Communication method, communication device, medium, and program product

Abstract

Embodiments of the present invention provide a communication method, a communication device, a computer-readable storage medium, and a computer program product. The communication method comprises: sending a quality of experience (QoE) report about a terminal device to a second network device, the QoE report being comprised in first information of a first network device, the first information being used for predicting a QoE measurement result when the terminal device is located in the second network device; and receiving predicted QoE information about the terminal device from the second network device, wherein the predicted QoE information comprises the predicted QoE measurement result. In this way, the second network device can predict a local QoE result of the terminal device and then send same to the first network device, such that the first network device and the second network device can recognize possible QoE problems in advance, thereby facilitating improvement of the overall satisfaction provided by a user equipment, and improving the radio resource efficiency.

Description

Communication method, communication device, medium and program product

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on September 28, 2023, with application number 202311295280.9 and invention name “A communication method, communication equipment, medium and program product”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure generally relates to the field of communications, and more particularly to a communication method, a communication device, a computer-readable storage medium, and a computer program product. Background Art

[0003] With technological advancements, artificial intelligence (AI) is increasingly being used in communications. The 3rd Generation Partnership Project (3GPP)'s Release 17 proposes applying AI to new radio (NR) to improve network performance and user experience through intelligent data collection and analysis. Quality of experience (QoE) is a performance metric used to evaluate users' overall subjective perception of the quality and performance (including effectiveness and availability) of devices, networks, systems, applications, or services. It is defined by the user's comfort level with service applications. Operators can use QoE scores to assess video service quality and optimize networks. For some streaming or voice services, signal quality alone cannot fully reflect the user experience. Therefore, collecting measurements from user devices can help optimize the network and enhance the user experience. This type of measurement collection is called QoE measurement collection, also known as application-layer measurement collection. To ensure a good user experience, QoE measurement collection mechanisms need further enhancement.

[0004] Summary of the Invention

[0005] Embodiments of the present application provide a communication method, a communication device, and a computer-readable storage medium, whereby a first network device selects a target cell based on predicted user experience information, and the target network device optimizes resource allocation based on the predicted user experience information, thereby improving overall user satisfaction and wireless resource efficiency.

[0006] In a first aspect of the present application, a communication method is provided. The method includes: sending a Quality of Experience (QoE) report about a terminal device to a second network device, wherein the QoE report includes first information from a first network device, the first information being used to predict a QoE measurement result when the terminal device is connected to the second network device; and receiving predicted QoE information about the terminal device from the second network device, wherein the predicted QoE information includes a predicted QoE measurement result. In this way, the first network device obtains the predicted QoE information, can identify possible QoE issues in advance, and thereby improve wireless resource efficiency.

[0007] In some embodiments, the QoE report includes at least one of the following: a time index; a QoE measurement result; a service type; an identifier of the terminal device; an identifier of the first network device; an identifier of the second network device; an identifier of a cell; a quality of service (QoS) parameter; a radio configuration; resource status information; or a signal quality of the terminal device in the cell of the second network device. Thus, QoE reports containing different contents can be indicated to the second network device.

[0008] In some embodiments, the predicted QoE information further includes at least one of the following: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; or a time index. Thus, the first network device can obtain information related to the QoE result predicted by the UE at the second network device.

[0009] In some embodiments, the method further includes: sending a QoE report to a third network device to which the terminal device can switch. Thus, the first network device can send the QoE report to multiple candidate target network devices. In some embodiments, the method further includes: receiving predicted QoE information about the terminal device from the third network device. Thus, the first network device can obtain predicted QoE information from multiple candidate target network devices. In some embodiments, the method further includes: selecting a target network device to which the terminal device is to switch from the second network device and the third network device based on the predicted QoE information; and sending a first indication to the target network device, wherein the first indication is used to indicate that the terminal device is to switch to the target network device. Thus, the first network device can select an appropriate target network device for the terminal device.

[0010] In some embodiments, selecting a target network device to which the terminal device is to switch from the second network device and the third network device includes selecting the second network device as the target network device. The method further includes receiving at least one of the following information from the second network device: an identifier of the terminal device; a predicted QoE measurement result; or an accuracy of the predicted QoE measurement result. Thus, the first network device can learn the accuracy of the prediction result of the selected target network device.

[0011] In some embodiments, the accuracy indicator is indicated by the first network device to the second network device. Thus, the second network device can provide feedback on the accuracy of the prediction result based on the indicator. In some embodiments, the accuracy indicator is indicated to the second network device in a handover request regarding the terminal device. Thus, the accuracy indicator can be flexibly sent to the second network device.

[0012] In some embodiments, the method of the first network device further includes: receiving a second indication from the second network device if the predicted QoE measurement result is lower than a threshold, wherein the second indication is used to instruct the second network device to reject handover of the terminal device, thereby avoiding providing low-quality service to the user equipment.

[0013] In some embodiments, the prediction of the QoE measurement result of the terminal device under the second network device is performed based on an artificial intelligence / machine learning (AI / ML) model, thereby improving the accuracy and efficiency of the prediction.

[0014] In some embodiments, at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface. Thus, the QoE report or the predicted QoE information can be transmitted between network devices.

[0015] In a second aspect of the present application, a communication method is provided. The method includes: receiving a quality of experience (QoE) report about a terminal device from a first network device, wherein the QoE report includes first information at the first network device, and the first information is used to predict a QoE measurement result when the terminal device is in a second network device; predicting a QoE measurement result based on the QoE report and auxiliary information at the second network device; and sending predicted QoE information about the terminal device to the first network device, wherein the predicted QoE information includes the predicted QoE measurement result. In this way, predicted QoE information can be generated to identify possible QoE issues, thereby improving wireless resource efficiency.

[0016] In some embodiments, predicting the QoE measurement results includes inputting the QoE report and auxiliary information into an artificial intelligence / machine learning (AI / ML) model to obtain predicted QoE measurement results, thereby improving the accuracy and efficiency of the prediction.

[0017] In some embodiments, the QoE report includes at least one of the following: a time index; a QoE measurement result; a service type; an identifier of the terminal device; an identifier of the first network device; an identifier of the second network device; an identifier of a cell; a quality of service (QoS) parameter; a radio configuration; resource status information; or a signal quality of the terminal device in the cell of the second network device. Thus, the second network device can obtain a QoE report containing different contents.

[0018] In some embodiments, the auxiliary information includes at least one of the following: historical resource status information of the second network device; predicted resource status information of the second network device; an identifier of the second network device; an identifier of a cell; a time index; the number of at least one terminal device; radio resource status information; the number of radio resource control (RRC) connections; a historical average signal quality of at least one terminal device; a historical average QoE measurement result of at least one terminal device; or a historical average QoS parameter of at least one terminal device. Thus, the second network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0019] In some embodiments, the auxiliary information further includes at least one of the following: historical resource status information of the second network device; predicted resource status information of the second network device; an identifier of the second network device; an identifier of a cell; a time index; an identifier of the terminal device; a signal quality for the terminal device; a QoE measurement result for the terminal device; or a QoS parameter for the terminal device. Thus, the second network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0020] In some embodiments, the predicted QoE information further includes at least one of the following: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; or a time index. Thus, information related to the QoE result predicted at the second network device can be indicated to the first network device.

[0021] In some embodiments, the method further includes: receiving a first indication from the first network device, wherein the first indication is used to indicate that the terminal device is to switch to the second network device; and performing resource optimization for the terminal device based on the predicted QoE information. Thus, the second network device can optimize resources for the terminal device.

[0022] In some embodiments, resource optimization includes at least one of the following: selection of a handover mode of the terminal device; optimization of random access channel (RACH) resources; or optimization of scheduled transmission resources. Thus, the second network device can optimize resources in multiple ways.

[0023] In some embodiments, the method further includes: receiving measured QoE information from the terminal device; comparing the measured QoE information with predicted QoE information; and, based on the comparison, at least one of updating, training, or monitoring the execution of an AI / ML model used to obtain the predicted QoE measurement result. Thus, the second network device can optimize the model based on the measured QoE information to improve model performance.

[0024] In some embodiments, the method further includes: sending at least one of the following information to the first network device: an identifier of the terminal device; a predicted QoE measurement result; or an accuracy of the predicted QoE measurement result. Thus, the accuracy of the predicted QoE measurement result can be indicated to the first network device.

[0025] In some embodiments, the accuracy indicator is indicated by the first network device to the second network device. Thus, the second network device can provide feedback on the accuracy of the prediction result based on the indicator. In some embodiments, the accuracy indicator is indicated to the second network device in a handover request regarding the terminal device. Thus, the accuracy indicator can be flexibly sent to the second network device.

[0026] In some embodiments, the method further includes: based on determining that the predicted QoE measurement result is lower than a threshold, sending a second indication to the first network device, the second indication being used to instruct the second network device to reject handover of the terminal device, thereby avoiding providing low-quality service to the user equipment.

[0027] In some embodiments, at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface. Thus, the QoE report or the predicted QoE information can be transmitted between network devices.

[0028] In a third aspect of the present application, a communication method is provided. The method includes: sending a request message to a second network device for requesting auxiliary information at the second network device, wherein the auxiliary information is used to predict a quality of experience (QoE) measurement result when the terminal device is under the second network device; receiving the auxiliary information from the second network device; predicting the QoE measurement result based on the auxiliary information and a QoE report, wherein the QoE report includes information at the first network device for predicting the QoE measurement result; and sending predicted QoE information about the terminal device to the second network device, wherein the predicted QoE information includes the predicted QoE measurement result. In this way, predicted QoE information can be generated for identifying possible QoE issues, thereby improving wireless resource efficiency.

[0029] In some embodiments, predicting the QoE measurement results includes inputting the QoE report and auxiliary information into an artificial intelligence / machine learning (AI / ML) model to obtain predicted QoE measurement results, thereby improving the accuracy and efficiency of the prediction.

[0030] In some embodiments, the request message includes at least one of the following: a measurement identifier identifying the assistance information request process; an identifier of the second network device; an identifier of the cell; a list of at least one terminal device identifier selected by the first network device; a service type; a third indication of the content of the assistance information; or time information for the assistance information. Thus, the first network device can request assistance information in a variety of ways.

[0031] In some embodiments, the auxiliary information includes at least one of the following: a measurement identifier; an identifier of the second network device; an identifier of a cell; a list of at least one terminal device identifier; a service type; the content of the auxiliary information indicated in the third indication; a fourth indication of unsupported content of the auxiliary information; or a time index. Thus, the first network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0032] In some embodiments, the auxiliary information includes at least one of the following: historical QoE information; predicted QoE information; historical resource status information; predicted resource status information; QoS parameters; wireless configuration; historical signal quality; or predicted signal quality. Thus, the first network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0033] In some embodiments, the QoE report includes at least one of the following: a time index; a QoE measurement result; a service type; an ID of a terminal device; an ID of a first network device; an ID of a second network device; an ID of a cell; a Quality of Service (QoS) parameter; a radio configuration; resource status information; or a signal quality of the terminal device in the cell of the second network device. Thus, the first network device can predict the QoE measurement result based on QoE reports containing different content.

[0034] In some embodiments, the predicted QoE information further includes at least one of the following: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; or a time index. Thus, the first network device can obtain information related to the predicted QoE result.

[0035] In some embodiments, the method further includes: sending a request message to a third network device to which the terminal device can be switched. Thus, the first network device can send the request message to multiple candidate target network devices. In some embodiments, the method further includes: receiving auxiliary information from the third network device. Thus, the first network device can obtain auxiliary information from multiple candidate target network devices.

[0036] In some embodiments, sending the predicted QoE information to the second network device includes: selecting a target network device to which the terminal device is to switch from the second network device and the third network device based on the predicted QoE information; and sending the predicted QoE information to the second network device. Thus, the first network device can select an appropriate target network device for the terminal device.

[0037] In some embodiments, the method further includes: sending a first indication to the second network device, wherein the first indication is used to indicate that the terminal device is to be switched to the second network device. This notifies the second network device that the terminal device is to be switched locally. In some embodiments, the method further includes: receiving at least one of the following information from the second network device: an identifier of the terminal device; a predicted QoE measurement result; or the accuracy of the predicted QoE measurement result. Based on this information, at least one of updating, training, or monitoring the AI / ML model used to obtain the predicted QoE measurement result is performed. This improves the accuracy and efficiency of the prediction.

[0038] In some embodiments, at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface. Thus, the QoE report or the predicted QoE information can be transmitted between network devices.

[0039] In a fourth aspect of the present application, a communication method is provided. The method includes: receiving a request message from a first network device for requesting auxiliary information from a second network device, wherein the auxiliary information is used to predict a quality of experience (QoE) measurement result when the terminal device is on the second network device; based on receiving the request message, sending the auxiliary information to the first network device; and receiving predicted QoE information about the terminal device from the first network device, wherein the predicted QoE information includes a predicted QoE measurement result. In this way, the predicted QoE information can be generated to assist in identifying possible QoE issues, thereby improving wireless resource efficiency.

[0040] In some embodiments, the request message includes at least one of the following: a measurement identifier identifying the assistance information request procedure; an identifier of the second network device; an identifier of the cell; a list of at least one terminal device identifier selected by the first network device; a service type; a third indication of the content of the assistance information; or time information for the assistance information. Thus, the first network device can request assistance information in a variety of ways.

[0041] In some embodiments, the auxiliary information includes at least one of the following: a measurement identifier; an identifier of the second network device; an identifier of a cell; a list of at least one terminal device identifier; a service type; the content of the auxiliary information indicated in the third indication; a fourth indication of unsupported content of the auxiliary information; or a time index. Thus, the first network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0042] In some embodiments, the auxiliary information includes at least one of the following: historical QoE information; predicted QoE information; historical resource status information; predicted resource status information; QoS parameters; wireless configuration; historical signal quality; or predicted signal quality. Thus, the first network device can predict the QoE measurement result based on the auxiliary information containing different contents.

[0043] In some embodiments, the predicted QoE information further includes at least one of the following: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; or a time index. Thus, the first network device can obtain information related to the predicted QoE result.

[0044] In some embodiments, the method further includes: receiving a first indication from the first network device, wherein the first indication is used to indicate that the terminal device is to switch to the second network device; and performing resource optimization for the terminal device based on the predicted QoE information. Thus, the second network device can optimize resources for the terminal device.

[0045] In some embodiments, the method further includes: receiving measured QoE information from the terminal device; comparing the measured QoE information with the predicted QoE information; and evaluating the accuracy of the predicted QoE measurement result based on the comparison. Thus, the performance of the model can be evaluated.

[0046] In some embodiments, the method of the second network device further includes: sending at least one of the following information to the first network device: an identifier of the terminal device; a predicted QoE measurement result; or an accuracy of the predicted QoE measurement result. Thus, the accuracy of the predicted QoE measurement result can be indicated to the first network device.

[0047] In some embodiments, the accuracy indicator is indicated by the first network device to the second network device. Thus, the second network device can provide feedback on the accuracy of the prediction result based on the indicator. In some embodiments, the accuracy indicator is indicated to the second network device in a handover request regarding the terminal device. Thus, the accuracy indicator can be flexibly sent to the second network device.

[0048] In some embodiments, the prediction of the QoE measurement result of the terminal device under the second network device is performed based on an artificial intelligence / machine learning (AI / ML) model, thereby improving the accuracy and efficiency of the prediction.

[0049] In some embodiments, the predicted QoE information is transmitted via an Xn interface. Thus, the predicted QoE information can be transmitted between network devices.

[0050] In a fifth aspect of the present application, a communication device is provided. The communication device includes a processor and a memory storing instructions. When executed by the processor, the instructions cause the communication device to perform any method according to any one of the first to fourth aspects and their implementations. In a sixth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed by an electronic device, cause the electronic device to perform any method according to any one of the first to fourth aspects and their implementations.

[0051] In a seventh aspect of the present application, a chip is provided, which includes a processing circuit configured to execute any method of any one of the first to fourth aspects and implementations thereof.

[0052] In an eighth aspect of the present application, a computer program product is provided, which includes instructions, and when executed by an electronic device, the instructions cause the electronic device to perform any method of any one of the first to fourth aspects and their implementations.

[0053] It should be understood that the contents described in the Summary of the Invention are not intended to define the key or important features of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] FIG1A shows a schematic diagram of a communication system in which embodiments of the present disclosure may be implemented.

[0055] FIG1B shows a schematic diagram of a centralized unit (CU)-distributed unit (DU) (CU-DU) architecture related to an embodiment of the present disclosure.

[0056] FIG1C shows a schematic diagram of an AI application framework in NR related to an embodiment of the present disclosure.

[0057] FIG1D shows a schematic diagram of a QoE measurement process related to an embodiment of the present disclosure.

[0058] FIG2 illustrates a first interactive signaling diagram of a communication process according to some embodiments of the present disclosure.

[0059] FIG3 shows a schematic diagram of AI input and output related to an embodiment of the present disclosure.

[0060] FIG4 illustrates a first example process of a communication process according to some embodiments of the present disclosure.

[0061] FIG5 illustrates a second interactive signaling diagram of a communication process according to some embodiments of the present disclosure.

[0062] FIG6 illustrates a second example process of a communication process according to some embodiments of the present disclosure.

[0063] FIG7 shows a schematic flowchart of a method implemented at a first network device according to an embodiment of the present disclosure.

[0064] FIG8 shows a schematic flowchart of a method implemented at a second network device according to an embodiment of the present disclosure.

[0065] FIG9 shows a schematic flowchart of a method implemented at a first network device according to an embodiment of the present disclosure.

[0066] FIG10 shows a schematic flowchart of a method implemented at a second network device according to an embodiment of the present disclosure.

[0067] FIG11 shows a simplified block diagram of an example device of a possible implementation method of an embodiment of the present application.

[0068] FIG12 shows a simplified block diagram of an example device of a possible implementation method of an embodiment of the present application.

[0069] Throughout the drawings, the same or similar reference numerals are used to designate the same or similar components. DETAILED DESCRIPTION

[0070] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0071] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to." The term "based on" should be understood as "based at least in part on." The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment." The terms "first," "second," etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0072] The embodiments of the present disclosure may be implemented according to any suitable communication protocol, including but not limited to cellular communication protocols such as third generation (3G), fourth generation (4G), fifth generation (5G), and future communication protocols (e.g., sixth generation (6G)), wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or developed in the future.

[0073] The technical solutions of the embodiments of the present disclosure are applied to communication systems that comply with any appropriate communication protocols, such as: General Packet Radio Service (GPRS), Global System for Mobile Communications (GSM), Enhanced Data rate for GSM Evolution (EDGE), Universal Mobile Telecommunications Service (UMTS), Long Term Evolution (LTE) system, Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access 2000 (CDMA2000), Time Division-Synchronization Code Division Multiple Access (TD-SCDMA), Frequency Division Duplex (FDD) system, Time Division Duplex (TDD), fifth generation (5G) system (e.g., New Radio (NR)) and future communication systems (e.g., sixth generation (6G) system), etc.

[0074] For illustrative purposes, the embodiments of the present disclosure are described below in the context of a 5G communication system in 3GPP. However, it should be understood that the embodiments of the present disclosure are not limited to this communication system, but can be applied to any communication system with similar problems, such as a wireless local area network (WLAN), a wired communication system, or other communication systems developed in the future.

[0075] The term "terminal" or "terminal device" as used in this disclosure refers to any terminal device capable of wired or wireless communication with network devices or with each other. Terminal devices may sometimes be referred to as user equipment or UE. Terminal devices may be any type of mobile terminal, fixed terminal, or portable terminal. Terminal devices may be various wireless communication devices with wireless communication capabilities. Terminal devices may be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; may also be deployed on water (such as ships); and may also be deployed in the air (such as on aircraft, balloons, and satellites). 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, a wireless terminal device in a smart grid, a wireless terminal in transportation safety, a wireless terminal device in a smart city, a wireless terminal in a smart home, and can also include user equipment (UE), etc.

[0076] The term "network node" or "network device" used in this disclosure refers to a device in a wireless network, an entity or node that can be used to communicate with a terminal device, such as an access network device. An access network device can be a device deployed in a wireless access network to provide wireless communication functions for a mobile terminal, such as a radio access network (RAN) node that connects a terminal device to a wireless network. Currently, some examples of RAN nodes include: gNB, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wifi) access point (AP), integrated access and backhaul (IAB), etc. In a network structure, the network device may also refer to a centralized unit (CU) or a distributed unit (DU), or the network device may also be composed of a CU and a DU. CU and DU can be understood as a division of the base station from a logical function perspective. Among them, the CU and DU can be physically separated or deployed together, and the embodiments of the present application do not specifically limit this. A CU can be connected to a DU, or multiple DUs can share a CU, which can save costs and facilitate network expansion. The division of CU and DU can be based on the protocol stack. One possible way is to deploy the radio resource control (RRC), service data adaptation protocol stack (SDAP) and packet data convergence protocol (PDCP) layer in the CU, and the remaining radio link control (RLC) layer, media access control (MAC) layer and physical layer in the DU.The embodiments of the present application are not limited to the above-mentioned protocol stack segmentation method, and other segmentation methods are also possible. The present application will be further described in detail below with reference to the accompanying drawings. The specific operation methods and functional descriptions in the method embodiments can also be applied to the device embodiments or system embodiments.

[0077] Figure 1A shows a schematic diagram of a communication system 100A in which embodiments of the present disclosure may be implemented. As shown in Figure 1A, system 100A may include a first network device 110, a second network device 120, a third network device 130, and a terminal device 140. The terminal device 140 may have wireless transceiver functionality, capable of communicating (e.g., wirelessly) with one or more network devices of one or more communication systems and receiving network services provided by the network devices, including but not limited to the network devices shown in the figure. For example, the terminal device 140 may be connected to the first network device 110 via an access link. The first network device 110 manages cell 101, the second network device 120 manages cell 102, and the third network device 130 manages cell 103. It should be understood that the cells shown in the figure include but are not limited to the cells shown in the figure. The first network device 110 can communicate with the second network device 120 and the third network device 130. For example, the first network device 110 can communicate directly with the second network device 120 or the third network device 130 via an XN port.

[0078] In some embodiments, the QoE measurement result of terminal device 140 accessing cell 101 under first network device 110 (also referred to as the source station) deteriorates, and first network device 110 determines that it is necessary to hand over terminal device 140 to another network device or cell. Terminal device 140 can be handed over to cell 102 under second network device 120 (also referred to as the target station) or cell 103 under third network device 130.

[0079] It should be understood that the number of terminals and network nodes shown in FIG1A is only an example, and there may be more or fewer terminals, network devices, and cells, and the present disclosure does not impose any limitation thereto.

[0080] In addition, it should be understood that the communication system 100A can be applied to various scenarios. For example, the application scenarios of the communication system 100A include but are not limited to the fourth generation system (4G), the fifth generation system (5G), the new radio (NR) communication system, the non-terrestrial network (NTN) system, and other existing communication systems or future evolved communication systems. In addition, it should also be understood that the above-mentioned communication can follow any appropriate communication technology and corresponding communication standards.

[0081] Figure 1B shows a schematic diagram of a CU-DU architecture 100B related to embodiments of the present disclosure. As shown in Figure 1B , the CU and DU are connected via the F1 interface. The CU, representing the gNB, is connected to the core network via the Ng interface. In embodiments of the present disclosure, the network device may also refer to a centralized unit control plane (CU-CP) node or a centralized unit user plane (CU-UP) node, or the network device may be a CU-CP and a CU-UP. The CU-CP is responsible for control plane functions, primarily including RRC and PDCP-C. PDCP-C is primarily responsible for encryption and decryption, integrity protection, and data transmission of control plane data. The CU-UP is responsible for user plane functions, primarily including SDAP and PDCP-U. SDAP is primarily responsible for processing core network data and mapping flows to bearers. PDCP-U is primarily responsible for encryption and decryption, integrity protection, header compression, sequence number maintenance, and data transmission on the data plane. The CU-CP and CU-UP are connected via the E1 interface. The CU-CP, representing the gNB, is connected to the core network via the Ng interface. It is connected to the DU via F1-C (control plane). The CU-UP is connected to the DU via the F1-U (user plane). Of course, another possible implementation is to also include the PDCP-C in the CU-UP.

[0082] The access network equipment mentioned in the embodiments of the present disclosure may be a device including a CU, or a DU, or a device including a CU and a DU, or a device including a control plane CU node (CU-CP node) and a user plane CU node (CU-UP node) and a DU node. The wireless access network equipment and terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on the water surface; they can also be deployed on aircraft, balloons and satellites in the air. The embodiments of the present application do not limit the application scenarios of the wireless access network equipment and terminal equipment.

[0083] The embodiments of the present disclosure can be applied to downlink signal transmission, uplink signal transmission, and device-to-device (D2D) signal transmission. For downlink signal transmission, the transmitting device is a wireless access network device, and the corresponding receiving device is a terminal device. For uplink signal transmission, the transmitting device is a terminal device, and the corresponding receiving device is a wireless access network device. For D2D signal transmission, the transmitting device is a terminal device, and the corresponding receiving device is also a terminal device. The embodiments of the present application do not limit the direction of signal transmission.

[0084] The wireless access network device and the terminal device, as well as the terminal device and the terminal device, can communicate through the licensed spectrum (licensed spectrum), can also communicate through the unlicensed spectrum (unlicensed spectrum), or can also communicate through the licensed spectrum and the unlicensed spectrum at the same time. The wireless access network device and the terminal device, as well as the terminal device and the terminal device, can communicate through the spectrum below 6 gigahertz (GHz), can also communicate through the spectrum above 6G, and can also communicate using the spectrum below 6G and the spectrum above 6G at the same time. The embodiments of the present disclosure do not limit the spectrum resources used between the wireless access network device and the terminal device.

[0085] Figure 1C shows a schematic diagram of an AI application framework 100C in NR according to some embodiments of the present disclosure. As shown in Figure 1C, a data source stores data input from gNBs, gNB-CUs, gNB-DUs, UEs, or other management entities, serving as a database for AI model training and data analysis and inference. The model training host analyzes the training data provided by the data source to generate an optimal AI model. The model inference host uses the AI ​​model to provide reasonable AI-based predictions about network operation based on the data provided by the data source, or to guide the network in making policy adjustments. The relevant policy adjustments are uniformly planned by the execution entity (actor) and sent to multiple network entities for execution. Furthermore, after the relevant policies are applied, the specific network performance is again entered into the database for storage.

[0086] QoE is a performance metric used to evaluate users' overall subjective perception of the quality and performance (including effectiveness and availability) of devices, networks, systems, applications, or services. It is defined by the user's comfort level with service applications. Operators can use QoE scores to assess video service quality and optimize their networks.

[0087] For streaming services or voice services, such as dynamic adaptive streaming over HTTP (DASH), multimedia telephony services for IP Multimedia Subsystem (IMS), and VR services, signal quality alone cannot fully reflect the user experience when using these services. Operators want to understand the user experience so they can better optimize the network to improve it. This type of measurement collection is called QoE measurement collection, also known as application-layer measurement collection.

[0088] The QoE measurement collection function (QMC) supports collecting application layer measurements from UEs. Supported service types include:

[0089] -QoE measurement collection for DASH streaming services;

[0090] -MTSI service QoE measurement and collection;

[0091] -Collect QoE measurements for VR services.

[0092] QoE measurement collection may only be supported in the RRC_CONNECTED state. Both signaling-based and management-based QoE measurement collection are supported. QMC is activated in the gNB through direct configuration from the operation administration and maintenance (OAM) system (management-based activation) or by sending signaling from OAM via 5GC (signaling-based activation), which contains the UE-associated QoE configuration. One or more QoE measurement collection jobs can be activated on a UE per service type, and each QoE measurement configuration is uniquely identified by a QoE reference. When the UE is configured with multi-rate dual connectivity (MR-DC), only the MN can configure the QoE configuration.

[0093] For signaling-based QoE measurement, OAM initiates QoE measurement activation for a specific UE via 5GC, and the gNB receives one or more QoE measurement configurations via UE-associated signaling. The QoE measurement configuration activated via signaling includes a list of application layer measurement configurations and corresponding information collected for QoE measurement, such as QoE reference, service type, MCE IP address, slice range, area range, MDT alignment information, and an indication of available RAN-visible QoE metrics.

[0094] For management-based QoE measurement activation, OAM sends one or more QoE measurement configurations directly to the gNB. The management-based QoE measurement configuration also includes a list of application layer measurement configurations and the corresponding QoE measurement collection information. The gNB selects UEs that meet the QoE measurement capability, area scope, and slice scope.

[0095] The gNB encapsulates the application layer measurement configuration received from the OAM or CN in a transparent container and forwards it to the UE as the application layer configuration in the RRCReconfiguration message (multiple configurations can be included in the same message). The application layer measurement report received from the UE application layer is encapsulated in a transparent container and sent to the network via the Measurement Report application layer message.

[0096] Figure 1D illustrates a schematic diagram of a QoE measurement flow related to an embodiment of the present disclosure. A UE can send multiple application layer measurement reports to the gNB in ​​a single Measurement Report application layer message. To allow transmission of application layer measurement reports exceeding the maximum PDCP SDU size, the gNB can enable segmentation of the Measurement Report application layer message. The RRC identity conveyed in RRC signaling is used to identify application layer measurement configurations and reports between the gNB and the UE. The RRC identity is mapped to a QoE reference in the gNB, and the gNB forwards the application layer measurement report along with the QoE reference to the MCE. The gNB can release one or more application layer measurement configurations from the UE at any time in a single RRCReconfiguration message. The gNB can also configure the UE to report when a QoE measurement session for a particular application layer measurement configuration starts or stops.

[0097] RAN-visible QoE measurements are configured by the gNB to the UE, where a subset of the configured QoE metrics is reported from the UE to the gNB as explicit IEs readable by the gNB. The gNB can leverage RAN-visible QoE measurements for network optimization. RAN-visible QoE measurements are supported for DASH streaming and VR services. The gNB configures RAN-visible QoE measurements to collect all or a subset of available RAN-visible QoE metrics, where an indication of metric availability is received from OAM or 5GC. The set of available RAN-visible QoE metrics is a subset of the metrics that have been configured as part of the QoE measurement configuration encapsulated in an application layer container. The UE may also report, along with the RAN-visible QoE measurement results, the PDU session identifier corresponding to the service being QoE measured.

[0098] RAN-visible QoE measurement can support multiple simultaneous RAN-visible QoE measurement configurations and reports, each of which is identified by the same RRC identifier as the QoE measurement configuration and measurement report. After the UE RRC layer receives the RAN-visible QoE measurement configuration, it forwards the configuration to the application layer, indicating the service type, RRC identifier and period. The RAN-visible QoE configuration can only be configured if there is a corresponding QoE measurement configuration for the same service type configured by the UE. The application layer sends the RAN-visible QoE measurement report associated with the RRC identifier to the AS layer of the UE. If the reporting period is not defined in the RAN-visible QoE configuration, the UE sends the RAN-visible QoE measurement report and the QoE measurement report to the gNB in ​​the same measurement report application layer message, unless a QoE measurement collection suspension indication is received (for example, in the case of RAN overload). When QoE measurement collection is suspended, if no reporting period is defined in the RAN-visible QoE configuration, encapsulated QoE reports are stored at the UE's RRC layer, but RAN-visible QoE reports continue to be reported to the gNB with the configured reporting period for encapsulated QoE reports. When the gNB is configured with a dedicated RAN-visible QoE reporting period, RAN-visible QoE measurements can be reported with a different reporting period than the corresponding encapsulated QoE measurements. The UE application layer can measure RAN-visible QoE metrics based on this reporting period. The gNB can release one or more RAN-visible QoE measurement configurations from the UE at any time in an RRCReconfiguration message.

[0099] In the current QoE mechanism, the QoE measurement configuration of the NG port includes: QoE reference, service type, QMC area range, MCE IP address, QoE measurement status, application layer measurement configuration container, measurement configuration application layer identifier, QMC slice support list, MDT alignment information, and an indication of available RAN-visible QoE metrics.

[0100] Among them, the QoE reference consists of the mobile country code (MCC), the mobile network code (MNC) and the QoE measurement collection function identifier (MCC+MNC+QMC ID), where the MCC and MNC together with the QMC activation request from the management system identify a PLMN containing the management system, and the QMC ID is a 3-byte octet string. The service type indicates the service type of the QoE measurement, which can be DASH streaming, MTSI, or VR. The QMC area range is used to indicate the measurement collection range of the QMC, which can be a cell identifier list, a tracking area (TA) list, a tracking area identity (TAI) list, or a PLMN list. The MCEIP address is the IP address of the entity that receives the QoE measurement report. The QoE measurement status indicates whether the QoE measurement is started, which exists in the case of NG switching. The application layer measurement configuration container contains application layer measurement configurations, which are not visible to the RAN. These include QoE measurement configurations for different services, such as throughput, initial play delay, buffered play time, bandwidth, height, width, bitrate, response time, device information, jitter duration, and desynchronization duration. The measurement configuration application layer identifier indicates the identifier of the application layer measurement configuration. This corresponds to the MeasConfigAppLayerId information element defined in the Uu interface and appears only when the message containing this information element is related to NG-based handover. The QMC slice support list indicates the slice information supported by QMC. The MDT alignment information indicates the MDT measurements that require alignment. The available RAN-visible QoE metrics indication indicates whether the gNB can collect RAN-visible QoE measurements.

[0101] The QoE measurement configuration for the Uu interface includes: service type, application layer measurement configuration container, measurement configuration application layer identifier, and RAN-visible QoE parameter configuration. The RAN-visible QoE parameter configuration includes the number of buffer level entries, operational visibility period, and report play delay media start. The number of buffer level entries specifies the maximum number of buffer level entries that can be reported for RAN-visible application layer measurements. The operational visibility period indicates the reporting period for RAN-visible application layer measurements. The report play delay media start option indicates whether the UE should report media start play delay measured by the RAN-visible application layer.

[0102] The QoE measurement results for the Uu interface include: an application layer measurement configuration identifier, an application layer report container, and RAN-visible QoE measurement results. The RAN-visible QoE measurement results include an application layer buffer level list, media start-up delay, and a PDU session list. The application layer buffer level list represents a list of application layer buffer levels, with each application layer buffer level measured in milliseconds. A value of 0 corresponds to 0ms, a value of 1 corresponds to 10ms, a value of 2 corresponds to 20ms, and so on. If the buffer level exceeds the maximum value of 30,000 (5 minutes), the UE reports 30,000. The media start-up delay is the media start-up application layer delay, measured in milliseconds. A value of 0 corresponds to 0ms, a value of 1 corresponds to 1ms, a value of 2 corresponds to 2ms, and so on. If the media start-up delay exceeds the maximum value of 30,000ms, the UE reports 30,000. The PDU session list contains the identifiers of PDU sessions, or PDU session identifiers, for application data flows subject to RAN-visible application layer measurements.

[0103] The QoE measurement results sent by the gNB to the MCE also include the QoE reference, not the RAN-visible QoE measurement results mentioned above. RAN-visible QoE measurement results are used only for network resource optimization on the RAN side. In traditional QoE mechanisms, RAN / OAM optimizes network resource allocation based on historical QoE measurement results. This results in delayed problem identification, meaning that it is impossible to proactively identify QoE issues and optimize network resource allocation.

[0104] In view of the above research and analysis, an embodiment of the present disclosure provides a communication method. In this method, a quality of experience (QoE) report on a terminal device is sent to a second network device, the QoE report includes first information on a first network device, and the first information is used to predict the QoE measurement result when the terminal device is under the second network device; and predicted QoE information about the terminal device is received from the second network device, wherein the predicted QoE information includes the predicted QoE measurement result. In this way, the second network device can predict the local QoE result of the terminal device and send it to the first network device, thereby enabling the first network device and the second network device to identify possible QoE problems in advance, thereby helping to improve the overall satisfaction of the user device and improve the efficiency of wireless resources.

[0105] FIG2 illustrates a first interactive signaling diagram of a communication process according to some embodiments of the present disclosure. For clarity of discussion and without limitation, process 200 will be discussed in conjunction with FIG1A .

[0106] In process 200, first network device 110 sends 201 a Quality of Experience (QoE) report 203 regarding a terminal device to second network device 120. QoE report 203 includes first information from first network device 110, which is used to predict a QoE measurement result when the terminal device is in the presence of second network device 120. The presence of the terminal device in the presence of second network device 120 may mean that the terminal device is switched to the second network device and is served by the second network device. Accordingly, second network device 120 receives 205 QoE report 203 from first network device 110. Optionally, first network device 110 also sends the QoE report to a third network device to which the terminal device can be switched. It should be understood that the first network device may select multiple candidate network devices, including the second network device and the third network device, and send the QoE report to the multiple candidate network devices.

[0107] For example, the first network device 110 receives a QoE measurement result from a terminal device, and the first network device 110 determines whether to trigger a handover process for the terminal device based on the implementation. For example, when the first network device 110 detects that the QoE measurement result of the terminal device is lower than a certain threshold, it is considered necessary to handover the terminal device to another base station or cell. The first network device 110 can generate a QoE report based on the QoE measurement result received from the terminal device, and then send the QoE report of the terminal device to the candidate network device for the candidate network device to predict the QoE result of the UE on the candidate network device or the cell of the candidate network device. That is, the QoE report can be used as input data for the AI ​​model used to predict QoE in the candidate network device.

[0108] In some embodiments, the QoE report may include a time index, a QoE measurement result, a service type, an identifier (ID) of the terminal device, an identifier of the first network device 110, an identifier of the second network device 120, an identifier of the cell, quality of service (QoS) parameters, a wireless configuration, resource status information, the signal quality of the terminal device in the cell of the second network device 120, or one or more of the above. For example, the QoE measurement result may be a RAN-visible QoE measurement result. The wireless configuration may include dual connectivity (DC) or carrier aggregation (CA), etc. The signal quality may include reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), signal to interference plus noise ratio (SINR), bit error rate, throughput, etc. The contents of the above-mentioned QoE report may have a specific correlation relationship. One possible implementation method is as follows, namely, the RAN-visible QoE measurement results, QoS parameters, wireless configuration of each cell for each service type within a historical time, and the signal quality of the UE in the candidate target cell:

[0109] Continuing with reference to Figure 2, based on the QoE report and the auxiliary information at the second network device 120, the second network device 120 predicts 207 the QoE measurement result. Additionally or alternatively, the prediction of the QoE measurement result of the terminal device under the second network device is performed based on an artificial intelligence / machine learning (AI / ML) model. Optionally, the second network device 120 can input the QoE report and the auxiliary information into the artificial intelligence / machine learning (AI / ML) model to obtain a predicted QoE measurement result. For example, after receiving the QoE report, the second network device 120 triggers the local AI model to predict the QoE parameters of the UE. The predicted QoE parameters in the embodiments of the present application are only for the RAN visible QoE parameters, and do not involve the prediction of the QoE parameters in the application layer report container, because this part is transparently transmitted on the RAN side in the form of a container, that is, it is not visible on the RAN side.

[0110] FIG3 illustrates a schematic diagram of AI input and output related to an embodiment of the present disclosure. A candidate network device (e.g., second network device 120 or third network device) can use an AI model to predict the UE's QoE results, i.e., pQoE metrics, in a candidate target cell based on pQoE auxiliary information (e.g., auxiliary information at second network device 120 or third network device) and historical QoE reports. In the figure, the historical QoE report is the received QoE report 203, i.e., information related to QoE prediction sent by the first network device 110.

[0111] Alternatively, the auxiliary information may include: historical resource status information of the second network device 120, predicted resource status information of the second network device 120, an identifier of the second network device 120, an identifier of the cell, a time index, the number of at least one terminal device, wireless resource status information, the number of wireless resource control RRC connections, the historical average signal quality of at least one terminal device, the historical average QoE measurement result of at least one terminal device, the historical average QoS parameter of at least one terminal device, or one or more of the above.

[0112] Since the terminal device has not established a connection with the candidate network device, the candidate network device can associate the terminal device's possible performance in the candidate network device based on the historical UE average signal quality and the historical UE average RAN visible QoE results. One possible implementation of the auxiliary information is as follows:

[0113] Alternatively, the auxiliary information may further include: historical resource status information of the second network device 120, predicted resource status information of the second network device 120, an identifier of the second network device 120, an identifier of a cell, a time index, an identifier of a terminal device, signal quality for the terminal device, a QoE measurement result for the terminal device, a QoS parameter for the terminal device, or one or more of the above. Another possible implementation of the auxiliary information may involve detailed terminal device information, i.e., information of the terminal device in the second network device 120 that may be associated with QoE, as follows:

[0114] 2 , the second network device 120 sends 210 predicted QoE information 213 about the terminal device to the first network device 110, where the predicted QoE information 213 includes a predicted QoE measurement result. Accordingly, the first network device 110 receives 215 the predicted QoE information 213 about the terminal device from the second network device 120. Optionally, the first network device 110 receives the predicted QoE information about the terminal device from a third network device. Additionally, the predicted QoE information may include an identifier of the terminal device, an identifier of the second network device, a service type, an identifier of a cell, a time index, or one or more of the above.

[0115] The predicted QoE information 213 is the pQoE metirc in FIG3 , which includes the QoE result predicted by the candidate network device at the local UE. A possible implementation is as follows:

[0116] In some embodiments, at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface. The Xn interface refers to the network interface between NG-RAN nodes (gNB or eNB).

[0117] Additionally or alternatively, based on the predicted QoE information, first network device 110 may select a target network device from second network device 120 and third network device to which the terminal device is to switch, and send a first indication to the target network device, wherein the first indication is used to indicate that the terminal device is to switch to the target network device. For example, after receiving the pQoE measurements of multiple candidate network devices, first network device 110 selects one of the multiple candidate network devices' cells as the target cell based on implementation selection. For example, first network device 110 may select the candidate cell with the smallest predicted playout delay value as the optimal target cell and notify the target network device to prepare for the handover.

[0118] Accordingly, the second network device 120 may receive a first indication from the first network device 110. Based on the predicted QoE information, the second network device 120 may perform resource optimization for the terminal device. Additionally, resource optimization may include selecting a handover mode for the terminal device, optimizing random access channel (RACH) resources, optimizing scheduled transmission resources, or one or more of the above. For example, after the source station notifies the target station that it is ready to perform a handover, the target station may optimize resources for the terminal based on the pQoE metric. For example, selection of a handover mode (DAPS, CHO, legacy), optimization of RACH resources, optimization of scheduled transmission resources, etc.

[0119] In some embodiments, the second network device 120 may also receive measured QoE information from the terminal device and compare the measured QoE information with the predicted QoE information. Based on the comparison, the second network device 120 performs at least one of updating, training, or monitoring the execution of the AI / ML model used to obtain the predicted QoE measurement result. Alternatively or additionally, the second network device 120 may also send the identifier of the terminal device, the predicted QoE measurement result, the accuracy of the predicted QoE measurement result, or one or more of the above to the first network device 110. Optionally, the accuracy indicator may be indicated to the second network device 120 by the first network device 110. Additionally, the accuracy indicator may be indicated to the second network device 120 in the handover request regarding the terminal device.

[0120] For example, after receiving the QoE measurement results, the destination station compares the QoE measurement results with the predicted pQoE metric to perform AI model optimization / monitoring. At the same time, since the destination station has already sent the pQoE metric to the source station for target cell selection, the destination station can also indicate the true value or accuracy of the pQoE to the source station, which is called pQoE feedback.

[0121] In one example, pQoE feedback can include UE identification and pQoE metrics. In another example, pQoE feedback can include pQoE accuracy. In this approach, the source station can specify the accuracy metric in advance. For example, the handover request can indicate AI model metrics such as macro-averaging, micro-averaging, mean absolute error (MAE), and mean squared error (MSE). Mean absolute error is the expected value of absolute error loss, and mean squared error is the expected value of error loss. Macro-averaging involves first calculating each evaluation metric for each class and then taking the arithmetic mean of the metrics. Micro-averaging involves first averaging the elements of the confusion matrix and then calculating each evaluation metric. These evaluation metrics typically include accuracy, precision, recall, and a comprehensive evaluation metric (F1). Accuracy is the number of correctly classified samples divided by the total number of samples. Precision is the number of correctly predicted positive samples divided by the number of samples predicted positive. Recall is the number of samples correctly predicted as positive divided by the number of samples labeled as positive. The comprehensive evaluation metric is the weighted harmonic average of precision and recall, i.e., F1 = 2(Precision + Recall) / (Precision * Recall).

[0122] Correspondingly, the first network device 110 selecting the target network device to which the terminal device is to switch from the second network device 120 and the third network device may include selecting the second network device 120 as the target network device. The first network device 110 may receive an identifier of the terminal device, a predicted QoE measurement result, an accuracy of the predicted QoE measurement result, or one or more of the above from the second network device 120.

[0123] In some embodiments, based on determining that the predicted QoE measurement result is lower than a threshold, the second network device 120 may further send a second indication to the first network device 110, where the second indication is used to instruct the second network device 120 to reject the handover of the terminal device. For example, if the candidate target station evaluates the pQoE measurement result as too poor, that is, the candidate target station does not receive the handover of the UE, then the candidate target station may indicate to the source station that the handover is rejected. Optionally, the reason for rejecting the handover may be carried, such as pQoE being lower than a threshold. Additionally, in the case where the predicted QoE measurement result is lower than a threshold, the first network device 110 may receive a second indication from the second network device 120, where the second indication is used to instruct the second network device 120 to reject the handover of the terminal device.

[0124] In process 200, the specific content of the QoE report and predicted QoE information, as well as their transmission at the XN interface, are clarified. The candidate target station predicts the UE's local QoE result, the source station selects the target station based on the predicted QoE information, and the target station optimizes resources based on the predicted QoE information. In this way, the candidate target station can predict the target UE's local QoE result and send it to the source station, allowing the source and target stations to identify potential QoE issues in advance. The source station selects the target cell based on the predicted QoE information, and the target station optimizes resource allocation based on the predicted QoE information, which helps improve the overall UE satisfaction and wireless resource efficiency.

[0125] FIG4 illustrates a first example process of a communication process according to some embodiments of the present disclosure, which can be considered as a specific implementation of the communication process 200 of FIG2 . The first example process involves UE 401, S-gNB 402 (i.e., source station 402), T-gNB1 403 (i.e., candidate target station 403), and T-gNB2 404 (i.e., candidate target station 404).

[0126] At 411, UE 401 sends the QoE measurement result to S-gNB 402. The content of the QoE measurement result can refer to the specific content of the QoE measurement result of the Uu port mentioned above, and will not be repeated here.

[0127] At 413, S-gNB 402 triggers the process of selecting candidate target stations and target cells.

[0128] Subsequently, S-gNB 402 sends QoE reports to the selected candidate target stations respectively.

[0129] At 415, S-gNB 402 sends a QoE report of UE 401 to T-gNB1 403. The content of the QoE report can be seen in the embodiment of process 200.

[0130] At 417, S-gNB 402 sends a QoE report of UE 401 to T-gNB2 404. The QoE report can be used by the candidate target station to predict the QoE result of UE 401 at the candidate target station. That is, the QoE report can be used as input data for the AI ​​model used to predict QoE within the candidate target station.

[0131] The candidate target station receives the QoE report and predicts the QoE parameters of UE 401 in the candidate target cell.

[0132] At 419 , T-gNB1 403 uses the local AI model to infer the QoE parameters of UE 401 in the candidate target cell, namely, pQoE metric 1. The content of the QoE parameters can refer to the embodiment of the predicted QoE information in process 200.

[0133] At 421, T-gNB2 404 uses the local AI model to infer the QoE parameters of UE 401 in the candidate target cell, i.e., pQoE metric 2.

[0134] At 423 , T-gNB1 403 sends the predicted QoE result, i.e., pQoE metric 1, to S-gNB 402 . For details about the content of the predicted QoE result, refer to the embodiment of the predicted QoE information in process 200 .

[0135] At 425 , T-gNB2 404 sends the predicted QoE result, i.e., pQoE metric 2, to S-gNB 402 .

[0136] If T-gNB1 403 and T-gNB2 404 evaluate the pQoE metric as being too poor, T-gNB1 403 and T-gNB2 404 may not accept the handover request from the UE. In this case, the candidate target station may indicate to the source station that the handover is rejected. Optionally, the indication may include a reason for the handover rejection, such as a pQoE metric being below a threshold.

[0137] At 427, after receiving the pQoE measurements, S-gNB 402 selects a target cell and a target gNB based on the implementation.

[0138] At 429, S-gNB 402 notifies the selected target station to prepare for handover. The target station can optimize resources for UE 401 based on the pQoE metric. For specific resource optimization methods, please refer to the embodiment of process 200.

[0139] At 431, UE 401 may send actual QoE measurements to T-gNB1 403. The content of the actual QoE measurements may refer to the specific content of the aforementioned Uu port QoE measurement results.

[0140] At 433, after receiving the actual QoE measurement, T-gNB1 403 compares it with the predicted pQoE measurement and sends pQoE feedback to S-gNB 402. The content of the pQoE feedback can refer to the embodiment in process 200.

[0141] In the first example process, the candidate target station predicts the UE's local QoE parameters and sends them to the source station. Based on the pQoE metric, the source station selects a target cell, and the target station performs network optimization.

[0142] Figure 5 illustrates a second interactive signaling diagram of a communication process according to some embodiments of the present disclosure. For clarity of discussion and without any limitation, process 500 will be discussed in conjunction with Figure 1A.

[0143] In process 500, first network device 110 sends 501 a request message 503 to second network device 120 for requesting auxiliary information at second network device 120, where the auxiliary information is used to predict a quality of experience (QoE) measurement result when the terminal device is under second network device 120. The request message is used by a source station to request information related to predicted QoE from a candidate destination station.

[0144] Additionally or alternatively, the request message may include: a measurement identifier that identifies the auxiliary information request process, an identifier of the second network device; an identifier of the cell; a list of at least one terminal device identifier selected by the first network device, a service type, a third indication of the content of the auxiliary information, time information for the auxiliary information, or one or more of the above.

[0145] For example, a possible request message implementation is as follows:

[0146] Among them, the measurement ID is used to identify which pQoE auxiliary information request process it is. The UE identification list is optional and is used to instruct the candidate target station to select UE, for example, all UEs whose buffer level in service type 1 in cell 1 is lower than threshold 1. If the UE identification list is not carried, the default is the average UE information requested. The request time indication is used to indicate the period of time for which the candidate target station provides pQoE auxiliary information. The specific implementation form is not limited and can be a time point or a time period. The service type is used to indicate which service or services the pQoE auxiliary information is requested for. The pQoE auxiliary information request indication information is used to indicate which auxiliary information the candidate target station provides, and may include at least one of the following: RAN visible QoE measurement / prediction results, wireless resource status measurement / prediction results, QoS parameters, wireless configuration, and signal quality measurement / prediction results. The implementation form of the pQoE auxiliary information request indication information can be 16 bits, for example, the second bit is 1, indicating a request for QoS parameters. The reporting period is used to indicate the time interval for each candidate target station to report pQoE auxiliary information. If it is carried, the default is periodic reporting. If it is not carried, the default is a one-time report, that is, the candidate target station reports all pQoE auxiliary information at one time according to the request time indication information.

[0147] Additionally, first network device 110 may also send a request message to a third network device to which the terminal device can be switched. Optionally, first network device 110 may receive auxiliary information from the third network device. It should be understood that the first network device (i.e., the source station) may send a request message to one or more candidate destination stations and receive auxiliary information from one or more candidate stations.

[0148] Based on receiving 505 the request message 503, the second network device 120 sends 510 assistance information 513 to the first network device 110. Accordingly, the first network device 110 receives 515 assistance information 513 from the second network device 120. For example, the pQoE assistance information message may be pQoE assistance information that the candidate target station may provide after receiving the pQoE assistance information request message.

[0149] Additionally or alternatively, the auxiliary information may include: a measurement identifier, an identifier of the second network device, an identifier of the cell, a list of at least one terminal device identifier, a service type, the content of the auxiliary information indicated in the third indication, a fourth indication of the content of unsupported auxiliary information, a time index, or one or more of the above.

[0150] Additionally, the content of the auxiliary information may include: historical QoE information, predicted QoE information, historical resource status information, predicted resource status information, QoS parameters, wireless configuration, historical signal quality, predicted signal quality, or one or more of the above.

[0151] In some embodiments, the auxiliary information may be implemented as follows:

[0152] The unsupported pQoE auxiliary information indication is used to indicate which pQoE auxiliary information the source station does not support reporting and the reasons, for example, the candidate target station does not support AI prediction.

[0153] 5 , the first network device 110 predicts 520 a QoE measurement result based on the auxiliary information and the QoE report, wherein the QoE report includes information at the first network device 110 for predicting the QoE measurement result.

[0154] In some embodiments, the first network device 110 can input the QoE report and auxiliary information into an artificial intelligence / machine learning (AI / ML) model to obtain predicted QoE measurement results. For example, after receiving the pQoE auxiliary information, the source station predicts the QoE parameters of the terminal device at the candidate target station based on the local AI model. It should be understood that the predicted QoE parameters in this disclosure only target the RAN-visible QoE parameters and do not involve the prediction of QoE parameters within the application layer report container, because this part is transparently transmitted on the RAN side in the form of a container, that is, it is not visible on the RAN side.

[0155] The input and output of the AI / ML model can refer to Figure 3. The source station can predict the QoE results of the UE in the candidate target cell, that is, the pQoE metric, through the AI ​​model based on the pQoE auxiliary information and historical QoE reports. The pQoE auxiliary information is the auxiliary information related to the QoE prediction sent by the candidate target station. The historical QoE report is the information related to the QoE prediction collected by the source station based on the implementation, which may include: time index, RAN visible QoE measurement results, service type, cell identity, QoS parameters, wireless configuration, resource status information, UE signal quality in the candidate target cell, or one or more of the above. The wireless configuration may include dual link (DC), or carrier aggregation (CA), etc. Signal quality may include RSRP, RSRQ, SINR, bit error rate, throughput, etc. A possible implementation of the pQoE metric is as follows:

[0156] After the source station predicts the pQoE metric of the UE at the candidate target stations, it selects one of them as the target cell based on the performance. For example, the source station may select the candidate target cell with the smallest predicted playout delay as the best target cell.

[0157] Continuing with FIG5 , the first network device 110 sends 525 predicted QoE information 527 about the terminal device to the second network device 120, where the predicted QoE information includes a predicted QoE measurement result. Additionally, the predicted QoE information may also include: an identifier of the terminal device, an identifier of the second network device, a service type, an identifier of a cell, a time index, or one or more of the foregoing. Additionally or alternatively, the predicted QoE information may be transmitted via an Xn interface.

[0158] Optionally, first network device 110 may select a target network device to which the terminal device is to be switched from second network device 120 and a third network device based on the predicted QoE information. Second network device 120 is determined as the target network device, and first network device 110 may send the predicted QoE information to second network device 120. Accordingly, second network device 120 receives 530 the predicted QoE information 527 from first network device 110.

[0159] In some embodiments, the first network device 110 may send a first indication to the second network device 120, and the first indication may be used to indicate that the terminal device is to switch to the second network device 120. Accordingly, the second network device 120 may receive the first indication from the first network device 110. Based on the predicted QoE information, the second network device 120 may perform resource optimization for the terminal device. Additionally, resource optimization may include selection of a switching mode for the terminal device, optimization of random access channel RACH resources, optimization of scheduled transmission resources, or one or more of the above. For example, after the source station notifies the target station that it is ready to switch, the target station may optimize resources for the terminal based on the pQoE metric. For example, selection of a switching mode (DAPS, CHO, legacy), optimization of RACH resources, optimization of scheduled transmission resources, etc.

[0160] Optionally, the second network device 120 may receive measured QoE information from the terminal device and compare the measured QoE information with the predicted QoE information. Based on the above comparison, the second network device 120 may evaluate the accuracy of the predicted QoE measurement result. For example, after the destination station receives the measured QoE measurement result, it may compare the pQoE metric received from the source station to evaluate the pQoE accuracy. Additionally, the second network device 120 may send the terminal device identifier, the predicted QoE measurement result, the accuracy of the predicted QoE measurement result, or one or more of the above to the first network device 110. For example, the destination station may also indicate the true value or accuracy of the pQoE to the source station, i.e., pQoE feedback, to assist the source station in training / monitoring the AI ​​model. Correspondingly, the first network device 110 may also receive the terminal device identifier, the predicted QoE measurement result, the accuracy of the predicted QoE measurement result, or one or more of the above from the second network device 120. Based on the received information, the first network device 110 may update, train, or monitor the AI / ML model used to obtain the predicted QoE measurement result.

[0161] In some embodiments, the accuracy indicator may be indicated by the first network device 110 to the second network device 120. Alternatively, the accuracy indicator may be indicated to the second network device 120 in a handover request regarding the terminal device.

[0162] In one example, pQoE feedback can include UE identification and pQoE metrics. In another example, pQoE feedback can include pQoE accuracy. In this approach, the source station can specify the accuracy metric in advance. For example, the handover request can indicate AI model metrics such as macro-averaging, micro-averaging, mean absolute error (MAE), and mean squared error (MSE). Mean absolute error is the expected value of absolute error loss, and mean squared error is the expected value of error loss. Macro-averaging involves first calculating each evaluation metric for each class and then taking the arithmetic mean of the metrics. Micro-averaging involves first averaging the elements of the confusion matrix and then calculating each evaluation metric. These evaluation metrics typically include accuracy, precision, recall, and a comprehensive evaluation metric (F1). Accuracy is the number of correctly classified samples divided by the total number of samples. Precision is the number of correctly predicted positive samples divided by the number of predicted positive samples. Recall is the number of samples correctly predicted as positive divided by the number of samples labeled as positive. The comprehensive evaluation metric is the weighted harmonic average of precision and recall, i.e., F1 = 2(Precision + Recall) / (Precision * Recall).

[0163] In process 500, the source station requests pQoE assistance information from the target station and predicts the UE's QoE results at candidate target stations. This allows the source station to predict the UE's QoE results at candidate target stations, enabling both the source station and candidate target stations to identify potential QoE issues in advance. The source station selects a target cell based on the predicted QoE information, and the target station optimizes resource allocation based on the predicted QoE information, improving overall UE satisfaction and wireless resource efficiency.

[0164] FIG6 illustrates a second example process of a communication process according to some embodiments of the present disclosure. This process can be considered a specific implementation of the communication process 500 of FIG5 . The second example process involves UE 601, S-gNB 602 (i.e., source station 602), T-gNB1 603 (i.e., candidate target station 603), and T-gNB2 604 (i.e., candidate target station 604).

[0165] At 611, UE 601 sends the QoE measurement result to S-gNB 602. The content of the QoE measurement result can refer to the specific content of the QoE measurement result of the Uu port mentioned above, and will not be repeated here.

[0166] At 613, the S-gNB 602 triggers the process of selecting candidate target stations and target cells.

[0167] The S-gNB 602 then sends a pQoE assistance information request message to each selected candidate target station.

[0168] At 615, S-gNB 602 sends a pQoE assistance information request message to T-gNB1 603. For details on the pQoE assistance information request message, refer to the example of the request message in process 500.

[0169] At 619, S-gNB 602 sends a pQoE assistance information request message to T-gNB2 604.

[0170] Accordingly, at 617, T-gNB1 603 sends pQoE assistance information to S-gNB 602. For the specific content of the pQoE assistance information, refer to the embodiment of the assistance information in process 500.

[0171] At 621, T-gNB2 604 sends pQoE assistance information to S-gNB 602.

[0172] At 623, after receiving the pQoE auxiliary information, S-gNB 602 predicts the QoE parameters of UE 601 in the candidate gNB based on the local AI model, i.e., the pQoE report in the candidate gNB. For the specific content of the QoE parameters, please refer to the embodiment of the predicted QoE information in process 500.

[0173] At 625, S-gNB 602 sends the predicted QoE result, i.e., pQoE metric, to T-gNB1 603. For the specific content of the pQoE metric, please refer to the embodiment of the predicted QoE information in process 500.

[0174] At 627, T-gNB1 603 optimizes resource allocation based on pQoE, and S-gNB 602 notifies the target station to prepare for switching. The target station can optimize resources for UE 601 based on pQoE metrics. For specific resource optimization methods, please refer to the embodiment in process 500.

[0175] At 629, UE 601 also sends the QoE measurement results to T-gNB1 603. The details of the QoE measurement results can be found in the aforementioned QoE measurement results for the Uu interface. After receiving the QoE measurement results, T-gNB1 603 compares the received pQoE metrics to assess the pQoE accuracy.

[0176] At 631, T-gNB1 603 may indicate the true value or accuracy of pQoE to S-gNB 602, i.e., pQoE feedback, to assist the source station in training / monitoring the AI ​​model. For details on the content of pQoE feedback, refer to the embodiment described in process 500.

[0177] In the second example process, the source station predicts the QoE parameters of the UE at the candidate target station. Based on the pQoE metric, the source station selects the target cell, and the target station performs network optimization.

[0178] FIG7 shows a schematic flow chart of a method 700 implemented at a first network device according to an embodiment of the present disclosure. For clarity of discussion and without limitation, process 700 will be discussed in conjunction with FIG1A . In one possible implementation, method 700 may be implemented by first network device 110 in communication system 100A. In other possible implementations, method 700 may also be implemented by other communication devices independent of communication system 100A. As an example, method 700 will be described below using implementation by network device 110 in communication system 100A as an example.

[0179] At block 710, first network device 110 sends a QoE report about a terminal device to second network device 120, where the QoE report includes first information on the first network device, the first information being used to predict a QoE measurement result when the terminal device is on the second network device. At block 720, first network device 110 receives predicted QoE information about the terminal device from second network device 120, where the predicted QoE information includes a predicted QoE measurement result.

[0180] In some example embodiments, the QoE report may include: a time index; a QoE measurement result; a service type; an identifier of the terminal device; an identifier of the first network device; an identifier of the second network device; an identifier of the cell; quality of service (QoS) parameters; a wireless configuration; resource status information; signal quality of the terminal device in the cell of the second network device; or one or more of the above.

[0181] In some example embodiments, the predicted QoE information may further include: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; a time index; or one or more of the above.

[0182] In some example embodiments, first network device 110 may further send a QoE report to a third network device to which the terminal device can be switched. In some example embodiments, first network device 110 may further receive predicted QoE information about the terminal device from the third network device. In some example embodiments, first network device 110 may further select a target network device from the second and third network devices to which the terminal device is to be switched based on the predicted QoE information, and send a first indication to the target network device, wherein the first indication is used to indicate that the terminal device is to be switched to the target network device.

[0183] In some example embodiments, the first network device 110 selects a target network device to which the terminal device is to switch from the second network device and the third network device, including selecting the second network device as the target network device. The first network device 110 may also receive the following information from the second network device: an identifier of the terminal device; a predicted QoE measurement result; an accuracy of the predicted QoE measurement result; or one or more of the above.

[0184] In some example embodiments, the indicator of accuracy may be indicated by the first network device 110 to the second network device, and the indicator of accuracy may be indicated to the second network device in a handover request regarding the terminal device.

[0185] In some example embodiments, when the predicted QoE measurement result is lower than a threshold, the first network device 110 may receive a second indication from the second network device, where the second indication is used to instruct the second network device to reject the handover of the terminal device.

[0186] In some example embodiments, the prediction of the QoE measurement result of the terminal device under the second network device may be performed based on an artificial intelligence / machine learning (AI / ML) model.

[0187] In some example embodiments, at least one of the QoE report or the predicted QoE information may be transmitted via an Xn interface.

[0188] FIG8 shows a schematic flow chart of a method 800 implemented at a second network device according to an embodiment of the present disclosure. For clarity of discussion and without limitation, process 800 will be discussed in conjunction with FIG1A . In one possible implementation, method 800 can be implemented by second network device 120 in communication system 100A. In other possible implementations, method 800 can also be implemented by other communication devices independent of communication system 100A. As an example, method 700 will be described below using implementation by second network device 120 in communication system 100A as an example.

[0189] At block 810, second network device 120 receives a QoE report regarding a terminal device from a first network device, wherein the QoE report includes first information at the first network device, the first information being used to predict a QoE measurement result when the terminal device is on the second network device. At block 820, second network device 120 predicts a QoE measurement result based on the QoE report and the auxiliary information at the second network device. At block 830, second network device 120 transmits predicted QoE information regarding the terminal device to first network device 110, wherein the predicted QoE information includes the predicted QoE measurement result.

[0190] In some example embodiments, predicting the QoE measurement results may include inputting the QoE report and the auxiliary information into an artificial intelligence / machine learning (AI / ML) model to obtain the predicted QoE measurement results.

[0191] In some example embodiments, the QoE report may include: a time index; a QoE measurement result; a service type; an identifier of the terminal device; an identifier of the first network device; an identifier of the second network device; an identifier of the cell; quality of service (QoS) parameters; a wireless configuration; resource status information; signal quality of the terminal device in the cell of the second network device; or one or more of the above.

[0192] In some example embodiments, the auxiliary information may include: historical resource status information of the second network device; predicted resource status information of the second network device; an identifier of the second network device; an identifier of the cell; a time index; the number of at least one terminal device; wireless resource status information; the number of wireless resource control RRC connections; the historical average signal quality of at least one terminal device; the historical average QoE measurement result of at least one terminal device; the historical average QoS parameter of at least one terminal device; or one or more of the above.

[0193] In some example embodiments, the auxiliary information may further include: historical resource status information of the second network device; predicted resource status information of the second network device; an identifier of the second network device; an identifier of a cell; a time index; an identifier of the terminal device; signal quality for the terminal device; a QoE measurement result for the terminal device; a QoS parameter for the terminal device; or one or more of the above. In some example embodiments, the predicted QoE information may further include: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; a time index; or one or more of the above.

[0194] In some example embodiments, second network device 120 may further receive a first indication from the first network device, where the first indication is used to indicate that the terminal device is to be handed over to the second network device; and perform resource optimization for the terminal device based on the predicted QoE information. In some example embodiments, resource optimization may include: selecting a handover method for the terminal device; optimizing random access channel (RACH) resources; optimizing scheduled transmission resources; or one or more of the above.

[0195] In some example embodiments, the second network device 120 may also receive measured QoE information from the terminal device; perform a comparison between the measured QoE information and the predicted QoE information; and based on the comparison, at least one of update, train, or monitor the execution of an AI / ML model used to obtain the predicted QoE measurement result.

[0196] In some example embodiments, second network device 120 may also send the following information to the first network device: an identifier of the terminal device; a predicted QoE measurement result; an accuracy of the predicted QoE measurement result; or one or more of the above. In some example embodiments, an accuracy indicator may be indicated by the first network device to second network device 120. In some example embodiments, the accuracy indicator may be indicated to second network device 120 in a handover request regarding the terminal device.

[0197] In some example embodiments, second network device 120 may further, based on determining that the predicted QoE measurement result is below a threshold, send a second indication to the first network device, the second indication being used to instruct the second network device to reject handover of the terminal device. In some example embodiments, at least one of the QoE report or the predicted QoE information may be transmitted via an Xn interface.

[0198] FIG9 is a schematic flow chart of a method 900 implemented at the first network device 110 according to an embodiment of the present disclosure. For clarity of discussion and without limitation, process 900 will be discussed in conjunction with FIG1A . In one possible implementation, method 900 may be implemented by the first network device 110 in the communication system 100A. In other possible implementations, method 900 may also be implemented by other communication devices independent of the communication system 100A. As an example, method 900 will be described below using implementation by the first network device 110 in the communication system 100A as an example.

[0199] At block 910, first network device 110 sends a request message to a second network device requesting auxiliary information from the second network device, where the auxiliary information is used to predict a QoE measurement result when the terminal device is on the second network device. At block 920, first network device 110 receives the auxiliary information from the second network device. At block 930, first network device 110 predicts a QoE measurement result based on the auxiliary information and a QoE report, where the QoE report includes information used to predict the QoE measurement result at the first network device. At block 940, first network device 110 sends predicted QoE information about the terminal device to the second network device, where the predicted QoE information includes the predicted QoE measurement result.

[0200] In some example embodiments, predicting the QoE measurement result may include: inputting the QoE report and the auxiliary information into an artificial intelligence / machine learning (AI / ML) model to obtain the predicted QoE measurement result. In some example embodiments, the request message may include: a measurement identifier identifying the auxiliary information request process; an identifier of the second network device; an identifier of the cell; a list of at least one terminal device identifier selected by the first network device; a service type; a third indication of the content of the auxiliary information; time information for the auxiliary information; or one or more of the above.

[0201] In some example embodiments, the auxiliary information may include: a measurement identifier; an identifier of a second network device; an identifier of a cell; a list of at least one terminal device identifier; a service type; the content of the auxiliary information indicated in a third indication; a fourth indication of unsupported auxiliary information content; a time index; or one or more of the above. In some example embodiments, the content of the auxiliary information may include: historical QoE information; predicted QoE information; historical resource status information; predicted resource status information; QoS parameters; a radio configuration; historical signal quality; or predicted signal quality; or one or more of the above. In some example embodiments, the predicted QoE information may also include: an identifier of the terminal device; an identifier of the second network device; a service type; an identifier of a cell; a time index; or one or more of the above.

[0202] In some embodiments, the QoE report includes at least one of the following: time index; QoE measurement results; service type; identification ID of the terminal device; identification of the first network device; identification of the second network device; identification of the cell; quality of service QoS parameters; wireless configuration; resource status information; or signal quality of the terminal device in the cell of the second network device.

[0203] In some example embodiments, first network device 110 may send a request message to a third network device to which the terminal device can be handed over, and receive auxiliary information from the third network device. In some example embodiments, sending the predicted QoE information to the second network device may include: selecting a target network device to which the terminal device is to be handed over from the second network device and the third network device based on the predicted QoE information; and sending the predicted QoE information to the second network device.

[0204] In some example embodiments, the first network device 110 may send a first indication to the second network device, where the first indication is used to indicate that the terminal device is to switch to the second network device. In some example embodiments, the first network device 110 may receive the following information from the second network device: an identification of the terminal device; a predicted QoE measurement result; an accuracy of the predicted QoE measurement result; or one or more of the above. In some example embodiments, the first network device 110 may perform at least one of updating, training, or monitoring an AI / ML model used to obtain the predicted QoE measurement result based on the above information. In some example embodiments, at least one of the QoE report or the predicted QoE information may be transmitted via an Xn interface.

[0205] Figure 10 shows a schematic flow chart of a method 1000 implemented at a second network device according to an embodiment of the present disclosure. For clarity of discussion and without limitation, process 1000 will be discussed in conjunction with Figure 1A. In one possible implementation, method 1000 can be implemented by network device 1420 in communication system 100A. In other possible implementations, method 1000 can also be implemented by other communication devices independent of communication system 100A. As an example, method 1000 will be described below using network device 120 in communication system 100A as an example.

[0206] At block 1010, second network device 120 receives a request message from a first network device requesting auxiliary information at second network device 120, wherein the auxiliary information is used to predict a QoE measurement result when the terminal device is located at second network device 120. At block 1020, second network device 120 transmits the auxiliary information to the first network device based on receipt of the request message. At block 1030, second network device 120 receives predicted QoE information about the terminal device from the first network device, wherein the predicted QoE information includes a predicted QoE measurement result.

[0207] In some example embodiments, the request message may include: a measurement identifier that identifies the auxiliary information request process; an identifier of the second network device 120; an identifier of the cell; a list of at least one terminal device identifier selected by the first network device; a service type; a third indication of the content of the auxiliary information; time information for the auxiliary information; or one or more of the above.

[0208] In some example embodiments, the auxiliary information may include: a measurement identifier; an identifier of the second network device 120; an identifier of a cell; a list of at least one terminal device identifier; a service type; the content of the auxiliary information indicated in the third indication; a fourth indication of unsupported content of the auxiliary information; a time index; or one or more of the above. In some example embodiments, the content of the auxiliary information may include: historical QoE information; predicted QoE information; historical resource status information; predicted resource status information; QoS parameters; radio configuration; historical signal quality; predicted signal quality; or one or more of the above.

[0209] In some example embodiments, the predicted QoE information may further include: an identifier of the terminal device; an identifier of the second network device 120; a service type; an identifier of a cell; a time index; or one or more of the above. In some example embodiments, the second network device 120 may receive a first indication from the first network device, wherein the first indication is used to indicate that the terminal device is to be handed over to the second network device; and perform resource optimization for the terminal device based on the predicted QoE information.

[0210] In some example embodiments, second network device 120 may receive measured QoE information from a terminal device; perform a comparison between the measured QoE information and predicted QoE information; and evaluate the accuracy of the predicted QoE measurement result based on the comparison.

[0211] In some example embodiments, second network device 120 may send the following information to first network device: an identifier of the terminal device; a predicted QoE measurement result; an accuracy of the predicted QoE measurement result; or one or more of the above. In some example embodiments, an accuracy indicator may be indicated by the first network device to second network device 120, and the accuracy indicator may be indicated to second network device 120 in a handover request regarding the terminal device.

[0212] In some example embodiments, second network device 120 may, based on determining that the predicted QoE measurement result is below a threshold, send a second indication to second network device 120, the second indication being used to instruct second network device 120 to reject handover of the terminal device. In some example embodiments, the prediction of the QoE measurement result of the terminal device when it is under second network device 120 may be performed based on an artificial intelligence / machine learning (AI / ML) model. In some example embodiments, the predicted QoE information may be transmitted via an Xn interface.

[0213] Figure 11 is a schematic diagram of the structure of possible communication devices provided by an embodiment of the present application. These communication devices can implement the functions of the terminal device or network device in the above method embodiment, and thus can also achieve the beneficial effects possessed by the above method embodiment. In the embodiment of the present application, the communication device can be the first network device 110, the second network device 120, the third network device 130 or the terminal device 140 as shown in Figure 1A, or it can be a module (such as a chip) applied to the first network device 110, the second network device 120, the third network device 130 or the terminal device 140.

[0214] As shown in Figure 11, a communication device 1100 includes a processing unit 1110, a receiving unit 1120, and a sending unit 1130. The communication device can be used to implement the functions of the network device in the method embodiments shown in any of Figures 2, 5, 7 to 10 above. In some embodiments, the processing unit can be a processor, the sending unit can be a transmitter, and the receiving unit can be a receiver.

[0215] As shown in Figure 12, communication device 1200 includes a processor 1210 and an interface circuit 1220. Processor 1210 and interface circuit 1220 are coupled to each other. It is understood that interface circuit 1220 may be a transceiver or an input / output interface. Optionally, communication device 1200 may further include a memory 1230 for storing instructions executed by processor 1210, input data required by processor 1210 to execute instructions, or data generated by processor 1210 after executing instructions.

[0216] When the communication device 1200 is used to implement the method in the above method embodiment, the processor 1210 is used to execute the functions of the above processing unit 1110, and the interface circuit 1220 is used to execute the functions of the above receiving unit 1120 and the sending unit 1130.

[0217] When the communication device is a chip used in the first network device 110, the second network device 120, the third network device 130, or the terminal device 140, the device chip implements the functions of the first network device 110, the second network device 120, the third network device 130, or the terminal device 140 in the above method embodiment. The device chip receives information from other modules (such as a radio frequency module or antenna) in the first network device 110, the second network device 120, the third network device 130, or the terminal device 140, and the information may be sent by other first network devices 110, the second network device 120, the third network device 130, or the terminal device 140; or the terminal device chip sends information to other modules (such as a radio frequency module or antenna) in the first network device 110, the second network device 120, the third network device 130, or the terminal device 140, and the information is sent to other first network devices 110, the second network device 120, the third network device 130, or the terminal device 140.

[0218] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0219] An embodiment of the present application provides a communication system. The communication system may include the communication apparatus involved in the embodiment shown in FIG11 above, such as the first network device 110, the second network device 120, the third network device 130, or the terminal device 140. Optionally, the first network device 110, the second network device 120, the third network device 130, or the terminal device 140 in the communication system may execute the communication method shown in any one of FIG2, FIG5, and FIG7 to FIG10.

[0220] The present application also provides a circuit that can be coupled to a memory and can be used to execute the process related to the first network device 110, the second network device 120, the third network device 130, or the terminal device 140 in any of the above method embodiments. The chip system may include the chip and may also include other components such as a memory or a transceiver.

[0221] It should be understood that the processor mentioned in the embodiments of the present application may be a CPU, or may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0222] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0223] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) is integrated into the processor.

[0224] It should be noted that the memory described herein is intended to include, but not be limited to, these and any other suitable types of memory.

[0225] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0226] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0227] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0228] In the several embodiments provided in this application, it should be understood that the disclosed communication methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0229] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of these elements may be selected to achieve the purpose of this embodiment according to actual needs.

[0230] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0231] If this function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that makes the contribution, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned computer-readable storage medium can be any available medium that can be accessed by a computer. By way of example and not limitation, computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), universal serial bus flash disk, mobile hard disk, or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0232] As used herein, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. can refer to different or the same objects and are only used to distinguish the objects referred to, and do not imply a specific spatial order, temporal order, order of importance, etc. of the objects referred to. In some embodiments, values, processes, selected items, determined items, devices, means, components, assemblies, etc. are referred to as "best", "lowest", "highest", "minimum", "maximum", etc. It should be understood that such descriptions are intended to indicate that a selection can be made from a number of available functional options, and that such a selection need not be better, lower, higher, smaller, larger, or otherwise preferred than other options in other aspects or all aspects. As used herein, the term "determine" can encompass a variety of actions. For example, "determine" can include calculating, computing, processing, deriving, investigating, searching (e.g., searching in a table, database, or another data structure), ascertaining, etc. Furthermore, "determining" may include receiving (eg, receiving information), accessing (eg, accessing data in a memory), etc. Furthermore, "determining" may include resolving, selecting, choosing, establishing, etc.

[0233] The above is only a specific embodiment of the present application, but the scope of protection of the embodiments of the present application is not limited thereto. Any person skilled in the art can easily conceive of changes or substitutions within the technical scope disclosed in the embodiments of the present application, and all such changes or substitutions should be included in the scope of protection of the embodiments of the present application. Therefore, the scope of protection of the embodiments of the present application should be based on the scope of protection of the claims.

Claims

1. A method applied to a first network device, comprising: Sending a quality of experience (QoE) report about a terminal device to a second network device, wherein the QoE report includes first information on the first network device, the first information being used to predict a QoE measurement result when the terminal device is under the second network device; and The predicted QoE information about the terminal device is received from the second network device, wherein the predicted QoE information includes the predicted QoE measurement result.

2. The method of claim 1, wherein the QoE report comprises at least one of the following: Time index; QoE measurement result; service type; identification ID of the terminal device; identification of the first network device; identification of the second network device; identification of the cell; quality of service QoS parameters; wireless configuration; resource status information; or signal quality of the terminal device in the cell of the second network device.

3. The method according to claim 1 or 2, wherein the predicted QoE information further comprises at least one of the following: The identifier of the terminal device; the identifier of the second network device; the service type; the identifier of the cell; or a time index.

4. The method according to any one of claims 1 to 3, further comprising: The QoE report is sent to a third network device to which the terminal device can switch.

5. The method according to any one of claims 1 to 4, further comprising: The predicted QoE information about the terminal device is received from the third network device.

6. The method according to any one of claims 1 to 5, further comprising: Based on the predicted QoE information, selecting a target network device to be switched by the terminal device from the second network device and the third network device; as well as A first indication is sent to the target network device, wherein the first indication is used to indicate that the terminal device is to switch to the target network device.

7. The method according to claim 6, wherein selecting the target network device to be switched by the terminal device from the second network device and the third network device comprises selecting the second network device as the target network device, and the method further comprises: Receive at least one of the following information from the second network device: The identification of the terminal device; The predicted QoE measurement result; or the accuracy of the predicted QoE measurement result. The method according to claim 7 , wherein the indicator of the accuracy is indicated by the first network device to the second network device.

9. The method according to claim 7, wherein the indicator of the accuracy is indicated to the second network device in a handover request regarding the terminal device.

10. The method according to any one of claims 1 to 9, further comprising: In a case where the predicted QoE measurement result is lower than a threshold, a second indication is received from the second network device, wherein the second indication is used to instruct the second network device to reject the switching of the terminal device.

11. The method according to any one of claims 1 to 10, wherein the prediction of the QoE measurement result of the terminal device under the second network device is performed based on an artificial intelligence / machine learning (AI / ML) model.

12. The method according to any one of claims 1 to 11, wherein at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface.

13. A method applied to a second network device, comprising: receiving a quality of experience (QoE) report about a terminal device from a first network device, wherein the QoE report includes first information at the first network device, the first information being used to predict a QoE measurement result when the terminal device is under the second network device; predicting the QoE measurement result based on the QoE report and the auxiliary information at the second network device; as well as Sending predicted QoE information about the terminal device to the first network device, wherein the predicted QoE information includes the predicted QoE measurement result.

14. The method of claim 13, wherein predicting the QoE measurement result comprises: The QoE report and the auxiliary information are input into an artificial intelligence / machine learning (AI / ML) model to obtain the predicted QoE measurement result.

15. The method of claim 13, wherein the QoE report comprises at least one of the following: Time index; QoE measurement result; service type; identification ID of the terminal device; identification of the first network device; identification of the second network device; identification of the cell; quality of service QoS parameters; wireless configuration; resource status information; or signal quality of the terminal device in the cell of the second network device.

16. The method according to any one of claims 13 to 15, wherein the auxiliary information comprises at least one of the following: Historical resource status information of the second network device; predicted resource status information of the second network device; identification of the second network device; identification of the cell; time index; number of at least one terminal device; wireless resource status information; number of wireless resource control RRC connections; historical average signal quality of at least one terminal device; historical average QoE measurement result of at least one terminal device; historical average QoS parameter of at least one terminal device.

17. The method according to any one of claims 13 to 15, wherein the auxiliary information further comprises at least one of the following: Historical resource status information of the second network device; predicted resource status information of the second network device; identification of the second network device; identification of the cell; time index; identification of the terminal device; signal quality for the terminal device; QoE measurement results for the terminal device; or QoS parameters for the terminal device.

18. The method according to any one of claims 13 to 17, wherein the predicted QoE information further comprises at least one of the following: The identifier of the terminal device; the identifier of the second network device; the service type; the identifier of the cell; or the time index.

19. The method according to any one of claims 13 to 18, further comprising: receiving a first indication from the first network device, wherein the first indication is used to indicate that the terminal device is to switch to the second network device; as well as Resource optimization is performed for the terminal device based on the predicted QoE information.

20. The method of claim 19, wherein the resource optimization comprises at least one of the following: Selection of a switching mode of the terminal device; Optimization of random access channel RACH resources; or Optimization of scheduling transmission resources.

21. The method according to any one of claims 13 to 20, further comprising: receiving measured QoE information from the terminal device; performing a comparison between the measured QoE information and the predicted QoE information; as well as Based on the comparison, at least one of updating, training, or monitoring execution of an AI / ML model used to obtain the predicted QoE measurement result.

22. The method according to claim 21, further comprising: Send at least one of the following information to the first network device: The identifier of the terminal device; the predicted QoE measurement result; or the accuracy of the predicted QoE measurement result.

23. The method of claim 22, wherein the indicator of accuracy is indicated by the first network device to the second network device.

24. The method according to claim 23, wherein the indicator of the accuracy is indicated to the second network device in a handover request regarding the terminal device.

25. The method according to any one of claims 13 to 24, further comprising: Based on determining that the predicted QoE measurement result is lower than a threshold, a second indication is sent to the first network device, where the second indication is used to instruct the second network device to reject the switching of the terminal device.

26. The method of any one of claims 13 to 25, wherein at least one of the QoE report or the predicted QoE information is transmitted via an Xn interface.

27. A communication device, comprising: A processor, and a memory storing instructions, wherein when the instructions are executed by the processor, the communication device executes the method according to any one of claims 1 to 12 and any one of claims 13 to 26.

28. A chip comprising a processing circuit, wherein the processing circuit is configured to perform the method according to any one of claims 1 to 12 and any one of claims 13 to 26.

29. A computer-readable storage medium storing instructions, wherein when the instructions are executed by a communication device, the communication device executes the method according to any one of claims 1 to 12 and any one of claims 13 to 26.

Images