Communication method, terminal device, and network device

Abstract

The present application relates to a communication method, a terminal device, a network device, a chip, a computer-readable storage medium, a computer program product, a computer program, and a communication system. The method comprises: a terminal device sends first indicator information to a network device, wherein the first indicator information is used for monitoring a first model, and the first model is used for determining, from among a plurality of measurement objects, a first measurement object that needs to be preferentially measured. Embodiments of the present application can reduce unnecessary measurements, thereby reducing the measurement costs.

Description

Communication method, terminal device and network device TECHNICAL FIELD

[0001] The present application relates to the field of communication, and more particularly, to a communication method, a terminal device, a network device, a chip, a computer readable storage medium, a computer program product, a computer program and a communication system. BACKGROUND

[0002] In a cellular communication system, a user equipment (UE) needs to measure the strength or quality of the radio signal of the current serving cell and the surrounding neighboring cells, and then report these contents to the network in a measurement report radio resource control (RRC) message. The network can make relevant handover decisions based on these contents.

[0003] In the related art, the UE will measure the detected neighboring cells as much as possible to ensure that the mobility management of the cellular system can proceed normally. The UE needs to pay a lot of costs for measurement, including energy consumption, traffic loss, etc., and needs to consider how to reduce the cost of measurement.

[0004] SUMMARY

[0005] The embodiments of the present application provide a communication method, a terminal device, a network device, a chip, a computer readable storage medium, a computer program product, a computer program and a communication system, which can reduce the cost of measurement.

[0006] The embodiments of the present application provide a communication method, comprising:

[0007] The terminal device sends first index information to the network device; wherein the first index information is used for monitoring of a first model, and the first model is used for determining a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

[0008] The embodiments of the present application provide a communication method, comprising:

[0009] The network device receives first index information from the terminal device; wherein the first index information is used for monitoring of a first model by the network device, and the first model is used for determining a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

[0010] The embodiments of the present application provide a terminal device, comprising:

[0011] The first communication module is configured to send first index information to the network device; wherein the first index information is used for monitoring of a first model, and the first model is used for determining a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

[0012] The embodiment of the present application provides a network device, comprising:

[0013] The second communication module is used for receiving first index information from the terminal device; wherein the first index information is used for the network device to monitor a first model, and the first model is used for determining a first measurement object which needs to be preferentially measured in a plurality of measurement objects.

[0014] The embodiment of the present application provides a terminal device, comprising a transceiver, a processor and a memory. The memory is used for storing a computer program, the transceiver is used for communicating with other devices, and the processor is used for calling the computer program stored in the memory, so that the terminal device executes the above-mentioned communication method.

[0015] The embodiment of the present application provides a network device, comprising a transceiver, a processor and a memory. The memory is used for storing a computer program, the transceiver is used for communicating with other devices, and the processor is used for calling the computer program stored in the memory, so that the network device executes the above-mentioned communication method.

[0016] The embodiment of the present application provides a chip, which is used for implementing the above-mentioned communication method.

[0017] Specifically, the chip comprises a processor, which is used for calling a computer program from a memory, so that the device installed with the chip executes the above-mentioned communication method.

[0018] The embodiment of the present application provides a computer readable storage medium, which is used for storing a computer program, and when the computer program is run by a device, the device executes the above-mentioned communication method.

[0019] The embodiment of the present application provides a computer program product, comprising computer program instructions, which make a computer execute the above-mentioned communication method.

[0020] The embodiment of the present application provides a computer program, which, when running on a computer, makes the computer execute the above-mentioned communication method.

[0021] The embodiment of the present application provides a communication system, comprising a terminal device and a network device used for executing the above-mentioned communication method.

[0022] The embodiment of the present application supports monitoring the first model by sending the first index information from the terminal device to the network device, so that the first model can have good performance, is applied to the communication system, helps the terminal device to determine the first measurement object which needs to be preferentially measured in a plurality of measurement objects, and is beneficial to reducing unnecessary measurement, thereby reducing the cost of measurement. BRIEF DESCRIPTION OF DRAWINGS

[0023] Fig. 1 is a schematic diagram of an application scenario according to the embodiment of the present application.

[0024] FIG. 2 is a schematic diagram of a measurement model of UE measurement.

[0025] FIG. 3 is a schematic diagram of an application manner of a TTT timer.

[0026] FIG. 4 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0027] FIG. 5 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0028] FIG. 6 is a schematic diagram of measurement results of cells in an application example of an embodiment of the present application.

[0029] FIG. 7 is a schematic block diagram of a terminal device according to an embodiment of the present application.

[0030] FIG. 8 is a schematic block diagram of a terminal device according to another embodiment of the present application.

[0031] FIG. 9 is a schematic block diagram of a terminal device according to another embodiment of the present application.

[0032] FIG. 10 is a schematic block diagram of a network device according to an embodiment of the present application.

[0033] FIG. 11 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0034] FIG. 12 is a schematic block diagram of a chip according to an embodiment of the present application.

[0035] FIG. 13 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0037] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: a Long Term Evolution (LTE) system, an Advanced long term evolution (LTE-A) system, a New Radio (NR) system, an evolved system of the NR system, a LTE-based access to unlicensed spectrum (LTE-U) system, a NR-based access to unlicensed spectrum (NR-U) system, a Non-Terrestrial Networks (NTN) system, a Universal Mobile Telecommunication System (UMTS), a Wireless Local Area Networks (WLAN), a Wireless Fidelity (WiFi), a 5th-Generation (5G) system, a 6th-Generation (6G) system, or other communication systems, and the like.

[0038] Generally, a conventional communication system supports a limited number of connections, and is easy to implement. However, with the development of communication technology, a mobile communication system will not only support conventional communication, but also support, for example, Device to Device (D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication, or Vehicle to everything (V2X) communication, and the like. The embodiments of the present application can also be applied to these communication systems.

[0039] In an embodiment, the communication system in the embodiments of the present application can be applied to a carrier aggregation (CA) scenario, can also be applied to a dual connectivity (DC) scenario, and can also be applied to a standalone (SA) network deployment scenario.

[0040] In an implementation, the communication system in embodiments of the present application can be applied to unlicensed spectrum, which can also be considered as shared spectrum, or applied to licensed spectrum, which can also be considered as unshared spectrum.

[0041] Embodiments of the present application describe various embodiments in combination with network devices and terminal devices, wherein the terminal device can also be referred to as user equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0042] The terminal device can be a station (STA) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device having wireless communication function, a computing device, or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a next-generation communication system such as a NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0043] In embodiments of the present application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or in-vehicle; can also be deployed on water surface (such as ships, etc.); and can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0044] In embodiments of the present application, the terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a Virtual Reality (VR) terminal device, an Augmented Reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self driving, a wireless terminal device in remote medical treatment, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, or a wireless terminal device in smart home, etc.

[0045] By way of example and not limitation, in embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The broad sense of wearable smart devices includes devices with full functions and large sizes that can realize complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and devices that focus on a certain type of application function and need to be used in cooperation with other devices, such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0046] In embodiments of the present application, the network device can be a device for communicating with the mobile device, and the network device can be an access point (Access Point, AP) in a WLAN, an evolved node B (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or an access point, or a vehicle-mounted device, a wearable device, and a network device in an NR network (gNB) or a future evolved PLMN network or a network device in an NTN network, etc.

[0047] By way of example and not limitation, in embodiments of the present application, the network device can have mobile characteristics, for example, the network device can be a mobile device. Alternatively, the network device can be a satellite, a balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geostationary earth orbit (geostationary earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite, etc. Alternatively, the network device can also be a base station arranged at a position on land, water, etc.

[0048] In the embodiments of the present application, the network device can serve a cell, and a terminal device communicates with the network device through a transmission resource (for example, a frequency domain resource, or a spectrum resource) used by the cell. The cell can be a cell corresponding to the network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell (Small cell). The small cell can include a metro cell, a micro cell, a pico cell, a femto cell, and the like. The small cell has the characteristics of small coverage and low transmit power, and is suitable for providing high-speed data transmission services.

[0049] FIG. 1 illustrates a communication system 100. The communication system includes one network device 110 and two terminal devices 120. In an embodiment, the communication system 100 can include multiple network devices 110, and each network device 110 can include other numbers of terminal devices 120 within its coverage, which is not limited in the embodiments of the present application.

[0050] In an embodiment, the communication system 100 can further include a mobility management entity (MME), an access and mobility management function (AMF), and other network entities, which are not limited in the embodiments of the present application.

[0051] The network device can include an access network device and a core network device. That is, the wireless communication system further includes multiple core networks for communicating with the access network device. The access network device can be an evolved node B (eNB or e-NodeB) macro base station, a micro base station (also referred to as a “small base station”), a pico base station, an access point (AP), a transmission point (TP), or a new generation Node B (gNodeB) in a long-term evolution (LTE) system, a next radio (NR) system, or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0052] It should be understood that the devices with communication function in the network / system in the embodiments of the present application can be referred to as communication devices. For example, the communication system shown in FIG. 1, the communication devices can include network devices and terminal devices with communication function, which can be specific devices in the embodiments of the present application, and will not be described here. The communication devices can also include other devices in the communication system, such as network controllers, mobile management entities and other network entities, which are not limited in the embodiments of the present application.

[0053] It should be understood that the terms "system" and "network" are often used interchangeably in this paper. The term "and / or" in this paper is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects before and after it.

[0054] It should be understood that the "indication" mentioned in the embodiments of the present application can be direct indication, indirect indication, or can represent an associated relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that A and B have an associated relationship.

[0055] In the description of the embodiments of the present application, the term "corresponding" can represent a direct or indirect corresponding relationship between the two, or can represent an associated relationship between the two, or can represent an indication and being indicated, configuration and being configured, etc.

[0056] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described as follows, which can be combined with the technical solutions of the embodiments of the present application in any way, and all belong to the protection scope of the embodiments of the present application.

[0057] (I) Artificial Intelligence (AI) / Machine Learning (ML)

[0058] In 3GPP, it is studied whether AI / ML algorithms can help improve the performance of the physical layer. The results of the study include core evaluation methods and results, as well as how to manage AI / ML on the network side, the UE side, or both sides. These contents become the contents of life cycle management (LCM). LCM is a relatively broad term, and its contents include: data collection; model training; function / model identification; model transmission; model inference; selection, activation, deactivation, replacement, and fallback of functions / models; function / model monitoring; model updating; UE capability reporting, and other contents.

[0059] 3GPP also studies how to use AI / ML algorithms to predict beam measurements for beam management purposes. One sub-use case is the prediction applied to the spatial domain, that is, by measuring a subset of beams in a set, using the spatial correlation between beams, to predict the best beam (the strongest wireless signal) or a pair of beams (downlink transmission and reception) in the full set of beams. Another use case is the beam prediction applied to the time domain, that is, based on the measurement results of historically measured beams (and beams that have been predicted), using the correlation of beams over time, to predict the measurement results of beams in the current time slot. From the recorded evaluation results, it can be proved that these two use cases are not only technically feasible, but also can provide high performance improvement.

[0060] (II) RRM measurement

[0061] In 3GPP's cellular communication system, the UE needs to measure the strength or quality of the wireless signal of the current serving cell and the surrounding neighboring cells, and then report these contents to the network in the form of a measurement report (measurementReport) RRC message. Generally, the network can make relevant handover decisions based on these contents.

[0062] Figure 2 is a schematic diagram of a measurement model for UE measurement, which describes how the UE performs intra-frequency or inter-frequency measurement processes, and how it measures samples according to beams at Layer 1 (L1) and how it makes measurement event decisions based on network-configured parameters.

[0063] The following describes several reference points in Figure 2:

[0064] A: This is the link where the UE performs physical layer measurement sampling, which is performed in the granularity of beams;

[0065] A1: UE performs L1 filtering on the measured L1 beam level measurement result. Generally, the protocol specifies the length of the measurement period under specific RRC configuration. The measurement period specifies that the UE should perform at least one sampling, and the beam measurement result after L1 filtering should meet the specified performance requirements. The specific sampling times of the UE at the reference point A within a measurement period are specified. In the test case, a measurement period generally uses 4-5 oversampling. For FR1 (Frequency Range 1) frequency band, the shortest measurement period is 200 ms, and for FR2 (Frequency Range 2) frequency band, the shortest measurement period is 400 ms. That is, the time of L1 oversampling is basically less than 100 ms.

[0066] B: The L1 beam level measurement result of a certain cell obtained at A1 is subjected to a merging operation to synthesize the L1 cell level measurement result;

[0067] C: The L1 cell level measurement result of a certain cell is sequentially subjected to Layer 3 (L3) filtering to obtain the L3 cell level measurement result;

[0068] D: The measurement result of the serving cell and / or the neighboring cell is subjected to a certain decision condition (configured by the network) to determine whether a specific measurement event is true. For example, whether the measurement result of the neighboring cell is higher than the measurement result of the primary cell (PCell) of the cell by an offset value (A3 event), etc.

[0069] In the second generation communication system, the measurement report is always reported according to a certain period. From the third generation communication system, including, for example, Wideband Code Division Multiple Access (WCDMA), the fourth generation communication system LTE, and the fifth generation communication system NR, the measurement report is distinguished from the reporting mode, which can be mainly divided into three types:

[0070] Periodic reporting;

[0071] Measurement event-based reporting;

[0072] Measurement event-based reporting and subsequent periodic reporting.

[0073] In any form of reporting of the measurement report, specific measurement events and / or measurement results, such as signal strength or signal quality of a cell, can be included in the measurement report; where the signal strength is, for example, Reference Signal Receiving Power (RSRP) in dbm, and the signal quality is, for example, Reference Signal Receiving Quality (RSRQ) in db. The reported cells include the current serving cell and the neighboring cells. The measurement objects can be the same frequency, different frequencies, or different systems.

[0074] The triggering of a measurement event includes the following basic elements:

[0075] 1. Measurement results, including the measurement results of the serving cell and / or the neighboring cells, such as the signal strength of a cell.

[0076] 2. Comparison parameters, such as threshold, hysteresis, offset, etc. The dimension of the measurement results is in the standard protocol, and the larger the value, the higher the signal strength or quality. Absolute comparison means comparing the measurement value of a cell with a threshold, and in this case, the measurement result greater than the sum of the threshold and the hysteresis indicates that the entering condition is met, and the measurement result less than the difference between the threshold and the hysteresis indicates that the leaving condition is met. Relative comparison usually means comparing the measurement results of the neighboring cells with the measurement results of the serving cell. Before comparison, each cell needs to be added with the relevant offset value. For the serving cell, the event-related offset value (Off_event) also needs to be added. Finally, when comparing, the hysteresis value (Hys) also needs to be considered. Taking the A3 event as an example, the measurement results, offset values, etc. of the serving cell are marked with s, and the measurement results, offset values, etc. of the neighboring cells are marked with n, then the entering condition of the A3 event can be expressed as:

[0077] Mn+Ofn>Ms+Ofs+Hys+Off_event;

[0078] The leaving condition of the A3 event can be expressed as:

[0079] Mn+Ofn<Ms+Ofs-Hys+Off_event;

[0080] Wherein Mn represents the measurement result of the neighboring cell, Ofn represents the offset value related to the neighboring cell; Ms represents the measurement result of the serving cell, Ofs represents the offset value related to the serving cell, Hys represents the hysteresis value, and Off_event represents the event-related offset value.

[0081] 3. Timer indicating the robustness of the measurement result, i.e. time to trigger (TTT) timer. Figure 3 is a schematic diagram of the application of the TTT timer. When a certain cell (target cell) meets the entering condition of a certain event at T0, the TTT timer starts. When the TTT timer expires, if the cell still meets the entering condition of the event, it means that the cell triggers the measurement event.

[0082] (III) AI mobility

[0083] The techniques for beam measurement prediction can be applied to RRM measurement. In the AI mobility project, AI models are adopted, and the following use cases are mainly studied:

[0084] RRM measurement prediction: the output of the model is the L3 cell level measurement result mentioned above, and the input can be the L1 beam level measurement result or the L3 cell level measurement result. The input and output measurement results can come from the same cell, or different cells of different frequency layers, or a group of cells. The prediction can be in the time domain or the frequency domain, or between different frequencies (i.e. in the frequency domain). In the time domain prediction model, if the purpose of prediction is to improve the mobility handover performance, the measurement results in a future window period will be predicted according to the historical measurement results. In addition, if the output of the model is set to the L3 beam level measurement result, the input of the model can be the L1 or L3 beam level measurement result. In this case, the input and output beams come from the same cell.

[0085] Measurement event prediction: one method is to infer whether a certain measurement event will occur at a certain point in time in the future based on the results of RRM measurement prediction, in combination with the configuration parameters of a certain measurement event related to network configuration. This method is called indirect prediction method. Direct prediction method can also be adopted, i.e. based on the input measurement results (at least including the serving cell and / or the neighboring cell directly related to the event), and then using the model to infer whether a certain measurement event will occur.

[0086] Abnormal mobility event: similar to measurement event prediction, direct or indirect prediction method can be adopted, but the input measurement results at least include the serving cell and / or the neighboring cell directly related to the event.

[0087] These AI models related to use cases can only be used in UEs after training. Generally, these AI models adopt supervised machine learning models. Taking RRM measurement time domain prediction as an example, if the input of the model is the L1 beam level measurement result and the output is the L3 cell level measurement result, the training steps are as follows:

[0088] Step 1: UE measures a certain cell, gets the L1 beam level measurement results of this cell, and gets the L3 cell level measurement results according to the existing measurement model. These measurement results are arranged in time domain according to the time sequence of obtaining these results.

[0089] Step 2: Use part of the L1 beam level measurement results in time domain as input to the AI model, and get the output of the model, i.e. the predicted L3 cell level measurement results.

[0090] Step 3: Compare the predicted L3 cell level measurement results at the same time point with the actually measured L3 cell level measurement results in step 1, and transfer the difference between the two to the AI model, and correct the parameters inside the model according to the principle of supervised AI model.

[0091] These three steps are repeated until a certain condition representing the model tends to be stable.

[0092] For such a training process, the nodes of the training model, generally a network node, need to obtain these measurement results from the UE, and train the AI model.

[0093] In the existing technical specification, the measurement object in a measurement task can be a frequency, or some cells on a certain frequency (called whitelist). When the measurement object is a certain frequency, the UE needs to measure all the adjacent cells that can be detected on this frequency, unless a certain adjacent cell appears on the blacklist of this frequency.

[0094] In either of the above cases, once a certain adjacent cell is detected, the UE will try to measure the detected adjacent cell as much as possible. In the existing technical specification, there are generally two cases in which a certain adjacent cell cannot be measured after being detected:

[0095] 1. The UE has already made the best effort to measure, so it cannot measure additional adjacent cells;

[0096] 2. The UE has the ability to measure, but under certain conditions, such as when the UE is close to the base station, the protocol specification allows the UE to measure only part of the adjacent cells.

[0097] In either of the above cases, the UE needs to measure a plurality of neighboring cells to ensure that the mobility management of the cellular system can proceed normally. In fact, the mobility event only occurs between the current serving cell and one of the neighboring cells, that is, among the plurality of neighboring cells, only one of the neighboring cells eventually meets the condition of handover or cell reselection. This means that most of the RRM measurements made by the UE are actually wasted. Since the UE needs to pay a lot of costs to make measurements, including energy consumption, traffic loss, etc. If the UE is required to make measurements, unnecessary measurements can be reduced, and the cost will be greatly reduced.

[0098] The technical solutions of the embodiments of the present application are mainly to solve at least one of the above technical problems.

[0099] FIG. 4 is a schematic flowchart of a communication method according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG. 1, but is not limited thereto. The method includes at least part of the following content.

[0100] S410, the terminal device sends first index information to the network device; wherein the first index information is used for monitoring of a first model, and the first model is used to determine a first measurement object that needs to be preferentially measured among a plurality of measurement objects.

[0101] According to the method of the embodiments of the present application, the terminal device can determine a first measurement object that needs to be preferentially measured among a plurality of measurement objects based on a first model. Optionally, the measurement object can include at least one of a frequency, a cell, and a beam. Or, the granularity of the measurement object can be at least one of a frequency, a cell, and a beam, for example, taking a frequency as the granularity of the measurement object, or taking a cell as the granularity of the measurement object, or taking a beam as the granularity of the measurement object. Illustratively, the terminal device can determine a first measurement object that needs to be preferentially measured among a plurality of frequencies based on a first model; and / or, the terminal device can determine a first cell that needs to be preferentially measured among a plurality of cells based on a first model; and / or, the terminal device can determine a first beam that needs to be preferentially measured among a plurality of beams based on a first model.

[0102] Optionally, the above plurality of measurement objects can include all measurement objects to be measured by the terminal device. For example, when the measurement object is a cell on a certain frequency, the above plurality of measurement objects can include all detectable neighboring cells on the frequency. For another example, when the measurement object is a beam in a cell, if there are multiple beams in a cell, the above plurality of measurement objects can include all beams of the cell. For another example, when the measurement object is a frequency, the plurality of measurement objects can include a plurality of frequency points configured by the network.

[0103] In the embodiments of the present application, the first measurement object is a measurement object determined based on the first model, and the measurement object is a measurement object that needs to be measured preferentially. In some example scenarios, the first measurement object can be understood as a best measurement object selected by the first model. For example, the terminal device selects a neighboring cell for handover or cell reselection in multiple neighboring cells, and the first model should select a cell that is most likely to meet the handover condition or the cell reselection condition to avoid affecting the communication performance. Therefore, the first measurement object can be understood as a best cell considered by the first model, and similarly, the first measurement object can also be understood as a best frequency or a best beam considered by the first model.

[0104] Optionally, when the granularity of the measurement object is multiple levels of granularity, the first model can be implemented based on a nested architecture or a hybrid architecture to determine the first measurement object from the multiple measurement objects.

[0105] The nested architecture refers to a process / algorithm for determining a measurement object at a low level, which can be nested in a process / algorithm for determining a measurement object at a high level. For example, a first frequency is determined from multiple frequencies, and a first cell is determined from multiple cells on the first frequency. For another example, a first cell is determined from multiple cells, and a first beam is determined from multiple beams of the first cell.

[0106] The hybrid architecture refers to selecting one or more first measurement objects at the lowest level from all the measurement objects at the lowest level. For example, one or more first cells are determined from all the cells of multiple different frequencies for measurement. For another example, one or more beams are determined from all the beams of multiple cells for measurement.

[0107] Optionally, the first model can include an AI model or an ML model. It should be noted that in the embodiments of the present application, the first model can be understood as a function or a feature (first function or first feature). Specifically, in different scenarios or in different description manners, any form of model, algorithm, function, and feature in the first device can be used to determine the first measurement object that needs to be measured preferentially from the multiple measurement objects. Taking the first model including an AI model as an example, the first device is deployed with an AI model or an AI algorithm, and the AI model or the AI algorithm can be used to determine the first measurement object that needs to be measured preferentially from the multiple measurement objects. Alternatively, the first device has an AI function, and the AI function can be used to determine the first measurement object that needs to be measured preferentially from the multiple measurement objects. Alternatively, the first device has an AI feature, and due to the AI feature, the first measurement object that needs to be measured preferentially can be determined from the multiple measurement objects. Therefore, in some examples or descriptions, the first model can also be referred to as a first algorithm, a first function, or a first feature.

[0108] Optionally, the number of the first measurement objects determined by the first model can be one or more, and the terminal device obtains the corresponding measurement results by measurement. Optionally, for the measurement objects other than the first measurement objects, the terminal device can not perform measurement or only perform measurement on part of the measurement objects or perform measurement as needed. For example, for the other measurement objects, the terminal device can not perform measurement or randomly select a small number of measurement objects to perform measurement without the need to determine the first index information and report the network device; the terminal device can perform measurement on all measurement objects with the need to determine the first index information and report the network device.

[0109] Optionally, the first index information can be information determined based on the output result of the first model. For example, the first index information can be a communication performance index after using the first model, or the first index information can be statistical information determined based on the first measurement object and the actual best measurement object determined by the first model. In this way, by transmitting the first index information, the network device can determine the performance of the first model to make decisions related to the first model, such as model selection, activation, deactivation, replacement, or fallback.

[0110] Corresponding to the above method, FIG. 5 is a schematic flowchart of a communication method according to an embodiment of the present application. The method can be optionally applied to the system shown in FIG. 1, but is not limited thereto. The method includes at least part of the following contents.

[0111] S510, the network device receives the first index information from the terminal device; wherein the first index information is used for the network device to monitor the first model, and the first model is used to determine the first measurement object that needs to be preferentially measured in the plurality of measurement objects.

[0112] According to the above method, by transmitting the first index information from the terminal device to the network device, the first model can be monitored, so that the first model can have good performance, be applied to the communication system, help the terminal device to determine the first measurement object that needs to be preferentially measured in the plurality of measurement objects, and be beneficial to reduce unnecessary measurement, thereby reducing the cost of measurement. Specifically, the hardware and software resources invested by the terminal device in RRM measurement can be reduced, the energy consumption can be reduced, the standby time can be prolonged, the configuration of the measurement interval can be reduced, and the uplink and downlink traffic of the terminal device can be improved.

[0113] In some embodiments, the first index information is determined based on measurement results of the plurality of measurement objects. That is, the terminal device determines the first index information based on the measurement results of the plurality of measurement objects, and then sends the first index information to the network device. Optionally, the first index information is determined based on the measurement results of the plurality of measurement objects and the first measurement object. The measurement results of the plurality of measurement objects can reflect whether the first measurement object selected by the first model is accurate (whether it is the actual best measurement object), and therefore, determining the first index information based on the measurement results of the plurality of measurement objects can accurately monitor and evaluate the performance of the first model.

[0114] In some embodiments, the first index information includes first proportion information, and the first proportion information is a proportion (or a percentage) of a number of times that the first measurement object contains the best measurement object. For example, after the first measurement object is determined by the first model for multiple times, the proportion between the number of times that the first measurement object contains the best measurement object and the total number of times can be taken as the first index information.

[0115] For example, each monitoring period includes M algorithm periods, in each algorithm period, the terminal device determines N first measurement objects (N is an integer greater than or equal to 1) that need to be measured in the plurality of measurement objects based on the first model, and measures the plurality of measurement objects to obtain measurement results; after the monitoring period ends, the first index information is obtained based on a ratio between a number of times that the N first measurement objects contain the best measurement object and M.

[0116] For example, the above-mentioned best measurement object can be understood as an actual best measurement object, that is, a best measurement object that can be measured by the terminal device without using the first model. Alternatively, the best measurement object can be a measurement object with the best measurement result (for example, the largest RSRP / RSRQ) in the plurality of measurement objects, or a measurement object that actually experiences a mobility event (for example, a target cell of cell handover / reselection). For example, the granularity of measurement is a cell, and L3 RSRP is used as a measurement quantity, in each algorithm period, the terminal device can select, for example, 3 cells to measure by using the first model. At the same time, the terminal device measures all the monitored neighboring cells. If the terminal device finds that the cell with the highest L3 RSRP obtained without using the first model is in the 3 cells selected by the algorithm, then the comparison result of the algorithm period is 1; otherwise, it is 0. In a monitoring period, for example, 60 seconds, the proportion of the periods with the result of 1 in the total number of periods is the first index information. The higher the proportion, the higher the performance of the first model.

[0117] In some embodiments, the communication method performed by the terminal device can further include: receiving, by the terminal device, a monitoring request from the network device; wherein the monitoring request is used to trigger the terminal device to measure a plurality of measurement objects when running the first model to determine the first index information.

[0118] Correspondingly, in some embodiments, the communication method performed by the network device can further include: sending, by the network device, a monitoring request to the terminal device; wherein the monitoring request is used to trigger the terminal device to measure a plurality of measurement objects when running the first model to determine the first index information.

[0119] Optionally, the monitoring request can be sent through Uu interface signaling.

[0120] Optionally, the network device first sends a monitoring request to the terminal device; the terminal device measures a plurality of measurement objects when running the first model to determine the first index information upon receiving the monitoring request; and then the terminal device sends a monitoring request confirmation message to the network device, and the monitoring request message contains the first index information.

[0121] In some application scenarios, the terminal device can use the first model to reduce unnecessary measurement, for example, when the terminal device needs to perform RRM measurement, the terminal device determines one or more first measurement objects based on the first model and measures the one or more first measurement objects, and optionally, the terminal device can not measure other measurement objects except the first measurement objects. When the terminal device receives the monitoring request, the terminal device measures a plurality of measurement objects while determining one or more first measurement objects based on the first model to determine the first index information. By performing global measurement in response to the monitoring request sent by the network device to perform model monitoring, the number of comprehensive measurements can be reduced, thereby reducing the measurement cost.

[0122] In some embodiments, the monitoring request is further used to indicate a first control parameter related to the monitoring of the first model. Optionally, the terminal device performs the monitoring of the first model based on the first control parameter.

[0123] In some embodiments, the first control parameter includes a monitoring period. The monitoring period is, for example, 30 seconds, 60 seconds, etc., and within the monitoring period, the terminal device measures a plurality of measurement objects when running the first model.

[0124] In some embodiments, the first control parameter can further include one or more of a number of monitoring periods, a monitoring condition, and a threshold parameter related to monitoring. For example, the network device issues a monitoring request to trigger the terminal device to determine the first index information in multiple monitoring periods, so that the network device can obtain more accurate monitoring data. The number of monitoring periods can be included in the monitoring request. For another example, after the network device issues the monitoring request, the terminal device can perform monitoring when the monitoring condition is met. The monitoring condition can be indicated in the monitoring request. For another example, the monitoring request issued by the network device can indicate that the terminal device reports the first index information when the measurement result is greater than or less than a certain threshold parameter. The monitoring request can include an indication of the threshold parameter.

[0125] In some embodiments, the terminal device can use the first model when in an RRC connected state (RRC_CONNECTED) to determine a first measurement object based on the first model, perform switching based on measurement of the first measurement object, or perform a secondary cell group change (SCG change) procedure when the terminal device is configured with dual connectivity. The terminal device in the RRC connected state can receive a monitoring request sent by the network device through a Uu interface and send the first index information to the network at the end of the monitoring period.

[0126] In some embodiments, the terminal device can use the first model when in an inactive state (RRC_INACTIVE) or an idle state (RRC_IDLE) to determine a first measurement object based on the first model, perform cell reselection based on measurement of the first measurement object. The terminal device can save the execution results required for model monitoring locally and send the first index information when entering the RRC connected state again. That is, in some embodiments, the terminal device sends the first index information to the network device, including: the terminal device sends the first index information to the network device when entering the RRC connected state; wherein the first index information is obtained by the terminal device based on measurement when in the inactive state or the idle state.

[0127] Correspondingly, in some embodiments, the network device receives the first index information from the terminal device, including: the network device receives the first index information from the terminal device when the terminal device enters the RRC connected state; wherein the first index information is obtained by the terminal device based on measurement when in the inactive state or the idle state.

[0128] Optionally, when the terminal device is in the inactive state or the idle state, the first model is run based on the first model and the overall measurement of the plurality of measurement objects to obtain the first index information, when the terminal device enters the RRC connected state again, the terminal device can send the first indication information to the network device, the first indication information being used to indicate that the first index information is saved. The network device can send the second indication information to the terminal device when receiving the first indication information, the second indication information being used to instruct the terminal device to report the first index information. Then, the terminal device sends the first index information to the network device. In this way, the monitoring of the first model used in the inactive state or the idle state can be realized.

[0129] In some embodiments, the communication method performed by the terminal device can further include: the terminal device receiving configuration information from the network device; wherein the configuration information is used to indicate the second control parameter of the first model.

[0130] Correspondingly, in some embodiments, the communication method performed by the network device can further include: the network device sending configuration information to the terminal device; wherein the configuration information is used to indicate the second control parameter of the first model.

[0131] The transmission of the above-mentioned configuration information can be realized before the terminal device determines the first measurement object that needs to be preferentially measured in the plurality of measurement objects based on the first model. Specifically, when the network device decides to let the terminal device start the first model, the network device can configure some parameters through the configuration information to control the terminal device to run the first model for inference. In this way, the first model can be run according to the network configuration, and the network performance can be guaranteed.

[0132] In some embodiments, the second control parameter includes the hyperparameter of the first model and / or the measurement object range to which the first model is applied.

[0133] Exemplarily, the hyperparameter of the first model can include the weight parameter, the threshold parameter and the like required for the running of the first model. For example, if the first model is an algorithm based on reinforcement learning, the reward value (Reward) needs to be calculated based on some hyperparameters in reinforcement learning, and the hyperparameter of the first model can include the hyperparameter used to calculate the reward value.

[0134] Exemplarily, if the first model is applied to determine the first cell among a plurality of cells, the measurement object range to which the first model is applied can include a frequency point / frequency, and accordingly, the first model is applied to determine the first cell among a plurality of cells at the frequency point / frequency. If the first model is applied to determine the first beam among a plurality of beams, the measurement object range to which the first model is applied can include a cell identifier, and accordingly, the first model is applied to determine the first beam among a plurality of beams of a cell corresponding to the cell identifier.

[0135] In some embodiments, the configuration information can be carried by RRC signaling, a MAC CE, or downlink control information (DCI). For example, when the terminal device is in an RRC connected state, the configuration information can be carried by RRC signaling, a MAC CE, or DCI.

[0136] In some embodiments, when the terminal device is in an inactive state or an idle state, the configuration information is carried by an RRC connection release message or a broadcast system message.

[0137] Exemplarily, the configuration information can be transmitted by the network device through an RRC connection release message when releasing the RRC connection, and the terminal device determines the first measurement object using the first model based on the configuration information and performs measurement on the first measurement object when in the inactive state or the idle state.

[0138] Exemplarily, the configuration information can be broadcast through a system message when the terminal device is in an inactive state or an idle state, and the terminal device determines the first measurement object using the first model based on the configuration information and performs measurement on the first measurement object when in the inactive state or the idle state. Optionally, if the cell in which the terminal device camps does not support determining the first measurement object that needs to be preferentially measured using the first model, the configuration information is not broadcast in the cell.

[0139] In some embodiments, the communication method performed by the terminal device can further include: the terminal device sending capability information to the network device; wherein the capability information is used to indicate that the terminal device supports the first model.

[0140] Correspondingly, in some embodiments, the communication method performed by the network device can further include: the network device receiving capability information from the terminal device; wherein the capability information is used to indicate that the terminal device supports the first model.

[0141] Optionally, the capability information can be carried by user equipment capability transfer (UE capability transfer) signaling. That is, the network device can acquire the capability of the terminal device to reduce the measurement object by using the "UE capability transfer" procedure framework.

[0142] In some embodiments, the capability information is reported per terminal device (per UE), or per frequency range (per FR), or per band.

[0143] Optionally, the terminal device reports the capability information per terminal device, that is, the terminal device reports the capability information per UE, that is, the capability is valid for all frequency ranges (FR), such as FR1, FR2 and FR3.

[0144] Optionally, the terminal device reports the capability information per frequency range, that is, the terminal device reports the capability information per FR, that is, the capability can have different capabilities for different FR. For example, part of the FR supports using the first model, and part of the FR does not support using the first model. Optionally, the capability information can include frequency range information of the terminal device supporting the first model.

[0145] Optionally, the terminal device reports the capability information per band, that is, the terminal device reports the capability information per band, that is, the capability can have different capabilities for different bands. For example, part of the band supports using the first model, and part of the band does not support using the first model. Optionally, the capability information can include band information of the terminal device supporting the first model.

[0146] In some embodiments, the capability information includes the granularity of the measurement object supporting the first model.

[0147] In some embodiments, the granularity of the measurement object includes at least one of frequency, cell and beam.

[0148] For example, if the capability information indicates that the granularity of the measurement object supporting the first model includes frequency (per frequency), the terminal device can determine part of the frequencies as the first frequency in the multiple frequencies and preferentially perform measurement.

[0149] For example, if the capability information indicates that the granularity of the measurement object supporting the first model includes cell (per cell), the terminal device can determine part of the cells as the first cell in the multiple cells and preferentially perform measurement.

[0150] Exemplarily, if the granularity of the measurement object of the first model indicated in the capability information includes per beam, the terminal device can determine part of the beams as the first beams in the multiple beams, and perform measurement preferentially.

[0151] Optionally, the different granularities can be complementary to each other, or in other words, the granularity of the measurement object of the first model in the capability information can include multiple levels. For example, per cell and per frequency can simultaneously support the first model. This means that the terminal device supports selecting individual frequency points for measurement in multiple frequency points, and selecting part of the cells for measurement in the selected frequency points. In specific implementation, a nested architecture or a hybrid architecture can be adopted. The implementation manners of the nested architecture and the hybrid architecture can refer to the foregoing embodiments, and will not be described herein.

[0152] In some embodiments, the communication method performed by the terminal device can further include: receiving, by the terminal device, model-related information from the network device; wherein the model-related information is used by the terminal device to determine the first model.

[0153] In some embodiments, the communication method performed by the network device can further include: sending, by the network device, model-related information to the terminal device; wherein the model-related information is used by the terminal device to determine the first model.

[0154] Exemplarily, the model-related information can include any information capable of determining the first model, such as one or more of the following: parameters, an identification (ID), a training data set, and the like of the first model. In this way, the network device and the terminal device can align the understanding of the first model, so as to facilitate the network device to accurately determine the performance of the first model according to the first index information.

[0155] In some embodiments, the model-related information is further used to indicate meta information of the first model. The meta information includes some key information of the first model.

[0156] In some embodiments, the meta information includes one or more of the following:

[0157] an RRC state to which the first model is applicable;

[0158] a range of measurement objects to which the first model is applicable;

[0159] a granularity of the measurement objects to which the first model is applicable;

[0160] a range of hyperparameters of the first model;

[0161] a determination manner of a reward value in the first model.

[0162] Exemplarily, the meta information can comprise a RRC state to which the first model is applicable and a range of measurement objects to which the first model is applicable; wherein the RRC state to which the first model is applicable can comprise at least one of a connected state, an inactive state and an idle state; and the range of measurement objects to which the first model is applicable can comprise a frequency range to which the first model is applicable, a cell range (e.g. cells on one or more specific frequencies) or a beam range (e.g. beams on one or more specific cells) and the like. Alternatively, the meta information can comprise the RRC state to which the first model is applicable, and the range of measurement objects to which the first model is applicable can be known by the terminal device through other ways, e.g. based on the configuration information issued by the network device.

[0163] Exemplarily, the meta information can comprise a granularity of measurement objects to which the first model is applicable, e.g. at least one of a frequency, a cell and a beam. The granularity can be achieved with reference to the granularity in the capability information in the foregoing embodiments, which will not be repeated here. Alternatively, the terminal device can also know the granularity of measurement objects to which the first model is applicable through other ways.

[0164] Exemplarily, the meta information can comprise a range of hyperparameters of the first model. For example, a range or a reasonable range of a threshold parameter and / or a weight parameter used for determining the reward value in the first model. It can be understood that the meta information can comprise a range of a combination of hyperparameters of the first model, e.g. considering multiple hyperparameters as a combination, corresponding to a group of hyperparameter ranges and an index, the model-related information can contain the index of the group of hyperparameter ranges.

[0165] Exemplarily, the meta information can comprise a determination manner of the reward value, e.g. comprising a calculation formula, an algorithm or an element (e.g. a measurement result, a change rate of a measurement result) used for determining the reward value and the like.

[0166] It can be understood that the meta information in the model-related information can comprise one or more of the above information, and in actual application, the type of the meta information can be determined according to system convention, protocol convention or network configuration and the like, which will not be listed one by one here for the sake of brevity.

[0167] In some embodiments, the first model can be a model based on a bandit arm of a reinforcement learning algorithm. Specifically, the first model is based on reward values of a plurality of measurement objects to determine a first measurement object in the plurality of measurement objects.

[0168] Alternatively, the reward value of each measurement object can be determined based on a measurement result of the measurement object.

[0169] Optionally, the measurement or non-measurement can be regarded as an action in the reinforcement learning algorithm, and the reward value in the reinforcement learning algorithm is determined based on the measurement result of each measurement object. In this way, for each measurement object, the first model outputs / predicts the action corresponding to the measurement object based on the reward value of the measurement object (optionally, the reward value of multiple measurement objects can also be used), and if the action is measurement, the measurement object is determined as the first measurement object that needs to be measured preferentially. By performing the measurement, the reward value of each measurement object in the multiple measurement objects is determined, and the next action is output. Optionally, the first model maximizes the reward value in multiple action predictions, so that the selection of the first measurement object can be continuously optimized.

[0170] In some embodiments, the reward value of the first measurement object is determined based on the measurement result of the first measurement object and / or the change rate of the measurement result of the first measurement object. That is, the communication method can further include: in the case that the terminal device measures the first measurement object, the terminal device updates the reward value of the first measurement object based on the measurement result of the first measurement object and / or the change rate of the measurement result of the first measurement object.

[0171] Optionally, for the first measurement object whose action is measurement, the reward value can be an increasing function of the measurement result (such as RSRP / RSRQ) of the first measurement object, or an increasing function of the change rate of the measurement result of the first measurement object. Wherein, the change rate of the measurement result of the first measurement object can be the difference between the current measurement result of the first measurement object and the measurement result of the first measurement object in the last evaluation period. Here, one evaluation period can be understood as one algorithm period.

[0172] According to the above embodiments, the terminal device updates the reward value of the first measurement object based on the measurement result of the first measurement object and / or the change rate of the measurement result of the first measurement object, which can make the measurement object with good measurement result and fast growth of measurement result obtain greater reward, thereby facilitating the measurement object to be selected as the first measurement object in the next algorithm period, improving the proportion of the first measurement object being the best measurement object, and thus improving the performance of the first model.

[0173] In some embodiments, the reward value of the first measurement object is determined based on the weighted calculation result of the difference and the change rate between the measurement result of the first measurement object and the measurement result of the serving cell; the change rate is the difference between the current measurement result of the first measurement object and the measurement result of the first measurement object in the last evaluation period.

[0174] Exemplarily, the above weighted calculation result can be defined as:

[0175] s * (RSRP n (t0) - RSRP s (t0)) + (1 - s) * (RSRP n (t0) - RSRP n (t0-T));

[0176] wherein RSRP n represents the measurement result of the first measurement object; RSRP s represents the measurement result of the serving cell; t0 represents the current time, and T represents the evaluation period, RSRP n (t0) is the measurement result of the first measurement object at the current time, RSRP s (t0) is the measurement result of the serving cell at the current time, RSRP n (t0-T) is the measurement result of the first measurement object in the last evaluation period, and s is a weight parameter.

[0177] Optionally, the reward value of the first measurement object can be obtained by normalizing the above weighted calculation result. By normalization, the reward values of the measurement objects with different measurement times can be comparable.

[0178] For example, in each evaluation period, the current reward value Reward(k+1) of the first measurement object can be defined as:

[0179] Reward(k+1)=((reward(k)*k+s*(RSRP_n(t0)-RSRP_s(t0))+(1-s)*(RSRP_n(t0)-RSRP_n(t0-T))) / (k+1);

[0180] wherein k is the cumulative evaluation times.

[0181] In some embodiments, the reward value of a second measurement object which is not measured in the plurality of measurement objects is unchanged. That is, the communication method can further include: in a case where the terminal device does not measure the second measurement object, the terminal device keeps the reward value of the second measurement object unchanged.

[0182] Optionally, in the first model based on the reinforcement learning algorithm, the first model can also be determined in combination with a greedy algorithm.

[0183] In some embodiments, the first model determines the first measurement object from the plurality of measurement objects based on the reward values of the plurality of measurement objects in a case where the first random number is less than a first value. Optionally, the first value can be a preset threshold value, or a numerical value determined based on configuration information or model-related information sent by the network device.

[0184] The first value can be understood as a hyperparameter of the greedy algorithm. By setting the first model to determine the first measurement object from the plurality of measurement objects based on the reward value when the first random number is less than the first value, and to randomly select the first measurement object from the plurality of measurement objects when the first random number is greater than or equal to the first value, the terminal device can measure as many measurement objects as possible in a plurality of algorithm cycles, so as to prevent the best measurement object from being ignored due to the low reward value and improve the performance of the first model.

[0185] In some embodiments, the hyperparameters of the first model at least include a third control parameter used to determine the reward value.

[0186] Exemplarily, the third control parameter can include a weight parameter (for example, s) used to determine the weighted calculation result, the first value, the maximum value of the number of first measurement objects, and the like.

[0187] In some embodiments, the measurement object with a high reward value in the plurality of measurement objects is preferentially determined as the first measurement object.

[0188] Optionally, the first model can select the top N measurement objects with the highest reward value from the plurality of measurement objects as the first measurement object. Alternatively, the first model processes the input reward value based on a neural network to obtain the action (measurement or non-measurement) corresponding to the measurement object, and the neural network is trained to limit the measurement object with a high reward value to the first measurement object.

[0189] It can be seen that, in the embodiments of the present application, in order to reduce RRM measurement, the solution is to introduce an AI / ML algorithm, which adopts the idea of reinforcement learning algorithm (bandit arm) in the field of artificial intelligence. In order to facilitate understanding of the above technical solutions, a specific application example is provided as follows.

[0190] 1. The measurement of a certain measurement object, such as a certain cell or a certain beam in a cell, is regarded as a bandit arm. Here, the certain cell refers to a neighboring cell, which can belong to the same frequency as the serving cell, or different frequencies of the same RAT, or different frequencies between different RATs. The measurement refers to L1 beam level measurement and / or L3 cell level measurement, and the measurement can also be L1 cell level measurement and / or L3 beam level measurement.

[0191] 2. The action (action) space of each bandit arm of the algorithm is:

[0192] Action_1: Measure the cell;

[0193] Action_2: Do not measure the cell.

[0194] 3. When action_1 is taken for a cell, the UE gets the measurement result of the cell or the beam, such as L1 or L3 RSRP. Assuming that the measurement result of the serving cell is expressed as RSRP_s (here, RSRP is taken as the measurement quantity, and RSRQ or SINR can also be taken), and the measurement result of the neighboring cell is expressed as RSRP_n, the Reward(RSRP_S, RSRP_n, s) function is an increasing function of RSRP_n and the rate of change of RSRP_n in the time domain, that is, the higher the RSRP and the faster the growth of the neighboring cell, the greater the reward obtained by the neighboring cell, where the parameter s is a hyperparameter used to balance the contribution of RSRP_n and the rate of change of RSRP_n to the result of the Reward function, and the value range of s is [0, 1]. Assuming that the same neighboring cell is measured k times, and the reward of the current record is reward(k), then the current reward can be defined as follows after the latest measurement is made:

[0195] Reward(k+1) = ((reward(k)*k + s*(RSRP_n(t0) - RSRP_s(t0)) + (1-s)*(RSRP_n(t0) - RSRP_n(t0-T)) / (k+1);

[0196] wherein:

[0197] t0 represents the current time; T represents the evaluation period; s represents the weight parameter; and k represents the cumulative evaluation times.

[0198] In the definition of the above Reward, the average value of k evaluation results is used for the purpose of normalization, so as to make the rewards of neighboring cells with different times comparable.

[0199] When action_2 is taken for a cell, the reward of the cell or the beam remains unchanged. The initial value of the reward of all measurement objects is the same, such as 0.

[0200] FIG. 6 is a schematic diagram of the measurement results of the cells in the present application example. It should be noted that, as shown in FIG. 6, the signal change trend of the neighboring cell can be downward (for example, the change trend of the neighboring cell N_cell_2 is downward after t0+T), and the measurement result of the neighboring cell can be lower than that of the serving cell (for example, the measurement results of the neighboring cells N_cell_1 and N_cell_2 are both lower than that of the serving cell S_cell at t-0), so the reward can be a negative value.

[0201] This algorithm can be expressed as:

[0202] Step 1: UE receives the measurement task from the network, such as the measurement object is the current serving frequency, which is equivalent to the measurement object is each cell on the current serving frequency. UE attempts to detect the frequency, and assumes that the detected neighboring cells are ni, i > 0. UE initializes the bandit arm algorithm, such as the hyperparameter s = 0.5 in the algorithm, the evaluation period is 1.2 seconds (which is usually an integer multiple of the measurement period), the hyperparameter eps = 0.05 of the greedy selection algorithm, the maximum number of simultaneously measured neighboring cells N is selected, and the Reward of each detected cell is set to 0, and the number k = 0.

[0203] Step 2: Run the following neighboring cells for measurement:

[0204] If the algorithm stopping condition is met:

[0205] Then the algorithm stops;

[0206] Otherwise, if the running time of the algorithm is less than a certain time (such as 500 milliseconds):

[0207] Randomly select N neighboring cells from the detected cells for measurement;

[0208] Otherwise,

[0209] UE takes a random number less than 1;

[0210] If the random number is less than eps:

[0211] Then UE selects the neighboring cells with Reward in the top N for measurement;

[0212] Otherwise,

[0213] UE randomly selects N neighboring cells from the detected cells for measurement;

[0214] UE calculates the Reward value of the selected cell according to the measurement result of the cell.

[0215] In the above algorithm, when selecting N neighboring cells, if the number of available cells is less than N, then all the detected neighboring cells are selected for measurement.

[0216] The stopping condition of the above algorithm is an event or a network configured condition. For example, the UE is in RRC_CONNECTED state, then the condition can be “UE is going to leave RRC_CONNECTED state”, or the UE receives a command from the network to stop the algorithm. In RRC_IDLE or RRC_INACTIVE state, the condition can be a timer configured by the network expires, or the UE is informed by the current camped cell that the UE is not allowed to use the measurement mechanism, etc.

[0217] Note that the above algorithm is an example of the application of the bandit arm algorithm, such as the definition of reward. This method can also be applied to different granularity of measurement objects. For example, when there are multiple beams in a cell, if the beam is taken as the granularity of the measurement object, then this method can be used to select part of the beams for measurement to get the best beam. In this case, the value of L1 RSRP is generally used when calculating the reward.

[0218] Alternatively, a frequency can be taken as the granularity of the measurement object, and individual frequency points in the network configured frequency points are selected for measurement. In this case, the rewards of the cells (or top M cells) measured in a frequency can be averaged; or the L3 RSRP measurement values of these cells are first averaged, and then the reward is calculated. An indirect result of the algorithm selecting part of the frequencies is that the measurement gap configuration can be reduced.

[0219] The metrics of the algorithm is used to measure the performance of the algorithm. In the above algorithm, the metrics can be defined as “the proportion of the actual best measurement object in the measurement objects selected by the algorithm”. The “actual best measurement object” refers to the best measurement object that the UE can measure without using the algorithm. For example, the granularity of measurement is a cell, and L3 RSRP is used as the measurement quantity. In each algorithm period, the UE can select 3 cells for measurement by the algorithm. At the same time, the UE can also measure all the monitored neighboring cells without using the algorithm. If the UE finds that the cell with the highest L3 RSRP without using the algorithm is in the 3 cells selected by the algorithm, then the comparison result of this period is 1; otherwise, it is 0. In an estimation period, such as 60 seconds, the proportion of the periods with the result of 1 is the result of the metrics. The higher the proportion, the higher the performance of the algorithm.

[0220] The algorithm in RRC_CONNECTED state and the algorithm in RRC_IDLE / RRC_INACTIVE state are basically consistent in idea, but the specific hyperparameters are likely to be different. Moreover, the main purpose of RRM measurement in RRC_CONNECTED state is for handover (or secondary cell group change (SCG change) procedure when the UE is configured with dual connectivity), and the main purpose of RRM measurement in RRC_IDLE / RRC_INACTIVE state is to complete cell reselection. For the convenience of description, the first model in RRC_CONNECTED state is referred to as Model 1, and the first model in RRC_IDLE / RRC_INACTIVE state is referred to as Model 2.

[0221] The above AI / ML for reducing measurement objects itself needs a number of hyperparameters for control, and the results of UE measurement will directly affect the quality of mobility procedures (handover or cell reselection), so the network needs to monitor such AI / ML models.

[0222] For Model 1, the network control procedure includes:

[0223] Procedure 1: UE capability reporting. The base station can use the "UE capability transfer" procedure framework to obtain the UE's capability for reducing measurement objects. The UE can report according to the granularity of "per UE" or "per FR" or "per band". Per UE means that this capability is valid for all FRs (such as FR1, FR2, FR3), per FR means that different FRs can have different capabilities, some support and some do not support, and per band means that the capability of each band can be different, some support and some do not support. The UE can also report the granularity of measurement objects, such as "per beam" or "per cell" or "per frequency", etc. Different granularities can be complementary to each other. For example, the UE reports support for per cell and per frequency, which means that the UE supports selecting individual frequency points for measurement among multiple frequency points, and then selecting part of the cells for measurement among the selected frequency points. In the specific implementation of the UE, a nested architecture can be used, or a hybrid architecture can be used. The nested architecture means that the algorithm for selecting the measurement object of the lower level can be nested in the algorithm for selecting the measurement object of the higher level or multiple levels. For example, first select a limited number of frequencies, and then select a limited number of cells in each of these frequencies, etc. The hybrid architecture is to complete all the measurement objects of the lowest level in the same step, such as selecting part of the cells for measurement among all the cells in different frequencies.

[0224] Flow 2: Inference configuration. When the network finally decides to let the UE start the mechanism, some parameters need to be configured to control the UE to run the mechanism for inference. For example, the range of the selected measurement objects to apply the mechanism. The common measurement object in the measurement task is the frequency point, so the selected measurement object is the cell in the frequency point. Some hyper-parameters in the algorithm, such as the hyper-parameters in the reward formula, etc.

[0225] Flow 3: Model monitoring. When the network needs to monitor the performance of the algorithm running in the UE, it will send a monitoring request message to the UE through the Uu interface signaling. This message may contain some control parameters required for performance monitoring, such as the monitoring period. After receiving such a message, the UE will perform comprehensive measurements on the detected measurement objects while running the algorithm, thereby obtaining the true best measurement object and obtaining the percentage specified in the metrics. After obtaining the result of this metrics, the UE sends the result to the network through the monitoring request confirmation message.

[0226] Flow 4: Model transmission. After the AI / ML model is trained, it needs to be sent to the UE. At the same time as sending the model to the UE, the network needs to describe some key information about the model, which is generally called meta information. For example, for model 1, the possible meta information is:

[0227] 1. Applicable to RRC_CONNECTED state.

[0228] 2. The range of applicable measurement objects and / or the granularity of measurement objects, which is similar to the description in the UE capability report. The UE may know this information through other means without the model.

[0229] 3. The reasonable range of some hyper-parameters in the algorithm, or the reasonable range of hyper-parameter combinations, etc.

[0230] 4. The definition of reward, etc.

[0231] For model 2, the above flow 1 is not required, and for other flows:

[0232] Flow 2: The parameters need to be broadcast to the UE through system messages. If the parameters are not broadcast in the cell, the cell does not support the model 2.

[0233] Flow 3: The difference from Model 1 is that the model monitoring needs to be performed by the UE itself, and the execution result is kept locally. When the UE enters the RRC_CONNECTED state again, the UE can inform the network that it has run the algorithm and has performance monitoring results, and then the network can require the UE to report the performance indicators.

[0234] Flow 4: Similar to Model 1.

[0235] The biggest advantage of the above application example is that the AI / ML algorithm selects part of the measurement objects for RRM measurement, which can reduce the hardware and software resources invested by the UE in RRM measurement, reduce energy consumption and prolong standby time, reduce the configuration of measurement interval, and thus improve the uplink and downlink traffic of the UE.

[0236] FIG. 7 is a schematic block diagram of a terminal device 700 according to an embodiment of the present application. The terminal device 700 can include:

[0237] The first communication module 710 is configured to send first indicator information to a network device; wherein the first indicator information is used for monitoring of a first model, and the first model is used to determine a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

[0238] In some embodiments, the first indicator information is determined based on measurement results of the plurality of measurement objects.

[0239] In some embodiments, the first indicator information includes first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains a best measurement object.

[0240] In some embodiments, the first communication module 710 is further configured to:

[0241] receive a monitoring request from the network device; wherein the monitoring request is used to trigger the terminal device to perform measurement on the plurality of measurement objects when running the first model to determine the first indicator information.

[0242] In some embodiments, the monitoring request is further used to indicate a first control parameter related to the monitoring of the first model.

[0243] In some embodiments, the first control parameter includes a monitoring period.

[0244] In some embodiments, the first communication module 710 is further configured to:

[0245] In the case of entering the RRC connected state, send the first indicator information to the network device; wherein the first indicator information is obtained based on measurement when the terminal device is in the inactive state or the idle state.

[0246] In some embodiments, the first communication module 710 is further directed to:

[0247] receiving configuration information from the network device; wherein the configuration information is used to indicate the second control parameter of the first model.

[0248] In some embodiments, the second control parameter comprises a hyper-parameter of the first model and / or a range of measurement objects applying the first model.

[0249] In some embodiments, the configuration information is carried by a RRC connection release message or a broadcasted system message when the terminal device is in an inactive state or an idle state.

[0250] In some embodiments, the first communication module 710 is further directed to:

[0251] sending capability information to the network device; wherein the capability information is used to indicate that the terminal device supports the first model.

[0252] In some embodiments, the capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

[0253] In some embodiments, the capability information comprises a granularity of measurement objects supporting the first model.

[0254] In some embodiments, the granularity of measurement objects comprises at least one of a frequency, a cell, and a beam.

[0255] In some embodiments, the first communication module 710 is further directed to:

[0256] receiving model-related information from the network device; wherein the model-related information is used for the terminal device to determine the first model.

[0257] In some embodiments, the model-related information is further used to indicate meta-information of the first model.

[0258] In some embodiments, the meta-information comprises one or more of the following:

[0259] an RRC state to which the first model is applicable;

[0260] a range of measurement objects to which the first model is applicable;

[0261] a granularity of measurement objects to which the first model is applicable;

[0262] a range of hyper-parameters of the first model;

[0263] a determination manner of a reward value in the first model.

[0264] In some embodiments, the first model determines a first measurement object among a plurality of measurement objects based on reward values of the plurality of measurement objects.

[0265] In some embodiments, as shown in FIG. 8, the terminal device 700 can further include a first processing module 810, configured to:

[0266] In a case where the terminal device measures the first measurement object, the reward value of the first measurement object is updated based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object.

[0267] In some embodiments, the reward value of the first measurement object is determined based on a weighted calculation result of a difference between the measurement result of the first measurement object and the measurement result of the serving cell and the change rate; the change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a previous evaluation period.

[0268] In some embodiments, the hyperparameters of the first model at least include a third control parameter used for determining the reward value.

[0269] In some embodiments, as shown in FIG. 9, the terminal device 700 can further include a second processing module 910, configured to:

[0270] In a case where the terminal device does not measure the second measurement object, the reward value of the second measurement object is kept unchanged.

[0271] In some embodiments, the first model determines the first measurement object from the plurality of measurement objects based on the reward values of the plurality of measurement objects in a case where the first random number is less than the first value.

[0272] In some embodiments, the measurement object with a high reward value in the plurality of measurement objects is preferentially determined as the first measurement object.

[0273] The terminal device 700 of the embodiments of the present application can implement the corresponding functions of the terminal device in the method embodiments described above. The processes, functions, implementation manners and beneficial effects of the respective modules (sub-modules, units or components, etc.) in the terminal device 700 can be referred to the corresponding descriptions in the method embodiments described above, which will not be described herein again. It should be noted that the functions described with respect to the respective modules (sub-modules, units or components, etc.) in the terminal device 700 of the embodiments of the present application can be implemented by different modules (sub-modules, units or components, etc.), or can be implemented by the same module (sub-module, unit or component, etc.).

[0274] FIG. 10 is a schematic block diagram of a network device 1000 according to an embodiment of the present application. The network device 1000 can include:

[0275] The second communication module 1010 is configured to receive the first index information from the terminal device; wherein the first index information is used for monitoring the first model by the network device, and the first model is used for determining a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

[0276] In some embodiments, the first index information is determined based on measurement results of the plurality of measurement objects.

[0277] In some embodiments, the first index information comprises first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains the best measurement object.

[0278] In some embodiments, the second communication module 1010 is further configured to:

[0279] send a monitoring request to the terminal device; wherein the monitoring request is used to trigger the terminal device to perform measurement on the plurality of measurement objects when running the first model, so as to determine the first index information.

[0280] In some embodiments, the monitoring request is further used to indicate a first control parameter related to the monitoring of the first model.

[0281] In some embodiments, the first control parameter comprises a monitoring period.

[0282] In some embodiments, the second communication module 1010 is further configured to:

[0283] In a case where the terminal device enters an RRC connected state, receive the first index information from the terminal device; wherein the first index information is obtained based on measurement when the terminal device is in an inactive state or an idle state.

[0284] In some embodiments, the second communication module 1010 is further configured to:

[0285] send configuration information to the terminal device; wherein the configuration information is used to indicate a second control parameter of the first model.

[0286] In some embodiments, the second control parameter comprises a hyperparameter of the first model and / or a range of measurement objects to which the first model is applied.

[0287] In some embodiments, in a case where the terminal device is in the inactive state or the idle state, the configuration information is carried by an RRC connection release message or a broadcast system message.

[0288] In some embodiments, the second communication module 1010 is further configured to:

[0289] receive capability information from the terminal device; wherein the capability information is used to indicate that the terminal device supports the first model.

[0290] In some embodiments, the capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

[0291] In some embodiments, the capability information comprises a granularity of a measurement object supported by the first model.

[0292] In some embodiments, the granularity of the measurement object comprises at least one of a frequency, a cell, and a beam.

[0293] In some embodiments, the second communication module 1010 is further configured to:

[0294] send model-related information to the terminal device, wherein the model-related information is used by the terminal device to determine the first model.

[0295] In some embodiments, the model-related information is further used to indicate meta-information of the first model.

[0296] In some embodiments, the meta-information comprises one or more of:

[0297] an RRC state to which the first model is applicable;

[0298] a range of measurement objects to which the first model is applicable;

[0299] a granularity of measurement objects to which the first model is applicable;

[0300] a range of hyperparameters of the first model;

[0301] a determination manner of a reward value in the first model.

[0302] In some embodiments, the first model determines a first measurement object from a plurality of measurement objects based on reward values of the plurality of measurement objects.

[0303] In some embodiments, the reward value of the first measurement object is determined based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object.

[0304] In some embodiments, the reward value of the first measurement object is determined based on a weighted calculation result of a difference between the measurement result of the first measurement object and a measurement result of a serving cell and a change rate; the change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a previous evaluation period.

[0305] In some embodiments, the hyperparameters of the first model at least comprise a third control parameter used to determine the reward value.

[0306] In some embodiments, a reward value of a second measurement object, which is not measured in the plurality of measurement objects, is unchanged.

[0307] In some embodiments, the first model determines, based on the reward values of the plurality of measurement objects, the first measurement object from the plurality of measurement objects in a case that the first random number is less than the first value.

[0308] In some embodiments, a measurement object with a high reward value in the plurality of measurement objects is preferentially determined as the first measurement object.

[0309] The network device 1000 of the embodiments of the present application can realize the corresponding functions of the network device in the method embodiments described above. The processes, functions, implementation manners and advantages of the respective modules (sub-modules, units or components, etc.) in the network device 1000 can be referred to the corresponding descriptions in the method embodiments described above, which will not be repeated here. It should be noted that the functions described with respect to the respective modules (sub-modules, units or components, etc.) in the network device 1000 of the embodiments of the present application can be realized by different modules (sub-modules, units or components, etc.), or can be realized by the same module (sub-module, unit or component, etc.).

[0310] FIG. 11 is a schematic structural diagram of a communication device 1100 according to the embodiments of the present application. The communication device 1100 includes a processor 1110, which can invoke a computer program from a memory to enable the communication device 1100 to implement the methods in the embodiments of the present application.

[0311] In an implementation manner, the communication device 1100 can further include a memory 1120. The processor 1110 can invoke a computer program from the memory 1120 to enable the communication device 1100 to implement the methods in the embodiments of the present application.

[0312] The memory 1120 can be a separate device independent of the processor 1110, or can be integrated in the processor 1110.

[0313] In an implementation manner, the communication device 1100 can further include a transceiver 1130, and the processor 1110 can control the transceiver 1130 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0314] The transceiver 1130 can include a transmitter and a receiver. The transceiver 1130 can further include an antenna, and the number of antennas can be one or more.

[0315] In an implementation manner, the communication device 1100 can be a network device of the embodiments of the present application, and the communication device 1100 can realize the corresponding processes realized by the network device in the various methods of the embodiments of the present application. For the sake of brevity, the details will not be repeated here.

[0316] In an embodiment, the communication device 1100 can be a terminal device of the embodiments of the present application, and the communication device 1100 can implement the corresponding procedures implemented by the terminal device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0317] FIG. 12 is a schematic structural diagram of a chip 1200 according to an embodiment of the present application. The chip 1200 includes a processor 1210, which can call a computer program from a memory to implement the method in the embodiments of the present application.

[0318] In an embodiment, the chip 1200 can further include a memory 1220. The processor 1210 can call a computer program from the memory 1220 to implement the method executed by the terminal device or the network device in the embodiments of the present application.

[0319] The memory 1220 can be a separate device independent of the processor 1210, or can be integrated in the processor 1210.

[0320] In an embodiment, the chip 1200 can further include an input interface 1230. The processor 1210 can control the input interface 1230 to communicate with other devices or chips, and specifically, can obtain information or data sent by other devices or chips.

[0321] In an embodiment, the chip 1200 can further include an output interface 1240. The processor 1210 can control the output interface 1240 to communicate with other devices or chips, and specifically, can output information or data to other devices or chips.

[0322] In an embodiment, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding procedures implemented by the network device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0323] In an embodiment, the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding procedures implemented by the terminal device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0324] The chip applied to the network device and the terminal device can be the same chip or different chips.

[0325] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.

[0326] The aforementioned processor can be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic device, a transistor logic device, a discrete hardware component, and the like. Among them, the aforementioned general-purpose processor can be a microprocessor or any conventional processor, etc.

[0327] The aforementioned memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM).

[0328] It should be understood that the aforementioned memory is an exemplary but non-limiting description, for example, the memory in the embodiments of the present application can also be a static RAM (SRAM), a dynamic RAM (DRAM), a synchronous DRAM (SDRAM), a double data rate SDRAM (DDR SDRAM), an enhanced SDRAM (ESDRAM), a synch link DRAM (SLDRAM), and a direct memory bus RAM (Direct Rambus RAM, DRRAM), etc. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable type of memory.

[0329] FIG. 13 is a schematic block diagram of a communication system 1300 according to an embodiment of the present application. The communication system 1300 includes a terminal device 1310 and a network device 1320.

[0330] The terminal device 1310 sends first index information to the network device 1320; wherein, the first index information is used for monitoring of the first model, and the first model is used for determining a first measurement object that needs to be measured preferentially from a plurality of measurement objects.

[0331] The network device 1320 receives the first index information from the terminal device 1310.

[0332] The terminal device 1310 can be used to implement the corresponding functions of the terminal device in the above method, and the network device 1320 can be used to implement the corresponding functions of the network device in the above method. For brevity, no longer described here.

[0333] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, all or part can be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, all or part generates a flow or function according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another through wired (such as coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), optical medium (for example, DVD), or semiconductor medium (for example, solid state disk (Solid State Disk, SSD)) and the like.

[0334] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0335] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0336] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method, comprising: a terminal device sending first indicator information to a network device; wherein the first indicator information is used for monitoring of a first model, and the first model is used to determine a first measurement object that needs to be measured preferentially among a plurality of measurement objects.

2. The method of claim 1, wherein, The first indicator information is determined based on measurement results of the plurality of measurement objects.

3. The method of claim 1 or 2, wherein, The first indicator information comprises first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains an optimal measurement object.

4. The method of any one of claims 1-3, wherein, The method further comprises: The terminal device receives a monitoring request from the network device; wherein the monitoring request is used to trigger the terminal device to measure the plurality of measurement objects when running the first model to determine the first indicator information.

5. The method of claim 4, wherein, The monitoring request is also used to indicate a first control parameter related to monitoring of the first model.

6. The method of claim 5, wherein, The first control parameter comprises a monitoring period.

7. The method of any one of claims 1-6, wherein, The terminal device sends the first indicator information to the network device, comprising: The terminal device sends the first indicator information to the network device in a case where the terminal device enters a radio resource management (RRC) connected state; wherein the first indicator information is obtained based on measurement when the terminal device is in an inactive state or an idle state.

8. The method of any one of claims 1-7, wherein, The method further comprises: The terminal device receives configuration information from the network device; wherein the configuration information is used to indicate a second control parameter of the first model.

9. The method of claim 8, wherein, The second control parameter comprises a hyperparameter of the first model and / or a range of measurement objects to which the first model is applied.

10. The method of claim 8 or 9, wherein, In a case where the terminal device is in an inactive state or an idle state, the configuration information is carried by an RRC connection release message or a broadcasted system message.

11. The method of any one of claims 1-10, wherein, The method further comprises: The terminal device sends capability information to the network device; wherein the capability information is used to indicate that the terminal device supports the first model.

12. The method of claim 11, wherein, The capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

13. The method of claim 11 or 12, wherein, The capability information comprises a granularity of a measurement object that supports the first model.

14. The method of claim 13, wherein, The granularity of the measurement object comprises at least one of a frequency, a cell, and a beam.

15. The method of any one of claims 1-14, wherein, The method further comprises: The terminal device receives model-related information from the network device; wherein the model-related information is used by the terminal device to determine the first model.

16. The method of claim 15, wherein, The model-related information is also used to indicate meta information of the first model.

17. The method of claim 16, wherein, The meta information comprises one or more of: An RRC state to which the first model is applicable; A range of measurement objects to which the first model is applicable; A granularity of a measurement object to which the first model is applicable; A range of hyperparameters of the first model; A determination manner of a reward value in the first model.

18. The method of any one of claims 1-17, wherein, The first model determines the first measurement object among the plurality of measurement objects based on reward values of the plurality of measurement objects.

19. The method of claim 18, wherein, The method further comprises: In a case where the terminal device measures the first measurement object, the terminal device updates a reward value of the first measurement object based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object.

20. The method of claim 19, wherein, The reward value of the first measurement object is determined based on a weighted calculation result of a difference between a measurement result of the first measurement object and a measurement result of a serving cell and the change rate; The change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a last evaluation period.

21. The method of claim 20, wherein, The hyperparameters of the first model at least include a third control parameter used for determining the reward value.

22. The method of any one of claims 18-21, wherein, The method further includes: In a case where the terminal device does not measure a second measurement object, the terminal device keeps the reward value of the second measurement object unchanged.

23. The method of any one of claims 18-22, wherein, The first model determines the first measurement object from the multiple measurement objects based on the reward values of the multiple measurement objects in a case where a first random number is less than a first value.

24. The method of any one of claims 18-23, wherein, The measurement object with a high reward value in the multiple measurement objects is preferentially determined as the first measurement object.

25. A communication method, comprising: A network device receives first index information from a terminal device; wherein the first index information is used for the network device to monitor a first model, and the first model is used to determine a first measurement object that needs to be preferentially measured from multiple measurement objects.

26. The method of claim 25, wherein, The first index information is determined based on measurement results of the multiple measurement objects.

27. The method of claim 25 or 26, wherein, The first index information includes first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains an optimal measurement object.

28. The method of any one of claims 25-27, wherein, The method further includes: The network device sends a monitoring request to the terminal device; wherein the monitoring request is used to trigger the terminal device to measure the multiple measurement objects when running the first model to determine the first index information.

29. The method of claim 28, wherein, The monitoring request is also used to indicate a first control parameter related to monitoring of the first model.

30. The method of claim 29, wherein, The first control parameter includes a monitoring period.

31. The method of any one of claims 25-30, wherein, The network device receives first index information from a terminal device, comprising: In a case where the terminal device enters an RRC connected state, the network device receives first index information from the terminal device; wherein the first index information is obtained based on measurement when the terminal device is in an inactive state or an idle state.

32. The method of any one of claims 25-31, wherein, The method further includes: The network device sends configuration information to the terminal device; wherein the configuration information is used to indicate a second control parameter of the first model.

33. The method of claim 32, wherein, The second control parameter includes hyperparameters of the first model and / or a measurement object range to which the first model is applied.

34. The method of claim 32 or 33, wherein, In a case where the terminal device is in an inactive state or an idle state, the configuration information is carried by an RRC connection release message or a broadcast system message.

35. The method of any one of claims 25-34, wherein, The method further includes: The network device receives capability information from the terminal device; wherein the capability information is used to indicate that the terminal device supports the first model.

36. The method of claim 35, wherein, The capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

37. The method of claim 35 or 36, wherein, The capability information includes a granularity of a measurement object that supports the first model.

38. The method of claim 37, wherein, The granularity of the measurement object includes at least one of a frequency, a cell and a beam.

39. The method of any one of claims 25-38, wherein, The method further includes: The network device sends model-related information to the terminal device; wherein the model-related information is used by the terminal device to determine the first model.

40. The method of claim 39, wherein, The model-related information is also used to indicate meta-information of the first model.

41. The method of claim 40, wherein, The meta-information includes one or more of the following: An RRC state to which the first model applies; A range of measurement objects to which the first model applies; A granularity of measurement objects to which the first model applies; A range of hyperparameters of the first model; A determination manner of a reward value in the first model.

42. The method of any one of claims 25-41, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects.

43. The method of claim 42, wherein, The reward value of the first measurement object is determined based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object.

44. The method of claim 43, wherein, The reward value of the first measurement object is determined based on a weighted calculation result of a difference between the measurement result of the first measurement object and a measurement result of a serving cell and the change rate; The change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a previous evaluation period.

45. The method of claim 44, wherein, The hyperparameters of the first model at least include a third control parameter used to determine the reward value.

46. The method of any one of claims 42-45, wherein, A reward value of a second measurement object, which is not measured in the plurality of measurement objects, is unchanged.

47. The method of any one of claims 42-46, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects when a first random number is less than a first value.

48. The method of any one of claims 42-47, wherein, Measurement objects with high reward values in the plurality of measurement objects are preferentially determined as the first measurement object.

49. A terminal device, comprising: a first communication module configured to send first index information to a network device; wherein the first index information is used for monitoring of a first model, and the first model is used to determine a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

50. The terminal device of claim 49, wherein, The first index information is determined based on measurement results of the plurality of measurement objects.

51. The terminal device of claim 49 or 50, wherein, The first index information includes first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains an optimal measurement object.

52. The terminal device of any one of claims 49-51, wherein, The first communication module is further configured to: receive a monitoring request from the network device; wherein the monitoring request is used to trigger the terminal device to measure the plurality of measurement objects when running the first model to determine the first index information.

53. The terminal device of claim 52, wherein, The monitoring request is also used to indicate a first control parameter related to monitoring of the first model.

54. The terminal device of claim 53, wherein, The first control parameter includes a monitoring period.

55. The terminal device of any one of claims 49-54, wherein, The first communication module is further configured to: in a case of entering an RRC connected state, send the first index information to the network device; wherein the first index information is obtained based on measurement when the terminal device is in an inactive state or an idle state.

56. The terminal device of any one of claims 49-55, wherein, The first communication module is further configured to: receive configuration information from the network device; wherein the configuration information is used to indicate a second control parameter of the first model.

57. The terminal device of claim 56, wherein, The second control parameter includes a hyperparameter of the first model and / or a measurement object range to which the first model applies.

58. The terminal device of claim 56 or 57, wherein, The configuration information is carried by an RRC connection release message or a broadcast system message when the terminal device is in an inactive state or an idle state.

59. The terminal device of any one of claims 49-58, wherein, The first communication module is further configured to: send capability information to the network device, wherein the capability information is used to indicate that the terminal device supports the first model.

60. The terminal device of claim 59, wherein, The capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

61. The terminal device of claim 59 or 60, wherein, The capability information includes a granularity of a measurement object that supports the first model.

62. The terminal device of claim 61, wherein, The granularity of the measurement object includes at least one of a frequency, a cell, and a beam.

63. The terminal device of any one of claims 49-62, wherein, The first communication module is further configured to: receive model-related information from the network device, wherein the model-related information is used by the terminal device to determine the first model.

64. The terminal device of claim 63, wherein, The model-related information is further used to indicate meta-information of the first model.

65. The terminal device of claim 64, wherein, The meta-information includes one or more of the following: an RRC state to which the first model applies; a range of measurement objects to which the first model applies; a granularity of measurement objects to which the first model applies; a range of hyperparameters of the first model; a determination manner of a reward value in the first model.

66. The terminal device of any one of claims 49-65, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects.

67. The terminal device of claim 66, wherein, The terminal device further includes a first processing module configured to: update a reward value of the first measurement object based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object, when the terminal device measures the first measurement object.

68. The terminal device of claim 67, wherein, The reward value of the first measurement object is determined based on a weighted calculation result of a difference between the measurement result of the first measurement object and a measurement result of a serving cell and the change rate; The change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a previous evaluation period.

69. The terminal device of claim 68, wherein, The hyperparameters of the first model at least include a third control parameter used to determine the reward value.

70. The terminal device of any one of claims 66-69, wherein, The terminal device further includes a second processing module configured to: keep a reward value of a second measurement object unchanged when the terminal device does not measure the second measurement object.

71. The terminal device of any one of claims 66-70, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects when a first random number is less than a first value.

72. The terminal device of any one of claims 66-71, wherein, Measurement objects with high reward values in the plurality of measurement objects are preferentially determined as the first measurement object.

73. A network device, comprising: a second communication module configured to receive first index information from a terminal device, wherein the first index information is used by the network device to monitor a first model, and the first model is used to determine a first measurement object that needs to be preferentially measured from a plurality of measurement objects.

74. The network device of claim 73, wherein, The first index information is determined based on measurement results of the plurality of measurement objects.

75. The network device of claim 73 or 74, wherein, The first index information includes first proportion information, and the first proportion information is a proportion of a number of times that the first measurement object contains an optimal measurement object.

76. The network device of any of claims 73-75, wherein, The second communication module is further configured to: sending a monitoring request to the terminal device; wherein the monitoring request is used to trigger the terminal device to measure the plurality of measurement objects when running the first model to determine the first index information.

77. The network device of claim 76, wherein, The monitoring request is also used to indicate a first control parameter related to the monitoring of the first model.

78. The network device of claim 77, wherein, The first control parameter includes a monitoring period.

79. The network device of any of claims 73-78, wherein, The second communication module is also used to: receive the first index information from the terminal device in the case that the terminal device enters an RRC connected state; wherein the first index information is obtained based on measurement when the terminal device is in an inactive state or an idle state.

80. The network device of any of claims 73-79, wherein, The second communication module is also used to: send configuration information to the terminal device; wherein the configuration information is used to indicate a second control parameter of the first model.

81. The network device of claim 80, wherein, The second control parameter includes a hyperparameter of the first model and / or a range of measurement objects to which the first model is applied.

82. The network device of claim 80 or 81, wherein, In the case that the terminal device is in an inactive state or an idle state, the configuration information is carried by an RRC connection release message or a broadcast system message.

83. The network device of any of claims 73-82, wherein, The second communication module is also used to: receive capability information from the terminal device; wherein the capability information is used to indicate that the terminal device supports the first model.

84. The network device of claim 83, wherein, The capability information is reported for the terminal device, or for a frequency range, or for a frequency band.

85. The network device of claim 83 or 84, wherein, The capability information includes a granularity of measurement objects that support the first model.

86. The network device of claim 85, wherein, The granularity of measurement objects includes at least one of a frequency, a cell, and a beam.

87. The network device of any of claims 73-86, wherein, The second communication module is also used to: send model-related information to the terminal device; wherein the model-related information is used by the terminal device to determine the first model.

88. The network device of claim 87, wherein, The model-related information is also used to indicate meta information of the first model.

89. The network device of claim 88, wherein, The meta information includes one or more of the following: an RRC state to which the first model is applicable; a range of measurement objects to which the first model is applicable; a granularity of measurement objects to which the first model is applicable; a range of hyperparameters of the first model; a determination manner of a reward value in the first model.

90. The network device of any of claims 73-89, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects.

91. The network device of claim 90, wherein, The reward value of the first measurement object is determined based on a measurement result of the first measurement object and / or a change rate of the measurement result of the first measurement object.

92. The network device of claim 91, wherein, The reward value of the first measurement object is determined based on a weighted calculation result of a difference between the measurement result of the first measurement object and a measurement result of a serving cell and the change rate; The change rate is a difference between a current measurement result of the first measurement object and a measurement result of the first measurement object in a previous evaluation period.

93. The network device of claim 92, wherein, The hyperparameter of the first model at least includes a third control parameter used to determine the reward value.

94. The network device of any of claims 90-93, wherein, A reward value of a second measurement object that is not measured in the plurality of measurement objects is unchanged.

95. The network device of any of claims 90-94, wherein, The first model determines the first measurement object from the plurality of measurement objects based on reward values of the plurality of measurement objects in the case that a first random number is less than a first value.

96. The network device of any of claims 90-95, wherein, The measurement object with a high reward value among the plurality of measurement objects is preferentially determined as the first measurement object.

97. A terminal device comprising: a transceiver for communicating with other devices, a processor for invoking the computer program stored in the memory, so that the terminal device executes the method according to any one of claims 1-24.

98. A network device comprising: a transceiver for communicating with other devices, a processor for invoking the computer program stored in the memory, so that the network device executes the method according to any one of claims 25-48.

99. A chip comprising: a processor for invoking the computer program from the memory, so that the device installed with the chip executes the method according to any one of claims 1-24.

100. A chip comprising: a processor for invoking the computer program from the memory, so that the device installed with the chip executes the method according to any one of claims 25-48.

101. A computer readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 1-24.

102. A computer readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 25-48.

103. A computer program product comprising computer program instructions for causing a computer to perform the method according to any one of claims 1-24.

104. A computer program product comprising computer program instructions for causing a computer to perform the method according to any one of claims 25-48.

105. A computer program for causing a computer to perform the method according to any one of claims 1-24.

106. A computer program for causing a computer to perform the method according to any one of claims 25-48.

107. A communication system comprising: a terminal device for performing the method according to any one of claims 1-24; a network device for performing the method according to any one of claims 25-48.

Images