Communication method, communication device and communication system

Abstract

The invention provides a communication method, a communication device and a communication system. The method comprises the following steps: the terminal equipment receives a first message from network equipment, wherein the first message is used for requesting the terminal equipment to report prediction information and the credibility of the prediction information; and the terminal equipment sends a second message to the network equipment, wherein the second message comprises the prediction information and the credibility of the prediction information. In the method, the network equipment requests the terminal equipment to report the prediction information and the credibility of the prediction information, so that the network equipment obtains the credibility of the prediction information while obtaining the prediction information from the terminal equipment, the network equipment is helped to accurately use the prediction information reported by the terminal equipment, and the reliability of the prediction information is improved. And the communication quality between the network equipment and the terminal equipment can be improved.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to communication methods, communication devices and communication systems. Background Technology

[0002] In application scenarios based on Artificial Intelligence (AI) for prediction, the terminal device typically reports its measurement information to the network device. This measurement information includes reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), and signal to interference plus noise ratio (SINR). The network device then makes predictions based on the measurement information and the AI ​​model to obtain the predicted information.

[0003] Alternatively, the terminal device can make predictions based on measurement information and AI models, obtain prediction information, and report the prediction information to the network device. However, the network device cannot know whether the prediction information is reliable, which prevents the network device from using the prediction information correctly. Summary of the Invention

[0004] This application provides a communication method, communication device, and communication system for network devices to correctly use prediction information.

[0005] In a first aspect, embodiments of this application provide a communication method, which can be executed by a terminal device or a module (such as a chip or chip system) within the terminal device. The method includes: receiving a first message from a network device, the first message being used to request the terminal device to report prediction information and the confidence level of the prediction information; and sending a second message to the network device, the second message including the prediction information and the confidence level of the prediction information.

[0006] Secondly, embodiments of this application provide a communication method that can be executed by a network device or a module (such as a chip or chip system) within the network device. The method includes: sending a first message to a terminal device, the first message requesting the terminal device to report prediction information and the confidence level of the prediction information; and receiving a second message from the terminal device, the second message including the prediction information and the confidence level of the prediction information.

[0007] Based on the above scheme, the network device requests the terminal device to report the prediction information and the credibility of the prediction information. In this way, the network device obtains the prediction information and the credibility of the prediction information from the terminal device, which helps the network device to accurately use the prediction information reported by the terminal device, thereby improving the communication quality between the network device and the terminal device.

[0008] Based on the first or second aspect mentioned above, one or more of the following implementation methods may exist:

[0009] In one possible implementation, the first message includes at least one of the following:

[0010] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0011] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0012] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0013] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information;

[0014] A measurement identifier, used to identify the first message; or,

[0015] A credibility indicator, which is used to indicate the credibility of the prediction information provided by the terminal device and at least one of the following: a calculation index for the credibility, a calculation method for the credibility, or a reporting configuration for the credibility.

[0016] Based on the above scheme, the first message carries a prediction quantity indicator, enabling the terminal device to accurately determine the prediction information; the first message carries an AI model indicator, enabling the terminal device to accurately use the AI ​​model that generates the prediction information; the first message carries a prediction time indicator, enabling the terminal device to accurately determine the prediction information within a specified time range of the network device; the first message carries a reporting time indicator, enabling the terminal device to accurately determine the reporting time of the prediction information; and the first message carries a credibility indicator, enabling the terminal device to accurately determine the credibility of the prediction information and the reporting method for the credibility.

[0017] In one possible implementation, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes cell-level measurement prediction information or beam-level measurement prediction information, and the reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes handover failure prediction information or radio link failure prediction information, and the reliability calculation index includes at least one of accuracy, precision, recall, or comprehensive evaluation index; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes measurement event prediction information, and the reliability calculation index includes at least one of macro average, micro average, or weighted average.

[0018] Based on the above scheme, the terminal device uses corresponding credibility calculation indicators according to different types of prediction information, which helps to accurately determine the credibility of the prediction information.

[0019] In one possible implementation, the credibility is calculated by using the credibility of prediction information from historical moments; or, the credibility is calculated by using the credibility of prediction information obtained through AI evaluation model reasoning.

[0020] Based on the above scheme, using the credibility of prediction information at historical moments to determine the credibility of prediction information at the current moment helps to simplify the credibility calculation method, thereby improving the calculation efficiency of credibility.

[0021] In one possible implementation, the confidence level is calculated using the confidence level of prediction information at historical time points, including: the confidence level is calculated by using the confidence level of prediction information at time NT as the confidence level of prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

[0022] In one possible implementation, the credibility is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

[0023] Based on the above approach, using the test accuracy or training accuracy of the AI ​​model to determine the credibility of the predicted information helps to accurately determine the credibility.

[0024] In one possible implementation, the method further includes: receiving model configuration information from the network device, the model configuration information including information of at least one AI model and credibility calculation auxiliary information corresponding to the at least one AI model, the credibility calculation auxiliary information including at least one of the following: an index of the credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric; wherein the credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

[0025] In one possible implementation, the credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

[0026] Thirdly, embodiments of this application provide a communication method that can be executed by a terminal device or a module (such as a chip or chip system) within the terminal device. The method includes: receiving a first message from a source network device, the first message requesting the terminal device to report prediction information and first confidence calculation auxiliary information; and sending a second message to the source network device, the second message including the prediction information and the first confidence calculation auxiliary information, wherein the first confidence calculation auxiliary information includes an identifier of the AI ​​model used by the terminal device to generate the prediction information, an identifier of the AI ​​function, or an identifier of the AI ​​service.

[0027] In one possible implementation, the first message includes at least one of the following:

[0028] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0029] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0030] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0031] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or...

[0032] A measurement identifier, which is used to identify the first message.

[0033] Fourthly, embodiments of this application provide a communication method that can be executed by a source network device or a module (such as a chip or chip system) within the source network device. The method includes: sending a first message to a terminal device, the first message requesting the terminal device to report prediction information and first credibility calculation auxiliary information; receiving a second message from the terminal device, the second message including the prediction information and the first credibility calculation auxiliary information, the first credibility calculation auxiliary information including an identifier of the AI ​​model used by the terminal device when generating the prediction information, an identifier of the AI ​​function, or an identifier of the AI ​​service; determining the credibility of the prediction information based on the first credibility calculation auxiliary information and credibility configuration information, wherein the credibility configuration information includes at least one of a credibility calculation index, a credibility calculation method, or a credibility reporting configuration; and sending a third message to a target network device, the third message including the prediction information and the credibility of the prediction information.

[0034] Based on the above scheme, the source network device and the target network device can negotiate the credibility configuration information. After receiving the prediction information from the terminal device, the source network device can calculate the credibility of the prediction information and report the prediction information and credibility to the target network device. This helps the target network device to accurately use the prediction information reported by the terminal device, thereby improving the communication quality between the target network device and the terminal device.

[0035] In one possible implementation, the trust configuration information is obtained through negotiation between the source network device and the target network device.

[0036] In one possible implementation, the source network device and the target network device negotiate the trust configuration information according to the following method: the source network device sends its trust configuration information to the target network device, and the target network device sends its trust configuration information to the source network device.

[0037] In one possible implementation, the first message includes at least one of the following:

[0038] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0039] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0040] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0041] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or...

[0042] A measurement identifier, which is used to identify the first message.

[0043] In one possible implementation, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes cell-level measurement prediction information or beam-level measurement prediction information, and the reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes handover failure prediction information or radio link failure prediction information, and the reliability calculation index includes at least one of accuracy, precision, recall, or comprehensive evaluation index; or, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes measurement event prediction information, and the reliability calculation index includes at least one of macro average, micro average, or weighted average.

[0044] In one possible implementation, the credibility is calculated by using the credibility of prediction information from historical moments; or, the credibility is calculated by using the credibility of prediction information obtained through AI evaluation model reasoning.

[0045] In one possible implementation, the confidence level is calculated using the confidence level of prediction information at historical time points, including: the confidence level is calculated by using the confidence level of prediction information at time NT as the confidence level of prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

[0046] In one possible implementation, the credibility is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

[0047] In one possible implementation, the method further includes: receiving model configuration information from the target network device, the model configuration information including information of at least one AI model and second credibility calculation auxiliary information corresponding to the at least one AI model, the second credibility calculation auxiliary information including at least one of the following: index of the second credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric; wherein the second credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

[0048] In one possible implementation, the credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

[0049] Fifthly, embodiments of this application provide a communication device, which may be a terminal device or a module (such as a chip or chip system) within a terminal device. This device has the function of implementing any of the methods described in the first and third aspects above. This function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions.

[0050] Sixthly, embodiments of this application provide a communication device, which may be a network device or a module (such as a chip or chip system) within a network device. This device has the function of implementing any of the methods described in the second and fourth aspects above. This function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions.

[0051] In a seventh aspect, embodiments of this application provide a communication device, including units or means for performing various steps of any of the implementation methods in the first to fourth aspects described above.

[0052] Eighthly, embodiments of this application provide a communication device, including a processor and an interface circuit. The processor is configured to communicate with other devices via the interface circuit and execute any of the implementation methods described in the first to fourth aspects. The processor may include one or more devices.

[0053] Optionally, the communication device may further include a memory for storing computer instructions, the memory being coupled to a processor that executes the computer instructions stored in the memory to cause the device to perform any of the implementation methods of the first to fourth aspects described above.

[0054] Ninthly, embodiments of this application also provide a computer program product, which includes a computer program or instructions that, when executed by a communication device, cause any of the implementation methods in the first to fourth aspects to be executed.

[0055] In a tenth aspect, embodiments of this application also provide a computer-readable storage medium storing instructions that, when executed on a communication device, cause any implementation method in the first aspect to be performed.

[0056] Eleventhly, this application provides a chip (or chip system) including a processor coupled to a memory storing a computer program; the processor is used to invoke part or all of the computer program in the memory, so that any implementation method of the first to fourth aspects described above is executed.

[0057] In a twelfth aspect, this application provides a communication system including a target network device and a source network device for performing any implementation method of the fourth aspect; the target network device is configured to receive a third message from the source network device, the third message including prediction information and the confidence level of the prediction information. Attached Figure Description

[0058] Figure 1(a) is a schematic diagram of the architecture of the communication system used in the embodiments of this application;

[0059] Figure 1(b) shows a schematic diagram of a network device;

[0060] Figures 2-4 A flowchart illustrating the communication method provided in an embodiment of this application;

[0061] Figure 5 This is a schematic diagram of the structure of the communication device provided in the embodiments of this application;

[0062] Figure 6 A schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0063] Figure 1(a) is a schematic diagram of the architecture of the communication system applied in the embodiments of this application. The communication system 1000 shown in Figure 1(a) includes a wireless access network 100 and a core network 200. Optionally, the communication system 100 also includes an Internet 300. The wireless access network 100 may include at least one network device (110a and 110b in Figure 1(a)) and at least one terminal device (120a-120j in Figure 1(a)). The terminal device is connected to the network device wirelessly, and the network device is connected to the core network wirelessly or via a wired connection. The core network device and the network device may be independent and different physical devices, or the functions of the core network device and the logical functions of the network device may be integrated on the same physical device, or a single physical device may integrate some of the functions of the core network device and some of the functions of the network device. Terminal devices and network devices may be interconnected via wired or wireless connections. Figure 1(a) is just a schematic diagram. The communication system may also include other network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in Figure 1(a).

[0064] Network devices are devices within a wireless network, such as radio access network (RAN) nodes that connect terminal devices to the wireless network. Examples of RAN nodes include: next-generation NodeBs (gNBs), transmission reception points (TRPs), evolved Node Bs (eNBs), radio network controllers (RNCs), Node Bs (NBs), base station controllers (BSCs), base transceiver stations (BTSs), home base stations (e.g., home evolved NodeBs or home Node Bs (HNBs), base band units (BBUs), wireless fidelity (Wi-Fi) access points (APs), and integrated access and backhaul (IABs). In a network architecture, network devices can refer to central units (CUs), distributed units (DUs), or radio units (RUs), or they can be composed of CUs, DUs, and RUs. CUs and DUs can be understood as a logical functional division of a base station. Physically, CUs and DUs can be separate or deployed together; this application does not specifically limit this. The embodiments of this application do not limit the specific technologies or device forms used in the network devices.

[0065] A terminal device is a device with wireless transceiver capabilities. Terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water (such as ships); and they can be deployed in the air (such as airplanes, balloons, and satellites). The terminal device can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical care, wireless terminal device in smart grids, wireless terminal device in transportation safety, wireless terminal device in smart cities, wireless terminal device in smart homes, and may also include user equipment (UE), etc.

[0066] Network devices and terminal devices can be fixed in location or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and artificial satellites. The embodiments of this application do not limit the application scenarios of the network devices and terminal devices.

[0067] The roles of network devices and terminal devices can be relative. For example, the helicopter or drone 120i in Figure 1(a) can be configured as a mobile network device. For terminal devices 120j that access the wireless access network 100 through 120i, terminal device 120i is a network device; however, for network device 110a, 120i is a terminal device. That is, 110a and 120i communicate through a wireless air interface protocol. Of course, 110a and 120i can also communicate through a network device-to-network device interface protocol. In this case, relative to 110a, 120i is also a network device. Therefore, both network devices and terminal devices can be collectively referred to as communication devices. 110a and 110b in Figure 1(a) can be called communication devices with network device functions, and 120a-120j in Figure 1(a) can be called communication devices with terminal device functions.

[0068] Communication between network devices and terminal devices, between network devices, and between terminal devices can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0069] In the embodiments of this application, the functions of the network device can be executed by modules (such as chips) within the network device, or by a control subsystem that includes network device functions. This control subsystem, including network device functions, can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of the terminal device can be executed by modules (such as chips or modems) within the terminal device, or by a device that includes terminal device functions.

[0070] In this application, the network device sends downlink signals or downlink information to the terminal device, with the downlink information carried on the downlink channel; the terminal device sends uplink signals or uplink information to the network device, with the uplink information carried on the uplink channel. In order to communicate with the network device, the terminal device needs to establish a wireless connection with a cell controlled by the network device. The cell with which the terminal device has established a wireless connection is called the serving cell of that terminal device.

[0071] Figure 1(b) shows a schematic diagram of a network device. As shown in Figure 1(b), the network device includes at least one of the following: one or more CUs, one or more DUs, or one or more RUs. For clarity, only one CU, one DU, and one RU are shown in Figure 1(b). The CU is used to connect to the core network and one or more DUs. Optionally, the CU may have some of the core network's functions. The CU may include a CU-control plane (CP) and a CU-user plane (UP).

[0072] The CU and DU can be configured according to the protocol layer functions of the wireless network they implement: for example, the CU can be configured to implement the functions of the Packet Data Convergence Protocol (PDCP) layer and above (such as the Radio Resource Control (RRC) layer and / or the Service Data Adaptation Protocol (SDAP) layer); the DU can be configured to implement the functions of the protocol layers below the PDCP layer (such as the Radio Link Control (RLC) layer, the Medium Access Control (MAC) layer, and / or the Physical (PHY) layer). Alternatively, the CU can be configured to implement the functions of the protocol layers above the PDCP layer (such as the RRC and / or SDAP layers), and the DU can be configured to implement the functions of the protocol layers below the PDCP layer (such as the RLC, MAC, and / or PHY layers).

[0073] The above CU and DU configurations are merely examples; the functions of the CU and DU can be configured as needed. For instance, the CU or DU can be configured to have more protocol layer functions, or only some protocol layer processing functions. For example, some RLC layer functions and protocol layer functions above the RLC layer can be placed in the CU, while the remaining RLC layer functions and protocol layer functions below the RLC layer can be placed in the DU. Furthermore, the functions of the CU or DU can be divided according to service type or other system requirements, such as by latency. Functions that require low latency can be placed in the DU, while functions that do not require low latency can be placed in the CU.

[0074] DU and RU can cooperate to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of DU and RU can be configured in various ways depending on the design. For example, a DU can be configured to implement baseband functions, and an RU can be configured to implement mid-RF functions. Another example is that a DU can be configured to implement higher-level functions in the PHY layer, and an RU can be configured to implement lower-level functions in the PHY layer, or to implement both lower-level and RF functions. Higher-level functions in the physical layer can include a portion of the physical layer's functions that are closer to the MAC layer, while lower-level functions in the physical layer can include another portion of the physical layer's functions that are closer to the mid-RF side.

[0075] The CU and DU can be separate entities or included in the same network element, such as a baseband unit (BBU). The RU can be included in radio frequency equipment or radio frequency units, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). In different systems, CU, DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open radio access network (ORAN) system, CU can also be called O-CU (open CU), DU can be called O-DU, and RU can be called O-RU. Any of the CU (or CU-CP, CU-UP), DU, and RU units in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0076] To facilitate understanding of the content of this application, the nouns or terms involved in the embodiments of this application will be explained below.

[0077] I. Artificial Intelligence (AI)

[0078] AI is a technology that simulates complex calculations by mimicking the human brain. With the improvement of data storage and computing power, AI is being used more and more. Currently, 3GPP has designed several basic application scenarios for AI on the RAN side, including: energy saving, load balancing, mobility optimization, channel status information reference signal (CSI-RS) feedback enhancement, beam management enhancement, and positioning accuracy enhancements.

[0079] II. AI Mobility

[0080] The current protocol will introduce the topic of AI mobility. This research will focus on enhancing air interface mobility in RRC-CONNECTED mode, following the existing mobility framework, where handover decisions are always made on the network side. For network-triggered L3 handover, research on AI-assisted mobility may include AI-based radio resource management (RRM) measurement and event prediction. Specific examples include cell-level measurement prediction, beam-level measurement prediction, handover failure (HOF) prediction, radio link failure (RLF) prediction, and measurement event prediction.

[0081] In AI-based prediction applications, terminal devices typically report their measurement information, such as RSRP, RSRQ, and SINR, to network devices. The network devices then use this measurement information and AI models to make predictions.

[0082] Alternatively, the terminal device can make predictions based on measurement information and AI models, obtain prediction information, and report the prediction information to the network device. However, the network device cannot know whether the prediction information is reliable, which prevents the network device from using the prediction information correctly.

[0083] To address this problem, this application provides corresponding embodiments, which are described in detail below.

[0084] Figure 2 This is a flowchart illustrating a communication method provided in an embodiment of this application. The method is executed by a network device or a module of a network device (such as a chip or chip system), and a terminal device or a module of a terminal device (such as a chip or chip system). The following description uses the execution of this method by a network device and a terminal device as examples.

[0085] The method includes the following steps:

[0086] Step 201: The network device sends a first message to the terminal device. Correspondingly, the terminal device receives the first message.

[0087] The first message may be, for example, a request message, a prediction information request message, or a notification message, and this application does not limit the type of the first message.

[0088] The first message is used to request the terminal device to report prediction information and the reliability of the prediction information.

[0089] The first message includes at least one of the following information (1) to (6):

[0090] (1) Predictive quantity indication.

[0091] This prediction quantity indication is used to indicate the prediction information that the terminal device needs to provide. For example, based on the prediction quantity indication, the terminal device performs one or more of the following predictions: cell-level measurement prediction, beam-level measurement prediction, handover failure prediction, radio link failure prediction, measurement event prediction, service prediction, traffic prediction, RRC status prediction, mobile path prediction, or QoS parameter prediction. Here, "measurement" can be, for example, measuring the RSRP, RSRQ, or SINR of a reference signal.

[0092] (2) AI model instructions.

[0093] The AI ​​model indicator is used to indicate the AI ​​model used by the terminal device when inferring and predicting information. For example, the AI ​​model indicator may be an AI model identifier, an AI function identifier, an AI business identifier, or other identifiers associated with an AI model / AI function / AI business identifier.

[0094] (3) Predicted time indication.

[0095] The prediction time indicator is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device, that is, to indicate which time point or time period the terminal device should predict.

[0096] (4) Reporting time instructions.

[0097] The reporting time indicator is used to indicate the period during which the terminal device reports forecast information (for cases of multiple reports), or to indicate the time during which the terminal device reports forecast information (for cases of one-time reports).

[0098] Optionally, the reporting time indicator is also used to indicate the deadline (or valid time) for reporting prediction information. That is, if the terminal device reports the prediction information after the deadline, the network device will consider the prediction information unreliable even if it receives the prediction information.

[0099] It should be noted that if the first message does not include the reporting time indication, it implicitly instructs the terminal device to make a one-time report, that is, to report only once. Optionally, the time for the terminal device to report the prediction information can also be implicitly indicated. For example, the prediction information can be reported immediately after it is generated, or after a set time has elapsed after the prediction information is generated, or after the terminal device has switched over, and so on.

[0100] (5) Measurement markings.

[0101] This measurement identifier is used to identify the first message initiated by the network device. Since the network device may send the first message to the terminal device multiple times, different measurement identifiers can be used to distinguish different first messages. Furthermore, the terminal device can carry the measurement identifier when reporting prediction information, so that the network device can distinguish different prediction information from the terminal device.

[0102] It should be noted that different AI model instructions, prediction time instructions, or reporting time instructions can be configured for different prediction information from terminal devices.

[0103] (6) Credibility indicator.

[0104] The credibility indicator is used to indicate the credibility of the prediction information provided by the terminal device and at least one of the calculation indicators, calculation methods or reporting configurations for indicating credibility, or the credibility indicator is used to indicate at least one of the calculation indicators, calculation methods or reporting configurations for credibility.

[0105] The following sections explain the calculation metrics for credibility, the calculation method for credibility, and the configuration for reporting credibility.

[0106] ① Indicators for calculating credibility.

[0107] Credibility metrics are used to indicate the standards or formulas used to calculate credibility.

[0108] For example, if the prediction indicator is used to indicate the need for the terminal device to provide prediction information, including cell-level measurement prediction information or beam-level measurement prediction information, since this type of prediction is a continuous value prediction, the calculated index can be one or more of the following indices: Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), or Mean Absolute Percentage Error (MAPE). Wherein, MSE is the ratio of the square of the deviation between the predicted value and the actual measured value to the number of measurements. RMSE is the square root of MSE. MAE is the average of the absolute values ​​of the deviations between the predicted value and the actual measured value. MAPE is the average of the deviations between the predicted value and the actual measured value divided by the absolute values ​​of the actual measured values.

[0109] For example, if the prediction indicator is used to indicate the prediction information required from the terminal device, including information on handover failure prediction or wireless link failure prediction, since this type of prediction belongs to binary discrete value prediction (i.e., the prediction result is yes or no), the calculated metric can be one or more of the following metrics: Accuracy, Precision, Recall, and the overall evaluation metric (F1). Accuracy is the number of correctly predicted samples divided by the total number of samples. Precision is the number of predicted and actually occurring samples divided by the number of predicted occurring samples. Recall is the number of predicted and actually occurring samples divided by the number of actually occurring samples. The overall evaluation metric is a weighted harmonic average of precision and recall, i.e., F1 = 2 * (Precision + Recall) / (Precision * Recall).

[0110] For example, if the predictive measure indicator is used to indicate the predictive information required from the terminal device, including information on the prediction of measurement events, since this type of prediction belongs to multi-class discrete value prediction (i.e., prediction of multiple event types), the calculated indicator can be one or more of the following indicators: macro-averaging, micro-averaging, and weight-averaging. Macro-averaging refers to first calculating the evaluation indicators for each class (i.e., the evaluation indicators Precision / accuracy / Recall / F1 in the binary classification problem above), and then calculating the arithmetic mean of the indicators. Micro-averaging refers to first averaging the elements of the confusion matrix, and then calculating the evaluation indicators. Weight-averaging refers to assigning different weights to different classes (the weights are determined based on the true distribution proportion of that class), then multiplying each class by its weight, and finally summing the results.

[0111] It should be noted that the above calculation indicators are only examples for illustration. This application does not impose the above restrictions on the type and method of calculation indicators, and other calculation indicators may also be used.

[0112] ② The method for calculating credibility.

[0113] The credibility calculation method is used to indicate how credibility is calculated. Specifically, the credibility calculation method can be indicated by the parameter value of the calculation method or by the index value of the calculation method. Three different calculation methods are described below.

[0114] Calculation method 1 uses the reliability of prediction information from historical moments.

[0115] For example, the confidence level of the prediction information at time NT is used as (or approximately as) the confidence level of the prediction information at time N.

[0116] Here, N is the time indicated by the prediction time indicator. Network devices can configure parameter T for terminal devices, and can pre-configure different T values ​​for different AI models / AI use cases / AI functions / predictive information used by the terminal devices. For example, if N represents 10:00 and T is 15 minutes, then the credibility of the prediction information at 10:00 is determined based on the credibility of the prediction information at 9:45.

[0117] Calculation Method 2: The accuracy of the AI ​​model is determined by using the test accuracy or training accuracy of the corresponding AI model.

[0118] The AI ​​model instruction mentioned above is the same as the AI ​​model instruction in the first message.

[0119] For example, a network device can send model configuration information to a terminal device. This model configuration information includes information about at least one AI model and corresponding credibility calculation auxiliary information for at least one AI model. The credibility calculation auxiliary information includes at least one of the following: an index of credibility calculation auxiliary information, associated test set data (which may only include input data, excluding label data), associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric. The credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model. The index of the credibility calculation auxiliary information is used to identify or index the credibility calculation auxiliary information. The associated test set data refers to the input data used to calculate the test accuracy or training accuracy of the AI ​​model. The associated AI model / AI service / AI function represents the AI ​​model / AI service / AI function related to credibility calculation. The associated prediction information indicates that the test set data is used to determine the test accuracy or training accuracy of the AI ​​model as the credibility of the prediction information for a specific prediction. The associated credibility calculation metric indicates the standard or formula for calculating credibility. Optionally, when the credibility calculation auxiliary information carries credibility calculation indicators, the credibility indication in the first message mentioned above may not need to indicate the credibility calculation indicators.

[0120] Optionally, the test set data can also be distributed by other nodes such as the 5G core network or the operations, administration and management (OAM) system. If it is strongly related to the AI ​​model / task, the above-mentioned specific test set data can be implemented by a dataset index.

[0121] For example, a terminal device uses an AI model to determine predictive information and determines the test accuracy or training accuracy of the AI ​​model based on test set data, using the test accuracy or training accuracy of the AI ​​model as the credibility of the predictive information.

[0122] Calculation method 3: reinforcement learning.

[0123] Reinforcement learning refers to the process by which terminal devices infer the credibility of predicted information based on AI evaluation models. In other words, predicted information is input into the AI ​​evaluation model, and the output is the credibility of the predicted information. Network devices can pre-configure different AI evaluation models for different AI models / AI use cases / AI functions / predicted information used by terminal devices. Specifically, the AI ​​model / AI use case / AI function is used to generate predicted information, and the AI ​​evaluation model is used to generate the credibility of the predicted information.

[0124] ③ Configuration for reporting credibility.

[0125] The credibility reporting configuration is used to indicate the reporting thresholds related to the credibility of the prediction information, such as credibility size thresholds and / or credibility time thresholds.

[0126] The confidence threshold includes a minimum confidence threshold and / or a maximum confidence threshold for the prediction information. For example, if the confidence of the prediction information is less than the minimum confidence threshold, the terminal device does not need to send the prediction information, but instead sends a failure indication and a cause value to the network device, such as low prediction accuracy. In this case, the terminal device can report the actual measurement value, allowing the network device to make a prediction based on the actual measurement value. For example, if the confidence of the prediction information is greater than the maximum confidence threshold, the terminal device may not include the confidence level of the prediction information when sending it.

[0127] The credibility time threshold is used to indicate the credibility of prediction information provided by a terminal device for a specified time period. For example, if a network device predicts that communication resources may be insufficient during the time period [t1, t2], it requests the terminal device to provide prediction information for that time period along with the credibility of that prediction information. It should be noted that when reporting prediction information, the terminal device can report the corresponding credibility for all prediction information, or it can report the corresponding credibility for only a portion of the prediction information (e.g., prediction information within a time period of interest to the network device).

[0128] Step 202: The terminal device sends a second message to the network device. Accordingly, the network device receives the second message.

[0129] The second message may be, for example, a response message, a prediction information response message, or a reporting message, and this application does not limit the type of the second message.

[0130] The second message includes forecast information and the credibility of that forecast information.

[0131] The predicted information is obtained by the terminal device through measurement based on the first message and reasoning from the measurement results using an AI model. For example, assuming the predicted quantity indicator is used to indicate that the predicted information required from the terminal device includes mobile path prediction information, the terminal device can perform mobile path measurement, input the measurement results into the AI ​​model to obtain mobile path prediction information, and send the mobile path prediction information to the network device through the second message.

[0132] Optionally, if the terminal device cannot carry credibility, the reason can be carried in the second message, such as the terminal device not having a suitable AI evaluation model, the terminal device not having historical prediction information at the NT time, or the terminal device not having enough computing resources.

[0133] As one implementation method, before step 201, the network device can also receive a request message from a third-party (Over The Top, OTT) device on the operator's network. This request message is used to request the terminal device to report prediction information and the reliability of the prediction information. Then, the network device executes the above step 201 according to the request message, that is, sends the first message to the terminal device.

[0134] Based on the above scheme, the network device requests the terminal device to report the prediction information and the credibility of the prediction information. In this way, the network device obtains the prediction information and the credibility of the prediction information from the terminal device, which helps the network device to accurately use the prediction information reported by the terminal device, thereby improving the communication quality between the network device and the terminal device.

[0135] Figure 3 This is a flowchart illustrating a communication method provided in an embodiment of this application. The method is executed by a network device or a module (such as a chip) of a network device, and a terminal device or a module (such as a chip) of a terminal device. The following description uses the execution of this method by a network device and a terminal device as an example. The network device includes an O-CU and an O-DU.

[0136] The method includes the following steps:

[0137] Step 301: The O-DU sends a first message to the O-RU. Correspondingly, the O-RU receives the first message.

[0138] Step 302: The O-RU sends a first message to the terminal device. Accordingly, the terminal device receives the first message.

[0139] Step 303: The terminal device sends a second message to the O-RU. Correspondingly, the O-RU receives the second message.

[0140] Step 304: The O-RU sends a second message to the O-DU. Correspondingly, the O-DU receives the second message.

[0141] For the specific meanings of the first and second messages, please refer to [link / reference]. Figure 2 The relevant descriptions in the embodiments.

[0142] Based on the above scheme, the network device requests the terminal device to report the prediction information and the credibility of the prediction information. In this way, the network device obtains the prediction information and the credibility of the prediction information from the terminal device, which helps the network device to accurately use the prediction information reported by the terminal device, thereby improving the communication quality between the network device and the terminal device.

[0143] Figure 4 This is a flowchart illustrating a communication method provided in an embodiment of this application. The method is executed by a network device (including a source network device and a target network device) or a module (such as a chip) of the network device, and a terminal device or a module (such as a chip) of the terminal device. The following description uses the execution of this method by a network device and a terminal device as an example. Here, the source network device refers to the network device accessed by the terminal device before the handover, and the target network device refers to the network device accessed by the terminal device after the handover.

[0144] The method includes the following steps:

[0145] Step 401: The source network device and the target network device negotiate the credibility configuration information of the prediction information.

[0146] The trustworthiness configuration information includes at least one of the following: trustworthiness calculation metrics, trustworthiness calculation method, or trustworthiness reporting configuration. For the meanings of the trustworthiness calculation metrics, trustworthiness calculation method, and trustworthiness reporting configuration, please refer to [link to relevant documentation]. Figure 2 The description in the embodiments.

[0147] In one implementation, the source network device and the target network device can negotiate the reliability configuration information of the prediction information in a newly defined process, or they can negotiate the reliability configuration information of the prediction information in an existing process (such as the XnSetup or XnConfigurationUpdate process).

[0148] For example, the source network device and the target network device may negotiate in any of the following ways, but not limited to:

[0149] Method 1: The source network device sends its trust configuration information to the target network device, and the target network device sends its trust configuration information to the source network device. This indicates that the target network device has received the trust configuration information from the source network device and then sends its trust configuration information back to the source network device.

[0150] Method 2: The source network device sends its trust configuration information to the target network device, and the target network device sends its trust configuration information back to the source network device, specifying which trust configuration information comes from the source network device and which comes from the target network device.

[0151] Step 401 is optional. In another implementation, the trust configuration information on the source network device can also be pre-configured on the source network device by other devices.

[0152] Step 402: The source network device sends a first message to the terminal device. Correspondingly, the terminal device receives the first message.

[0153] The first message is used to request the terminal device to report prediction information and auxiliary information for the first confidence calculation.

[0154] For example, the first message includes a confidence calculation assistance information request indication, which is used to request confidence calculation assistance information. This confidence calculation assistance information request indication may include 1 bit, which indicates a request for confidence calculation assistance information for all predefined prediction information. Alternatively, the confidence calculation assistance information request indication includes a bitmap comprising N bits, where N is the total number of predefined prediction information types. Each bit in the bitmap corresponds to confidence calculation assistance information for one type of prediction information; therefore, the bitmap can be used to indicate a request for confidence calculation assistance information for some or all of the prediction information. Furthermore, the confidence calculation assistance information request indication may additionally include indication information for indicating detailed confidence calculation assistance information identifiers, such as at least one of AI model identifier indication information, AI business identifier indication information, or AI function identifier indication information.

[0155] Step 403: The terminal device sends a second message to the source network device. Correspondingly, the source network device receives the second message.

[0156] The second message includes prediction information and first confidence calculation auxiliary information. The first confidence calculation auxiliary information includes the identifier of the AI ​​model used by the terminal device to generate the prediction information, the identifier of the AI ​​function, or the identifier of the AI ​​service. For different implementation methods of the prediction information, please refer to... Figure 2 The relevant descriptions in the embodiments will not be repeated here.

[0157] The source network device calculates auxiliary information based on the first level of trustworthiness and selects the corresponding trustworthiness calculation indicators, trustworthiness calculation methods, and trustworthiness reporting configurations from the trustworthiness configuration information.

[0158] Step 404: The source network device calculates auxiliary information and credibility configuration information based on the first credibility level to determine the credibility of the prediction information.

[0159] The source network device calculates auxiliary information based on the first credibility level corresponding to the predicted information. It selects the appropriate credibility calculation metric, credibility calculation method, and credibility reporting configuration from the credibility configuration information. Then, it determines the credibility of the predicted information based on the credibility calculation metric and method, and decides whether to report the credibility level based on the credibility reporting configuration. Note that the credibility calculation metric, credibility calculation method, or credibility reporting configuration may be the same or different for different predicted information.

[0160] Step 405: The source network device sends a third message to the target network device. Correspondingly, the target network device receives the third message.

[0161] For example, the third message may be a switch request message or other types of messages, which are not limited in this application.

[0162] The third message includes forecast information and the credibility of that forecast information.

[0163] Upon receiving the third message, the target network device can determine whether to use the predictive information, or how to use it. Taking a handover request message as an example, the target network device determines whether to accept the access requests from terminal devices based on the reliability of at least one predictive message in the third message. For instance, if the target network device receives access requests from multiple terminal devices, but resources are limited and it can only accept access requests from two terminal devices, the target network device can select the access requests from the two terminal devices with the highest reliability, and send a handover request failure message to the source network device of the other terminal devices, indicating the reason (e.g., the predictive information of the terminal devices has low reliability or resources are limited).

[0164] In another implementation, the third message may not carry prediction information, but only a confidence level, which indicates the confidence level of the third message. The confidence level of the third message may be determined based on the confidence level of the prediction information, or it may be the same as the confidence level of the prediction information.

[0165] Based on the above scheme, the source network device and the target network device can negotiate the credibility configuration information. After receiving the prediction information from the terminal device, the source network device can calculate the credibility of the prediction information and report the prediction information and credibility to the target network device. This helps the target network device to accurately use the prediction information reported by the terminal device, thereby improving the communication quality between the target network device and the terminal device.

[0166] It is understood that, in order to achieve the functions in the above embodiments, the terminal device or network device includes hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0167] Figure 5 and Figure 6 The diagram illustrates the possible structures of communication devices provided in the embodiments of this application. These communication devices can be used to implement the functions of the terminal device or network device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be a terminal device or a network device, or it can be a module (such as a chip) applied to the terminal device or network device.

[0168] Figure 5 The communication device 500 shown includes a processing unit 510 and a transceiver unit 520. The communication device 500 is used to implement the functions of the terminal device or network device in the above method embodiments.

[0169] When the communication device 500 is used to achieve the above Figure 2 or Figure 3 In the method embodiment, the terminal device functions as follows: the processing unit 510 controls the transceiver unit 520 to receive a first message from the network device, the first message being used to request the terminal device to report prediction information and the reliability of the prediction information; and to send a second message to the network device, the second message including the prediction information and the reliability of the prediction information.

[0170] In one possible implementation, the first message includes at least one of the following:

[0171] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0172] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0173] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0174] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information;

[0175] A measurement identifier, used to identify the first message; or,

[0176] A credibility indicator, which is used to indicate the credibility of the prediction information provided by the terminal device and at least one of the following: a calculation index for the credibility, a calculation method for the credibility, or a reporting configuration for the credibility.

[0177] In one possible implementation, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes cell-level measurement prediction information or beam-level measurement prediction information, and the reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes handover failure prediction information or radio link failure prediction information, and the reliability calculation index includes at least one of accuracy, precision, recall, or comprehensive evaluation index; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes measurement event prediction information, and the reliability calculation index includes at least one of macro average, micro average, or weighted average.

[0178] In one possible implementation, the credibility is calculated by using the credibility of prediction information from historical moments; or, the credibility is calculated by using the credibility of prediction information obtained through AI evaluation model reasoning.

[0179] In one possible implementation, the confidence level is calculated using the confidence level of prediction information at historical time points, including: the confidence level is calculated by using the confidence level of prediction information at time NT as the confidence level of prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

[0180] In one possible implementation, the credibility is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

[0181] In one possible implementation, the method further includes: receiving model configuration information from the network device, the model configuration information including information of at least one AI model and credibility calculation auxiliary information corresponding to the at least one AI model, the credibility calculation auxiliary information including at least one of the following: an index of the credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric; wherein the credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

[0182] In one possible implementation, the credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

[0183] When the communication device 500 is used to achieve the above Figure 2 or Figure 3 In the method embodiment, the network device functions as follows: the processing unit 510 is used to control the transceiver unit 520 to send a first message to the terminal device, the first message being used to request the terminal device to report prediction information and the reliability of the prediction information; and to receive a second message from the terminal device, the second message including the prediction information and the reliability of the prediction information.

[0184] In one possible implementation, the first message includes at least one of the following:

[0185] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0186] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0187] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0188] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information;

[0189] A measurement identifier, used to identify the first message; or,

[0190] A credibility indicator, which is used to indicate the credibility of the prediction information provided by the terminal device and at least one of the following: a calculation index for the credibility, a calculation method for the credibility, or a reporting configuration for the credibility.

[0191] In one possible implementation, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes cell-level measurement prediction information or beam-level measurement prediction information, and the reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes handover failure prediction information or radio link failure prediction information, and the reliability calculation index includes at least one of accuracy, precision, recall, or comprehensive evaluation index; or, the prediction quantity indicator is used to indicate that the prediction information required from the terminal device includes measurement event prediction information, and the reliability calculation index includes at least one of macro average, micro average, or weighted average.

[0192] In one possible implementation, the credibility is calculated by using the credibility of prediction information from historical moments; or, the credibility is calculated by using the credibility of prediction information obtained through AI evaluation model reasoning.

[0193] In one possible implementation, the confidence level is calculated using the confidence level of prediction information at historical time points, including: the confidence level is calculated by using the confidence level of prediction information at time NT as the confidence level of prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

[0194] In one possible implementation, the credibility is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

[0195] In one possible implementation, the method further includes: receiving model configuration information from the network device, the model configuration information including information of at least one AI model and credibility calculation auxiliary information corresponding to the at least one AI model, the credibility calculation auxiliary information including at least one of the following: an index of the credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric; wherein the credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

[0196] In one possible implementation, the credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

[0197] When the communication device 500 is used to achieve the above Figure 4 In the method embodiment, the terminal device functions as follows: the processing unit 510 controls the transceiver unit 520 to receive a first message from the source network device, the first message being used to request the terminal device to report prediction information and first credibility calculation auxiliary information; and to send a second message to the source network device, the second message including the prediction information and the first credibility calculation auxiliary information, the first credibility calculation auxiliary information including the identifier of the AI ​​model used by the terminal device when generating the prediction information, the identifier of the AI ​​function, or the identifier of the AI ​​service.

[0198] In one possible implementation, the first message includes at least one of the following:

[0199] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0200] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0201] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0202] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or...

[0203] A measurement identifier, which is used to identify the first message.

[0204] When the communication device 500 is used to achieve the above Figure 4 In the method embodiment, the source network device has the following functions: a transceiver unit 520 is used to send a first message to a terminal device, the first message being used to request the terminal device to report prediction information and first credibility calculation auxiliary information; and to receive a second message from the terminal device, the second message including the prediction information and the first credibility calculation auxiliary information, the first credibility calculation auxiliary information including the identifier of the AI ​​model used by the terminal device when generating the prediction information, the identifier of the AI ​​function, or the identifier of the AI ​​service; a processing unit 510 is used to determine the credibility of the prediction information based on the first credibility calculation auxiliary information and credibility configuration information, wherein the credibility configuration information includes at least one of credibility calculation indicators, credibility calculation methods, or credibility reporting configurations; the transceiver unit 520 is also used to send a third message to a target network device, the third message including the prediction information and the credibility of the prediction information.

[0205] In one possible implementation, the trust configuration information is obtained through negotiation between the source network device and the target network device.

[0206] In one possible implementation, the first message includes at least one of the following:

[0207] A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device;

[0208] AI model indicator, which is used to indicate the AI ​​model used by the terminal device when inferring and predicting information;

[0209] Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device;

[0210] Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or...

[0211] A measurement identifier, which is used to identify the first message.

[0212] In one possible implementation, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes cell-level measurement prediction information or beam-level measurement prediction information, and the reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes handover failure prediction information or radio link failure prediction information, and the reliability calculation index includes at least one of accuracy, precision, recall, or comprehensive evaluation index; or, the prediction quantity indicator is used to indicate that the prediction information required to be provided by the terminal device includes measurement event prediction information, and the reliability calculation index includes at least one of macro average, micro average, or weighted average.

[0213] In one possible implementation, the credibility is calculated by using the credibility of prediction information from historical moments; or, the credibility is calculated by using the credibility of prediction information obtained through AI evaluation model reasoning.

[0214] In one possible implementation, the confidence level is calculated using the confidence level of prediction information at historical time points, including: the confidence level is calculated by using the confidence level of prediction information at time NT as the confidence level of prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

[0215] In one possible implementation, the credibility is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

[0216] In one possible implementation, the transceiver unit 520 is further configured to receive model configuration information from the target network device. The model configuration information includes information about at least one AI model and second credibility calculation auxiliary information corresponding to the at least one AI model. The second credibility calculation auxiliary information includes at least one of the following: an index of the second credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric. The second credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

[0217] In one possible implementation, the credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

[0218] For a more detailed description of the processing unit 510 and the transceiver unit 520, please refer directly to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0219] Figure 6 The communication device 600 shown includes a processor 610 and an interface circuit 620. The processor 610 and the interface circuit 620 are coupled to each other. It is understood that the interface circuit 620 can be a transceiver or an input / output interface. Optionally, the communication device 600 may also include a memory 630 for storing instructions executed by the processor 610, or storing input data required by the processor 610 to execute instructions, or storing data generated after the processor 610 executes instructions.

[0220] When the communication device 600 is used to implement the above method embodiment, the processor 610 is used to implement the function of the processing unit 510, and the interface circuit 620 is used to implement the function of the transceiver unit 520.

[0221] It is understood that the processor in the embodiments of this application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0222] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Additionally, the ASIC can reside in a terminal device or network device. Alternatively, the processor and storage medium can exist as discrete components in an access network device or terminal.

[0223] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. A computer program is a set of instructions that directs each step of an action of an electronic computer or other device with message processing capabilities. It is typically written in a programming language and runs on a target architecture. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be volatile or non-volatile, or it can include both types of storage media.

[0224] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0225] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates an "or" relationship between the preceding and following related objects; in the formulas of this application, the character " / " indicates a "division" relationship between the preceding and following related objects.

[0226] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

Claims

1. A communication method, characterized in that, The method includes: Receive a first message from a network device, the first message being used to request the terminal device to report prediction information and the reliability of the prediction information; A second message is sent to the network device, the second message including the prediction information and the confidence level of the prediction information.

2. A communication method, characterized in that, The method includes: Send a first message to the terminal device, the first message being used to request the terminal device to report prediction information and the reliability of the prediction information; A second message is received from the terminal device, the second message including the prediction information and the confidence level of the prediction information.

3. The method as described in claim 1 or 2, characterized in that, The first message includes at least one of the following: A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device; An artificial intelligence (AI) model indicator, which is used to indicate the AI ​​model used by the terminal device when reasoning and predicting information; Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device; Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; A measurement identifier, used to identify the first message; or, The credibility indicator is used to indicate the credibility of the prediction information provided by the terminal device, and at least one of the following: a calculation index for the credibility, a calculation method for the credibility, or a reporting configuration for the credibility.

4. The method as described in claim 3, characterized in that, The predicted quantity indicator is used to indicate the required prediction information from the terminal device, including cell-level measurement prediction information or beam-level measurement prediction information. The reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or... The prediction quantity indicator is used to indicate the prediction information required from the terminal device, including handover failure prediction information or wireless link failure prediction information. The reliability calculation index includes at least one of accuracy, precision, recall, or a comprehensive evaluation index; or, The prediction quantity indicator is used to indicate the prediction information that needs to be provided by the terminal device, including information on the prediction of measurement events, and the confidence index includes at least one of macro average, micro average, or weighted average.

5. The method as described in claim 3 or 4, characterized in that, The reliability is calculated using the reliability of prediction information from historical moments; or, The credibility is calculated based on the credibility of the predicted information obtained through AI evaluation model reasoning.

6. The method as described in claim 5, characterized in that, The reliability is calculated using the reliability of prediction information from historical moments, including: The confidence level is calculated by using the confidence level of the prediction information at time NT as the confidence level of the prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

7. The method as described in claim 3 or 4, characterized in that, The reliability is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

8. The method as described in claim 7, characterized in that, The method further includes: The system receives model configuration information from the network device. The model configuration information includes information about at least one AI model and credibility calculation auxiliary information corresponding to the at least one AI model. The credibility calculation auxiliary information includes at least one of the following: an index of the credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric. The credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

9. The method according to any one of claims 3 to 8, characterized in that, The credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

10. A communication method, characterized in that, The method includes: Receive a first message from the source network device, the first message being used to request the terminal device to report prediction information and first confidence calculation auxiliary information; A second message is sent to the source network device. The second message includes the prediction information and the first credibility calculation auxiliary information. The first credibility calculation auxiliary information includes the identifier of the AI ​​model, the identifier of the AI ​​function, or the identifier of the AI ​​service used by the terminal device when generating the prediction information.

11. The method as described in claim 10, characterized in that, The first message includes at least one of the following: A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device; An artificial intelligence (AI) model indicator, which is used to indicate the AI ​​model used by the terminal device when reasoning and predicting information; Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device; Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or... A measurement identifier, which is used to identify the first message.

12. A communication method, characterized in that, The method includes: Send a first message to the terminal device, the first message being used to request the terminal device to report prediction information and first confidence calculation auxiliary information; The system receives a second message from the terminal device. The second message includes the prediction information and the first credibility calculation auxiliary information. The first credibility calculation auxiliary information includes the identifier of the AI ​​model, the identifier of the AI ​​function, or the identifier of the AI ​​service used by the terminal device when generating the prediction information. The credibility of the prediction information is determined based on the first credibility calculation auxiliary information and credibility configuration information, wherein the credibility configuration information includes at least one of credibility calculation indicators, credibility calculation methods, or credibility reporting configurations. A third message is sent to the target network device, the third message including the prediction information and the confidence level of the prediction information.

13. The method as described in claim 12, characterized in that, The trust configuration information is obtained through negotiation between the source network device and the target network device.

14. The method as described in claim 12 or 13, characterized in that, The first message includes at least one of the following: A prediction quantity indicator, which is used to indicate the prediction information that needs to be provided by the terminal device; An artificial intelligence (AI) model indicator, which is used to indicate the AI ​​model used by the terminal device when reasoning and predicting information; Prediction time indication, which is used to indicate the time corresponding to the prediction information that needs to be provided by the terminal device; Reporting time indication, wherein the reporting time indication is used to indicate the period during which the terminal device reports prediction information; or... A measurement identifier, which is used to identify the first message.

15. The method as described in claim 14, characterized in that, The predicted quantity indicator is used to indicate the predicted information required from the terminal device, including cell-level measurement prediction information or beam-level measurement prediction information. The reliability calculation index includes at least one of mean square error, root mean square error, mean absolute error, or mean absolute percentage error; or... The prediction quantity indicator is used to indicate the prediction information required from the terminal device, including handover failure prediction information or wireless link failure prediction information. The reliability calculation index includes at least one of accuracy, precision, recall, or a comprehensive evaluation index; or, The prediction quantity indicator is used to indicate the prediction information that needs to be provided by the terminal device, including information on the prediction of measurement events, and the confidence index includes at least one of macro average, micro average, or weighted average.

16. The method according to any one of claims 12 to 15, characterized in that, The reliability is calculated using the reliability of prediction information from historical moments; or, The credibility is calculated based on the credibility of the predicted information obtained through AI evaluation model reasoning.

17. The method as described in claim 16, characterized in that, The reliability is calculated using the reliability of prediction information from historical moments, including: The confidence level is calculated by using the confidence level of the prediction information at time NT as the confidence level of the prediction information at time N; wherein, N is indicated by the prediction time indicator, and T is configured by the network device.

18. The method according to any one of claims 12 to 15, characterized in that, The reliability is calculated by using the AI ​​model to indicate the test accuracy or training accuracy of the corresponding AI model.

19. The method as described in claim 18, characterized in that, The method further includes: The system receives model configuration information from the target network device. The model configuration information includes information about at least one AI model and second credibility calculation auxiliary information corresponding to the at least one AI model. The second credibility calculation auxiliary information includes at least one of the following: an index of the second credibility calculation auxiliary information, associated test set data, associated AI model, associated AI service, associated AI function, associated prediction information, or associated credibility calculation metric. The second credibility calculation auxiliary information is used to determine the test accuracy or training accuracy of the AI ​​model.

20. The method according to any one of claims 12 to 19, characterized in that, The credibility reporting configuration is used to indicate a reporting threshold related to the credibility of the prediction information. The reporting threshold includes a credibility size threshold and / or a credibility time threshold. The credibility size threshold includes a minimum credibility threshold and / or a maximum credibility threshold. The credibility time threshold is used to indicate the credibility of the prediction information provided by the terminal device at a specified time.

21. A communication device, characterized in that, Includes a module for performing the method according to any one of claims 1 to 20.

22. A communication device, characterized in that, It includes a processor and an interface circuit, the processor being configured to communicate with other devices via the interface circuit and to perform the method according to any one of claims 1 to 20.

23. A computer program product, characterized in that, The computer program product includes instructions that, when executed on a processor, cause the processor to perform the method of any one of claims 1 to 20.

24. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method described in any one of claims 1 to 20.

25. A communication system, characterized in that, It includes a target network device and a source network device for performing the method of any one of claims 12 to 20; the target network device is configured to receive a third message from the source network device, the third message including prediction information and the confidence level of the prediction information.

Images