Additional condition indication based on model monitoring

Abstract

Methods, systems, and devices are described for wireless communication. A first wireless device can be configured to communicate signaling with a second wireless device, an additional wireless device, or both, and perform one or more inferences using a machine learning model based on the signaling. The first wireless device can transmit, to the second wireless device, an indication that the machine learning model is applicable to performing the one or more inferences, and receive, from the second wireless device, control signaling indicating that the machine learning model is applicable to communications associated with a first set of conditions associated with the communication of the signaling, where the control signaling indicates a model identifier (ID) associated with the machine learning model, that the first set of conditions is associated with the machine learning model, or both.

Description

[0001] Cross-referencing

[0002] This patent application claims the benefit of U.S. Patent Application No. 18 / 930,689, filed October 29, 2024, entitled “ADDITIONAL CONDITION INDICATION BASED ON MODEL MONITORING,” and U.S. Provisional Patent Application No. 63 / 596,162, filed November 3, 2023, entitled “ADDITIONAL CONDITION INDICATION BASED ON MODEL MONITORING,” each of which is assigned to the assignee of this application and is incorporated herein by reference. Technical Field

[0003] The following section relates to wireless communications, including technologies for additional condition indications for model-based monitoring. Background Technology

[0004] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, message sending and receiving, broadcasting, and so on. These systems can 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-A Advanced (LTE-A) systems, or LTE-A Pro systems) and fifth-generation (5G) systems (which may be referred to as New Radio (NR) systems). These systems may employ technologies such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), or Discrete Fourier Transform Extended Orthogonal Frequency Division Multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations, each supporting wireless communication of communication devices, which may be referred to as User Equipment (UE).

[0005] Some wireless devices (e.g., UEs) can be configured to use machine learning models (e.g., machine learning algorithms, neural networks) to infer or predict various characteristics of wireless communication, such as channel quality metrics, beam prediction, UE location, etc. Summary of the Invention

[0006] Machine learning models used within wireless communication systems can be generated or trained in various ways. In some cases, machine learning models can be trained to make specific inferences on a particular training or test dataset. However, the model may be additionally or alternatively used for other situations or conditions unknown at the time of training (e.g., for situations that are out of distribution relative to the training or test dataset). Therefore, the model may not be fully utilized, which could lead to the network unnecessarily training additional models to make inferences or predictions in the same situations or conditions that the previously trained model might have covered.

[0007] The described techniques relate to improved methods, systems, apparatuses, and devices for supporting techniques for identifying, defining, and updating machine learning models used to perform various inferences or predictions within a wireless communication system. Specifically, aspects of this disclosure relate to techniques for: (1) identifying and defining machine learning models to be used for inference or prediction for a specific set of conditions within a wireless network, and (2) updating machine learning models to apply them to new / additional sets of conditions. For example, a user equipment (UE) may test different machine learning models for inference or prediction while communicating with a network entity. In this example, the UE, the network entity, or both may determine that a model is useful or accurate in inference or prediction for a given set of conditions, and thus may define a model identifier (ID) for the machine learning model so that the model can be referenced and used in the future for inference or prediction for that set of conditions. Continuing with the same example, when using a machine learning model to infer or predict for a set of conditions, a wireless device (e.g., a UE, a network entity) may determine that the machine learning model can also be used for inference or prediction for additional conditions. In such cases, wireless devices can exchange signaling with each other to update the metadata associated with the machine learning model, making the model available for use in additional situations, thereby extending the use of the model to other situations or circumstances.

[0008] A method performed by a first wireless device is described. The method may include: communicating signaling with a second wireless device, an additional wireless device, or both; performing one or more inferences using a machine learning model based on the communication of the signaling; sending an instruction to the second wireless device that the machine learning model is suitable for performing the one or more inferences; and receiving control signaling from the second wireless device that indicates the machine learning model is suitable for communication associated with a first set of conditions related to the communication of the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, an instruction that the first set of conditions is associated with the machine learning model, or both.

[0009] A first wireless device is described. The first wireless device may include: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories. The one or more processors may be able to operate individually or jointly to execute the code to cause the first wireless device to: communicate signals with a second wireless device, an additional wireless device, or both; perform one or more inferences using a machine learning model based on the communication of the signaling; send an instruction to the second wireless device that the machine learning model is suitable for performing the one or more inferences; and receive control signaling from the second wireless device that indicates that the machine learning model is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, an instruction that the first set of conditions is associated with the machine learning model, or both.

[0010] Another first wireless device is described. The first wireless device may include: components for communicating signaling with a second wireless device, an additional wireless device, or both; components for performing one or more inferences using a machine learning model based on the communication of the signaling; components for sending to the second wireless device an indication that the machine learning model is suitable for performing the one or more inferences; and components for receiving control signaling from the second wireless device, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, an indication that the first set of conditions is associated with the machine learning model, or both.

[0011] A non-transitory computer-readable medium storing code is described. The code may include instructions executable by a processor to: communicate a signal to a second wireless device, an additional wireless device, or both; perform one or more inferences using a machine learning model based on the communication of the signaling; send an instruction to the second wireless device indicating that the machine learning model is suitable for performing the one or more inferences; and receive control signaling from the second wireless device instructing the machine learning model to be suitable for communication associated with a first set of conditions related to the communication of the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, an instruction associated with the first set of conditions, or both.

[0012] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: storing a data object that associates the machine learning model with the model ID, the first set of conditions, or both, based on receiving the control signaling; receiving additional control signaling from the second wireless device indicating the model ID, the first set of conditions, or both; and using the machine learning model to perform one or more additional inferences based on storing the data object and receiving the additional control signaling.

[0013] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: storing a data object associated with the machine learning model and the model ID, the first set of conditions, or both, based on receiving the control signaling; identifying that the second wireless device may communicate according to the first set of conditions; and using the machine learning model to perform one or more additional inferences based on storing the data object and identifying that the second wireless device may be communicating according to the first set of conditions.

[0014] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for sending to the second wireless device a capability signaling indicating a second set of conditions used by the first wireless device to convey the signaling, wherein one or more inferences may be associated with the second set of conditions.

[0015] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the control signaling indicates that the machine learning model is applicable to communications associated with the second set of conditions.

[0016] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the second set of conditions includes the number of communication layers supported at the first wireless device, the number of antennas at the first wireless device, or both.

[0017] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: communicating additional signaling with the second wireless device, the additional wireless device, or both, based on an additional set of conditions associated with the second wireless device; using the machine learning model to perform one or more additional inferences based on communicating the additional signaling according to the additional set of conditions; and sending a control message to the second wireless device instructing the machine learning model to be suitable for performing the one or more additional inferences associated with the additional set of conditions.

[0018] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: receiving from the second wireless device additional control signaling indicating that the machine learning model can be associated with the additional set of conditions; and updating a data object associated with the machine learning model based on the received additional control signaling to include information associated with the association between the machine learning model and the additional set of conditions.

[0019] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the set of additional conditions includes the speed of the first wireless device, signal quality metrics of wireless communications received by the first wireless device, network-based additional conditions, or any combination thereof.

[0020] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the first set of conditions includes one or more network settings, radio resource control (RRC) configurations, or both.

[0021] In some examples of the methods described herein, the first wireless device, and the nontransient computer-readable medium, the one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographic location of the first wireless device, or any combination thereof.

[0022] In some examples of the methods described herein, the first wireless device, and the non-transitory computer-readable medium, the machine learning model includes a neural network model.

[0023] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the first wireless device includes a UE and the second wireless device includes a network entity, and the first wireless device includes the network entity and the second wireless device includes the UE.

[0024] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: monitoring the performance of the machine learning model based on performing the one or more inferences; and determining, based on monitoring the performance of the machine learning model, whether the machine learning model is suitable for performing the one or more inferences.

[0025] A method performed by a first wireless device is described. The method may include: communicating signaling with a second wireless device, an additional wireless device, or both; performing one or more inferences using a functionality based on the communication of the signaling; sending an indication to the second wireless device that the functionality is suitable for performing the one or more inferences; and receiving control signaling from the second wireless device, the control signaling indicating that the functionality is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a functionality ID associated with the functionality, an indication that the first set of conditions is associated with the functionality, or both.

[0026] A first wireless device is described. The first wireless device may include: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories. The one or more processors may be able to operate individually or jointly to execute the code to cause the first wireless device to: communicate signals with a second wireless device, an additional wireless device, or both; perform one or more inferences using functionality based on the communication of the signaling; send an indication to the second wireless device that the functionality is suitable for performing the one or more inferences; and receive control signaling from the second wireless device that indicates that the functionality is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a functionality ID associated with the functionality, an indication of the first set of conditions associated with the functionality, or both.

[0027] Another first wireless device is described. The first wireless device may include: components for communicating signaling with a second wireless device, an additional wireless device, or both; components for performing one or more inferences using functionality based on the communication of the signaling; components for sending to the second wireless device an indication that the functionality is suitable for performing the one or more inferences; and components for receiving control signaling from the second wireless device, the control signaling indicating that the functionality is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a functionality ID associated with the functionality, an indication that the first set of conditions is associated with the functionality, or both.

[0028] A non-transitory computer-readable medium storing code is described. The code may include instructions executable by a processor to: communicate signals with a second wireless device, an additional wireless device, or both; perform one or more inferences using functionality based on the communication of the signaling; send an instruction to the second wireless device indicating that the functionality is suitable for performing the one or more inferences; and receive control signaling from the second wireless device indicating that the functionality is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a functionality ID associated with the functionality, an indication of the first set of conditions associated with the functionality, or both.

[0029] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: storing a data object that associates the functionality with the functionality identifier, the first set of conditions, or both, based on receiving the control signaling; receiving additional control signaling from the second wireless device that indicates the functionality identifier, the first set of conditions, or both; and using the functionality to perform one or more additional inferences based on storing the data object and receiving the additional control signaling.

[0030] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: storing a data object associated with the functionality and the functionality identifier, the first condition set, or both, based on receiving the control signaling; identifying that the second wireless device may communicate according to the first condition set; and using the functionality to perform one or more additional inferences based on storing the data object and identifying that the second wireless device may be communicating according to the first condition set.

[0031] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for sending to the second wireless device a capability signaling indicating a second set of conditions used by the first wireless device to convey the signaling, wherein one or more inferences may be associated with the second set of conditions.

[0032] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the control signaling indicates that the functionality is applicable to communications associated with the second set of conditions.

[0033] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the second set of conditions includes the number of communication layers supported at the first wireless device, the number of antennas at the first wireless device, or both.

[0034] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: communicating additional signaling with the second wireless device, the additional wireless device, or both based on an additional set of conditions associated with the second wireless device; using the functionality to perform one or more additional inferences based on communicating the additional signaling according to the additional set of conditions; and sending a control message to the second wireless device instructing the functionality to be suitable for performing the one or more additional inferences associated with the additional set of conditions.

[0035] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: receiving from the second wireless device additional control signaling indicating that the functionality can be associated with the additional condition set; and updating a data object associated with the functionality based on the received additional control signaling to include information associated with the association between the functionality and the additional condition set.

[0036] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the set of additional conditions includes the speed of the first wireless device, signal quality metrics of wireless communications received by the first wireless device, network-based additional conditions, or any combination thereof.

[0037] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the first set of conditions includes one or more network settings, radio resource control configurations, or both.

[0038] In some examples of the methods described herein, the first wireless device, and the nontransient computer-readable medium, the one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographic location of the first wireless device, or any combination thereof.

[0039] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, this functionality may be associated with one or more machine learning models that can be executed by the first wireless device, the second wireless device, or both.

[0040] In some examples of the methods described herein, the first wireless device, and the nontransitory computer-readable medium, the first wireless device includes a UE and the second wireless device includes a network entity, and the first wireless device includes the network entity and the second wireless device includes the UE.

[0041] The methods described herein, examples of the first wireless device, and some examples of nontransitory computer-readable media may also include operations, features, components, or instructions for: monitoring the performance of the functionality based on performing the one or more inferences; and determining, based on monitoring the performance of the functionality, whether the functionality is suitable for performing the one or more inferences. Attached Figure Description

[0042] Figure 1 Examples of wireless communication systems supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown.

[0043] Figure 2 Examples of wireless communication systems supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown.

[0044] Figure 3 An example of a process flow supporting a technique for model-based monitoring of additional condition indications, according to one or more aspects of this disclosure, is shown.

[0045] Figure 4 An example of a process flow supporting a technique for model-based monitoring of additional condition indications, according to one or more aspects of this disclosure, is shown.

[0046] Figure 5 An example of a process flow supporting a technique for model-based monitoring of additional condition indications, according to one or more aspects of this disclosure, is shown.

[0047] Figure 6 and Figure 7 A block diagram of an apparatus for providing additional condition indications based on model monitoring, according to one or more aspects of this disclosure, is shown.

[0048] Figure 8 A block diagram of a communication manager supporting techniques for additional condition indications based on model monitoring, according to one or more aspects of this disclosure, is shown.

[0049] Figure 9 A diagram of a system including a device for supporting additional condition indications for model-based monitoring, according to one or more aspects of this disclosure, is shown.

[0050] Figure 10 and Figure 11 A flowchart illustrating a method for providing additional condition indications based on model monitoring, according to one or more aspects of this disclosure, is shown. Detailed Implementation

[0051] Some wireless devices (e.g., user equipment (UE), network entities) can be configured to store and use machine learning models (such as neural network models) to make various inferences or predictions related to wireless communication. Machine learning models can be used to infer or predict channel conditions (e.g., for channel state feedback), beam prediction, UE location, etc. For example, a UE can perform measurements on reference signals received from the network and can input these measurements into a machine learning algorithm to predict the relative quality of the received (Rx) beam applied to future communications.

[0052] Machine learning models used within wireless communication systems can be generated or trained in various ways. For example, in some cases, wireless devices can test different models through trial and error. However, such trial-and-error techniques can be very time-consuming. Furthermore, if a wireless device discovers that a machine learning model can be used to perform various inferences, that model may only be usable by the specific wireless device that made the discovery and may not be usable by other wireless devices within the network. In other cases, machine learning models can be trained to make specific inferences for a particular training or test dataset. For example, a model can be trained to perform beam prediction when the UE and network entities are in direct line-of-sight and when the signal-to-noise ratio (SNR) is above a threshold. Therefore, the model can be used to perform beam prediction in a very specific set of situations or conditions (e.g., direct line-of-sight and SNR above a threshold). However, the model can be additionally or alternatively used for other situations or conditions unknown at the time of training (e.g., for situations that are out of distribution relative to the training or test datasets). For example, the model may also be used for non-direct line-of-sight situations or for situations where the SNR is not above a threshold. Therefore, the model may not be fully utilized, which may lead the network to unnecessarily train additional models to make inferences or predictions in the same situations or conditions that the previously trained model may cover.

[0053] Therefore, aspects of this disclosure relate to techniques for identifying, defining, and updating machine learning models used to perform various inferences or predictions within a wireless communication system. Specifically, aspects of this disclosure relate to signaling and configuration that enables a wireless device to: (1) initialize and define a machine learning model to be used for inference or prediction in a particular set of conditions, and (2) update the machine learning model to apply the machine learning model to a new or additional set of conditions.

[0054] For example, a UE can test different machine learning models for inference or prediction while communicating with a network entity. In this example, the UE or the network entity can determine whether a model is useful or accurate in making inference or prediction, and thus define a model ID for the machine learning model, making the model referential and usable between the UE and the network entity in the future for a specific set of conditions.

[0055] Continuing with the same example, a wireless device can be configured to use a machine learning model for a specific set of conditions (e.g., RRC configuration, SNR, UE speed, line-of-sight, etc.) that has previously been trained or used for that specific set of conditions. In such cases, by using the model and by monitoring its accuracy or performance, the wireless device (e.g., UE, network entity) can determine that the model can also be used to infer or predict for additional conditions. In such cases, the wireless device can send signaling to those other wireless devices to update the metadata associated with the model, making the model usable in the context of the additional conditions, thereby extending the use of the model to other conditions or situations. In this respect, the applicability of the model to different additional conditions can be crowdsourced across different wireless devices within the network.

[0056] In some cases, determining whether a particular model can be extended or used for additional conditions may only apply to that specific UE, as different UEs may not use the same model. In such situations, the network entity and the UE determining the model's applicability can update the metadata associated with the model, making the model usable in the additional conditions and thus extending the model's use to other conditions or situations. However, in some cases, the same physical model can be shared across other radio devices.

[0057] The aspects of this disclosure are first described in the context of a wireless communication system. Additional aspects of this disclosure are described in the context of an example process flow. The aspects of this disclosure are further illustrated by apparatus diagrams, system diagrams, and flowcharts relating to techniques for additional condition indication based on model monitoring, and are described with reference to these diagrams.

[0058] Figure 1 Examples of wireless communication systems 100 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown. 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, wireless communication system 100 may be a Long Term Evolution (LTE) network, an Advanced LTE (LTE-A) network, an LTE-A Pro network, a New Radio (NR) network, or a network operating under other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.

[0059] Network entity 105 may be distributed across a geographical area to form wireless communication system 100, and may include devices employing different forms or having different capabilities. In various examples, network entity 105 may be referred to as a network element, mobility element, radio access network (RAN) node, or network equipment, among other designations. In some examples, network entity 105 and UE 115 may wirelessly communicate via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, network entity 105 may support coverage area 110 (e.g., a geographical coverage area) within which UE 115 and network entity 105 may establish one or more communication links 125. Coverage area 110 may be an example of a geographical area within which network entity 105 and UE 115 may support the transmission of signals according to one or more radio access technologies (RATs).

[0060] UE 115 can be distributed throughout the coverage area 110 of wireless communication system 100, and each UE 115 can be stationary or mobile, or stationary and mobile at different times. UE 115 can be devices in different forms or with different capabilities. Figure 1 Examples of UE 115 are illustrated herein. The UE 115 described herein can be able to support communication with various types of devices, such as other UE 115s or network entities 105, such as Figure 1 As shown.

[0061] As described herein, nodes of the wireless communication system 100 (which may be referred to as network nodes or wireless nodes) may be network entity 105 (e.g., any network entity described herein), UE 115 (e.g., any UE described herein), network controller, apparatus, device, computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, a node may be UE 115. Alternatively, a node may be network entity 105. Furthermore, a first node may be configured to communicate with a second or third node. In one aspect of this example, the first node may be UE 115, the second node may be network entity 105, and the third node may be UE 115. In another aspect of this example, the first node may be UE 115, the second node may be network entity 105, and the third node may be network entity 105. In other aspects of this example, the first node, the second node, and the third node may be different from these examples. Similarly, references to UE 115, network entity 105, device, equipment, computing system, etc., may include disclosures of UE 115, network entity 105, device, equipment, computing system, etc., as nodes. For example, a disclosure that UE 115 is configured to receive information from network entity 105 also discloses that a first node is configured to receive information from a second node.

[0062] In some examples, network entity 105 may communicate with core network 130, communicate with each other, or both. For example, network entity 105 may communicate with core network 130 via one or more backhaul communication links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some examples, network entities 105 may communicate with each other directly (e.g., directly between network entities 105) or indirectly (e.g., via core network 130) via backhaul communication links 120 (e.g., according to X2, Xn, or other interface protocols). In some examples, network entities 105 may communicate with each other via midhaul communication link 162 (e.g., according to midhaul interface protocol) or fronthaul communication link 168 (e.g., according to fronthaul interface protocol) or any combination thereof. Backhaul communication link 120, midhaul communication link 162, or fronthaul communication link 168 may be or include one or more wired links (e.g., electrical links, fiber optic links), one or more wireless links (e.g., radio links, wireless optical links), etc., or various combinations thereof. UE 115 can communicate with core network 130 via communication link 155.

[0063] One or more network entities in network entity 105 described herein may include or be referred to as base station 140 (e.g., transceiver base station, radio base station, NR base station, access point, radio transceiver, node B, eNodeB (eNB), next-generation node B or gigabit node B (any of which may be referred to as gNB), 5G NB, next-generation eNB (ng-eNB), home node B, home evolution node B, or other suitable terms). In some examples, network entity 105 (e.g., base station 140) may be implemented in an aggregated (e.g., monolithic, standalone) base station architecture that may be configured to utilize a protocol stack that is physically or logically integrated within a single network entity 105 (e.g., a single RAN node, such as base station 140).

[0064] In some examples, network entity 105 may be implemented in a decomposed architecture (e.g., a decomposed base station architecture, a decomposed RAN architecture) that can be configured to utilize protocol stacks physically or logically distributed across two or more network entities 105, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, network entity 105 may include one or more of the following: a central unit (CU) 160, a distributed unit (DU) 165, a radio unit (RU) 170, a RAN intelligent controller (RIC) 175 (e.g., a near real-time RIC, a non-real-time RIC), a service management and orchestration (SMO) 180 system, or any combination thereof. 170 may also be referred to as a radio headend, intelligent radio headend, remote radio headend (RRH), remote radio unit (RRU), or transmit / receive point (TRP). One or more components of network entity 105 in a decomposed RAN architecture may be co-located, or one or more components of network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 in a decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0065] The functional splitting among CU 160, DU 165, and RU 170 is flexible and can support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, and any combination thereof) are performed at CU 160, DU 165, or RU 170. For example, a protocol stack functional splitting can be used between CU 160 and DU 165, allowing CU 160 to support one or more layers of the protocol stack, and DU 165 to support one or more different layers of the protocol stack. In some examples, CU 160 can host higher protocol layer (e.g., Layer 3 (L3), Layer 2 (L2)) functionalities and signaling (e.g., Radio Resource Control (RRC), Serving Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP)). CU 160 can connect to one or more DU 165 or RU 170, and one or more DU 165 or RU 170 can host lower protocol layers, such as Layer 1 (L1) (e.g., Physical (PHY) layer) or L2 (e.g., Radio Link Control (RLC) layer, Medium Access Control (MAC) layer) functionality and signaling, and each can be at least partially controlled by CU 160. Additionally or alternatively, a protocol stack functional split can be employed between DU 165 and RU 170, such that DU 165 can support one or more layers of the protocol stack, and RU 170 can support one or more different layers of the protocol stack. DU 165 can support one or more different cells (e.g., via one or more RU 170). In some cases, functional decomposition between CU 160 and DU 165, or between DU 165 and RU 170, can be performed within the protocol layer (e.g., some functions of the protocol layer can be performed by one of CU 160, DU 165, or RU 170, while other functions of the protocol layer can be performed by different of CU 160, DU 165, or RU 170). CU 160 can be further functionally decomposed into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 160 can be connected to one or more DU 165 via midhaul communication link 162 (e.g., F1, F1-c, F1-u), and DU 165 can be connected to one or more RU 170 via fronthaul communication link 168 (e.g., open fronthaul (FH) interface). In some examples, the midhaul communication link 162 or the fronthaul communication link 168 may be implemented based on the interfaces (e.g., channels) between the layers of the protocol stack, which are supported by the corresponding network entities 105 communicating via such communication links.

[0066] In some wireless communication systems (e.g., wireless communication system 100), the infrastructure and spectrum resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture (e.g., to core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB node 104) may be partially controlled by each other. One or more IAB nodes 104 may be referred to as donor entities or IAB donors. One or more DU 165s or one or more RU 170s may be partially controlled by one or more CU 160s associated with donor network entity 105 (e.g., donor base station 140). One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB node 104) via supported access and backhaul links (e.g., backhaul communication link 120). IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a DU 165 of a coupled IAB donor. The IAB-MT may include a separate set of antennas for relaying communication with UE 115, or may share the same antennas (e.g., those of RU 170) for access to IAB node 104 via DU 165 of IAB node 104. (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, IAB node 104 may include a DU 165 that supports communication links with additional entities (e.g., IAB node 104, UE 115) within a relay chain or configuration (e.g., downstream) of the access network. In such cases, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of IAB node 104) may be configured to operate according to the techniques described herein.

[0067] For example, the access network (AN) or RAN may include communication between an access node (e.g., an IAB donor), IAB node 104, and one or more UEs 115. The IAB donor may facilitate connectivity between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130). That is, an IAB donor may refer to a RAN node having a wired or wireless connection to the core network 130. The IAB donor may include a CU 160 and at least one DU 165 (e.g., and RU 170), where the CU 160 may communicate with the core network 130 via an interface (e.g., a backhaul link). The IAB donor and IAB node 104 may communicate via an F1 interface according to a protocol defining the signaling messages (e.g., the F1 AP protocol). Additionally or alternatively, the CU 160 may communicate with the core network via an interface (which may be part of a backhaul link) and may communicate with other CU 160s (e.g., CU 160 associated with an alternative IAB donor) via an Xn-C interface (which may be part of a backhaul link).

[0068] IAB node 104 may refer to a RAN node that provides IAB functionality (e.g., access for UE 115, radio self-backhaul capability, etc.). DU 165 may act as a distributed scheduling node toward child nodes associated with IAB node 104, and IAB-MT may act as a scheduled node toward a parent node associated with IAB node 104. That is, an IAB donor may be referred to as a parent node communicating with one or more child nodes (e.g., an IAB donor may relay UE transmissions through one or more other IAB nodes 104). Additionally or alternatively, depending on the AN's relay chain or configuration, IAB node 104 may also be referred to as a parent or child node of other IAB nodes 104. Therefore, the IAB-MT entity of IAB node 104 can provide a Uu interface for child IAB node 104 to receive signaling from parent IAB node 104, and the DU interface (e.g., DU 165) can provide a Uu interface for parent IAB node 104 to send signaling notifications to child IAB node 104 or UE 115.

[0069] For example, IAB node 104 may be referred to as a parent node supporting communication to child IAB nodes, or as a child IAB node associated with an IAB donor, or both. An IAB donor may include a CU 160 having a wired or wireless connection to core network 130 (e.g., backhaul communication link 120) and may act as a parent node of IAB node 104. For example, the IAB donor's DU 165 may relay transmissions to UE 115 via IAB node 104, or may signal transmissions directly to UE 115, or both. The IAB donor's CU 160 may signal the establishment of a communication link to IAB node 104 via an F1 interface, and IAB node 104 may schedule transmissions via DU 165 (e.g., transmissions relayed from the IAB donor to UE 115). That is, data may be relayed to and from IAB node 104 via signaling through the NR Uu interface of the MT to IAB node 104. Communication with IAB node 104 can be scheduled by DU 165 of the IAB donor, and communication with IAB node 104 can be scheduled by DU 165 of IAB node 104.

[0070] In the context of applying the techniques described herein to a decomposed RAN architecture, one or more components of the decomposed RAN architecture may be configured to support techniques for additional condition indications for model-based monitoring as described herein. For example, some operations described as being performed by UE 115 or network entity 105 (e.g., base station 140) may be additionally or alternatively performed by one or more components of the decomposed RAN architecture (e.g., IAB node 104, DU 165, CU 160, RU 170, RIC 175, SMO 180).

[0071] UE 115 may include or be referred to as a mobile device, wireless device, remote device, handheld device, or subscriber device, or any other suitable term, wherein "device" may also be referred to as a cell, station, terminal, or client, etc. UE 115 may also include or 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, UE 115 may include or be referred to as a wireless local loop (WLL) station, Internet of Things (IoT) device, Internet of Everything (IoE) device, or machine-type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0072] The UE 115 described herein can communicate with various types of devices, such as other UEs 115 that may sometimes act as relays, as well as network entities 105 and network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, relay base stations, etc. Figure 1 As shown.

[0073] UE 115 and network entity 105 can wirelessly communicate with each other via one or more communication links 125 (e.g., access links) using resources associated with one or more carriers. The term "carrier" can refer to a set of RF spectrum resources having a physical layer structure defined for supporting communication link 125. For example, a carrier for communication link 125 may include a portion of the RF spectrum band (e.g., a bandwidth portion (BWP)) 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 coordinating carrier operation, user data, or other signaling. Wireless communication system 100 may support communication with UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, UE 115 may be configured using multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation may be used in conjunction with both frequency division duplex (FDD) component carriers and time division duplex (TDD) component carriers. Communication between network entity 105 and other devices can refer to communication between these devices and any part of network entity 105 (e.g., entity, sub-entity). For example, the terms “send,” “receive,” or “communicate” when referring to network entity 105 can refer to any part of the RAN’s network entity 105 (e.g., base station 140, CU160, DU 165, RU 170) communicating with another device (e.g., directly or via one or more other network entities 105).

[0074] In some examples, such as in carrier aggregation configurations, a carrier may also have acquisition signaling or control signaling to coordinate the operation of other carriers. A carrier may be associated with a frequency channel (e.g., an Evolved Universal Mobile Telecommunications System Terrestrial Radio Access (E-UTRA) Absolute RF Channel Number (EARFCN)) and may be identified according to a channel grating used for discovery by UE 115. A carrier may operate in standalone mode, in which case initial acquisition and connection can be performed by UE 115 via that carrier, or the carrier may operate in non-standalone mode, in which case different carriers (e.g., the same or different radio access technologies) are used to anchor the connection.

[0075] The communication link 125 shown in the wireless communication system 100 may include downlink transmission (e.g., forward link transmission) from network entity 105 to UE 115, uplink transmission (e.g., return link transmission) from UE 115 to network entity 105, or both, as well as other transmission configurations. A carrier may carry downlink communication or uplink communication (e.g., in FDD mode), or may be configured to carry both downlink and uplink communication (e.g., in TDD mode).

[0076] A carrier may be associated with a specific bandwidth of the RF spectrum, and in some examples, the carrier bandwidth may be referred to as the carrier or the “system bandwidth” of the wireless communication system 100. For example, the carrier bandwidth may be one bandwidth in a set of bandwidths for a particular radio access technology (e.g., 1.4 MHz, 3 MHz, 5 MHz, 10 MHz, 15 MHz, 20 MHz, 40 MHz, or 80 MHz). Devices of the wireless communication system 100 (e.g., network entity 105, UE 115, or both) may have a hardware configuration that supports communication using a specific carrier bandwidth, or may be configured to support communication using one of the carrier bandwidths in the set of carrier bandwidths. In some examples, the wireless communication system 100 may include a network entity 105 or UE 115 that supports concurrent communication using carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 may be configured to operate using a portion (e.g., subband, BWP) or all of the carrier bandwidth.

[0077] The signal waveform transmitted via a carrier may include multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform extended OFDM (DFT-S-OFDM)). In a system employing MCM, a resource element may refer to a resource of one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be 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 decoding rate of the modulation scheme, or both), such that a relatively high number of resource elements (e.g., in the transmission duration) and a relatively high modulation scheme order may correspond to a relatively high communication rate. Wireless communication resources may refer to a combination of RF spectrum resources, temporal resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial resources may increase the data rate or data integrity used for communication with UE 115.

[0078] It can support one or more sets of parameters for a carrier, and the set of parameters may include subcarrier spacing ( (and cyclic prefix). A carrier can be divided into one or more BWPs with the same or different sets of parameters. In some examples, multiple BWPs can be used to configure UE 115. In some examples, a single BWP of a carrier can be active at a given time, and the communication of UE 115 can be constrained to one or more active BWPs.

[0079] The time interval for network entity 105 or UE 115 can be expressed as a multiple of a basic time unit, such as the sampling period. seconds, of which It can represent the supported subcarrier spacing, and This can represent the supported Discrete Fourier Transform (DFT) size. The time interval of the communication resources can be organized according to radio frames, each with a specified duration (e.g., 10 milliseconds (ms)). Each radio frame can be identified by a System Frame Number (SFN) (e.g., ranging from 0 to 1023).

[0080] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, a frame may (e.g., in the time domain) be divided into subframes, and each subframe may be further divided into a number of time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include a number of symbol periods (e.g., depending on the length of the cyclic prefix appended to each symbol period). In some wireless communication systems 100, time slots may be further divided into multiple micro-time slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., The duration of a symbol period is associated with a (number) sampling period. The duration of a symbol period can depend on the subcarrier spacing or the operating frequency band.

[0081] A subframe, time slot, micro-time slot, or symbol can be the smallest scheduling unit of the wireless communication system 100 (e.g., in the time domain) and can be referred to as a transmission time interval (TTI). In some examples, the duration of the TTI (e.g., the number of symbol periods in the TTI) can be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 can be dynamically selected (e.g., in a burst of shortened TTIs (sTTIs)).

[0082] Depending on the technology, carriers can be used to multiplex physical channels for communication. For example, one or more of Time Division Multiplexing (TDM), Frequency Division Multiplexing (FDM), or hybrid TDM-FDM techniques can be used to multiplex physical control channels and physical data channels for signaling via a downlink carrier. The control region (e.g., control resource set (CORESET)) of the physical control channel can be defined by a set of symbol periods and can extend across the system bandwidth of the carrier or a subset of that bandwidth. One or more control regions (e.g., CORESET) can be configured for a set of UEs 115. For example, one or more UEs in UE 115 can monitor or search for control regions to obtain control information based on one or more search space sets, and each search space set can include one or more control channel candidates in one or more aggregation levels arranged in a concatenated manner. The aggregation level of control channel candidates can refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space set may include: a common search space set configured to transmit control information to multiple UEs 115, and a UE-specific search space set used to transmit control information to a specific UE 115.

[0083] In some examples, network entity 105 (e.g., base station 140, RU 170) may be mobile, and thus provide communication coverage to mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 use the same or different radio access technologies to provide coverage for various coverage areas 110.

[0084] Wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication, or various combinations thereof. For example, wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable or low-latency or critical functions. Ultra-reliable communication may include private or group communication and may be supported by one or more services, such as push-to-talk, video, or data. Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general business applications. The terms “ultra-reliable,” “low-latency,” and “ultra-reliable low-latency” are used interchangeably herein.

[0085] In some examples, UE 115 may be configured to support direct communication with other UE 115s via device-to-device (D2D) communication link 135 (e.g., according to peer-to-peer (P2P), D2D, or sidelink protocols). In some examples, one or more UE 115s performing D2D communication in a group may be within the coverage area 110 of network entity 105 (e.g., base station 140, RU 170), which may support aspects of such D2D communication configured (e.g., scheduled by network entity 105). In some examples, one or more UE 115s in such a group may be outside the coverage area 110 of network entity 105, or may otherwise be unable or not configured to receive transmissions from network entity 105. In some examples, the group of UE 115s communicating via D2D communication may support a one-to-many (1:M) system, where each UE 115 transmits to each of the other UE 115s in the group. In some examples, network entity 105 may facilitate the scheduling of resources used for D2D communication. In other examples, D2D communication may be performed between UEs 115 without involving network entity 105.

[0086] In some systems, the D2D communication link 135 may be an example of a communication channel (such as a sidelink communication channel) between vehicles (e.g., UE 115). In some examples, vehicles may communicate using vehicle-to-vehicle (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination of these. Vehicles may signal information related to traffic conditions, signaling, weather, safety, emergencies, or any other information relevant to the V2X system. In some examples, vehicles in a V2X system may communicate with roadside infrastructure (such as roadside units), or communicate with the network via one or more network nodes (e.g., network entity 105, base station 140, RU 170) using vehicle-to-network (V2N) communication, or both.

[0087] Core network 130 provides user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. Core network 130 may be an evolved packet core (EPC) or a 5G core (5GC), and may include at least one control plane entity (e.g., a Mobility Management Entity (MME), Access and Mobility Management Function (AMF)) for managing access and mobility, and at least one user plane entity (e.g., a Serving Gateway (S-GW), Packet Data Network (PDN) Gateway (P-GW), or User Plane Function (UPF)) for routing packets or interconnecting to external networks. The control plane entity manages non-access stratum (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by network entity 105 (e.g., base station 140) associated with core network 130. User IP packets can be delivered through user plane entities, which provide IP address allocation and other functions. User plane entities may connect to one or more network operator IP services 150. IP services 150 may include access to the Internet, intranets, IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0088] Wireless communication system 100 can operate using one or more frequency bands in the range of 300 MHz to 300 GHz. Generally, the area from 300 MHz to 3 GHz is referred to as the Ultra High Frequency (UHF) band or decimeter band because the wavelength range is approximately one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features (which may be referred to as clusters), but these waves are sufficient to penetrate structures so that macrocells can provide service to UE 115 located indoors. Compared to communication using smaller frequencies and longer wavelengths in the High Frequency (HF) or Very High Frequency (VHF) portions of the spectrum below 300 MHz, communication using UHF waves can be associated with smaller antennas and shorter ranges (e.g., less than 100 km).

[0089] Wireless communication system 100 may utilize licensed and unlicensed RF spectrum bands. For example, wireless communication system 100 may use unlicensed frequency bands (such as the 5 GHz Industrial, Scientific, and Medical (ISM) band) to employ Licensed Assisted Access (LAA), unlicensed LTE (LTE-U) radio access technology, or NR technology. When operating with unlicensed RF spectrum bands, devices such as network entity 105 and UE 115 may employ carrier sensing for collision detection and avoidance. In some examples, operation using unlicensed frequency bands may be combined with component carriers operating with licensed frequency bands based on carrier aggregation configurations (e.g., LAA). Operation using unlicensed spectrum may include downlink transmission, uplink transmission, P2P transmission, or D2D transmission, etc.

[0090] Network entity 105 (e.g., base station 140, RU 170) or UE 115 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 network entity 105 or UE 115 may be located within one or more antenna arrays or antenna panels, which can support MIMO operation or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly such as an antenna tower. In some examples, the antennas or antenna arrays associated with network entity 105 may be located at different geographical locations. Network entity 105 may include an antenna array having a collection of multiple rows and columns of antenna ports that network entity 105 can use to support beamforming for communication with UE 115. Similarly, UE 115 may include one or more antenna arrays that can support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals transmitted via the antenna ports.

[0091] Network entity 105 or UE 115 can use MIMO communication to leverage multipath signal propagation and improve spectral efficiency by transmitting or receiving multiple signals via different spatial layers. This technique is known as spatial multiplexing. The multiple signals can be transmitted, for example, by a transmitting device via different antennas or different combinations of antennas. Similarly, the multiple signals can be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals can be referred to as a separate spatial stream and can carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers can be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include: single-user MIMO (SU-MIMO), where multiple spatial layers are transmitted to the same receiving device; and multi-user MIMO (MU-MIMO), where multiple spatial layers are transmitted to multiple devices.

[0092] Beamforming (also known as spatial filtering, directional transmission, or directional reception) is a signal processing technique that can be used at a transmitting or receiving device (e.g., network entity 105, UE 115) to shape or guide an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting and receiving devices. Beamforming can be achieved by combining signals transmitted via antenna elements of an antenna array such that some signals propagating along a specific orientation relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to the signals transmitted via the antenna elements may include applying amplitude shifts, phase shifts, or both to the signals carried via the antenna elements associated with the device. The adjustments associated with each of these antenna elements may be defined by a beamforming weight set associated with a specific orientation (e.g., relative to the antenna array of the transmitting or receiving device or relative to some other orientation).

[0093] Network entity 105 or UE 115 may use beam scanning technology as part of beamforming operations. For example, network entity 105 (e.g., base station 140, RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted multiple times by network entity 105 along different directions. For example, network entity 105 may transmit signals according to different beamforming weight sets associated with different transmission directions. Transmission along different beam directions may be used to identify (e.g., by a transmitting device (such as network entity 105) or by a receiving device (such as UE 115)) the beam direction for later transmission or reception by network entity 105.

[0094] Some signals (such as data signals associated with a specific receiving device) may be transmitted by a transmitting device (e.g., transmitting network entity 105, transmitting UE 115) along a single beam direction (e.g., the direction associated with the receiving device (such as receiving network entity 105 or receiving UE 115). In some examples, the beam direction associated with transmission along a single beam direction may be determined based on the signals transmitted along one or more beam directions. For example, UE 115 may receive one or more signals transmitted by network entity 105 along different directions and may report to network entity 105 an indication of signals received by UE 115 with the highest signal quality or other acceptable signal quality.

[0095] In some examples, transmissions performed by a device (e.g., network entity 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital pre-decoding or beamforming to generate a combined beam for transmission (e.g., from network entity 105 to UE 115). UE 115 may report feedback indicating pre-decoding weights for one or more beam directions, and this feedback may correspond to a set of beams configured across the system bandwidth or one or more sub-bands. Network entity 105 may transmit reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)) that may or may not be pre-decoded. UE 115 may provide feedback for beam selection, which may be a pre-decoding matrix indicator (PMI) or codebook-based feedback (e.g., multi-panel codebook, linear combination codebook, port selection codebook). Although these techniques are described with reference to signals transmitted by network entity 105 (e.g., base station 140, RU 170) along one or more directions, UE 115 may use similar techniques to transmit signals multiple times along different directions (e.g., to identify the beam direction used by UE 115 for subsequent transmission or reception), or to transmit signals along a single direction (e.g., to transmit data to a receiving device).

[0096] A receiving device (e.g., UE 115) may perform reception operations according to multiple reception configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a transmitting device (e.g., network entity 105). For example, the receiving device may perform reception according to multiple reception directions by: receiving via different antenna subarrays; processing the received signal according to different antenna subarrays; receiving according to different sets of reception beamforming weights (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of the antenna array; or processing the received signal according to different sets of reception beamforming weights applied to signals received at multiple antenna elements of the antenna array. Any of these operations may be referred to as “listening” according to different reception configurations or reception directions. In some examples, the receiving device may use a single reception configuration to receive along a single beam direction (e.g., when a data signal is received). The single receiver configuration can be aligned along a beam direction determined by listening based on different receiver configuration directions (e.g., based on the beam direction determined to have the highest signal strength, highest SNR, or other acceptable signal quality based on listening to multiple beam directions).

[0097] The wireless communication system 100 can be a packet-based network operating according to a layered protocol stack. In the user plane, communication at the bearer or PDCP layer can be IP-based. The RLC layer performs packet segmentation and reassembly for transmission via logical channels. The MAC layer performs priority processing and multiplexing of logical channels to transport channels. The MAC layer can also implement error detection, error correction, or both to support retransmission and improve link efficiency. In the control plane, the RRC layer can provide the establishment, configuration, and maintenance of RRC connections between the UE 115 and network entity 105 or core network 130 supporting user plane data radio bearers. The PHY layer maps transport channels to physical channels.

[0098] UE 115 and network entity 105 can support data retransmission to increase the likelihood of successful data reception. Hybrid Automatic Repeat Request (HARQ) feedback is a technique used to increase the likelihood of correctly receiving data via communication links (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using Cyclic Redundancy Check (CRC)), forward error correction (FEC), and retransmission (e.g., Automatic Repeat Request (ARQ)). HARQ can improve throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, the device may support same-slot HARQ feedback, in which case the device can provide HARQ feedback in a specific time slot for data received via a previous symbol in that time slot. In some other examples, the device may provide HARQ feedback in subsequent time slots or according to a different time interval.

[0099] In some respects, the corresponding wireless devices of the wireless communication system 100 (e.g., UE 115, network entity 105, IAB node, etc.) may support techniques for identifying, defining, and updating machine learning models used to perform various inferences or predictions within the wireless communication system 100. Specifically, the wireless communication system 100 may support signaling and configuration that enables the wireless devices to: (1) initialize and define machine learning models to be used for inferences or predictions in a particular set of conditions, and (2) update the machine learning models to apply them to new or additional sets of conditions.

[0100] For example, UE 115 of wireless communication system 100 can test different machine learning models for inference or prediction while communicating with network entities. In this example, UE 115 or network entity 105 can determine whether the model is useful or accurate in making inference or prediction, and thus define a model ID for the machine learning model, making it referable and usable for a specific set of conditions in the future. Continuing with the same example, a wireless device can be configured to use a machine learning model for a specific set of conditions (e.g., RRC configuration, SNR, UE speed, line-of-sight, etc.) that has previously been trained or used for that specific set of conditions. In such cases, by using the model, the wireless device (e.g., UE 115, network entity 105) can determine that the model can also be used for inference or prediction for additional conditions. In such cases, the wireless device can send signaling to other wireless devices to update the metadata associated with the model, making the model usable in the case of the additional conditions, thereby extending the use of the model to other conditions or situations. In this respect, the applicability of the model to different additional conditions can be crowdsourced across different wireless devices within the network.

[0101] The techniques described herein facilitate more efficient identification of machine learning models that can be used to perform inference or prediction within wireless communication systems. By enhancing the ability of wireless devices to identify and define machine learning models (e.g., assign them model IDs), the techniques described herein enable wireless devices to distribute information associated with the identified models throughout the network. This leads to more general use of the model for inference or prediction, and consequently, more efficient and reliable wireless communication. Furthermore, the techniques described herein enable wireless devices to efficiently update previously trained machine learning models to apply them to new sets of additional situations not initially targeted by these models during training. Therefore, aspects of this disclosure enable machine learning models to be extended to additional use cases and scenarios (e.g., additional situations), thereby increasing the use of the model and preventing the need to train additional models for additional situations.

[0102] Figure 2 Examples of wireless communication systems 200 supporting techniques for additional condition indications based on model monitoring, according to one or more aspects of this disclosure, are shown. In some examples, aspects of wireless communication system 200 may implement, or be implemented by, aspects of wireless communication system 100. Specifically, wireless communication system 200 may support techniques for identifying, defining, and updating machine learning models used to perform various inferences or predictions within wireless communication system 100.

[0103] Wireless communication system 200 may include UE 115-a and network entity 105-a, which may be examples of wireless devices as described herein. In some aspects, UE 115-a and network entity 105-a may communicate with each other using communication link 205, which may be an example of an NR or LTE link between corresponding devices, a side link (e.g., a PC5 link), etc. In some cases, communication link 205 may include an example of an access link (e.g., a Uu link), which may include a bidirectional link that enables both uplink and downlink communication. For example, UE 115-a may use communication link 205 to send uplink signals, such as uplink control signals or uplink data signals, to one or more components of network entity 105-a, and one or more components of network entity 105-a may use communication link 205 to send downlink signals, such as downlink control signals or downlink data signals, to UE 115-a.

[0104] As previously noted, some wireless devices (e.g., UE 115-a, network entity 105-a) can be configured to store and use machine learning models 210 (such as neural network models) to make various inferences or predictions related to wireless communication. Figure 2 As shown, machine learning model 210 can receive measurements as model input 215 and perform inferences or predictions as model output 220. Machine learning model 210 can be used to infer or predict channel conditions (e.g., for channel state feedback), beam prediction, UE location, etc. For example, UE 115-a can be configured to perform measurements on reference signals received from network entity 105-a, and the measurements can be input into a machine learning algorithm (e.g., machine learning model 210) to predict the relative quality of Rx beams applied to future communications.

[0105] In this regard, one or more model inputs 215 may include, but are not limited to: measurements performed by UE 115-a or network entity 105-a, the previous location of UE 115-a (e.g., historical location data), previous channel conditions between the respective devices, previous beams used to transmit or receive signals at the respective devices, etc. One or more model outputs 220 may include various inferences or predictions performed by machine learning model 210, including channel state information, channel quality information, beam quality, beam selection, UE location, etc.

[0106] One or more machine learning models 210 may be stored in the memory of the corresponding device (e.g., network entity 105-a, UE 115-a), retrieved from a remote database, etc. One or more machine learning models 210 used within the wireless communication system 200 can be generated or trained in various ways. For example, in some cases, the wireless device may test different machine learning models 210 in a trial-and-error manner. However, such trial-and-error techniques can be very time-consuming. Furthermore, if a wireless device discovers that a machine learning model 210 can be used to perform various inferences (e.g., model output 220), the machine learning model 210 may only be used by the corresponding wireless device that made that discovery and may not be usable by other wireless devices within the network.

[0107] In other cases, the machine learning model 210 can be trained to make specific inferences (e.g., model output 220) for a specific training or test dataset (which may be referred to herein as situation 225). For example, the model can be trained to perform beam prediction when UE 115-a and network entity 105-a are in direct line of sight and when the SNR is above a certain threshold. Therefore, the model can be used to perform beam prediction in very specific situations or sets of situations (e.g., direct line of sight and SNR above a threshold). In this example, UE 115-a can use the measurement as model input 215, use direct line of sight and low SNR as situation 225, and can perform beam inference or beam prediction as model output 220. However, the model can be additionally or alternatively used for other situations or situations 225 that are unknown at the time of training (e.g., for situations that are out of distribution relative to the training or test dataset). For example, the model may also be used for non-direct line-of-sight situations or for situations where the SNR is not above a threshold.

[0108] In other words, if the input data sample at inference time is similar to the data sample used to train the machine learning model 210, then the machine learning model 210 (e.g., an artificial intelligence (AI) model) can be expected to provide good inference accuracy (e.g., accurate inference or prediction). Specifically, the machine learning model 210 can only be expected to be accurate or reliable if the distribution of the test dataset used for inference or prediction is within the distribution of the training dataset. Out-of-distribution samples (e.g., use cases that fall outside the training data used to train the model) may not provide accurate inference results because the loss function is not evaluated for such samples during training optimization.

[0109] In other words, the machine learning model 210 can only be expected to be accurate or reliable if it is used under the same (or similar) model inputs 215 and conditions 225 as those used to train the model. For example, if the machine learning model 210 is trained to infer or predict the location of UE 115-a when UE 115-a is outdoors with high SNR (e.g., condition 225 is outdoors and high SNR), then the machine learning model 210 may not be expected to be reliable or accurate when UE 115-a is indoors with low SNR.

[0110] The distribution of the training dataset (e.g., the data used to train machine learning model 210) can be implicitly described in the form of certain criteria associated with the collection of the training data. For example, the data collected when UE 115-a is outdoors may have a specific distribution that may differ from the distribution of the data collected when UE 115-a is indoors (therefore, the model may be inaccurate when UE 115-a is indoors, since the model is only trained on the data collected when UE 115-a is outdoors).

[0111] The data or criteria used to train the machine learning model 210 (e.g., condition 225) can be network-side (e.g., network settings, RRC configuration) or UE-side (e.g., UE speed, SNR, UE location). Furthermore, other data or criteria used to train the machine learning model 210 may be independent of the corresponding device, such as time of day, ambient temperature, weather conditions, etc. In other words, the machine learning model 210 can be trained on a specific set of criteria that can be associated with UE 115-a, network entity 105-a, external factors, or any combination thereof, to make predictions or inferences. For example, a first machine learning model 210 can be trained or used for a first RRC configuration and when UE 115-a is moving below 30 mph to infer, predict, or estimate channel conditions. In contrast, a second machine learning model 210 can be trained or used for a specific set of network settings and only in the morning between 6:00 am and 12:00 pm to infer, predict, or estimate channel conditions.

[0112] For the purposes of this disclosure, the term "condition 225" may be used to refer to the criteria that UE 115-a can report via capability signaling (e.g., capability report) in connection with training or using machine learning model 210. In contrast, the term "additional condition 230" may be used to refer to other criteria associated with training or using machine learning model 210 that are not included in the capability report. For example, the number of communication layers supported by UE 115-a or the number of antenna elements at UE 115-a may be reported via UE capability signaling and therefore may be referred to as "condition 225" in connection with machine learning model 210 (e.g., a first model for a single communication layer and a second model for multiple communication layers). In contrast, UE speed or location is not reported via UE capability signaling and therefore may be referred to as "additional condition 230".

[0113] In other words, in the context of AI or machine learning model 210, the term “additional condition 230” can be used to refer to any aspect of the training assumptions of machine learning model 210, but these aspects are not part of the reporting UE capability for features that enable AI machine learning. Additional condition 230 can be divided into two categories: (1) network-side additional condition and (2) UE-side additional condition.

[0114] Wireless communication systems can utilize various techniques to ensure that the machine learning model 210 is used in the correct context (e.g., for the expected condition 225). For example, in the context of a UE-side model (e.g., the machine learning model 210 implemented by UE 115-a to perform inference or prediction), to ensure consistency between training and inference regarding the network-side additional condition 230 (if identified), network entity 105-a may explicitly (to UE 115-a) indicate the machine learning model 210 to be used by UE 115-a to achieve alignment between the network side and the UE side on the network-side additional condition 230. In this example, network entity 105-a may know (e.g., be aware of) the condition 225 and the additional condition 230 used to train the machine learning model 210 and may assign or indicate a model ID to UE 115-a.

[0115] In other cases, network entity 105-a may train machine learning model 210 and transmit (e.g., instruct, send) that model to UE 115-a. In this example, the model may be trained for a specific additional condition 230. As another example, information or instructions associated with network-side additional conditions 230 may be provided to UE 115-a (so that UE 115-a can identify network-side additional conditions 230 that are available or useful for a given machine learning model 210). In yet another few cases, consistency in model usage may be aided by monitoring (e.g., UE 115-a or network entity 105-a monitors the performance or functionality of UE-side candidate models to select a model or functionality). These methods for ensuring consistency regarding network-side additional conditions 230 between training and inference exhibit some overlap, and wireless communication systems may utilize additional or alternative methods to ensure consistency in the use of machine learning model 210 across devices.

[0116] In some cases, the criteria or conditions 225 used to train the machine learning model 210 may not be fully known or determined at the time of model training. In such cases, it may be unclear which conditions 225 the machine learning model 210 can actually be used in. For example, a training dataset for training the machine learning model 210 may have been collected under a specific network setting A (e.g., condition A, first condition 225). However, if the data distribution remains the same, or if the data distribution under setting B is covered by the data distribution under setting A, the same machine learning model 210 may also work well under different settings B (e.g., condition B, second condition 225). In such cases, the wireless device may only utilize the model under setting A and may not be aware that the model is also useful under setting B.

[0117] For example, machine learning model 210 can be used to infer channel conditions in the morning (e.g., condition 225 or the training dataset is morning time) using a specific set of network settings (which may be based on traffic, the number of UEs 115, etc.). In this example, the wireless device may only use the model in the morning because the model is only trained on data collected during the morning time period. However, the model may also be useful in the evening when network entity 105-a uses the same or similar set of network settings. Therefore, even if the test dataset (e.g., communications in the evening) is different from the training dataset (e.g., communications in the morning), the model can still be useful in the evening when using the same or similar set of network settings.

[0118] As previously described herein, several methods exist to ensure that the machine learning model 210 selected for performing inference or prediction is well-suited to the current situation in which the model will be used (e.g., ensuring that the additional situation 230 at the inference time is consistent with the distribution of the training dataset). In some cases, a model identification process can be used to enable network entity 105-a and UE 115-a to reach a common understanding of various aspects relating to the machine learning model 210 to be used, including the criteria applicable to model use, wherein network entity 105-a may then indicate to UE 115-a the model ID of the machine learning model 210 that is well-suited to the current situation (e.g., well-suited to current situation 225 and additional situation 230). In additional or alternative implementations, if network entity 105-a knows the criteria assumed when training the machine learning model 210, network entity 105-a may select a model suitable for the current situation and pass that model to UE 115-a, or indicate the assumed criteria to UE 115-a to allow UE 115-a to select a model.

[0119] However, such implementations may not be effective for cases where the model's criteria are not fully known at training time (e.g., situation 225, additional situation 230). In such cases, achieving consistency in model usage may require trial-and-error operations based on model monitoring methods, which could lead to increased latency or control signaling overhead.

[0120] Therefore, aspects of this disclosure relate to techniques for identifying, defining, and updating machine learning models 210 used to perform various inferences or predictions within a wireless communication system 200. Specifically, aspects of this disclosure relate to signaling and configuration that enables a wireless device to: (1) initialize and define machine learning models 210 for inferences or predictions in a particular set of conditions 225, and (2) update machine learning models 210 to apply them to new or additional conditions 230.

[0121] refer to Figure 2 UE 115-a can send capability signaling 235 to network entity 105-a. Capability signaling 235 can indicate various capabilities of UE 115-a. In addition, as previously described herein, capability signaling 235 can be used to indicate conditions 225 associated with UE 115-a, such as the number of communication layers supported at UE 115-a, the number of antenna elements at UE 115-a, etc.

[0122] Wireless devices in wireless communication system 200 can perform initial model identification to mark machine learning model 210 as suitable for use under (new) condition 225 or additional condition 230, which is determined based on model monitoring performed at network entity 105-a, the current UE 115-a, or by other UEs 115 in the network. In other words, the network can crowdsource initial model identification across UE 115 and other wireless devices in the network, where various wireless devices test different machine learning models 210 to determine which conditions 225 or additional conditions 230 the model can be used for.

[0123] For example, in the context of initial model identification, network entity 105-a and UE 115-a may communicate with each other via communication link 205. Through communication, the wireless device may perform model monitoring, where UE 115-a or network entity 105-a tests different machine learning models 210 for making various inferences or predictions. For example, during model monitoring, UE 115-a may perform measurements on signals received from network entity 105-a and may use these measurements as model inputs 215 to various machine learning models 210 for inferences or predictions (e.g., model outputs 220). During the model monitoring process, the wireless device may determine which conditions 225 or additional conditions 230 the machine learning models 210 are accurate, reliable, or otherwise available.

[0124] Continuing with the same example, based on the machine learning model 210 identified as usable for the set of conditions 225 or the set of additional conditions 230, UE 115-a may send a control message 240-a to network entity 105-a, wherein the control message 240-a indicates the machine learning model 210, the set of conditions 225 or the set of additional conditions 230 for that model. Thus, network entity 105-a can identify the conditions 225 or additional conditions 230 in which the machine learning model 210 functions well. Based on the received control message 240-a, network entity 105-a may assign a model ID to the machine learning model 210 and may store the machine learning model 210, the model ID, and the conditions 225 or additional conditions 230 for that model in memory (e.g., store data objects or metadata associated with the machine learning model 210).

[0125] Network entity 105-a may send control signaling 245-a to UE 115-a, wherein the control signaling indicates a model ID, a set of conditions 225 in which the model functions well, or a set of additional conditions 230. Such annotations may be included in the model metadata and may be indicated during initial model identification. Based on this determination, network entity 105-a may use conditions 225 or additional conditions 230 for lifecycle management operations, such as model selection and switching. In other words, network entity 105-a may assign a model ID to machine learning model 210, making machine learning model 210 referable and usable in the future. Based on the received control signaling 245-a, UE 115-a may assign a model ID to machine learning model 210 and may store machine learning model 210, model ID, and conditions 225 or additional conditions 230 for that model in memory (e.g., storing data objects or metadata associated with machine learning model 210).

[0126] Similar steps or processes can be used for model reidentification or updating. In the context of model reidentification, the previously identified and previously trained machine learning model 210 can be marked as suitable for use under new additional conditions 230 that are different from the additional conditions 230 that the model was trained on or indicated to target during model identification. In other words, when UE 115-a or network entity 105-a uses machine learning model 210, the radio device can identify new additional conditions 230 in which the model is accurate, reliable, or otherwise useful, and can update or re-annotate the model to be suitable for the new identified additional conditions 230. Such re-annotation can update the metadata associated with machine learning model 210 that was initially indicated during model identification. In other words, UE 115-a, network entity 105-a, or both can update the data objects or metadata used for machine learning model 210 based on the new identified additional conditions 230 suitable for the model.

[0127] New additional conditions 230 for model reidentification or reannotation can be identified based on model monitoring performed at network entity 105-a, the current UE 115-a, or other UE 115 within the network. For example, as previously described herein, network entity 105-a can use the machine learning model 210 for conditions 225 or additional conditions 230 initially identified during the model identification process, and for other additional conditions 230. In this respect, network entity 105-a can identify new additional conditions 230 that were not initially identified during model identification or training, for which the model can be accurately, reliably, or otherwise used for inference or prediction. Based on the identification of the new additional conditions 230 for the model, network entity 105-a can reidentify, reannotate, or otherwise update the data objects or metadata associated with the machine learning model 210 based on the newly identified additional conditions 230.

[0128] In this example, network entity 105-a may send control signaling 245-b to UE 115-a, where control signaling 245-b indicates additional status 230 of a newly identified identifier available in the machine learning model 210. This re-annotation may be included in the model metadata. Based on the re-annotation, network entity 105-a may use the new additional status 230 for lifecycle management operations, such as model selection and switching. Based on the received control signaling 245-b, UE 115-a may update the machine learning model 210 with the additional status 230 (e.g., update the data objects or metadata associated with the machine learning model 210). In other words, network entity 105-a and UE 115-a may update the data objects or metadata used for the machine learning model 210, making the updated (e.g., re-annotated) model available for future reference and use.

[0129] The model identification or re-identification (e.g., update, annotation) process described herein can be performed in either direction (e.g., from UE 115-a to network entity 105-a, or vice versa) for both UE-side additional conditions and network-side additional conditions 230. For example, model identification or re-identification can take the form of an indication or information about a new network-side additional condition 230 transmitted from network entity 105-a to UE 115-a, where network entity 105-a can identify new criteria in which machine learning model 210 is observed to perform well (e.g., new additional condition 230). Conversely, as previously described herein, identification or re-identification can also occur from UE 115-a to network entity 105-a in the form of a report about a new UE-side additional condition 230, where UE 115-a can identify new criteria in which machine learning model 210 is observed to perform well (e.g., new additional condition 230).

[0130] In some respects, initial model identification and model re-annotation can be implicit, without referencing any explicit signaling from the conditions of network entity 105-a. For example, UE 115-a may send a message or report to network entity 105-a indicating that UE 115-a has identified a machine learning model 210 that works well for any condition 225 or additional condition 230 currently being used by network entity 105-a. In this example, UE 115-a may not know the actual condition 225 or additional condition 230 being used by network entity 105-a, but may request model identification (e.g., assigning a model ID) so that the model can be used by network entity 105-a in future instances where the same condition 225 or additional condition 230 is used (e.g., in subsequent lifecycle management (LCM)). Therefore, the process may involve assigning a model ID or updating the model ID associated with machine learning model 210.

[0131] While much of this disclosure is described in the context of machine learning models 210 that may be known or identified at both UE 115-a and network entity 105-a, this should not be considered a limitation of the disclosure unless otherwise indicated herein. Specifically, in some cases, machine learning models 210 at UE 115-a may be transparent to the network. In other words, network entity 105-a may not know which machine learning models 210 (or how many machine learning models 210) are implemented at UE 115-a.

[0132] In such cases, in order for UE 115-a to implement a machine learning model 210 that is transparent (e.g., unknown) to network entity 105-a, the devices may alternatively exchange signaling for different functionalities. For the purposes of this disclosure, the term "functionality" may be used to refer to a configuration that can be referenced by both UE 115-a and network entity 105-a, wherein the functionality or configuration can be used by UE 115-a to implement one or more machine learning models 210. Thus, even if network entity 105-a is unaware of the actual machine learning model 210 being implemented, network entity 105-a may still be able to identify, update, and indicate the various functionalities (e.g., configurations) used by UE 115-a to implement machine learning model 210.

[0133] For example, the process for functionality identification may be similar to the process for model identification described herein. In the context of functionality identification, network entity 105-a and UE 115-a may communicate with each other via communication link 205. Through communication, the wireless device may perform functionality monitoring, where UE 115-a or network entity 105-a tests the functionality used for various inferences or predictions (e.g., for the configuration of machine learning model 210). During the functionality monitoring process, the wireless device may determine which conditions 225 or additional conditions 230 a given functionality is accurate, reliable, or otherwise available.

[0134] Continuing with the same example, based on a functionality identified as being applicable to either the set of conditions 225 or the set of additional conditions 230, UE 115-a may send a control message 240-a to network entity 105-a, wherein control message 240-a indicates the functionality, the set of conditions 225 for that functionality, or the set of additional conditions 230. Thus, network entity 105-a can identify conditions 225 or additional conditions 230 in which the functionality functions well. Based on the received control message 240-a, network entity 105-a may assign a functionality ID to the functionality and may store the functionality, the functionality ID, conditions 225 for that functionality, additional conditions 230, or combinations thereof in memory (e.g., storing data objects or metadata associated with the functionality). Network entity 105-a may send control signaling 245-a to UE 115-a, wherein control signaling indicates the functionality ID, the set of conditions 225 in which the functionality functions well, or the set of additional conditions 230. Such annotations can be included in the functionality metadata and can be indicated during initial functionality identification. Based on this determination, network entity 105-a can use condition 225 or additional condition 230 for lifecycle management operations, such as functionality selection and handover. In other words, network entity 105-a can assign a functionality ID to a functionality so that the functionality can be referenced and used in the future. Based on received control signaling 245-a, UE 115-a can assign a functionality ID to the functionality and can store the functionality, functionality ID, condition 225 for the functionality, additional condition 230, or a combination thereof in memory (e.g., store data objects or metadata associated with the functionality).

[0135] Figure 3 Examples of process flow 300 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown. In some examples, aspects of process flow 300 may implement aspects of wireless communication system 100, wireless communication system 200, or both, or be implemented by these aspects. For example, process flow 300 exemplifies signaling for initial model identification, as previously described herein.

[0136] Process flow 300 includes UE 115-b and network entity 105-b, which can be examples of wireless devices as described herein. For example, Figure 3 The UE 115-b and network entity 105-b illustrated herein may include, for example: Figure 2 Examples of UE115-a and network entity 105-a are shown in the figure.

[0137] In some examples, the operations illustrated in process flow 300 may be performed by hardware (e.g., including circuits, processing blocks, logic components, and other components), code executed by a processor (e.g., software or firmware), or any combination thereof. Alternative examples are possible, some of which may be performed in a different order than described or not at all. In some cases, steps may include additional features not mentioned below, or additional steps may be added.

[0138] As previously described in this document, wireless devices (e.g., UE 115-b, network entity 105-b) can perform... Figure 3 The initial model identifier shown is used to mark the machine learning model 210 as suitable for use under (new) condition 225 or additional condition 230, which is determined based on model monitoring performed at network entity 105-b, the current UE 115-b, or by other UEs 115 in the network. In other words, the network can crowdsource the initial model identifier across UE 115 and other wireless devices in the network, where various wireless devices test different machine learning models 210 to determine which conditions 225 or additional conditions 230 the model can be used for.

[0139] At 305, UE 115-b can send capability signaling to network entity 105-b. Capability signaling can indicate various capabilities of UE 115-b. In addition, as previously described herein, capability signaling can be used to indicate conditions associated with UE 115-b, such as the number of communication layers supported at UE 115-b, the number of antenna elements at UE 115-b, etc.

[0140] At point 310, UE 115-b and network entity 105-b can communicate with each other. That is, UE 115-b can send uplink signals or uplink messages to network entity 105-b, and network entity 105-b can send downlink signals or downlink messages to UE 115-b. The radio device can perform communication using various network-side and UE-side conditions. Furthermore, as previously described, the radio device can perform communication using various additional conditions. Additionally, the radio device can perform communication at point 310 based on sending or receiving capability signaling at point 305.

[0141] At 315, UE 115-b, network entity 105-b, or both can utilize one or more machine learning models to perform inference or prediction. In other words, the wireless device can test different machine learning models in a trial-and-error manner. The wireless device can perform inference or prediction at 315 based on sending or receiving capability signaling at 305, performing communication at 310, or both.

[0142] For example, via communication at 310, the wireless device can perform model monitoring, where UE 115-b or network entity 105-b tests different machine learning models used for various inferences or predictions. For example, during model monitoring, UE 115-b can perform measurements on signals received from network entity 105-b, and can use the measurements as model inputs to various machine learning models for inferences or predictions (e.g., model outputs).

[0143] At 320, UE 115-a, network entity 105-b, or both may identify a situation in which the machine learning model is accurate, reliable, or otherwise available (e.g., situation 225) or an additional situation (e.g., additional situation 230). In some cases, a machine learning model that can be used for one or more situations may be referred to as being applicable to one or more such situations.

[0144] At 325, if UE 115-a identifies a model that can be used for a set of conditions or an additional set of conditions, UE 115-b may send a control message (e.g., control message 240-a) to network entity 105-b, wherein the control message indicates the identified machine learning model, the set of conditions for that model, or the additional set of conditions.

[0145] At 330, network entity 105-b may assign a model ID to the machine learning model and may store the machine learning model, the model ID, or conditions or additional conditions for that model in memory (e.g., storing data objects or metadata associated with the machine learning model). Network entity 105-b may store data objects or metadata for the machine learning model at 330 based on identifying conditions or additional conditions for the model at 320, receiving control messages from UE 115-b at 325, or both.

[0146] At 335, network entity 105-b may send control signaling to UE 115-b, wherein the control signaling indicates a model ID or a set of conditions in which the model functions well or an additional set of conditions.

[0147] At 340, UE 115-b may assign a model ID to machine learning model 210 and may store machine learning model 210, model ID, condition 225 for the model, additional condition 230 or a combination thereof in memory (e.g., store data objects or metadata associated with machine learning model 210).

[0148] After identifying the model and assigning a model ID, wireless devices may be able to reference the model (e.g., via the model ID) to make inferences or predictions using the machine learning model in the future. Furthermore, in some cases, network entity 105-b or UE 115-b may be able to share the model ID with other wireless devices within the network.

[0149] Figure 4 Examples of process flow 400 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown. In some examples, aspects of process flow 400 may implement, or be implemented by, aspects of wireless communication system 100, wireless communication system 200, process flow 300, or any combination thereof. For example, process flow 300 exemplifies signaling for model updates or re-identification, as previously described herein.

[0150] Process flow 400 includes UE 115-c and network entity 105-c, which can be examples of wireless devices as described herein. For example, Figure 4 The UE 115-c and network entity 105-c illustrated herein may include, for example: Figure 2 Examples of UE115-a and network entity 105-a are shown respectively. Furthermore, Figure 4 The UE 115-c and network entity 105-c illustrated herein may include, for example: Figure 3 Examples of UE 115-b and network entity 105-b are shown in the figure.

[0151] In some examples, the operations illustrated in process flow 400 may be performed by hardware (e.g., including circuits, processing blocks, logic components, and other components), code executed by a processor (e.g., software or firmware), or any combination thereof. Alternative examples are possible, some of which may be performed in a different order than described or not at all. In some cases, steps may include additional features not mentioned below, or additional steps may be added.

[0152] In some aspects, steps in process flow 400 for updating or re-identifying a machine learning model may be performed after steps in process flow 300, during which the machine learning model was initially identified. For example, in some cases, steps 405 and 410 of process flow 400 may be identical to steps 335 and 340 of process flow 300. In this respect, process flow 400 may exemplify steps or functions for updating or re-identifying a machine learning model initially identified in process flow 300.

[0153] At 405, network entity 105-c may send control signaling to UE 115-c, wherein the control signaling indicates the model ID or the set of conditions or additional sets of conditions targeted by the machine learning model. In some cases, step 405 may be the same as step 335 from process flow 300.

[0154] At 410, UE 115-c may assign a model ID to the machine learning model and may store the machine learning model, the model ID, the conditions for that model, additional conditions, or a combination thereof in memory (e.g., store data objects or metadata associated with the machine learning model). In some cases, step 410 may be the same as step 340 from process flow 300.

[0155] At 415, UE 115-c and network entity 105-c can communicate with each other. That is, UE 115-c can send uplink signals or uplink messages to network entity 105-c, and network entity 105-c can send downlink signals or downlink messages to UE 115-c. The radio device can perform communication using various network-side and UE-side conditions. Furthermore, as previously described, the radio device can perform communication using various additional conditions. Additionally, the radio device can perform communication at 415 based on receiving or sending instructions for a machine learning model at 405, storing a machine learning model at 410, or both.

[0156] At 420, UE 115-c, network entity 105-c, or both may utilize the indicated machine learning model to make inferences or predictions. In some aspects, the wireless device may use the machine learning model both for the situation or additional situation for which the model was initially identified or trained, and for new situations or additional situations. The wireless device may perform inferences or predictions at 420 based on receiving or transmitting instructions for the machine learning model at 405, storing the machine learning model at 410, performing communication at 415, or any combination thereof.

[0157] At 425, network entity 105-c can identify a new situation (e.g., situation 225) or a new additional situation (e.g., additional situation 230) in which the machine learning model is accurate, reliable or otherwise available.

[0158] At 430, network entity 105-c may update the data object (e.g., metadata) associated with the machine learning model based on (e.g., to include) new identifiers or additional conditions for the model. Network entity 105-c may store the data object or metadata for the machine learning model at 430 based on new identifiers or additional conditions for the model at 425.

[0159] At 435, network entity 105-c may send control signaling to UE 115-c, wherein the control signaling instructs UE 115-c to update the machine learning model with a newly identified condition or additional condition.

[0160] At 445, UE 115-c may update the machine learning model based on (for example, to include) conditions or additional conditions for a new identifier of the model (e.g., updating the stored data object or metadata associated with the machine learning model).

[0161] Figure 5 Examples of process flow 500 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, are shown. In some examples, aspects of process flow 400 may implement, or be implemented by, aspects of wireless communication system 100, wireless communication system 200, process flow 300, process flow 400, or any combination thereof. For example, process flow 500 exemplifies signaling for initial functional identification, as previously described herein.

[0162] Process flow 500 includes UE 115-d and network entity 105-d, which can be examples of wireless devices as described herein. For example, Figure 5 The UE 115-d and network entity 105-d illustrated herein may include, for example: Figure 2 Examples of UE115-a and network entity 105-a are shown respectively. Furthermore, Figure 5 The UE 115-d and network entity 105-d illustrated herein may include, for example: Figures 3 to 4 Examples of UE 115-b, UE 115-c, and network entities 105-b and 105-c are shown below.

[0163] In some examples, the operations illustrated in process flow 400 may be performed by hardware (e.g., including circuits, processing blocks, logic components, and other components), code executed by a processor (e.g., software or firmware), or any combination thereof. Alternative examples are possible, some of which may be performed in a different order than described or not at all. In some cases, steps may include additional features not mentioned below, or additional steps may be added.

[0164] As previously described herein, in some cases, the machine learning models used at UE 115-d may be transparent to network entity 105-d. In other words, network entity 105-d may not know which models (or how many models) can be implemented at UE 115-d. In such cases, in order for UE 115-d to implement machine learning models that are transparent (e.g., unknown) to network entity 105-d, the devices may alternatively exchange signaling for different “functionalities.” For the purposes of this disclosure, the term “functionality” can be used to refer to a configuration that can be referenced by both UE 115-d and network entity 105-d, wherein this functionality or configuration can be used by UE 115-d to implement one or more machine learning models. Therefore, even when network entity 105-d is unaware of the actual machine learning models being implemented, network entity 105-d may still be able to identify, update, and indicate the various functionalities (e.g., configurations) used by UE 115-d to implement machine learning models.

[0165] Wireless devices (e.g., UE 115-d, network entity 105-d) can perform Figure 5 The initial functionality identifiers shown are used to "mark" functionality as suitable for use in (new) or additional conditions, determined based on functionality monitoring performed at network entity 105-d, the current UE 115-d, or by other UEs 115 in the network. In other words, the network can crowdsource initial functionality identifiers across UEs 115 and other radio devices in the network, where various radio devices test different functionality to determine which conditions or additional conditions these functionality can be used in.

[0166] At point 505, UE 115-d may send capability signaling to network entity 105-d. Capability signaling may indicate various capabilities of UE 115-d. In addition, as previously described herein, capability signaling may be used to indicate conditions 225 associated with UE 115-d, such as the number of communication layers supported by UE 115-d, the number of antenna elements at UE 115-d, etc.

[0167] At point 510, UE 115-d and network entity 105-d can communicate with each other. That is, UE 115-d can send uplink signals or uplink messages to network entity 105-d, and network entity 105-d can send downlink signals or downlink messages to UE 115-d. The radio device can perform communication using various network-side and UE-side conditions. Furthermore, as previously described, the radio device can perform communication using various additional conditions. Additionally, the radio device can perform communication at point 510 based on sending or receiving capability signaling at point 505.

[0168] At 515, UE 115-d, network entity 105-d, or both, can use one or more functionalities to make inferences or predictions. In other words, the radio device can test different functionalities in a trial-and-error manner. The radio device can make inferences or predictions at 515 based on sending or receiving capability signaling at 505, performing communication at 510, or both.

[0169] For example, through communication at 510, the wireless device can perform functional monitoring, where UE 115-d or network entity 105-d tests different functionalities for various inferences or predictions. For example, during functional monitoring, UE 115-d can perform measurements on signals received from network entity 105-d, and can use the measurements as functional inputs to various functionalities for inferences or predictions (e.g., functional outputs).

[0170] At 520, UE 115-a, network entity 105-d, or both can identify a condition in which functionality is accurate, reliable, or otherwise available (e.g., condition 225) or an additional condition (e.g., additional condition 230).

[0171] At 525, if UE 115-a identifies a functionality that can be used for a set of conditions or an additional set of conditions, UE 115-d may send a control message (e.g., control message 240-a) to network entity 105-d, wherein the control message indicates the identified functionality, the set of conditions for that functionality, or the additional set of conditions.

[0172] At 530, network entity 105-d may assign a functional ID to a functionality and may store the functionality, the functional ID, or a status or additional status for that functionality in memory (e.g., store a data object or metadata associated with the functionality). Network entity 105-d may store the data object or metadata for the functionality at 530 based on identifying the status or additional status for the functionality at 520, receiving a control message from UE 115-d at 525, or both.

[0173] At 535, network entity 105-d may send control signaling to UE 115-d, wherein the control signaling indicates a functional ID or a set of conditions in which the functionality functions well or an additional set of conditions.

[0174] At 540, UE 115-d can assign a functional ID to the functionality and can store the functionality, the functional ID, or the status or additional status of the functionality in memory (e.g., store data objects or metadata associated with the functionality).

[0175] After identifying a function and assigning a function ID, a wireless device may be able to reference the function (e.g., via the function ID) to make inferences or predictions about the function in the future. Furthermore, in some cases, network entity 105-d or UE 115-d may be able to share the function ID with other wireless devices within the network.

[0176] Figure 6 A block diagram 600 illustrates a device 605 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure. Device 605 may be an example of a UE 115, network entity 105, or aspects of both, as described herein. Device 605 may include a receiver 610, a transmitter 615, and a communication manager 620. Device 605, or one or more components of device 605 (e.g., receiver 610, transmitter 615, and communication manager 620), may include at least one processor that may be coupled to at least one memory to individually or jointly support or implement the described techniques. Each of these components may communicate with each other (e.g., via one or more buses).

[0177] Receiver 610 may provide components for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to techniques for additional condition indications based on model monitoring). The information may be passed to other components of device 605. Receiver 610 may utilize a single antenna or a collection of antennas.

[0178] Transmitter 615 may provide components for transmitting signals generated by other components of device 605. For example, transmitter 615 may transmit information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to techniques for additional status indication based on model monitoring). In some examples, transmitter 615 may be co-located with receiver 610 in a transceiver module. Transmitter 615 may utilize a single antenna or a collection of multiple antennas.

[0179] The communication manager 620, receiver 610, transmitter 615, or various combinations thereof, or various components thereof, may be examples of components for performing various aspects of the techniques for providing additional condition indications based on model monitoring as described herein. For example, the communication manager 620, receiver 610, transmitter 615, or various combinations thereof, or components thereof, may be able to perform one or more of the functions described herein.

[0180] In some examples, the communication manager 620, receiver 610, transmitter 615, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). The hardware may include at least one of the following: a processor, digital signal processor (DSP), central processing unit (CPU), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, microcontroller, discrete gate or transistor logic device, discrete hardware component, or any combination thereof, configured as or otherwise individually or collectively to support components for performing the functions described herein. In some examples, at least one processor and at least one memory coupled to said at least one processor may be configured to perform one or more of the functions described herein (e.g., executing instructions stored in at least one memory individually or collectively by one or more processors).

[0181] Additionally or alternatively, the communication manager 620, receiver 610, transmitter 615, or various combinations or components thereof may be implemented in code executed by at least one processor (e.g., as communication management software or firmware). If implemented in code executed by at least one processor, the functionality of the communication manager 620, receiver 610, transmitter 615, or various combinations or components thereof may be performed by a general-purpose processor, DSP, CPU, ASIC, FPGA, microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise individually or jointly to support components for performing the functions described in this disclosure).

[0182] In some examples, the communication 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., receiving, acquiring, monitoring, outputting, transmitting). For example, the communication manager 620 may receive information from the receiver 610, transmit information to the transmitter 615, or be integrated with the receiver 610, the transmitter 615, or both to acquire information, output information, or perform various other operations as described herein.

[0183] For example, the communication manager 620 can, is configured, or is operable to support components for communicating signaling with a second wireless device, an additional wireless device, or both. The communication manager 620 can, is configured, or is operable to support components for performing one or more inferences using a machine learning model based on signaling communication. The communication manager 620 can, is configured, or is operable to support components for sending instructions to the second wireless device that the machine learning model is suitable for performing one or more inferences. The communication manager 620 can, is configured, or is operable to support components for receiving control signaling from the second wireless device, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions related to the signaling communication, wherein the control signaling indicates a model ID associated with the machine learning model, the first set of conditions associated with the machine learning model, or both.

[0184] By including or configuring a communication manager 620 according to examples as described herein, device 605 (e.g., at least one processor that controls or is otherwise coupled to receiver 610, transmitter 615, communication manager 620, or a combination thereof) can support techniques for facilitating more efficient identification of machine learning models that can be used to perform inference or prediction within a wireless communication system. By enhancing the ability of wireless devices to identify and define machine learning models (e.g., assign model IDs), the techniques described herein enable wireless devices to distribute information associated with the identified model throughout the network, leading to more general use of the model for inference or prediction, and thus more efficient and reliable wireless communication. Furthermore, the techniques described herein enable wireless devices to efficiently update previously trained machine learning models to apply them to new sets of additional situations not initially targeted by these models during training. Therefore, aspects of this disclosure enable machine learning models to be extended to additional use cases and scenarios (e.g., additional situations), thereby increasing the use of the model and preventing the need to train additional models for additional situations.

[0185] Figure 7 A block diagram 700 of a device 705 supporting techniques for additional condition indication based on model monitoring, according to one or more aspects of this disclosure, is shown. Device 705 may be an example of aspects of device 605, UE 115, or network entity 105 as described herein. Device 705 may include a receiver 710, a transmitter 715, and a communication manager 720. Device 705, or one or more components of device 705 (e.g., receiver 710, transmitter 715, and communication manager 720), may include at least one processor that can be coupled to at least one memory to support the described techniques. Each of these components may communicate with each other (e.g., via one or more buses).

[0186] Receiver 710 may provide components for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to techniques for additional condition indications based on model monitoring). The information may be transmitted to other components of device 705. Receiver 710 may utilize a single antenna or a collection of antennas.

[0187] Transmitter 715 may provide components for transmitting signals generated by other components of device 705. For example, transmitter 715 may transmit information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels, data channels, information channels related to techniques for additional status indication based on model monitoring). In some examples, transmitter 715 may be co-located with receiver 710 in a transceiver module. Transmitter 715 may utilize a single antenna or a collection of multiple antennas.

[0188] Device 705 or its various components may be examples of parts for performing various aspects of techniques for providing additional condition indications based on model monitoring as described herein. For example, communication manager 720 may include signaling manager 725, machine learning model manager 730, control signaling manager 735, or any combination thereof. Communication manager 720 may be an example of aspects of communication manager 620 as described herein. In some examples, communication manager 720 or its various components may be configured to use or otherwise cooperate with receiver 710, transmitter 715, or both to perform various operations (e.g., receiving, acquiring, monitoring, outputting, transmitting). For example, communication manager 720 may receive information from receiver 710, transmit information to transmitter 715, or be integrated in combination with receiver 710, transmitter 715, or both to acquire information, output information, or perform various other operations as described herein.

[0189] Signaling manager 725 is capable of, configured to, or operable to support components for communicating signaling with a second wireless device, an additional wireless device, or both. Machine learning model manager 730 is capable of, configured to, or operable to support components for performing one or more inferences using a machine learning model based on signaling communication. Signaling manager 725 is capable of, configured to, or operable to support components for sending instructions to the second wireless device that the machine learning model is suitable for performing one or more inferences. Control signaling manager 735 is capable of, configured to, or operable to support components for receiving control signaling from the second wireless device, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions related to the signaling communication, wherein the control signaling indicates a model ID associated with the machine learning model, a first set of conditions associated with the machine learning model, or both.

[0190] Figure 8 A block diagram 800 illustrates a communication manager 820 supporting techniques for additional condition indications based on model monitoring, according to one or more aspects of this disclosure. The communication manager 820 may be an example of aspects of the communication manager 620, communication manager 720, or both as described herein. The communication manager 820 or its various components may be examples of parts for performing various aspects of the techniques for additional condition indications based on model monitoring, as described herein. For example, the communication manager 820 may include a signaling manager 825, a machine learning model manager 830, a control signaling manager 835, a data object manager 840, a capability signaling manager 845, or any combination thereof. Each of these components, or its components or sub-components (e.g., one or more processors, one or more memories), may communicate directly or indirectly with each other (e.g., via one or more buses).

[0191] Signaling manager 825 is capable of, configured to, or operable to support components for communicating signaling with a second wireless device, an additional wireless device, or both. Machine learning model manager 830 is capable of, configured to, or operable to support components for signaling-based communication, using a machine learning model to perform one or more inferences. In some examples, signaling manager 825 is capable of, configured to, or operable to support components for sending instructions to a second wireless device that the machine learning model is suitable for performing one or more inferences. Control signaling manager 835 is capable of, configured to, or operable to support components for receiving control signaling from a second wireless device, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions related to the signaling communication, wherein the control signaling indicates a model ID associated with the machine learning model, a first set of conditions associated with the machine learning model, or both.

[0192] In some examples, the data object manager 840 is capable of, configured to, or operable to support components for storing data objects that associate a machine learning model with a model ID, a first set of conditions, or both, based on received control signaling. In some examples, the control signaling manager 835 is capable of, configured to, or operable to support components for receiving additional control signaling from a second wireless device indicating a model ID, a first set of conditions, or both. In some examples, the machine learning model manager 830 is capable of, configured to, or operable to support components for performing one or more additional inferences using a machine learning model based on stored data objects and received additional control signaling.

[0193] In some examples, the data object manager 840 is capable of, configured to, or operable to support components for storing data objects that associate a machine learning model with a model ID, a first set of conditions, or both, based on received control signaling. In some examples, the signaling manager 825 is capable of, configured to, or operable to support components for identifying that a second wireless device will communicate according to the first set of conditions. In some examples, the machine learning model manager 830 is capable of, configured to, or operable to support components for performing one or more additional inferences using a machine learning model based on stored data objects and identification that a second wireless device is communicating according to the first set of conditions.

[0194] In some examples, the capability signaling manager 845 is capable of, configured to, or able to operate to support components for sending capability signaling to a second wireless device that indicates a second set of conditions used by the first wireless device to communicate signaling, wherein one or more inferences are associated with the second set of conditions.

[0195] In some examples, control signaling instructs the machine learning model to be used in communications associated with a second set of conditions.

[0196] In some examples, the second set of conditions includes the number of communication layers supported at the first wireless device, the number of antennas at the first wireless device, or both.

[0197] In some examples, the signaling manager 825 is capable of, configured to, or operable to support components for communicating additional signaling with a second wireless device, an additional wireless device, or both, based on an additional set of conditions associated with a first wireless device. In some examples, the machine learning model manager 830 is capable of, configured to, or operable to support components for using a machine learning model to perform one or more additional inferences based on the additional signaling communicated according to the additional set of conditions. In some examples, the signaling manager 825 is capable of, configured to, or operable to support components for sending a control message to the second wireless device instructing that the machine learning model is suitable for performing one or more additional inferences associated with the additional set of conditions.

[0198] In some examples, the control signaling manager 835 is capable of, configured to, or operable to support components for receiving additional control signaling from a second wireless device that indicates the association of the machine learning model with an additional set of conditions. In some examples, the data object manager 840 is capable of, configured to, or operable to support components for updating the data object associated with the machine learning model based on the received additional control signaling to include information related to the association between the machine learning model and the additional set of conditions.

[0199] In some examples, the set of additional conditions includes the speed of the first wireless device, signal quality metrics of the wireless communications received by the first wireless device, network-based additional conditions, or any combination thereof.

[0200] In some examples, the first set of conditions includes one or more network settings, RRC configurations, or both.

[0201] In some examples, one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographic location of the first wireless device, or any combination thereof.

[0202] In some examples, machine learning models include neural network models.

[0203] In some examples, the first wireless device is a UE and the second wireless device is a network entity.

[0204] Figure 9 A diagram of a system 900 including a device 905 supporting additional condition indications for model-based monitoring, according to one or more aspects of this disclosure, is shown. Device 905 may be an example of device 605, device 705, UE 115, or network entity 105 as described herein, or may include components thereof. Device 905 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof (e.g., wirelessly). Device 905 may include components for bidirectional voice and data communication, including components for transmitting and receiving communications, such as a communication manager 920, an input / output (I / O) controller 910, a transceiver 915, an antenna 925, at least one memory 930, code 935, and at least one processor 940. These components may communicate electronically via one or more buses (e.g., bus 945) or be coupled in other ways (e.g., operational ground, communication ground, functional ground, electronic ground, electrical ground).

[0205] I / O controller 910 manages the input and output signals of device 905. I / O controller 910 can also manage peripheral devices not integrated into device 905. In some cases, I / O controller 910 may represent a physical connection or port to an external peripheral device. In some cases, I / O controller 910 may utilize an operating system such as iOS. ® ANDROID ® MS-DOS ® MS-WINDOWS ® OS / 2 ® UNIX® LINUX ® 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 one or more processors, such as at least one processor 940. In some cases, a user may interact with the device 905 via the I / O controller 910 or via hardware components controlled by the I / O controller 910.

[0206] In some cases, device 905 may include a single antenna 925. However, in other cases, device 905 may have more than one antenna 925, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. Transceiver 915 may communicate bidirectionally via one or more antennas 925 as described herein, or via a wired or wireless link. For example, transceiver 915 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Transceiver 915 may also include a modem for: modulating packets; providing the modulated packets to one or more antennas 925 for transmission; and demodulating packets received from one or more antennas 925. Transceiver 915, or transceiver 915 and one or more antennas 925, may be an example of transmitter 615, transmitter 715, receiver 610, receiver 710, or any combination thereof or components thereof as described herein.

[0207] At least one memory 930 may include random access memory (RAM) and read-only memory (ROM). At least one memory 930 may store computer-readable, computer-executable code 935, including instructions that, when executed by at least one processor 940, cause device 905 to perform the various functions described herein. Code 935 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 935 may not be directly executable by at least one processor 940, but may enable a computer (e.g., when compiled and executed) to perform the functions described herein. In some cases, among other things, at least one memory 930 may also include a basic I / O system (BIOS) that controls basic hardware or software operations, such as interaction with peripheral components or devices.

[0208] At least one 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, at least one 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 at least one processor 940. At least one processor 940 may be configured to execute computer-readable instructions stored in memory (e.g., at least one memory 930) to cause device 905 to perform various functions (e.g., functions or tasks supporting techniques for additional condition indications based on model monitoring). For example, device 905 or components of device 905 may include at least one processor 940 and at least one memory 930 coupled to or coupled to at least one processor 940, wherein at least one processor 940 and at least one memory 930 are configured to perform the various functions described herein. In some examples, at least one processor 940 may include multiple processors, and at least one memory 930 may include multiple memories. One or more of a plurality of processors may be coupled to one or more of a plurality of memories, which may be configured individually or collectively to perform the various functions described herein. In some examples, at least one processor 940 may be a component of a processing system, which may refer to a system of machines (such as a series of machines), circuitry (including, for example, one or both of processor circuitry (which may include at least one processor 940) and memory circuitry (which may include at least one memory 930)) or components that receive or receive input and process the input to produce, generate or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. Thus, at least one processor 940 or a processing system including at least one processor 940 may be configured, capable of being configured, or operable to cause device 905 to perform one or more of the functions described herein. Furthermore, as described herein, “configured to,” “capable of being configured,” and “operable to” are used interchangeably and may be associated with the ability to perform one or more of the functions described herein when executing code stored in at least one memory 930 or otherwise.

[0209] For example, the communication manager 920 can, is configured, or is operable to support components for communicating signaling with a second wireless device, an additional wireless device, or both. The communication manager 920 can, is configured, or is operable to support components for performing one or more inferences using a machine learning model based on signaling communication. The communication manager 920 can, is configured, or is operable to support components for sending instructions to the second wireless device that the machine learning model is suitable for performing one or more inferences. The communication manager 920 can, is configured, or is operable to support components for receiving control signaling from the second wireless device, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions related to the signaling communication, wherein the control signaling indicates a model ID associated with the machine learning model, the first set of conditions associated with the machine learning model, or both.

[0210] By including or configuring a communication manager 920 according to the examples described herein, device 905 can support techniques for facilitating more efficient identification of machine learning models that can be used to perform inference or prediction within a wireless communication system. By enhancing the ability of wireless devices to identify and define machine learning models (e.g., assign model IDs), the techniques described herein enable wireless devices to distribute information associated with the identified model throughout the network, leading to more general use of the model for inference or prediction, and thus more efficient and reliable wireless communication. Furthermore, the techniques described herein enable wireless devices to efficiently update previously trained machine learning models to apply them to new sets of additional situations not initially targeted by these models during training. Therefore, aspects of this disclosure enable machine learning models to be extended to additional use cases and scenarios (e.g., additional situations), thereby increasing the use of the model and preventing the need to train additional models for additional situations.

[0211] In some examples, the communication manager 920 may be configured to perform various operations (e.g., receiving, monitoring, transmitting) using a transceiver 915, one or more antennas 925, or any combination thereof, or otherwise cooperating with them. Although the communication manager 920 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 920 may be supported by or performed by at least one processor 940, at least one memory 930, code 935, or any combination thereof. For example, code 935 may include instructions that can be executed by at least one processor 940 to cause device 905 to perform various aspects of the techniques for additional condition indication as described herein for model-based monitoring, or at least one processor 940 and at least one memory 930 may be otherwise configured to perform or support such operations individually or jointly.

[0212] Figure 10 A flowchart illustrating a method 1000 for providing additional condition indication based on model monitoring, according to various aspects of this disclosure, is shown. Operation of method 1000 may be implemented by a UE or network entity 105 as described herein. For example, operation of method 1000 may be implemented by, as referenced... Figures 1 to 9 The described UE 115 or network entity 105 performs this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0213] At 1005, the method may include: communicating signaling with a second wireless device, an additional wireless device, or both. The operation of block 1005 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1005 may be provided by reference to [reference needed]. Figure 8 The signaling manager 825 described is used to execute this.

[0214] At 1010, the method may include: based on signaling communication, using a machine learning model to perform one or more inferences. The operation of box 1010 may be performed according to examples disclosed herein. In some examples, aspects of the operation of 1010 may be derived from references... Figure 8 The machine learning model manager 830 described is used to execute this.

[0215] At 1015, the method may include: sending an instruction to a second wireless device that the machine learning model is suitable for performing one or more inferences. The operation of box 1015 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1015 may be derived from references... Figure 8 The signaling manager 825 described is used to execute this.

[0216] At 1020, the method may include: receiving control signaling from a second wireless device, the control signaling instructing the machine learning model to be adapted to communications associated with a first set of conditions related to the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, the first set of conditions associated with the machine learning model, or both. Operation of block 1020 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1020 may be derived from references... Figure 8 The control signaling manager 835 described is used to execute this.

[0217] Figure 11 A flowchart illustrating a method 1100 for providing additional condition indication based on model monitoring, according to various aspects of this disclosure, is shown. Operation of method 1100 can be implemented by a UE or network entity as described herein. For example, operation of method 1100 can be performed by, as referenced... Figures 1 to 9 The described UE 115 or network entity 105 performs this function. In some examples, the UE can execute a set of instructions to control the functional elements of the UE to perform the described function. Additionally or alternatively, the UE may use dedicated hardware to perform aspects of the described function.

[0218] At 1105, the method may include: communicating signaling with a second wireless device, an additional wireless device, or both. The operation of block 1105 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1105 may be derived from references... Figure 8 The signaling manager 825 described is used to execute this.

[0219] At 1110, the method may include: based on the transmission of signaling, using a machine learning model to perform one or more inferences. The operation of box 1110 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1110 may be derived from, as referenced... Figure 8 The machine learning model manager 830 described is used to execute this.

[0220] At 1115, the method may include: sending an instruction to a second wireless device that the machine learning model is suitable for performing one or more inferences. The operation of box 1115 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1115 may be derived from references... Figure 8 The signaling manager 825 described is used to execute this.

[0221] At 1120, the method may include: receiving control signaling from a second wireless device, the control signaling instructing the machine learning model to be adapted to communications associated with a first set of conditions related to the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, the first set of conditions associated with the machine learning model, or both. Operation of block 1120 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1120 may be derived from references... Figure 8 The control signaling manager 835 described is used to execute this.

[0222] At 1125, the method may include: storing a data object that associates a machine learning model with a model ID, a first set of states, or both, based on received control signaling. The operation of block 1125 may be performed according to examples disclosed herein. In some examples, aspects of the operation of 1125 may be provided by reference to [reference needed]. Figure 8 The described data object manager 840 is used to execute this.

[0223] At 1130, the method may include: receiving additional control signaling from a second wireless device indicating a model ID, a first set of conditions, or both. Operation of block 1130 may be performed according to examples as disclosed herein. In some examples, aspects of the operation of 1130 may be provided by reference to [reference needed]. Figure 8 The control signaling manager 835 described is used to execute this.

[0224] At 1135, the method may include: based on a stored data object and upon receiving additional control signaling, using a machine learning model to perform one or more additional inferences. The operation of box 1135 may be performed according to examples disclosed herein. In some examples, aspects of the operation of 1135 may be derived from references... Figure 8 The machine learning model manager 830 described is used to execute this.

[0225] The following provides an overview of the various aspects of this disclosure: Aspect 1: A method for wireless communication at a first wireless device, the method comprising: communicating signaling with a second wireless device, an additional wireless device, or both; performing one or more inferences using a machine learning model, at least in part based on the communication of the signaling; sending to the second wireless device an indication that the machine learning model is suitable for performing the one or more inferences; and receiving from the second wireless device control signaling, the control signaling indicating that the machine learning model is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a model ID associated with the machine learning model, an indication that the first set of conditions is associated with the machine learning model, or both.

[0226] Aspect 2: The method according to aspect 1, further comprising: storing a data object that associates the machine learning model with the model ID, the first set of conditions, or both, at least in part based on receiving the control signaling; receiving additional control signaling from the second wireless device indicating the model ID, the first set of conditions, or both; and using the machine learning model to perform one or more additional inferences, at least in part based on storing the data object and receiving the additional control signaling.

[0227] Aspect 3: The method according to any one of Aspects 1 to 2, the method further comprising: storing a data object that associates the machine learning model with the model ID, the first set of conditions, or both, at least in part based on receiving the control signaling; identifying that the second wireless device will communicate according to the first set of conditions; and using the machine learning model to perform one or more additional inferences, at least in part based on storing the data object and identifying that the second wireless device is communicating according to the first set of conditions.

[0228] Aspect 4: The method according to any one of Aspects 1 to 3, the method further comprising: sending to the second wireless device a capability signaling indicating a second set of conditions for the first wireless device to transmit the signaling, wherein one or more inferences are associated with the second set of conditions.

[0229] Aspect 5: According to the method of aspect 4, wherein the control signaling instructs the machine learning model to be used in communication associated with the second set of conditions.

[0230] Aspect 6: The method according to any one of Aspects 4 to 5, wherein the second set of conditions includes the number of communication layers supported at the first wireless device, the number of antennas at the first wireless device, or both.

[0231] Aspect 7: The method according to any one of Aspects 1 to 6, the method further comprising: communicating additional signaling to the second wireless device, the additional wireless device, or both based on an additional set of conditions associated with the second wireless device; using the machine learning model to perform one or more additional inferences based at least in part on communicating the additional signaling based on the additional set of conditions; and sending a control message to the second wireless device instructing the machine learning model to be suitable for performing the one or more additional inferences associated with the additional set of conditions.

[0232] Aspect 8: The method according to aspect 7, the method further comprising: receiving from the second wireless device additional control signaling indicating that the machine learning model is associated with the additional set of conditions; and updating a data object associated with the machine learning model to include information associated with the association between the machine learning model and the additional set of conditions, at least in part based on the received additional control signaling.

[0233] Aspect 9: The method according to any one of Aspects 7 to 8, wherein the set of additional conditions includes the speed of the first wireless device, a signal quality indicator of wireless communication received by the first wireless device, network-based additional conditions, or any combination thereof.

[0234] Aspect 10: The method according to any one of Aspects 1 to 9, wherein the first set of conditions includes one or more network settings, RRC configurations, or both.

[0235] Aspect 11: The method according to any one of Aspects 1 to 10, wherein the one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographical location of the first wireless device, or any combination thereof.

[0236] Aspect 12: The method according to any one of Aspects 1 to 11, wherein the machine learning model includes a neural network model.

[0237] Aspect 13: The method according to any one of Aspects 1 to 12, wherein the first wireless device includes a UE and the second wireless device includes a network entity, or the first wireless device includes the network entity and the second wireless device includes the UE.

[0238] Aspect 14: The method according to any one of Aspects 1 to 13, the method further comprising: monitoring the performance of the machine learning model at least in part based on performing the one or more inferences; and determining, at least in part based on monitoring the performance of the machine learning model, that the machine learning model is suitable for performing the one or more inferences.

[0239] Aspect 15: A method for wireless communication at a first wireless device, the method comprising: communicating signaling with a second wireless device, an additional wireless device, or both; performing one or more inferences using functionality based at least in part on the communication of the signaling; sending to the second wireless device an indication that the functionality is suitable for performing the one or more inferences; and receiving from the second wireless device control signaling indicating that the functionality is suitable for communication associated with a first set of conditions associated with the communication of the signaling, wherein the control signaling indicates a functionality identifier associated with the functionality, an indication that the first set of conditions is associated with the functionality, or both.

[0240] Aspect 16: The method according to aspect 15, the method further comprising: storing a data object that associates the functionality with the functionality identifier, the first set of conditions, or both, at least in part based on receiving the control signaling; receiving additional control signaling from the second wireless device indicating the functionality identifier, the first set of conditions, or both; and using the functionality to perform one or more additional inferences, at least in part based on storing the data object and receiving the additional control signaling.

[0241] Aspect 17: The method according to any one of Aspects 15 to 16, the method further comprising: storing a data object that associates the functionality with the functionality identifier, the first condition set, or both, at least in part based on receiving the control signaling; identifying that the second wireless device will communicate according to the first condition set; and using the functionality to perform one or more additional inferences, at least in part based on storing the data object and identifying that the second wireless device is communicating according to the first condition set.

[0242] Aspect 18: The method according to any one of aspects 15 to 17, the method further comprising: sending to the second wireless device a capability signaling indicating a second set of conditions for the first wireless device to transmit the signaling, wherein one or more inferences are associated with the second set of conditions.

[0243] Aspect 19: The method according to aspect 18, wherein the control signaling instructs the functionality to be adapted for communication associated with the second set of conditions.

[0244] Aspect 20: The method according to any one of Aspects 18 to 19, wherein the second set of conditions includes the number of communication layers supported at the first wireless device, the number of antennas at the first wireless device, or both.

[0245] Aspect 21: The method according to any one of Aspects 15 to 20, the method further comprising: communicating additional signaling with the second wireless device, the additional wireless device, or both based on an additional set of conditions associated with the second wireless device; using the functionality to perform one or more additional inferences based at least in part on communicating the additional signaling based on the additional set of conditions; and sending a control message to the second wireless device instructing the functionality to be suitable for performing the one or more additional inferences associated with the additional set of conditions.

[0246] Aspect 22: The method according to aspect 21, the method further comprising: receiving from the second wireless device additional control signaling indicating that the functionality is associated with the additional condition set; and updating a data object associated with the functionality to include information associated with the association between the functionality and the additional condition set, at least in part based on the received additional control signaling.

[0247] Aspect 23: The method according to any one of Aspects 21 to 22, wherein the set of additional conditions includes the speed of the first wireless device, a signal quality index of wireless communication received by the first wireless device, network-based additional conditions, or any combination thereof.

[0248] Aspect 24: The method according to any one of aspects 15 to 23, wherein the first set of conditions includes one or more network settings, radio resource control configurations, or both.

[0249] Aspect 25: The method according to any one of Aspects 15 to 24, wherein the one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographical location of the first wireless device, or any combination thereof.

[0250] Aspect 26: The method according to any one of aspects 15 to 25, wherein the functionality is associated with one or more machine learning models that can be executed by the first wireless device, the second wireless device, or both.

[0251] Aspect 27: The method according to any one of Aspects 15 to 26, wherein the first wireless device includes a UE and the second wireless device includes a network entity, or the first wireless device includes the network entity and the second wireless device includes the UE.

[0252] Aspect 28: The method according to any one of aspects 15 to 27, the method further comprising: monitoring the performance of the functionality at least in part based on performing the one or more inferences; and determining, at least in part based on monitoring the performance of the functionality, that the functionality is suitable for performing the one or more inferences.

[0253] Aspect 29: A first wireless device comprising: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories and capable of operating individually or jointly to execute the code to cause the first wireless device to perform a method according to any one of aspects 1 to 14.

[0254] Aspect 30: A first wireless device, the first wireless device comprising at least one component for performing the method according to any one of aspects 1 to 14.

[0255] Aspect 31: A non-transitory computer-readable medium storing code, said code comprising instructions executable by a processor to perform the method according to any one of aspects 1 to 14.

[0256] Aspect 32: A first wireless device comprising: one or more memories storing processor-executable code; and one or more processors coupled to the one or more memories and capable of operating individually or jointly to execute the code to cause the first wireless device to perform the method according to aspects 15 to 28.

[0257] Aspect 33: A first wireless device, the first wireless device comprising at least one component for performing the method according to any one of aspects 15 to 28.

[0258] Aspect 34: A non-transitory computer-readable medium storing code, said code comprising instructions executable by a processor to perform the method according to any one of aspects 15 to 28.

[0259] In some cases, one or more features of aspects 15 to 28 may be combined with one or more features of any of aspects 1 to 14. For example, techniques or other teachings in this document relating to machine learning models (e.g., relating to identifying or updating machine learning models) may be additionally or alternatively applied to functionality (e.g., relating to identifying or updating functionality), and vice versa.

[0260] It should be noted that the methods described herein describe possible specific implementations, and the operations and steps can be rearranged or otherwise modified, and other specific implementations are also possible. Furthermore, aspects from two or more of these methods can be combined.

[0261] While aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for illustrative purposes, and the terms LTE, LTE-A, LTE-A Pro, or NR may be used in most of the description, the techniques described herein are also applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described are applicable to a variety of 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 radio technologies not explicitly mentioned herein.

[0262] The information and signals described herein can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the description can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0263] The various exemplary blocks and components described herein can be implemented or performed using a general-purpose processor, DSP, ASIC, CPU, FPGA or other programmable logic device, discrete gate or transistor logic unit, discrete hardware component, or any combination thereof, designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in alternative embodiments, a processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors working in conjunction with a DSP core, or any other such configuration). Any function or operation described herein that can be performed by a processor may be performed by multiple processors capable of performing the described functions or operations individually or jointly.

[0264] The functions described herein can be implemented using hardware, software executed by a processor, firmware, or any combination thereof. When implemented using software executed by a processor, the functions can be stored as one or more instructions or code on a computer-readable medium or transmitted using one or more instructions or code on a computer-readable medium. Other examples and specific implementations are within the scope of this disclosure and the appended claims. For example, due to the nature of software, the functions described herein can be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination of these. Features implementing the functions can also be physically located in various locations, including portions distributed such that the functions are implemented in different physical locations.

[0265] Computer-readable media includes both non-transitory computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. Non-transitory storage media can be any available medium accessible by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compressed optical disc (CD) ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code components in the form of instructions or data structures, and accessible by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Furthermore, any connection is 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 within the definition of computer-readable media. As used herein, disks and optical discs include CDs, laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs. Disks can magnetically reproduce data, and optical discs can optically reproduce data using lasers. Combinations of the above are also included within the scope of computer-readable media. Any function or operation described herein that can be performed by memory can be performed by multiple memories capable of performing the described function or operation individually or jointly.

[0266] As used herein, the word "or," as in the claims, as in a list of two or more items (e.g., an list of items accompanied by phrases such as "at least one of" or "one or more of"), indicates an inclusive enumeration, such that an enumeration of at least one of, for example, A, B, or C, means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Furthermore, as used herein, the phrase "based on" should not be construed as a reference to a closed set of conditions. For example, an example step described as "based on condition A" could 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" should be interpreted in the same manner as the phrase "at least partially based on".

[0267] As used herein, including in claims, the article “a” preceding a noun is open-ended and is understood to refer to “at least one” or “one or more” of those nouns. Therefore, the terms “a,” “at least one,” “one or more,” and “at least one of one or more” are interchangeable. For example, where a claim enumerates “components” performing one or more functions, each of the individual functions may be performed by a single component or by any combination of multiple components. Thus, the term “component” having a characteristic or performing a function may refer to “at least one of one or more components” having a particular characteristic or performing a particular function. Subsequent references to a component introduced with the article “a” using the terms “the” or “the” may refer to any or all of the one or more components. For example, a component introduced with the article “a” may be understood to mean “one or more components,” and subsequent reference to “component” in a claim may be understood to be equivalent to referring to “at least one of the one or more components.” Similarly, subsequent references to a component introduced with the terms “the” or “the” as “one or more components” may refer to any or all of the one or more components. For example, reference to "one or more components" in subsequent claims can be understood as equivalent to reference to "at least one of the one or more components".

[0268] The term "determine" encompasses a variety of actions, and therefore, "determine" can include calculation, computation, processing, derivation, investigation, lookup (such as by searching in a table, database, or other data structure), identification, and similar actions. Furthermore, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data stored in memory), etc. Moreover, "determine" can include parsing, acquiring, selecting, choosing, building, and other similar actions.

[0269] Furthermore, as used in this article, the phrase "set" should be understood to include the possibility of a set having one member. That is, the phrase "set" should be interpreted in the same way as "one or more".

[0270] In the accompanying drawings, similar components or features may have the same reference numerals. Furthermore, various components of the same type can be distinguished by adding a dash after the reference numeral and a second reference numeral to differentiate them. If only the first reference numeral is used in the description, the description can be applied to any of the similar components having the same first reference numeral, regardless of the second or other subsequent reference numerals.

[0271] The description herein, illustrated with reference to the accompanying drawings, describes an example configuration and does not represent all achievable examples or those within the scope of the claims. The term "example" as used herein means "serving as an example, instance, or illustration," not "preferred" or "advantageous over other examples." The detailed description includes specific details used to provide an understanding of the described techniques. However, these techniques can be practiced without these specific details. In some instances, known structures and devices are shown in block diagram form to avoid obscuring the concept of the described examples.

[0272] The description herein is provided to enable those skilled in the art to implement or use this disclosure. Various modifications to this disclosure will be apparent 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. Therefore, this disclosure is not limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A first wireless device, the first wireless device comprising: One or more memories, wherein the one or more memories store processor-executable code; and One or more processors, said one or more processors coupled to said one or more memories and capable of operating individually or jointly to execute said code to enable the first wireless device: To communicate signaling with a second wireless device, an additional wireless device, or both; At least in part based on the transmission of the signaling, a machine learning model is used to perform one or more inferences; Send to the second wireless device an instruction that the machine learning model is suitable for performing the one or more inferences; as well as The second wireless device receives control signaling, which instructs the machine learning model to be adapted to communication associated with a first set of conditions related to the communication of the signaling, wherein the control signaling indicates a model identifier associated with the machine learning model, the first set of conditions associated with the machine learning model, or both.

2. The first wireless device of claim 1, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: The data object that associates the machine learning model with the model identifier, the first set of conditions, or both is stored, at least in part based on the received control signaling. Receive additional control signaling from the second wireless device indicating the model identifier, the first state set, or both; and At least in part, based on storing the data object and receiving the additional control signaling, the machine learning model is used to perform one or more additional inferences.

3. The first wireless device of claim 1, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: The data object that associates the machine learning model with the model identifier, the first set of conditions, or both is stored, at least in part based on the received control signaling. The second wireless device is identified as communicating based on the first set of conditions; as well as At least in part, based on storing the data object and identifying that the second wireless device is communicating according to the first set of conditions, the machine learning model is used to perform one or more additional inferences.

4. The first wireless device of claim 1, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: Send to the second wireless device a capability signaling indicating a second set of conditions used by the first wireless device to convey the signaling, wherein one or more inferences are associated with the second set of conditions.

5. The first wireless device of claim 4, wherein the control signaling instructs the machine learning model to be adapted for communication associated with the second set of conditions.

6. The first wireless device of claim 4, wherein the second set of conditions includes the number of communication layers supported by the first wireless device, the number of antennas at the first wireless device, or both.

7. The first wireless device of claim 1, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: Additional signaling is communicated with the second wireless device, the additional wireless device, or both based on an additional set of conditions associated with the second wireless device. At least in part, based on the additional signaling conveyed according to the additional set of additional conditions, the machine learning model is used to perform one or more additional inferences; as well as Send a control message to the second wireless device instructing the machine learning model to perform one or more additional inferences associated with the additional set of conditions.

8. The first wireless device of claim 7, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: Receive additional control signaling from the second wireless device, indicating that the machine learning model is associated with the additional set of conditions; and The data object associated with the machine learning model is updated, at least in part, based on the received additional control signaling, to include information related to the association between the machine learning model and the set of additional conditions.

9. The first wireless device of claim 7, wherein the set of additional conditions includes the speed of the first wireless device, signal quality indicators of wireless communications received by the first wireless device, network-based additional conditions, or any combination thereof.

10. The first wireless device of claim 1, wherein the first set of conditions includes one or more network settings, radio resource control configurations, or both.

11. The first wireless device of claim 1, wherein the one or more inferences include inferences associated with channel state feedback, inferences associated with one or more beams that can be used by the first wireless device, inferences associated with the geographical location of the first wireless device, or any combination thereof.

12. The first wireless device according to claim 1, wherein the machine learning model includes a neural network model.

13. The first wireless device according to claim 1, Wherein the first wireless device includes user equipment (UE) and the second wireless device includes a network entity, or The first wireless device includes the network entity and the second wireless device includes the UE.

14. The first wireless device of claim 1, wherein the one or more processors are individually or jointly further operable to execute the code to cause the first wireless device to: The performance of the machine learning model is monitored at least in part based on performing one or more of the inferences; and The suitability of the machine learning model for performing the one or more inferences is determined at least in part based on monitoring the performance of the machine learning model.

15. A method for performing wireless communication at a first wireless device, the method comprising: To communicate signaling with a second wireless device, an additional wireless device, or both; At least in part based on the transmission of the signaling, a machine learning model is used to perform one or more inferences; Send to the second wireless device an instruction that the machine learning model is suitable for performing the one or more inferences; as well as The second wireless device receives control signaling, which instructs the machine learning model to be adapted to communication associated with a first set of conditions related to the communication of the signaling, wherein the control signaling indicates a model identifier associated with the machine learning model, the first set of conditions associated with the machine learning model, or both.

16. The method according to claim 15, further comprising: The data object that associates the machine learning model with the model identifier, the first set of conditions, or both is stored, at least in part based on the received control signaling. Receive additional control signaling from the second wireless device indicating the model identifier, the first set of conditions, or both; as well as At least in part, based on storing the data object and receiving the additional control signaling, the machine learning model is used to perform one or more additional inferences.

17. The method according to claim 15, further comprising: The data object that associates the machine learning model with the model identifier, the first set of conditions, or both is stored, at least in part based on the received control signaling. The second wireless device is identified as communicating based on the first set of conditions; as well as At least in part, based on storing the data object and identifying that the second wireless device is communicating according to the first set of conditions, the machine learning model is used to perform one or more additional inferences.

18. The method according to claim 15, further comprising: Send to the second wireless device a capability signaling indicating a second set of conditions used by the first wireless device to convey the signaling, wherein one or more inferences are associated with the second set of conditions.

19. The method according to claim 15, further comprising: Additional signaling is communicated with the second wireless device, the additional wireless device, or both based on an additional set of conditions associated with the second wireless device. At least in part, based on the additional signaling conveyed according to the additional set of additional conditions, the machine learning model is used to perform one or more additional inferences; as well as Send a control message to the second wireless device instructing the machine learning model to perform one or more additional inferences associated with the additional set of conditions.

20. A non-transitory computer-readable medium storing code, the code comprising instructions executable by one or more processors to: To communicate signaling with a second wireless device, an additional wireless device, or both; At least in part based on the transmission of the signaling, a machine learning model is used to perform one or more inferences; Send to the second wireless device an instruction that the machine learning model is suitable for performing the one or more inferences; as well as The second wireless device receives control signaling, which instructs the machine learning model to be adapted to communication associated with a first set of conditions related to the communication of the signaling, wherein the control signaling indicates a model identifier associated with the machine learning model, the first set of conditions associated with the machine learning model, or both.

Images