System and device for granting priority to a model configuration and associated method

Abstract

A system (100), an apparatus (104), and a method (300) for granting precedence to a model configuration are disclosed. The method (300) includes: obtaining, by a source cell, data associated with a model configuration of a destination cell; processing the model configuration data to generate one or more model parameters associated with the model of the destination cell; communicating the one or more model parameters to a user device; and configuring the user device based on the one or more model parameters of the destination cell before the user device roams to the destination cell.

Description

Field of the invention

[0001] The present disclosure generally relates to a system and / or apparatus and / or device for prioritizing a model configuration, for example, in connection with a user equipment (UE) or radio cell (or node / access point) usable for communication. The present disclosure further relates to a method that may be associated with the system, apparatus, and / or device. Background of the invention

[0002] In general, energy efficiency would be helpful in communication networks, for example a telecommunications network based on the 3rd Generation Partnership Project (3GPP) standard for the fifth generation of mobile communications (5G NR - 5th Generation New Radio).

[0003] Current techniques for granting priority or configuring a model for a user equipment (UE) in a communications network can be prone to problems such as service irregularity, service delay, and inefficient or even inaccurate model reconfiguration during frequent handovers. Thus, current techniques cannot optimally improve efficiency.

[0004] The present disclosure contemplates that it would be helpful to address or at least mitigate one or more problems associated with conventional techniques in order to improve energy efficiency and energy conservation. Brief description of the invention

[0005] According to a first aspect of the present invention, a method for granting precedence to a model configuration is provided, the method comprising: obtaining, by a source cell, data associated with a model configuration of a destination cell; processing the model configuration data to generate one or more model parameters associated with the model of the destination cell; communicating the one or more model parameters to a user device; and configuring the user device based on the one or more model parameters of the destination cell before the user device roams to the destination cell.

[0006] Advantageously, the method as described in this document can provide an efficient method for prioritizing a model (e.g., AI / ML model) of a mobile user equipment (UE) subject to frequent handover, such that the mobile user equipment (UE) is equipped with the parameters of the model (e.g., AI / ML model) before being handed over to the destination radio cell.

[0007] In one embodiment, the method may include requesting, by the source cell, data associated with the model configuration of the destination cell.

[0008] In one embodiment, requesting data associated with the model configuration comprises requesting the data via a commit request.

[0009] In one embodiment, the model is an artificial intelligence / machine learning (AIML) model.

[0010] In one embodiment, communicating the one or more model parameters to a user device comprises communicating through at least one of the following: a handover command message or a user equipment (UE)-specific message.

[0011] In one embodiment, the destination radio cell and the source radio cell correspond to at least one base station.

[0012] In one embodiment, the at least one base station corresponds to at least one next generation node B (gNB).

[0013] In one embodiment, the model configuration data comprises at least one of the following: life cycle management (LCM) parameters, a model identification (ID), and / or a pre-trained dataset.

[0014] In one embodiment, obtaining the data associated with a model configuration comprises obtaining data associated with a specific model configuration.

[0015] In one embodiment, the method may include: receiving a request for the model configuration of the target cell; processing the request to generate data associated with the model configuration of the target cell; and transmitting the data associated with the model configuration of the target cell to the source cell.

[0016] In one embodiment, a computer program is provided comprising instructions which, when executed by a computer, cause the computer to perform the method according to the first aspect.

[0017] In one embodiment, a computer-readable storage medium is provided having stored therein data representing computer-executable software, the software containing instructions which, when executed by the computer, cause the method according to the first aspect to be carried out.

[0018] In one embodiment, an apparatus for prioritizing a model configuration includes: a first module configured to receive data associated with a model configuration of a target cell; a second module configured to process and / or enhance the method of the first aspect to generate at least one output signal; and a third module configured to communicate at least one output signal, wherein the output signal corresponds to a control signal for configuring the user device based on the one or more model parameters of the target cell before the user device roams to the target cell.

[0019] In one embodiment, the device corresponds to a base station communicable with a device corresponding to a user equipment (UE), wherein the base station corresponds to a next generation node B (gNB) configured to communicate the at least one output signal to the UE.

[0020] In one embodiment, a system is provided comprising: at least one device and at least one facility, wherein the facility and the device are coupleable via wired coupling and / or wireless coupling.

[0021] Advantageously, the system disclosed in this document may not experience service interruption due to a model configuration change because the UE is provided with the AIML configuration of the target cell before moving to the target cell. Accordingly, service delay resulting from a model reconfiguration can be mitigated. Short description of the drawings

[0022] Embodiments of the disclosure are described below with reference to the following drawings, in which: Fig. 1A shows a schematic diagram illustrating a model configuration prioritization system according to an embodiment of the invention, which may include at least one device. Fig. 1B to Fig. 1D show exemplary scenarios in connection with the system of Fig. 1A according to an embodiment of the invention. Fig. Figure 2 shows a schematic diagram illustrating the device of Fig. 1A according to an embodiment of the invention. Fig. 3 shows a method in connection with the system of Fig. 1A according to an embodiment of the invention. Fig. 4A to Fig. 4D show schematic diagrams illustrating the flow of information associated with the process of Fig. 3 according to an embodiment of the invention. Detailed description

[0023] This specification discloses devices for performing the operations of the methods. Such devices may be specially constructed for the required purposes, or they may comprise a computer or other device that is specifically activated or reconfigured by a computer program stored in the computer. The algorithms and representations presented in this specification are not tied to any specific computer or other device. Various machines with programs consistent with the teachings of this specification may be used. Alternatively, the construction of more specialized devices for performing the required method steps may be indicated. The structure of a computer is apparent from the description below.

[0024] Furthermore, the present description also implicitly discloses a computer program, so that it will be apparent to those skilled in the art that the individual steps of the method described in this document can be implemented by computer code. The computer program is not intended to be limited to a specific programming language and its implementation. It is understood that a variety of programming languages ​​and their coding can be used to implement the teachings of the disclosure contained in this document. Furthermore, the computer program is not intended to be limited to a specific control flow. There are many other variations of the computer program that can use different control flows without departing from the spirit or scope of the disclosure.

[0025] Furthermore, one or more of the steps of the computer program may be performed in parallel rather than sequentially. Such a computer program may be stored on any computer-readable medium. The computer-readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interoperating with a computer. The computer-readable medium may also comprise a hardwired medium, exemplified by the Internet system, or a wireless medium, exemplified by the mobile telephone system. The computer program, when loaded and executed on such a computer, provides a device implementing the steps of the preferred method.

[0026] According to one embodiment of the invention, the present disclosure generally contemplates the improvement and optimization of a network (e.g., in conjunction with 3GPP-based standards / specifications, etc.) and / or the efficiency and mobility (e.g., energy efficiency or energy saving) of user equipment (UE). In particular, the present disclosure contemplates the possibility of configuring (or prioritizing) an artificial intelligence / machine learning (AIML or AI / ML)-based model of the UE in conjunction with the 3GPP standard(s).

[0027] In communication networks, methods or mechanisms are used to define how AIML (or AI / ML) can help optimize a handover (HO) for a mobile device (or UE). Performing a good handover, for example, from a source cell to a destination cell, is important because it can allow the UE to remain connected in the network and information to be properly transmitted from one base station (e.g., source cell) to another base station (e.g., destination cell). In one example embodiment, base stations (or cells), such as a Next Generation Node B (gNB), can coordinate the implementation of an AI / ML model in a network or determine whether the implementation of an AI / ML model is cell-specific (e.g., destination cell or source cell). In another example embodiment, a UE can implement multiple models (e.g.,multiple AI / ML models) in the serving cell (or source cell), all of which may or may not be available in the destination cell.

[0028] The present disclosure generally contemplates that such mechanisms and methods may not be efficient. For example, AI / ML inference may need to be reserved for the serving (or source) cell, thus preventing active use of AIML (or AI / ML) capabilities. In another example, the target gNB (or target cell) may provide the AIML (or AI / ML) model configuration when / after the UE roams to the target gNB (or target cell). This may cause a delay in AIML (or AI / ML) inference when the UE roams between the serving (or source) cell and the target cell.

[0029] The present disclosure also contemplates that, for example, it may be possible to have AI / ML-assisted mobility with handover optimization on the network side or on the UE side. This may include, for example, prediction of source (or candidate) cell(s) or destination cell(s) in Layer 3 (L3)-based mobility, as well as prediction of candidate or destination beam(s) and cell(s) in lower layer-triggered mobility (LTM), such as the Radio Layer 2 and Radio Layer 3 Radio Resource Control (RAN2) and a UTRAN / E-UTRAN / NG-RAN architecture and related network interfaces (RAN3).

[0030] The present disclosure contemplates that artificial intelligence / machine learning (AI / ML or AIML) can be an important technology in network optimization, leading to energy-efficient networks. In particular, the application of AIML (or AI / ML) to communication links (e.g., an air interface) can lead to handover optimization. If the UE is not configured with the AIML (or AI / ML) model of the destination cell when handing over to the destination cell, problems such as service interruption and delay, as well as handover failure, may occur.

[0031] The present disclosure considers how AIML (or AI / ML) can be prioritized in / with standard network systems, signaling aspects, and triggering mechanisms. Specifically, receiving the target cell AIML (or AI / ML) model configuration by the UE in a handover command message may be important in light of maintaining energy efficiency.

[0032] In the above manner, according to an embodiment of the invention, energy saving and energy consumption efficiency at the UE or in the network may be improved.

[0033] The above is explained below with reference to Fig. 1 to Fig. 4 is discussed in more detail.

[0034] Referring to Fig. 1A, a schematic diagram illustrating a model configuration prioritization system 100 is shown, according to one embodiment of the invention. System 100 may, for example, be adapted to improve energy and power efficiency, according to one embodiment of the invention.

[0035] As shown, the system 100 according to an embodiment of the invention may include one or more devices 102, at least one apparatus 104, and optionally a communications network 106.

[0036] The device(s) 102 may be coupled to the device(s) 104. In particular, according to one embodiment of the invention, the device(s) 102 may be coupled to the device(s) 104, for example, via the communications network 106.

[0037] In one embodiment, the device(s) 102 may be coupled to the communications network 106, and the apparatus(es) 104 may be coupled to the communications network 106. The coupling may be via a wired coupling and / or a wireless coupling. The device(s) 102 may be generally configured to communicate with the apparatus(es) 104 via the communications network 106, according to one embodiment of the invention.

[0038] For example, according to one embodiment of the invention, the device(s) 102 may be associated with, correspond to, or include one or more user equipment (UE) (or user device(s)) that may carry one or more computers. According to one embodiment of the invention, a device 102 may, for example, correspond to a UE carrying at least one computer (e.g., an electronic device or module with computing capabilities, such as a mobile electronic device that may be carried in a vehicle or an electronic module that may be installed in a vehicle, according to one embodiment of the invention), which may be configured to perform one or more tasks related to adaptive / dynamic / stage control.

[0039] The device(s) 104 may, for example, be associated with or correspond to at least one base station, wherein the at least one base station may be a Next Generation Node B (gNB). Furthermore, the device(s) 104 may, for example, be configured to carry / be associated with / contain one or more computers (e.g., an electronic device / module with computing capabilities), which may, for example, be configured to perform one or more processing tasks in conjunction with the base station. The device(s) 104 may, according to an embodiment of the invention, be configured to generate one or more output signals that may be communicated to the device(s) 102. This will be discussed in more detail later in the context of an exemplary scenario according to an embodiment of the invention.

[0040] In one embodiment, the device(s) 104 may, for example, be configured to receive data associated with a model (e.g., an AI / ML model) configuration of a target radio cell and to perform at least one processing task based on the data in such a way that one or more output signals are generated. The model (e.g., AI / ML model) configuration data may, for example, be communicated from a target base station (or a target radio cell) and received by the device(s) 104 according to an embodiment of the invention. As a possible option, the output signal(s) may, for example, be communicated from the device(s) 104 according to an embodiment of the invention. The output signal may correspond to a control signal for configuring (or granting precedence) of the device(s) 102 (or user device or user equipment) to the model (e.g.,AI / ML model) of the target base station (or target radio cell). The device(s) 104 according to an embodiment of the invention will be described later with reference to FIG. Fig. 2 is discussed in more detail.

[0041] The communication network 106 may, for example, correspond to an internet communication network, a cellular-based communication network, a wired communication network, a global navigation satellite system (GNSS)-based communication network, a wireless communication network, or any combination thereof. Communication (e.g., between the devices 102 and / or between the device(s) 102 and the device(s) 104) via the communication network 106 may be via wired communication and / or wireless communication.

[0042] As mentioned, the device(s) 104 may, for example, be configured to receive data associated with a model (e.g., an AI / ML model) configuration of a target cell and perform at least one processing task related to dynamic / adaptive / stage control on the data in such a way that at least one output signal is generated. Furthermore, according to an embodiment of the invention, the device(s) 104 may, for example, be configured to receive the data from another device 104 (e.g., a target base station or a target cell) and generate (and communicate) the output signal to the device(s) 102. Accordingly, the device(s) 104 may request this data from another device 104 (e.g., a target base station or a target cell) before generating the output signal.This will be explained below according to an embodiment of the invention in the context of an exemplary scenario with reference to . Fig. 1B to Fig. 1D discussed.

[0043] Fig. 1B to Fig. 1D show exemplary scenarios related to the system of Fig. 1A according to an embodiment of the invention. In particular, Fig. 1B to Fig. 1D various examples of model (e.g., AI / ML model) training on the device(s) 102 and the apparatus(es) 104 of Fig. 1A. Fig. 1B shows an example with training only on one side of the system: either at the device(s) 104 / base station (or network-side, e.g., gNB) or at the device(s) 102 (or UE-side). As shown in the figure, a training entity may be provided at each of the device(s) 104 and the device(s) 102. The training entity for each of the device(s) 104 and the device(s) 102 may include a module (not shown) configured to implement a respective neural network for handover, such that the neural network determines the handover solely by the device(s) 104 (network-side) or solely by the device(s) 102 (UE-side). Therefore, a model transfer from one side to the other is required, i.e.either a model transmission from the device(s) 104 (network-side) to the device(s) 102 (UE-side) or a model transmission from the device(s) 102 (UE-side) to the device(s) 104 (network-side).

[0044] In an alternative embodiment, Fig. 1C shows an example with joint training on both sides of the system: at the device(s) 104 / base station (or network-side, e.g., gNB) or the device(s) 102 (or UE-side). In this embodiment, training entities may be provided at each of the device(s) 104 (network-side) and the device(s) 102 (UE-side). Each of the training entities may include a respective module (not shown) configured to implement a respective handover neural network, such that the respective neural networks may determine the handover by both the device(s) 104 (network-side) and the device(s) 102 (UE-side).In particular, the network-side neural network (or network-side neural network) is trained and configured to determine a handover by the device(s) 104, while the UE-side neural network (or UE-side neural network) is trained and configured to determine a handover by the device(s) 102. Furthermore, the network-side neural network may perform a backward pass (backward gradient technique) on the device(s) 102 (UE-side), and the UE-side neural network may perform a forward pass (forward activation technique) on the device(s) 104 (network-side) to determine and optimize a handover by the device(s) 104 and the device(s) 102. In such an embodiment, training iterations may be required to exchange the results of the forward pass or the backward pass / backpropagation.In addition, simultaneous interactions between the network side and the UE side may be required during the training process.

[0045] In another embodiment, Fig. 1D shows an example with separate training on both sides of the system: at the device(s) 104 / base station (or network-side, e.g., gNB) and at the device(s) 102 (or UE-side). In this embodiment, training entities may be provided at each of the device(s) 104 (network-side) and the device(s) 102 (UE-side). Each of the training entities may include a respective module (not shown) configured to implement a respective handover neural network, such that the respective neural networks may be used to determine the handover by both the device(s) 104 (network-side) and the device(s) 102 (UE-side). In particular, the UE-side neural network (or the UE-side neural network) may be trained using a first training data set and configured to determine a handover by the device(s) 102.The UE-side neural network then shares the training dataset with the network-side neural network (or the network-side neural network), which is then trained and configured to determine a handover by the device(s) 104. It should be understood that the training order may be reversed, i.e., the network-side neural network is trained first using a training dataset, followed by the UE-side neural network after the network-side neural network shares the training dataset with the UE-side neural network. Furthermore, the generation of channel status information (CSI) on the UE side and the CSI reconstruction on the network side are trained by the UE-side neural network and the network-side neural network, respectively.In addition, the training dataset may be shared by both sides (UE side and network side) and transmission of the dataset and a reference model (e.g. AI / ML model) may be required.

[0046] The neural network as described in the present disclosure may be an artificial intelligence (AI) / machine learning-based neural network model, such as support vector machines, decision trees, ensemble models, k-nearest neighbor models, or Bayesian networks. It is understood that the neural network may also be a multimodal neural network and may include other types of models, including linear models and / or nonlinear models, as well as feedforward neural networks, convolutional neural networks (CNNs), or recurrent neural networks (RNNs). It is also understood that other types of neural network training may be available, which are not limited to the examples described herein.

[0047] The above-described aspect(s) of the system 100 of the present invention may also apply analogously to the (all) aspect(s) of a device 104 of the present invention described below. Likewise, the (all) aspect(s) of the device 104 of the invention described below may also apply analogously to the (all) aspect(s) of the system 100 of the invention described above.

[0048] The said device(s) 104 or the radio cell (e.g. source radio cell or destination radio cell) will be referred to below with reference to Fig. 2 is discussed in more detail.

[0049] Referring to Fig. 2, in connection with an exemplary implementation 200 according to an embodiment of the invention, a schematic diagram illustrating a device 104 is shown in more detail.

[0050] In the exemplary implementation 200, the device 104 may correspond to an electronic module 200a. In one example, the electronic module 200a according to an embodiment of the invention may correspond to a module positioned at a base station (or radio cell). In another example, the electronic module 200a according to an embodiment of the invention may correspond to an electronic device that may be installed / mounted in the base station (or radio cell).

[0051] It is contemplated that the electronic module 200a according to an embodiment of the invention may be capable of performing one or more processing tasks associated with adaptive / dynamic / stage-by-stage control-related processing.

[0052] The electronic module 200a may, for example, include a housing 200b. Furthermore, the electronic module 200a may, for example, support a first module 202, a second module 204, a third module 206, or any combination thereof.

[0053] In one embodiment, the electronic module 200a may support a first module 202, a second module 204, and / or a third module 206. In a specific example, the electronic module 200a may support a first module 202, a second module 204, and a third module 206 according to an embodiment of the invention.

[0054] In this regard, it will be appreciated that in one embodiment, the housing 200b may be shaped and sized to support the first module 202, the second module 204, the third module 206, or any combination thereof.

[0055] The first module 202 may be coupled to the second module 204 and / or the third module 206. The second module 204 may be coupled to the first module 202 and / or the third module 206. The third module 206 may be coupled to the first module 202 and / or the second module 204. In one example, according to an embodiment of the invention, the first module 202 may be coupled to the second module 204, and the second module 204 may be coupled to the third module 206. The coupling between the first module 202, the second module 204, and / or the third module 206 may, for example, be via wired coupling and / or wireless coupling. The first module 202, the second module 204, and the third module 206 may correspond to a hardware-based module and / or a software-based module according to an embodiment of the invention.

[0056] In one example, the first module 202 may correspond to a hardware-based receiver that may be configured to receive (or receive) one or more input signals or data. The input signal(s) or data may be communicated, for example, by another device(s) 104 (or base station, e.g., a gNB) according to an embodiment of the invention.

[0057] The second module 204 may, for example, correspond to a hardware-based processor that may be configured to perform one or more processing tasks (e.g., in a manner that generates one or more output signals), as described later with reference to Fig. 3 is discussed in more detail, according to an embodiment of the invention.

[0058] The third module 206 may correspond to a hardware-based transmitter that may be configured to communicate one or more output signals from the electronic module 200a. The output signal(s) may, for example, include one or more instructions / commands / control signals associated with the aforementioned dynamic / adaptive / stage-by-stage control configuration / determination strategy to improve efficiency (e.g., power / energy efficiency and / or communication efficiency) according to an embodiment of the invention. For example, the output signal(s) may be control signals for configuring the device(s) 102 (or the user device or equipment) to the model (e.g., AI / ML model) of the target base station (or target radio cell).

[0059] The present disclosure contemplates the possibility that the first and second modules 202, 204 may be an integrated software / hardware-based module, for example, an electronic part carrying a software program or algorithm associated with receiving and processing functions, or an electronic module programmed to perform the receiving and processing functions. The present disclosure further contemplates the possibility that the first and third modules 202, 206 may be an integrated software / hardware-based module, for example, an electronic part carrying a software program or algorithm associated with receiving and transmitting functions, or an electronic module programmed to perform the receiving and transmitting functions.The present disclosure further contemplates the possibility that the first and third modules 202, 206 may be an integrated hardware module, such as a hardware-based transceiver, capable of performing the functions of receiving and transmitting.

[0060] For example, the device 104 (or base station or radio cell) may, according to an embodiment of the invention, be further configured to process the input signal(s) or data in a manner as described later with reference to Fig. 3, one or more output signals are generated in a manner to improve efficiency, e.g., power efficiency or energy efficiency. In a specific example according to an embodiment of the invention, the output signal(s) may include one or more control signals to improve some type of dynamic / adaptive / stage-by-stage control configuration / determination strategy such that efficiency, e.g., power efficiency or energy efficiency, is improved. For example, the output signal(s) may be a control signal to configure (or prioritize) the device(s) 102 (or user device(s)) to the model (e.g., AI / ML model) of the target base station (or target radio cell).

[0061] The above-described aspect(s) of the device 104 of the present invention may also apply analogously to the (all) aspect(s) of a processing / communication method of the present invention described below. Likewise, the (all) aspect(s) of the method of the invention described below may also apply analogously to the (all) aspect(s) of the device 104 of the invention described above. It should be appreciated that these statements apply analogously to the previously discussed system 100 of the present disclosure.

[0062] Referring to Fig. 3, a method 300 (or a communication method) for granting priority to a model configuration, for example an artificial intelligence / machine learning (AIML or AI / ML) model, is shown in connection with the system 100, according to one embodiment of the invention.

[0063] According to one embodiment of the invention, the method 300 may, for example, be suitable for improving energy efficiency, network optimization and energy savings.

[0064] The method 300 may include an input step 302, a processing step 304, or an output step 306, or any combination thereof, according to one embodiment of the invention.

[0065] In one embodiment, processing method 300 may include input step 302. In another embodiment, processing method 300 may include input step 302 and processing step 304. In another embodiment, processing method 300 may include input step 302, processing step 304, and output step 306. In yet another embodiment, processing method 300 may include processing step 304 and / or input step 302 and / or output step 306. In yet another embodiment, processing method 300 may include input step 302, processing step 304, and output step 306. In yet another additional embodiment, processing method 300 may include processing step 304.In yet another further additional embodiment, the processing method 300 may include the input step 302, the processing step 304, or the output step 306, or any combination thereof (ie, the input step 302, the processing step 304, and / or the output step 306).

[0066] With respect to input step 302, one or more input signals or data may be received. For example, according to one embodiment of the invention, the one or more input signals may include data associated with a model (e.g., AI / ML model) configuration of a target cell and may be communicated by another device(s) 104 (e.g., target cell).

[0067] The input step 302 may include obtaining data associated with a model configuration of a target radio cell (or device 104 or a target base station) by a source radio cell (or device 104 or a source base station). The at least one base station (e.g., the target radio cell and the source radio cell) may correspond to at least one Next Generation Node B (gNB). The source radio cell (or device 104 or source base station) may request data associated with the model configuration of the target radio cell via a handover request. The model may be an artificial intelligence / machine learning (AI / ML or AIML)-based model, while the data may be associated with a specific model configuration. Furthermore, the model (e.g.,AI / ML model) configuration data may contain at least one of the following: life cycle management model (LCM) parameters, a model identifier (ID), and / or a pre-trained dataset, or any combination thereof.

[0068] With regard to processing step 304, according to one embodiment of the invention, at least one processing task may be performed in connection with the received input signal(s) or data in a manner that generates one or more output signals.

[0069] Processing step 304 may include at least one of the following: processing the model configuration data to generate one or more model parameters associated with the target cell model; communicating the one or more model parameters to a user device; and configuring the user device based on the one or more target cell model parameters before the user device roams to the target cell. Communicating the one or more model parameters to a user device may include communicating, through at least one of the following: a handover command message or a user equipment (UE)-specific message (e.g., a radio resource control (RRC) reconfiguration).

[0070] Processing step 304 may further include at least one of the following: receiving a request for the model (e.g., AI / ML model) configuration of the target cell; processing the request to generate data associated with the model (e.g., AI / ML model) configuration of the target cell; and transmitting the data associated with the model (e.g., AI / ML model) configuration of the target cell to the source cell.

[0071] With regard to output step 306, the output signal(s) may, for example, be optionally communicated according to one embodiment of the invention. For example, the output signal(s) may optionally be communicated by the device 104. In a more specific example, the output signal(s) may, according to one embodiment of the invention, be optionally communicated by the device 104 to at least one device 102 and / or to another device 104. In one embodiment, the device 104 (or the base station / radio cell) may also perform the input step 302, the processing step 304, and the output step 306.

[0072] The present disclosure further contemplates a computer program (not shown) that may include instructions that, when executed by a computer (not shown), cause the computer to perform input step 302, processing step 304, and / or output step 306, as discussed with reference to method 300. For example, according to one embodiment of the invention, the computer program may include instructions that, when executed by a computer, cause the computer to perform input step 302 and / or processing step 304.

[0073] The present disclosure further contemplates a computer-readable storage medium (not shown) having stored therein data representing software executable by a computer (not shown), the software including instructions that, when executed by the computer, cause the performance of input step 302, processing step 304, and / or output step 306, as discussed with reference to method 300. For example, according to one embodiment of the invention, the computer-readable storage medium may have stored therein data representing computer-executable software, the software including instructions that, when executed by the computer, cause the computer to perform input step 302 and / or processing step 304.

[0074] Further, in view of the foregoing, it is understood that the present disclosure generally contemplates an apparatus 104 that may include a first module 202, a second module 204, and / or a third module 206.

[0075] The first module 202 may be configured to receive one or more input signals. The input signal(s) may include, for example, receiving data associated with a model (e.g., AI / ML model) configuration of a target radio cell.

[0076] The second module 204 may be configured to process and / or enhance the processing of the input signal(s) or data according to the method 300, as discussed above, to generate one or more output signals.

[0077] The third module 206 may be configured to communicate one or more output signals. The output signal(s) may, for example, correspond to one or more control signals for configuring (or granting priority) to the user device (or UE) based on the one or more model (e.g., AI / ML model) parameters of the target cell before the user device roams to the target cell.

[0078] In one embodiment, device 102 may correspond to a user equipment (UE) that can communicate with a device 104 that corresponds to a base station (or a radio cell). The base station (or radio cell) may, for example, correspond to a next-generation node B (gNB), which may be configured to communicate one or more signals or data to the UE. The one or more signals may include one or more model (e.g., AI / ML model) parameters associated with the model (e.g., AI / ML model) of the target radio cell.

[0079] Furthermore, in light of the foregoing, it should be understood that the present disclosure generally contemplates a system 100 that may include one or more devices 102 and one or more apparatuses 104. The device(s) 102 and the apparatus(es) 104 may be coupled, for example, via a wired coupling and / or a wireless coupling.

[0080] It should be appreciated that the embodiments described above may be combined in any manner (e.g., one or more embodiments as discussed in the "Detailed Description" section may be combined with one or more embodiments as described in the "Summary of the Invention").

[0081] Furthermore, those skilled in the art should recognize that variations and combinations of embodiments described above that are not alternatives or replacements can be combined to form still further embodiments.

[0082] In one example, the possibility that the output signal(s) is / are communicated by the device(s) 104 was discussed. It should be appreciated that the output signal(s) do not necessarily have to be communicated by the device(s) 104. In particular, according to one embodiment of the invention, the possibility is contemplated that the output signal(s) do not necessarily have to be communicated externally to the device(s) 104. More specifically, according to one embodiment of the invention, the output signal(s) may, for example, correspond to internal command(s) / instruction(s) (e.g., communicated only within a device 102) for adaptively controlling the operating configuration of a device 102.

[0083] In another example according to an embodiment of the invention, application(s) of the present disclosure may be possible in connection with / in connection with a low-power wake-up radio and / or ambient IoT (Internet of Things) device(s).

[0084] Fig. 4A to Fig. 4D show schematic diagrams illustrating the flow of information associated with the process of Fig. 3 according to an embodiment of the invention.

[0085] In the exemplary context as in Fig. 4A, according to an embodiment of the invention, a user equipment (UE) may, for example, be configured to obtain / receive an AIML (or AI / ML) model configuration, such as AIML (or AI / ML) parameters, of a radio cell in a handover command message.

[0086] In the exemplary context as in Fig. For example, as shown in Figure 4B, according to one embodiment of the invention, a source gNB (or source base station / source cell) may be configured to request data associated with the model configuration (e.g., AIML or AI / ML model configuration) of a target gNB (or target base station / source cell). The source gNB (or source base station / source cell) may also configure the UE (or user device) with the AIML (or AI / ML) model configuration of the target gNB (or target base station / source cell), according to one embodiment of the invention.

[0087] In the exemplary context as in Fig. 4C, according to one embodiment of the invention, a target gNB (or target base station / target cell) may provide its AIML (or AI / ML) model configuration to the source gNB (or source base station / source cell).

[0088] In the exemplary context as in Fig.As shown in Figure 4D, a source gNB (or source cell) may be configured to request an AIML (or AI / ML) model configuration of a target gNB (or target cell) at step 1 upon a handover request. For example, at step 2, the target gNB (or target cell) may be configured to receive the request for its AIML (or AI / ML) model configuration and process the request to generate data associated with the model (e.g., the AIML model) configuration of the target cell. The target gNB (or target cell) may then transmit the data associated with its model (e.g., AI / ML model) configuration to the source gNB (or source cell) at step 3 upon a handover request acknowledgment. The source gNB (or source cell) receives the data associated with the model (e.g. AI / ML model) configuration of the target cell and processes the model (e.g.B AI / ML model) configuration data to generate one or more model parameters (e.g. AIML parameters) associated with the model (e.g. AIML model) of the target radio cell.

[0089] In step 5, the source gNB (or source cell) communicates the one or more model parameters (e.g., AIML parameters) of the target gNB (or target cell) to the UE (or user device) via an RRC reconfiguration message to configure the UE (or user device). Subsequently, in step 6, the UE (or user device) roams to the new cell (e.g., target cell or target gNB), and in step 7, the reconfiguration of the UE (or user device) is completed.

[0090] In the foregoing, various embodiments of the disclosure have been described to overcome at least one of the aforementioned disadvantages. These embodiments are intended to be encompassed by the following claims and are not limited to the specific forms or arrangements of parts so described, and it will be apparent to those skilled in the art, in light of this disclosure, that numerous changes and / or modifications may be made, which are also intended to be encompassed by the following claims.

Claims

[1] A method (300) for granting priority to a model configuration, the method comprising: Obtaining, by a source cell, data associated with a model configuration of a destination cell; Processing the model configuration data to generate one or more model parameters associated with the target cell model; Communicating the one or more model parameters to a user device; and Configuring the user device based on the one or more model parameters of the target cell before the user device moves to the target cell. [2] The method (300) of claim 1, further comprising: Requesting, by the source cell, data associated with the model configuration of the destination cell. [3] The method (300) of claim 2, wherein requesting data associated with the model configuration comprises requesting the data via a commit request. [4] The method (300) of claim 1, wherein the model is an artificial intelligence / machine learning (AIML) based model. [5] The method (300) of claim 1, wherein communicating the one or more model parameters to a user device comprises communicating by at least one of the following: a handover command message or a user equipment (UE) specific message. [6] The method (300) of claim 1, wherein the destination radio cell and the source radio cell correspond to at least one base station. [7] The method (300) of claim 6, wherein the at least one base station corresponds to at least one next generation node B (gNB). [8] The method (300) of claim 1, wherein the model configuration data comprises at least one of the following: life cycle management (LCM) parameters, a model identification (ID), and / or a pre-trained dataset. [9] The method (300) of claim 1, wherein obtaining the data associated with a model configuration comprises data associated with a specific model configuration. [10] The method (300) of claim 1, further comprising: Receiving a request for the model configuration of the target radio cell; Processing the request to generate data associated with the model configuration of the target radio cell; and Transferring the data associated with the target cell's model configuration to the source cell. [11] A computer program comprising instructions which, when executed by a computer, cause the computer to perform the method (300) according to any one of the preceding claims. [12] A computer-readable storage medium having stored therein data representing computer-executable software, the software containing instructions which, when executed by the computer, cause the method (300) of any one of claims 1-10 to be performed. [13] Device (104) for granting priority to a model configuration, comprising: a first module (202) configured to receive data associated with a model configuration of a target radio cell; a second module (204) configured to process and / or improve the method (300) according to claim 1 to claim 10 to generate at least one output signal; and a third module (206) configured to communicate at least one output signal, wherein the output signal corresponds to a control signal for configuring the user device based on the one or more model parameters of the target radio cell before the user device changes to the target radio cell. [14] Device (104) according to claim 13, wherein the device (104) corresponds to a base station capable of communicating with a device (102) corresponding to a user equipment (UE), and wherein the base station corresponds to a next generation node B (gNB) configured to communicate the at least one output signal to the UE. [15] System (100), comprising: at least one device (104) according to one of claims 13 and 14; and at least one device (102) according to claim 14, wherein the device (102) and the apparatus (104) can be coupled via a wired coupling and / or a wireless coupling.

Images