techniques for reduced processing and reduced power consumption. By receiving information related to signal processing, device 605 may be able to implement a neural network model. By implementing a neural network model, device 605 may optimize the communication process, thereby reducing power consumption in device 605.

[0158]

[0166] Figure 7 shows a block diagram 700 of device 705 supporting a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Device 705 may be an example of an embodiment of device 605 or UE115 as described herein. Device 705 may include a receiver 710, a transmitter 715, and a communications manager 720. Device 705 may also include a processor. Each of these components may communicate with one another (for example, via one or more buses).

[0159]

[0167] The receiver 710 may provide means for acquiring (e.g., receiving) information such as packets, user data, control information, or any combination thereof, related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models). The information may be passed to other components of device 705. The receiver 710 may utilize a single antenna or a set of multiple antennas.

[0160]

[0168] The transmitter 715 may provide means for outputting (e.g., transmitting) signals generated by other components of device 705. For example, the transmitter 715 may transmit information such as packets related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models), user data, control information, or any combination thereof. In some examples, the transmitter 715 may be collated with the receiver 710 in the transceiver module. The transmitter 715 may utilize a single antenna or a set of multiple antennas.

[0161]

[0169] Device 705, or various components thereof, may be examples of means for implementing various embodiments of techniques for demonstrating signal processing procedures for network-deployed neural network models as described herein. For example, the communications manager 720 may include the UE model manager 725, the UE signal processing manager 730, the execution component 735, or any combination thereof. The communications manager 720 may be an example of an embodiment of the communications manager 620 as described herein. In some examples, the communications manager 720, or various components thereof, may be configured to use or otherwise cooperate with the receiver 710, the transmitter 715, or both to perform various operations (e.g., acquire / receive, monitor, output / transmit). For example, the communications manager 720 may be incorporated in combination with the receiver 710, the transmitter 715, or both to receive information from the receiver 710, send information to the transmitter 715, or receive information, transmit information, or perform various other operations as described herein.

[0162]

[0170] The communication manager 720 may support wireless communication in a device in a wireless network in accordance with the examples disclosed herein. The UE model manager 725 may be configured as a means for receiving configuration messages for a device, or otherwise support such means, the configuration messages indicating one or more neural network models for the device. The UE signal processing manager 730 may be configured as a means for receiving indications of sequences of operations for signal processing procedures for at least one of the one or more neural network models, the signal processing procedures including one of input preprocessing procedures related to at least one neural network model, or output preprocessing procedures related to at least one neural network model. The execution component 735 may be configured as a means for performing signal processing procedures for at least one neural network model using signals received in the device in accordance with sequences of operations, or otherwise support such means.

[0163]

[0171] Figure 8 shows a block diagram 800 of a communications manager 820 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Communications manager 820 may be an example of an embodiment of communications manager 620, communications manager 720, or both, as described herein. Communications manager 820, or various components thereof, may be an example of means for implementing various embodiments of the technique for demonstrating signal processing procedures for a network-deployed neural network model, as described herein. For example, communications manager 820 may include a UE model manager 825, a UE signal processing manager 830, an execution component 835, a UE capability manager 840, or any combination thereof. Each of these components may communicate with one another directly or indirectly (for example, via one or more buses).

[0164]

[0172] The communication manager 820 may support wireless communication in a device in a wireless network in accordance with the examples disclosed herein. The UE model manager 825 may be configured as a means for receiving configuration messages for a device, or otherwise support such means, the configuration messages indicating one or more neural network models for the device. The UE signal processing manager 830 may be configured as a means for receiving indications of sequences of operations for signal processing procedures for at least one of the one or more neural network models, the signal processing procedures including one of input preprocessing procedures related to at least one neural network model, or output preprocessing procedures related to at least one neural network model. The execution component 835 may be configured as a means for performing signal processing procedures for at least one neural network model using signals received in the device in accordance with sequences of operations, or otherwise support such means.

[0165]

[0173] In some examples, the UE signal processing manager 830 may be configured as a means for receiving signaling that constitutes a device with a set of actions including one or more actions from a sequence of actions for at least one neural network model, or may otherwise support such means. In some examples, the device may include a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0166]

[0174] In some examples, the UE signal processing manager 830 may be configured or otherwise support means for receiving an indication of a sequence of actions for a signal processing procedure in a configuration message, where the configuration message includes a set of actions that include all of the actions of a sequence of actions for at least one neural network model.

[0167]

[0175] In some examples, the UE signal processing manager 830 may be configured as a means for receiving a second configuration message for the device, or may otherwise support such means, the second configuration message indicating a set of operations including at least one neural network model, an indication of a sequence of operations, and all operations from a sequence of operations for at least one neural network model.

[0168]

[0176] In some examples, the UE signal processing manager 830 may be configured as a means for receiving a set of input parameters, a set of output parameters, or both for one or more operations in a sequence of operations for at least one neural network model, or it may support such means in other ways.

[0169]

[0177] In some examples, the UE model manager 825 may be configured as a means for receiving indications of mappings between one or more neural network models and sets of operating states, where signals received in the device according to a sequence of operations based on the mappings between one or more neural network models and sets of operating states are used to perform a signal processing procedure for at least one neural network model.

[0170]

[0178] In some examples, the set of operating states includes signal-to-noise ratio range, bandwidth range, signal scaling range, channel delay profile, signal peak range, or any combination thereof, related to the signal received in the device.

[0171]

[0179] In some examples, the UE capability manager 840 may be configured or otherwise support such means for sending messages indicating the device's ability to support one or more actions for one or more signal processing procedures, where receiving an indication of a sequence of actions for at least one neural network model is based on the device's capability. In some examples, the sequence of actions includes one or more actions supported by the device.

[0172]

[0180] In some examples, messages indicating a device's ability to support one or more operations for signal processing include indications of threshold input dimensions for each of the one or more operations for signal processing, or threshold runtimes for each of the one or more operations for signal processing.

[0173]

[0181] In some examples, the UE signaling manager 830 may be configured as a means for receiving RRC signaling or MAC-CE, which includes indications of the sequence of operations, or may otherwise support such means.

[0174]

[0182] In some examples, the UE signal processing manager 830 may be configured as a means for receiving indications of one or more data formats relating to one or more actions in a sequence of actions, the one or more data formats including XML data format, JSON data format, or any combination thereof.

[0175]

[0183] Figure 9 shows a diagram of a system 900 including a device 905 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. Device 905 may be an example of, or include, a component of, device 605, device 705, or UE 115 as described herein. Device 905 may wirelessly communicate with one or more network entities 105, UE 115, or any combination thereof. Device 905 may include components for bidirectional voice and data communication, including components for transmitting and receiving communications, such as a communications manager 920, an input / output (I / O) controller 910, a transceiver 915, an antenna 925, a memory 930, a code 935, and a processor 940. These components may communicate electronically or be coupled (e.g., operably, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 945).

[0176]

[0184] The I / O controller 910 can manage input and output signals for device 905. The I / O controller 910 can also manage peripherals not integrated into device 905. In some cases, the I / O controller 910 may represent physical connections or ports to external peripherals. In some cases, the I / O controller 910 may utilize an operating system, such as iOS®, ANDROID®, MS-DOS®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. Additionally or alternatively, the I / O controller 910 may represent or interact with a modem, keyboard, mouse, touchscreen, or similar device. In some cases, the I / O controller 910 may be implemented as part of a processor, such as processor 940. In some cases, a user may interact with device 905 via the I / O controller 910 or through hardware components controlled by the I / O controller 910.

[0177]

[0185] In some cases, device 905 may include a single antenna 925. However, in some other cases, device 905 may have two or more antennas 925 that may be capable of simultaneously transmitting or receiving multiple wireless transmissions. Transceiver 915 may communicate bidirectionally via one or more antennas 925, a wired link, or a wireless link, as described herein. For example, transceiver 915 may represent a wireless transceiver and communicate bidirectionally with another wireless transceiver. Transceiver 915 may also include a modem for modulating packets and providing the modulated packets to one or more antennas 925 for transmission, and for demodulating packets received from one or more antennas 925. Transceiver 915, or transceiver 915 and one or more antennas 925, may be examples of transmitters 615, transmitters 715, receivers 610, receivers 710, or any combination thereof or their components, as described herein.

[0178]

[0186] Memory 930 may include random access memory (RAM) and read-only memory (ROM). Memory 930 may store computer-readable, computer-executable code 935, which, when executed by processor 940, contains instructions that cause device 905 to perform various functions described herein. Code 935 may be stored in a non-temporary computer-readable medium, such as system memory or another type of memory. In some cases, code 935 may not be directly executable by processor 940, but (for example, when compiled and executed) can cause the computer to perform the functions described herein. In some cases, memory 930 may include a basic I / O system (BIOS) that can control basic hardware or software operations, in particular, such as interaction with peripheral components or devices.

[0179]

[0187] The processor 940 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, the processor 940 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 940. The processor 940 may be configured to execute computer-readable instructions stored in memory (e.g., memory 930) to cause device 905 to perform various functions (e.g., functions or tasks supporting techniques for demonstrating signal processing procedures for network-deployed neural network models). For example, device 905 or components of device 905 may include the processor 940 and memory 930 coupled to the processor 940, and the processor 940 and memory 930 are configured to perform the various functions described herein.

[0180]

[0188] The communication manager 920 may support wireless communication in a device in a wireless network in accordance with the examples disclosed herein. For example, the communication manager 920 may be configured or otherwise supported as a means for receiving a configuration message for a device, the configuration message indicating one or more neural network models for the device. The communication manager 920 may be configured or otherwise supported as a means for receiving an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The communication manager 920 may be configured or otherwise supported as a means for performing a signal processing procedure for at least one neural network model using signals received in the device in accordance with the sequence of operations.

[0181]

[0189] By including or configuring a communications manager 920 as described herein, device 905 may support techniques for an improved user experience relating to reduced processing and reduced power consumption. The methods described herein may support the deployment of new neural network models that may perform better than existing neural network models.

[0182]

[0190] In some examples, the communications manager 920 may be configured to use or otherwise cooperate with the transceiver 915, one or more antennas 925, or any combination thereof to perform various operations (e.g., receiving, monitoring, transmitting). Although the communications manager 920 is shown as a separate component, in some examples, one or more functions described with reference to the communications manager 920 may be supported or performed by the processor 940, memory 930, code 935, or any combination thereof. For example, code 935 may include instructions executable by the processor 940 to cause the device 905 to perform various aspects of techniques for demonstrating signal processing procedures for the network-deployed neural network model described herein, or the processor 940 and memory 930 may be configured to perform or support such operations in other ways.

[0183]

[0191] Figure 10 shows a block diagram 1000 of a device 1005 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Device 1005 may be an example of an embodiment of a base station 105 described herein. Device 1005 may include a receiver 1010, a transmitter 1015, and a communications manager 1020. Device 1005 may also include a processor. Each of these components may communicate with one another (for example, via one or more buses).

[0184]

[0192] The receiver 1010 may provide means for receiving information such as packets, user data, control information, or any combination thereof, related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models). The information may be passed to other components of device 1005. The receiver 1010 may utilize a single antenna or a set of multiple antennas.

[0185]

[0193] The transmitter 1015 may provide means for transmitting signals generated by other components of device 1005. For example, the transmitter 1015 may transmit information such as packets related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models), user data, control information, or any combination thereof. In some examples, the transmitter 1015 may be collated with the receiver 1010 in the transceiver module. The transmitter 1015 may utilize a single antenna or a set of multiple antennas.

[0186]

[0194] The communication manager 1020, receiver 1010, transmitter 1015, or various combinations thereof or various components thereof may be examples of means for implementing various aspects of the techniques for demonstrating signal processing procedures for the network-deployed neural network model described herein. For example, the communication manager 1020, receiver 1010, transmitter 1015, or various combinations thereof or components thereof may support methods for implementing one or more of the functions described herein.

[0187]

[0195] In some examples, the communications manager 1020, the receiver 1010, the transmitter 1015, or various combinations or components thereof may be implemented in hardware (for example, in communications management circuits). The hardware may include processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination thereof, which are configured as means for performing the functions described herein or otherwise support such means. In some examples, a processor and memory coupled to the processor may be configured to perform one or more of the functions described herein (for example, by the processor executing instructions stored in the memory).

[0188]

[0196] As an addition or alternative, in some examples, the communications manager 1020, receiver 1010, transmitter 1015, or various combinations or components thereof may be implemented in code executed by a processor (for example, as communications management software or firmware). When implemented in code executed by a processor, the functions of the communications manager 1020, receiver 1010, transmitter 1015, or various combinations or components thereof may be implemented by a general-purpose processor, DSP, CPU, ASIC, FPGA, or any combination thereof or other programmable logic device (for example, configured as a means for performing the functions described in this disclosure or otherwise supporting such means).

[0189]

[0197] In some examples, the communications manager 1020 may be configured to use or otherwise cooperate with the receiver 1010, the transmitter 1015, or both to perform various operations (e.g., receiving, monitoring, transmitting). For example, the communications manager 1020 may be incorporated in combination with the receiver 1010, the transmitter 1015, or both to receive information from the receiver 1010, send information to the transmitter 1015, or receive information, transmit information, or perform various other operations as described herein.

[0190]

[0198] The communication manager 1020 may support wireless communication at a base station as illustrated herein. For example, the communication manager 1020 may be configured or otherwise support means for sending a configuration message to a device, the configuration message indicating one or more neural network models for the device. The communication manager 1020 may be configured or otherwise support means for sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The communication manager 1020 may be configured or otherwise support means for sending a signal to a device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0191]

[0199] By including or configuring the communications manager 1020 as described herein, the device 1005 (for example, a processor controlling the receiver 1010, transmitter 1015, communications manager 1020, or a combination thereof, or otherwise coupled thereto) can support techniques for reduced processing and reduced power consumption.

[0192]

[0200] Figure 11 shows a block diagram 1100 of device 1105 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Device 1105 may be an example of an embodiment of device 1005 or base station 105 described herein. Device 1105 may include a receiver 1110, a transmitter 1115, and a communications manager 1120. Device 1105 may also include a processor. Each of these components may communicate with one another (for example, via one or more buses).

[0193]

[0201] The receiver 1110 may provide means for receiving information such as packets, user data, control information, or any combination thereof, related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models). The information may be passed to other components of device 1105. The receiver 1110 may utilize a single antenna or a set of multiple antennas.

[0194]

[0202] The transmitter 1115 may provide means for transmitting signals generated by other components of device 1105. For example, the transmitter 1115 may transmit information such as packets related to various information channels (e.g., control channels, data channels, information channels related to techniques for demonstrating signal processing procedures for network-deployed neural network models), user data, control information, or any combination thereof. In some examples, the transmitter 1115 may be collated with the receiver 1110 in the transceiver module. The transmitter 1115 may utilize a single antenna or a set of multiple antennas.

[0195]

[0203] Device 1105, or various components thereof, may be examples of means for carrying out various embodiments of techniques for demonstrating signal processing procedures for network-deployed neural network models as described herein. For example, the communications manager 1120 may include the model manager 1125, the signal processing manager 1130, the signal transmitter 1135, or any combination thereof. The communications manager 1120 may be an example of an embodiment of the communications manager 1020 as described herein. In some examples, the communications manager 1120, or various components thereof, may be configured to use or otherwise cooperate with the receiver 1110, the transmitter 1115, or both, to carry out various operations (e.g., receiving, monitoring, transmitting). For example, the communications manager 1120 may be incorporated in combination with the receiver 1110, the transmitter 1115, or both, to receive information from the receiver 1110, send information to the transmitter 1115, or receive information, transmit information, or carry out various other operations as described herein.

[0196]

[0204] The communication manager 1120 may support wireless communication at a base station as illustrated herein. The model manager 1125 may be configured or otherwise support the means for sending a configuration message to a device, the configuration message indicating one or more neural network models for the device. The signal processing manager 1130 may be configured or otherwise support the means for sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The signal transmitter 1135 may be configured or otherwise support the means for sending a signal to a device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0197]

[0205] Figure 12 shows a block diagram 1200 of a communications manager 1220 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. The communications manager 1220 may be an example of an embodiment of communications manager 1020, communications manager 1120, or both, as described herein. The communications manager 1220, or various components thereof, may be an example of means for implementing various embodiments of the technique for demonstrating signal processing procedures for a network-deployed neural network model, as described herein. For example, the communications manager 1220 may include a model manager 1225, a signal processing manager 1230, a signal transmitter 1235, a capability manager 1240, or any combination thereof. Each of these components may communicate with one another directly or indirectly (for example, via one or more buses).

[0198]

[0206] The communication manager 1220 may support wireless communication at a base station as illustrated herein. The model manager 1225 may be configured or otherwise support the means for sending a configuration message to a device, the configuration message indicating one or more neural network models for the device. The signal processing manager 1230 may be configured or otherwise support the means for sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The signal transmitter 1235 may be configured or otherwise support the means for sending a signal to a device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0199]

[0207] In some examples, the signal processing manager 1230 may be configured as a means for transmitting signaling that constitutes a device with a set of actions including one or more actions from a sequence of actions for at least one neural network model, or may otherwise support such means. In some examples, the device may include a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0208] In some examples, the signal processing manager 1230 may be configured as a means for receiving a second sequence of operations for a second signaling procedure performed at the base station, or may otherwise support such means.

[0200]

[0209] In some examples, the signal processing manager 1230 may be configured or otherwise support means for sending an indication of a sequence of actions for a signal processing procedure in a configuration message, where the configuration message includes a set of actions that include all of the actions of a sequence of actions for at least one neural network model.

[0201]

[0210] In some examples, the signal processing manager 1230 may be configured as a means for sending a second configuration message to the device, or may otherwise support such means, the second configuration message indicating a set of operations including at least one neural network model, an indication of a sequence of operations, and all operations from a sequence of operations for at least one neural network model.

[0202]

[0211] In some examples, the signal processing manager 1230 may be configured as a means for transmitting a set of input parameters, a set of output parameters, or both for one or more operations in a sequence of operations for at least one neural network model, or it may support such means in other ways.

[0203]

[0212] In some examples, the model manager 1225 may be configured as a means for transmitting indications of mappings between one or more neural network models and sets of operational states, or may otherwise support such means.

[0204]

[0213] In some examples, the set of operating states may include signal-to-noise ratio range, bandwidth range, signal scaling range, channel delay profile, signal peak range, or any combination thereof, related to the signal sent to the device.

[0205]

[0214] In some examples, the capability manager 1240 may be configured as a means for receiving messages indicating the device's capability to support one or more actions for one or more signal processing procedures, where receiving an indication of a sequence of actions for at least one neural network model is based on the device's capability.

[0206]

[0215] In some examples, the sequence of actions includes one or more actions supported by the device.

[0207]

[0216] In some examples, messages indicating a device's ability to support one or more operations for signal processing include indications of threshold input dimensions for each of the one or more operations for signal processing, or threshold runtimes for each of the one or more operations for signal processing.

[0208]

[0217] In some examples, the signal processing manager 1230 may be configured as a means for transmitting RRC signaling (or MAC-CE) including indication of a sequence of operations, or may otherwise support such means.

[0209]

[0218] In some examples, the signal processing manager 1230 may be configured as a means for transmitting indications of one or more data formats relating to one or more operations in a sequence of operations, or otherwise supporting such means, where one or more data formats include XML data format, JSON data format, or any combination thereof.

[0210]

[0219] Figure 13 shows a diagram of a system 1300 including a device 1305 that supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. Device 1305 may be an example of, or include, a component of, device 1005, device 1105, or base station 105 as described herein. Device 1305 may wirelessly communicate with one or more network entities 105, UE 115, or any combination thereof. Device 1305 may include components for bidirectional voice and data communication, including components for transmitting and receiving communications, such as a communications manager 1320, a network communications manager 1310, a transceiver 1315, an antenna 1325, a memory 1330, a code 1335, a processor 1340, and an inter-station communications manager 1345. These components may communicate electronically or be coupled (e.g., operably, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1350).

[0211]

[0220] The network communication manager 1310 may manage communication with the core network 130 (for example, via one or more wired backhaul links). For example, the network communication manager 1310 may manage the transfer of data communications for client devices, such as one or more UEs 115.

[0212]

[0221] In some cases, device 1305 may include a single antenna 1325. However, in some other cases, device 1305 may have two or more antennas 1325 that may be capable of simultaneously transmitting or receiving multiple wireless transmissions. Transceiver 1315 may communicate bidirectionally via one or more antennas 1325, a wired link, or a wireless link, as described herein. For example, transceiver 1315 may represent a wireless transceiver and communicate bidirectionally with another wireless transceiver. Transceiver 1315 may also include a modem for modulating packets and providing the modulated packets to one or more antennas 1325 for transmission, and for demodulating packets received from one or more antennas 1325. Transceiver 1315, or transceiver 1315 and one or more antennas 1325, may be examples of transmitters 1015, transmitters 1115, receivers 1010, or any combination thereof or their components, as described herein.

[0213]

[0222] Memory 1330 may include RAM and ROM. Memory 1330 may store computer-readable, computer-executable code 1335, which, when executed by processor 1340, contains instructions that cause device 1305 to perform various functions described herein. Code 1335 may be stored in a non-temporary computer-readable medium, such as system memory or another type of memory. In some cases, code 1335 may not be directly executable by processor 1340, but (for example, when compiled and executed) may cause the computer to perform the functions described herein. In some cases, memory 1330 may include a BIOS that can control basic hardware or software operations, in particular, such as interactions with peripheral components or devices.

[0214]

[0223] The processor 1340 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, the processor 1340 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into the processor 1340. The processor 1340 may be configured to execute computer-readable instructions stored in memory (e.g., memory 1330) to cause device 1305 to perform various functions (e.g., functions or tasks supporting techniques for demonstrating signal processing procedures for network-deployed neural network models). For example, device 1305 or components of device 1305 may include the processor 1340 and memory 1330 coupled to the processor 1340, and the processor 1340 and memory 1330 are configured to perform the various functions described herein.

[0215]

[0224] The inter-station communication manager 1345 may manage communication with other network entities 105 and may include a controller or scheduler for coordinating communication with the UE 115 in cooperation with the other network entities 105. For example, the inter-station communication manager 1345 may coordinate scheduling for transmissions to the UE 115 for various interference mitigation techniques such as beamforming or joint transmission. In some examples, the inter-station communication manager 1345 may provide an X2 interface within the LTE / LTE-A wireless communication network technology for communication between network entities 105.

[0216]

[0225] The communication manager 1320 may support wireless communication at a base station as illustrated herein. For example, the communication manager 1320 may be configured or otherwise support means for sending a configuration message to a device, the configuration message indicating one or more neural network models for the device. The communication manager 1320 may be configured or otherwise support means for sending an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the signal processing procedure including one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The communication manager 1320 may be configured or otherwise support means for sending a signal to a device based on having sent an indication of a sequence of operations for a signal processing procedure for at least one neural network model.

[0217]

[0226] By including or configuring a communications manager 1320 as described herein, device 1305 may support techniques for an improved user experience relating to reduced processing and reduced power consumption.

[0218]

[0227] In some examples, the communications manager 1320 may be configured to use or otherwise cooperate with the transceiver 1315, one or more antennas 1325, or any combination thereof, to perform various operations (e.g., receiving, monitoring, transmitting). Although the communications manager 1320 is shown as a separate component, in some examples, one or more functions described with reference to the communications manager 1320 may be supported or performed by the processor 1340, memory 1330, code 1335, or any combination thereof. For example, code 1335 may include instructions executable by the processor 1340 to cause device 1305 to perform various aspects of techniques for demonstrating signal processing procedures for the network-deployed neural network model described herein, or the processor 1340 and memory 1330 may be configured to perform or support such operations in other ways.

[0219]

[0228] Figure 14 shows a flowchart illustrating Method 1400, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. The operation of Method 1400 may be implemented by a UE or its components as described herein. For example, the operation of Method 1400 may be performed by UE 115 as described with reference to Figures 1 to 9. In some examples, the UE may execute a set of instructions to control a functional element of the UE to perform the described function. Additionally or alternatively, the UE may perform aspects of the described function using dedicated hardware.

[0220]

[0229] In 1405, the method may include obtaining (e.g., receiving) a configuration message for a device, where the configuration message indicates one or more neural network models for the device. The operation of 1405 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1405 may be carried out by the UE Model Manager 825, as described with reference to Figure 8.

[0221]

[0230] In 1410, the method may include obtaining an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operation of 1410 may be carried out according to the examples disclosed herein. In some examples, the operation of 1410 may be carried out by a UE signal processing manager 830 as described with reference to Figure 8.

[0222]

[0231] In 1415, the method may include performing a signal processing procedure for at least one neural network model using signals acquired in the device according to a sequence of operations. The operation of 1415 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1415 may be carried out by the execution component 835 described with reference to Figure 8.

[0223]

[0232] Figure 15 shows a flowchart illustrating Method 1500, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. The operation of Method 1500 may be implemented by a UE or its components as described herein. For example, the operation of Method 1500 may be performed by UE 115 as described with reference to Figures 1 to 9. In some examples, the UE may execute a set of instructions to control a functional element of the UE to perform the described function. Additionally or alternatively, the UE may perform aspects of the described function using dedicated hardware.

[0224]

[0233] In 1505, the method may include obtaining (e.g., receiving) a configuration message for a device, where the configuration message indicates one or more neural network models for the device. The operation of 1505 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1505 may be carried out by the UE Model Manager 825, as described with reference to Figure 8.

[0225]

[0234] In 1510, the method may optionally include obtaining signaling that constitutes the device with a set of operations including one or more operations from a sequence of operations for at least one neural network model. Operations of 1510 may be carried out according to the examples disclosed herein. In some examples, the actions of 1510 may be carried out by the UE signal processing manager 830 described with reference to Figure 8.

[0226]

[0235] In 1515, the method may include obtaining an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operations of 1515 may be carried out according to the examples disclosed herein. In some examples, the operations of 1515 may be carried out by the UE signal processing manager 830 described with reference to Figure 8.

[0227]

[0236] In 1520, the method may include performing a signal processing procedure for at least one neural network model using signals acquired in the device according to a sequence of operations. The operation of 1520 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1520 may be carried out by the execution component 835 described with reference to Figure 8.

[0228]

[0237] Figure 16 shows a flowchart illustrating Method 1600, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. The operation of Method 1600 may be implemented by a UE or its components as described herein. For example, the operation of Method 1600 may be performed by UE 115 as described with reference to Figures 1 to 9. In some examples, the UE may execute a set of instructions to control a functional element of the UE to perform the described function. Additionally or alternatively, the UE may perform aspects of the described function using dedicated hardware.

[0229]

[0238] In 1605, the method may include obtaining (e.g., receiving) a configuration message for a device, where the configuration message indicates one or more neural network models for the device. The operation of 1605 may be carried out according to the examples disclosed herein. In some examples, the operation of 1605 may be carried out by the UE Model Manager 825, as described with reference to Figure 8.

[0230]

[0239] In 1610, the method may include obtaining an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operation of 1610 may be carried out according to the examples disclosed herein. In some examples, the operation of 1610 may be carried out by a UE signal processing manager 830 as described with reference to Figure 8.

[0231]

[0240] In 1615, the method may optionally include obtaining an indication of a sequence of operations for a signal processing procedure in a configuration message, where the configuration message includes a set of operations that include all operations of a sequence of operations for at least one neural network model. The operations of 1615 may be carried out according to the examples disclosed herein. In some examples, the actions of 1615 may be carried out by the UE signal processing manager 830, as described with reference to Figure 8.

[0232]

[0241] In 1620, the method may include performing a signal processing procedure for at least one neural network model using signals acquired in the device according to a sequence of operations. The operation of 1620 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1620 may be carried out by the execution component 835 described with reference to Figure 8.

[0233]

[0242] Figure 17 shows a flowchart illustrating Method 1700, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. The operation of Method 1700 may be implemented by a base station or its components as described herein. For example, the operation of Method 1700 may be implemented by a base station 105 as described with reference to Figures 1–5 and 10–13. In some examples, the base station may execute a set of instructions for controlling the functional elements of the base station to perform the functions described. Additionally or alternatively, the base station may perform embodiments of the functions described using dedicated hardware.

[0234]

[0243] In 1705, the method may include outputting (e.g., sending, providing) a configuration message to the device, where the configuration message indicates one or more neural network models for the device. The operation of 1705 may be carried out according to the examples disclosed herein. In some examples, the operation of 1705 may be carried out by the model manager 1225 described with reference to Figure 12.

[0235]

[0244] In 1710, the method may include outputting an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operation of 1710 may be carried out according to the examples disclosed herein. In some examples, the operation of 1710 may be carried out by a signal processing manager 1230 described with reference to Figure 12.

[0236]

[0245] In 1715, the method may include outputting a signal to a device based on an indication of a sequence of actions for a signal processing procedure for at least one neural network model. The operation of 1715 may be carried out according to the examples disclosed herein. In some examples, the actions of 1715 may be carried out by a signal transmitter 1235 described with reference to Figure 12.

[0237]

[0246] Figure 18 shows a flowchart illustrating Method 1800, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more embodiments of the present disclosure. The operation of Method 1800 may be implemented by a base station or its components as described herein. For example, the operation of Method 1800 may be implemented by a base station 105 as described with reference to Figures 1-5 and 10-13. In some examples, the base station may execute a set of instructions for controlling the functional elements of the base station to perform the functions described. Additionally or alternatively, the base station may perform embodiments of the functions described using dedicated hardware.

[0238]

[0247] In 1805, the method may include outputting (e.g., sending, providing) a configuration message to the device, where the configuration message indicates one or more neural network models for the device. The operation of 1805 may be carried out according to the examples disclosed herein. In some examples, the operation of 1805 may be carried out by the model manager 1225 described with reference to Figure 12.

[0239]

[0248] In 1810, the method may optionally include outputting a signaling that constitutes the device with a set of operations including one or more operations from a sequence of operations for at least one neural network model. Operations of 1810 may be carried out according to the examples disclosed herein. In some examples, aspects of operations of 1810 may be carried out by a signal processing manager 1230 described with reference to Figure 12.

[0240]

[0249] In 1815, the method may include outputting an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operation of 1815 may be carried out according to the examples disclosed herein. In some examples, aspects of the operation of 1815 may be carried out by a signal processing manager 1230 described with reference to Figure 12.

[0241]

[0250] In 1820, the method may include outputting a signal to a device based on an indication of a sequence of actions for a signal processing procedure for at least one neural network model. The actions of 1820 may be carried out according to the examples disclosed herein. In some examples, the actions of 1820 may be carried out by a signal transmitter 1235 described with reference to Figure 12.

[0242]

[0251] Figure 19 shows a flowchart illustrating Method 1900, which supports a technique for demonstrating signal processing procedures for a network-deployed neural network model, according to one or more aspects of the present disclosure. The operation of Method 1900 may be implemented by a base station or its components as described herein. For example, the operation of Method 1900 may be implemented by a base station 105 as described with reference to Figures 1-5 and 10-13. In some examples, the base station may execute a set of instructions for controlling the functional elements of the base station to perform the functions described. In addition or alternatively, the base station may perform aspects of the functions described using dedicated hardware.

[0243]

[0252] In 1905, the method may include outputting (e.g., sending, providing) a configuration message to the device, where the configuration message indicates one or more neural network models for the device. The operation of 1905 may be carried out according to the examples disclosed herein. In some examples, the operation of 1905 may be carried out by the model manager 1225 described with reference to Figure 12.

[0244]

[0253] In 1910, the method may include outputting an indication of a sequence of operations for a signal processing procedure for at least one of one or more neural network models, wherein the signal processing procedure includes one of either an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model. The operation of 1910 may be carried out according to the examples disclosed herein. In some examples, the operation of 1910 may be carried out by a signal processing manager 1230 described with reference to Figure 12.

[0245]

[0254] In 1915, the method may optionally include outputting an indication of a sequence of operations for a signal processing procedure in a configuration message, wherein the configuration message includes a set of operations that include all operations of a sequence of operations for at least one neural network model. The operations of 1915 may be carried out according to the examples disclosed herein. In some examples, the actions of 1915 may be carried out by the signal processing manager 1230 described with reference to Figure 12.

[0246]

[0255] In 1920, the method may include outputting a signal to a device based on an indication of a sequence of actions for a signal processing procedure for at least one neural network model. The actions of 1920 may be carried out according to the examples disclosed herein. In some examples, aspects of the actions of 1920 may be carried out by a signal transmitter 1235 described with reference to Figure 12.

[0247]

[0256] The following provides an overview of the aspects of this disclosure.

[0248]

[0257] Embodiment 1: A method for wireless communication in a device in a wireless network, comprising: obtaining a configuration message for the device, wherein the configuration message obtains an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, the configuration message indicating one or more neural network models for the device, and wherein the signal processing procedure is performed using signals obtained in the device according to a sequence of operations, the sequence of operations comprising one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model.

[0249]

[0258] Embodiment 2: The method of Embodiment 1, further comprising obtaining signaling that constitutes a device with a set of actions comprising one or more actions from a sequence of actions for at least one neural network model.

[0250]

[0259] Embodiment 3: Any method of Embodiments 1 to 2, wherein obtaining an indication of a sequence of actions comprises obtaining an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message comprises a set of actions comprising all actions of a sequence of actions for at least one neural network model.

[0251]

[0260] Embodiment 4: Any method of Embodiments 1 to 3, wherein obtaining an indication of a sequence of actions comprises obtaining a second configuration message for a device, wherein the second configuration message indicates a set of actions comprising all actions from at least one neural network model, an indication of a sequence of actions, and a sequence of actions for at least one neural network model.

[0252]

[0261] Embodiment 5: Any method of Embodiments 1 to 4, wherein obtaining an indication of a sequence of actions comprises obtaining a set of input parameters, a set of output parameters, or both for one or more actions in a sequence of actions for at least one neural network model.

[0253]

[0262] Embodiment 6: Any method of Embodiments 1 to 5, further comprising obtaining an indication of a mapping between one or more neural network models and a set of operating states, wherein a signal processing procedure for at least one neural network model is performed using signals obtained in the device in accordance with a sequence of operations, at least in part on the mapping between one or more neural network models and a set of operating states.

[0254]

[0263] Embodiment 7: The method of Embodiment 6, wherein the set of operating states comprises a signal-to-noise ratio range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, related to a signal acquired in the device.

[0255]

[0264] Embodiment 8: Any method of Embodiments 1 to 7, further comprising outputting a message indicating the device's ability to support one or more operations for one or more signal processing procedures, wherein an indication of a sequence of operations for a signal processing procedure for at least one neural network model is obtained at least in part on the device's ability.

[0256]

[0265] Embodiment 9: The method of Embodiment 8, wherein the sequence of operations comprises one or more operations supported by the device.

[0257]

[0266] Embodiment 10: Any method of Embodiments 8 to 9, wherein a message indicating the device's ability to support one or more operations for one or more signal processing procedures comprises an indication of a threshold input dimension for each of the one or more operations for one or more signal processing procedures, or a threshold runtime for each of the one or more operations for one or more signal processing procedures.

[0258]

[0267] Embodiment 11: Any method of Embodiments 1 to 10, wherein obtaining an indication of a sequence of operations comprises obtaining an RRC signaling or MAC-CE that includes an indication of a sequence of operations.

[0259]

[0268] Embodiment 12: Any method of Embodiments 1 to 11, further comprising obtaining an indication of one or more data formats relating to one or more actions in a sequence of actions, wherein the one or more data formats include an XML data format, a JSON data format, or any combination thereof.

[0260]

[0269] Embodiment 13: Any method according to Embodiments 1 to 12, wherein the device comprises a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0261]

[0270] Embodiment 14: A method for wireless communication in a network entity, comprising: outputting a configuration message to a device, wherein the configuration message outputs an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, which indicates one or more neural network models for the device, wherein the signal processing procedure outputs a signal to the device based at least in part on the indication of a sequence of operations for a signal processing procedure for at least one neural network model, which comprises one of an input preprocessing procedure related to at least one neural network model or an output preprocessing procedure related to at least one neural network model.

[0262]

[0271] Embodiment 15: The method of Embodiment 14, further comprising outputting a signaling that constitutes a device with a set of actions comprising one or more actions from a sequence of actions for at least one neural network model.

[0263]

[0272] Embodiment 16: Any method of Embodiments 14 to 15, further comprising obtaining a second sequence of operations for a second signaling procedure performed in a network entity.

[0264]

[0273] Embodiment 17: Any method of Embodiments 14 to 16, wherein outputting an indication of a sequence of actions comprises outputting an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message comprises a set of actions comprising all actions of a sequence of actions for at least one neural network model.

[0265]

[0274] Embodiment 18: Any method of Embodiments 14 to 17, wherein outputting an indication of a sequence of actions comprises outputting a second configuration message to a device, wherein the second configuration message indicates a set of actions comprising at least one neural network model, an indication of a sequence of actions, and all actions of a sequence of actions for at least one neural network model.

[0266]

[0275] Embodiment 19: Any method of Embodiments 14 to 18, wherein outputting an indication of a sequence of actions comprises outputting a set of input parameters, a set of output parameters, or both for one or more actions in a sequence of actions for at least one neural network model.

[0267]

[0276] Embodiment 20: Any method of Embodiments 14 to 19, further comprising outputting an indication of a mapping between one or more neural network models and a set of operating states.

[0268]

[0277] Embodiment 21: The method of Embodiment 20, wherein the set of operating states comprises a signal-to-noise ratio range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to a signal transmitted to a device.

[0269]

[0278] Aspect 22: The method of any one of aspects 14 to 21, further comprising obtaining a message indicating a capability of a device to support one or more operations for one or more signal processing procedures, wherein obtaining an indication of a sequence of operations for a signal processing procedure for at least one neural network model is based at least in part on the capability of the device.

[0270]

[0279] Aspect 23: The method of aspect 22, wherein the sequence of operations comprises one or more operations supported by the device.

[0271]

[0280] Aspect 24: The method of any one of aspects 22 to 23, wherein the message indicating the capability of the device to support one or more operations for one or more signal processing procedures comprises a threshold input dimension for each of the one or more operations for the one or more signal processing procedures, or an indication of a threshold runtime for each of the one or more operations for the one or more signal processing procedures.

[0272]

[0281] Aspect 25: The method of any one of aspects 14 to 24, wherein outputting an indication of the sequence of operations comprises outputting RRC signaling or a MAC-CE that comprises the indication of the sequence of operations.

[0273]

[0282] Aspect 26: The method of any one of aspects 14 to 25, further comprising outputting an indication of one or more data formats associated with one or more operations in the sequence of operations, wherein the one or more data formats comprise an XML data format, a JSON data format, or any combination thereof.

[0274]

[0283] Aspect 27: The method of any one of aspects 14 to 26, wherein the device comprises a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0275]

[0284] Aspect 28: An apparatus for wireless communication at a device in a wireless network, comprising a processor and a memory coupled to the processor, wherein the processor is configured to cause the apparatus to perform the method of any one of aspects 1 to 13.

[0276]

[0285] Aspect 29: An apparatus for wireless communication at a device in a wireless network, comprising at least one means for performing the method of any one of aspects 1 to 13.

[0277]

[0286] Aspect 30: A non-transitory computer-readable medium storing code for wireless communication at a device in a wireless network, the code comprising instructions executable by a processor to perform the method of any one of aspects 1 to 13.

[0278]

[0287] Aspect 31: An apparatus for wireless communication at a network entity, comprising a processor and a memory coupled to the processor, wherein the processor is configured to cause the apparatus to perform the method of any one of aspects 14 to 27.

[0279]

[0288] Aspect 32: An apparatus for wireless communication at a network entity, comprising at least one means for performing the method of any one of aspects 14 to 27.

[0280]

[0289] Aspect 33: A non-transitory computer-readable medium storing code for wireless communication at a network entity, the code comprising instructions executable by a processor to perform the method of any one of aspects 14 to 27.

[0281]

[0290] Embodiment 34: A method for wireless communication in a device in a wireless network, comprising: receiving a configuration message for the device; receiving an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the configuration message indicates one or more neural network models for the device; and performing the signal processing procedure using signals received in the device according to a sequence of operations, wherein the signal processing procedure comprises one of an input preprocessing procedure related to at least one neural network model, or an output preprocessing procedure related to at least one neural network model.

[0282]

[0291] Embodiment 35: The method of Embodiment 34, further comprising receiving signaling that constitutes a device with a set of actions comprising one or more actions from a sequence of actions for at least one neural network model.

[0283]

[0292] Embodiment 36: Any method of Embodiments 34 to the present, wherein receiving an indication of a sequence of actions comprises receiving an indication of a sequence of actions for a signal processing procedure in a configuration message, wherein the configuration message comprises a set of actions comprising all of the actions of a sequence of actions for at least one neural network model.

[0284]

[0293] Embodiment 37: A method of any of embodiments 34 to 36, comprising receiving an indication of a sequence of actions, which comprises receiving a second configuration message for a device, the second configuration message indicating a set of actions comprising all actions from at least one neural network model, an indication of a sequence of actions, and a sequence of actions for at least one neural network model.

[0285]

[0294] Embodiment 38: A method of any of embodiments 34 to 37, wherein receiving an indication of a sequence of actions comprises receiving a set of input parameters, a set of output parameters, or both for one or more actions in a sequence of actions for at least one neural network model.

[0286]

[0295] Embodiment 39: Any method of Embodiments 34 to 38, further comprising receiving an indication of a mapping between one or more neural network models and a set of operating states, wherein a signal processing procedure for at least one neural network model is performed using signals received in the device in accordance with a sequence of operations, at least partially based on the mapping between one or more neural network models and a set of operating states.

[0287]

[0296] Embodiment 40: The method of Embodiment 39, wherein the set of operating states comprises an SNR range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to a signal received in the device.

[0288]

[0297] Embodiment 41: Any method of Embodiments 34 to 40, further comprising transmitting a message indicating the device's ability to support one or more operations for signal processing, wherein receiving an indication of a sequence of operations for a signal processing procedure for at least one neural network model is at least partially based on the device's ability.

[0289]

[0298] Embodiment 42: The method of Embodiment 41, wherein the sequence of operations comprises operations supported by the device.

[0290]

[0299] Embodiment 43: Any method of Embodiments 41 to 42, wherein a message indicating the device's ability to support one or more operations for signal processing includes an indication of a threshold input dimension for each of the one or more operations for signal processing, or a threshold runtime for each of the one or more operations for signal processing.

[0291]

[0300] Embodiment 44: Any method of Embodiments 34 to 43, wherein receiving an indication of a sequence of operations comprises receiving an RRC signaling or MAC-CE comprising an indication of a sequence of operations.

[0292]

[0301] Embodiment 45: Any method of Embodiments 34 to 44, further comprising receiving an indication of one or more data formats relating to one or more actions in a sequence of actions, wherein the one or more data formats include an XML data format, a JSON data format, or any combination thereof.

[0293]

[0302] Embodiment 46: Any method according to Embodiments 34 to 45, wherein the device comprises a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0294]

[0303] Aspect 47: A method for wireless communication at a base station, comprising: transmitting a configuration message to a device; transmitting an indication of a sequence of operations for a signal processing procedure for at least one neural network model among one or more neural network models, wherein the configuration message indicates the one or more neural network models for the device, and the signal processing procedure comprises one of an input preprocessing procedure associated with the at least one neural network model or an output preprocessing procedure associated with the at least one neural network model; and transmitting a signal to the device based at least in part on having transmitted the indication of the sequence of operations for the signal processing procedure for the at least one neural network model.

[0295]

[0304] Aspect 48: The method of Aspect 47, further comprising transmitting signaling that configures the device with a set of operations comprising one or more operations in the sequence of operations for the at least one neural network model.

[0296]

[0305] Aspect 49: The method of any one of Aspects 47 to 48, further comprising receiving a second sequence of operations for a second signaling procedure implemented at the base station.

[0297]

[0306] Aspect 50: The method of any one of Aspects 47 to 49, wherein transmitting the indication of the sequence of operations comprises transmitting the indication of the sequence of operations for the signal processing procedure in the configuration message, and wherein the configuration message comprises a set of operations comprising all operations in the sequence of operations for the at least one neural network model.

[0298]

[0307] Embodiment 51: Any method of Embodiments 47 to 50, wherein transmitting an indication of a sequence of actions comprises transmitting a second configuration message to a device, the second configuration message indicating a set of actions comprising at least one neural network model, an indication of a sequence of actions, and all actions of a sequence of actions for at least one neural network model.

[0299]

[0308] Embodiment 52: Any method of Embodiments 47 to 51, wherein transmitting an indication of a sequence of actions comprises transmitting a set of input parameters, a set of output parameters, or both for one or more actions in a sequence of actions for at least one neural network model.

[0300]

[0309] Embodiment 53: Any method of Embodiments 47 to 52, further comprising transmitting an indication of a mapping between one or more neural network models and a set of operating states.

[0301]

[0310] Embodiment 54: The method of Embodiment 53, wherein the set of operating states comprises an SNR range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to a signal transmitted to a device.

[0302]

[0311] Embodiment 55: Any method of Embodiments 47 to 54, further comprising receiving a message indicating the device's ability to support one or more operations for signal processing, wherein receiving an indication of a sequence of operations for a signal processing procedure for at least one neural network model is at least partially based on the device's ability.

[0303]

[0312] Embodiment 56: The method of Embodiment 55, wherein the sequence of operations comprises operations supported by the device.

[0304]

[0313] Embodiment 57: Any method of Embodiments 55 to 56, wherein a message indicating the device's ability to support one or more operations for signal processing includes an indication of a threshold input dimension for each of the one or more operations for signal processing, or a threshold runtime for each of the one or more operations for signal processing.

[0305]

[0314] Embodiment 58: Any method of Embodiments 47 to 57, wherein transmitting an indication of a sequence of operations comprises transmitting an RRC signaling or MAC-CE comprising an indication of a sequence of operations.

[0306]

[0315] Embodiment 59: Any method of Embodiments 47 to 58, further comprising transmitting an indication of one or more data formats relating to one or more actions in a sequence of actions, wherein the one or more data formats include an XML data format, a JSON data format, or any combination thereof.

[0307]

[0316] Embodiment 60: Any method according to Embodiments 47 to 59, wherein the device comprises a UE, a base station, a network entity, a relay device, a sidelink device, or an IAB node.

[0308]

[0317] Embodiment 61: An apparatus for wireless communication in a device in a wireless network, comprising a processor, a memory coupled to the processor, and instructions stored in the memory that can be executed by the processor to cause the apparatus to perform any of the methods of Embodiments 34 to 46.

[0309]

[0318] Embodiment 62: An apparatus for wireless communication in a device in a wireless network, comprising at least one means for carrying out any of the methods of Embodiments 34 to 46.

[0310]

[0319] Embodiment 63: A non-temporary computer-readable medium for storing code for wireless communication in a device in a wireless network, wherein the code comprises instructions that can be executed by a processor to carry out any of the methods of Embodiments 34 to 46.

[0311]

[0320] Apparatus 64: A device for wireless communication at a base station, comprising a processor, a memory coupled to the processor, and instructions stored in the memory that can be executed by the processor to cause the device to perform any of the methods of Apparatus 47 to 60.

[0312]

[0321] Embodiment 65: An apparatus for wireless communication at a base station, comprising at least one means for carrying out any of the methods of Embodiments 47 to 60.

[0313]

[0322] Embodiment 66: A non-temporary computer-readable medium for storing code for wireless communication at a base station, wherein the code comprises instructions that can be executed by a processor to carry out any of the methods of Embodiments 47 to 60.

[0314]

[0323] It should be noted that the methods described herein describe possible implementations, that the operations and steps may be rearranged or, in some cases, modified, and that other implementations are possible. Furthermore, two or more embodiments of the methods may be combined.

[0315]

[0324] While embodiments of LTE, LTE-A, LTE-A Pro, or NR systems may be described as examples, and the terms LTE, LTE-A, LTE-A Pro, or NR may be used for the majority of the description, the techniques described herein are applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR. For example, the techniques described may be applicable to various other wireless communication systems such as Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, Flash-OFDM, and other systems and wireless technologies not expressly mentioned herein.

[0316]

[0325] The information and signals described herein may be represented using any of the various different techniques and methods. For example, the data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0317]

[0326] The various exemplary blocks and components described in relation to the disclosure herein may be implemented or carried out using general-purpose processors, DSPs, ASICs, CPUs, FPGAs or other programmable logic devices, individual gate or transistor logic, individual hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, a processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors working with a DSP core, or any other such configuration).

[0318]

[0327] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or a combination thereof. When implemented in software executed by a processor, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or codes. Other examples and implementations fall within the scope of this disclosure and the accompanying claims. For example, depending on the nature of the software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination thereof. Features implementing the functions may also be physically located in various locations, including the distribution of parts of the function so that they are implemented in different physical locations.

[0319]

[0328] Computer-readable media include both non-temporary computer storage media and communication media, including any media that facilitates the transfer of computer programs from one location to another. Non-temporary storage media can be any available media that can be accessed by a general-purpose or dedicated computer. Examples, but not limited to, non-temporary computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM®), flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-temporary media that can be used to carry or store desired program code means in the form of instructions or data structures, and can be accessed by a general-purpose or dedicated computer or general-purpose or dedicated processor. Any connection is also appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of computer-readable media. As used herein, disk and disc include CD, LaserDisc®, OpticalDisc, Digital Multipurpose Disc (DVD), FloppyDisc, and Blu-ray®, where disk typically reproduces data magnetically and disc optically reproduces data by laser. Any combination of the above is also included in the scope of computer-readable media.

[0320]

[0329] As used herein, including in the claims, "or" in an enumeration of items (for example, an enumeration of items ending with a phrase such as "at least one of" or "one or more of") indicates an inclusive enumeration, such as an enumeration of at least one of A, B, or C meaning A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase "based on" shall not be construed as a reference to a closed set of conditions. For example, an exemplary step described as "based on condition A" may be based on both condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase "based on" shall be construed in the same way as the phrase "at least partially based on."

[0321]

[0330] The term "decide" or "make a decision" encompasses a wide variety of actions, and therefore "making a decision" can include calculating, calculating, processing, deriving, investigating, looking up (such as by looking up in a table, database, or other data structure), confirming, etc. It can also include receiving (such as receiving information), accessing (such as accessing data in memory), etc. Furthermore, "making a decision" can include resolving, selecting, choosing, establishing, and other similar actions.

[0322]

[0331] In the attached diagrams, similar components or features may have the same reference label. Furthermore, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes them from similar components. When only the first reference label is used herein, its description is applicable to any similar component having the same first reference label, regardless of the second reference label or any other subsequent reference labels.

[0323]

[0332] The descriptions provided herein with respect to the accompanying drawings describe exemplary configurations and do not necessarily represent all examples that may be implemented or that fall within the scope of the claims. The term “example” as used herein means “acting as an example, case, or illustration,” and does not mean “preferred” or “advantageous over other examples.” Detailed descriptions include specific details to provide an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0324]

[0333] The descriptions herein are provided to enable those skilled in the art to create or use this disclosure. Various modifications of this disclosure will be obvious to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of this disclosure. Accordingly, this disclosure should be given the broadest scope that is consistent with the principles and novel features disclosed herein, and is not limited to the examples and designs described herein. The invention described in the original claims of this application is listed below. [C1] A device for wireless communication in a device in a wireless network, comprising a processor and The processor comprises a memory coupled to the processor, and the processor is Obtain a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device. Obtaining an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of the input preprocessing procedure or output preprocessing procedure related to the at least one neural network model. Performing the signal processing procedure for the at least one neural network model using the signals acquired in the device according to the sequence of operations, A device configured to perform the following actions. [C2] The aforementioned processor is The apparatus according to C1, further configured to acquire signaling comprising a set of operations comprising one or more operations from the sequence of operations for at least one neural network model, the device comprising the device. [C3] In order to obtain the indication of the sequence of operations, the processor is configured to obtain the indication of the sequence of operations for the signal processing procedure in the configuration message, wherein the configuration message comprises a set of operations comprising all of the sequences of operations for the at least one neural network model. The apparatus described in C1. [C4] In order to obtain the indication of the sequence of operations, the processor is configured to obtain a second configuration message for the device, wherein the second configuration message indicates a set of operations comprising all of the operations from the at least one neural network model, the indication of the sequence of operations, and the sequence of operations for the at least one neural network model. The apparatus described in C1. [C5] The apparatus according to C1, wherein the processor is configured to obtain an indication of the sequence of operations for at least one neural network model, by obtaining a set of input parameters, a set of output parameters, or both for one or more operations of the sequence of operations for at least one neural network model. [C6] The aforementioned processor is The system is further configured to obtain indications of a mapping between one or more neural network models and a set of operating states, wherein the signal processing procedure for at least one neural network model is performed using the signals obtained in the device according to the sequence of operations, at least partially based on the mapping between the one or more neural network models and the set of operating states. The apparatus described in C1. [C7] The apparatus according to C6, wherein the set of operating states comprises a signal-to-noise ratio range, bandwidth range, signal scaling range, channel delay profile, signal peak range, or any combination thereof, related to the signal acquired in the device. [C8] The aforementioned processor is Further configured to output a message indicating the device's ability to support one or more operations for one or more signal processing procedures, The indication of the sequence of operations for the signal processing procedure for the at least one neural network model is obtained at least in part based on the capabilities of the device. The apparatus described in C1. [C9] The apparatus according to C8, wherein the sequence of operations comprises one or more operations supported by the device. [C10] The apparatus according to C8, wherein the message indicating the device's ability to support the one or more operations for the one or more signal processing procedures comprises an indication of a threshold input dimension for each of the one or more operations for the one or more signal processing procedures, or a threshold runtime for each of the one or more operations for the one or more signal processing procedures. [C11] In order to obtain the indication of the sequence of operations, the processor obtains a media access control (MAC) control element (MAC-CE) or radio resource control (RRC) signaling that includes the indication of the sequence of operations. The apparatus described in C1, configured as follows. [C12] Further comprising an antenna configured to obtain indications of one or more data formats relating to one or more operations in one or more of the sequence of operations, wherein the one or more data formats include an Extensible Markup Language data format, a Java® Script object notation data format, or any combination thereof. The apparatus described in C1. [C13] The device described in C1, comprising user equipment (UE), base station, network entity, relay device, sidelink device, or integrated access and backhaul (IAB) node. [C14] Device for wireless communication in a network entity, Processor and The processor comprises a memory coupled to the processor, and the processor is Outputting a configuration message to the device, wherein the configuration message indicates one or more neural network models for the device. Outputting an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of the input preprocessing procedure or the output preprocessing procedure related to the at least one neural network model. Outputting a signal to the device based at least in part on the indication of the sequence of operations for the signal processing procedure for the at least one neural network model, A device configured to perform the following actions. [C15] The aforementioned processor is The apparatus according to C14, further configured to output signaling comprising a set of operations comprising one or more operations from the sequence of operations for at least one neural network model. [C16] The aforementioned processor is The apparatus according to C14, further configured to obtain a second sequence of operations for a second signaling procedure performed in the network entity. [C17] In order to output the indication of the sequence of operations, the processor is configured to output the indication of the sequence of operations for the signal processing procedure in the configuration message, wherein the configuration message comprises a set of operations comprising all of the operations of the sequence of operations for the at least one neural network model. The device described in C14. [C18] In order to output the indication of the sequence of operations, the processor is configured to output a second configuration message to the device, wherein the second configuration message indicates a set of operations comprising all of the operations from the at least one neural network model, the indication of the sequence of operations, and the sequence of operations for the at least one neural network model. The device described in C14. [C19] The apparatus according to C14, wherein the processor is configured to output a set of input parameters, a set of output parameters, or both for one or more operations of the sequence of operations for the at least one neural network model. [C20] The aforementioned processor is The apparatus according to C14, further configured to output an indication of a mapping between one or more neural network models and a set of operating states. [C21] The apparatus according to C20, wherein the set of operating states comprises a signal-to-noise ratio range, bandwidth range, signal scaling range, channel delay profile, signal peak range, or any combination thereof, relating to the signal transmitted to the device. [C22] The aforementioned processor is Further configured to obtain a message indicating the device's ability to support one or more operations for one or more signal processing procedures, Obtaining the indication of the sequence of operations for the signal processing procedure for the at least one neural network model is at least partially based on the capabilities of the device. The device described in C14. [C23] The apparatus according to C22, wherein the sequence of operations comprises one or more operations supported by the device. [C24] The apparatus according to C22, wherein the message indicating the device's ability to support the one or more operations for the one or more signal processing procedures comprises an indication of a threshold input dimension for each of the one or more operations for the one or more signal processing procedures, or a threshold runtime for each of the one or more operations for the one or more signal processing procedures. [C25] In order to output the indication of the sequence of operations, the processor outputs a media access control (MAC) control element (MAC-CE) or radio resource control (RRC) signaling comprising the indication of the sequence of operations. The apparatus described in C14, configured as such. [C26] Further comprising an antenna configured to output indications of one or more data formats relating to one or more operations in one or more of the sequence of operations, wherein the one or more data formats include an Extensible Markup Language data format, a JavaScript® object notation data format, or any combination thereof. The device described in C14. [C27] The device described in C14, comprising user equipment (UE), base stations, network entities, relay devices, sidelink devices, or integrated access and backhaul (IAB) nodes. [C28] A method for wireless communication in a device in a wireless network, comprising obtaining a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device. Obtaining an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of the input preprocessing procedure or the output preprocessing procedure associated with the at least one neural network model. Performing the signal processing procedure for the at least one neural network model using the signals acquired in the device according to the sequence of operations, A method that includes [something]. [C29] Obtaining signaling that constitutes the device with a set of operations comprising one or more operations from the sequence of operations for at least one neural network model, A method using C28 that further incorporates these features. [C30] A method for wireless communication in a network entity, Outputting a configuration message to the device, wherein the configuration message indicates one or more neural network models for the device. Outputting an indication of a sequence of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of the input preprocessing procedure or the output preprocessing procedure associated with the at least one neural network model. Outputting a signal to the device at least in part based on having transmitted the indication of the sequence of operations for the signal processing procedure for the at least one neural network model, A method that includes [something].

Claims

1. A device for wireless communication in a device within a wireless network, One or more memory units, The device comprises one or more processors coupled to one or more of the memory, and the one or more processors provide the device with Obtain a configuration message for the device, wherein the configuration message indicates one or more neural network models for the device. Obtaining signaling that includes an indication of the time order of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of an input preprocessing procedure related to the at least one neural network model, or an output postprocessing procedure related to the at least one neural network model. Performing the signal processing procedure for the at least one neural network model using signals acquired in the device according to the aforementioned time sequence of operations, A device configured to perform the following action.

2. The one or more processors in the device The apparatus according to claim 1, further configured to cause the device to acquire signaling comprising a set of operations comprising one or more operations of the time-order operations for at least one neural network model.

3. In order to obtain the indication of the time sequence of operations, one or more processors provide the device with The configuration message is configured to obtain the indication of the time sequence of operations for the signal processing procedure, wherein the configuration message comprises a set of operations comprising all of the operations of the time sequence for at least one neural network model. The apparatus according to claim 1.

4. In order to obtain the indication of the time sequence of operations, one or more processors provide the device with The device is configured to obtain a second configuration message, wherein the second configuration message indicates a set of operations comprising all of the operations of the at least one neural network model, the indication of the time sequence of operations, and the operations of the time sequence for the at least one neural network model. The apparatus according to claim 1.

5. In order to obtain the indication of the time sequence of operations, one or more processors provide the device with The apparatus according to claim 1, configured to obtain a set of input parameters, a set of output parameters, or both for one or more of the time-sequence operations for the at least one neural network model.

6. The one or more processors in the device The system is further configured to obtain indications of a mapping between one or more neural network models and a set of operating states, wherein the signal processing procedure for at least one neural network model is performed using the signals acquired in the device in accordance with the time order of operations, based at least partially on the mapping between the one or more neural network models and the set of operating states. The apparatus according to claim 1.

7. The one or more processors in the device Further configured to output a message indicating the device's ability to support one or more operations for one or more signal processing procedures, The indication of the time sequence of operations for the signal processing procedure for the at least one neural network model is obtained at least in part based on the capabilities of the device. The apparatus according to claim 1.

8. The apparatus according to claim 7, wherein the time sequence of operations comprises one or more operations supported by the device.

9. The apparatus according to claim 7, wherein the message indicating the device's ability to support the one or more operations for the one or more signal processing procedures comprises an indication of a threshold input dimension for each of the one or more operations for the one or more signal processing procedures, or a threshold runtime for each of the one or more operations for the one or more signal processing procedures.

10. In order to obtain the indication of the time sequence of operations, one or more processors provide the device with To obtain a media access control (MAC) control element (MAC-CE) or radio resource control (RRC) signaling that includes the indication of the time sequence of operations. The apparatus according to claim 1, configured as described above.

11. The present invention further comprises an antenna configured to obtain indications of one or more data formats relating to one or more operations of the sequence of operations, wherein the one or more data formats include an Extensible Markup Language data format, a Java® Script object notation data format, or any combination thereof. The apparatus according to claim 1.

12. The apparatus according to claim 1, comprising user equipment (UE), base stations, network entities, relay devices, sidelink devices, or integrated access and backhaul (IAB) nodes.

13. A device for wireless communication in a network entity, One or more memory units, The system comprises one or more processors coupled to one or more of the memory, and the one or more processors provide the network entity Outputting a configuration message to the device, wherein the configuration message indicates one or more neural network models for the device. Outputting a signaling having an indication of the time order of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of an input preprocessing procedure related to the at least one neural network model, or an output postprocessing procedure related to the at least one neural network model. Outputting a signal to the device based at least partially on the indication of the time sequence of operations for the signal processing procedure for the at least one neural network model, A device configured to perform the following action.

14. The one or more processors provide the network entity The apparatus according to claim 13, further configured to output signaling comprising a set of operations comprising one or more operations from the time sequence of operations for at least one neural network model, the device.

15. The one or more processors provide the network entity The apparatus according to claim 13, further configured to obtain a second time sequence of operations for a second signaling procedure performed in the network entity.

16. In order to output the indication of the time sequence of operations, one or more processors provide the network entity: The configuration message is configured to output an indication of the time sequence of operations for the signal processing procedure, wherein the configuration message comprises a set of operations comprising all of the operations in the time sequence of operations for at least one neural network model. The apparatus according to claim 13.

17. In order to output the indication of the time sequence of operations, one or more processors provide the network entity: The device is configured to output a second configuration message, wherein the second configuration message indicates a set of operations comprising all of the operations among the at least one neural network model, the indication of the time order of operations, and the time order of operations for the at least one neural network model. The apparatus according to claim 13.

18. In order to output the indication of the time sequence of operations, one or more processors provide the network entity: The apparatus according to claim 13, configured to output a set of input parameters, a set of output parameters, or both, for one or more operations in the time sequence of operations for at least one neural network model.

19. The one or more processors provide the network entity The apparatus according to claim 13, further configured to output an indication of a mapping between one or more neural network models and a set of operating states.

20. The apparatus according to claim 19, wherein the set of operating states comprises a signal-to-noise ratio range, a bandwidth range, a signal scaling range, a channel delay profile, a signal peak range, or any combination thereof, relating to the signal transmitted to the device.

21. The one or more processors provide the network entity Further configured to cause the device to receive a message indicating its ability to support one or more operations for one or more signal processing procedures, Obtaining the indication of the time sequence of operations for the signal processing procedure for the at least one neural network model is at least partially based on the capabilities of the device. The apparatus according to claim 13.

22. The apparatus according to claim 21, wherein the time sequence of operations comprises one or more operations supported by the device.

23. The apparatus according to claim 21, wherein the message indicating the device's ability to support the one or more operations for the one or more signal processing procedures comprises an indication of a threshold input dimension for each of the one or more operations for the one or more signal processing procedures, or a threshold runtime for each of the one or more operations for the one or more signal processing procedures.

24. In order to output the indication of the time sequence of operations, one or more processors provide the network entity: This causes a media access control (MAC) control element (MAC-CE) or radio resource control (RRC) signaling to output, which includes the indication of the time sequence of operations. The apparatus according to claim 13, configured as described above.

25. The device further comprises an antenna configured to output an indication of one or more data formats relating to one or more operations in the time sequence of operations, wherein the one or more data formats include an Extensible Markup Language data format, a JavaScript® object notation data format, or any combination thereof. The apparatus according to claim 13.

26. The apparatus according to claim 13, comprising user equipment (UE), base station, network entity, relay device, sidelink device, or integrated access and backhaul (IAB) node.

27. A method for wireless communication in devices within a wireless network, Obtain a configuration message for the device, and the configuration message indicates one or more neural network models for the device. Obtaining signaling that includes an indication of the time order of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of an input preprocessing procedure related to the at least one neural network model, or an output postprocessing procedure related to the at least one neural network model. Performing the signal processing procedure for the at least one neural network model using signals acquired in the device according to the aforementioned time sequence of operations, A method that includes [something].

28. A method for wireless communication in a network entity, Outputting a configuration message to the device, wherein the configuration message indicates one or more neural network models for the device. Outputting a signaling having an indication of the time order of operations for a signal processing procedure for at least one of the one or more neural network models, wherein the signal processing procedure comprises one of an input preprocessing procedure related to the at least one neural network model, or an output postprocessing procedure related to the at least one neural network model. Outputting a signal to the device at least in part based on having transmitted the indication of the time sequence of operations for the signal processing procedure for the at least one neural network model, A method that includes [something].

Images