System, method, device, and program for managing the interface of AI / ML applications via wireless access parameters

Abstract

A method for adaptive machine learning related action signaling in a telecommunications network may be provided. The method may be executed by at least one processor and may include detecting, by a user device, a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol, transmitting, by the user device, first information related to the transition in response to detecting the transition, receiving, by the user device, change information related to a target action based on the first information transmitted by the user device, and performing, by the user device, the target action based on the change information.

Description

[Technical field]

[0001] The present disclosure relates to managing Artificial Intelligence and Machine-Learning (AI / ML) models using radio access parameters and interfaces. In particular, the present disclosure relates to methods, apparatus, and systems for adaptive machine learning related operation(s) signaling in telecommunications and / or wireless networks. [Background technology]

[0002] In telecommunication networks, AI / ML modeling can be used to optimize multiple functions performed by components of the telecommunication network. While there are some discussions on using AI / ML models to optimize some functions of a telecommunication network, those discussions may focus on application frameworks, model evaluation, etc. However, there are no existing standards or discussions on the use of specific radio access parameters, New Radio protocols, and / or interfaces to manage AI / ML models. For example, there is no discussion on specific radio access parameters, New Radio protocols, and / or interfaces that may be used to signal coordination information, user device capability information, or other parameters that impact the real-time application of the optimized AI / ML models in the telecommunication network.

[0003] In other words, there is no discussion and / or consensus regarding the management of AI / ML models and their application in telecommunications networks. More specifically, there is no discussion and / or standards related to signaling dynamic application of AI / ML functionality using radio access parameters. This lack of signaling guidance can result in ineffective utilization of AI / ML modeling in telecommunications networks, increasing latency and inefficiencies in the telecommunications networks.

[0004] Therefore, there is a need to define which radio access parameters, New Radio protocols, and / or New Radio interfaces can be used to effectively leverage and dynamically manage the use of AI / ML in telecommunication networks. Summary of the Invention

[0005] According to an embodiment, a method for adaptive machine learning related action signaling in a telecommunications network is provided. The method may be executed by at least one processor and may include: detecting, by a user device, a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol; transmitting, by the user device, first information related to the transition in response to detecting the transition; receiving, by the user device, change information related to a target action based on the first information transmitted by the user device; and performing, by the user device, the target action based on the change information.

[0006] According to one aspect, the first information may include a machine learning collaboration level change request associated with the user device, and the change information may include at least one of an acknowledgment of the machine learning collaboration level change request or a new machine learning collaboration level based on the machine learning collaboration level change request.

[0007] According to one aspect, the modification information may be further based on at least one of a type of the target behavior, a time sensitivity of the target behavior, and an importance associated with the target behavior.

[0008] According to one aspect, performing the target operation may include one of: performing the target operation based on received assistance information related to the target operation based on the new machine learning coordination level being a first level, where the received assistance information may be based on one or more machine learning models related to the target operation; performing the target operation without the received assistance information related to the target operation based on the new machine learning coordination level being a second level; and terminating the target operation at the user device based on the new machine learning coordination level being a third level.

[0009] According to one aspect, the first state may be one of an RRC idle state or an RRC inactive state, the second state may be an RRC connected state, and the change information may include an indication of a machine learning coordination level based on one or more capabilities of the user device.

[0010] According to one aspect, the first state may be a Radio Resource Control (RRC) Connected state, the second state may be one of an RRC Idle state or an RRC Inactive state, and the change information may include a new machine learning coordination level based on the transition.

[0011] According to one aspect, the first 5G New Radio protocol may be associated with a radio resource control layer.

[0012] According to one aspect, based on the target action being associated with the real-time application, an information exchange can be signaled using one or more physical layer protocols. The information exchange can include transmitting first information and receiving change information.

[0013] According to one aspect, based on the target action being associated with a near real-time application, the information exchange may be signaled using one or more physical layer protocols, a non-access stratum layer protocol, and a radio resource control layer protocol.

[0014] According to one aspect, based on the target action being associated with a non-real-time application, the information exchange may be signaled using one or more non-access stratum layer protocols and a radio resource control layer protocol.

[0015] According to an embodiment, an apparatus for adaptive machine learning related action signaling in a telecommunications network may be provided. The apparatus may include at least one memory configured to store computer program code, and at least one processor configured to access the computer program code and operate as instructed by the computer program code. The program code may include a detection code configured to cause the at least one processor to detect a transition of a user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol, a transmission code configured to cause the at least one processor to transmit first information related to the transition in response to detecting the transition, a receiving code configured to cause the at least one processor to receive change information related to a target action based on the first information transmitted by the user device, and an execution code configured to cause the at least one processor to execute the target action based on the change information.

[0016] According to an embodiment, a non-transitory computer-readable medium may be provided having instructions stored thereon for adaptive machine learning related action signaling in a telecommunications network. The instructions include one or more instructions, when executed by one or more processors, that cause the one or more processors to detect, by the user device, a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol, in response to detecting the transition, transmit, by the user device, first information related to the transition, receive, by the user device, change information related to a target action based on the first information transmitted by the user device, and perform, by the user device, the target action based on the change information.

[0017] The features, advantages, and importance of exemplary embodiments of the present disclosure will now be described with reference to the accompanying drawings, in which like reference numerals refer to like elements. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is an exemplary schematic diagram of a network architecture in which systems and / or methods described in the present disclosure may be implemented.

[0019] [Diagram 2] 1 is an example flow chart illustrating an example process for adaptive machine learning related action signaling in a telecommunications network according to an embodiment of the present disclosure.

[0020] [Diagram 3] FIG. 1 is an example workflow diagram illustrating an example process for adaptive machine learning related operation signaling in a telecommunications network according to an embodiment of the present disclosure.

[0021] [Figure 4] FIG. 2 is an example schematic diagram of components of the network architecture of FIG. 1 according to an embodiment of the present disclosure.

[0022] [Diagram 5] FIG. 2 is an example schematic diagram of components of the network architecture of FIG. 1 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] The following detailed description of the exemplary embodiments refers to the accompanying drawings, in which the same reference numbers in different drawings may identify the same or similar elements.

[0024] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the implementation to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practicing the implementations.

[0025] It will be apparent that the systems and / or methods described herein may be implemented in various forms of hardware, firmware, or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods is not intended to limit the implementation. Thus, the operation and behavior of the systems and / or methods are described herein without reference to any specific software code, and it will be understood that software and hardware can be designed to implement the systems and / or methods based on the description herein.

[0026] As is conventional in the art, the embodiments may be described and illustrated in terms of blocks performing one or more described functions. These blocks, sometimes referred to herein as units, modules, or the like, may be physically implemented by analog or digital circuits, such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, and the like, and may be driven by firmware and software. The circuits may be embodied, for example, in one or more semiconductor chips, or on a substrate support, such as a printed circuit board. The circuits included in the blocks may be implemented by dedicated hardware, or by a processor (e.g., one or more programmed microprocessors and associated circuits), or by a combination of dedicated hardware for performing some functions of the block and a processor for performing other functions of the block. Each block of the embodiments may be physically separated into two or more interacting individual blocks. Similarly, the blocks of the embodiments may be physically combined into more complex blocks.

[0027] Although particular combinations of features are recited in the claims and / or disclosed herein, these combinations are not intended to limit the disclosure of possible implementations. Indeed, many of these features may be combined in ways not specifically recited in the claims and / or disclosed herein. Although each dependent claim listed below may depend directly on only one claim, the disclosure of possible implementations includes each dependent claim in combination with all other claims in the set of claims.

[0028] No element, act, or instruction used herein should be construed as critical or essential unless expressly described as such. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more." When only one item is intended, the term "one" or similar phraseology is used. Also, as used herein, terms such as "has," "have," "having," "include," "including," and the like are intended to be open-ended terms. Furthermore, the phrase "based on" is intended to mean "based at least in part on," unless specifically noted otherwise.

[0029] As mentioned above, there are no existing standards or even discussions regarding the use of specific radio access parameters, New Radio protocols, and / or interfaces for managing AI / ML models, e.g., there is no discussion of specific radio access parameters, New Radio protocols, and / or interfaces that may be used to signal collaboration information, user device capability information, or other parameters that impact real-time application of optimized AI / ML models in telecommunications networks.

[0030] In other words, there is no discussion and / or consensus regarding the management of AI / ML models and their application in telecommunication networks. More specifically, there is no discussion and / or standards related to signaling dynamic application of AI / ML functionality using radio access parameters. This lack of signaling guidance may result in ineffective utilization of AI / ML modeling in telecommunication networks and increase latency and inefficiency in the telecommunication network. Therefore, there is a need to define which radio access parameters, New Radio protocols, and / or New Radio interfaces can be used to effectively leverage and dynamically manage the use of AI / ML in telecommunication networks.

[0031] According to aspects of the present disclosure, the AI / M1 model may be dynamically managed and adapted to execute a target action using appropriate radio access parameters, New Radio protocols, and / or interfaces, which may be based on one or more capabilities of the user device, the type and properties of the target action, the time sensitivity and priority of the target action, and / or changes in conditions related to the user device's connection with the telecommunications network.

[0032] According to aspects of the present disclosure, a user device may communicate with a telecommunications network via a network element to dynamically manage AI / ML models associated with a target action being performed by the user device. AI / ML application functions may be defined that enable a user device to adaptively and in real-time control AI / ML models deployed on the user device using radio access parameters and interfaces in response to one or more capabilities of the user device, types and properties of the target action, time sensitivity and priority of the target action, and / or changing conditions related to the user device's connection with the telecommunications network.

[0033] In some embodiments, the AI / ML adaptation function may interface with multiple layers in a 5G New Radio protocol stack. As an example, the AI / ML adaptation function may interface with a Radio Resource Control (RRC) layer, a Non-Access Stratum (NAS) layer, and / or a Physical (PHY) layer of the 5G New Radio protocol stack.

[0034] According to aspects of the present disclosure, the AI / ML application function may be used to determine a machine learning coordination level associated with a user device. The machine learning coordination level associated with a user device may indicate whether an AI / ML model associated with an operation may require additional information from a telecommunications network or may be implemented on the user device without additional information from the telecommunications network. The machine learning coordination level associated with a user device may be changed in response to a change in a connection state of the user device. As an example, when a user device is in a "sleep mode", the connection between the user device and a network element may be inactive or idle. In some embodiments, based on the connection state being changed to idle or inactive, the machine learning coordination level associated with the user device may be changed and one or more of the AI / ML models may be deployed to the network element or core network. Based on the change in the connection state and the resumption of the connection between the user device and the network element, the machine learning coordination level associated with the user device may be changed and one or more of the AI / ML models may be deployed to the user device. The machine learning coordination level associated with the user device or the changed machine learning coordination level associated with the user device may be signaled using RRCResumeRequest1, RRCResumeRequest, RRCReconfiguration, and / or RRCRelease messages.

[0035] In some embodiments, the AI / ML application function may be used to determine a machine learning capability level associated with a user device. The machine learning capability level associated with a user device may indicate whether an AI / ML model associated with an operation may be trained, updated, and / or deployed on the user device. The machine learning capability level associated with a user device may be changed in response to a change in a connection state of the user device. As an example, when a user device is in a "sleep mode", the connection between the user device and a network element may be inactive or idle. In some embodiments, when the connection state changes to idle or inactive, the machine learning capability level associated with the user device may be changed and one or more of the AI / ML models may be deployed to the network element or core network. Based on the change in the connection state and the resumption of the connection between the user device and the network element, the machine learning capability level associated with the user device may be changed and one or more of the AI / ML models may be deployed to the user device. The machine learning capability level associated with the user device or the changed machine learning capability level associated with the user device may be signaled using RRCResumeRequest1, RRCResumeRequest, RRCReconfiguration, and / or RRCRelease messages.

[0036] According to aspects of the disclosure, the AI / ML application function may interface and / or communicate with the telecommunications network using one or more of the RRC layer, the NAS layer, or the PHY layer of the 5G New Radio protocol stack. In some embodiments, the NAS layer may be used to transmit and / or receive information related to a user device type, a user device property, slice type information, user device positioning information, time sensitivity information, etc. The NAS layer may also be used to transmit one or more of the user device capabilities to the telecommunications network. In some embodiments, the RRC layer may be used to transmit and / or receive user device connectivity with the telecommunications network. Based on the user device's connectivity state with the telecommunications network or based on changes in the user device's connectivity state with the telecommunications network, the AI / ML model may be trained, updated, and / or deployed on the user device.

[0037] FIG. 1 is an exemplary schematic diagram of a portion of a network architecture in which the systems and / or methods described in the present disclosure may be implemented.

[0038] As shown in FIG. 1, a network infrastructure 100 of a telecommunications network may include one or more user devices 110, one or more network elements 105, and a core network 115.

[0039] According to an embodiment, the user device 110 may be any device used by an end user to communicate using a telecommunications network. The user device 110 may communicate with the network element 105 over a wireless channel. The user device 110 may be replaced with a "terminal", "User Equipment (UE)", "mobile station", "subscriber station", "Customer Premises Equipment (CPE)", "remote terminal", "wireless terminal", "user device", "device", "laptop", "computing device", or other terms having equivalent technical meanings.

[0040] In some embodiments, the user device 110 may include multiple 5G New Radio layers and / or protocol stacks. As an example, the user device 110 may include a NAS layer 132, an RRC layer 134, a Service Data Adaptation Protocol (SDAP) layer 136, a Packet Data Convergence Protocol (PDCP) layer 138, a Radio Link Control (RLC) layer 140, a Medium Access Control (MAC) layer 142, and a PHY layer 144. According to one embodiment, the user device 110 may include a data management function 120 and an AI / ML application function 125.

[0041] According to aspects of the present disclosure, a user device may communicate with a telecommunications network via a network element to dynamically manage AI / ML models associated with a target action being performed by the user device. An AI / ML application function 125 may be defined that enables a user device to adaptively and in real-time control the AI / ML models deployed on the user device using radio access parameters and interfaces in response to one or more capabilities of the user device, the type and properties of the target action, the time sensitivity and priority of the target action, and / or changing conditions related to the user device's connection with the telecommunications network.

[0042] In some embodiments, the AI / ML adaptation function 125 can interface with multiple layers in a 5G New Radio protocol stack. As an example, the AI / ML adaptation function can interface with the RRC layer 134, the NAS layer 132, and / or the PHY layer 144 of the 5G New Radio protocol stack.

[0043] According to aspects of the disclosure, the AI / ML application function 125 may be used to determine a machine learning coordination level associated with a user device. The machine learning coordination level associated with a user device may indicate whether an AI / ML model associated with an operation may require additional information from a telecommunications network or may be implemented on the user device without additional information from the telecommunications network. The machine learning coordination level associated with a user device may be changed in response to a change in a connection state of the user device. As an example, when a user device is in a "sleep mode", the connection between the user device 110 and the network element 105 may be inactive or idle. In some embodiments, based on the connection state being changed to idle or inactive, the machine learning coordination level associated with the user device may be changed and one or more of the AI / ML models may be deployed to the network element 105 or the core network 115. Based on the change in the connection state and the resumption of the connection between the user device 110 and the network element 105, the machine learning coordination level associated with the user device 110 may be changed and one or more of the AI / ML models may be deployed to the user device 110.

[0044] In some embodiments, the AI / ML application function 125 may be used to determine a machine learning capability level associated with the user device 110. The machine learning capability level associated with the user device may indicate whether an AI / ML model associated with an operation may be trained, updated, and / or deployed on the user device 110. The machine learning capability level associated with the user device may be changed in response to a change in a connection state of the user device 110. As an example, when the user device 110 is in a "sleep mode", the connection between the user device 110 and the network element 105 may be inactive or idle. In some embodiments, when the connection state changes to idle or inactive, the machine learning capability level associated with the user device 110 may be changed and one or more of the AI / ML models may be deployed to the network element 105 or the core network 115. Based on the change in the connection state and the resumption of the connection between the user device 110 and the network element 105, the machine learning capability level associated with the user device 110 may be changed and one or more of the AI / ML models may be deployed to the user device 110.

[0045] According to one embodiment of the present disclosure, the user device 110 may include a data management function 120. The data management function 120 may interface with an AI / ML application function 125. The data management function 120 may collect and share information regarding one or more AI / ML models. In some embodiments, the data management function 120 may selectively share information regarding one or more applications, operations, and / or functionality of the telecommunications network being performed using the AI / ML modeling.

[0046] In some embodiments, the user device 110 can communicate with a telecommunications network using a network element 105, such as a base station. An example of a base station may be a gNodeB or an eNodeB. The network element 105 may be a node that enables communication between the user device 110 and the telecommunications system using radio channels. The network element 105 may be a network infrastructure component that can provide wireless connectivity to the user device 110. The network element 105 may have coverage defined as a particular geographic area, also known as a sector, based on signal transmission range.

[0047] The network element 105 may include multiple 5G New Radio layers and / or protocol stacks. As an example, the network element 105 may include an RRC layer 154, an SDAP layer 156, a PDCP layer 158, an RLC layer 160, a MAC layer 162, and a PHY layer 164.

[0048] The NAS layer 132 and the NAS layer 172 may be used to determine the user device 110 and the positioning of the user device 110 in the core network 115, respectively. In some embodiments, the AI / ML application function 125 may interface with the NAS layer 132 to send and / or receive user device type, user device properties, slice type information, user device indoor positioning, time sensitivity information related to one or more target actions being performed using the AI / ML model. In some embodiments, the NAS layer 132 may be used to interface with the AI / ML model being used to perform the target actions, which may include, but are not limited to, actions related to model transfer, control for normal time optimization, user device AI / ML capabilities, user device AI / ML cooperation level, user device type and properties, user device positioning, etc.

[0049] The RRC layer 134 and the RRC layer 154 may be used to determine where the AI / ML models reside and / or may be executed. In some embodiments, the AI / ML application function 125 may interface with the RRC layer 134 to send and / or receive connectivity status between the user device 110 and the network element 105. In some embodiments, the RRC layer 134 may be used to interface with the AI / ML models being used to perform target operations, which may include, but are not limited to, operations related to model transfer, control for near real-time optimization, control for normal time optimization, key performance indicator monitoring, tuning of parameters associated with the device, user device AI / ML capabilities, user device AI / ML coordination level, user device positioning, etc.

[0050] The PHY layer 144 and the PHY layer 164 may be used to set, exchange, and signal radio control parameters related to the configuration of wireless communication between the user device 110 and the telecommunications network (network element 105 and / or core network 115). In some embodiments, the AI / ML adaptation function 125 may interface with the PHY layer 144 to send and / or receive parameters related to connection establishment and / or adjustment between the user device 110 and the network element 105 or the core network 115. In some embodiments, the PHY layer 144 may be used to interface with AI / ML models that are being used to perform target operations, which may include, but are not limited to, operations related to model transfer, control for real-time optimization, control for normal-time optimization, user device AI / ML capabilities, user device AI / ML coordination level, user device positioning, etc.

[0051] According to embodiments, SDAP layer 136 and SDAP layer 156 may be used for quality of service and flow handling between user device 110 and network element 105. In some embodiments, SDAP layer 136 may be used to interface with AI / ML models that are being used to perform target actions, which may include, but are not limited to, actions related to quality of service and flow handling.

[0052] According to an embodiment, PDCP layer 138 and PDCP layer 158 may be used for packet compression, encryption, and maintaining data integrity between user device 110 and network element 105. In some embodiments, PDCP layer 138 may be used to interface with an AI / ML model that is being used to perform target operations, which may include, but are not limited to, operations related to packet compression, encryption, and maintaining data integrity.

[0053] According to an embodiment, RLC layer 140 and RLC layer 160 may be used for error correction, sequence numbering, segmentation, and deduplication between user device 110 and network element 105. In some embodiments, RLC layer 140 may be used to interface with an AI / ML model that is being used to perform target operations, which may include, but are not limited to, operations related to error correction, sequence numbering, segmentation, and deduplication.

[0054] According to embodiments, MAC layer 142 and MAC layer 162 may be used for mapping between logical channels and transport channels, multiplexing, demultiplexing, scheduling, HARQ optimization, etc. In some embodiments, MAC layer 142 may be used to interface with AI / ML models that are being used to perform target operations, which may include, but are not limited to, operations related to mapping between logical channels and transport channels, multiplexing, demultiplexing, scheduling, HARQ optimization.

[0055] In some embodiments, the network infrastructure 100 may include a core network 115. The core network 115 may include an AI / ML enabler 175 and one or more databases 180. The AI / ML enabler 175 may communicate with the network elements 105 using an N1 protocol and / or interface. The AI / ML enabler 175 may communicate with the user devices 110 using an N2 protocol and / or interface. The AI / ML enabler 175 may store AI / ML models that may be used to perform one or more operations and / or functionality of the telecommunications network. The database 180 may store data related to training, testing, and validation of the AI / ML models. The database 180 may send data to and / or receive data from the AI / ML enabler 175.

[0056] According to an embodiment of the present disclosure, the network infrastructure 100 may include one or more real-time applications 190 and one or more near real-time applications 195. According to an aspect of the present disclosure, the AI / ML application function 125 may select one or more interfaces for exchanging information related to the AI / ML model and / or one or more operations being performed on the user device based on the type of application. As an example, for a real-time application using an AI / ML model, the information exchange related to the real-time application and / or the AI / ML model may be signaled using one or more physical layer protocols. As an example, for a near real-time application using an AI / ML model, the information exchange related to the near real-time application and / or the AI / ML model may be signaled using one or more physical layer protocols, a non-access stratum layer protocol, and a radio resource control layer protocol. As an example, for a non-real-time application using an AI / ML model, the information exchange related to the near real-time application and / or the AI / ML model may be signaled using one or more non-access stratum layer protocols, and a radio resource control layer protocol.

[0057] FIG. 2 is an example flow chart illustrating an example process 200 for adaptive machine learning related action signaling in a telecommunications network according to an embodiment of the present disclosure.

[0058] As shown in Figure 2, one or more process blocks of process 200 may be performed by any of the components described in this application in Figures 1 and 5-6. In Figure 2, one or more process blocks of process 200 may correspond to operations associated with user device 110.

[0059] In operation 205, the user device may detect a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol. By way of example, the first state and the second state may include an RRC connected state, an RRC idle state, and an RRC inactive state. The first 5G New Radio protocol may include an RRC layer, a NAS layer, and / or a PHY layer.

[0060] In one embodiment of the present disclosure, at operation 210, in response to detecting the transition, the user device may transmit first information related to the transition.

[0061] In one embodiment of the present disclosure, the first information may include a machine learning collaboration level change request associated with the user device or one or more capabilities of the user device.

[0062] In operation 215, the user device may receive change information related to the target operation from the network element 105 and / or the core network 115. The change information may be based on the first information sent by the user device.

[0063] In some embodiments, the modification information may include at least one of an indication of the machine learning coordination level based on one or more capabilities of the user device, an acknowledgment of the machine learning coordination level change request, or a new machine learning coordination level based on the machine learning coordination level change request or transition. Further, in some embodiments, the modification information may be further based on at least one of a type of goal behavior, a time sensitivity of the goal behavior, and an importance associated with the goal behavior.

[0064] At operation 220, the user device may execute the target action based on the change information. According to one aspect, based on the change information including the machine learning coordination level associated with the user device, the target action may be executed using information from the AI / ML model and / or the network element. In some embodiments, executing the target action based on the new machine learning coordination level being a first level may be based on received assistance information associated with the target action, and the received assistance information may be based on one or more machine learning models associated with the target action. In some embodiments, executing the target action based on the new machine learning coordination level being a second level may not be based on received assistance information associated with the target action. In some embodiments, terminating the target action at the user device based on the new machine learning coordination level being a third level.

[0065] According to one aspect of the present disclosure, the information exchange between the user device and the network element and / or the core network, including transmitting the first information and receiving the change information, may be signaled using a specific 5G New Radio protocol based on an application associated with the target operation. As an example, based on the target operation being associated with a real-time application, the information exchange may be signaled using one or more physical layer protocols. As an example, based on the target operation being associated with a near-real-time application, the information exchange may be signaled using one or more physical layer protocols, a non-access stratum layer protocol, and a radio resource control layer protocol. As an example, based on the target operation being associated with a non-real-time application, the information exchange may be signaled using one or more non-access stratum layer protocols and a radio resource control layer protocol.

[0066] FIG. 3 is an example workflow diagram illustrating an example workflow 300 for adaptive machine learning related action signaling in a telecommunications network according to an embodiment of the present disclosure.

[0067] As shown in Figure 3, one or more operational blocks of workflow 300 may be performed by any of the components described in this application in Figures 1 and 4-5. In Figure 3, one or more operational blocks of workflow 300 may correspond to operations related to user device 110, network element 105, and / or core network 115.

[0068] At operation 305, the user device 110 may transmit one or more user device capabilities to the network element 105 and / or the core network 115. In some embodiments, the user device 110 may signal the user device capabilities using the NAS layer 132.

[0069] At operation 310, the AI / ML framework may determine a machine learning coordination level and / or a machine learning capability level associated with the user device based on the user device capabilities. In some embodiments, the AI / ML framework may determine a machine learning coordination level and / or a machine learning capability level associated with the user device at the network element 105 and / or the core network 115. At operation 315, the network element 105 and / or the core network 115 may send an indication of the machine learning coordination level and / or the machine learning capability level associated with the user device to the user device 110. In some embodiments, the indication of the machine learning coordination level and / or the machine learning capability level associated with the user device may be signaled using an RRCReconfiguration message.

[0070] In operation 320, the connection state of the user device 110 can be changed to a connected state, and in operation 325, the user device 110 can be enabled to fully cooperate with the network element 105 and / or the core network 115 to perform a target operation, such as indoor positioning of the user device 110.

[0071] In operation 330, the network element 105 or the core network 115 may use the RRCRelease message to transmit an indication of a change in the machine learning coordination level and / or a change in the machine learning capability level associated with the user device. The change in the machine learning coordination level and / or the change in the machine learning capability level associated with the user device may be an example of change information.

[0072] Based on the change information received in operation 330, a connection state of the user device 110 may be changed from a connected state to an idle state or an inactive state in operation 335. In operation 340, the user device 110 may be enabled to perform a target operation, such as indoor positioning of the user device 110, without further cooperation with the network element 105 and / or the core network 115, i.e., in a standalone mode.

[0073] FIG. 4 is a diagram of an example environment for implementing one or more of the devices, operations, and / or frameworks of FIGS.

[0074] As shown in FIG. 4, environment 400 may include user device 110, platform 420, and network 430. The devices of environment 400 may be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections. In an embodiment, any of the functions of the elements included in network infrastructure 100 may be performed by any combination of the elements shown in FIG. 4. For example, in an embodiment, user device 110 may perform one or more functions associated with a personal computing device, and platform 420 may perform one or more functions associated with any of network elements 105.

[0075] User device 110 may include one or more devices that can receive, generate, store, process, and / or provide information related to platform 420. For example, user device 110 may include a computing device (e.g., a desktop computer, a laptop computer, a tablet computer, a handheld computer, a smart speaker, a server, etc.), a mobile phone (e.g., a smartphone, a wireless phone, etc.), a camera device, a wearable device (e.g., smart glasses or a smart watch), or a similar device. In some implementations, user device 110 can receive information from platform 420 and / or transmit information to platform 420.

[0076] Platform 420 may include one or more devices that can receive, generate, store, process, and / or provide information. In some implementations, platform 420 may include a cloud server or a group of cloud servers. In some implementations, platform 420 may be designed to be modular, such that particular software components may be swapped in or out depending on particular needs. In that way, platform 420 may be easily and / or quickly reconfigured for different uses.

[0077] In some implementations, as shown, platform 420 may be hosted in a cloud computing environment 422. Of note, although the implementations described herein describe platform 420 as being hosted in a cloud computing environment 422, in some implementations platform 420 may not be cloud-based (i.e., may be implemented outside of a cloud computing environment) or may be partially cloud-based.

[0078] Cloud computing environment 422 includes an environment that hosts platform 420. Cloud computing environment 422 can provide services, such as computing, software, data access, storage, etc., that do not require end-user (e.g., user device 110) knowledge of the physical location and configuration of the system(s) and / or device(s) that host platform 420. As shown, cloud computing environment 422 can include a group of computing resources 424 (collectively referred to as “computing resources 424” and individually referred to as “computing resource 424”).

[0079] The computing resource(s) 424 may include one or more personal computers, clusters of computing devices, workstation computers, server devices, or other types of computing and / or communication devices. In some implementations, the computing resource(s) 424 may host the platform 420. Cloud resources may include computational instances executing within the computing resource(s) 424, storage devices provided within the computing resource(s) 424, data transfer devices provided by the computing resource(s) 424, etc. In some implementations, the computing resource(s) 424 may communicate with other computing resources 424 via wired connections, wireless connections, or a combination of wired and wireless connections.

[0080] As further shown in FIG. 4, the computing resource(s) 424 include a group of cloud resources such as one or more Applications (APP) 424-1, one or more Virtual Machines (VMs) 424-2, Virtualized Storage (VS) 424-3, and one or more Hypervisors (HYPs) 424-4.

[0081] Applications 424-1 include one or more software applications that may be provided to or accessed by user device 110 or network element 105. Applications 424-1 may eliminate the need to install and run software applications on user device 110 or network element 105. For example, applications 424-1 may include software associated with platform 420 and / or any other software that may be provided via cloud computing environment 422. In some implementations, one application 424-1 may send information to or receive information from one or more other applications 424-1 via virtual machine 424-2.

[0082] The virtual machine 424-2 includes a software implementation of a machine (e.g., a computer) that executes programs like a physical machine. The virtual machine 424-2 can be either a system virtual machine or a process virtual machine, depending on the use and the degree to which the virtual machine 424-2 corresponds to an actual machine. A system virtual machine can provide a complete system platform that supports the execution of a complete Operating System (OS). A process virtual machine can execute a single program and support a single process. In some implementations, the virtual machine 424-2 can run on behalf of a user (e.g., the user device 110) and can manage the infrastructure of the cloud computing environment 422, such as data management, synchronization, or long-term data transfer.

[0083] Virtualized storage 424-3 includes one or more storage systems and / or one or more devices that use virtualization technology within the storage systems or devices of computing resource(s) 424. In some implementations, in the context of storage systems, types of virtualization may include block virtualization and file virtualization. Block virtualization may refer to the abstraction (or separation) of logical storage from physical storage such that the storage system can be accessed regardless of the physical storage or heterogeneous structure. Separation may give administrators of storage systems flexibility in how they manage storage for end users. File virtualization may eliminate the dependency between data accessed at the file level and the location where the file is physically stored. This may enable performance optimization of storage usage, server consolidation, and / or non-disruptive file migration.

[0084] The hypervisor 424-4 may provide hardware virtualization technology that allows multiple operating systems (e.g., "guest operating systems") to run simultaneously on a host computer, such as computing resource 424. The hypervisor 424-4 may present a virtual operating platform to the guest operating systems and may manage the execution of the guest operating systems. Multiple instances of different operating systems may share the virtualized hardware resources.

[0085] Network 430 may include one or more wired and / or wireless networks. For example, network 430 may include a cellular network (e.g., a Fifth Generation (5G) network, a Long-Term Evolution (LTE) network, a Third Generation (3G) network, a Code Division Multiple Access (CDMA) network, etc.), a Public Land Mobile Network (PLMN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a telephone network (e.g., a Public Switched Telephone Network (PSTN)), a private network, an ad-hoc network, an intranet, the Internet, an optical fiber-based network, etc., and / or a combination of these or other types of networks.

[0086] The number and arrangement of devices and networks shown in Figure 4 are provided as an example. In practice, there may be additional devices and / or networks, fewer devices and / or networks, different devices and / or networks, or different arrangements of devices and / or networks than those shown in Figure 4. Furthermore, two or more devices shown in Figure 4 may be implemented within a single device, or a single device shown in Figure 4 may be implemented as multiple distributed devices. Additionally, or alternatively, a set of devices (e.g., one or more devices) of environment 400 may perform one or more functions described as being performed by another set of devices of environment 400.

[0087] FIG. 5 is a diagram of example components of one or more of the devices of FIGS. 1-4 according to an embodiment of the present disclosure.

[0088] According to one embodiment, Figure 5 may be a diagram of example components of a user device 110. The user device 110 may correspond to a device associated with an authorized user, a cell operator, or an RF engineer. The user device 110 may be used to communicate with a cloud platform 420 via a network element 105. As shown in Figure 5, the user device 110 may include a bus 510, a processor 520, a memory 530, a storage component 540, an input component 550, an output component 560, and a communication interface 570.

[0089] The bus 510 may include components that enable communication between components of the user device 110. The processor 520 may be implemented in hardware, firmware, or a combination of hardware and software. The processor 520 may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), an Accelerated Processing Unit (APU), a microprocessor, a microcontroller, a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), or another type of processing component. In some implementations, the processor 520 includes one or more processors that can be programmed to perform functions. Memory 530 may include Random Access Memory (RAM), Read Only Memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, and / or optical memory) that stores information and / or instructions for use by processor 520.

[0090] The storage component 540 stores information and / or software related to the operation and use of the user device 110. For example, the storage component 540 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optical disk, and / or a solid state disk), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of non-transitory computer-readable medium along with a corresponding drive. The input component 550 includes components that enable the user device 110 to receive information via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, and / or a microphone), and the like. Additionally or alternatively, the input component 550 may include sensors for sensing information (e.g., a Global Positioning System (GPS) component, an accelerometer, a gyroscope, and / or an actuator). Output components 560 include components that provide output information from user device 110 (eg, a display, a speaker, and / or one or more Light-Emitting Diodes (LEDs)).

[0091] The communication interface 570 includes transceiver-like components (e.g., a transceiver and / or a separate receiver and transmitter) that enable the user device 110 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. The communication interface 570 may enable the user device 110 to receive information from another device and / or provide information to another device. For example, the communication interface 570 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a Radio Frequency (RF) interface, a Universal Serial Bus (USB) interface, a Wi-Fi interface, a cellular network interface, etc.

[0092] The user device 110 may perform one or more processes described herein. The user device 110 may perform these processes in response to the processor 520 executing software instructions stored by a non-transitory computer-readable medium, such as the memory 530 and / or the storage component 540. A computer-readable medium may be defined herein as a non-transitory memory device. A memory device includes memory space within a single physical storage device or memory space across multiple physical storage devices.

[0093] The software instructions may be loaded into memory 530 and / or storage component 540 from another computer-readable medium or from another device via communication interface 570. When executed, the software instructions stored in memory 530 and / or storage component 540 may cause processor 520 to perform one or more processes described herein.

[0094] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the implementation to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practicing the implementations.

[0095] Some embodiments may relate to systems, methods, and / or computer-readable media at any possible level of technical detail integration. Furthermore, one or more of the above components described above may be implemented as instructions stored on a computer-readable medium and executable by at least one processor (and / or may include at least one processor). The computer-readable medium may include a computer-readable non-transitory storage medium or media having computer-readable program instructions for causing a processor to perform operations.

[0096] A computer readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer readable storage media includes portable computer diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disc read-only memories (CDs), digital versatile discs (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge structures in a groove on which instructions are recorded, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as being a transitory signal per se, such as electric waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted through wires.

[0097] The computer readable program instructions described herein can be downloaded from a computer readable storage medium to the respective computing / processing device or to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing / processing device.

[0098] The computer readable program code / instructions for carrying out the operations may be either source code or object code written in any combination of one or more programming languages, including assembler instructions, Instruction-Set-Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or object-oriented programming languages ​​such as Smalltalk, C++, and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a Local Area Network (LAN) or Wide Area Network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform an aspect or operation.

[0099] These computer readable program instructions may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus to generate a machine such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for performing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer readable program instructions may also be stored in a computer readable storage medium capable of directing a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer readable storage medium on which the instructions are stored comprises an article of manufacture including instructions implementing aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0100] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to generate a computer-implemented process, such that the instructions executing on the computer, other programmable apparatus, or other device perform the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0101] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer-readable media according to various embodiments. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions that includes one or more executable instructions for implementing a particular logical function(s). The methods, computer systems, and computer-readable media may include additional, fewer, different, or differently arranged blocks compared to the blocks shown in the figures. In some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the figures. For example, two blocks shown in succession may actually be executed simultaneously or nearly simultaneously, or the blocks may sometimes be executed in the reverse order depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart diagrams, as well as combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a dedicated hardware-based system that performs the specified functions or actions or executes a combination of dedicated hardware and computer instructions.

[0102] It will be apparent that the systems and / or methods described herein may be implemented in various forms of hardware, firmware, or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods is not intended to limit the implementation. Thus, the operation and behavior of the systems and / or methods are described herein without reference to any specific software code, and it will be understood that software and hardware can be designed to implement the systems and / or methods based on the description herein.

Claims

1. 1. A method for adaptive machine learning related action signaling in a telecommunications network, executed by one or more processors, comprising: Detecting, by a user device, a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol; transmitting, by the user device, first information related to the transition in response to detecting the transition; receiving, by the user device, change information related to a target motion based on the first information transmitted by the user device; executing, by the user device, the target action based on the modification information; A method comprising:

2. 2. The method of claim 1 , wherein the first information includes a machine learning collaboration level change request associated with the user device, and the change information includes at least one of an acknowledgment of the machine learning collaboration level change request or a new machine learning collaboration level based on the machine learning collaboration level change request.

3. The method of claim 2 , wherein the modification information is further based on at least one of a type of the target behavior, a time sensitivity of the target behavior, and an importance associated with the target behavior.

4. Executing the target action based on the change information, performing the target motion based on received assistance information related to the target motion based on the new machine learning collaboration level being a first level, the received assistance information being based on one or more machine learning models associated with the target motion; performing the target action without the received assistance information related to the target action based on the new machine learning collaboration level being a second level; and terminating the target action based on the new machine learning collaboration level being a third level; and The method of claim 2 , comprising one of:

5. 2. The method of claim 1 , wherein the first state is one of an RRC idle state or an RRC inactive state, the second state is an RRC connected state, and the change information includes an indication of a machine learning coordination level based on one or more capabilities of the user device.

6. 2. The method of claim 1 , wherein the first state is a radio resource control (RRC) connected state, the second state is one of an RRC idle state or an RRC inactive state, and the change information includes a new machine learning coordination level based on the transition.

7. The method of claim 1 , wherein the first 5G New Radio protocol is associated with a radio resource control layer.

8. 2. The method of claim 1, wherein the information exchange, including transmitting the first information and receiving the change information based on the target action being associated with a real-time application, is signaled using one or more physical layer protocols.

9. 2. The method of claim 1, wherein the information exchange, including transmitting the first information and receiving the change information based on the target action being associated with a near real-time application, is signaled using one or more of a physical layer protocol, a non-access stratum layer protocol, and a radio resource control layer protocol.

10. 2. The method of claim 1, wherein the information exchange, including sending the first information and receiving the change information based on the target operation being associated with a non-real-time application, is signaled using one or more non-access stratum layer protocols and a radio resource control layer protocol.

11. An apparatus for adaptive machine learning related action signaling in a telecommunications network, comprising: at least one memory configured to store program code; at least one processor configured to read the program code and to operate as instructed by the program code, the program code comprising: detection code configured to cause the at least one processor to detect a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol; transmitting code configured to cause the at least one processor to transmit, in response to detecting the transition, first information associated with the transition; receiving code configured to cause the at least one processor to receive modification information related to a target motion based on the first information transmitted by a user device; execution code configured to cause the at least one processor to perform the target action based on the change information; 13. An apparatus comprising:

12. 12. The apparatus of claim 11, wherein the first information includes a machine learning collaboration level change request associated with the user device, and the change information includes at least one of an acknowledgment of the machine learning collaboration level change request or a new machine learning collaboration level based on the machine learning collaboration level change request.

13. The apparatus of claim 12 , wherein the modification information is further based on at least one of a type of the target behavior, a time sensitivity of the target behavior, and an importance associated with the target behavior.

14. The execution code is performing the target motion based on received assistance information related to the target motion based on the new machine learning collaboration level being a first level, the received assistance information being based on one or more machine learning models associated with the target motion; performing the target action without the received assistance information related to the target action based on the new machine learning collaboration level being a second level; and terminating the target action based on the new machine learning collaboration level being a third level; and The apparatus of claim 12 further comprising:

15. 12. The apparatus of claim 11, wherein the first state is one of an RRC idle state or an RRC inactive state, the second state is an RRC connected state, and the change information includes an indication of a machine learning coordination level based on one or more capabilities of the user device.

16. 12. The apparatus of claim 11, wherein the first state is a radio resource control (RRC) connected state, the second state is one of an RRC idle state or an RRC inactive state, and the change information comprises a new machine learning coordination level based on the transition.

17. 12. The apparatus of claim 11, wherein the information exchange, including transmitting the first information and receiving the change information based on the target action being associated with a real-time application, is signaled using one or more physical layer protocols.

18. 12. The apparatus of claim 11, wherein the information exchange, including transmitting the first information and receiving the change information based on the target action being associated with a near real-time application, is signaled using one or more of a physical layer protocol, a non-access stratum layer protocol, and a radio resource control layer protocol.

19. 1. A non-transitory computer-readable medium storing instructions for adaptive machine learning related operation signaling in a telecommunications network, the instructions, when executed by one or more processors, causing the one or more processors to: detecting, by a user device, a transition of the user device from a first state associated with a first 5G New Radio protocol to a second state associated with the first 5G New Radio protocol; in response to detecting the transition, causing transmission, by the user device, of first information related to the transition; receiving, by the user device, modified information related to a target motion based on the first information transmitted by the user device; causing the user device to execute the target action based on the change information; A non-transitory computer-readable medium containing one or more instructions.

20. 20. The non-transitory computer-readable medium of claim 19, wherein the first information includes a machine learning collaboration level change request associated with the user device, and the change information includes at least one of an acknowledgment of the machine learning collaboration level change request or a new machine learning collaboration level based on the machine learning collaboration level change request.

Images