Method and apparatus for actively communicating resource mappings to network element implementations for performing tasks

Abstract

Embodiments of the present disclosure relate to methods and apparatus for actively communicating resource mappings to network element implementations for performing tasks. A network element may receive, from a network node of a wireless communication system, information indicating an association between a plurality of implementations by which the network element of the wireless communication system performs respective tasks and resource allocations required by the network element to perform the respective tasks according to one or more respective implementations of the plurality of implementations. The network element may select a first implementation of the plurality of implementations to perform the respective task based on an allocation of available resources for the network element to perform the respective task relative to resources required to perform the respective task according to the first implementation. The network elements may perform respective tasks according to the first implementation. A network element may cause transmission of information to a network node indicating a first implementation selected to perform a respective task.

Description

Technical Field

[0001] Example embodiments relate generally to wireless communications and, more particularly, but not exclusively, to methods, apparatus, and computer program products implemented for actively communicating resource mappings to network elements for performing tasks. Background Art

[0002] Some wireless communication systems may include communication devices configured to perform various tasks utilizing artificial intelligence (e.g., machine learning or any other type of artificial intelligence). For example, a communication device such as a user equipment (UE) may be configured to utilize one or more machine learning models for one or more channel state information (CSI) processes, such as a CSI determination process. In this case, the UE may utilize a machine learning model to predict CSI for one or more channels, which may enhance one or more operations performed by the UE. In addition to machine learning-assisted CSI processes, the communication device may also utilize one or more artificial intelligence models for beam management, for positioning, or for any other type of task performed by the communication device. However, utilizing artificial models at a communication device for various tasks may consume more resources than the communication device performing the same tasks without relying on artificial intelligence. In addition, some communication devices may indiscriminately utilize artificial intelligence models without considering available resources, which may result in reduced performance at the communication device. Summary of the invention

[0003] According to one or more aspects of the present disclosure, a communication device may be (e.g., actively) configured with a mapping table that links (e.g., associates, pairs) corresponding implementations (e.g., configurations, operations, features, functions, models, model parameters) for performing one or more tasks with corresponding conditions (e.g., resource conditions, required resource allocation) of the communication device. The communication device may then select an implementation that corresponds to the current conditions of the communication device, which may improve resource utilization and performance of the communication device.

[0004] As an illustrative example, a mapping table may include an entry indicating that a corresponding first implementation of a task requires a range of available resources of 20% to 30% and another entry indicating that a corresponding second implementation of the same task requires a range of available resources of 50% or more. The first implementation may include performing a task (e.g., positioning operation, beam management operation, channel state information (CSI) operation, etc.) without using artificial intelligence or using an artificial intelligence model with a given resource requirement (e.g., a relatively low resource requirement), while the second implementation may include using an artificial intelligence model with a significantly greater resource requirement to perform the same task. Therefore, a communication device may select an implementation using a mapping table corresponding to the resource availability at a given time. For example, a communication device may select an implementation corresponding to the current condition of the communication device (e.g., current resource utilization) from a mapping table. The communication device may then perform a task (e.g., positioning operation) according to the implementation selected by the communication device. More specifically, the implementation may specify whether artificial intelligence is used to perform the task. In addition, or alternatively, the implementation may specify one or more parameters for performing the task or one or more models (e.g., artificial intelligence models) for performing the task. As described in further detail herein, such techniques may enable a communication device to more effectively and efficiently utilize or avoid utilizing artificial intelligence for various tasks and communications based on the available resources of the communication device, which may improve the performance of the communication device.

[0005] A method for performing the techniques described herein is provided. The method may include receiving information from a network node of a wireless communication system, the information indicating an association between (i) a plurality of implementations for a network element of the wireless communication system to perform a corresponding task and (ii) a resource allocation required for the network element to perform the corresponding task according to one or more of the plurality of implementations, selecting a first implementation of the plurality of implementations to perform the corresponding task based at least in part on available resources for the network element to perform the corresponding task relative to the resource allocation required to perform the corresponding task according to the first implementation, and performing the corresponding task according to the first implementation.

[0006] The method also includes causing transmission to the network node of information indicating the first implementation selected to perform the corresponding task. In some cases, the plurality of implementations corresponds to one or more of: one or more implementations of the network element associated with the corresponding artificial intelligence or machine learning enabled feature or feature group, one or more implementations of the network element associated with the corresponding artificial intelligence or machine learning enabled functionality, or one or more implementation variants of the network element associated with a given artificial intelligence or machine learning enabled functionality.

[0007] In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that rely on artificial intelligence or machine learning. In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that do not rely on artificial intelligence or machine learning. In some cases, selecting the first implementation from the plurality of implementations is based at least in part on a priority associated with the respective implementation in the plurality of implementations.

[0008] The method of the example embodiment also includes causing resource availability information to be transmitted to the network node, wherein multiple implementations are based at least in part on the resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs for performing the corresponding task, availability information of one or more outputs for the corresponding task, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources (e.g., communication resources) allocated by another network entity to the network entity performing the corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0009] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0010] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0011] Another method for performing the techniques described herein is provided. The method may include: causing information to be transmitted toward a network element of a wireless communication system, the information indicating an association between (i) a plurality of implementations of a corresponding task performed by the network element of the wireless communication system and (ii) resource allocation required for the network element to perform the corresponding task according to one or more of the plurality of implementations; and receiving information from the network element indicating a first implementation of performing the corresponding task.

[0012] In some cases, the multiple implementations correspond to one or more of: one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled features or feature groups, one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled functions, or one or more implementation variants for a network element associated with a given artificial intelligence or machine learning enabled function.

[0013] In some cases, the plurality of implementations include one or more implementations that rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, the plurality of implementations include one or more implementations that do not rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, corresponding implementations in the plurality of implementations are assigned corresponding priorities.

[0014] The method of the example embodiment may also include receiving resource availability information of the network element from the network element, wherein the multiple implementations are based at least in part on the resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs of the network element, availability information of one or more outputs of the network element, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to the network entity performing the corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals. In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability may involve multiple levels of dynamism, such that the availability of resources may range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in the lowest time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of the following: a geographic area in which one or more resources of the network element are available, and outside the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside the time period, one or more resources of the network element are not available.

[0015] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of available resources. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0016] An apparatus for performing the techniques described herein is provided. The apparatus may include at least one processor. The apparatus also includes at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive information from a network node of a wireless communication system, the information indicating an association between (i) multiple implementations of a network element of the wireless communication system performing a corresponding task and (ii) resource allocation required by the network element to perform the corresponding task according to one or more of the multiple implementations, select a first implementation of the multiple implementations to perform the corresponding task based at least in part on available resources of the network element to perform the corresponding task relative to the resource allocation required to perform the corresponding task according to the first implementation, and perform the corresponding task according to the first implementation.

[0017] The instructions may also cause the apparatus to at least cause transmission to the network node of information indicating the first implementation selected to perform the corresponding task. In some cases, the plurality of implementations corresponds to one or more of: one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled feature or feature group, one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled function, or one or more implementation variants of a network element associated with a given artificial intelligence or machine learning enabled function.

[0018] In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that rely on artificial intelligence or machine learning. In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that do not rely on artificial intelligence or machine learning. In some cases, selecting the first implementation from the plurality of implementations is based at least in part on a priority associated with the respective implementation in the plurality of implementations.

[0019] In some cases, the instruction, when executed by at least one processor, further causes the apparatus to at least cause resource availability information to be transmitted to a network node, wherein multiple implementations are based at least in part on the resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of a network element, availability information for memory resources of a network element, battery life information of a network element, availability information of one or more inputs for performing a corresponding task, availability information of one or more outputs for a corresponding task, a connection state of a network element with a wireless communication system, or a connection quality of a network element with a wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0020] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0021] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0022] Another apparatus for performing the techniques described herein is provided. The apparatus may include at least one processor. The apparatus also includes at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least perform: causing information to be transmitted toward a network element of a wireless communication system, the information indicating an association between (i) a plurality of implementations of a corresponding task performed by the network element of the wireless communication system and (ii) resource allocation required for the network element to perform the corresponding task according to one or more corresponding implementations of the plurality of implementations, and receiving information from the network element indicating a first implementation of performing the corresponding task.

[0023] In some cases, the multiple implementations correspond to one or more of: one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled features or feature groups, one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled functions, or one or more implementation variants of network elements associated with a given artificial intelligence or machine learning enabled function.

[0024] In some cases, the plurality of implementations include one or more implementations that rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, the plurality of implementations include one or more implementations that do not rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, corresponding implementations in the plurality of implementations are assigned corresponding priorities.

[0025] In some cases, the instructions, when executed by at least one processor, further cause the apparatus to receive at least resource availability information for the network element from the network element, wherein the plurality of implementations are based at least in part on the resource availability information. In some cases, two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models.

[0026] In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs of the network element, availability information of one or more outputs of the network element, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power for the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to the detected positioning reference signal.

[0027] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0028] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0029] According to another example embodiment, a non-transitory computer-readable medium is provided. The non-transitory computer-readable medium may include program instructions stored thereon, which are configured to receive information from a network node of a wireless communication system, the information indicating (i) a plurality of implementations of a network element of the wireless communication system to perform a corresponding task and (ii) an association between resource allocations required for the network element to perform the corresponding task according to one or more of the plurality of implementations; select a first implementation of the plurality of implementations to perform the corresponding task based at least in part on available resources for the network element to perform the corresponding task relative to the resource allocations required to perform the corresponding task according to the first implementation; and perform the corresponding task according to the first implementation.

[0030] The instructions may also be configured to at least cause transmission to the network node of information indicating the first implementation selected to perform the corresponding task. In some cases, the plurality of implementations corresponds to one or more of: one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled feature or feature group, one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled function, or one or more implementation variants of a network element associated with a given artificial intelligence or machine learning enabled function.

[0031] In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that rely on artificial intelligence or machine learning. In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that do not rely on artificial intelligence or machine learning. In some cases, selecting the first implementation from the plurality of implementations is based at least in part on a priority associated with the respective implementation in the plurality of implementations.

[0032] In some cases, the instruction is also configured to execute at least causing resource availability information to be transmitted to the network node, wherein multiple implementations are at least partially based on resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs for performing the corresponding task, availability information of one or more outputs for the corresponding task, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to the network entity performing the corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold, "detection" may occur. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0033] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0034] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0035] According to another example embodiment, another non-transitory computer-readable medium is provided. The non-transitory computer-readable medium may include program instructions stored thereon, which are configured to cause information to be transmitted toward a network element of a wireless communication system, the information indicating an association between (i) a plurality of implementations of a corresponding task performed by the network element of the wireless communication system and (ii) resource allocation required for the network element to perform the corresponding task according to one or more of the plurality of implementations, and receiving information from the network element indicating a first implementation of performing the corresponding task.

[0036] In some cases, the multiple implementations correspond to one or more of: one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled features or feature groups, one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled functions, or one or more implementation variants of network elements associated with a given artificial intelligence or machine learning enabled function.

[0037] In some cases, multiple implementations include one or more implementations for network elements that rely on artificial intelligence or machine learning to perform the corresponding tasks. In some cases, multiple implementations include one or more implementations for network elements that do not rely on artificial intelligence or machine learning to perform the corresponding tasks.

[0038] In some cases, respective implementations in the plurality of implementations are assigned respective priorities. In some cases, the instructions are further configured to perform at least receiving resource availability information for the network element from the network element, wherein the plurality of implementations are based at least in part on the resource availability information. In some cases, two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models.

[0039] In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs of the network element, availability information of one or more outputs of the network element, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power for the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to the detected positioning reference signal.

[0040] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0041] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0042] According to another example embodiment, another apparatus is provided. The apparatus may include a component for receiving information from a network node of a wireless communication system, the information indicating an association between (i) multiple implementations of a network element of the wireless communication system to perform a corresponding task and (ii) resource allocation required for the network element to perform the corresponding task according to one or more of the multiple implementations; a component for selecting a first implementation of the multiple implementations to perform the corresponding task based at least in part on available resources for the network element to perform the corresponding task relative to the resource allocation required to perform the corresponding task according to the first implementation; and a component for performing the corresponding task according to the first implementation.

[0043] The apparatus may also include means for causing transmission to the network node of information indicating the first implementation selected to perform the corresponding task. In some cases, the plurality of implementations corresponds to one or more of: one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled feature or feature group, one or more implementations of a network element associated with a corresponding artificial intelligence or machine learning enabled functionality, or one or more implementation variants of a network element associated with a given artificial intelligence or machine learning enabled functionality.

[0044] In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that rely on artificial intelligence or machine learning. In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that do not rely on artificial intelligence or machine learning. In some cases, selecting the first implementation from the plurality of implementations is based at least in part on a priority associated with the respective implementation in the plurality of implementations.

[0045] The apparatus may also include a component for transmitting resource availability information to a network node, wherein multiple implementations are based at least in part on resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of a network element, availability information for memory resources of a network element, battery life information of a network element, availability information for one or more inputs for performing a corresponding task, availability information for one or more outputs of a corresponding task, a connection state of a network element with a wireless communication system, or a connection quality of a network element with a wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0046] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available, or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0047] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims.

[0048] According to another example embodiment, another apparatus is provided. The apparatus may include means for causing information to be transmitted toward a network element of a wireless communication system, the information indicating an association between (i) a plurality of implementations of a corresponding task performed by the network element of the wireless communication system and (ii) resource allocation required for the network element to perform the corresponding task according to one or more of the plurality of implementations, and means for receiving information from the network element indicating a first implementation of performing the corresponding task.

[0049] In some cases, the multiple implementations correspond to one or more of: one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled features or feature groups, one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled functions, or one or more implementation variants of network elements associated with a given artificial intelligence or machine learning enabled function.

[0050] In some cases, the plurality of implementations include one or more implementations that rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, the plurality of implementations include one or more implementations that do not rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, corresponding implementations in the plurality of implementations are assigned corresponding priorities.

[0051] The apparatus may also include a component for receiving resource availability information for the network element from the network element, wherein the plurality of implementations are based at least in part on the resource availability information. In some cases, two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs of the network element, availability information of one or more outputs of the network element, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold, "detection" may occur. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0052] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static, where the dynamic resource availability information is valid for a limited duration. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in a minimum time unit level), or any level of dynamism in between. In some cases, the resource availability information indicates one or more of: a geographic area in which one or more resources of the network element are available, and outside of the geographic area, one or more resources of the network element are not available; or a time period during which one or more resources of the network element are available, and outside of the time period, one or more resources of the network element are not available.

[0053] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resources for the network element, a percentage of resources available relative to a threshold amount of the corresponding resources for the network element, or an absolute amount of resources available. Other technical features may become apparent to those skilled in the art from the following drawings, descriptions, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Having thus described certain example embodiments of the present disclosure in general terms, reference will hereinafter be made to the accompanying drawings, which are not necessarily drawn to scale, and in which:

[0055] Figure 1 A wireless communication system is shown, via which a user equipment (UE) and one or more base stations may be configured to actively communicate resource mappings;

[0056] Figure 2 is a block diagram of an apparatus that may be specially configured in accordance with an example embodiment of the present disclosure;

[0057] Figure 3 A signal flow diagram is shown supporting a technique for communicating resource mapping between network elements, network nodes, and a lifecycle management (LCM) entity;

[0058] Figure 4 shows tables for communicating or otherwise storing information associated with resources used to perform various tasks; and

[0059] Figure 5 and Figure 6 is a flow diagram of operations in accordance with certain example embodiments, such as may be implemented by the apparatus described herein. DETAILED DESCRIPTION

[0060] Some embodiments of the present invention will now be described more fully below with reference to the accompanying drawings, in which some but not all embodiments of the present invention are shown. In fact, various embodiments of the present invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; on the contrary, these embodiments are provided so that the present disclosure will satisfy applicable legal requirements. Similar reference numerals refer to similar elements throughout. As used herein, the terms "data", "content", "information" and similar terms may be used interchangeably to refer to data that can be sent, received and / or stored according to embodiments of the present invention. Therefore, the use of any such terms should not be considered to limit the spirit and scope of embodiments of the present invention.

[0061] In addition, as used herein, the term "circuit" refers to (a) a pure hardware circuit implementation (e.g., an implementation in analog circuits and / or digital circuits); (b) a combination of a circuit and (multiple) computer program products, the (multiple) computer program products including software and / or firmware instructions stored on one or more computer-readable memories, which work together to cause the device to perform one or more functions described herein; and (c) a circuit, such as, for example, (multiple) microprocessors or a portion of (multiple) microprocessors, which requires software or firmware for operation even if the software or firmware is not physically present. This definition of "circuit" applies to all uses of the term herein, including in any claims. As yet another example, as used herein, the term "circuit" also includes an implementation including one or more processors and / or (multiple) portions thereof and accompanying software and / or firmware. As another example, as used herein, the term "circuit" also includes, for example, a baseband integrated circuit or application processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, other network equipment (such as a core network device), a field programmable gate array, and / or other computing devices.

[0062] As used herein, the term "computer-readable medium" refers to non-transitory storage hardware, non-transitory storage devices, or non-transitory computer system memory that can be accessed by a controller, a microcontroller, a computing system, or a module of a computing system to encode computer-executable instructions or software programs thereon. Non-transitory "computer-readable media" can be accessed by a computing system or a module of a computing system to retrieve and / or execute computer-executable instructions or software programs encoded on the medium. Examples of non-transitory computer-readable media may include, but are not limited to, one or more types of hardware memory, non-transitory tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more USB flash drives), computer system memory, or random access memory (e.g., DRAM, SRAM, EDO RAM), etc.

[0063] Figure 1An example of a wireless communication system 100 that supports methods and apparatus for actively communicating resource mappings to network elements for performing tasks is shown. In some embodiments, the wireless communication system 100 may include one or more UEs 105 and one or more base stations 110 of a radio access network (RAN), which may communicate with each other. The one or more base stations 110 may be examples of network entities and may be embodied by any of a variety of access points or nodes, including, for example, a Node B (e.g., a gNB) of the RAN, etc. In some cases, the UE 105 and / or the RAN (such as the base stations 110 of the RAN) may communicate with a core network including one or more network nodes of the core network. Figure 1 As shown in , the network node of the example embodiment may include one or more life cycle management (LCM) entities 115, such as hosted by a location management function (LMF). The LCM entity 115 may be an example of a virtualized entity, such as implemented by software, and is responsible for performing one or more operations related to life cycle management.

[0064] By way of example, the wireless communication system 100 may be deployed within a radio access architecture based on Long Term Evolution Advanced (LTE Advanced, LTE-A) and / or New Radio (NR, 5G). However, the system may be deployed in other network architectures including within other communication networks, including, for example, other communication networks developed in the future, such as sixth generation (6G) networks, and any of many existing networks including: Universal Mobile Telecommunications System (UMTS), Radio Access Network (UTRAN or E-UTRAN), Wireless Local Area Network (WLAN or Wi-Fi), Worldwide Interoperability for Microwave Access (WiMAX), Personal Communications Service (PCS), Wideband Code Division Multiple Access (WCDMA), systems using Ultra-Wideband (UWB) technology, sensor networks, mobile ad hoc networks (MANETs), and Internet Protocol Multimedia Subsystem (IMS), or any combination thereof.

[0065] UE 105 may be any type of user terminal, terminal device, node (e.g., network node), element (e.g., network element), etc., to which resources on the air interface are allocated and assigned. For example, UE 105 may be a portable computing device, such as a wireless mobile communication device, including but not limited to the following types of devices: mobile station (mobile phone), smart phone, personal digital assistant (PDA), mobile phone, device using wireless modem (alarm or measurement device, etc.), laptop computer and / or touch screen computer, tablet computer, game console, notebook, multimedia device, car, truck, drone, airplane and other types of vehicles. As a non-exhaustive list of some examples, UE 105 may also be referred to as a subscriber unit, mobile station, network element, remote terminal, access terminal or user terminal.

[0066] The techniques and apparatus described herein may relate to implementations embodied by a network element, such as a UE 105, for performing tasks using artificial intelligence. Although some examples described herein broadly refer to artificial intelligence, it should be understood that the term "artificial intelligence" encompasses any type of artificial intelligence, such as machine learning, deep learning, narrow artificial intelligence (e.g., weak artificial intelligence), general artificial intelligence (e.g., strong artificial intelligence), natural language processing (NLP), computer vision, etc.

[0067] Some communication devices (e.g., UE 105, base station 110) can employ artificial intelligence (e.g., artificial intelligence / machine learning) to perform one or more tasks related to use case applications of artificial intelligence (e.g., using artificial intelligence for UE positioning). For example, the communication device can utilize artificial intelligence for channel state information (CSI) feedback (e.g., for CSI feedback enhancement). In this case, the communication device can use artificial intelligence (e.g., using a two-sided artificial intelligence model) to perform spatial and / or frequency domain CSI compression. In addition, or alternatively, the communication device can use artificial intelligence (e.g., using a UE-side model) to perform time domain CSI prediction.

[0068] In some cases, the communication device can utilize artificial intelligence for beam management. For example, the communication device can perform spatial domain downlink beam prediction on the first beam set based on measurements of the second beam set (e.g., historical measurements of the second beam set). In addition, or alternatively, the communication device can perform temporal downlink beam prediction on the first beam set based on measurements of the second beam set (e.g., historical measurements of the second beam set).

[0069] In some cases, the communication device may utilize artificial intelligence for positioning (e.g., for positioning accuracy enhancement). For example, the communication device may perform direct artificial intelligence positioning. In this case, the communication device may utilize an artificial intelligence model to output the location of the communication device (e.g., the location of UE 105). In addition, or alternatively, the communication device may perform one or more fingerprinting operations based on channel observations used as input to the artificial intelligence model. In some cases, the communication device may perform one or more artificial intelligence-assisted positioning operations. For example, the communication device may utilize an artificial intelligence model to output new measurements or enhancements to existing measurements (e.g., measurements of the location of the communication device). In addition, or alternatively, the communication device may (e.g., using an artificial intelligence model) perform line of sight (LOS) or non-line of sight (NLOS) identification, timing and / or angle measurements, and / or one or more operations to determine the likelihood of a measurement (e.g., the likelihood that the communication device is located at a given location).

[0070] Artificial intelligence can be utilized by various communication devices within the wireless communication system 100. Several scenarios or use cases can utilize artificial intelligence in conjunction with positioning tasks. For example, a first use case (e.g., case 1) may include UE-based positioning (e.g., for determining one or more locations of UE 105) using a UE-side model (e.g., a model executed by UE 105). The first use case may also include direct artificial intelligence or artificial intelligence-assisted positioning, which is also referred to as one-step positioning. The second use case (e.g., case 2) may include UE-assisted and location management function (LMF)-based positioning using a UE-side model. For example, an artificial intelligence operation (e.g., an artificial intelligence model) may be run or executed by UE 105. The second use case may also include artificial intelligence-assisted positioning, which is also referred to as two-step positioning. The third use case (e.g., case 3) may include next generation (NG) radio access network (RAN)-assisted positioning using a base station side model. For example, an artificial intelligence operation (e.g., an artificial intelligence model) may be run or executed by base station 110. The third use case may also include artificial intelligence-assisted (e.g., two-step) positioning.

[0071] Although the use cases described herein may refer to positioning operations as an illustrative example, any type of artificial intelligence operation may be implemented for a given use case. For example, any of the use cases described above may be applied to CSI feedback operations, beam management operations, or any other operation performed by a communication device. In addition, any type of communication device (also referred to as a network element) may perform or run an artificial intelligence operation. In some cases, multiple types of communication devices may perform artificial intelligence operations (e.g., concurrently, for the same process). For example, both UE 105 and base station 110 may perform beam management operations using artificial intelligence.

[0072] Some examples described herein may refer to a network node as an LMF, which may be an example of an LCM entity 115 or an LCM function. In some cases, the LMF may perform one or more operations to manage the location of a communication device (e.g., UE 105) within the wireless communication system 100. For example, when the UE 105 registers with the network or moves into the coverage area of ​​the base station 110, the LMF may handle location updates and ensure that the network (e.g., base station 110) has the current location of the UE 105. In some cases, the LMF may be a virtualized entity and may run on a specific network server or network node (e.g., base station 110). The LMF may be implemented by any of the various network nodes in the core radio network.

[0073] Some of the techniques and devices described herein may be related to or implemented as protocols or standardized processes for communication devices. Such techniques may include communication capability indication, configuration and control processes (e.g., training processes, reasoning processes), management of data, and management of artificial intelligence models (e.g., LCM for artificial intelligence models). In some cases, LCM may involve or may include performing operations for: data collection (e.g., including associated auxiliary information, if applicable), model training, function / model identification, model reasoning operations, function / model selection, function / model activation, function / model deactivation, function / model switching, function / model monitoring, model update, model tuning (e.g., model fine-tuning), model retraining, model secondary development via online / offline training, UE capabilities, determinations made by UE 105 (e.g., as triggered by network-configured events, UE determinations reported to the network, UE autonomous decisions with or without UE determinations reported to the network), and determinations made by base station 110 (e.g., network-initiated or UE-initiated and requested from the network).

[0074] The artificial intelligence model may have a model identifier (ID) that may indicate the model (e.g., by type, by parameters associated with the model). In some cases, the model ID may indicate a model function for one or more artificial intelligence operations. The model ID may include one or more bits or other parameters that may correspond to the model (e.g., model type, one or more parameters of the model, model function). Various techniques may be used to identify one or more functions of the artificial intelligence model. For example, some 3GPP frameworks (e.g., utilized for other identifications) may be utilized for functional identification. In some cases, the UE 105 may indicate one or more supported functions (e.g., artificial intelligence model functions) for a specific use case (e.g., for a sub-use case). In some cases, the technique for indicating UE capabilities may be adapted to also include one or more indications of artificial intelligence model functions. In some cases, the model ID may be identified by a model ID at the network. In addition, or alternatively, the UE 105 may indicate one or more supported artificial intelligence models. The techniques described herein for indicating model IDs and functions may be utilized for UE-side models and UE portions of bilateral models.

[0075] For function-based LCM, the network (e.g., core network) may indicate activation / deactivation / fallback / switching of the artificial intelligence function via 3GPP signaling (e.g., radio resource control (RRC) signaling, medium access control element (MAC-CE) signaling, downlink control information (DCI) signaling). In some cases, one or more artificial intelligence models may not be recognizable at the network, and the UE 105 may perform model-level LCM operations. In some other cases, one or more artificial intelligence models may be recognizable at the network. In some cases, one or more functions may be defined within an artificial intelligence-enabled feature (e.g., a feature in which artificial intelligence may be used).

[0076] Some examples described herein may refer to features, functions, and models that can be performed using artificial intelligence. A feature may be the ability (e.g., skill) of a communication device to perform a task or operation. For example, a UE 105 may have a positioning feature (e.g., a location tracking feature) that may enable the location of the UE 105 to be determined (e.g., by the UE 105, by the base station 110). A function may describe how a communication device performs a feature or one or more conditions associated with the feature. For example, a function may specify the number of antenna ports that the UE 105 uses to perform a positioning feature. In some cases, each feature may be associated with one or more functions. A model may be a program or algorithm that is run by a communication device to perform one or more features or tasks. For example, a UE 105 with an artificial intelligence-enabled positioning feature may run an artificial intelligence model to perform the feature. Some examples described herein may also refer to a feature group. A feature group may include a feature set. In some cases, the features included in the feature group may be related to a common theme or function of a communication device. As described herein, the term "implementation" may be used to refer to features, functions, and models collectively and generally. For example, the term "implementation" may describe various options for utilizing a feature, function, model, or any combination thereof.

[0077] For AI function identification and function-based LCM of the UE-side model and / or the UE portion of the bilateral model, the term "function" may refer to an AI-enabled feature or feature group (FG) enabled by one or more configurations, where the one or more configurations are supported based on conditions indicated by UE capabilities. In addition, or alternatively, the function-based LCM operates based on one or more configurations of an AI-enabled feature, feature group (FG), or a specific configuration of an AI-enabled feature or FG.

[0078] In addition to function identification, a mechanism is described for the UE 105 to report updates to applicable functions among the configured / identified functions. In some cases, the UE 105 may or may not report updates to applicable functions. In some cases, the applicable functions may be a subset of all configured / identified functions. In model ID-based LCM, the model is identified at the network. In this case, the network, the UE 105, or both can activate / deactivate / select / switch individual artificial intelligence models via the model ID.

[0079] For artificial intelligence model identification and model ID-based LCM for the UE-side model and the UE portion of the bilateral model, the model ID-based LCM can operate based on the identified model, where the model can be associated with one or more specific configurations or conditions associated with UE capabilities for artificial intelligence-enabled features or feature groups. In addition, or alternatively, the model can be associated with one or more specification configurations or conditions associated with additional conditions (e.g., scenarios, sites, data sets) as determined or otherwise identified by the UE 105 or base station 110.

[0080] In some cases, the artificial intelligence model identified by the model ID may be logical, and how it maps to a physical artificial intelligence model may depend on the implementation (e.g., by the UE 105). In some cases, the phrase "logical artificial intelligence model" may refer to a model that is identified and assigned a model ID, and the phrase "physical artificial intelligence model" may refer to the actual implementation of such a model.

[0081] The efficiency of selection, activation, deactivation, switching, and fallback for artificial intelligence operations (e.g., tasks, functions, models) can play a key role in effectively utilizing artificial intelligence at a communication device. As described herein, the term "switching" can refer to deactivating a first model (e.g., a current model) and activating a second model (e.g., a new model) to perform the same task. Additionally, the term "fallback" can refer to deactivating an artificial intelligence model and performing a task without using the artificial intelligence model, such as using a traditional implementation.

[0082] In some cases, one or more capabilities of the UE 105 (e.g., resource availability conditions) may be relatively static (e.g., not expected to change within a relatively short time frame). In some other cases, one or more capabilities of the UE 105 may be relatively dynamic. For example, one or more conditions (e.g., dynamic conditions) may affect whether the UE 105 utilizes or switches to an artificial intelligence function / model at a particular time. Examples of such conditions include the availability of resources, such as the processing power of the UE 105 to perform one or more artificial intelligence functions. Although the artificial intelligence model is utilized by the UE 105 to perform one or more tasks (e.g., location estimation), the UE 105 may perform as expected in certain environments and situations, but the UE 105 may not be able to run the artificial intelligence model due to an overload of the central processing unit (CPU) of the UE 105. For example, the resources of the CPU may be prioritized or allocated for other tasks, which may produce an unexpected but temporary decrease in the performance of the artificial intelligence model. In this case, switching to another model with similar resource availability requirements may not improve the ability of the UE 105 to run the artificial intelligence model. However, the UE 105 of example embodiments may be configured to address model selection, activation, deactivation, switching, and fallback in such resource-constrained situations of the UE 105 .

[0083] According to one or more aspects of the present disclosure, a communication device (e.g., UE 105, base station 110) may be configured with multiple implementations (e.g., options, configurations, mappings) for performing operations (e.g., tasks) using artificial intelligence, and in some instances, without using artificial intelligence. The communication device may be actively configured with such implementations so that the operation of the communication device can be customized according to a specific resource scenario when a specific resource scenario occurs (e.g., in the case where UE 105 experiences a reduction in available resources for performing artificial intelligence tasks). According to the techniques described herein, a location server (e.g., LMF) or other network node may configure a UE 105 that is capable of performing a task using artificial intelligence (e.g., positioning functionality) before the UE 105 performs the task. Thus, the UE 105 may be able to determine an implementation to be utilized when processing resources are insufficient. As an example, if processing resources are insufficient for a more computationally intensive implementation that utilizes artificial intelligence, the UE 105 may switch to a model with lower computational complexity or fall back to a non-artificial intelligence task with lower computational complexity.

[0084] In some cases, such implementation (e.g., configuration) may be associated with the required resource allocation via a mapping table provided to the UE 105 by a network node (e.g., LCM 115, LMF), which may map the requested UE-side artificial intelligence feature, function, or model to the corresponding resource condition (e.g., range of resources, resource boundary) of the UE 105. According to the techniques described herein, if the current UE-side artificial intelligence feature, function, or model cannot be performed as desired at the UE 105, the UE 105 may switch to a different artificial intelligence feature, function, or model based on the implementation provided by the network node and the associated required resource allocation. In some cases, as an example, if resource availability does not permit the performance of artificial intelligence-assisted positioning, the UE may switch to performing a different positioning function that does not involve artificial intelligence or machine learning processing.

[0085] Figure 2 An example of an apparatus 200 supporting a method for actively communicating a resource mapping to a network element implementation for performing a task is shown. The apparatus 200 may be embodied by or may include a network element, such as a UE 105 or a base station 110, configured to perform one or more tasks using a plurality of different implementations, at least one of which relies on artificial intelligence. Figure 2 As shown in , the device 200 may include, be associated with or communicate with a processing circuit 205 (e.g., one or more processors), a memory 210 and a communication interface 215. The processing circuit may communicate with the memory 210 via a bus for transferring information between components of the device. The memory 210 may be non-transitory and may include, for example, one or more volatile and / or non-volatile memories. In other words, for example, the memory 210 may be an electronic storage device (e.g., a computer-readable storage medium) that includes a storage component configured to store data (e.g., bits) that can be retrieved by a machine (e.g., a computing device like the processing circuit 205). The memory 210 may be configured to store information, data, content, applications, instructions, etc., so that the device 200 can perform various functions according to the example embodiments of the present disclosure. For example, the memory 210 may be configured to buffer input data for processing by the processing circuit 205. In addition, or alternatively, the memory 210 may be configured to store instructions for execution by the processing circuit 205.

[0086] In some embodiments, the apparatus 200 may be embodied in various computing devices as described above. However, in some embodiments, the apparatus 200 may be embodied as a chip or a chip set. In other words, the apparatus 200 may include one or more physical packages (e.g., chips) that include materials, components, and / or wires on a structural assembly (e.g., a substrate). The structural assembly may provide physical strength, savings in size, and / or limitations on electrical interactions for the component circuits included thereon. Thus, in some cases, the apparatus 200 may be configured to implement embodiments of the present invention on a single chip or as a single "system on a chip." Thus, in some cases, a chip or a chip set may constitute a component for performing one or more operations to provide the functionality described herein.

[0087] The processing circuit 205 can be embodied in a variety of different ways. For example, the processing circuit 205 can be embodied as one or more of various hardware processing components such as a coprocessor, a microprocessor, a controller, a digital signal processor (DSP), a processing element with or without an accompanying DSP, or various other circuits, including integrated circuits, such as, for example, ASICs (application specific integrated circuits), FPGAs (field programmable gate arrays), microcontroller units (MCUs), hardware accelerators, special-purpose computer chips, etc. Therefore, in some embodiments, the processing circuit 205 may include one or more processing cores configured to execute independently. Multi-core processing circuits can implement multi-processing within a single physical package. In addition, or alternatively, the processing circuit 205 may include one or more processors configured in series via a bus to implement independent execution of instructions, pipelining, and / or multi-threading.

[0088] In an example embodiment, the processing circuit 205 may be configured to execute instructions stored in the memory 210 or otherwise accessible to the processing circuit 205. In addition, or alternatively, the processing circuit 205 may be configured to execute hard-coded instructions. Therefore, whether configured by hardware or software methods, or by a combination of the two, the processing circuit 205 may represent an entity (e.g., physically embodied in a circuit) that is capable of performing operations according to embodiments of the present disclosure while being configured accordingly. Therefore, for example, when the processing circuit 205 is embodied as an ASIC, FPGA, etc., the processing circuit 205 may be specially configured hardware for performing the operations described herein. Or, as another example, when the processing circuit 205 is embodied as an executor of instructions, the instructions may specifically configure the processing circuit 205 to perform the algorithms and / or operations described herein when executing the instructions. However, in some cases, the processing circuit 205 may be a processor of a specific device (e.g., an image or video processing system) that is configured to employ embodiments of the present invention by further configuring the processing circuit 205 by instructions for performing the algorithms and / or operations described herein. The processing circuit 205 may include, among other things, a clock, an arithmetic logic unit (ALU), and logic gates configured to support the operation of the processing circuit 205 .

[0089] The communication interface 215 can be any component, such as a device or circuit embodied in hardware or a combination of hardware and software, which is configured to receive and / or send data, including media content in the form of video or image files, one or more audio tracks, etc. In this regard, the communication interface 215 may include, for example, an antenna (or multiple antennas) and supporting hardware and / or software for enabling communication with a wireless communication network (e.g., with one or more communication devices of the wireless communication system 100). In addition, or alternatively, the communication interface 215 may include one or more antennas to enable transmission of signals via one or more antennas or processing of reception of signals received via one or more antennas. In some environments, the communication interface 215 may alternatively or also support wired communications. Thus, for example, the communication interface 215 may include a communication modem and / or other hardware / software for supporting communication via cable, digital subscriber line (DSL), universal serial bus (USB) or other mechanisms.

[0090] In some cases, the device 200 can be configured to perform one or more tasks related to a use case application of artificial intelligence (e.g., using artificial intelligence for UE positioning). For example, the device 200 can be configured to utilize one or more machine learning models for one or more CSI processes, such as a CSI determination process. In this case, the device 200 can utilize the machine learning model to predict the CSI of one or more channels, which can enhance one or more operations performed by the device 200. In addition to machine learning-assisted CSI processes, the device 200 can also utilize one or more artificial intelligence models for beam management, for positioning, or for any other type of operation performed by the device 200. However, utilizing artificial models for various operations at the device 200 may consume more resources than performing the same tasks without relying on artificial intelligence.

[0091] According to one or more aspects of the present disclosure, the device 200 may be (e.g., actively) configured with a mapping table that links (e.g., associates, pairs) corresponding implementations (e.g., configurations, operations, features, functions, models, model parameters) for performing one or more tasks with corresponding required resource allocations of the device 200, where resources refer to physical resources at the device or resources provided by another network entity for the device to perform the corresponding tasks. The device 200 may then select an implementation corresponding to the current conditions of the device 200, which may improve resource utilization and performance of the device 200.

[0092] Figure 3 An example of a signal flow graph 300 of an example embodiment of the present disclosure is shown. The signal flow graph 300 may include communications between a network element 305 (such as a UE), a radio access network (RAN) node 310, and a network node 115 of a core network (such as an LCM entity 115). The network element 305, the RAN node 310, and the network node may be reference Figure 1 and Figure 2 For example, the network element 305 may be an example of the UE 105, the RAN node 310 may be an example of the base station 110 of the RAN, and the network node may be as described in reference Figure 1 The described LCM entity 115 (such as LMF). According to an example embodiment, the signal flow diagram 300 may depict the communication between the network element 305, the RAN node 310 and the network nodes (eg, LCM 115, LMF).

[0093] At 315, the network element 305 may cause resource availability information to be transmitted to a network node (e.g., the LCM entity 115). Resource availability information may be provided for various types of resources. For example, resource types may include processing power (e.g., of a graphics processing unit (GPU), a CPU, a tensor processing unit (TPU)), available memory (e.g., a random access memory (RAM)), power (e.g., a battery state, including a related power level relative to a threshold level, a CPU throttling level), input conditions of the network element 305, output conditions of the network element 305, and a connection state and / or quality of the network element 305. Some example input / output conditions of the network element 305 may include one or more conditions indicating whether a sensor is blocked or sensor data is lost. In some cases, the data obtained by the sensor may be used as a label during the training of a radio frequency (RF)-based artificial intelligence positioning method.

[0094] In instances where resource availability may vary in a predictable manner (such as based on previous calculations performed for the same task), the resource availability information may include a resource availability pattern. In this regard, the resource availability pattern may be referred to as dynamic by a parameter (e.g., a flag comprising one or more bits). Then, the network node (e.g., LCM entity 115) may know that the resources used by the network element 305 to perform tasks (including those tasks that may be performed using artificial intelligence (e.g., positioning tasks, beam management tasks, CSI tasks, etc.)) are not constant but dynamically allocated. In addition, or alternatively, the network element 305 may indicate the timing (e.g., resource density) associated with the resource requirements. For example, the artificial intelligence model may utilize resources for a relatively short period of time at each inference (i.e., the resource requirements of the artificial intelligence model are not constant). In some cases, when artificial intelligence-related resources (as an example) for positioning are available or at a threshold (e.g., a minimum or maximum level or range), the network element 305 may indicate to the network node (e.g., LCM entity 115) a resource availability pattern in terms of (e.g., including) an expected area (e.g., a geographic area) and / or an expected time period. Such artificial intelligence-related resources for positioning may refer to physical resources available at the network element 305 or positioning resources provided by another network element (e.g., the LCM entity 115) for the network element 305 to perform positioning, such as the number of detected positioning reference signals and their corresponding detection or reception quality.

[0095] In some cases, the network element 305 may indicate geographic boundaries within which it expects to deploy artificial intelligence computing resources above a given threshold (e.g., a resource threshold, a geographic threshold, a time threshold). In some cases, the network element 305 may indicate to a network node (e.g., an LCM entity 115) one or more time periods or time windows during which consumption of computing resources is expected to be above or below a given threshold. By way of example, the network element 305 may know that during a certain time of day, there may be more objects in an area than during other times of the day, which may result in the use of non-line-of-sight (NLOS) positioning, which further increases CPU requirements. In this case, the network element 305 may communicate the resource availability pattern to a network node, such as the LCM entity 115.

[0096] In some cases, the network element 305 may indicate to a network node, such as the LCM entity 115, the percentage of the total available AI-related resources that are currently allocated for positioning (e.g., because 20% of the AI ​​processing power is currently dedicated to positioning-related AI tasks). In some cases, the network element 305 indicates the percentage of AI-related resources expected to be deployed for positioning as a function of a future time window. In some cases, the network element 305 indicates the percentage of AI-related resources expected to be deployed for positioning as a function of a geographic area (e.g., a geo-fenced area). In some cases, the network element 305 indicates positioning resources (e.g., detected positioning reference signals) provided by another network entity (e.g., the LMF or the LCM entity 115) that are expected to be detectable at the network element 305 during a future time window or in a geographic area (or both).

[0097] At 320, the network node (e.g., LCM entity 115) may cause information indicating an association between (i) a plurality of implementations for the network element of the wireless communication system to perform a respective task and (ii) resource allocation required for the network element to perform the respective task according to one or more respective implementations of the plurality of implementations to be transmitted toward the network element 305. In an example embodiment, the information may be in the form of one or more mappings.

[0098] With respect to the mapping table, an example of a mapping table may include one or more inputs indicating one or more ranges (e.g., by minimum and / or maximum values) of computing resources that the network element 305 will need to deploy to perform a task, such as positioning, utilizing a specific implementation, such as an implementation that relies on artificial intelligence or an implementation that does not rely on artificial intelligence. The mapping table may include one or more outputs indicating a specific implementation associated with the required resource allocation, such as one or more artificial intelligence-related positioning functions as a function of the one or more required resource allocations. Examples of such positioning functions may include one-step positioning or direct artificial intelligence-assisted positioning (e.g., fingerprint positioning methods) versus two-step positioning or artificial intelligence-assisted positioning (e.g., artificial intelligence-related methods for line of sight (LOS) identification and conventional positioning methods, such as downlink / uplink (DL / UL) time difference of arrival (TDoA)), iterative refinement of the position estimate by a hybrid positioning method (e.g., applying multiple positioning methods to converge to a high accuracy estimate), or by positioning reference unit (PRU) related correction data. In some cases, the network element 305 can be configured such that if the available resources fail to meet a threshold associated with a particular implementation utilizing artificial intelligence (e.g., fall below a threshold), the network element 305 can abandon the artificial intelligence-assisted positioning implementation and revert to a non-artificial intelligence positioning implementation (e.g., DL-TDoA, UL-TDoA, DL Angle of Departure (AoD), etc.). In some cases, the mapping table can include one or more inputs that indicate one or more ranges (e.g., by minimum and / or maximum values) of computing resources (e.g., the number of detected positioning reference signals and the quality of each) that the network element 305 will need to deploy to perform a task, such as positioning, utilizing a particular implementation, such as an implementation that relies on artificial intelligence or an implementation that does not rely on artificial intelligence, relative to resources provided by another network node for the network element 305 to perform a corresponding task (e.g., artificial intelligence-assisted positioning).

[0099] In some cases, the implementation identified by the mapping table may include or be associated with a set of conditions that the mapping table application is to satisfy. Such conditions may include a level of a signal-to-noise ratio (SINR) associated with one or more positioning-related measurements, a time window during which the mapping table is valid, and / or a geographic area in which the mapping table is valid. In some cases, a network node (such as an LCM entity 115) may assign priorities to different implementations for performing a task, which define an order of precedence. The order of priority may indicate which implementation is used first to perform a task in the case of limited computing resources (e.g., for a network element 305).

[0100] In some other cases, the implementation identified by the mapping table may include or be associated with one or more relaxation parameters such that the network element 305 is permitted to reduce the frequency of inference of the model (e.g., the network element 305 may be configured to be permitted to reduce the frequency of reports containing inference outputs of an artificial intelligence model to temporarily make additional resources available for another model). Based on the available resources, the network element 305 may then perform the implementation as configured by the network node (e.g., LCM entity 115), such as an artificial intelligence-related positioning model or function.

[0101] In some cases, the network element 305 with artificial intelligence capabilities may be able to run parallel artificial intelligence models simultaneously. For example, the network element 305 may simultaneously run models for positioning, CSI feedback for massive multiple input multiple output (MIMO), and beam management. In this case, the RAN node 310 may assign new tasks to the network element 305 at any time. The network element 305 may be configured to then estimate the computing resources required for each assigned artificial intelligence-related task. In this case, the network element 305 may reduce the computing resources assigned to the pre-existing tasks so as to have sufficient resources to perform all tasks in parallel, including the newly assigned tasks. This event may trigger the operations performed at 345.

[0102] At 325, the network element 305 may perform a specific implementation of the task, such as one or more artificial intelligence models or one or more artificial intelligence features. The implementation utilized may be based on a mapping table provided by the RAN node 310 and resources available at the network element.

[0103] At 330, the RAN node 310 may optionally assign one or more additional tasks to the network element 305. The one or more tasks may be one or more tasks that may be performed using an artificial intelligence implementation. For example, the RAN node 310 may assign one or more CSI feedback tasks or one or more beam management calculations to the network element 305 that has performed the initial task using an artificial intelligence implementation. By way of example and not limitation, the initial task will hereinafter be referred to as a positioning task.

[0104] At 335 , network element 305 may process the parallel artificial intelligence implementation to estimate the computing resources required to perform the implementation of the various tasks.

[0105] At 340, the network element 305 may adjust one or more task priorities (e.g., for the assigned one or more tasks). For example, due to an outage from the RAN node 310 that assigned the network element 305 additional tasks, the network element 305 may lower the priority of the positioning tasks.

[0106] At 345, the network element 305 may select a mapping (e.g., select an implementation from a mapping table), and at 350, the network element may update an implementation that performs one or more tasks that are being performed simultaneously. For example, the network element 305 may process the mapping table and determine to switch implementations (e.g., switching models, switching parameters) or fall back to different implementations of the positioning task, depending on the allocation of resources available at the network element to perform the positioning task relative to the resources required for the different implementations to perform the positioning task. In some cases, the triggering of the modification of the computational resources for artificial intelligence positioning may be internal to the network element 305.

[0107] By way of example, if configured accordingly, the network element 305 may switch from the computationally heavier one-step AI positioning to the two-step positioning, thereby allowing resource balancing between AI-based positioning and other AI-related tasks (e.g., CSI feedback, beam feedback for massive MIMO).

[0108] In some cases, the network element 305 can be configured to stop AI positioning and transition to a non-AI positioning implementation (e.g., DL-TDoA) to further save resources. The network element 305 can then update the AI-related functions running in parallel at the network element 305. That is, the network element 305 can perform the selection, activation, deactivation, switching, or fallback of AI implementations at the network element 305, which can include implementations that perform tasks such as CSI feedback and beam management.

[0109] At 355, once the operation of the network element 305 converges to a steady state, the network element 305 may indicate (e.g., to the RAN node 310, to a network node such as the LCM entity 115) one or more selected mappings, such as by indicating the implementation that has been selected and is being executed for each task. In some cases, the network element may indicate the computational resources allocated for each implementation, including for each artificial intelligence-related implementation (e.g., positioning, CSI feedback, beam management). In some cases, the network element 305 may report the achieved quality of service (QoS) for each implementation including each artificial intelligence-related function. In addition, or alternatively, the network element 305 may report a portion (e.g., one or more fields) of the mapping table configured (e.g., received) at 320, which is used to arrive at an updated set of implementations, including those that are artificial intelligence-related implementations.

[0110] Figure 4 An example of a table 405 is shown, which may be used or otherwise stored by a communication device (such as a network element 305, for example a UE or a base station of a RAN) after being provided by a network node 115 of a core network, as shown in FIG. Figure 3The information stored in one or more of the tables 405 may be utilized to select an implementation for performing one or more tasks, as described herein. Figure 4 The table 405 described includes information related to the location of the communication device, but one or more tables 405 can be utilized to store information related to any type of task. In addition, it should be noted that the table 405 described herein provides an illustrative example of a data structure that can be utilized to organize and store a map of information. However, other data structures can be utilized to perform the techniques described herein.

[0111] Table 405-a may include resource availability information (e.g., of UE 105), which may be provided to a network node. Table 405-a may include a plurality of rows 410 (e.g., row 410-a, row 410-b, row 410-c, row 410-d, and row 410-e) and a plurality of columns 415 (e.g., column 415-a, column 415-b, column 415-c, column 415-d, and column 415-e). Table 405-a may include a plurality of information elements, which may be identified by or otherwise correspond to the respective rows 410 and columns 415. Column 415-a may include a title or information identifying the respective row 410. Row 410-a may include a title or information identifying the respective column 415. Column 415-b may include a corresponding percentage or absolute amount of available memory for UE 105, column 415-c may include a corresponding percentage or absolute amount of CPU processing power available at UE 105, column 415-d may include a corresponding time period (e.g., time window) for which the indicated information (e.g., memory, CPU power) is valid, and column 415-e may include a corresponding use case (e.g., a corresponding task type). As an illustrative example, the information included in row 410-c of table 405-a may indicate that, for a given time range (e.g., 9:00 to 17:00), UE 105 has or is expected to have 128 megabits (mbits) of memory and 65% of the total CPU processing power available. In addition, row 410-a may include a total amount of resources for UE 105 (e.g., the total amount of memory for UE 105 may be 256 mbits).

[0112] Table 405-b may be information for various artificial intelligence models (e.g., utilized by UE 105) that may be provided to a network node. Table 405-b may include multiple rows 410 (e.g., row 410-f, row 410-g, and row 410-h) and multiple columns 415 (e.g., column 415-f, column 415-g, column 415-h, column 415-i, and column 415-j). Table 405-b may include multiple information elements, which may be identified by or otherwise correspond to corresponding rows 410 and columns 415. Column 415-f may include a title or information identifying the corresponding row 410. Row 410-a may include a title or information identifying various implementations or methods utilized by UE 105. For example, UE 105 may perform a first implementation (e.g., a first TDOA implementation) or a second implementation (e.g., a second TDOA implementation). In some cases, various implementations or methods may be associated with corresponding memory usage, CPU usage, duty cycle, and accuracy, which may be indicated by columns 415-g, 415-h, 415-i, and 415-j, respectively. As an illustrative example, and as indicated by row 410-g, UE 105 may perform a positioning task using a first implementation (e.g., a first TDOA method) that utilizes 64 mbits of memory, 25% of the total CPU power of UE 105, has a duty cycle of 10%, and has an accuracy of 95%.

[0113] Table 405-c may include mapping information, which may be provided by a network node to UE 105. The mapping information may associate respective implementations (e.g., methods) for performing one or more respective tasks with respective resource conditions (e.g., required resource allocations) of UE 105. The mapping information may also include respective priorities and respective fallback implementations corresponding to the respective implementations and resource conditions.

[0114] Table 405-c may include a plurality of rows 410 (e.g., row 410-i, row 410-j, row 410-k, row 410-L, and row 410-m) and a plurality of columns 415 (e.g., column 415-k, column 415-L, column 415-m, column 415-n, and column 415-o). Table 405-c may include a plurality of information elements, which may be identified by or otherwise correspond to respective rows 410 and columns 415. Row 410-i may include a header or information identifying respective columns 415. Column 415-k may include a priority of the respective implementation (e.g., where "0" is the highest priority), column 415-L may include a memory range of the respective implementation, column 415-m may include a CPU range of the respective implementation, column 415-n may include a respective implementation (e.g., a primary implementation), and column 415-o may include a fallback implementation of the respective implementation. As an illustrative example, the information included in row 410-j of table 405-c may indicate that if UE 105 has more than 64 mbits of memory and more than 25% of total CPU power available, UE 105 should utilize a first implementation (e.g., TDOA method 1) to perform one or more given tasks. The information included in row 410-j may also indicate that if one or more current resource availability conditions fail to meet corresponding thresholds (e.g., if the current available memory is less than 64 mbits, or if the current available CPU power is less than 25%), UE 105 should fall back to a second implementation (e.g., DLAoD method 2).

[0115] Figure 5 An example of a flowchart 500 showing operations performed by an apparatus, such as may be embodied by a network element 305, a UE 105, a base station of a RAN, etc., as shown in FIG. Figure 1 and Figure 3 As shown in block 505, the apparatus may include means, such as the processing circuit 205, the communication interface 215, etc., for receiving information indicating an association between (i) a plurality of implementations of a network element of the wireless communication system to perform a corresponding task and (ii) resource allocation required for the network element to perform the corresponding task according to one or more corresponding implementations of the plurality of implementations from a network node (e.g., the LCM entity 115).

[0116] In some cases, multiple implementations correspond to one or more of: one or more implementations of an apparatus associated with a corresponding artificial intelligence or machine learning enabled feature or feature group, one or more implementations of an apparatus associated with a corresponding artificial intelligence or machine learning enabled functionality, or one or more implementation variants for an apparatus associated with a given artificial intelligence or machine learning enabled functionality.

[0117] In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that rely on artificial intelligence or machine learning. In some cases, the plurality of implementations include one or more implementations for performing the respective tasks that do not rely on artificial intelligence or machine learning. In some cases, selecting the first implementation from the plurality of implementations is based at least in part on a priority associated with the respective implementation in the plurality of implementations.

[0118] As shown in block 510, the apparatus may include means, such as processing circuit 205, for selecting a first implementation from a plurality of implementations to perform a corresponding task based at least in part on available resources of a network element to perform the corresponding task relative to an allocation of resources required to perform the corresponding task according to the first implementation.

[0119] As shown in block 515 , the apparatus further includes means, such as processing circuitry 205 , for performing corresponding tasks according to the first implementation.

[0120] The device may also include a component for transmitting resource availability information to a network node, wherein multiple implementations are at least partially based on resource availability information. In some cases, two or more of the multiple implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information of the processing resources of the device, availability information of the memory resources of the device, battery life information of the device, availability information of one or more inputs for performing the corresponding task, availability information of one or more outputs for the corresponding task, connection status of the device with the wireless communication system, or connection quality of the device with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing the corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, if the received power for the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold, "detection" may occur. Thresholds may be specified for time and frequency resources allocated to the detected positioning reference signal.

[0121] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, so that the availability of the resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., changing in the lowest time unit level), or any level of dynamism in between. In some instances, the dynamic resource availability information can be valid for a limited duration. In some cases, the resource availability information indicates one or more geographic areas in which one or more resources of the device are available, and outside the geographic area, one or more resources of the device are not available, or a time period during which one or more resources are available, and outside the time period, one or more resources of the device are not available.

[0122] In some cases, the resource availability information indicates one of: a percentage of a resource that is available relative to a total amount of a corresponding resource of the device, a percentage of a resource that is available relative to a threshold amount of a corresponding resource of the device, or an absolute amount of a resource that is available. With respect to available memory, for example, the resource availability information of one embodiment may indicate that a specific percentage (e.g., 20%) of the total memory capacity is available, while in another embodiment, the resource availability information may indicate that 5 gigabytes (GB) of memory is available.

[0123] Figure 6 An example of a flowchart 600 showing operations performed by an apparatus, such as may be embodied by a network node (eg, LCM entity 115), as shown in FIG. Figure 1 and Figure 3 As shown in block 605, the apparatus may include means for causing information to be transmitted toward a network element of the wireless communication system, the information indicating an association between (i) a plurality of implementations of the network element of the wireless communication system to perform a corresponding task and (ii) resource allocation required for the network element to perform the corresponding task according to one or more corresponding implementations of the plurality of implementations, such as the processing circuit 205, the communication interface 215, etc.

[0124] In some cases, the multiple implementations correspond to one or more of: one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled features or feature groups, one or more implementations of network elements associated with corresponding artificial intelligence or machine learning enabled functions, or one or more implementation variants of network elements associated with a given artificial intelligence or machine learning enabled function.

[0125] In some cases, the plurality of implementations include one or more implementations that rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, the plurality of implementations include one or more implementations that do not rely on artificial intelligence or machine learning to perform the corresponding tasks for the network element. In some cases, corresponding implementations in the plurality of implementations are assigned corresponding priorities.

[0126] As shown in block 610, the apparatus may include means for receiving information from a network element, such as processing circuitry 205, communication interface 215, or the like, indicating that a first implementation of a corresponding task is to be performed.

[0127] In some cases, the apparatus may further include a component for receiving resource availability information for the network element from the network element, wherein the plurality of implementations are based at least in part on the resource availability information. In some cases, two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models. In some cases, the resource availability information includes one or more of the following: availability information for processing resources of the network element, availability information for memory resources of the network element, battery life information of the network element, availability information of one or more inputs of the network element, availability information of one or more outputs of the network element, connection status of the network element with the wireless communication system, or connection quality of the network element with the wireless communication system. In some cases, in addition to other examples of resource availability information described herein (e.g., physical resources at a network element for performing a task), the resource availability information may also include availability information of resources allocated by another network entity to a network entity performing a corresponding task. As an example, if the network entity is a device performing a positioning task, the resource availability information may include the number of positioning reference signals and / or the number of transmission / reception points detected at the network entity. In this case, "detection" may occur if the received power of the positioning reference signal from the transmission / reception point meets (e.g., is higher than) a specified threshold. Thresholds may be specified for time and frequency resources allocated to detected positioning reference signals.

[0128] In some cases, the resource availability information indicates whether the resource availability information is dynamic or static. In some cases, the level of dynamic resource availability can involve multiple levels of dynamism, such that the availability of a resource can range from completely static (i.e., no dynamism) to completely dynamic (i.e., varying in the lowest time unit level), or any level of dynamism in between. In some embodiments, the dynamic resource availability information is valid for a limited duration. In some cases, the resource availability information indicates one or more of the following: a geographic area in which one or more resources of the network element are available, and outside the geographic area one or more resources of the network element are not available, or a time period during which one or more resources of the network element are available, and outside the time period, one or more resources of the network element are not available.

[0129] In some cases, the resource availability information indicates one of: a percentage of resources available relative to a total amount of the corresponding resource of the network element, a percentage of resources available relative to a threshold amount of the corresponding resource of the network element, or an absolute amount of resources available.

[0130] As described above, the network element 305 can be configured to select a specific implementation of the task based on the current status of the network element and information provided by the network node, the information indicating an association between (i) multiple implementations of the network element to perform the task and (ii) resource allocation required for the network element to perform the task according to one or more corresponding implementations of the multiple implementations. Therefore, resource utilization and performance of the network element can be enhanced by selecting an implementation that is consistent with the resources available to the network element (such as an artificial intelligence-enabled implementation).

[0131] Figure 3 , Figure 5 and Figure 6Flowcharts and signal flow diagrams of methods according to example embodiments are shown. It will be understood that each block or signal and combinations of blocks and signals can be implemented by various components such as hardware, firmware, processors, circuits, and / or other communication devices associated with executing software including one or more computer program instructions. For example, one or more of the above processes can be embodied by computer program instructions. In this regard, the computer program instructions embodying the above processes can be stored by the memory 210 of the device using the example embodiment and executed by the processing circuit 205. As will be appreciated, any such computer program instructions can be loaded onto a computer or other programmable device (e.g., hardware) to produce a machine so that the resulting computer or other programmable device implements the functions specified in the flowchart blocks. These computer program instructions can also be stored in a computer-readable memory, which can instruct the computer or other programmable device to operate in a specific manner so that the instructions stored in the computer-readable memory produce an article, the execution of which implements the functions specified in the flowchart blocks. The computer program instructions can also be loaded onto a computer or other programmable device so that a series of operations are performed on the computer or other programmable device to produce a computer-implemented process so that the instructions executed on the computer or other programmable device provide operations for implementing the functions specified in the flowchart blocks.

[0132] Therefore, the blocks of the flowchart support the combination of components for performing the specified functions and the combination of operations for performing the specified functions. It will also be understood that one or more blocks of the flowchart and the combination of blocks in the flowchart can be implemented by a computer system based on special-purpose hardware or a combination of special-purpose hardware and computer instructions that performs the specified functions.

[0133] Those skilled in the art of the present invention will appreciate many modifications and other embodiments of the present invention set forth herein, having benefited from the teachings presented in the foregoing description and the associated drawings. It should be understood, therefore, that the present invention is not limited to the specific embodiments disclosed, and modifications and other embodiments are intended to be included within the scope of the appended claims. In addition, although the foregoing description and the associated drawings describe example embodiments in the context of certain example combinations of elements and / or functions, it should be appreciated that different combinations of elements and / or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, for example, combinations of elements and / or functions different from those explicitly described above are also foreseen, as may be set forth in some of the claims in the appended claims. Although specific terms are employed herein, they are used only in a general and descriptive sense, and not for limiting purposes.

Claims

1. A device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least perform: receiving information from a network node of a wireless communication system, the information indicating an association between: (i) a plurality of implementations of a network element of the wireless communication system to perform a respective task and (ii) a resource allocation required by the network element to perform the respective task according to one or more respective implementations of the plurality of implementations; selecting the first of the plurality of implementations to perform the corresponding task based at least in part on an allocation of resources available to the network element to perform the corresponding task relative to the required resources to perform the corresponding task according to the first implementation; performing the corresponding task according to the first implementation; as well as Causes transmission to the network node of information indicative of the first implementation selected to perform the respective task.

2. The apparatus of claim 1 , wherein the plurality of implementations correspond to one or more of: one or more implementations of said network elements associated with corresponding artificial intelligence or machine learning enabled features or groups of features; one or more implementations of said network elements associated with corresponding artificial intelligence or machine learning enabled functionality; or One or more implementation variants of the network element associated with a given artificial intelligence or machine learning enabled functionality.

3. The apparatus according to any one of claims 1 to 2, wherein the plurality of implementations comprises: One or more implementations that rely on artificial intelligence or machine learning to perform the corresponding tasks.

4. The apparatus of claim 3, wherein two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models.

5. A device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least perform: causing transmission of information towards a network element of a wireless communication system, the information indicating an association between: (i) a plurality of implementations for the network element of the wireless communication system to perform a respective task and (ii) a resource allocation required for the network element to perform the respective task according to one or more respective ones of the plurality of implementations; and Information instructing to perform a first implementation of the corresponding task is received from the network element.

6. The apparatus of claim 5, wherein the plurality of implementations correspond to one or more of: one or more implementations of said network elements associated with corresponding artificial intelligence or machine learning enabled features or groups of features; one or more implementations of said network elements associated with corresponding artificial intelligence or machine learning enabled functionality; or One or more implementation variants of the network element associated with a given artificial intelligence or machine learning enabled functionality.

7. The apparatus according to any one of claims 5 to 6, wherein the plurality of implementations comprises: The network element relies on artificial intelligence or machine learning to perform one or more implementations of the corresponding tasks.

8. The apparatus of claim 7, wherein two or more of the plurality of implementations are associated with different types of artificial intelligence or machine learning models.

9. A device for use in a communication network, comprising: means for receiving information from a network node of a wireless communication system, the information indicating an association between: (i) a plurality of implementations for a network element of the wireless communication system to perform a respective task and (ii) resource allocation required for the network element to perform the respective task according to one or more respective ones of the plurality of implementations; for selecting the first of the plurality of implementations to perform the corresponding task component based at least in part on available resources of the network element to perform the corresponding task relative to the required allocation of resources to perform the corresponding task according to the first implementation; means for performing said corresponding task according to said first implementation; as well as Means for causing transmission to the network node of information indicative of the first implementation selected to perform the respective task.

10. A device for use in a communication network, comprising: means for causing transmission of information towards a network element of a wireless communication system, the information indicating an association between: (i) a plurality of implementations for the network element of the wireless communication system to perform a respective task and (ii) resource allocation required for the network element to perform the respective task in accordance with one or more respective ones of the plurality of implementations; as well as Means for receiving, from the network element, information indicative of performing a first implementation of the corresponding task.

Images