Methods and apparatus for model activation and management in mobile communications
The proposed methods and apparatus for model activation and management in mobile networks address the need for precise control of AI model activation and resource allocation, enhancing service quality and stability by utilizing applicability reports for timely activation and resource management.
Patent Information
- Application Number
- PCT/CN2026/095076
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-07
- Filing Date
- 2026-05-07
- Publication Date
- 2026-11-12
AI Technical Summary
The activation timing and resource allocation for AI models in mobile communication networks require precise control mechanisms to ensure service quality and system stability, particularly in dynamic network environments.
Implementing methods and apparatus for model activation and management that involve transmitting a model inference configuration, receiving an applicability report indicating time to model availability, and activating the AI model before the specified time to enhance resource allocation and scheduling.
Enhances the activation and management of AI models in mobile networks, improving service quality and system stability by ensuring timely and efficient resource utilization.
Smart Images

Figure CN2026095076_12112026_PF_FP_ABST
Abstract
Description
METHODS AND APPARATUS FOR MODEL ACTIVATION AND MANAGEMENT IN MOBILE COMMUNICATIONSCROSS REFERENCE TO RELATED PATENT APPLICATION (S)
[0001] The present disclosure is part of a non-provisional application claiming the priority benefit of PCT Application No. PCT / CN2025 / 093109, filed 7 May 2025, the content of which herein being incorporated by reference in its entirety.TECHNICAL FIELD
[0002] The present disclosure is generally related to mobile communications and, more particularly, to methods and apparatus for model activation and management in mobile communications.BACKGROUND
[0003] Unless otherwise indicated herein, approaches described in this section are not prior art to the claims listed below and are not admitted as prior art by inclusion in this section.
[0004] With the continuous evolution of mobile communication technologies, the 3rd Generation Partnership Project (3GPP) has established the global foundation for mobile networks since the era of third-generation (3G) systems. The introduction of fourth-generation (4G LTE) networks enabled high-speed data transmission and packet-switched architectures, accelerating the growth of mobile Internet and cloud-based services. In recent years, the fifth-generation (5G) mobile communication system standardized by 3GPP has further introduced key capabilities such as ultra-reliable and low-latency communications (URLLC) , massive machine-type communications (mMTC) , and enhanced mobile broadband (eMBB) . These advancements have transformed mobile networks from simple data transport infrastructures into core platforms that support diverse applications and intelligent services.
[0005] In 5G and its subsequent evolution, including 5G-Advanced, network virtualization, software-defined networking (SDN) , and network function virtualization (NFV) have become fundamental design principles, enabling dynamic network configuration according to service requirements. At the same time, the introduction of network slicing allows multiple logical networks with differentiated performance characteristics to coexist on a shared physical infrastructure. These technologies provide a robust foundation for the integration of artificial intelligence (AI) and machine learning (ML) into communication networks, thereby allowing AI to function not only at the application layer but also as a key enabler for network management, resource optimization, and automated operations.
[0006] However, as AI models become increasingly crucial to network operations, their activation timing, computational resource allocation, and cross-node coordination directly affect service quality and system stability. Accordingly, to effectively support distributed and dynamic AI functionalities, the network requires more precise control mechanisms for AI activation processes, as well as enhanced resource allocation and scheduling capabilities.SUMMARY
[0007] The following summary is illustrative only and is not intended to be limiting in any way. That is, the following summary is provided to introduce concepts, highlights, benefits and advantages of the novel and non-obvious techniques described herein. Select implementations are further described below in the detailed description. Thus, the following summary is not intended to identify essential features of the claimed subject matter, nor is it intended for use in determining the scope of the claimed subject matter.
[0008] An objective of the present disclosure is to propose solutions or schemes that address the aforementioned issue pertaining to methods and apparatus for model activation and management in mobile communications.
[0009] In one aspect, a method may involve an apparatus receiving a model inference configuration from a network node. The model inference configuration may be related to inference of an artificial intelligence (AI) model. The method may also involve the apparatus transmitting an applicability report to the network node in response to the model inference configuration. The applicability report may indicate a time to model availability for activating the AI model. The method may further involve the apparatus activating the AI model before an end of the time to model availability.
[0010] In one aspect, an apparatus may include a transceiver which, during operation, wirelessly communicates with a network. The apparatus may also include a processor communicatively coupled to the transceiver. The processor, during operation, may perform operations including receiving, via the transceiver, a model inference configuration from a network node. The model inference configuration may be related to inference of an AI model. The processor may also perform operations including transmitting, via the transceiver, an applicability report to the network node in response to the model inference configuration. The applicability report may indicate a time to model availability for activating the AI model. The processor may further perform operations including activating the AI model before an end of the time to model availability.
[0011] In another aspect, a method may involve a network node transmitting a model inference configuration to an apparatus. The model inference configuration may be related to inference of an AI model. The method may also involve the network node receiving an applicability report from the apparatus. The applicability report may indicate a time to model availability for activating the AI model. The method may further involve the network node receiving data generated by the AI model from the apparatus after an end of the time to model availability.
[0012] It is noteworthy that, although description provided herein may be in the context of certain radio access technologies, networks and network topologies such as LTE, LTE-Advanced, LTE-Advanced Pro, 5G, NR, 5G-Advanced, Internet-of-Things (IoT) , Narrow Band Internet of Things (NB-IoT) , Industrial Internet of Things (IIoT) , beyond 5G (B5G) , and 6th Generation (6G) , the proposed concepts, schemes and any variation (s) / derivative (s) thereof may be implemented in, for and by other types of radio access technologies, networks and network topologies. Thus, the scope of the present disclosure is not limited to the examples described herein.BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The accompanying drawings are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of the present disclosure. The drawings illustrate implementations of the disclosure and, together with the description, serve to explain the principles of the disclosure. It is appreciable that the drawings are not necessarily in scale as some components may be shown to be out of proportion than the size in actual implementation in order to clearly illustrate the concept of the present disclosure.
[0014] FIG. 1 is a diagram depicting an example scenario 100 of a mobile communication network 100 in accordance with an implementation of the present disclosure.
[0015] FIG. 2 illustrates an exemplary flowchart for applicable functionality reporting and model activation in accordance with implementations of the present disclosure.
[0016] FIG. 3 is a diagram depicting an example scenario 300 of a timing diagram for model activation based on a model inference configuration in accordance with an implementation of the present disclosure.
[0017] FIG. 4 is a diagram depicting an example scenario 400 of a timing diagram for a model activation procedure involving an iterative configuration update in accordance with an implementation of the present disclosure.
[0018] FIG. 5 is a diagram depicting an example scenario 500 of a signaling design for a unified applicability report list in accordance with an implementation of the present disclosure.
[0019] FIG. 6 is a diagram depicting an example scenario 600 of a signaling design for a split applicability report list in accordance with an implementation of the present disclosure.
[0020] FIG. 7 is a diagram depicting an example scenario 700 of a process of a UE reporting an applicability report based on different states of an AI model in accordance with an implementation of the present disclosure.
[0021] FIG. 8 illustrates an example communication system 800 having an example communication apparatus 810 and an example network apparatus 820 in accordance with an implementation of the present disclosure.
[0022] FIG. 9 illustrates an example process 900 in accordance with an implementation of the present disclosure.
[0023] FIG. 10 illustrates an example process 1000 in accordance with an implementation of the present disclosure. DETAILED DESCRIPTION OF PREFERRED IMPLEMENTATIONS
[0024] Detailed embodiments and implementations of the claimed subject matters are disclosed herein. However, it shall be understood that the disclosed embodiments and implementations are merely illustrative of the claimed subject matters which may be embodied in various forms. The present disclosure may, however, be embodied in many different forms and should not be construed as limited to the exemplary embodiments and implementations set forth herein. Rather, these exemplary embodiments and implementations are provided so that description of the present disclosure is thorough and complete and will fully convey the scope of the present disclosure to those skilled in the art. In the description below, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the presented embodiments and implementations. Overview
[0025] Implementations in accordance with the present disclosure relate to various techniques, methods, schemes and / or solutions pertaining to methods and apparatus for model activation and management in mobile communications. According to the present disclosure, a number of possible solutions may be implemented separately or jointly. That is, although these possible solutions may be described below separately, two or more of these possible solutions may be implemented in one combination or another.
[0026] FIG. 1 is a diagram depicting an example scenario 100 of a mobile communication network 100 in accordance with an implementation of the present disclosure. As shown in FIG. 1, scenario 100 involves a UE 110 in wireless communication with a wireless communication network (e.g., an LTE network, a 5G / NR network, an IoT network, or a 6G network) consisting of an access network 120 and a core network 130. The UE 110 may be a smart phone, a wearable device, an IoT device, a tablet, etc. Alternatively, the UE 110 may be a notebook (NB) or personal computer (PC) inserted or installed with a data card which includes a modem and radio frequency (RF) transceiver (s) to provide the functionality of wireless communication. In one embodiment, the access network 120 is connected to the core network 130 by means of the NG interface, more specifically to a user plane function (UPF) by means of the NG user-plane part (NG-u) , and to an access and mobility management function (AMF) by means of the NG control-plane part (NG-c) . The access network 120 may include a base station (BS) 121, which may be connected to multiple UPFs / AMFs for the purpose of load sharing and redundancy. In addition, the core network may include other entities, such as a session management function (SMF) and a unified data management (UDM) , etc.
[0027] FIG. 2 illustrates an exemplary flowchart for applicable functionality reporting and model activation in accordance with implementations of the present disclosure. In a UE capability report stage S201, the BS 121 may transmit a UE Capability Enquiry message to initiate a procedure for the UE 110 to report its Artificial Intelligence / Machine Learning (AI / ML) supported functionalities. The UE 110 may report its AI / ML supported functionalities (e.g., measurement prediction) to the BS 121 via a UE Capability Information message or other dedicated signaling. When the BS 121 intends the UE 110 to use one or multiple AI / ML models (e.g., perform inference on) , the BS 121 may transmit the corresponding configuration to the UE 110. If the report from the UE 110 indicates that the UE 110 does not support AI / ML, the BS 121 may refrain from transmitting the corresponding configuration to the UE 110. In some embodiments, the stage of UE capability report S201 may be omitted. In such cases, the AI / ML supported functionalities of the UE 110 may instead be implicitly indicated to the BS 121 via the applicability report. For example, the successful transmission of the applicability report by the UE 110 in response to a model inference configuration may implicitly indicate to the BS 121 that the UE 110 supports AI / ML.
[0028] In the model inference configuration stage S202, the BS 121 may transmit a model inference configuration to the UE 110. In one embodiment, the model inference configuration may be indicated via a control message (e.g., a Radio Resource Control (RRC) Reconfiguration message) . After the UE 110 receives the model inference configuration, in one embodiment, the UE 110 may transmit an Applicability Report to the BS 121 via an RRC Reconfiguration Complete message. In another embodiment, the UE 110 may transmit the Applicability Report to the BS 121 via a UE assistance information (UAI) message.
[0029] In the model inference configuration updating stage S203, the BS 121 may transmit another model inference configuration to the UE 110 after the BS 121 receives the Applicability Report from the UE 110 in some embodiments. The BS 121 may adjust the model scheduling and inference strategy based on the Applicability Report from the UE 110 and refresh the model inference configuration. In one embodiment, the BS 121 may refrain from the model inference configuration updating stage, and the UE 110 may proceed to activate the model based on the initial configuration.
[0030] In the model activation stage S204, the BS 121 may manage the usage of models according to the information provided in the Applicability Report. In one embodiment, the Applicability Report may include at least one of an Applicability Report ID, an Applicability Status, a time to model availability, an Applicability Duration, or an Inapplicability Cause. The BS 121 may use the model indicated as applicable in the report and may suspend the use of the model indicated as inapplicable. In one embodiment, the BS 121 may start a prohibit timer of a corresponding length for the time to model availability of the model indicated as applicable, and may activate the model after the corresponding prohibit timer expires. Additionally, the UE 110 may indicate a model is inapplicable by setting the time to model availability to a predetermined value (e.g., infinity) or by including a specific Inapplicability Cause. In one embodiment, the UE 110 may transmit the Applicability Report to the BS 121 via a UE assistance information message at any time to update the model applicability after receiving the model inference configuration.
[0031] FIG. 3 is a diagram depicting an example scenario 300 of a timing diagram for model activation based on a model inference configuration in accordance with an implementation of the present disclosure. In scenario 300, the BS 121 may transmit an RRC Reconfiguration message to the UE 110, which may contain a model inference configuration. Upon receiving this configuration, the UE 110 may reply to the BS 121 with an RRC Reconfiguration Complete message. As shown in FIG. 3, this message may include an Applicability Report. The Applicability Report may specify a "Time to model availability, " which indicates the time duration for the model to be activated. In some embodiments, the UE 110 may activate the model at or before the end of the "Time to model availability" duration. Following the activation point, the UE 110 may proceed to perform model inference according to the configuration provided by the BS 121.
[0032] FIG. 4 is a diagram depicting an example scenario 400 of a timing diagram for a model activation procedure involving an iterative configuration update in accordance with an implementation of the present disclosure. In scenario 400, the BS 121 may initially transmit a model inference configuration to the UE 110, such as via an RRC Reconfiguration message. The UE 110 may respond by replying with its model availability to the BS 121. This reply may be transmitted in an RRC Reconfiguration Complete message that includes an Applicability Report. In some embodiments, the BS 121 may update the model configuration based on the report received from the UE 110. As shown in FIG. 4, the BS 121 may transmit a second RRC Reconfiguration message to provide the updated configuration. The UE 110 may then reply again with its updated model availability, for instance, by sending a second RRC Reconfiguration Complete message containing an updated Applicability Report. The UE 110 may be configured to activate the model at or before the end of a "Time to model availability" duration. This duration may indicate the time required for the model to be successfully activated. Following the activation, the UE 110 may perform model inference according to the finalized configuration provided by the BS 121.
[0033] FIG. 5 is a diagram depicting an example scenario 500 of a signaling design for a unified applicability report list in accordance with an implementation of the present disclosure. In scenario 500, the UE 110 may transmit an Applicability Report List to the BS 121. The Applicability Report List may include one or more report entries, such as Applicability Report 1 and Applicability Report 2. In one embodiment, each report entry may include a plurality of Information Elements (IEs) , including but not limited to: an Applicability Report ID to identify the specific model; an Applicability status (e.g., an enumerated value of "applicable" or "inapplicable" ) ; a Time to model availability (e.g., 0 millisecond (ms) to infinity) ; an Applicability duration; and an Inapplicability cause.
[0034] The signaling design in FIG. 5 provides the advantage of structural simplicity. By utilizing a consistent format for every report entry, regardless of its status, the BS 121 may implement a simplified parsing logic to process the list. However, this design may result in higher signaling overhead. For example, if a model is indicated as "inapplicable, " the fields for Time to model availability and Applicability duration may still be present in the message as padding or redundant data, thereby consuming unnecessary radio resources.
[0035] FIG. 6 is a diagram depicting an example scenario 600 of a signaling design for a split applicability report list in accordance with an implementation of the present disclosure. In scenario 600, the Applicability Report List is categorized into at least two sub-lists: an Applicable report list and an Inapplicable report list. The Applicable report list may include entries for models that are ready or becoming ready for use, including IEs such as Applicability Report ID, Time to model availability, and Applicability duration. Conversely, the Inapplicable report list may include entries for models that cannot be activated, including IEs such as Inapplicability Report ID and an Inapplicability cause.
[0036] The signaling design in FIG. 6 provides the advantage of improved signaling efficiency. By separating the reports, the UE 110 may refrain from transmitting irrelevant IEs (e.g., omitting the "duration" field for an inapplicable model) , which reduces the overall payload size of the RRC message. Furthermore, the "Applicability status" IE may be omitted as the status is implicitly indicated by the sub-list in which the model ID is located. A potential disadvantage of this design may be the increased complexity of the signaling transition and data structure, as the BS 121 may be configured to handle two different entry formats within the same report list.
[0037] In one embodiment, the UE 110 may utilize an explicit signaling method to indicate that a model is inapplicable. Specifically, the UE 110 may report an explicit enumerated value to the BS 121 within an applicability status field. For example, the enumerated value may be set to a first value (e.g., 0) to represent that a model is inapplicable, and to a second value (e.g., 1) to represent that the model is applicable. This explicit indication allows the BS 121 to immediately identify models that are not acquired or are unavailable for specific reasons. In another embodiment, the UE 110 may add a model ID in the inapplicable report list to indicate that the model is inapplicable.
[0038] Alternatively, the UE 110 may utilize an implicit signaling method to indicate that a model is inapplicable. In one embodiment, it is assumed that the Applicability Report may not include "Applicability status" IE, the UE 110 may set the Time to model availability to a predetermined value representing a lack of availability, such as "infinity" . When the BS 121 receives a report where the time duration for model activation is set to infinity, the BS 121 may determine that the corresponding model is currently inapplicable without requiring an explicit status bit.
[0039] Furthermore, the presence of an inapplicability cause IE may serve to further define the status of a model. In some embodiments, it is assumed that the Applicability Report includes an enumerated list of reasons (e.g., {cause1, cause2, ...} ) indicating why the model cannot be used, and that the Applicability Report does not include an “Applicability Status” IE. The mere presence of the inapplicability cause IE in a report for a specific model ID may be interpreted as an indication that the model is inapplicable. This detailed diagnostic information enables the BS 121 to better manage resource allocation and scheduling, or to determine whether to trigger a configuration update stage as described in S203.
[0040] FIG. 7 is a diagram depicting an example scenario 700 of a process of a UE reporting an applicability report based on different states of an AI model in accordance with an implementation of the present disclosure. In scenario 700, when a model is located at an Over-The-Top (OTT) server or is in the process of being downloaded in process 701, the UE may transmit an applicability report indicating that the model is "inapplicable" . Subsequently, when the model download is complete but the model is still undergoing model preparation and is stored in an outer memory (e.g., a non-volatile storage such as a built-in SSD or flash memory) in process 702, the UE may transmit an applicability report indicating either an "inapplicable" status or an "applicable" status with a time to model availability set to a long-time duration or infinity. Furthermore, once the model is loaded into an inner memory (e.g., volatile memory such as RAM) in process 703, the UE may send an applicability report indicating an "applicable" status with the time to model availability set to a short time duration. Finally, when the model reaches the model activation stage and is fully ready for inference in process 704, the UE may transmit an applicability report indicating an "applicable" status with the time to model availability set to 0 ms. Illustrative Implementations
[0041] FIG. 8 illustrates an example communication system 800 having an example communication apparatus 810 and an example network apparatus 820 in accordance with an implementation of the present disclosure. Each of communication apparatus 810 and network apparatus 820 may perform various functions to implement schemes, techniques, processes and methods described herein pertaining to model activation and management in mobile communications, including scenarios / schemes described above as well as process 900 and process 1000 described below.
[0042] Communication apparatus 810 may be a part of an electronic apparatus, which may be a UE such as a portable or mobile apparatus, a wearable apparatus, a wireless communication apparatus, or a computing apparatus. For instance, communication apparatus 810 may be implemented in a smartphone, a smartwatch, a personal digital assistant, a digital camera, or a computing equipment such as a tablet computer, a laptop computer, or a notebook computer. Communication apparatus 810 may also be a part of a machine type apparatus, which may be an IoT, NB-IoT, or IIoT apparatus such as an immobile or a stationary apparatus, a home apparatus, a wire communication apparatus or a computing apparatus. For instance, communication apparatus 810 may be implemented in a smart thermostat, a smart fridge, a smart door lock, a wireless speaker or a home control center. Alternatively, communication apparatus 810 may be implemented in the form of one or more integrated-circuit (IC) chips, such as, for example and without limitation, one or more single-core processors, one or more multi-core processors, one or more reduced-instruction set computing (RISC) processors, or one or more complex-instruction-set-computing (CISC) processors. Communication apparatus 810 may include at least some of those components shown in FIG. 8, such as a processor 812, for example. Communication apparatus 810 may further include one or more other components not pertinent to the proposed scheme of the present disclosure (e.g., internal power supply, display device and / or user interface device) , and, thus, such component (s) of communication apparatus 810 are neither shown in FIG. 8 nor described below in the interest of simplicity and brevity.
[0043] Network apparatus 820 may be a part of a network apparatus, which may be a network node such as a satellite, a base station, a small cell, a router, a gateway, or other network element. For instance, network apparatus 820 may be implemented in an eNodeB in an LTE network, in a gNB in a 5G / NR, IoT, NB-IoT or IIoT network or in a satellite or base station in a 6G network. Alternatively, network apparatus 820 may be implemented in the form of one or more IC chips such as, for example and without limitation, one or more single-core processors, one or more multi-core processors, or one or more RISC or CISC processors. Network apparatus 820 may include at least some of those components shown in FIG. 8 such as a processor 822, for example. Network apparatus 820 may further include one or more other components not pertinent to the proposed scheme of the present disclosure (e.g., internal power supply, display device and / or user interface device) , and, thus, such component (s) of network apparatus 820 are neither shown in FIG. 8 nor described below in the interest of simplicity and brevity.
[0044] In one aspect, each of processor 812 and processor 822 may be implemented in the form of one or more single-core processors, one or more multi-core processors, or one or more CISC processors. That is, even though a singular term “aprocessor” is used herein to refer to processor 812 and processor 822, each of processor 812 and processor 822 may include multiple processors in some implementations and a single processor in other implementations in accordance with the present disclosure. In another aspect, each of processor 812 and processor 822 may be implemented in the form of hardware (and, optionally, firmware) with electronic components including, for example and without limitation, one or more transistors, one or more diodes, one or more capacitors, one or more resistors, one or more inductors, one or more memristors and / or one or more varactors that are configured and arranged to achieve specific purposes in accordance with the present disclosure. In other words, in at least some implementations, each of processor 812 and processor 822 is a special-purpose machine specifically designed, arranged and configured to perform specific tasks including model activation and management in accordance with various implementations of the present disclosure.
[0045] In some implementations, communication apparatus 810 may also include a transceiver 816 coupled to processor 812 and capable of wirelessly transmitting and receiving data. In some implementations, communication apparatus 810 may further include a memory 814 coupled to processor 812 and capable of being accessed by processor 812 and storing data therein. In some implementations, network apparatus 820 may also include a transceiver 826 coupled to processor 822 and capable of wirelessly transmitting and receiving data. In some implementations, network apparatus 820 may further include a memory 824 coupled to processor 822 and capable of being accessed by processor 822 and storing data therein. Accordingly, communication apparatus 810 and network apparatus 820 may wirelessly communicate with each other via transceiver 816 and transceiver 826, respectively.
[0046] To aid better understanding, the following description of the operations, functionalities and capabilities of each of communication apparatus 810 and network apparatus 820 is provided in the context of a mobile communication environment in which communication apparatus 810 is implemented in or as a communication apparatus or a UE and network apparatus 820 is implemented in or as a network node of a communication network. Illustrative Processes
[0047] FIG. 9 illustrates an example process 900 in accordance with an implementation of the present disclosure. Process 900 may be an example implementation of above scenarios / schemes, whether partially or completely, with respect to model activation and management in mobile communications. Process 900 may represent an aspect of implementation of features of communication apparatus 810. Process 900 may include one or more operations, actions, or functions as illustrated by one or more of blocks 910, 920, and 930. Although illustrated as discrete blocks, various blocks of process 900 may be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Moreover, the blocks of process 900 may be executed in the order shown in FIG. 9 or, alternatively, in a different order. Process 900 may be implemented by communication apparatus 810 or any suitable UE or machine type devices. Solely for illustrative purposes and without limitation, process 900 is described below in the context of communication apparatus 810 as a UE. Process 900 may begin at block 910.
[0048] At block 910, process 900 may involve processor 812 of communication apparatus 810 receiving, via transceiver 816, a model inference configuration from a network node (e.g., network apparatus 820) . The model inference configuration may be related to inference of an artificial intelligence (AI) model. Process 900 may proceed from block 910 to block 920.
[0049] At block 920, process 900 may involve processor 812 transmitting, via transceiver 816, an applicability report to the network node (e.g., network apparatus 820) in response to the model inference configuration. The applicability report may indicate a time to model availability for activating the AI model. Process 900 may proceed from block 920 to block 930.
[0050] At block 930, process 900 may involve processor 812 activating the AI model before an end of the time to model availability.
[0051] In some implementations, the applicability report includes at least one of an applicability report identifier (ID) , an applicability status, and an applicability duration.
[0052] In some implementations, the applicability report includes an inapplicability cause indicating a reason why the AI model is not available.
[0053] In some implementations, Process 900 may further involve processor 812 determining a model applicability based on the model inference configuration and a status of the apparatus to generate the applicability report.
[0054] In some implementations, the applicability report may be transmitted via at least one of a Radio Resource Control (RRC) Reconfiguration Complete message and a user equipment (UE) Assistance Information (UAI) message.
[0055] In some implementations, Process 900 may further involve processor 812 setting the time to model availability to an infinity value to indicate an inapplicability of the AI model.
[0056] In some implementations, an applicability status of the applicability report includes an enumerated value. Process 900 may further involve processor 812 reporting an enumerated value in an applicability status of the applicability report to indicate applicability of the AI model.
[0057] In some implementations, the applicability duration may indicate a valid operational period of the AI model after the AI model is activated.
[0058] In some implementations, Process 900 may further involve processor 812 transmitting an AI supported functionality of the apparatus to the network node.
[0059] FIG. 10 illustrates an example process 1000 in accordance with an implementation of the present disclosure. Process 1000 may be an example implementation of above scenarios / schemes, whether partially or completely, with respect to model activation and management in mobile communications. Process 1000 may represent an aspect of implementation of features of network apparatus 820. Process 1000 may include one or more operations, actions, or functions as illustrated by one or more of blocks 1010, 1020 and 1030. Although illustrated as discrete blocks, various blocks of process 1000 may be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Moreover, the blocks of process 1000 may be executed in the order shown in FIG. 10 or, alternatively, in a different order. Process 1000 may be implemented by network apparatus 820 or any base stations or network nodes. Solely for illustrative purposes and without limitation, process 1000 is described below in the context of network apparatus 820. Process 1000 may begin at block 1010.
[0060] At block 1010, Process 1000 may involve processor 822 of network apparatus 820 transmitting, via transceiver 826, a model inference configuration to an apparatus (e.g., communication apparatus 810) . The model inference configuration may be related to inference of an artificial intelligence (AI) model. Process 1000 may proceed from block 1010 to block 1020.
[0061] At block 1020, Process 1000 may involve processor 822 of network apparatus 820 receiving, via transceiver 826, an applicability report from the apparatus (e.g., communication apparatus 810) . The applicability report may indicate a time to model availability for activating the AI model. Process 1000 may proceed from block 1020 to block 1030.
[0062] At block 1030, Process 1000 may involve processor 822 of network apparatus 820 receiving, by the processor, data generated by the AI model from the apparatus (e.g., communication apparatus 810) after an end of the time to model availability.
[0063] In some implementations, Process 1000 may further involve processor 822 updating the model inference configuration based on the applicability report. And Process 1000 may further involve processor 822 transmitting, via transceiver 826, the updated model inference configuration to the apparatus (e.g., communication apparatus 810) .
[0064] In some implementations, the applicability report includes an inapplicability cause in an event that the apparatus indicates that the AI model is unavailable.
[0065] In some implementations, the network apparatus 820 may identify that the AI model is inapplicable at the apparatus (e.g., communication apparatus 810) when the time to model availability in the applicability report is set to an infinity value.
[0066] In some implementations, the model inference configuration may be transmitted via an RRC Reconfiguration message. Additional Notes
[0067] The herein-described subject matter sometimes illustrates different components contained within, or connected with, different other components. It is to be understood that such depicted architectures are merely examples, and that in fact many other architectures can be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively "associated" such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality can be seen as "associated with" each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated can also be viewed as being "operably connected" , or "operably coupled" , to each other to achieve the desired functionality, and any two components capable of being so associated can also be viewed as being "operably couplable" , to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and / or physically interacting components and / or wirelessly interactable and / or wirelessly interacting components and / or logically interacting and / or logically interactable components.
[0068] Further, with respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.
[0069] Moreover, it will be understood by those skilled in the art that, in general, terms used herein, and especially in the appended claims, e.g., bodies of the appended claims, are generally intended as “open” terms, e.g., the term “including” should be interpreted as “including but not limited to, ” the term “having” should be interpreted as “having at least, ” the term “includes” should be interpreted as “includes but is not limited to, ” etc. It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim containing such introduced claim recitation to implementations containing only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an, " e.g., “a” and / or “an” should be interpreted to mean “at least one” or “one or more; ” the same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number, e.g., the bare recitation of "two recitations, " without other modifiers, means at least two recitations, or two or more recitations. Furthermore, in those instances where a convention analogous to “at least one of A, B, and C, etc. ” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention, e.g., “asystem having at least one of A, B, and C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc. In those instances where a convention analogous to “at least one of A, B, or C, etc. ” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention, e.g., “asystem having at least one of A, B, or C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc. It will be further understood by those within the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase “A or B” will be understood to include the possibilities of “A” or “B” or “A and B. ”
[0070] From the foregoing, it will be appreciated that various implementations of the present disclosure have been described herein for purposes of illustration, and that various modifications may be made without departing from the scope and spirit of the present disclosure. Accordingly, the various implementations disclosed herein are not intended to be limiting, with the true scope and spirit being indicated by the following claims.
Claims
1.A method, comprising:receiving, by a processor of an apparatus, a model inference configuration from a network node, wherein the model inference configuration is related to inference of an artificial intelligence (AI) model;transmitting, by the processor, an applicability report to the network node in response to the model inference configuration, wherein the applicability report indicates a time to model availability for activating the AI model; andactivating, by the processor, the AI model before an end of the time to model availability.2.The method of Claim 1, wherein the applicability report comprises at least one of:an applicability report identifier (ID) ;an applicability status; andan applicability duration.3.The method of Claim 1, wherein the applicability report comprises an inapplicability cause indicating a reason why the AI model is not available.4.The method of Claim 1, further comprising:determining, by the processor, a model applicability based on the model inference configuration and a status of the apparatus to generate the applicability report.5.The method of Claim 1, wherein the applicability report is transmitted via at least one of a Radio Resource Control (RRC) Reconfiguration Complete message and a user equipment (UE) Assistance Information (UAI) message.6.The method of Claim 1, further comprising:setting, by the processor, the time to model availability to an infinity value to indicate an inapplicability of the AI model.7.The method of Claim 1, wherein the transmitting of the applicability report to the network node comprises:reporting, by the processor, an enumerated value in an applicability status of the applicability report to indicate applicability of the AI model.8.The method of Claim 2, wherein the applicability duration indicates a valid operational period of the AI model after the AI model is activated.9.The method of Claim 1, further comprising:transmitting, by the processor, an AI supported functionality of the apparatus to the network node.10.A method, comprising:transmitting, by a processor of a network node, a model inference configuration to an apparatus, wherein the model inference configuration is related to inference of an artificial intelligence (AI) model;receiving, by the processor, an applicability report from the apparatus, wherein the applicability report indicates a time to model availability for activating the AI model; andreceiving, by the processor, data generated by the AI model from the apparatus after an end of the time to model availability.11.The method of Claim 10, further comprising:updating, by the processor, the model inference configuration based on the applicability report; andtransmitting, by the processor, the updated model inference configuration to the apparatus.12.The method of Claim 10, wherein the applicability report comprises an inapplicability cause in an event that the apparatus indicates that the AI model is unavailable.13.The method of Claim 10, wherein the network node identifies that the AI model is inapplicable at the apparatus when the time to model availability in the applicability report is set to an infinity value.14.The method of Claim 10, wherein the model inference configuration is transmitted via an RRC Reconfiguration message.15.An apparatus, comprising:a transceiver which, during operation, communicates wirelessly; anda processor communicatively coupled to the transceiver such that, during operation, the processor performs operations comprising:receiving, via the transceiver, a model inference configuration from a network node, wherein the model inference configuration is related to inference of an artificial intelligence (AI) model;transmitting, via the transceiver, an applicability report to the network node in response to the model inference configuration, wherein the applicability report indicates a time to model availability for activating the AI model; andactivating the AI model before an end of the time to model availability.16.The apparatus of Claim 15, wherein the applicability report further comprises an applicability status and an inapplicability cause, and the processor is further configured to perform operations comprising:setting the applicability status to inapplicable in an event that the AI model is not available.17.The apparatus of Claim 15, wherein the processor is further configured to perform operations comprising:setting the time to model availability to an infinity value to indicate an inapplicability of the AI model.18.The apparatus of Claim 15, wherein the processor is further configured to perform operations comprising:transmitting, via the transceiver, the applicability report via at least one of a Radio Resource Control (RRC) Reconfiguration Complete message and a user equipment (UE) Assistance Information (UAI) message.19.The apparatus of Claim 15, wherein the processor is further configured to perform operations comprising:transmitting, via the transceiver, supported AI functionalities to the network before receiving the model inference configuration.20.The apparatus of Claim 15, wherein the processor is further configured to perform operations comprising:determining a model applicability based on the model inference configuration and a status of the apparatus to generate the applicability report.
