WO2025030519A1

WO2025030519A1 - Devices and methods of communication

Info

Publication number: WO2025030519A1
Application number: PCT/CN2023/112330
Authority: WO
Inventors: Rao SHI; Zhen He; Peng Guan; Gang Wang
Original assignee: NEC Corp
Current assignee: NEC Corp
Priority date: 2023-08-10
Filing date: 2023-08-10
Publication date: 2025-02-13
Anticipated expiration: 2026-02-10

Abstract

Embodiments of the present disclosure relate to devices and methods of communication. In one aspect, upon transmission of a measurement report comprising predicted measurement results for a set of cells based on an AI model, a terminal device determines whether the measurement report is invalid. If the measurement report is invalid, the terminal device transmits information indicating invalidity of the measurement report. In this way, by evaluating validity of an AI-based measurement report, reliability of the AI-based measurement report may be improved.

Description

DEVICES AND METHODS OF COMMUNICATION

TECHNICAL FIELD

Embodiments of the present disclosure generally relate to the field of telecommunication, and in particular, to devices and methods of communication for an artificial intelligence (AI) -based measurement report.

BACKGROUND

It has been proposed to introduce AI for mobility enhancement to improve handover performance. One use case of AI mobility is that user equipment (UE) may use measurement results of several cells (which is obtained from a real measurement performed by the UE) to predict measurement results of more cells and use these predicted measurement results to initiate a measurement report procedure (i.e., an AI-based measurement report) . Such use case may decrease massive measurements performed by the UE.

SUMMARY

In general, embodiments of the present disclosure provide methods, devices and computer storage media of communication for an AI-based measurement report.

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: transmit, to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; and in accordance with a determination that the measurement report is invalid, transmit, to the network device, information indicating invalidity of the measurement report.

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: transmit, to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; increment number of transmitted measurement reports; in accordance with a determination that the number of transmitted measurement reports is less than a configured number of measurement reports, determine real measurement results for the set of cells by performing measurements on the set of cells; and transmit, to the network device, a further measurement report comprising the real measurement results.

In a third aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: determine that a measurement report comprising predicted measurement results for a set of cells is to be transmitted, the predicted measurement results being based on an AI model; determine real measurement results for the set of cells by performing measurements on the set of cells; and in accordance with a determination that a difference between the predicted measurement results and the real measurement results is below a threshold, transmit the measurement report to a network device.

In a fourth 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 configuration comprising a first inference period of an AI model; determine a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements; and predict results of the cell measurements via the AI model based on the second inference period.

In a fifth aspect, there is provided a method of communication. The method comprises: transmitting, at a terminal device and to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; and in accordance with a determination that the measurement report is invalid, transmitting, to the network device, information indicating invalidity of the measurement report.

In a sixth aspect, there is provided a method of communication. The method comprises: transmitting, at a terminal device and to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; incrementing number of transmitted measurement reports; in accordance with a determination that the number of transmitted measurement reports is less than a configured number of measurement reports, determining real measurement results for the set of cells by performing measurements on the set of cells; and transmitting, to the network device, a further measurement report comprising the real measurement results.

In a seventh aspect, there is provided a method of communication. The method comprises: determining, at a terminal device, that a measurement report comprising predicted measurement results for a set of cells is to be transmitted, the predicted measurement results being based on an AI model; determining real measurement results for the set of cells by performing measurements on the set of cells; and in accordance with a determination that a difference between the predicted measurement results and the real measurement results is below a threshold, transmitting the measurement report to a network device..

In an eighth aspect, there is provided a method of communication. The method comprises: receiving, at a terminal device and from a network device, a configuration comprising a first inference period of an AI model; determining a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements; and predicting results of the cell measurements via the AI model based on the second inference period.

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.

Other features of the present disclosure will become easily comprehensible through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

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:

FIG. 1 illustrates an example communication network in which some embodiments of the present disclosure can be implemented;

FIG. 2 illustrates a schematic diagram of an AI model inference and monitoring in which some embodiments of the present disclosure can be implemented;

FIG. 3 illustrates a schematic diagram illustrating a process of communication for an AI-based measurement report according to embodiments of the present disclosure;

FIG. 4A illustrates a schematic diagram illustrating an example measurement report procedure according to embodiments of the present disclosure;

FIG. 4B illustrates a schematic diagram illustrating another example measurement report procedure according to embodiments of the present disclosure;

FIG. 4C illustrates a schematic diagram illustrating an example evaluation from AI model monitoring according to embodiments of the present disclosure;

FIG. 4D illustrates a schematic diagram illustrating another example measurement report procedure according to embodiments of the present disclosure;

FIG. 5 illustrates a schematic diagram illustrating another process of communication for an AI-based measurement report according to embodiments of the present disclosure;

FIG. 6 illustrates a schematic diagram illustrating an example measurement report procedure according to embodiments of the present disclosure;

FIG. 7 illustrates a schematic diagram illustrating another process of communication for an AI-based measurement report according to embodiments of the present disclosure;

FIG. 8 illustrates a schematic diagram illustrating a process of communication for AI model inference according to embodiments of the present disclosure;

FIG. 9 illustrates an example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;

FIG. 10 illustrates another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;

FIG. 11 illustrates another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;

FIG. 12 illustrates another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure; and

FIG. 13 is a simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure.

Throughout the drawings, the same or similar reference numerals represent the same or similar element.

DETAILED DESCRIPTION

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.

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.

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) , 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.

The term “network device” may refer to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of an access network device include, but not limited to, a satellite, a unmanned aerial systems (UAS) platform, 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) , and the like.

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.

The terminal 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 connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.

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.

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, first information may be transmitted to the terminal device from the first network device and second information 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.

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. Other definitions, explicit and implicit, may be included below.

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.

In the context of the present disclosure, the term “AI” may be interchangeably used with “machine learning (ML) ” or “AI/ML” . The term “AI model” may be interchangeably used with “ML model” or “AI/ML model” .

Embodiments of the present disclosure provide solutions for an AI-based measurement report. In one solution, upon transmission of a measurement report (i.e., AI-based measurement report) comprising predicted measurement results for a set of cells based on an AI model, a terminal device determines whether the measurement report is invalid. If the measurement report is invalid, the terminal device transmits information indicating invalidity of the measurement report. In this way, by evaluating validity of a measurement report after transmitting the measurement report, reliability of the AI-based measurement report may be improved.

In another solution, upon transmission of a measurement report (i.e., AI-based measurement report) comprising predicted measurement results for a set of cells based on an AI model, a terminal device increments number of transmitted measurement reports. If the number of transmitted measurement reports is less than a configured number of measurement reports, the terminal device determines real measurement results for the set of cells by performing measurements on the set of cells, and transmits a further measurement report comprising the real measurement results. In this way, by transmitting both predicted measurement results and real measurement results in multiple transmissions configured for a measurement report, reliability of the AI-based measurement report may be improved.

In another solution, upon transmission of a measurement report (i.e., AI-based measurement report) comprising predicted measurement results for a set of cells based on an AI model, a terminal device determines real measurement results for the set of cells by performing measurements on the set of cells. If a difference between the predicted measurement results and the real measurement results is below a threshold, the terminal device transmits the measurement report to a network device. In this way, by evaluating validity of a measurement report before transmitting the measurement report, reliability of the AI-based measurement report may be improved, and signaling overhead for transmitting the measurement report may be saved.

In another solution, upon reception of a configuration comprising a first inference period of an AI model, a terminal device determines a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements, and predicts results of the cell measurements via the AI model based on the second inference period. In this way, a reasonable inference period may be determined and unnecessary AI model inference may be reduced.

Principles and implementations of the present disclosure will be described in detail below with reference to the figures.

EXAMPLE OF COMMUNICATION NETWORK

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 network devices 120, 121, 122, 123 and 124. In this example, the terminal device 110 is located in a serving cell provided by the network device 120 and is served by the network device 120.

As shown in FIG. 1, the network device 121 may provide a cell (denoted as Cell 1) , the network device 122 may provide a cell (denoted as Cell 2) , the network device 123 may provide a cell (denoted as Cell 3) , the network device 124 may provide a cell (denoted as Cell 4) .

It is to be understood that the number of devices or cells 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 and/or cells adapted for implementing implementations of the present disclosure.

As shown in FIG. 1, the terminal device 110 and any of the network devices 120, 121, 122, 123 and 124 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.

In some scenarios, the network device 120 may transmit a configuration of cell measurements to the terminal device 110. In some embodiments, the configuration may comprise a measurement identity (ID) associated with a measurement object and a reporting configuration. The measurement object may be associated with a set of cells. Then the terminal device 110 may perform measurements on the set of cells and report results of the measurements based on the reporting configuration.

In some scenarios, the terminal device 110 may perform measurements (i.e., real measurements) on the serving cell of the network device 120, the Cell 1 of the network device 121, and the Cell 3 of the network device 123. The real measurements may be intra-frequency measurements or inter-frequency measurements. Measurement results of the real measurements may be used to predict measurement results of the Cell 2 of the network device 122 and the Cell 4 of the network device 124. It is assumed that predicted measurement results of the Cell 2 or Cell 4 fulfill a condition (e.g., Event A3) for initiating a measurement report procedure. In this case, a measurement report procedure may be triggered. The triggered measurement report procedure may be called as an AI-based measurement report.

Network may trigger a handover based on the AI-based measurement report. However, AI prediction may not be always accurate or correct. If the predicted measurement results are incorrect, an incorrect handover may be caused.

FIG. 2 illustrates a schematic diagram 200 of an AI model inference and monitoring in which some embodiments of the present disclosure can be implemented. As shown in FIG. 2, model training may be performed based on training data. An AI model may be deployed or updated by the model training. With an input data set as an input of the AI model, an output data set may be obtained by model inference. This is an AI model inference procedure. An inference period may refer to a period of time from input of the input data set to output of the output data set.

With reference to FIG. 2, a model monitoring may be performed to monitor performance of the model inference of the AI model. In other words, the model monitoring may be used to determine whether AI model is valid. The model monitoring may be classified into three types: comparison between inference results and ground-truth results; evaluation for system performance (e.g., throughout, block error rate (BLER) , reference signal receiving power (RSRP) , positive acknowledgement (ACK) /NACK) ; distribution detection for the input or output data set.

A terminal device may perform real measurements on several cells based on a measurement period, and predict measurement results of more cells based on an inference period of an AI model. If the measurement period and the inference period are not aligned, unnecessary inference may happen. For example, the terminal device may predict measurement results always based on the same input data set due to the measurement period is much larger.

In view of this, embodiments of the present disclosure provide solutions for an AI-based measurement report so as to optimize the AI-based measurement report. More details of the solutions will be described with reference to FIGs. 3 to 8 below.

EXAMPLE IMPLEMENTATION OF AI-BASED MEASUREMENT REPORT

FIG. 3 illustrates a schematic diagram illustrating a process 300 of communication for an AI-based measurement report according to embodiments of the present disclosure. For the purpose of discussion, the process 300 will be described with reference to FIG. 1. The process 300 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. 3 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. It is assumed that model training and deployment of an AI model is finished, and the AI model is deployed at the terminal device 110 or the network device 120.

As shown in FIG. 3, the terminal device 110 transmits 310, to the network device 120, a measurement report comprising predicted measurement results for a set of cells (i.e., an AI-based measurement report) . The predicted measurement results are obtained based on an AI model. In some embodiments, the terminal device 110 may obtain real measurement results for a further set of cells by performing real measurements on the further set of cells. The real measurement results for the further set of cells may be used as an input of the AI model. Based on an output of the AI model, the terminal device 110 may obtain the predicted measurement results for the set of cells. When the predicted measurement results for one or more of the set of cells fulfill a condition (e.g., Event A3) for initiating the measurement report, the terminal device 110 may transmit the measurement report.

Continuing to refer to FIG. 3, upon transmission of the measurement report, the terminal device 110 determines 320 whether the measurement report is invalid. In some embodiments, the terminal device 110 may determine real measurement results for the set of cells by performing measurements on the set of cells. If a difference between the predicted measurement results and the real measurement results is above (i.e., larger than or equal to) a threshold, the terminal device 110 may determine that the measurement report is invalid. In some embodiments, the threshold may be predefined. In some embodiments, the threshold may be configured.

In some embodiments, if the terminal device 110 receives, from the network device 120, a request for performing measurements on the set of cells, the terminal device 110 may determine that the transmitted measurement report is invalid.

In some embodiments, the terminal device 110 may perform a monitoring on the AI model. The monitoring means determining whether the AI model is valid. In some embodiments, the terminal device 110 may compare the AI output with the ground truth value. If a difference between the AI output and the ground truth value is below (i.e., smaller than or equal to) a threshold difference, the terminal device 110 may determine that the AI model is valid. If the difference between the AI output and the ground truth value is above the threshold difference, the terminal device 110 may determine that the AI model is invalid.

In some embodiments, the terminal device 110 may consider system performance, e.g., a handover failure rate, a throughput, or a channel state (e.g., reference signal receiving power (RSRP) ) . If the system performance is better than threshold performance, the terminal device 110 may determine that the AI model is valid. If the system performance is worse than the threshold performance, the terminal device 110 may determine that the AI model is invalid.

In some embodiments, the terminal device 110 may consider a distribution of AI input data set or AI output data set. If a change of the distribution of AI input data set or AI output data set is smaller than or equal to threshold change, the terminal device 110 may determine that the AI model is valid. If the change of the distribution of AI input data set or AI output data set is larger than or equal to the threshold change, the terminal device 110 may determine that the AI model is invalid.

It is to be understood that the monitoring of the AI model may be carried out in any suitable ways, and the present disclosure does not limit this aspect. If the AI model is invalid, the terminal device 110 may determine that the transmitted measurement report is invalid.

Continuing to refer to FIG. 3, upon determination that the transmitted measurement report is invalid, the terminal device 110 transmits 330 information indicating invalidity of the measurement report. In some embodiments, the terminal device 110 may transmit the information via uplink control information (UCI) . In some embodiments, the terminal device 110 may transmit the information via a medium access control (MAC) control element (CE) . In some embodiments, the terminal device 110 may transmit the information via a radio resource control (RRC) signaling.

In some embodiments, the terminal device 110 may transmit an indication of the invalidity of the measurement report. For example, the indication may indicate that the AI-based measurement report is not correct or accurate. In some embodiments, the terminal device 110 may transmit (i.e., re-initiate) a further measurement report comprising the real measurement results for the set of cells. In some embodiments, the terminal device 110 may transmit an indication of the invalidity of the AI model. In this way, the invalidity of the transmitted measurement report may be indicated to the network.

In some embodiments, based on the measurement report, the network device 120 may transmit, to the terminal device 110, a command for a handover to one of the set of cells. For example, the network device 120 may transmit an RRC message (e.g., RRC reconfiguration with synchronization) to the terminal device 110. In some embodiments where the RRC message has been received, if the measurement report is invalid, the terminal device 110 may transmit an indication for rejecting the handover.

In this way, the invalidity of the transmitted measurement report may be indicated to the network. For illustration, some example embodiments will be described in connection with FIGs. 4A to 4D.

FIG. 4A illustrates a schematic diagram illustrating an example measurement report procedure 400A according to embodiments of the present disclosure. For the purpose of discussion, the procedure 400A will be described with reference to FIG. 1.

As shown in FIG. 4A, the terminal device 110 may transmit 410, to the network device 120, a measurement report comprising predicted measurement results for a set of cells (i.e., an AI-based measurement report) . The predicted measurement results are obtained based on an AI model.

Upon transmission of the measurement report, the terminal device 110 may perform 411 real measurements on the set of cells to determine real measurement results for the set of cells. In some embodiments, once the AI-based measurement report is triggered or transmitted for a measurement ID, the terminal device 110 may perform the real measurements according to AI predicted measurement object or triggered cell for this measurement ID.

It is to be noted that even though some cells are predicted by AI (which means no need to perform measurements) , a measurement object corresponding to these cells may still be associated with a measurement ID and a reporting configuration. For example, the terminal device 110 may need to report a measurement ID for the predicted cell, an evaluation event related to the measurement report, etc..

Continuing to refer to FIG. 4A, the terminal device 110 may compare 412 the predicted measurement results and the real measurement results. If a difference between the predicted measurement results and the real measurement results is above a threshold, the terminal device 110 transmit 413, to the network device 120, an indication of invalidity of the measurement report. Alternatively or additionally, the terminal device 110 may transmit 414 a further measurement report comprising the real measurement results for the set of cells.

If the difference between the predicted measurement results and the real measurement results is below the threshold, the terminal device 110 may not take any subsequent actions. That means the AI-based measurement report is correct.

For illustration, an example procedure may be described as below.

Upon AI-based measurement report is initiated (e.g., some AI predicted cell measurement result as well as the corresponding measId are included in this measurement report) , the UE shall:

1> for each measId included in the measurement report or VarMeasReportList (based on AI prediction) :

2> if the rsType within reportConfig that is associated with the measId is set to ssb:

3> derive cell measurement results (for the predicted cell) based on SS/PBCH block for the trigger quantity and each measurement quantity indicated in reportQuantityCell (e.g., RSRP/RSRQ/SINR) using parameters from the associated measObject;

2> if the rsType within reportConfig that is associated with the measId is set to csi-rs:

3> derive cell measurement results (for the predicted cell) based on CSI-RS for the trigger quantity and each measurement quantity indicated in reportQuantityCell (e.g., RSRP/RSRQ/SINR) using parameters from the associated measObject;

Once the UE derives the real measurement result for the predicted cell /measurement object, the UE shall:

1> if the difference between the real measurement result (i.e., RSRP/RSRQ/SINR of the predicted cell) and the predicted measurement result is greater than AI_real_comparison:

(option 1)

2> (immediately) send an indication (via UCI /MAC CE /RRC) to network indicating that the predicted measurement result is not correct/accurate;

(option 2)

2> initiate the measurement reporting procedure;

2> include the (real) measurement result of the AI predicted triggered cell /measurement object into the measurement report for transmission.

In this example, it is up to network implementation after the reception of the indication or the further measurement report, for example, the handover procedure which is ongoing during NG-RAN nodes could be cancelled based on this information. In this example, measId denotes a measurement ID, VarMeasReportList denotes a UE variable storing information about measurements for which triggering conditions have been met, rsType denotes a type of a reference signal for measurements, reportConfig denotes a reporting configuration, reportQuantityCell denotes cell quantity to be reported, measObject denotes a measurement object, and AI_real_comparison denotes a threshold.

Continuing to refer to FIG. 4A, in some embodiments, based on the measurement report, the network device 120 may transmit 415, to the terminal device 110, a command for a handover to one of the set of cells. For example, the network device 120 may transmit an RRC message (e.g., RRC reconfiguration with synchronization) to the terminal device 110. In this case, if the difference between the predicted measurement results and the real measurement results is above the threshold, the terminal device 110 may transmit 416 an indication for rejecting the handover (i.e., rejecting the RRC message) .

In some embodiments, once AI-based measurement report is triggered or transmitted for a measurement ID, and the terminal device 110 receives RRC reconfiguration with synchronization (i.e., handover command) , the terminal device 110 may reject or ignore this handover based on results of the real measurements performed after the AI-based measurement report is triggered or transmitted.

For illustration, an example procedure may be described as below.

Upon AI-based measurement report is initiated (e.g., some AI predicted cell measurement result as well as the corresponding measId are included in this MR) , the UE shall:

1> if RRCReconfiguration (with synchronization) is received:

2> if the difference between the real measurement result (i.e., RSRP/RSRQ/SINR of the predicted cell) and the predicted measurement result is greater than AI_real_comparison:

3> the UE may reject /ignore the received RRCReconfiguration, e.g., by responding RejectHandover (carrying cause –predicted result is not correct) to network, or not apply any configuration from this message or do not perform handover.

In this example, measId denotes a measurement ID, VarMeasReportList denotes a UE variable storing information about measurements for which triggering conditions have been met, rsType denotes a type of a reference signal for measurements, reportConfig denotes a reporting configuration, reportQuantityCell denotes cell quantity to be reported, measObject denotes a measurement object, and AI_real_comparison denotes a threshold.

FIG. 4B illustrates a schematic diagram illustrating another example measurement report procedure 400B according to embodiments of the present disclosure. For the purpose of discussion, the procedure 400B will be described with reference to FIG. 1.

As shown in FIG. 4B, the terminal device 110 may transmit 420, to the network device 120, a measurement report comprising predicted measurement results for a set of cells (i.e., an AI-based measurement report) . The predicted measurement results are obtained based on an AI model.

Upon transmission of the measurement report, the terminal device 110 may perform 421 a monitoring on the AI model to determine whether the AI model is valid. In some embodiments, once AI-based measurement report is triggered or transmitted for a measurement ID, the terminal device 110 may start to perform the monitoring on the AI model to determine whether the AI model is still valid. The details of the monitoring are similar as that described in FIG. 3 and thus are omitted here for conciseness.

In some embodiments, a monitoring period of the monitoring may be a multiple of an inference period of the AI model. For example, the monitoring period and the inference period may satisfy equation (1) below.
T_monitoring = N × T_inference (1)

where T_monitoring denotes a monitoring period of an AI model monitoring, T_inference denotes an inference period of an AI model inference, and N denotes a positive integer.

FIG. 4C illustrates a schematic diagram 400C illustrating an example evaluation from AI model monitoring according to embodiments of the present disclosure. As shown in FIG. 4C, after an AI-based measurement report (MR) transmission, an AI model monitoring may be started while an AI inference is continued. Reasonably, a period of the AI model monitoring may be multiple of a period of the AI inference.

Returning to with reference to FIG. 4B, if the AI model is invalid, the terminal device 110 may transmit 422 an indication of invalidity of the AI model to the network device 120. The indication may be transmitted in any suitable ways such as UCI, MAC CE or RRC signaling.

FIG. 4D illustrates a schematic diagram illustrating another example measurement report procedure 400D according to embodiments of the present disclosure. For the purpose of discussion, the procedure 400D will be described with reference to FIG. 1.

As shown in FIG. 4D, the terminal device 110 may transmit 430, to the network device 120, a measurement report comprising predicted measurement results for a set of cells (i.e., an AI-based measurement report) . The predicted measurement results are obtained based on an AI model.

Upon reception of the measurement report, the network device 120 may transmit 431, to the terminal device 110, a request for performing measurements on the set of cells. In some embodiments, upon reception of an AI-based measurement report for a measurement ID from the terminal device 110, the network device 120 may request the terminal device 110 to perform real measurements for the AI predicted triggered cell or measurement object for the measurement ID. In other words, the network device 120 may consider that the measurement report is invalid and request the terminal device 110 to perform the real measurements.

In some embodiments, the request may indicate at least one of the following: a measurement identity for the measurements; the set of cells; a type of a reference signal for the measurements; a time interval between two measurement reports; configured number of measurement reports; cell quantity to be reported; or a reporting configuration for the measurement report is reused for the further measurement report. In some embodiments, the request may be transmitted via downlink control information (DCI) . In some embodiments, the request may be transmitted via a MAC CE. In some embodiments, the request may be transmitted via an RRC signaling.

For illustration, an example message of the request may be described as below.

In this example, IE “measId” indicates a measurement ID. IE “cellsTriggeredList” indicates a set of cells to be really measured. IE “reportInterval” indicates a time interval between two measurement reports in case multiple transmissions are configured for measurement reporting. IE “reportAmount” indicates configured number of measurement reports. IE “reportQuantityCell” indicates cell quantity to be reported. IE “useReportConfig” indicates that a reporting configuration for the AI-based measurement report is reused for a reporting of real measurements.

Continuing to refer to FIG. 4D, based on the request, the terminal device 110 may perform 432 real measurements on the set of cells to determine the real measurement results for the set of cells. Then the terminal device 110 may transmit (i.e., re-initiate) 433 a further measurement report comprising the real measurement results for the set of cells. For example, based on related configurations in the request, the terminal device 110 may perform the real measurements for the AI predicted triggered cell or measurement object for the corresponding measurement ID which triggers the AI based measurement report, and initiate or re-initiate a measurement report transmission.

For illustration, an example procedure may be described as below.

1> if performRealMeas is received (after the transmission of MR) :

2> for each measId /CellstriggeredList included in the performRealMeas:

3> if the rsType within performRealMeas that is associated with the measId is set to ssb:

4> derive cell measurement results (for the predicted cell) based on SS/PBCH block for the trigger quantity and each measurement quantity indicated in reportQuantityCell (e.g., RSRP/RSRQ/SINR) using parameters from the associated measObject;

3> if the rsType within performRealMeas that is associated with the measId is set to csi-rs:

4> derive cell measurement results (for the predicted cell) based on CSI-RS for the trigger quantity and each measurement quantity indicated in reportQuantityCell (e.g., RSRP/RSRQ/SINR) using parameters from the associated measObject;

2> initiate the measurement reporting procedure for this measId;

2> increment the numberOfReportsSent as defined within the performRealMeas or reportConfig (if useReportConfig is set to true) for this measId by 1;

2> stop the periodical reporting timer, if running;

2> if the numberOfReportsSent as defined within the performRealMeas or reportConfig (if useReportConfig is set to true) for this measId is less than the reportAmount as defined within the corresponding performRealMeas or reportConfig (if useReportConfig is set to true) for this measId:

3> start the periodical reporting timer with the value of reportInterval as defined within the corresponding reportConfig for this measId;

1> upon expiry of the periodical reporting timer for this measId:

2> (re) initiate the measurement reporting procedure (as above) for this measId.

In this example, performRealMeas denotes a request for performing real measurements, measId denotes a measurement ID, rsType denotes a type of a reference signal for measurements, reportConfig denotes a reporting configuration, reportQuantityCell denotes cell quantity to be reported, measObject denotes a measurement object, numberOfReportsSent denotes number of transmitted measurement reports, reportInterval denotes a time interval between two measurement reports, reportAmount denotes configured number of measurement reports, and useReportConfig denotes an indication of reusing a reporting configuration for an AI-based measurement report.

So far, a solution of evaluating validity of an AI-based measurement report after transmission of the measurement report is described. With the solution, reliability of the AI-based measurement report may be improved.

FIG. 5 illustrates a schematic diagram illustrating another process 500 of communication for an AI-based measurement report according to embodiments of the present disclosure. For the purpose of discussion, the process 500 will be described with reference to FIG. 1. The process 500 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. 5 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. It is assumed that model training and deployment of an AI model is finished, and the AI model is deployed at the terminal device 110 or the network device 120.

As shown in FIG. 5, the network device 120 may transmit 505, to the terminal device 110, a configuration indicating multiple transmissions of a measurement report (e.g., an event-triggered periodical measurement reporting) . In some embodiments, the configuration may indicate a configured number of measurement reports (denoted as reportAmount) . In some embodiments, the configuration may indicate a time interval between two measurement reports (denoted as reportInterval) . It is to be understood that the configuration may also comprise any other suitable information such as a measurement ID, a cell list, a type of a reference signal for measurements, cell quantity to be reported, etc.. A measurement ID may be associated with a measurement object and a reporting configuration.

Based on the configuration, for one triggered cell, once a criterion is fulfilled for measurement report transmission, the terminal device 110 may transmit a measurement report for several times as indicated by reportAmount with a period as indicated by reportInterval.

Continuing to refer to FIG. 5, the terminal device 110 may transmit 510, to the network device 120, a measurement report comprising predicted measurement results for a set of cells (i.e., an AI-based measurement report) . The predicted measurement results are obtained based on an AI model.

As shown in FIG. 5, upon transmission of the measurement report, the terminal device 110 may increment 520 number of transmitted measurement reports. If the number of transmitted measurement reports is less than the configured number of measurement reports, the terminal device 110 may determine 530 real measurement results for the set of cells by performing measurements on the set of cells. Then the terminal device 110 may transmit 540, to the network device, a further measurement report comprising the real measurement results. The steps 520 to 540 may be repeated until the number of transmitted measurement reports is equal to the configured number of measurement reports.

In other words, if reportAmount within a reporting configuration for a measurement ID is configured as being greater than one, once an AI-based measurement report is triggered or transmitted for the measurement ID for the first time, subsequent MR within reportAmount number of measurement report transmission may be determined based on real measurement results (i.e., the terminal device 110 performs real measurements for the next measurement report transmission) . That is, except that the first time of measurement report is based on AI prediction, the terminal device 110 may perform real measurements for one or more subsequent measurement reports.

FIG. 6 illustrates a schematic diagram 600 illustrating an example measurement report procedure according to embodiments of the present disclosure. In this example, configured number of measurement reports (i.e., reportAmount) is 3. As shown by reference sign 610 in FIG. 6, an AI-based measurement configuration may be provided to indicate using measurements on a set of measurement objects (MOs) (e.g., measObject 1 and measureObject 2) to predict measurement results for a further set of measurement objects (e.g., measObject 3, measObject 4 and measObject 5) .

As shown by reference sign 620 in FIG. 6, real measurements are performed on the set of measurement objects (e.g., measObject 1 and measureObject 2) . Results of the real measurements are used to predict the measurement results for the further set of measurement objects (e.g., measObject 3, measObject 4 and measObject 5) . It is assumed that Cell X in measObject 4 fulfils a reporting criterion or condition. Then a measurement report (MR) for measId 4 is initiated. This is an AI-based measurement report.

Upon initiation of the measurement report for measId 4, the number of transmitted measurement reports (i.e., numberOfReportsSent) may be incremented to 1. After a time interval (i.e., reportInterval) , a subsequent MR comprising results of real measurements for measObject 4 or Cell X in measObject 4 may be initiated. Accordingly, numberOfReportsSent may be incremented to 2. After another time interval (i.e., reportInterval) , another subsequent MR comprising results of real measurements for measObject 4 or Cell X in measObject 4 may be initiated. Accordingly, numberOfReportsSent may be incremented to 3. So far, the measurement report procedure ends.

For illustration, an example procedure may be described as below.

1> increment the numberOfReportsSent as defined within the VarMeasReportList for this measId by 1;

1> stop the periodical reporting timer, if running;

1> if the numberOfReportsSent as defined within the VarMeasReportList for this measId is less than the reportAmount as defined within the corresponding reportConfig for this measId:

2> start the periodical reporting timer with the value of reportInterval as defined within the corresponding reportConfig for this measId;

1> upon expiry of the periodical reporting timer for this measId:

2> for each measId included in the measurement report or VarMeasReportList (based on AI prediction) :

3> if the rsType within reportConfig that is associated with the measId is set to ssb:

3> if the rsType within reportConfig that is associated with the measId is set to csi-rs:

2> initiate the measurement reporting procedure;

In this example, VarMeasReportList denotes a UE variable storing information about measurements for which triggering conditions have been met, measId denotes a measurement ID, rsType denotes a type of a reference signal for measurements, reportConfig denotes a reporting configuration, reportQuantityCell denotes cell quantity to be reported, measObject denotes a measurement object, numberOfReportsSent denotes number of transmitted measurement reports, reportInterval denotes a time interval between two measurement reports, and reportAmount denotes configured number of measurement reports.

So far, a solution of a measurement report is described for the case that multiple transmissions of a measurement report are configured. With the solution, reliability of the AI-based measurement report may be improved.

FIG. 7 illustrates a schematic diagram illustrating another process 700 of communication for an AI-based measurement report according to embodiments of the present disclosure. For the purpose of discussion, the process 700 will be described with reference to FIG. 1. The process 700 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. 7 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. It is assumed that model training and deployment of an AI model is finished, and the AI model is deployed at the terminal device 110 or the network device 120.

As shown in FIG. 7, the terminal device 110 may determine 710 that a measurement report comprising predicted measurement results for a set of cells is to be transmitted. The predicted measurement results are based on an AI model. For example, when predicted measurement results for the set of cells fulfill a criterion or condition for initiating the measurement report, the terminal device 110 may determine that the measurement report is to be transmitted.

Continuing to refer to FIG. 7, the terminal device 110 may determine 720 real measurement results for the set of cells by performing measurements on the set of cells. The terminal device 110 may compare 730 the predicted measurement results and the real measurement results. If a difference between the predicted measurement results and the real measurement results is below a threshold, the terminal device 110 may transmit 740 the measurement report to the network device 120.

In some embodiments, if the difference between the predicted measurement results and the real measurement results is above the threshold, the terminal device 110 may consider that the measurement report is invalid or incorrect, and cancel 750 the measurement report. In some embodiments, the terminal device 110 may transmit 760 an indication that the measurement report is cancelled.

With the process 700, by evaluating validity of a measurement report before transmitting the measurement report, reliability of the AI-based measurement report may be improved, and signaling overhead for transmitting the measurement report may be saved.

EXAMPLE IMPLEMENTATION OF AI MODEL INFERENCE

FIG. 8 illustrates a schematic diagram illustrating a process 800 of communication for AI model inference according to embodiments of the present disclosure. For the purpose of discussion, the process 800 will be described with reference to FIG. 1. The process 800 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. 8 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. It is assumed that model training and deployment of an AI model for BFD is finished, and the AI model is deployed at the terminal device 110 or the network device 120.

As shown in FIG. 8, the terminal device 110 may transmit 810 assistance information to the network device 120. The terminal device 110 may use the assistance information to inform the network device 120 of a preference on an inference period for AI-based cell measurement result prediction or a measurement period for real cell measurements.

For AI inference, AI input is results of real measurements performed on several cells, and AI output is predicted measurement results for more cells. Thus AI inference here means predicting measurement results of more cells based on real measurements of several cells. The inference period indicates a frequency of cell measurement results prediction.

In some embodiments, the assistance information may comprise a preferred inference period. In some embodiments, the assistance information may comprise a preferred measurement period. In some embodiments, the assistance information may comprise a preferred synchronization signal and physical broadcast channel block (SSB) measurement timing configuration (SMTC) period. In some embodiments, the assistance information may comprise a preferred channel state information-reference signal (CSI-RS) period. In some embodiments, the assistance information may comprise a preferred discontinuous reception (DRX) cycle. In some embodiments, the assistance information may comprise a preferred measurement gap repetition period (MGRP) . It is to be understood that any combination of these information may also be feasible.

For illustration, an example assistance information may be described as below.

In this example, IE “preferredInferencePeriod” indicates a preference on an inference period, and IE “preferredMeasurementPeriod” indicates a preference on a measurement period. As shown by option 1 (denoted as opt. 1) , the assistance information may indicate a measurement period. Alternatively, as shown by option 2 (denoted as opt. 2) , the assistance information may indicate one or more of a SMTC period, CSI-RS period, DRX cycle and MGRP.

For illustration, an example procedure may be described as below.

A UE capable of providing its preference on inference period or measurement period for AI based cell measurement result prediction may initiate the procedure if it was configured to do so, including upon having a preference on parameters and upon change of its preference on parameters.

The UE shall set the contents of the UEAssistanceInformation message as follows:

1> if transmission of the UEAssistanceInformation message is initiated to provide AI-Preference:

2> include AI-Preference in the UEAssistanceInformation message;

2> if the UE has a preference on AI based cell measurement results:

3> if the UE has a preference for measurement period:

4> include measurementPeriod in the AI-Preference IE and set it to the preferred value;

3> if the UE has a preference for SMTC:

4> include smtc in the AI-Perference IE and set it to the preferred value;

3> if the UE has a preference for CSI-RS period:

4> include csi-rs-Resource-Mobility (i.e, to provide CSI-RS period) in the AI_Preference IE and set it to the preferred value;

3> if the UE has a preference for DRX-Config:

4> include drx-Config in the AI_Preference IE and set it to the preferred value;

3> if the UE has a preference for measurement gap:

4> include mgrp in the AI_Preference IE and set it to the preferred value;

3> if the UE has a preference for inference period:

4> include preferredInferencePeriod in the AI_Preference IE and set it to the preferred value;

1> submit the UEAssistanceInformation message to lower layers for transmission.

Continuing to refer to FIG. 8, the network device 120 may transmit 820, to the terminal device 110, a configuration comprising an inference period (for convenience, also referred to as a first inference period herein) of an AI model. The AI model is used for cell measurement result prediction. In some embodiments, the network device 120 may determine the inference period based on the assistance information. This may be dependent on network implementation.

With reference to FIG. 8, the network device 120 may transmit 830, to the terminal device 110, a further configuration indicating information of a measurement period for cell measurements. In some embodiments, the further configuration may indicate the measurement period. In some embodiments, the further configuration may indicate a SMTC period. In some embodiments, the further configuration may indicate a CSI-RS period. In some embodiments, the further configuration may indicate a DRX cycle. In some embodiments, the further configuration may indicate a MGRP. Any combination of such information may also be feasible. In some embodiments, the network device 120 may determine the information of the measurement period based on the assistance information. This may be dependent on network implementation.

Continuing to refer to FIG. 8, the terminal device 110 may determine 840 a measurement period of cell measurements. In some embodiments, the cell measurements may be intra-frequency measurements. In some embodiments, the cell measurements may be inter-frequency measurements. In some embodiments, based on the information of the measurement period in the further configuration, the terminal device 110 may determine the measurement period. In some embodiments, the measurement period may be predefined.

Then the terminal device 110 may determine 850 a used inference period (for convenience, also referred to as a second inference period herein) of the AI model based on at least one of the first inference period or the measurement period for cell measurements.

In some embodiments, the terminal device 110 may determine, as the second inference period, a larger one of the first inference period and the measurement period. For example, the second inference period may be determined based on equation (2) below.
T_{inference_period} = max (T_{inference_period}’, T_{measure_period}) (2)

where T_{inference_period} denotes the used inference period (i.e., the second inference period) , T_{inference_period}’ denotes a configured inference period (i.e., the first inference period) , and T_{measure_period} denotes a measurement period.

For example, if inference (100 ms) is performed twice within 200 ms, both AI input are the same due to T_{measure_period} = 200 ms. This will cause unnecessary inference for predicted cell measurement results. Thus, if T_{measure_period} = 200 ms and T_{inference_period}’ is 100 ms, the finally used inference period should be 200 ms. In this way, unnecessary inference for predicted cell measurement results may be avoided.

In another example, T_{measure_period} = 200 ms and T_{inference_period}’ is 400 ms, the final used inference period should be 400 ms. This is reasonable behavior as the inference (400 ms) will be performed based on different real measurement results due to T_{measure_period} =200 ms.

In some alternative embodiments, the configuration may indicate that the first inference period is equal to the measurement period. In these embodiments, the terminal device may determine the second inference period as being equal to the measurement period.

For illustration, an example procedure may be described as below.

When AI prediction (for cell measurement results) capable UE receives the configuration containing inference period, the UE shall determine the (final) used inference period based on the following formula:

The used T_{inference_period} = max (T_{inference_period} configured by NW, T_{measure_period})

Optionally, the used inference period could (directly) equal to T_{measure_period}.

Continuing to refer to FIG. 8, the terminal device 110 may predict 860 results of the cell measurements via the AI model based on the second inference period.

With the process 800, a reasonable inference period may be determined and unnecessary AI model inference may be reduced.

It is to be understood that the processes described in connection with FIGs. 3 to 8 may be carried out separately or in any suitable combination, and the present disclosure does not limit this aspect.

EXAMPLE IMPLEMENTATION OF METHODS

Corresponding to the above processes, embodiments of the present disclosure provide methods of communication implemented at a terminal device. These methods will be described below with reference to FIGs. 9 to 12.

FIG. 9 illustrates an 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 900 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.

At block 910, the terminal device 110 transmits, to the network device 120, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model.

At block 920, the terminal device 110 determines the measurement report is invalid.

In some embodiments, if the measurement report is transmitted, the terminal device 110 may determine real measurement results for the set of cells by performing measurements on the set of cells. If a difference between the predicted measurement results and the real measurement results is above a threshold, the terminal device 110 may determine that the measurement report is invalid.

In some embodiments, if the measurement report is transmitted, the terminal device 110 may perform a monitoring on the AI model. If the AI model is invalid, the terminal device 110 may determine that the measurement report is invalid. In some embodiments, a monitoring period of the monitoring may be a multiple of an inference period of the AI model.

In some embodiments, the terminal device 110 may receive, from the network device 120, a request for performing measurements on the set of cells. Based on the request, the terminal device 110 may determine that the measurement report is invalid.

At block 930, the terminal device 110 transmits, to the network device 120, information indicating invalidity of the measurement report.

In some embodiments, the terminal device 110 may transmit an indication of the invalidity of the measurement report. In some embodiments, the terminal device 110 may transmit a further measurement report comprising the real measurement results for the set of cells. In some embodiments, if a command for a handover to one of the set of cells is received, the terminal device 110 may transmit an indication for rejecting the handover. In some embodiments, the terminal device 110 may transmit an indication of invalidity of the AI model.

In some embodiments where the request for performing measurements on the set of cells is received from the network device 120, the terminal device 110 may determine the real measurement results for the set of cells by performing the measurements on the set of cells based on the request. The terminal device 110 may transmit, to the network device 120, a further measurement report comprising the real measurement results for the set of cells.

In some embodiments, the request may indicate at least one of the following: a measurement identity for the measurements; the set of cells; a type of a reference signal for the measurements; a time interval between two measurement reports; configured number of measurement reports; cell quantity to be reported; or a reporting configuration for the measurement report is reused for the further measurement report.

With the method 900, by evaluating validity of a measurement report after transmitting the measurement report, reliability of the AI-based measurement report may be improved.

FIG. 10 illustrates another example method 1000 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 1000 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 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.

At block 1010, the terminal device 110 transmits, to the network device 120, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model.

At block 1020, the terminal device 110 increments number of transmitted measurement reports.

At block 1030, the terminal device 110 determines that the number of transmitted measurement reports is less than a configured number of measurement reports.

At block 1040, the terminal device 110 determines real measurement results for the set of cells by performing measurements on the set of cells.

At block 1050, the terminal device 110 transmits, to the network device 120, a further measurement report comprising the real measurement results.

With the method 1000, by transmitting both predicted measurement results and real measurement results in multiple transmissions configured for a measurement report, reliability of the AI-based measurement report may be improved.

FIG. 11 illustrates another example method 1100 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 1100 may be performed at the terminal device 110 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.

At block 1110, the terminal device 110 determines that a measurement report comprising predicted measurement results for a set of cells is to be transmitted. The predicted measurement results are based on an AI model.

At block 1120, the terminal device 110 determines real measurement results for the set of cells by performing measurements on the set of cells.

At block 1130, the terminal device 110 determines that a difference between the predicted measurement results and the real measurement results is below a threshold.

At block 1140, the terminal device 110 transmits the measurement report to the network device 120.

In some embodiments, if the difference between the predicted measurement results and the real measurement results is above the threshold, the terminal device 110 may cancel the measurement report. In some embodiments, the terminal device 110 may transmit, to the network device 120, an indication that the measurement report is cancelled.

With the method 1100, by evaluating validity of a measurement report before transmitting the measurement report, reliability of the AI-based measurement report may be improved, and signaling overhead for transmitting the measurement report may be saved.

FIG. 12 illustrates another example method 1200 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 1200 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1200 will be described with reference to FIG. 1. It is to be understood that the method 1200 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.

At block 1210, the terminal device 110 receives, from the network device 120, a configuration comprising a first inference period of an AI model.

In some embodiments, the terminal device may transmit assistance information to the network device 120. The assistance information may comprise at least one of the following: a preferred inference period; a preferred measurement period; a preferred SMTC period; a preferred CSI-RS period; a preferred DRX cycle; or a preferred MGRP.

At block 1220, the terminal device 110 determines a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements.

In some embodiments, the terminal device 110 may determine, as the second inference period, a larger one of the first inference period and the measurement period.

In some embodiments, the configuration may indicate that the first inference period is equal to the measurement period. In this case, the terminal device 110 may determine the second inference period as being equal to the measurement period.

At block 1230, the terminal device 110 predicts results of the cell measurements via the AI model based on the second inference period.

With the method 1200, a reasonable inference period may be determined and unnecessary AI model inference may be reduced.

It is to be understood that operations of the methods 900 to 1200 correspond to that described in connection with FIGs. 3 to 8, and thus other details are not repeated here for concise.

EXAMPLE IMPLEMENTATION OF DEVICES

FIG. 13 is a simplified block diagram of a device 1300 that is suitable for implementing embodiments of the present disclosure. The device 1300 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 1300 can be implemented at or as at least a part of the terminal device 110 or the network device 120.

As shown, the device 1300 includes a processor 1310, a memory 1320 coupled to the processor 1310, a suitable transceiver 1340 coupled to the processor 1310, and a communication interface coupled to the transceiver 1340. The memory 1310 stores at least a part of a program 1330. The transceiver 1340 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1340 may include at least one of a transmitter 1342 or a receiver 1344. The transmitter 1342 and the receiver 1344 may be functional modules or physical entities. The transceiver 1340 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.

The program 1330 is assumed to include program instructions that, when executed by the associated processor 1310, enable the device 1300 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGs. 1 to 12. The embodiments herein may be implemented by computer software executable by the processor 1310 of the device 1300, or by hardware, or by a combination of software and hardware. The processor 1310 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1310 and memory 1320 may form processing means 1350 adapted to implement various embodiments of the present disclosure.

The memory 1320 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 1320 is shown in the device 1300, there may be several physically distinct memory modules in the device 1300. The processor 1310 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 1300 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.

In some embodiments, a terminal device comprises a circuitry configured to: transmit, to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; and in accordance with a determination that the measurement report is invalid, transmit, to the network device, information indicating invalidity of the measurement report.

In some embodiments, a terminal device comprises a circuitry configured to: transmit, to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an AI model; increment number of transmitted measurement reports; in accordance with a determination that the number of transmitted measurement reports is less than a configured number of measurement reports, determine real measurement results for the set of cells by performing measurements on the set of cells; and transmit, to the network device, a further measurement report comprising the real measurement results.

In some embodiments, a terminal device comprises a circuitry configured to: determine that a measurement report comprising predicted measurement results for a set of cells is to be transmitted, the predicted measurement results being based on an AI model; determine real measurement results for the set of cells by performing measurements on the set of cells; and in accordance with a determination that a difference between the predicted measurement results and the real measurement results is below a threshold, transmit the measurement report to a network device.

In some embodiments, a terminal device comprises a circuitry configured to: receive, from a network device, a configuration comprising a first inference period of an AI model; determine a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements; and predict results of the cell measurements via the AI model based on the second inference period.

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.

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.

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 12. 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.

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.

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.

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.

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

A terminal device, comprising:

a processor configured to cause the terminal device to:

transmit, to a network device, a measurement report comprising predicted measurement results for a set of cells, the predicted measurement results being based on an artificial intelligence (AI) model; and

in accordance with a determination that the measurement report is invalid, transmit, to the network device, information indicating invalidity of the measurement report.
The terminal device of claim 1, wherein the terminal device is further caused to:

in accordance with a determination that the measurement report is transmitted, determine real measurement results for the set of cells by performing measurements on the set of cells; and

in accordance with a determination that a difference between the predicted measurement results and the real measurement results is above a threshold, determine that the measurement report is invalid.
The terminal device of claim 2, wherein the terminal device is caused to transmit the information by at least one of the following:

transmitting an indication of the invalidity of the measurement report;

transmitting a further measurement report comprising the real measurement results for the set of cells; or

in accordance with a determination that a command for a handover to one of the set of cells is received, transmitting an indication for rejecting the handover.
The terminal device of claim 1, wherein the terminal device is further caused to:

in accordance with a determination that the measurement report is transmitted, perform a monitoring on the AI model; and

in accordance with a determination that the AI model is invalid, determine that the measurement report is invalid.
The terminal device of claim 4, wherein a monitoring period of the monitoring is a multiple of an inference period of the AI model.
The terminal device of claim 4, wherein the terminal device is caused to transmit the information by:

transmitting an indication of invalidity of the AI model.
The terminal device of claim 1, wherein the terminal device is further caused to:

receive, from the network device, a request for performing measurements on the set of cells; and

determine, based on the request, that the measurement report is invalid.
The terminal device of claim 7, wherein the terminal device is caused to transmit the information by:

determining the real measurement results for the set of cells by performing the measurements on the set of cells based on the request; and

transmitting a further measurement report comprising the real measurement results for the set of cells.
The terminal device of claim 8, wherein the request indicates at least one of the following:

a measurement identity for the measurements;

the set of cells;

a type of a reference signal for the measurements;

a time interval between two measurement reports;

configured number of measurement reports;

cell quantity to be reported; or

a reporting configuration for the measurement report is reused for the further measurement report.
A terminal device, comprising:

a processor configured to cause the terminal device to:

determine that a measurement report comprising predicted measurement results for a set of cells is to be transmitted, the predicted measurement results being based on an artificial intelligence (AI) model;

determine real measurement results for the set of cells by performing measurements on the set of cells; and

in accordance with a determination that a difference between the predicted measurement results and the real measurement results is below a threshold, transmit the measurement report to a network device.
The terminal device of claim 10, wherein the terminal device is further caused to at least one of the following:

in accordance with a determination that the difference between the predicted measurement results and the real measurement results is above the threshold,

cancel the measurement report; or

transmit an indication that the measurement report is cancelled.
A terminal device, comprising:

a processor configured to cause the terminal device to:

receive, from a network device, a configuration comprising a first inference period of an artificial intelligence (AI) model;

determine a second inference period of the AI model based on at least one of the first inference period or a measurement period for cell measurements; and

predict results of the cell measurements via the AI model based on the second inference period.
The terminal device of claim 12, wherein the terminal device is caused to determine the second inference period by:

determining, as the second inference period, a larger one of the first inference period and the measurement period.
The terminal device of claim 12, wherein the configuration indicates that the first inference period is equal to the measurement period, and wherein the terminal device is caused to determine the second inference period by:

determining the second inference period as being equal to the measurement period.
The terminal device of claim 12, wherein the terminal device is further caused to:

transmit, to the network device, assistance information comprising at least one of the following:

a preferred inference period;

a preferred measurement period;

a preferred synchronization signal and physical broadcast channel block (SSB) measurement timing configuration (SMTC) period;

a preferred channel state information-reference signal (CSI-RS) period;

a preferred discontinuous reception (DRX) cycle; or

a preferred measurement gap repetition period (MGRP) .