Devices and methods of communication
By managing AI/ML functionalities based on computing resources, memory, and power consumption, the terminal device optimizes energy usage in communication networks, addressing the challenge of high power consumption.
Patent Information
- Application Number
- PCT/CN2025/093216
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2026-11-12
AI Technical Summary
The deployment of AI/ML functionality in communication networks leads to increased power consumption, which is undesirable for user equipment and network sides, necessitating efficient management of computing resources, memory, storage, and power consumption to reduce energy costs.
A terminal device manages AI/ML functionalities based on received configurations and factors such as computing resources, memory, storage, power consumption, and duration, and performs life cycle management under specific conditions like low power or overheating detection.
This approach enables wise and power-saving operation of AI/ML functionalities, facilitating efficient resource allocation and reducing energy consumption.
Smart Images

Figure CN2025093216_12112026_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS OF COMMUNICATIONTECHNICAL FIELD
[0001] Embodiments of the present disclosure generally relate to the field of telecommunication, and in particular, to devices, methods and computer storage media of communication for artificial intelligence (AI) / machine learning (ML) functionality management.BACKGROUND
[0002] AI / ML functionality will be deployed anywhere in the future communication network no matter it is for native AI or use cases. Thus, more computing resources for AI / ML functionality may be required in the future communication network, which will cause more power consumption. It is undesirable that AI / ML functionality costs huge power consumption from either user equipment (UE) -side or network (NW) -side. Thus, green AI is promising. It is needed to consider how to wisely operate AI / ML functionality for the future communication network.SUMMARY
[0003] In general, embodiments of the present disclosure provide devices, methods and computer storage media of communication for AI / ML functionality management.
[0004] In a first aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: receive, from a network device, a set of configurations indicating a set of functionalities related to AI / ML; and manage an operation of the set of functionalities based on a set of factors comprising at least one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0005] In a second aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: receive, from a network device, a set of configurations indicating a set of functionalities related to AI / ML; and in accordance with a determination that a condition is fulfilled, perform life cycle management (LCM) for the set of functionalities, wherein the condition comprises at least one of the following: low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected.
[0006] In a third aspect, there is provided a network device. The network device comprises a processor. The processor is configured to cause the network device to: transmit, to a terminal device, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to AI / ML, wherein a threshold in the set of thresholds is associated with one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0007] In a fourth aspect, there is provided a network device. The network device comprises a processor. The processor is configured to cause the network device to: transmit, to a terminal device, a set of configurations indicating a set of functionalities related to AI / ML; and receive, from the terminal device, information of life cycle management for the set of functionalities comprising at least one of the following: information of deactivated or reduced one or more functionalities, or information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured.
[0008] In a fifth aspect, there is provided a method of communication at a terminal device. The method comprises: receiving, from a network device, a set of configurations indicating a set of functionalities related to AI / ML; and managing an operation of the set of functionalities based on a set of factors comprising at least one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0009] In a sixth aspect, there is provided a method of communication at a terminal device. The method comprises: receiving, from a network device, a set of configurations indicating a set of functionalities related to AI / ML; and in accordance with a determination that a condition is fulfilled, performing life cycle management for the set of functionalities, wherein the condition comprises at least one of the following: low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected.
[0010] In a seventh aspect, there is provided a method of communication at a network device. The method comprises: transmitting, to a terminal device, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to AI / ML, wherein a threshold in the set of thresholds is associated with one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0011] In an eighth aspect, there is provided a method of communication at a network device. The method comprises: transmitting, to a terminal device, a set of configurations indicating a set of functionalities related to AI / ML; and receiving, from the terminal device, information of life cycle management for the set of functionalities comprising at least one of the following: information of deactivated or reduced one or more functionalities, or information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured.
[0012] In a ninth aspect, there is provided a computer readable medium having instructions stored thereon. The instructions, when executed on at least one processor, cause the at least one processor to perform the method according to any of the fifth to eighth aspects of the present disclosure.
[0013] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Through the more detailed description of some embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:
[0015] FIG. 1 illustrates an example communication network in which some embodiments of the present disclosure can be implemented;
[0016] FIG. 2 illustrates a schematic diagram of an example functional framework for AI / ML for a new radio (NR) air interface in which some embodiments of the present disclosure can be implemented;
[0017] FIG. 3A illustrates a signaling chart illustrating an example process of network decision and network-initiated AI / ML management in which some embodiments of the present disclosure can be implemented;
[0018] FIG. 3B illustrates a signaling chart illustrating an example process of network decision and UE-initiated AI / ML management in which some embodiments of the present disclosure can be implemented;
[0019] FIG. 3C illustrates a signaling chart illustrating an example process of UE decision and event-triggered AI / ML management in which some embodiments of the present disclosure can be implemented;
[0020] FIG. 4 illustrates a signaling chart illustrating an example process of communication in accordance with some embodiments of the present disclosure;
[0021] FIG. 5A illustrates a schematic diagram of an example reporting of computing resources in accordance with some embodiments of the present disclosure;
[0022] FIG. 5B illustrates a schematic diagram of an example functionality operation management in accordance with some embodiments of the present disclosure;
[0023] FIG. 6 illustrates a signaling chart illustrating another example process of communication in accordance with some embodiments of the present disclosure;
[0024] FIG. 7A illustrates a schematic diagram of an example process of LCM in accordance with some embodiments of the present disclosure;
[0025] FIG. 7B illustrates a schematic diagram of another example process of LCM in accordance with some embodiments of the present disclosure;
[0026] FIG. 8 illustrates a flowchart of an example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;
[0027] FIG. 9 illustrates a flowchart of another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;
[0028] FIG. 10 illustrates a flowchart of an example method of communication implemented at a network device in accordance with some embodiments of the present disclosure;
[0029] FIG. 11 illustrates a flowchart of another example method of communication implemented at a network device in accordance with some embodiments of the present disclosure; and
[0030] FIG. 12 is a simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure.
[0031] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0032] Principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitations as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.
[0033] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
[0034] As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, Internet of things (IoT) devices, ultra-reliable and low latency communications (URLLC) devices, Internet of everything (IoE) devices, machine type communication (MTC) devices, device on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure / network, devices for integrated access and backhaul (IAB) , small data transmission (SDT) , mobility, multicast and broadcast services (MBS) , positioning, dynamic / flexible duplex in commercial networks, reduced capability (RedCap) , Space borne vehicles or air borne vehicles in non-terrestrial networks (NTN) including Satellites and high altitude platforms (HAPs) encompassing unmanned aircraft systems (UAS) , extended reality (XR) devices including different types of realities such as augmented reality (AR) , mixed reality (MR) and virtual reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast / broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple subscriber identity module (SIM) as known as multi-SIM. The term ‘terminal device’ can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.
[0035] The term ‘network device’ refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , Network-controlled Repeaters, and the like.
[0036] The terminal device or the network device may have AI or machine learning (ML) capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.
[0037] The terminal device or the network device may work on several frequency ranges, e.g. FR1 (410 MHz to 7125 MHz) , FR2 (24.25GHz to 71GHz) , frequency band larger than 100GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connections with the network devices under MR-DC application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0038] The network device may have the function of network energy saving, self-organizing networks (SON) / minimization of drive tests (MDT) . The terminal device may have the function of power saving.
[0039] The embodiments of the present disclosure may be performed in test equipment, e.g. signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator.
[0040] In one embodiment, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In one embodiment, the first network device may be a first RAT device and the second network device may be a second RAT device. In one embodiment, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device or the second network device. In one embodiment, information A may be transmitted to the terminal device from the first network device and information B may be transmitted to the terminal device from the second network device directly or via the first network device. In one embodiment, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
[0041] As used herein, the singular forms ‘a’ , ‘an’ and ‘the’ are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘one embodiment’ and ‘an embodiment’ are to be read as ‘at least one embodiment. ’ The term ‘another embodiment’ is to be read as ‘at least one other embodiment. ’ The terms ‘first, ’ ‘second, ’ and the like may refer to different or same objects. The term ‘and / or’ indicates that there may be three relationships. For example, A and / or B may indicate cases includes ‘only A’ , ‘both A and B’ , and ‘only B’ . The term ‘at least one of the following items’ or a similar expression thereof refers to any combination of these items, including any combination of a single item or a plurality of items. For example, the term ‘at least one of A, B, or C’ may represent A, B, C, ‘A and B’ , ‘A and C’ , ‘B and C’ , or ‘A, B and C’ . The term ‘aset of’ may be interchangeably used with ‘one or more’ . Other definitions, explicit and implicit, may be included below.
[0042] In some examples, values, procedures, or apparatus are referred to as ‘best, ’ ‘lowest, ’ ‘highest, ’ ‘minimum, ’ ‘maximum, ’ or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.
[0043] In the context of the present disclosure, the term ‘AI / ML’ may be interchangeably used with ‘AI or ML’ or ‘ML’ or ‘AI’ . The term ‘AI / ML functionality’ may be interchangeably used with ‘functionality related to AI / ML’ or ‘functionality’ . The term ‘functionality’ may be interchangeably used with ‘model’ or ‘use case’ . The term ‘operate’ may be interchangeably used with ‘run’ , ‘apply’ , ‘use’ or ‘activate’ . Operating AI / ML functionality is mainly for inference, but not limited to only inference. The term ‘low memory’ may mean full memory. The term ‘low storage’ may mean full storage.
[0044] It is to be noted that embodiments of the present disclosure are mainly designed for a UE-side model, but not limited to the UE-side model in case some embodiments are also applicable to a NW-side model.
[0045] As mentioned above, it is needed to consider how to wisely operate AI / ML functionality for the future communication network, e.g., resource allocation, AI / ML functionality operation determination, etc.
[0046] In view of the above, embodiments of the present disclosure provide solutions of communication so as to overcome the above and other potential issues.
[0047] In one aspect, upon reception a set of configurations indicating a set of functionalities related to AI / ML, a terminal device may manage an operation of the set of functionalities based on a set of factors comprising at least one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities. In this way, the terminal device may operate the set of functionalities wisely or in a power saving manner.
[0048] In another aspect, a network device may transmit, to a terminal device, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to AI / ML, wherein a threshold in the set of thresholds is associated with one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities. In this way, a wise or power-saving operation of the set of functionalities may be facilitated.
[0049] In another aspect, upon reception a set of configurations indicating a set of functionalities related to AI / ML, a terminal device may perform LCM for the set of functionalities upon fulfilling of a condition. The condition may comprise at least one of the following: low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected. In this way, the terminal device may perform LCM for the set of functionalities under some conditions specific to AI / ML.
[0050] In another aspect, a network device may transmit, to a terminal device, a set of configurations indicating a set of functionalities related to AI / ML; and receive, from the terminal device, information of LCM for the set of functionalities. The information of LCM may comprise at least one of the following: information of deactivated or reduced one or more functionalities, or information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured. In this way, LCM for the set of functionalities may be facilitated.
[0051] In the context of the present disclosure, the term ‘reduce’ means that a terminal device may just modify power class or occupied computing resource, etc., for specific functionality when one functionality could have multiple options. Furthermore, ‘reduce’ may also mean selecting some low level parameters to operate a model which may save power.
[0052] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.EXAMPLE OF COMMUNICATION NETWORK
[0053] FIG. 1 illustrates a schematic diagram of an example communication network 100 in which some embodiments of the present disclosure can be implemented. As shown in FIG. 1, the communication network 100 may include a terminal device 110 and a network device 120. In some embodiments, the network device 120 may provide one or more serving cells (not shown) to serve the terminal device 110.
[0054] The terminal device 110 may have a plurality of beams (not shown) , and the network device 120 may have a plurality of beams (not shown) . A channel (or called as a sub-channel in this case) may be formed between one of the plurality of beams of the terminal device 110 and one of the plurality of beams of the network device 120. The terminal device 110 may transmit information to the network device 120 or receive information from the network device 120 via one or more sub-channels.
[0055] It is to be understood that the number of devices in FIG. 1 is given for the purpose of illustration without suggesting any limitations to the present disclosure. The communication network 100 may include any suitable number of network devices and / or terminal devices and / or other network elements adapted for implementing implementations of the present disclosure.
[0056] As shown in FIG. 1, the terminal device 110 and the network device 120 may communicate with each other via a channel such as a wireless communication channel. The communications in the communication network 100 may conform to any suitable standards including, but not limited to, global system for mobile communications (GSM) , long term evolution (LTE) , LTE-evolution, LTE-advanced (LTE-A) , new radio (NR) , wideband code division multiple access (WCDMA) , code division multiple access (CDMA) , GSM EDGE radio access network (GERAN) , machine type communication (MTC) and the like. The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-advanced networks, or the sixth generation (6G) networks.
[0057] FIG. 2 illustrates a schematic diagram 200 of an example functional framework for AI / ML for a NR air interface in which some embodiments of the present disclosure can be implemented. FIG. 2 may be considered as an LCM overview. As shown in FIG. 2, training data, monitoring or testing data, and / or inference data may be obtained through an entity of data collection 210.
[0058] With reference to FIG. 2, the training data may be used for model training by an entity of model training 220. An AI model may be trained or updated through the model training. The trained or updated AI model may be stored by an entity of model storage 230.
[0059] With reference to FIG. 2, the monitoring or testing data may be used for model management by an entity of model management 240. The model management may comprise model monitoring, model testing, model selection, model activation, model deactivation, model switching, and / or model fallback. The entity of model management 240 may send performance feedback or retraining request to the entity of model training 220 for model retraining. The entity of model management 240 may send model transfer or delivery request to the entity of model storage 230, and the entity of model storage 230 may transfer or delivery the stored AI model to an entity of model inference 250.
[0060] As shown in FIG. 2, the inference data may be used for model inference by the entity of model inference 250. With the inference data as an input of the AI model, an output data set may be obtained by the model inference. The entity of model inference 250 may provide a monitoring or testing output to the entity of model management 240 and receive an indication of model selection / activation / deactivation / switching / fallback from the entity of model management 240.
[0061] So far, LCM of an AI model is described with reference to FIG. 2. It is to be understood that although the entities 210 to 250 are shown or described as separate entities in FIG. 2, these entities 210-250 may be implemented in one or more physical entities.
[0062] FIG. 3A illustrates a signaling chart illustrating an example process 300A of network decision and network-initiated AI / ML management in which some embodiments of the present disclosure can be implemented. The process 300A corresponds to the case where an LCM decision is taken and initiated by a network device. For example, the process 300A may involve the terminal device 110 and the network device 120 in FIG. 1.
[0063] As shown in FIG. 3A, at step 310, the network device 120 may transmit a configuration such as measurement and / or reporting to the terminal device 110. At step 311, the terminal device 110 may transmit performance or assistance information such as measurements to the network device 120.
[0064] At step 312, the network device 120 may decide to perform LCM. At step 313, the network device 120 may transmit a management instruction to the terminal device 110. It is to be noted that the management instruction may be a result of model / functionality performance monitoring at the network device 120. The management instruction may include information about the model or functionality.
[0065] FIG. 3B illustrates a signaling chart illustrating an example process 300B of network decision and UE-initiated AI / ML management in which some embodiments of the present disclosure can be implemented. The process 300B corresponds to the case where an LCM decision is taken by a network device but where a request for LCM is initiated by a terminal device. For example, the process 300B may involve the terminal device 110 and the network device 120 in FIG. 1.
[0066] As shown in FIG. 3B, at step 320, the network device 120 may transmit a configuration such as measurement and / or reporting to the terminal device 110. At step 321, the terminal device 110 may decide to perform LCM.
[0067] At step 322, the terminal device 110 may transmit a management request to the network device 120. It is to be noted that the management request may be a result of model / functionality performance monitoring at the terminal device 110. The management request may include information about the model or functionality. The network device 120 may accept or reject the management request from the terminal device 110.
[0068] At step 323, the network device 120 may transmit a management instruction to the terminal device 110. It is to be noted that the network device 120 may transmit the management instruction in response to the management request. The management instruction may include information about the model or functionality.
[0069] FIG. 3C illustrates a signaling chart illustrating an example process 300C of UE decision and event-triggered AI / ML management in which some embodiments of the present disclosure can be implemented. The process 300C corresponds to the case where an LCM decision is taken by a terminal device according to prior network configuration and initiated by the network. For example, the process 300C may involve the terminal device 110 and the network device 120 in FIG. 1.
[0070] As shown in FIG. 3C, at step 330, the network device 120 may transmit a configuration such as measurement and / or reporting to the terminal device 110. At step 331, the terminal device 110 may decide to perform LCM. At step 332, the terminal device 110 may transmit a management decision report to the network device 120. The management decision report may include information about the model or functionality.
[0071] It is to be noted that use case-specific events / conditions may be configured by the network device 120 for event-triggered AI / ML management at the terminal device 110. The terminal device 110 may transmit a management decision report to the network device 120 following event-triggered AI / ML management at the terminal device 110.
[0072] Embodiments of the present disclosure provide solutions of communication for AI / ML functionality management. For illustration, the solutions will be detailed below with reference to FIGs. 4 to 7B.EXAMPLE IMPLEMENTATION OF FUNCTIONALITY OPERATION MANAGEMENT
[0073] FIG. 4 illustrates a signaling chart illustrating an example process 400 of communication in accordance with embodiments of the present disclosure. For the purpose of discussion, the process 400 will be described with reference to FIG. 1. The process 400 may involve the terminal device 110 and the network device 120 as illustrated in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 4 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added.
[0074] As shown in FIG. 4, at step 410, the terminal device 110 may transmit, to the network device 120, information (also referred to as first information herein) of an operation of a set of functionalities related to AI / ML. The set of functionalities may comprise one or more functionalities. The first information may be considered as AI / ML specific assistance information to facilitate functionality operation management.
[0075] In some embodiments, the first information may indicate a computing resource for the operation of the set of functionalities. The computing resource may be an occupied hardware resource which is used to run AI / ML, e.g., central processing unit (CPU) , graphics processing unit (GPU) , tensor processing unit (TPU) , field programmable gate array (FPGA) , memory, storage, AI specified processing unit (APU / PU) , etc. In some embodiments, the computing resource may be a dedicated computing resource for specific functionality. In some embodiments, the computing resource may be common / shared computing resource for all functionalities.
[0076] In some embodiments, the first information may indicate complexity for the operation of the set of functionalities. For example, number of layers, number of neurons, connection patterns, total number of parameters, parameter distribution, time complexity, space complexity, and data scale, data size, data diversity.
[0077] In some embodiments, the first information may indicate a model size for the operation of the set of functionalities. For example, X MB for the one general large model, or X MB for each model when multiple models are deployed.
[0078] In some embodiments, the first information may indicate radio time or frequency domain resource for the operation of the set of functionalities. For example, occupied frequency / time, e.g., when radio resource management (RRM) measurement prediction is applied, a measurement window such as a synchronization signal block (SSB) measurement timing configuration (SMTC) should be given. When beam spatial prediction is applied, channel state information (CSI) resource (e.g., Set A / B) should be given.
[0079] In some embodiments, the first information may indicate a duration or timer for the operation of the set of functionalities, e.g., how long one functionality that the terminal device 110 is expecting to apply / use.
[0080] In some embodiments, the first information may indicate a priority or importance value for the operation of the set of functionalities. For example, the priority or importance value may be an integer. A functionality can be configured with one value, to indicate priority or importance value of this functionality. In another example, the priority or importance value may be represented by high / medium / low, etc. Additionally, a timer may be configured, which means how long the priority is expected / valid.
[0081] In some embodiments, the first information may indicate power consumption for the operation of the set of functionalities. For example, the first information may be an integer which indicates a power consumption level (also referred to as power class herein) . In other example, the first information may just be a power state / mode, e.g., non-power-saving mode (also referred to as normal mode herein) or power saving mode.
[0082] In some embodiments, the first information may indicate a model format. For example, the model format may be open format. In another example, the model format may be a proprietary format.
[0083] In some embodiments, the first information may indicate requirement on model monitoring or model training (retraining / fine-tuning) or data collection or model transfer. For example, the first information may indicate whether model monitoring or model training (retraining / fine-tuning) or data collection or model transfer is needed or not for operating a functionality.
[0084] In some embodiments, the first information may indicate preference on a threshold associated with the number of functionalities. For example, the first information may indicate an integer value for the threshold. The terminal device 110 is not allowed to simultaneously operate multiple functionalities when the number of functionalities is greater than the threshold.
[0085] In some embodiments, the first information may indicate a key performance indicator of a model output. For example, the first information may indicate prediction accuracy / precise, output number, F1 score, etc.
[0086] It is to be understood that any combinations of the above first information may also be feasible.
[0087] In some embodiments, the terminal device 110 may report its expected dedicated computing resource for one specific functionality with power consumption level and priority, and expected common computing resource for all functionalities. FIG. 5A illustrates a schematic diagram 500A of an example reporting of computing resources in accordance with some embodiments of the present disclosure. As shown in FIG. 5A, the terminal device 110 may report a total resource comprising dedicated resource for func-1 (with power class / priority) , dedicated resource for func-2 (with power class / priority) and a common / shared resource for all functionalities.
[0088] In some embodiments, the terminal device 110 may report functionalities combination, which means the terminal device 110 is expecting that combined functionalities should be operated simultaneously. For example, the terminal device 110 may report its expected combination, for example {func-1, func-3} . The network device 120 may, based on this information, simultaneously configure func-1 and func-3 to the terminal device 110, which means it is not likely to simultaneously configure func-1 with func-5 to the terminal device 110.
[0089] In some embodiments, if the power saving mode is set, the terminal device 110 may determine a first set of parameters as the first information. If the non-power-saving mode is set, the terminal device 110 may determine a second set of parameters as the first information. In other words, the above first information may be included in a set-level, i.e., the first information is reported in set-level. For example, when the terminal device 110 is expecting to operate functionalities with the power saving mode, there should be one set (e.g., Set-1) and parameter / assistance information within this Set-1 is included based on power saving mode, e.g., low power class, low computing resource, short duration / timer. On the other hand, there could be normal set (e.g., Set-2) which is to include a parameter which does not count power saving.
[0090] In some embodiments, the terminal device may transmit the first information upon an initiation condition is fulfilled. In some embodiments, the terminal device 110 may transmit the first information based on that a request for the transmission of the first information is received from the network device 120. For example, the terminal device 110 may transmit the first information via a UE information procedure (i.e., on-demand transmission) . During the UE information procedure, the network device 120 may request the terminal device 110 to provide the first information for operating functionality via a UE information request (UEInformationRequest) message, and the terminal device 110 may give a response via a UE information response (UEInformationResponse) message by including the above expected first information into the response.
[0091] In some embodiments, the terminal device 110 may transmit the first information based on implementation of the terminal device 110. In some embodiments, the terminal device 110 may transmit the first information based on that a configuration enabling the transmission of the first information is received from the network device 120. For example, the network device 120 may configure an enable indication to the terminal device 110 via e.g., OtherConfig, to indicate that the terminal device 110 is enabled to report the first information upon the first information is generated / available at UE-side, upon condition (e.g., low power, low computing resource, overheating, low memory, and low storage) is fulfilled. For example, the terminal device 110 may transmit the first information via a UE assistance information (UAI) message.
[0092] In some embodiments, if the first information is transmitted, the terminal device 110 may start a prohibit timer. The terminal device 110 is not allowed to transmit further first information during the prohibit timer is running. The prohibit timer is introduced to avoid frequent transmission.
[0093] In some embodiments, based on the first information, the network device 120 may configure proper configuration to the terminal device 110 for applying AI / ML model / functionality.
[0094] For illustration, an example UAI embodiment may be described as below. RRC reconfiguration - Reception of an RRCReconfiguration by UE 1> if the RRCReconfiguration message includes the otherConfig: 2> perform the other configuration procedure; - Other configuration The UE shall: 1> if the received otherConfig includes AIMLFuntionalityPreference: 2> if AIMLFuntionalityPreference is set to setup: 3> consider itself to be configured to provide AIML assistance information; 2> else: 3> consider itself not to be configured to provide AIML assistance information; UE Assistance Information The purpose of this procedure is for the UE to inform the network of: its AIML assistance information; - Initiation A UE capable of providing its preference on AIML functionality parameters may initiate the procedure in several cases, if it was configured to do so, including upon having a preference on AIML functionality parameters and upon change of its preference on parameters, upon condition (e.g., low power, low computing resource, overheating, low memory, low storage) is fulfilled. 1> if configured to provide AIML report: 2> if the UE did not transmit a UEAssistanceInformation message with AIMLFuntionalityPreference since it was configured; or 2> if the current AIML assistance information is different from the one indicated in the last transmission of the UEAssistanceInformation message including AIMLFuntionalityPreference and prohibit timer (if configured) is not running: 3> start or restart prohibit timer; 3> initiate transmission of the UEAssistanceInformation message to provide AIML assistance information; - Actions related to transmission of UEAssistanceInformation message 1> if transmission of the UEAssistanceInformation message is initiated to provide AIMLFuntionalityPreference: 2> include AIMLFuntionalityPreference in the UEAssistanceInformation message; 3> if the UE has a preference on Computing resource, Complexity, Model size, Radio time / frequency domain resource, Duration / Timer, Priority / Importance value, Power class / level / consumption, Model format, Requirement on model monitoring / model training (retraining / fine-tuning) / data collection / mode transfer, number threshold: 4> include [the above parameters] in the AIMLFuntionalityPreference IE; 1> submit the UEAssistanceInformation message to lower layers for transmission.
[0095] In some embodiments, the terminal device 110 may transmit the first information based on that low power is detected. In some embodiments, the terminal device 110 may transmit the first information based on that overheating is detected. In some embodiments, the terminal device 110 may transmit the first information based on that a low or short computing resource is detected. In some embodiments, the terminal device 110 may transmit the first information based on that a low or full memory is detected. In some embodiments, the terminal device 110 may transmit the first information based on that a low or full storage is detected.
[0096] It is to be noted that any combinations of the above initiation conditions may also be feasible.
[0097] As shown in step 420, in some embodiments, the terminal device 110 may transmit information (also referred to as second information herein) of capability of the terminal device 110 for the operation of the set of functionalities.
[0098] In some embodiments, the second information may indicate at least one of the following: a maximum or minimum supported total computing resource; a maximum or minimum supported computing resource for a functionality (e.g., each functionality) ; maximum or minimum supported total model complexity; maximum or minimum supported model complexity for a functionality (e.g., each functionality) ; a maximum or minimum supported model size (e.g., for one general large model) ; a maximum or minimum supported model size for a functionality (e.g., each functionality) ; a maximum or minimum supported threshold associated with number of functionalities; maximum or minimum supported total power consumption; maximum or minimum supported power consumption for a functionality (e.g., each functionality) ; a supported model format; support of model monitoring, model training (retraining / fine-tuning) , data collection or model transfer when operating a functionality; a maximum or minimum supported duration or timer of operating a functionality; or a maximum or minimum supported radio time or frequency domain resource (e.g., bandwidth, periodicity) .
[0099] In some embodiments, the terminal device 110 may receive a request for the second information via a UE capability enquiry (UECapabilityEnquiry) message from the network device 120. The terminal device 110 may transmit the second information to the network device 120 via a UE capability information (UECapabilityInformation) message.
[0100] By introducing new aspects, a network device may wisely configure AI / ML functionality to a terminal device for power consumption based on the assistance information / capability information.
[0101] As shown in FIG. 4, at step 430, the terminal device 110 may receive, from the network device 120, a set of configurations indicating a set of functionalities related to AI or ML. The set of configurations may comprise one or more configurations. The set of functionalities may comprise one or more functionalities. It is to be noted that the set of configurations may be implemented in any suitable ways, and the present disclosure does not limit this aspect.
[0102] At step 440, the terminal device 110 may manage an operation of the set of functionalities based on a set of factors (i.e., one or more factors) . The set of factors may comprise at least one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities. For example, based on some conditions associated with the one or more factors, the terminal device 110 may determine how or whether to operate the one or more functionalities.
[0103] In some embodiments, the power consumption for one or all of the set of functionalities may be characterized by a power consumption level (e.g., a power class or level value) . For example, the power consumption level may be an integer value. Different values may correspond to different power classes of operating a functionality. In some embodiments, a greater value may represent higher power consumption. In some embodiments, a smaller value may represent higher power consumption.
[0104] In some embodiments, the power consumption for one or all of the set of functionalities may be characterized by a power state or mode (e.g., a non-power-saving mode (also referred to as normal mode herein) or a power saving mode) . The non-power-saving mode means the terminal device 110 does not need to consider power consumption when operating a functionality. The power saving mode means the terminal device 110 needs to operate a functionality with specific power consumption, e.g., low power.
[0105] In some embodiments, the terminal device 110 may determine a set of thresholds for the set of factors, and manage the operation of the set of functionalities based on the set of thresholds. Such management may also be called as a threshold-based solution.
[0106] In some embodiments, the set of thresholds may be predefined. In some embodiments, the set of thresholds may be generated by the terminal device 110 and reported to the network device 120. In some embodiments, the set of thresholds may be configured by the network device 120.
[0107] In some embodiments, the terminal device 110 may transmit a cause value for a threshold in the set of thresholds to the network device 120, and receive a configuration of the threshold from the network device 120. That is, before network configuration, the terminal device 110 may report the cause value to the network device 120, the network device 120 may, based on this cause value, determine whether to configure the threshold to the terminal device 110.
[0108] In some embodiments, the set of thresholds may comprise a threshold (also referred to as a first threshold herein) associated with the computing resource or memory or storage for all of the set of functionalities. In some embodiments, the first threshold may be a computing resource threshold associated with the computing resource for all of the set of functionalities. In some embodiments, the first threshold may be a memory threshold associated with the memory for all of the set of functionalities. In some embodiments, the first threshold may be a storage threshold associated with the storage for all of the set of functionalities.
[0109] In some embodiments, the first threshold may be expressed by central processing unit (CPU) , graphics processing unit (GPU) , tensor processing unit (TPU) , field programmable gate array (FPGA) , memory, storage, or AI specified processing unit (APU / PU) .
[0110] In some embodiments, the terminal device 110 may transmit a cause value for the first threshold to the network device 120 and receive the configuration of the first threshold from the network device 120. For example, the cause value for the computing resource threshold may indicate a computing resource issue, and the terminal device 110 may receive the configuration of the computing resource threshold from the network device 120. In another example, the cause value for the memory threshold may indicate a memory issue, and the terminal device 110 may receive the configuration of the memory threshold from the network device 120. In another example, the cause value for the storage threshold may indicate a storage issue, and the terminal device 110 may receive the configuration of the storage threshold from the network device 120.
[0111] Some embodiments of applying the computing resource threshold for functionality management will be described as below.
[0112] In some embodiments, the network device 120 may provide multiple functionalities configurations with one (common) computing resource threshold to the terminal device 110. In some embodiments, the terminal device 110 may determine a total computing resource by evaluating computing resources of all operated functionalities at the same time, e.g., a sum of the computing resources of all operated functionalities. Alternatively, an occupied computing resource may mean a maximum allowed operated computing resources for each time domain / unit, i.e., regardless of when the maximum allowed operated computing resources are reached.
[0113] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by disabling the terminal device 110 to operate functionalities in the set of functionalities with the total computing resource greater than the computing resource threshold. That is, the terminal device 110 is not allowed to operate functionality with the total computing resource greater than the computing resource threshold.
[0114] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by selecting one or more functionalities in the set of functionalities for operation until the total computing resource is greater than or equal to the computing resource threshold. The selection may be performed based on functionality priority (e.g., firstly select those functionalities which are configured with higher priority) . FIG. 5B illustrates a schematic diagram 500B of an example functionality operation management in accordance with some embodiments of the present disclosure. As shown in FIG. 5B, NW configuration comprises functionality-Awith high priority, functionality-B with medium priority, functionality-C with low priority, and a computing resource threshold. Based on priorities of the functionalities, the terminal device 110 may firstly select operating functionality-A, and then select operating functionality-B. When the terminal device 110 selects operating functionality-C, a total computing resource is equal to a sum of computing resources for functionality-A, functionality-B and functionality-C. In this example, the total computing resource is greater than the computing resource threshold, and thus the terminal device 110 will not operate functionality-C.
[0115] It is to be noted that the selection may be performed based on implementation of the terminal device 110, and the present disclosure does not limit this aspect. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation.
[0116] In some embodiments, if the computing resource threshold is changed and the total computing resource for a set of operating functionalities is greater than the computing resource threshold, the terminal device 110 may deactivate one or more functionalities in the set of operating functionalities until the total computing resource is smaller than or equal to the computing resource threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating the deactivated one or more functionalities.
[0117] In some embodiments, if the computing resource threshold is changed and the total computing resource for a set of operating functionalities is greater than the computing resource threshold, the terminal device 110 may reduce the computing resource for operating one functionality until the total computing resource is smaller than or equal to the computing resource threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating one or more functionalities with the reduced computing resource.
[0118] Some embodiments of applying the memory threshold for functionality management will be described as below.
[0119] In some embodiments, the network device 120 may provide multiple functionalities configurations with one (common) memory threshold to the terminal device 110. In some embodiments, the terminal device 110 may determine a total memory by evaluating memories of all operated functionalities at the same time, e.g., a sum of the memories of all operated functionalities. Alternatively, an occupied memory may mean maximum allowed operated memories for each time domain / unit, i.e., regardless of when the maximum allowed operated memories are reached.
[0120] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by disabling the terminal device 110 to operate functionalities in the set of functionalities with the total memory greater than the memory threshold. That is, the terminal device 110 is not allowed to operate functionality with the total memory greater than the memory threshold.
[0121] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by selecting one or more functionalities in the set of functionalities for operation until the total memory is greater than or equal to the memory threshold. The selection may be performed based on functionality priority (e.g., firstly select those functionalities which are configured with higher priority) , or based on implementation of the terminal device 110. It is to be noted that the selection may be performed in any other suitable ways. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation.
[0122] In some embodiments, if the memory threshold is changed and the total memory for a set of operating functionalities is greater than the memory threshold, the terminal device 110 may deactivate one or more functionalities in the set of operating functionalities until the total memory is smaller than or equal to the memory threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating the deactivated one or more functionalities.
[0123] In some embodiments, if the memory threshold is changed and the total memory for a set of operating functionalities is greater than the memory threshold, the terminal device 110 may reduce the memory for operating one functionality until the total memory is smaller than or equal to the memory threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating one or more functionalities with the reduced memory.
[0124] Some embodiments of applying the storage threshold for functionality management will be described as below.
[0125] In some embodiments, the network device 120 may provide multiple functionalities configurations with one (common) storage threshold to the terminal device 110. In some embodiments, the terminal device 110 may determine a total storage by evaluating storages of all operated functionalities at the same time, e.g., by a sum of storages of all operated functionalities. Alternatively, an occupied storage may mean maximum allowed operated storages for each time domain / unit, i.e., regardless of when the maximum allowed operated storages are reached.
[0126] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by disabling the terminal device 110 to operate functionalities in the set of functionalities with the total storage greater than the storage threshold. That is, the terminal device 110 is not allowed to operate functionality with the total storage greater than the storage threshold.
[0127] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by selecting one or more functionalities in the set of functionalities for operation until the total storage is greater than or equal to the storage threshold. The selection may be performed based on functionality priority (e.g., firstly select those functionalities which are configured with higher priority) , or based on implementation of the terminal device 110. It is to be noted that the selection may be performed in any other suitable ways. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation.
[0128] In some embodiments, if the storage threshold is changed and the total computing resource for a set of operating functionalities is greater than the storage threshold, the terminal device 110 may deactivate one or more functionalities in the set of operating functionalities until the total storage is smaller than or equal to the storage threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating the deactivated one or more functionalities.
[0129] In some embodiments, if the storage threshold is changed and the total storage for a set of operating functionalities is greater than the storage threshold, the terminal device 110 may reduce the storage for operating one functionality until the total storage is smaller than or equal to the storage threshold. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating one or more functionalities with the reduced storage.
[0130] In some embodiments, if the first threshold (i.e., the computing resource threshold or the memory threshold or the storage threshold) is not configured, the terminal device 110 may operate all of the set of functionalities, i.e., all functionalities configured by the network device 120.
[0131] Alternatively or additionally, the set of thresholds may comprise a threshold (also referred to as a second threshold herein) associated with the computing resource or memory or storage for one functionality in the set of functionalities. That is, considering even for the same functionality, it could have different operation levels (e.g., different computing resource choices) , the network device 120 may provide each functionality with its corresponding computing resource threshold.
[0132] For example, the second threshold may be a dedicated computing resource threshold associated with the computing resource for the functionality. In some embodiments, the second threshold may be a dedicated memory threshold associated with the memory for the functionality. In some embodiments, the second threshold may be a dedicated storage threshold associated with the storage for the functionality.
[0133] In some embodiments, the terminal device 110 may select a maximum or minimum computing resource smaller than or equal to the dedicated computing resource threshold for operation of the functionality. In some embodiments, the total selected computing resources for all operated functionalities may not be greater than the common computing resource threshold described above.
[0134] In some embodiments, the terminal device 110 may select a maximum or minimum memory smaller than or equal to the dedicated memory threshold for operation of the functionality. In some embodiments, the total selected memories for all operated functionalities may not be greater than the common memory threshold described above.
[0135] In some embodiments, the terminal device 110 may select a maximum or minimum storage smaller than or equal to the dedicated storage threshold for operation of the functionality. In some embodiments, the total selected storages for all operated functionalities may not be greater than the common storage threshold described above.
[0136] In some embodiments, the set of thresholds may comprise a threshold (also referred to as a third threshold or a power class / level / consumption threshold herein) associated with the power consumption level for a functionality in the set of functionalities.
[0137] In some embodiments, the terminal device 110 may disable the terminal device 110 to operate the functionality with the power consumption level higher than the third threshold. That is, the terminal device is not allowed to operate one functionality with its power consumption level higher than the third threshold.
[0138] In some embodiments, the terminal device 110 may transmit a cause value for the third threshold to the network device 120 and receive the configuration of the third threshold from the network device 120. For example, the cause value for the third threshold may indicate a power consumption issue.
[0139] In some embodiments, if the functionality is configured with multiple power consumption levels, and at least one of the multiple power consumption levels is lower than the third threshold, the terminal device 110 is allowed to operate the functionality. In some embodiments, the terminal device 110 may select an allowed highest power consumption level to operate the functionality. In some embodiments, the terminal device 110 may select an allowed lowest power consumption level to operate the functionality. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating at least one of the following: the functionality operated with the allowed highest or lowest power consumption level; or one or more functionalities that are not operated. In other words, after the selection, the terminal device 110 may need to report an applied functionality with its power consumption level to the network device 120. Alternatively or additionally, the terminal device 110 may report an inapplicable functionality to the network device 120.
[0140] For example, the network device 120 configures to the terminal device 110 multiple functionalities fun-1, fun-2 and fun-3 and a power consumption level threshold equal to 5. The terminal device 110 can support operating fun-1 with power consumption level 6, fun-2 with power consumption level 1, and fun-3 with power consumption levels 3 and 7. Based on the power consumption level threshold equal to 5, the terminal device 110 may determine to only operate fun-2 with power consumption level 1 and fun-3 with power consumption level 3. Additionally, the terminal device 110 may report information indicating that fun-2 is operated with power consumption level 1 and fun-3 is operated with power consumption level 3, and / or information indicating that fun-1 is not operated.
[0141] In some embodiments, the set of thresholds may comprise a threshold (also referred to as a fourth threshold herein) associated with the number of functionalities. In some embodiments, the terminal device 110 may transmit a cause value for the fourth threshold to the network device 120 and receive the configuration of the fourth threshold from the network device 120. For example, the cause value for the fourth threshold may indicate a number of functionalities issue.
[0142] In some embodiments, if the number of functionalities is smaller than the fourth threshold, the terminal device 110 may operate the set of functionalities, i.e., apply all configured functionalities. In some embodiments, the terminal device 110 may select one or more functionalities in the set of functionalities for operation until the number of functionalities is greater than or equal to the fourth threshold. In some embodiments, the selection may be performed based on functionality priority (e.g., firstly select those functionalities which are configured with higher priority) , or based on implementation of the terminal device 110. It is to be noted that the selection may be performed in any other suitable ways. In some embodiments, the terminal device 110 may transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation.
[0143] In some embodiments, the set of thresholds may comprise a threshold (also referred to as a fifth threshold herein) associated with the duration or timer for a functionality in the set of functionalities. In some embodiments, the terminal device 110 may transmit a cause value for the fifth threshold to the network device 120 and receive the configuration of the fifth threshold from the network device 120. For example, the cause value for the fifth threshold may indicate a duration or timer issue.
[0144] In some embodiments, if a configuration of the functionality is applied, the terminal device 110 may start the duration or timer. If the duration or timer is expired, the terminal device 110 may deactivate or release or delete or remove the configuration of the functionality.
[0145] In some embodiments, the network device 120 may indicate whether the duration / timer can be refreshed, i.e., whether to restart the duration / timer. In some embodiments, this indication may be transmitted by a layer 1 (L1) / layer 2 (L2) signaling, e.g., downlink control information (DCI) / medium access control control element (MAC CE) . In some embodiments, this indication may be transmitted by a radio resource control (RRC) message.
[0146] In some embodiments, if an updated configuration of the functionality is received, the terminal device 110 may stop the duration or timer. In some embodiments, if an indication of restarting the duration or timer is received, the terminal device 110 may restart the duration or timer.
[0147] So far, the threshold-based solution for functionality operation management is described. The present disclosure also provides a solution of activation or deactivation of the threshold-based solution. In the solution, if a condition is fulfilled, the terminal device 110 may manage the operation of the set of functionalities based on the set of thresholds. That is, even though the above set of thresholds may be configured or predefined, but the set of thresholds may not be activated immediately. The threshold-based solution may be only activated upon the condition is fulfilled.
[0148] In some embodiments, the condition may comprise at least one of the following: low power is detected; overheating is detected; a low or short computing resource is detected; a low or full memory is detected; or a low or full storage is detected.
[0149] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities based on the power mode. In some embodiments, if the power saving mode is set (e.g., by either the terminal device 110 or the network device 120) , the terminal device 110 may not operate a functionality configured or labeled or indicated with a non-power-saving mode. That is, the terminal device 110 is disabled or not allowed to operate the functionality configured or labeled or indicated with the non-power-saving mode.
[0150] In some embodiments, if the non-power-saving mode is set (e.g., by either the terminal device 110 or the network device 120) , the terminal device 110 may operate a functionality configured or labeled or indicated with the power saving mode or the non-power-saving mode. That is, the terminal device 110 is allowed to operate the functionality configured or labeled or indicated with the power saving mode or the non-power-saving mode.
[0151] In some embodiments, there may be a network indication to indicate whether a functionality configured or labeled or indicated with power saving mode can also be operated in case of the non-power saving-mode (i.e., normal mode) . The terminal device 110 may operate a functionality configured or labeled or indicated with the power saving mode based on reception of the indication indicating that the functionality configured with the power saving mode can be operated in the non-power-saving mode.
[0152] As such, based on introduced AI specific aspect / condition, a terminal device may operate a functionality more wisely, and achieve control of AI / ML power consumption.EXAMPLE IMPLEMENTATION OF LCM MANAGEMENT
[0153] Embodiments of the present disclosure also provide a solution of LCM management. This solution will be described in connection with FIG. 6 below.
[0154] FIG. 6 illustrates a signaling chart illustrating another example process 600 of communication in accordance with embodiments of the present disclosure. For the purpose of discussion, the process 600 will be described with reference to FIG. 1. The process 600 may involve the terminal device 110 and the network device 120 as illustrated in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 6 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added.
[0155] As shown in FIG. 6, at step 610, the terminal device 110 may receive, from the network device 120, a set of configurations indicating a set of functionalities related to AI or ML.
[0156] At step 620, the terminal device 110 may determine whether a condition (for convenience, also referred to as a first condition herein) is fulfilled. The first condition is used for triggering LCM of the set of functionalities. In some embodiments, the first condition may be configured or predefined for one or more functionalities.
[0157] In some embodiments, the first condition may comprise at least one of the following: low power (e.g., low battery) is detected; overheating is detected; a low or short computing resource is detected; a low or full memory is detected; or a low or full storage is detected.
[0158] At step 630, upon determination that the condition is fulfilled, the terminal device 110 may perform LCM for the set of functionalities. As such, LCM management based on a condition or problem may be achieved. Some example embodiments will be described in connection with FIGs. 7A and 7B below.
[0159] FIG. 7A illustrates a schematic diagram of an example process 700A of LCM in accordance with some embodiments of the present disclosure. In this example, a request for LCM is transmitted by the terminal device 110, and LCM decision is done by the network device 120.
[0160] As shown in FIG. 7A, at step 710, the network device 120 may transmit a set of configurations indicating a set of functionalities related to AI or ML.
[0161] At step 711, the terminal device 110 may determine whether the first condition is fulfilled. Other details of the first condition are similar as that described in the step 620 of FIG. 6, and thus not repeated here for conciseness. It is assumed that the first condition is detected.
[0162] At step 712, upon determination that the first condition is fulfilled, the terminal device 110 may transmit, to the network device 120, information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured. For example, the terminal device 110 may transmit a management request comprising the information of the first subset of functionalities. In other words, the management request is for de-configuring or re-configuring or deactivating or reducing the first subset of functionalities.
[0163] At step 713, the terminal device 110 may receive, from the network device 120, an indication of de-configuring or re-configuring a second subset of functionalities in the set of functionalities. Based on this indication, the terminal device 110 may de-configure or re-configure a second subset of functionalities in the set of functionalities. The second subset of functionalities may be the same as the first subset of functionalities. Alternatively, the second subset of functionalities may be different from the first subset of functionalities.
[0164] That is, the terminal device 110 sends an indication of LCM and expected deactivated / reduced / de-configured / re-configured functionality to the network device 120. (Then the network device 120 may de-configure or re-configure functionality to the terminal device 110 to alleviate problem of the terminal device 110 caused by the condition / problem) .
[0165] One embodiment is that once the terminal device 110 detects low power state meanwhile the terminal device 110 is operating a functionality with power class value set to 6 (amaximum value) and a big amount of required PU, the terminal device 110 sends assistance information to request the network device 120 to de-configure this functionality. (After that the network device 120 may de-configure this functionality) .
[0166] So far, LCM management based on UE request and NW decision is completed.
[0167] FIG. 7B illustrates a schematic diagram of another example process 700B of LCM in accordance with some embodiments of the present disclosure. In this example, LCM decision is done by the terminal device 110 and reported to the network device 120.
[0168] As shown in FIG. 7B, at step 720, the network device 120 may transmit a set of configurations indicating a set of functionalities related to AI or ML.
[0169] At step 721, the terminal device 110 may determine whether the first condition is fulfilled, and upon determination that the first condition is fulfilled, the terminal device 110 may perform the LCM management by deactivating or reducing one or more functionalities in the set of functionalities.
[0170] Other details of the first condition are similar as that described in the step 620 of FIG. 6, and thus not repeated here for conciseness.
[0171] At step 722, the terminal device 110 may transmit information of the deactivated or reduced one or more functionalities to the network device 120. For example, the terminal device 110 may transmit, to the network device 120, a management decision report comprising the information of the deactivated or reduced one or more functionalities.
[0172] That is, the terminal device 110 deactivates / reduces some functionality based on the detected condition / problem, after that the terminal device 110 reports to the network device 120 with the information about deactivated / reduced functionality, e.g., the current power state value, overheating problem, etc.
[0173] So far, LCM management based on UE decision and report is completed.
[0174] It is to be understood that the above solutions or steps in the solutions as described in connection with FIGs. 1 to 7B may be carried out separately or in any suitable combinations.EXAMPLE IMPLEMENTATION OF METHODS
[0175] Corresponding to the above processes or solutions, embodiments of the present disclosure provide methods of communication implemented at a terminal device and a network device. These methods will be described below with reference to FIGs. 8 to 11.
[0176] FIG. 8 illustrates a flowchart of an example method 800 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 800 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 800 will be described with reference to FIG. 1. It is to be understood that the method 800 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0177] At block 810, the terminal device 110 may receive, from the network device 120, a set of configurations indicating a set of functionalities related to AI or ML.
[0178] At block 820, the terminal device 110 may manage an operation of the set of functionalities based on a set of factors. The set of factors comprise at least one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0179] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by: determining a set of thresholds for the set of factors; and managing the operation of the set of functionalities based on the set of thresholds.
[0180] In some embodiments, the terminal device 110 may determine the set of thresholds by:transmitting, to the network device 129, a cause value for a threshold in the set of thresholds; and receiving a configuration of the threshold from the network device 120
[0181] In some embodiments, the set of thresholds may comprise a first threshold associated with the computing resource or memory or storage for all of the set of functionalities. The terminal device 110 may manage the operation of the set of functionalities by at least one of the following: disabling the terminal device to operate functionalities in the set of functionalities with a total computing resource or memory or storage greater than the first threshold; selecting one or more functionalities in the set of functionalities for operation until the total computing resource or memory or storage is greater than or equal to the first threshold; in accordance with a determination that the first threshold is changed and the total computing resource or memory or storage for a set of operating functionalities is greater than the first threshold, deactivating one or more functionalities in the set of operating functionalities until the total computing resource or memory or storage is smaller than or equal to the first threshold; in accordance with a determination that the first threshold is changed and the total computing resource or memory or storage for a set of operating functionalities is greater than the first threshold, reducing the computing resource or memory or storage for operating one functionality until the total computing resource or memory or storage is smaller than or equal to the first threshold; or in accordance with a determination that the first threshold is not configured, operating all of the set of functionalities.
[0182] In some embodiments, the terminal device 110 may be further caused to at least one of the following: transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation; transmit, to the network device 120, information indicating one or more functionalities with the reduced computing resource; or transmit, to the network device 120, information indicating the deactivated one or more functionalities.
[0183] In some embodiments, the set of thresholds may further comprise a second threshold associated with the computing resource or memory or storage for a functionality in the set of functionalities. The terminal device 110 may manage the operation of the set of functionalities by: selecting a maximum or minimum computing resource or memory or storage smaller than or equal to the second threshold for operation of the functionality.
[0184] In some embodiments, the set of thresholds may comprise a third threshold associated with a power consumption level of the power consumption for a functionality in the set of functionalities. The terminal device 110 may manage the operation of the set of functionalities by at least one of the following: disabling the terminal device to operate the functionality with the power consumption level higher than the third threshold; or in accordance with a determination that the functionality is configured with multiple power consumption levels, and at least one of the multiple power consumption levels is lower than the third threshold, operating the functionality with an allowed highest or lowest power consumption level. In some embodiments, the terminal device 110 may be further caused to:transmit, to the network device 120, information indicating at least one of the following: the functionality operated with the allowed highest or lowest power consumption level; or one or more functionalities that are not operated.
[0185] In some embodiments, the set of thresholds may comprise a fourth threshold associated with the number of functionalities. The terminal device 110 may manage the operation of the set of functionalities by at least one of the following: in accordance with a determination that the number of functionalities is smaller than the fourth threshold, operating the set of functionalities; or selecting one or more functionalities in the set of functionalities for operation until the number of functionalities is greater than or equal to the fourth threshold. In some embodiments, the terminal device 110 may be further caused to: transmit, to the network device 120, information indicating at least one of the following: the one or more functionalities selected for operation; or one or more functionalities unselected for operation.
[0186] In some embodiments, the set of thresholds may comprise a fifth threshold associated with the duration or timer for a functionality in the set of functionalities. The terminal device 110 may manage the operation of the set of functionalities by at least one of the following: in accordance with a determination that a configuration of the functionality is applied, starting the duration or timer; in accordance with a determination that the duration or timer is expired, deactivating or releasing or deleting or removing the configuration of the functionality; in accordance with a determination that an updated configuration of the functionality is received, stopping the duration or timer; or in accordance with a determination that an indication of restarting the duration or timer is received, restarting the duration or timer.
[0187] In some embodiments, in accordance with a determination that a condition is fulfilled, the terminal device 110 may manage the operation of the set of functionalities based on the set of thresholds. The condition comprises at least one of the following: low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected.
[0188] In some embodiments, the terminal device 110 may manage the operation of the set of functionalities by at least one of the following: in accordance with a determination that a power saving mode is set, disabling the terminal device to operate a functionality configured with a non-power-saving mode; in accordance with a determination that the non-power-saving mode is set, enabling the terminal device to operate a functionality configured with the power saving mode or the non-power-saving mode; or enabling the terminal device to operate a functionality configured with the power saving mode based on reception of an indication indicating that the functionality configured with the power saving mode can be operated in the non-power-saving mode.
[0189] In some embodiments, the terminal device 110 may be further caused to: transmit, to the network device 120, first information of the operation of the set of functionalities. The first information indicates at least one of the following: a computing resource for the operation of the set of functionalities, complexity for the operation of the set of functionalities, a model size for the operation of the set of functionalities, radio time or frequency domain resource for the operation of the set of functionalities, a duration or timer for the operation of the set of functionalities, a priority or importance value for the operation of the set of functionalities, power consumption for the operation of the set of functionalities, requirement on model monitoring or model training or data collection or model transfer, preference on a threshold associated with the number of functionalities, or a key performance indicator of a model output.
[0190] In some embodiments, in accordance with a determination that a power saving mode is set, the terminal device 110 may determine a first set of parameters as the first information. In accordance with a determination that a non-power-saving mode is set, the terminal device 110 may determine a second set of parameters as the first information.
[0191] In some embodiments, the terminal device 110 may transmit the first information based on at least one of the following: a request for the transmission of the first information is received from the network device, a configuration enabling the transmission of the first information is received from the network device, low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected.
[0192] In some embodiments, in accordance with a determination that the first information is transmitted, the terminal device 110 may start a prohibit timer. The terminal device is not allowed to transmit further first information during the prohibit timer is running.
[0193] In some embodiments, the terminal device 110 may transmit, to the network device 120, second information of capability of the terminal device 110 for the operation of the set of functionalities. The second information indicates at least one of the following: a maximum or minimum supported total computing resource, a maximum or minimum supported computing resource for a functionality, maximum or minimum supported total model complexity, maximum or minimum supported model complexity for a functionality, a maximum or minimum supported model size, a maximum or minimum supported model size for a functionality, a maximum or minimum supported threshold associated with number of functionalities, maximum or minimum supported total power consumption, maximum or minimum supported power consumption for a functionality, a supported model format, support of model monitoring, model training, data collection or model transfer when operating a functionality, a maximum or minimum supported duration or timer of operating a functionality, or a maximum or minimum supported radio time or frequency domain resource.
[0194] With the method 800, a terminal device may operate a set of functionalities wisely or in a power saving manner.
[0195] FIG. 9 illustrates a flowchart of another example method 900 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 900 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1000 will be described with reference to FIG. 1. It is to be understood that the method 900 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0196] At block 910, the terminal device 110 may receive, from the network device 120, a set of configurations indicating a set of functionalities related to AI or ML.
[0197] At block 920, the terminal device 110 may determine that a condition is fulfilled. The condition comprises at least one of the following: low power is detected, overheating is detected, a low or short computing resource is detected, a low or full memory is detected, or a low or full storage is detected.
[0198] At block 930, in accordance with a determination that the condition is fulfilled, the terminal device 110 may perform life cycle management for the set of functionalities.
[0199] In some embodiments, the terminal device 110 may perform the life cycle management by: deactivating or reducing one or more functionalities in the set of functionalities; and transmitting information of the deactivated or reduced one or more functionalities to the network device.
[0200] In some embodiments, the terminal device 110 may perform the life cycle management by: transmitting, to the network device 120, information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured; and receiving, from the network device 120, an indication of de-configuring or re-configuring a second subset of functionalities in the set of functionalities.
[0201] With the method 900, a terminal device may perform LCM for a set of functionalities under some conditions specific to AI / ML.
[0202] FIG. 10 illustrates a flowchart of an example method 1000 of communication implemented at a network device in accordance with some embodiments of the present disclosure. For example, the method 1000 may be performed at the network device 120 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1000 will be described with reference to FIG. 1. It is to be understood that the method 1000 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0203] At block 1010, the network device 120 may transmit, to the terminal device 110, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to AI or ML. A threshold in the set of thresholds is associated with one of the following: a computing resource for one or all of the set of functionalities, a memory for one or all of the set of functionalities, a storage for one or all of the set of functionalities, power consumption for one or all of the set of functionalities, number of functionalities in the set of functionalities, or a duration or timer for one or all of the set of functionalities.
[0204] In some embodiments, the network device 120 may transmit the configuration by: receiving, from the terminal device 110, a cause value for a threshold in the set of thresholds; and transmitting the configuration of the threshold to the terminal device 110.
[0205] In some embodiments, the network device 120 may be further caused to at least one of the following: receive, from the terminal device 110, information indicating at least one of the following: one or more functionalities selected for operation, or one or more functionalities unselected for operation; receive, from the terminal device 110, information indicating one or more functionalities with a reduced computing resource; receive, from the terminal device 110, information indicating deactivated one or more functionalities; receive, from the terminal device 110, information indicating at least one of the following: a functionality operated with an allowed highest or lowest power consumption level; or one or more functionalities that are not operated.
[0206] In some embodiments, the network device 120 may be further caused to at least one of the following: transmit, to the terminal device 110, a request for transmission of first information of the operation of the set of functionalities; transmit, to the terminal device 110, a configuration enabling the transmission of the first information; or receive, from the terminal device 110, the first information of the operation of the set of functionalities. The first information indicates at least one of the following: a computing resource for the operation of the set of functionalities, complexity for the operation of the set of functionalities, a model size for the operation of the set of functionalities, radio time or frequency domain resource for the operation of the set of functionalities, a duration or timer for the operation of the set of functionalities, a priority or importance value for the operation of the set of functionalities, power consumption for the operation of the set of functionalities, requirement on model monitoring or model training or data collection or model transfer, preference on a threshold associated with the number of functionalities, or a key performance indicator of a model output.
[0207] In some embodiments, the network device 120 may receive, from the terminal device 110, second information of capability of the terminal device 110 for the operation of the set of functionalities. The second information indicates at least one of the following: a supported total computing resource, a supported computing resource for a functionality, supported total model complexity, supported model complexity for a functionality, a supported model size, a supported model size for a functionality, a supported threshold associated with number of functionalities, supported total power consumption, supported power consumption for a functionality, a supported model format, support of model monitoring, model training, data collection or model transfer when operating a functionality, a supported duration or timer of operating a functionality, or a supported radio time or frequency domain resource.
[0208] With the method 1000, a wise or power-saving operation of the set of functionalities may be facilitated.
[0209] FIG. 11 illustrates a flowchart of another example method 1100 of communication implemented at a network device in accordance with some embodiments of the present disclosure. For example, the method 1100 may be performed at the network device 120 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1100 will be described with reference to FIG. 1. It is to be understood that the method 1100 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0210] At block 1110, the network device 120 may transmit, to the terminal device 110, a set of configurations indicating a set of functionalities related to AI or ML.
[0211] At block 1120, the network device 120 may receive, from the terminal device 110, information of life cycle management for the set of functionalities. The information comprises at least one of the following: information of deactivated or reduced one or more functionalities, or information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured.
[0212] In some embodiments, the network device 120 may transmit, to the terminal device 110, an indication of de-configuring or re-configuring a second subset of functionalities in the set of functionalities.
[0213] With the method 1100, LCM for the set of functionalities may be facilitated.
[0214] It is to be understood that operations of the methods 800, 900, 1000 and 1100 correspond to that described in connection with FIGs. 1 to 7B, and thus other details are not repeated here for conciseness.EXAMPLE IMPLEMENTATION OF DEVICES
[0215] FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing embodiments of the present disclosure. The device 1200 can be considered as a further example implementation of the terminal device 110 or the network device 120 as shown in FIG. 1. Accordingly, the device 1200 can be implemented at or as at least a part of the terminal device 110 or the network device 120.
[0216] As shown, the device 1200 includes a processor 1210, a memory 1220 coupled to the processor 1210, a suitable transceiver 1240 coupled to the processor 1210, and a communication interface coupled to the transceiver 1240. The memory 1210 stores at least a part of a program 1230. The transceiver 1240 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1240 may include at least one of a transmitter 1242 or a receiver 1244. The transmitter 1242 and the receiver 1244 may be functional modules or physical entities. The transceiver 1240 has at least one antenna to facilitate communication, though in practice an access node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2 / Xn interface for bidirectional communications between eNBs / gNBs, S1 / NG interface for communication between a mobility management entity (MME) / access and mobility management function (AMF) / SGW / UPF and the eNB / gNB, Un interface for communication between the eNB / gNB and a relay node (RN) , or Uu interface for communication between the eNB / gNB and a terminal device.
[0217] The program 1230 is assumed to include program instructions that, when executed by the associated processor 1210, enable the device 1200 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGs. 1 to 11. The embodiments herein may be implemented by computer software executable by the processor 1210 of the device 1200, or by hardware, or by a combination of software and hardware. The processor 1210 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1210 and memory 1220 may form processing means 1250 adapted to implement various embodiments of the present disclosure.
[0218] The memory 1220 may be of any type suitable to the local technical network and may be implemented using any suitable data storage technology, such as a non-transitory computer readable storage medium, semiconductor based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. While only one memory 1220 is shown in the device 1200, there may be several physically distinct memory modules in the device 1200. The processor 1210 may be of any type suitable to the local technical network, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1200 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.
[0219] In some embodiments, a terminal device comprises a circuitry configured to perform the method 800 or 900. In some embodiments, a network device comprises a circuitry configured to perform the method 1000 or 1100. The term ‘circuitry’ used herein may refer to hardware circuits and / or combinations of hardware circuits and software. For example, the circuitry may be a combination of analog and / or digital hardware circuits with software / firmware. As a further example, the circuitry may be any portions of hardware processors with software including digital signal processor (s) , software, and memory (ies) that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In a still further example, the circuitry may be hardware circuits and or processors, such as a microprocessor or a portion of a microprocessor, that requires software / firmware for operation, but the software may not be present when it is not needed for operation. As used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (s) or a portion of a hardware circuit or processor (s) and its (or their) accompanying software and / or firmware.
[0220] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representation, it will be appreciated that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
[0221] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGs. 1 to 11. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.
[0222] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0223] The above program code may be embodied on a machine readable medium, which may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0224] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0225] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1.A terminal device, comprising:a processor configured to cause the terminal device to:receive, from a network device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andmanage an operation of the set of functionalities based on a set of factors comprising at least one of the following:a computing resource for one or all of the set of functionalities,a memory for one or all of the set of functionalities,a storage for one or all of the set of functionalities,power consumption for one or all of the set of functionalities,number of functionalities in the set of functionalities, ora duration or timer for one or all of the set of functionalities.2.The terminal device of claim 1, wherein the terminal device is caused to manage the operation of the set of functionalities by:determining a set of thresholds for the set of factors; andmanaging the operation of the set of functionalities based on the set of thresholds.3.The terminal device of claim 2, wherein the terminal device is caused to determine the set of thresholds by:transmitting, to the network device, a cause value for a threshold in the set of thresholds; andreceiving a configuration of the threshold from the network device.4.The terminal device of claim 2, wherein the set of thresholds comprises a first threshold associated with the computing resource or memory or storage for all of the set of functionalities, and wherein the terminal device is caused to manage the operation of the set of functionalities by at least one of the following:disabling the terminal device to operate functionalities in the set of functionalities with a total computing resource or memory or storage greater than the first threshold;selecting one or more functionalities in the set of functionalities for operation until the total computing resource or memory or storage is greater than or equal to the first threshold;in accordance with a determination that the first threshold is changed and the total computing resource or memory or storage for a set of operating functionalities is greater than the first threshold, deactivating one or more functionalities in the set of operating functionalities until the total computing resource or memory or storage is smaller than or equal to the first threshold;in accordance with a determination that the first threshold is changed and the total computing resource or memory or storage for a set of operating functionalities is greater than the first threshold, reducing the computing resource or memory or storage for operating one functionality until the total computing resource or memory or storage is smaller than or equal to the first threshold; orin accordance with a determination that the first threshold is not configured, operating all of the set of functionalities.5.The terminal device of claim 4, wherein the terminal device is further caused to at least one of the following:transmit, to the network device, information indicating at least one of the following: the one or more functionalities selected for operation, or one or more functionalities unselected for operation;transmit, to the network device, information indicating one or more functionalities with the reduced computing resource; ortransmit, to the network device, information indicating the deactivated one or more functionalities.6.The terminal device of claim 4, wherein the set of thresholds further comprises a second threshold associated with the computing resource or memory or storage for a functionality in the set of functionalities, and wherein the terminal device is caused to manage the operation of the set of functionalities by:selecting a maximum or minimum computing resource or memory or storage smaller than or equal to the second threshold for operation of the functionality.7.The terminal device of claim 2, wherein the set of thresholds comprises a third threshold associated with a power consumption level of the power consumption for a functionality in the set of functionalities, and wherein the terminal device is caused to manage the operation of the set of functionalities by at least one of the following:disabling the terminal device to operate the functionality with the power consumption level higher than the third threshold; orin accordance with a determination that the functionality is configured with multiple power consumption levels, and at least one of the multiple power consumption levels is lower than the third threshold, operating the functionality with an allowed highest or lowest power consumption level.8.The terminal device of claim 7, wherein the terminal device is further caused to:transmit, to the network device, information indicating at least one of the following: the functionality operated with the allowed highest or lowest power consumption level; or one or more functionalities that are not operated.9.The terminal device of claim 2, wherein the set of thresholds comprises a fourth threshold associated with the number of functionalities, and wherein the terminal device is caused to manage the operation of the set of functionalities by at least one of the following:in accordance with a determination that the number of functionalities is smaller than the fourth threshold, operating the set of functionalities; orselecting one or more functionalities in the set of functionalities for operation until the number of functionalities is greater than or equal to the fourth threshold.10.The terminal device of claim 9, wherein the terminal device is further caused to:transmit, to the network device, information indicating at least one of the following: the one or more functionalities selected for operation; or one or more functionalities unselected for operation.11.The terminal device of claim 2, wherein the set of thresholds comprises a fifth threshold associated with the duration or timer for a functionality in the set of functionalities, and wherein the terminal device is caused to manage the operation of the set of functionalities by at least one of the following:in accordance with a determination that a configuration of the functionality is applied, starting the duration or timer;in accordance with a determination that the duration or timer is expired, deactivating or releasing or deleting or removing the configuration of the functionality;in accordance with a determination that an updated configuration of the functionality is received, stopping the duration or timer; orin accordance with a determination that an indication of restarting the duration or timer is received, restarting the duration or timer.12.The terminal device of claim 2, wherein the terminal device is caused to manage the operation of the set of functionalities by:in accordance with a determination that a condition is fulfilled, managing the operation of the set of functionalities based on the set of thresholds, wherein the condition comprises at least one of the following:low power is detected,overheating is detected,a low or short computing resource is detected,a low or full memory is detected, ora low or full storage is detected.13.The terminal device of claim 1, wherein the terminal device is caused to manage the operation of the set of functionalities by at least one of the following:in accordance with a determination that a power saving mode is set, disabling the terminal device to operate a functionality configured with a non-power-saving mode;in accordance with a determination that the non-power-saving mode is set, enabling the terminal device to operate a functionality configured with the power saving mode or the non-power-saving mode; orenabling the terminal device to operate a functionality configured with the power saving mode based on reception of an indication indicating that the functionality configured with the power saving mode can be operated in the non-power-saving mode.14.The terminal device of claim 1, wherein the terminal device is further caused to:transmit, to the network device, first information of the operation of the set of functionalities, wherein the first information indicates at least one of the following:a computing resource for the operation of the set of functionalities,complexity for the operation of the set of functionalities,a model size for the operation of the set of functionalities,radio time or frequency domain resource for the operation of the set of functionalities,a duration or timer for the operation of the set of functionalities,a priority or importance value for the operation of the set of functionalities,power consumption for the operation of the set of functionalities,requirement on model monitoring or model training or data collection or model transfer,preference on a threshold associated with the number of functionalities, ora key performance indicator of a model output.15.The terminal device of claim 14, wherein the terminal device is further caused to:in accordance with a determination that a power saving mode is set, determine a first set of parameters as the first information; andin accordance with a determination that a non-power-saving mode is set, determine a second set of parameters as the first information.16.The terminal device of claim 14, wherein the terminal device is caused to transmit the first information by:transmitting the first information based on at least one of the following:a request for the transmission of the first information is received from the network device,a configuration enabling the transmission of the first information is received from the network device,low power is detected,overheating is detected,a low or short computing resource is detected,a low or full memory is detected, ora low or full storage is detected.17.The terminal device of claim 14, wherein the terminal device is further caused to:in accordance with a determination that the first information is transmitted, start a prohibit timer, wherein the terminal device is not allowed to transmit further first information during the prohibit timer is running.18.The terminal device of claim 1, wherein the terminal device is further caused to:transmit, to the network device, second information of capability of the terminal device for the operation of the set of functionalities, wherein the second information indicates at least one of the following:a maximum or minimum supported total computing resource,a maximum or minimum supported computing resource for a functionality,maximum or minimum supported total model complexity,maximum or minimum supported model complexity for a functionality,a maximum or minimum supported model size,a maximum or minimum supported model size for a functionality,a maximum or minimum supported threshold associated with number of functionalities,maximum or minimum supported total power consumption,maximum or minimum supported power consumption for a functionality,a supported model format,support of model monitoring, model training, data collection or model transfer when operating a functionality,a maximum or minimum supported duration or timer of operating a functionality, ora maximum or minimum supported radio time or frequency domain resource.19.A terminal device, comprising:a processor configured to cause the terminal device to:receive, from a network device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andin accordance with a determination that a condition is fulfilled, perform life cycle management for the set of functionalities, wherein the condition comprises at least one of the following:low power is detected,overheating is detected,a low or short computing resource is detected,a low or full memory is detected, ora low or full storage is detected.20.The terminal device of claim 19, wherein the terminal device is caused to perform the life cycle management by:deactivating or reducing one or more functionalities in the set of functionalities; andtransmitting information of the deactivated or reduced one or more functionalities to the network device.21.The terminal device of claim 19, wherein the terminal device is caused to perform the life cycle management by:transmitting, to the network device, information of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured; andreceiving, from the network device, an indication of de-configuring or re-configuring a second subset of functionalities in the set of functionalities.22.A network device, comprising:a processor configured to cause the network device to:transmit, to a terminal device, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to artificial intelligence (AI) or machine learning (ML) , wherein a threshold in the set of thresholds is associated with one of the following:a computing resource for one or all of the set of functionalities,a memory for one or all of the set of functionalities,a storage for one or all of the set of functionalities,power consumption for one or all of the set of functionalities,number of functionalities in the set of functionalities, ora duration or timer for one or all of the set of functionalities.23.The network device of claim 22, wherein the network device is caused to transmit the configuration by:receiving, from the terminal device, a cause value for a threshold in the set of thresholds; andtransmitting the configuration of the threshold to the terminal device.24.The network device of claim 22, wherein the network device is further caused to at least one of the following:receive, from the terminal device, information indicating at least one of the following: one or more functionalities selected for operation, or one or more functionalities unselected for operation;receive, from the terminal device, information indicating one or more functionalities with a reduced computing resource;receive, from the terminal device, information indicating deactivated one or more functionalities;receive, from the terminal device, information indicating at least one of the following: a functionality operated with an allowed highest or lowest power consumption level; or one or more functionalities that are not operated.25.The network device of claim 22, wherein the network device is further caused to at least one of the following:transmit, to the terminal device, a request for transmission of first information of the operation of the set of functionalities;transmit, to the terminal device, a configuration enabling the transmission of the first information; orreceive, from the terminal device, the first information of the operation of the set of functionalities, wherein the first information indicates at least one of the following:a computing resource for the operation of the set of functionalities,complexity for the operation of the set of functionalities,a model size for the operation of the set of functionalities,radio time or frequency domain resource for the operation of the set of functionalities,a duration or timer for the operation of the set of functionalities,a priority or importance value for the operation of the set of functionalities,power consumption for the operation of the set of functionalities,requirement on model monitoring or model training or data collection or model transfer,preference on a threshold associated with the number of functionalities, ora key performance indicator of a model output.26.The network device of claim 22, wherein the network device is further caused to:receive, from the terminal device, second information of capability of the terminal device for the operation of the set of functionalities, wherein the second information indicates at least one of the following:a supported total computing resource,a supported computing resource for a functionality,supported total model complexity,supported model complexity for a functionality,a supported model size,a supported model size for a functionality,a supported threshold associated with number of functionalities,supported total power consumption,supported power consumption for a functionality,a supported model format,support of model monitoring, model training, data collection or model transfer when operating a functionality,a supported duration or timer of operating a functionality, ora supported radio time or frequency domain resource.27.A network device, comprising:a processor configured to cause the network device to:transmit, to a terminal device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andreceive, from the terminal device, information of life cycle management for the set of functionalities comprising at least one of the following:information of deactivated or reduced one or more functionalities, orinformation of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured.28.The network device of claim 27, wherein the network device is further caused to:transmit, to the terminal device, an indication of de-configuring or re-configuring a second subset of functionalities in the set of functionalities.29.A method of communication at a terminal device, comprising:receiving, from a network device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andmanaging an operation of the set of functionalities based on a set of factors comprising at least one of the following:a computing resource for one or all of the set of functionalities,a memory for one or all of the set of functionalities,a storage for one or all of the set of functionalities,power consumption for one or all of the set of functionalities,number of functionalities in the set of functionalities, ora duration or timer for one or all of the set of functionalities.30.A method of communication at a terminal device, comprising:receiving, from a network device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andin accordance with a determination that a condition is fulfilled, performing life cycle management for the set of functionalities, wherein the condition comprises at least one of the following:low power is detected,overheating is detected,a low or short computing resource is detected,a low or full memory is detected, ora low or full storage is detected.31.A method of communication at a network device, comprising:transmitting, to a terminal device, a configuration indicating a set of thresholds for management of an operation of a set of functionalities related to artificial intelligence (AI) or machine learning (ML) , wherein a threshold in the set of thresholds is associated with one of the following:a computing resource for one or all of the set of functionalities,a memory for one or all of the set of functionalities,a storage for one or all of the set of functionalities,power consumption for one or all of the set of functionalities,number of functionalities in the set of functionalities, ora duration or timer for one or all of the set of functionalities.32.A method of communication at a network device, comprising:transmitting, to a terminal device, a set of configurations indicating a set of functionalities related to artificial intelligence (AI) or machine learning (ML) ; andreceiving, from the terminal device, information of life cycle management for the set of functionalities comprising at least one of the following:information of deactivated or reduced one or more functionalities, orinformation of a first subset of functionalities in the set of functionalities that is expected to be deactivated or reduced or de-configured or re-configured.
