Beam prediction model switching method and apparatus, terminal, base station, and storage medium

Abstract

Embodiments of the present application relate to the technical field of communications and provide a beam prediction model switching method and apparatus, a terminal, a base station, and a storage medium. The method comprises: obtaining signal qualities corresponding to beams comprised in a first monitoring beam set, and using the signal quality having the highest numerical value as a measured signal quality; acquiring, from the signal qualities corresponding to the beams comprised in the first monitoring beam set, signal qualities of beams comprised in a first measurement beam set, and inputting same into a first beam prediction model to obtain a first predicted signal quality outputted by the first beam prediction model; on the basis of the first predicted signal quality and the measured signal quality, calculating a first prediction error value of the first beam prediction model; and if the first prediction error value is greater than or equal to a specified threshold value, selecting a target beam prediction model from a plurality of second beam prediction models, and switching an effective beam prediction model to the target beam prediction model. The invention enables timely switching to a beam prediction model more suitable for a current scenario.

Description

Beam prediction model switching method, device, terminal, base station and storage medium Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a beam prediction model switching method, device, terminal, base station and storage medium. Background Art

[0002] In mobile communications, factors such as user movement and random signal obstruction can cause time-varying channels. Therefore, repeated beam measurement and tracking are required to accurately determine the channel information between base stations and terminals in real time. Traditional beam prediction involves the base station sending pilot signals in all transmit beam directions to predict the optimal transmit beam direction. However, this approach incurs significant pilot overhead.

[0003] In order to reduce pilot overhead, a beam prediction algorithm based on machine learning has been developed. The beam prediction model can be trained using machine learning, and then the beam prediction model can be used to predict the beam direction of the optimal transmission beam based on the measurement results of fewer beams.

[0004] Due to the time-varying nature of wireless channel environments and the diversity of scenarios, it is difficult to develop a model that generalizes well across time and space. Therefore, it is currently possible to train multiple beam prediction models and select the appropriate one for beam prediction. However, due to terminal mobility and environmental changes, the beam training model suitable for each scenario may vary. Therefore, selecting the appropriate beam prediction model is a pressing issue.

[0005] Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a beam prediction model switching method, apparatus, terminal, base station, and storage medium to timely switch to a beam prediction model that is more suitable for the current scenario. The specific technical solutions are as follows:

[0007] In a first aspect, an embodiment of the present application provides a beam prediction model switching method, which is applied to a terminal, wherein the terminal includes a first beam prediction model and multiple second beam prediction models, and the effective beam prediction model of the terminal is the first beam prediction model. The method includes:

[0008] measuring a pilot signal of each beam included in the first monitoring beam set to obtain a signal quality corresponding to each beam included in the first monitoring beam set, and selecting a signal quality with a maximum value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0009] Obtaining a signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0010] Calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0011] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0012] In a possible implementation manner, selecting a target beam prediction model from the multiple second beam prediction models includes:

[0013] Perform the following traversal operations on each second beam prediction model in turn:

[0014] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0015] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0016] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0017] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0018] In a possible implementation, after calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality, the method further includes:

[0019] If the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

[0020] In a possible implementation, calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality includes:

[0021] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0022] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0023] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0024] The first prediction error value is calculated by the following formula:

[0025] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0026] Among them, α is the filtering factor.

[0027] In a possible implementation, before measuring the pilot signal of each beam included in the first monitoring beam set, the method further includes:

[0028] receiving configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station;

[0029] Receive a first RRC message sent by the base station, where the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor. The first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and to perform beam prediction using the first measurement beam set.

[0030] In a possible implementation manner, after deactivating the first beam prediction model, the method further includes:

[0031] Sending UCI to the base station, where the UCI includes beam indices and signal qualities of multiple beams, where the signal qualities of the multiple beams are all minimum signal quality values;

[0032] Receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use the configuration information of the full beam set to perform beam measurement and beam prediction.

[0033] In a possible implementation manner, after selecting a target beam prediction model from the multiple second beam prediction models, the method further includes:

[0034] Sending a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set and an identifier of a third monitoring beam set corresponding to the target beam prediction model;

[0035] Receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to use the third monitoring beam set to perform beam measurement and use the third measurement beam set to perform beam prediction.

[0036] In a second aspect, an embodiment of the present application provides a beam prediction model switching method, which is applied to a base station, wherein the base station includes a first beam prediction model and multiple second beam prediction models, and the effective beam prediction model of the base station is the first beam prediction model. The method includes:

[0037] Obtaining signal qualities corresponding to respective beams included in the first monitoring beam set reported by the terminal, and selecting a signal quality with a maximum value from the signal qualities corresponding to the respective beams included in the first monitoring beam set as the measured signal quality;

[0038] Obtaining a signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0039] Calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0040] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0041] In a possible implementation manner, selecting a target beam prediction model from the multiple second beam prediction models includes:

[0042] Perform the following traversal operations on each second beam prediction model in turn:

[0043] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0044] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0045] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0046] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0047] In a possible implementation, after calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality, the method further includes:

[0048] If the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

[0049] In a possible implementation, calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality includes:

[0050] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0051] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0052] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0053] The first prediction error value is calculated by the following formula:

[0054] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0055] Among them, α is the filtering factor.

[0056] In a third aspect, an embodiment of the present application provides a beam prediction model switching device, applied to a terminal, the terminal including a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the terminal being the first beam prediction model, the device including:

[0057] a measurement module, configured to measure the pilot signal of each beam included in the first monitoring beam set, obtain a signal quality corresponding to each beam included in the first monitoring beam set, and select a signal quality with a maximum value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0058] a prediction module, configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0059] a calculation module, configured to calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0060] A switching module is used to select a target beam prediction model from the multiple second beam prediction models if the first prediction error value is greater than or equal to a specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0061] In a possible implementation, the switching module is specifically configured to:

[0062] Perform the following traversal operations on each second beam prediction model in turn:

[0063] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0064] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0065] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0066] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0067] In one possible implementation, the prediction module is also used to deactivate the first beam prediction model and use the full beam set for beam prediction if the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value.

[0068] In a possible implementation, the calculation module is specifically configured to:

[0069] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0070] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0071] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0072] The first prediction error value is calculated by the following formula:

[0073] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0074] Among them, α is the filtering factor.

[0075] In a possible implementation, the apparatus further includes:

[0076] A receiving module is used to receive configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station; and receive a first RRC message sent by the base station, wherein the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor, and the first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and to perform beam prediction using the first measurement beam set.

[0077] In a possible implementation, the apparatus further includes a sending module;

[0078] The sending module is configured to send UCI to the base station, where the UCI includes beam indexes and signal qualities of multiple beams, and the signal qualities of the multiple beams are all minimum signal quality values;

[0079] The receiving module is also used to receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use the configuration information of the full beam set to perform beam measurement and beam prediction.

[0080] In a possible implementation, the sending module is further configured to send a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set;

[0081] The receiving module is further used to receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to use the third monitoring beam set to perform beam measurement and use the third measurement beam set to perform beam prediction.

[0082] In a fourth aspect, an embodiment of the present application provides a beam prediction model switching device, which is applied to a base station, wherein the base station includes a first beam prediction model and multiple second beam prediction models, and the effective beam prediction model of the base station is the first beam prediction model. The device includes:

[0083] an acquisition module, configured to acquire the signal quality corresponding to each beam included in the first monitoring beam set reported by the terminal, and select the signal quality with the largest value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0084] a prediction module, configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0085] a calculation module, configured to calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0086] A switching module is used to select a target beam prediction model from the multiple second beam prediction models if the first prediction error value is greater than or equal to a specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0087] In a possible implementation, the switching module is specifically configured to:

[0088] Perform the following traversal operations on each second beam prediction model in turn:

[0089] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0090] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0091] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0092] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0093] In one possible implementation, the prediction module is further used to deactivate the first beam prediction model and use the full beam set for beam prediction if the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value.

[0094] In a possible implementation, the calculation module is specifically configured to:

[0095] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0096] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0097] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0098] The first prediction error value is calculated by the following formula:

[0099] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0100] Among them, α is the filtering factor.

[0101] In a fifth aspect, an embodiment of the present application provides a terminal, the terminal including a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the terminal being the first beam prediction model, and the terminal including:

[0102] processor; transceiver;

[0103] A machine-readable storage medium storing machine-executable instructions capable of being executed by the processor; the machine-executable instructions prompting the processor to perform the following steps:

[0104] measuring a pilot signal of each beam included in the first monitoring beam set to obtain a signal quality corresponding to each beam included in the first monitoring beam set, and selecting a signal quality with a maximum value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0105] Obtaining a signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0106] Calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0107] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0108] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0109] Perform the following traversal operations on each second beam prediction model in turn:

[0110] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0111] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0112] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0113] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0114] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0115] If the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

[0116] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0117] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0118] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0119] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0120] The first prediction error value is calculated by the following formula:

[0121] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0122] Among them, α is the filtering factor.

[0123] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0124] receiving configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station;

[0125] Receive a first RRC message sent by the base station, where the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor. The first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and to perform beam prediction using the first measurement beam set.

[0126] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0127] Sending UCI to the base station, where the UCI includes beam indices and signal qualities of multiple beams, where the signal qualities of the multiple beams are all minimum signal quality values;

[0128] Receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use the configuration information of the full beam set to perform beam measurement and beam prediction.

[0129] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0130] Sending a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set and an identifier of a third monitoring beam set corresponding to the target beam prediction model;

[0131] Receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to use the third monitoring beam set to perform beam measurement and use the third measurement beam set to perform beam prediction.

[0132] In a sixth aspect, an embodiment of the present application provides a base station, the base station including a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the base station being the first beam prediction model, and the base station including:

[0133] processor; transceiver;

[0134] A machine-readable storage medium storing machine-executable instructions capable of being executed by the processor; the machine-executable instructions prompting the processor to perform the following steps:

[0135] Obtaining signal qualities corresponding to respective beams included in the first monitoring beam set reported by the terminal, and selecting a signal quality with a maximum value from the signal qualities corresponding to the respective beams included in the first monitoring beam set as the measured signal quality;

[0136] Obtaining a signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0137] Calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0138] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0139] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0140] Perform the following traversal operations on each second beam prediction model in turn:

[0141] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0142] using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0143] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0144] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation is continued.

[0145] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0146] If the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

[0147] In one possible implementation, the machine executable instructions further cause the processor to execute the following steps:

[0148] using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or,

[0149] Calculating a difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0150] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period;

[0151] The first prediction error value is calculated by the following formula:

[0152] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0153] Among them, α is the filtering factor.

[0154] In a seventh aspect, an embodiment of the present application provides a machine-readable storage medium storing machine-executable instructions. When called and executed by a processor, the machine-executable instructions prompt the processor to implement the method described in the first aspect or the second aspect.

[0155] In an eighth aspect, an embodiment of the present application provides a computer program product, which prompts the processor to implement the method described in the first aspect or the second aspect.

[0156] Using the above technical solution, the terminal measures the signal quality corresponding to each beam in the first monitoring beam set and uses the signal quality with the largest value among the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality. The signal quality of each beam included in the first measurement beam set is then obtained from the signal quality corresponding to the first monitoring beam set. The signal quantity of each beam included in the first measurement beam set is input into the first beam prediction model to obtain the first predicted signal quality of the predicted beam output by the first beam prediction model. Since the measured signal quality is the optimal signal quality actually measured by the terminal, the first predicted signal quality is the optimal signal quality predicted by the first beam prediction model. Therefore, a first prediction error value of the first beam prediction model can be obtained based on the measured signal quality and the first predicted signal quality. If this first prediction error value is greater than or equal to a specified threshold, it indicates that the error of the first beam prediction model is large, that is, the first beam prediction model is not suitable for the current communication scenario between the base station and the terminal. The terminal can then promptly select a target beam prediction model from multiple second beam prediction models and switch the effective beam prediction model to the target beam prediction model. Since the prediction error value is less than the specified threshold value, the second prediction model is more suitable for the current communication scenario and can improve the communication quality between the base station and the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0157] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0158] FIG1 is a flow chart of a beam prediction model switching method provided by an embodiment of the present application;

[0159] FIG2 is a flowchart of another beam prediction model switching method provided in an embodiment of the present application;

[0160] FIG3 is a flowchart of another beam prediction model switching method provided in an embodiment of the present application;

[0161] FIG4 is a flowchart of another beam prediction model switching method provided in an embodiment of the present application;

[0162] FIG5 is a flowchart of another beam prediction model switching method provided in an embodiment of the present application;

[0163] FIG6 is a schematic structural diagram of a beam prediction model device provided in an embodiment of the present application;

[0164] FIG7 is a schematic structural diagram of another beam prediction model device provided in an embodiment of the present application;

[0165] FIG8 is a schematic structural diagram of a terminal provided in an embodiment of the present application;

[0166] FIG9 is a schematic structural diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0167] To make the objectives, technical solutions, and advantages of this application more clearly understood, the present application is further described below with reference to the accompanying drawings and examples. It is apparent that the described examples are only a portion of the embodiments of this application, and not all of them. All other embodiments derived by persons of ordinary skill in the art based on the examples in this application are intended to fall within the scope of protection of this application.

[0168] The beam prediction model involved in the embodiments of the present application is a pre-trained artificial intelligence (AI) model. The beam prediction model can be deployed in a terminal or a base station. The beam prediction model is used to predict the optimal beam in the full set of beams using the signal quality of a small number of beams. The input of the beam prediction model can be the beam index and corresponding signal quality of a small number of beams, and the output can be the beam index and signal quality of the predicted optimal beam, or the beam index and signal quality of the top N beams in terms of signal quality.

[0169] When multiple beam prediction models are deployed in the terminal, after performing beam measurement, the terminal uses the beam measurement result to monitor the performance of the currently effective beam prediction model to determine whether the currently effective beam prediction model needs to be switched.

[0170] When multiple beam prediction models are deployed in the base station, the terminal reports the beam measurement results to the base station. The base station monitors the performance of the currently effective beam prediction model based on the beam measurement results to determine whether the currently effective beam prediction model needs to be switched.

[0171] The following is a detailed introduction to the improved beam prediction model switching method of the embodiment of the present application.

[0172] An embodiment of the present application provides a beam prediction model switching method, which is applied to a terminal. The terminal includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the terminal is the first beam prediction model. As shown in FIG1 , the method includes:

[0173] S101. Measure the pilot signal of each beam included in the first monitoring beam set to obtain the signal quality corresponding to each beam included in the first monitoring beam set, and select the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality.

[0174] The measured signal quality is the signal quality with the largest value among the signal qualities corresponding to the beams included in the first monitoring beam set, that is, the optimal signal quality obtained by actual measurement.

[0175] As will be appreciated, the base station transmits pilot signals in the beam direction of each beam included in the first monitoring beam set according to a preconfigured measurement period. Accordingly, the terminal measures the pilot signals in each beam direction to obtain the signal quality corresponding to each beam, and determines the signal quality with the highest value from the measured signal qualities, and uses the signal quality with the highest value as the measured signal quality.

[0176] The signal quality can be represented by Layer 1 Reference Signal Received Power (L1-RSRP). L1-RSRP can be used to represent the strength of the physical layer pilot signal. The larger the L1-RSRP, the better the signal quality.

[0177] S102. Obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model.

[0178] The input parameters of the first beam prediction model are the signal quality of each beam included in the first measurement beam set. The first measurement beam set is a subset of the first monitoring beam set. That is, the first monitoring beam set includes more beams than the first measurement beam set, thereby achieving the purpose of performance monitoring of the first beam prediction model.

[0179] Since the first measurement beam set is a subset of the first monitoring beam set, after the terminal measures and obtains the signal quality corresponding to each beam included in the first monitoring beam set, the terminal can obtain the signal quality corresponding to each beam in the first measurement beam set.

[0180] The first beam prediction model can use the signal quality corresponding to each beam in the first measurement beam set to predict the optimal beam between the current base station and the terminal, namely the predicted beam. The first beam prediction model can also predict the signal quality of the predicted beam, namely the first predicted signal quality.

[0181] S103. Calculate a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality.

[0182] It can be understood that the first predicted signal quality is the signal quality of the optimal prediction beam predicted by the first beam prediction model, and the measured signal quality is the signal quality of the optimal beam among the beams in the first monitoring beam set, as measured. Therefore, the first prediction error value can represent the error between the signal quality of the optimal beam predicted by the first beam prediction model and the measured signal quality of the optimal beam as measured.

[0183] S104. If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0184] As can be understood, if the first prediction error value is greater than or equal to the specified threshold value, it indicates that the prediction error of the first beam prediction model is large and the first beam prediction model cannot accurately predict the optimal beam. The terminal can then select a target beam prediction model from multiple second beam prediction models whose prediction error value is less than the specified threshold value to avoid deterioration of communication quality between the base station and the terminal.

[0185] Using the above method, the terminal measures the signal quality corresponding to each beam in the first monitoring beam set and uses the signal quality with the largest value among the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality. The signal quality of each beam included in the first measurement beam set is then obtained from the signal quality corresponding to the first monitoring beam set. The signal quantity of each beam included in the first measurement beam set is input into the first beam prediction model to obtain the first predicted signal quality of the predicted beam output by the first beam prediction model. Since the measured signal quality is the optimal signal quality actually measured by the terminal, the first predicted signal quality is the optimal signal quality predicted by the first beam prediction model. Therefore, a first prediction error value of the first beam prediction model can be obtained based on the measured signal quality and the first predicted signal quality. If this first prediction error value is greater than or equal to a specified threshold, it indicates that the error of the first beam prediction model is large, that is, the first beam prediction model is not suitable for the current communication scenario between the base station and the terminal. The terminal can then promptly select a target beam prediction model from multiple second beam prediction models and switch the effective beam prediction model to the target beam prediction model. Since the prediction error value is less than the specified threshold value, the second prediction model is more suitable for the current communication scenario and can improve the communication quality between the base station and the terminal.

[0186] Before executing the method shown in FIG1 , the base station needs to configure the terminal. That is, before S101 , the following steps need to be performed:

[0187] The terminal receives configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set from a base station. The terminal also receives a first RRC message from the base station, where the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, a specified threshold value, and a filter factor. The first RRC message is used to instruct the terminal to use the first monitoring beam set for beam measurement and the first measurement beam set for beam prediction.

[0188] In one implementation, the at least one measurement beam set is all measurement beam sets supported by the base station, and the at least one monitoring beam set is all monitoring beam sets supported by the base station.

[0189] In another implementation, at least one measurement beam set is a measurement beam set corresponding to each beam prediction model in the terminal, and at least one monitoring beam set is a monitoring beam set corresponding to each beam prediction model in the terminal.

[0190] The input of the beam prediction model is the signal quality of each beam included in the measurement beam set. The inputs of different beam prediction models in the terminal can be the same or different. When the inputs are different, the corresponding measurement beam sets are also different.

[0191] The monitoring beam sets corresponding to different measurement beam sets can be the same or different. Monitoring beam sets can be pre-configured. For example, a measurement beam set and a monitoring beam set can have a one-to-one relationship. A monitoring beam set can be obtained by adding some beams to the measurement beam set. Alternatively, a measurement beam set and a monitoring beam set can have a many-to-one relationship, meaning that multiple measurement beam sets are subsets of the same monitoring beam set.

[0192] Each beam supported by the base station corresponds to a beam index. The configuration information of each beam set includes: beam set identifier, beam index, measurement period and number of beams.

[0193] The terminal can store the configuration information of the full beam set, the configuration information of at least one measurement beam set, and the configuration information of at least one monitoring beam set. Then, when the first RRC message is received, the configuration information of the first measurement beam set is searched using the identifier of the first measurement beam set, and the configuration information of the first monitoring beam set is searched using the identifier of the first monitoring beam set. Then, beam measurement is performed on each beam included in the first monitoring beam set according to the configuration information of the first monitoring beam set, and beam prediction is performed using the signal quality of each beam included in the first measurement beam set. It can be understood that the base station can activate the first measurement beam set and the first monitoring beam set through the first RRC message, so that the terminal starts to use the first measurement beam set and the first monitoring beam set.

[0194] It should be noted that the input parameters corresponding to each beam prediction model in the terminal have a certain degree of flexibility. If the first measurement beam set does not completely match the current input parameters of the first beam prediction model, the input parameters of the first beam prediction model can be adjusted so that the input parameters of the first beam prediction model are adapted to the first measurement beam set.

[0195] By adopting this method, the base station can pre-send the configuration information of the full beam set, the configuration information of at least one measurement beam set, and the configuration information of at least one monitoring beam set to the terminal. Subsequently, the measurement beam set and the monitoring beam set required by the terminal can be configured for the terminal through the first RRC message. Therefore, there is no need to re-send the configuration information of the measurement beam set and the configuration information of the monitoring beam set each time the terminal switches the beam prediction model, which can improve the model switching efficiency.

[0196] In another embodiment of the present application, for the above S103, calculating the first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality, there are the following two implementation methods:

[0197] Method 1: taking the difference between the measured signal quality and the first predicted signal quality as the first prediction error value.

[0198] The terminal may determine the measured signal quality and the first predicted signal quality in each measurement period of the first monitoring beam set, and further calculate the first prediction error value in each measurement period.

[0199] Method 2: Calculate the difference between the measured signal quality and the first predicted signal quality to obtain the current prediction error value;

[0200] Obtain a historical prediction error value, where the historical prediction error value is the difference between the measured signal quality obtained in the previous measurement period and the predicted signal quality output by the first beam prediction model in the previous measurement period;

[0201] The first prediction error value is calculated using the following formula:

[0202] The first prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|; where α is a filter factor.

[0203] When the signal quality is L1-RSRP, the current prediction error value can be expressed as L1_RSRP_Gap_Current, and the historical prediction error value can be expressed as L1_RSRP_Gap_Prev. Then, the first prediction error value Gap=|α*L1_RSRP_Gap_Current+(1-α)*L1_RSRP_Gap_Prev|.

[0204] In Method 2, since no historical prediction error values ​​exist in the first measurement cycle of the first monitoring beam set, the current prediction error value calculated in the first measurement cycle can be used as the first prediction error value for the first measurement cycle. Furthermore, in the second measurement cycle, the current prediction error value of the first measurement cycle can be used as the historical prediction error value, and the first prediction error value for the second measurement cycle can be calculated using the above formula. Similarly, in the third measurement cycle, the current prediction error value of the second measurement cycle can be used as the historical prediction error value.

[0205] For the first measurement cycle, the above-mentioned first prediction error value can reflect the difference between the actual measured signal quality and the first predicted signal quality, and the difference can reflect the performance of the first beam prediction model in the current communication scenario between the terminal and the base station. In mode 2, the first prediction error value is obtained by filtering the current prediction error value and the historical prediction error value, which can accurately reflect the performance of the first beam prediction model in two consecutive measurement cycles, so that the model switching can be performed more accurately based on the first prediction error value and the specified threshold value. Because the looser the switching conditions, the more frequent the model switching, and the correspondingly greater the air interface overhead caused by the model switching. The stricter the switching conditions, the less frequent the model switching, which may accordingly lead to untimely model switching. By setting the filtering factor and the specified threshold value, the embodiment of the present application can make the switching conditions more reasonable, and can balance the real-time nature of the switching and the air interface overhead, thereby maximizing the overall performance.

[0206] In some embodiments of the present application, when the first prediction error value is greater than or equal to a specified threshold value, the terminal may traverse multiple second beam prediction models and select a target beam prediction model from them. The selection process includes the following steps:

[0207] Perform the following traversal operations on each second beam prediction model in turn:

[0208] Step 1: For the second beam prediction model, input the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model.

[0209] The measurement beam set corresponding to the second beam prediction model corresponds to an input parameter of the second beam measurement model. The terminal may obtain configuration information of at least one measurement beam set from configuration information of the measurement beam set sent by the base station, thereby obtaining a beam index included in the measurement beam set from the configuration information of the measurement beam set.

[0210] Then, the terminal obtains the signal quality corresponding to each beam included in the measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set according to the beam index included in the measurement beam set.

[0211] If the first monitoring beam set includes all beams of the measurement beam set, the signal quality corresponding to each beam included in the measurement beam set can be directly obtained; if the first monitoring beam set does not include all beams of the measurement beam set, the terminal can obtain the signal quality corresponding to some beams not included in the measurement beam set from the first monitoring beam set, thereby obtaining the same signal quality as the number of beams included in the measurement beam set, and then adaptively adjust the input parameters of the second beam prediction model, and input the obtained signal quality corresponding to each beam into the second beam prediction model.

[0212] Alternatively, the first RRC message may include identifiers of multiple monitoring beam sets, and then the terminal will measure the beams included in the multiple monitoring beam sets to obtain the signal quality of each beam included in each monitoring beam set.

[0213] In this step, the terminal may obtain the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model from the signal quality of each beam included in the monitoring beam set corresponding to the second beam prediction model. The signal quality of each beam included in the measurement beam set may then be input into the second beam prediction model.

[0214] Step 2: The difference between the measured signal quality and the second predicted signal quality is used as the second prediction error value of the second beam prediction model.

[0215] The measured signal quality may be the highest signal quality among the signal qualities of the beams included in the first monitoring beam set. Alternatively, if the first RRC message includes identifiers of multiple monitoring beam sets, the measured signal quality may be the highest signal quality among the signal qualities of the beams included in the monitoring beam set corresponding to the second beam prediction model.

[0216] Step 3: If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated.

[0217] Then, the terminal switches the effective beam prediction model to the target beam prediction model.

[0218] Step 4: If the second prediction error value is greater than or equal to the specified threshold value, continue the traversal operation.

[0219] The traversal operation ends when a second prediction model is found whose second prediction error value is less than the specified threshold value.

[0220] If after completing the traversal operation on all the second beam prediction models, it is determined that the second prediction error values ​​of all the second beam prediction models are greater than or equal to the specified threshold value, the traversal operation is stopped.

[0221] At this time, the terminal can determine that the first prediction error value and the prediction error values ​​of multiple second beam prediction models are greater than or equal to the specified threshold value, that is, there is no beam prediction model suitable for the current scenario, then the first beam prediction model is disabled and the full beam set is used for beam prediction.

[0222] If there is no beam prediction model suitable for the current scenario, the terminal can fall back to non-AI mode, that is, use the full beam set for beam prediction. This can achieve rapid fallback to non-AI mode when the performance of the beam prediction model deteriorates or when the generalization performance of the beam prediction model is poor in the early stage of beam prediction model deployment, so as to avoid affecting the communication quality between the base station and the terminal.

[0223] Among them, the terminal uses the full beam set for beam prediction, which means that the base station sends pilot signals in all beam directions respectively, and the terminal measures the pilot signals in each beam direction to predict the beam corresponding to the optimal signal quality. The terminal and the base station can subsequently communicate using the beam corresponding to the optimal signal quality.

[0224] Specifically, when the first prediction error value and the prediction error values ​​of multiple second beam prediction models are greater than or equal to the specified threshold value, after deactivating the first beam prediction model, the terminal can notify the base station that each beam prediction model is no longer applicable by sending uplink control information (UCI) to the base station, thereby initiating a model fallback request to the base station. After deactivating the first beam prediction model, the terminal can perform the following steps:

[0225] Step A: Send UCI to the base station.

[0226] In the embodiment of the present application, the UCI measurement reporting format can be reused, and the UCI includes the beam index and signal quality of multiple beams, and the signal quality of multiple beams is the minimum signal quality. Among them, the minimum signal quality is -140dBm (milliwatt decibel). In the embodiment of the present application, by setting each signal quality in the current UCI measurement reporting format to the minimum value, the base station can be notified that each beam prediction model is no longer applicable, without the need to design a dedicated model fallback request, and the implementation is relatively simple.

[0227] The number of beam indices included in the UCI is pre-configured by the base station for the terminal.

[0228] As shown in Table 1, Table 1 exemplarily shows a UCI format.

[0229] Table 1

[0230] Step B: Receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set. The first indication message is used to instruct the terminal to use the configuration information of the full beam set for beam measurement and beam prediction. That is, the first indication message activates the full beam set.

[0231] After receiving the first indication message, the terminal can deactivate the first beam prediction model and fall back to the non-AI mode.

[0232] The first indication message may be a transmission configuration indication message (TCI), a media access control control element (MAC-CE) message or an RRC message.

[0233] Using this method, the terminal sets the signal quality in the UCI to the minimum value, thereby notifying the base station that no applicable beam prediction model currently exists. The base station then instructs the terminal to use the full beam set for beam prediction via a first indication message, enabling a rapid fallback to non-AI mode. Furthermore, the model fallback can be implemented between the terminal and the base station using existing message types, minimizing the impact on current standard protocols.

[0234] It is understandable that after the terminal selects the target beam prediction model from multiple second beam prediction models, the terminal also needs to request the base station for a subsequent measurement beam set and a monitoring beam set applicable to the second beam prediction model.

[0235] The terminal sends a second RRC message to the base station, where the second RRC message includes an identifier of a third beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set. The terminal then receives a second indication message from the base station, instructing the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

[0236] The second indication message includes an identifier of the third measurement beam set and an identifier of the third monitoring beam set. It can be understood that the base station can activate the third measurement beam set and the third monitoring beam set and deactivate the first measurement beam set and the first monitoring beam set through the second indication message.

[0237] The second indication message may be a TCI message, a MAC-CE message or an RRC message.

[0238] Since the base station has sent the configuration information of each measurement beam set and the configuration information of each monitoring beam set to the terminal in advance, the base station can start the terminal's measurement of the third measurement beam set and the third monitoring beam set through the second indication message, thereby realizing rapid switching of the beam prediction model.

[0239] The following describes a beam prediction model switching method provided by an embodiment of the present application with reference to a specific example. Assuming that the terminal is configured to use a monitoring beam set Set_monitor for beam measurement and a measurement beam set Set_measure for beam prediction, as shown in FIG2 . The method includes:

[0240] S201. Traverse the L1_RSRP corresponding to the monitoring beam set Set_monitor in sequence to obtain the L1_RSRP of the beam with the best performance, which is recorded as L1_RSRP_Best.

[0241] The best-performing beam is the beam with the measured signal quality. The terminal searches through the beams included in Set_monitor for the beam with the highest L1_RSRP and records this L1_RSRP as L1_RSRP_Best. The black square to the left of S201 in Figure 2 represents the best-performing beam.

[0242] S202 : Extract the L1_RSRP of each beam included in the measurement beam set Set_measure from the L1_RSRP of each beam included in Set_monitor, and use it as the input of the current beam prediction model.

[0243] The black squares on the left side of S202 in FIG. 2 are beams included in Set_measure.

[0244] S203: Based on the current beam prediction model, predict the optimal beam in Set_measure and the L1_RSRP of the beam, which is recorded as L1_RSRP_Predict.

[0245] The shaded squares on the left side of S203 in Figure 2 are the optimal beams predicted by the beam prediction model, and the black squares are the beams with the best performance in S201.

[0246] S204: Calculate the difference between L1_RSRP_Best and L1_RSRP_Predict and perform filtering to obtain a prediction error value.

[0247] The filtering method may refer to the formula for calculating the first prediction error value using the filtering factor in the above embodiment.

[0248] S205: Determine whether the prediction error value is less than a specified threshold value.

[0249] If yes, execute S206; if no, execute S209.

[0250] S206: Whether the currently traversed beam prediction model is a valid beam prediction model in the terminal.

[0251] If yes, execute S207; if no, execute S208.

[0252] S207: The beam prediction model remains unchanged and no operation is required.

[0253] S208: Initiate a model switching request.

[0254] The model switching request may be the second RRC message in the above embodiment.

[0255] S209: Determine whether all beam prediction models have been traversed.

[0256] If yes, execute S210; if no, execute S211.

[0257] S210, beam prediction model selection failed, falling back to non-AI mode.

[0258] The model selection failure means that the prediction error values ​​corresponding to the beam prediction models deployed in the terminal are all greater than or equal to the specified threshold value.

[0259] S211: Select the next beam prediction model and return to S201 for the next beam prediction model, so that each beam prediction model can be traversed.

[0260] By setting filtering factors and specifying thresholds, this method dynamically balances air interface measurement overhead with beam prediction performance, enabling timely switching to the appropriate beam prediction model to meet the needs of different scenarios. Furthermore, if the performance of all beam prediction models deteriorates, it can quickly fall back to non-AI mode to prevent terminal disconnection.

[0261] When the beam prediction model is deployed in the terminal, as shown in FIG3 , which illustrates an interaction process between the terminal and the base station, the method includes:

[0262] S301. The base station sends configuration information of the full beam set, configuration information of the measurement beam set, and configuration information of the monitoring beam set to the terminal.

[0263] S302: The base station activates the measurement beam set and the monitoring beam set, and sends down the filter factor and the designated threshold value.

[0264] This step can be implemented through the first RRC message introduced in the above embodiment, and will not be repeated here.

[0265] S303: The terminal measures the pilot signal of each beam included in the monitoring beam set, obtains the L1_RSRP corresponding to each beam, and defines the beam with the largest L1_RSRP as the measured optimal beam.

[0266] The measured optimal beam is the beam corresponding to the above-mentioned measured signal quality.

[0267] S304: The terminal performs beam prediction using the current beam prediction model, and analyzes the performance difference between the predicted optimal beam and the measured optimal beam.

[0268] This performance difference is the prediction error value introduced in the above embodiment. The method of calculating the prediction error value can refer to the relevant description in the above embodiment and will not be repeated here.

[0269] S305: The terminal decides to switch models or fall back to non-AI mode.

[0270] The method for the terminal to determine whether to switch models and whether to fall back to the AI ​​mode based on the specified threshold value can be referred to the relevant description in the above embodiment and will not be repeated here.

[0271] S306. The terminal sends a model switching request or a request to fall back to a non-AI mode to the base station.

[0272] S307: The base station activates / deactivates the monitoring beam set and the measurement beam set for the terminal.

[0273] This step can be implemented through the first indication message or the second indication message in the above embodiment.

[0274] In this way, when the beam measurement model is configured on the terminal side, reasonable switching of the beam measurement model can be achieved to ensure the communication quality between the base station and the terminal.

[0275] Corresponding to the above method embodiment, an embodiment of the present application further provides a beam prediction model switching method, which is applied to a base station. The base station includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the base station is the first beam prediction model. As shown in Figure 4, the method includes:

[0276] S401: Obtain signal qualities corresponding to beams included in a first monitoring beam set reported by a terminal, and select a signal quality with the largest value from the signal qualities corresponding to beams included in the first monitoring beam set as the measured signal quality.

[0277] The base station pre-configures the measurement period and reporting method for the first monitoring beam set for the terminal. The base station then transmits pilot signals in the beam direction of each beam included in the first monitoring beam set according to the pre-configured measurement period. Accordingly, the terminal measures the pilot signals in each beam direction, obtains the signal quality corresponding to each beam, and reports the signal quality of each beam to the base station.

[0278] S402. Obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model.

[0279] The first measurement beam set is a subset of the first monitoring beam set.

[0280] S403. Calculate a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality.

[0281] S404. If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0282] Using the above method, the base station obtains the signal quality corresponding to each beam in the first monitoring beam set reported by the terminal and uses the signal quality with the largest value among the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality. The base station then obtains the signal quality of each beam included in the first measurement beam set from the signal qualities corresponding to the first monitoring beam set. The signal quality of each beam included in the first measurement beam set is input into the first beam prediction model to obtain the first predicted signal quality of the predicted beam output by the first beam prediction model. Since the measured signal quality is the optimal signal quality actually measured by the terminal, the first predicted signal quality is the optimal signal quality predicted by the first beam prediction model. Therefore, a first prediction error value of the first beam prediction model can be obtained based on the measured signal quality and the first predicted signal quality. If this first prediction error value is greater than or equal to a specified threshold, it indicates that the error of the first beam prediction model is large, that is, the first beam prediction model is not suitable for the current communication scenario between the base station and the terminal. The base station can then promptly select a target beam prediction model from multiple second beam prediction models and switch the effective beam prediction model to the target beam prediction model. Since the prediction error value is less than the specified threshold value, the second prediction model is more suitable for the current communication scenario and can improve the communication quality between the base station and the terminal.

[0283] It should be noted that the implementation of the above S402-S404 is the same as the implementation of S102-S104 on the terminal side. Please refer to the relevant description in the above embodiment and will not be repeated here.

[0284] When the base station determines that the first prediction error value and the prediction error values ​​of multiple second beam prediction models are greater than or equal to the specified threshold value, the first beam prediction model can also be disabled and fall back to the non-AI mode, using the full beam set for beam prediction.

[0285] Before falling back to non-AI mode, the base station can configure the measurement period and reporting method of the full beam set for the terminal. After falling back to non-AI mode, the base station sends pilot signals in the beam directions of each beam included in the full beam set, and receives the measurement results reported by the terminal. It then selects the beam with the best signal quality as the beam for subsequent communication with the terminal based on the measurement results.

[0286] The following describes the complete process of the beam prediction model switching method when the beam prediction model is deployed in the base station in conjunction with FIG5 . As shown in FIG5 , the method includes:

[0287] S501: A base station sends a pilot signal to a terminal in a beam direction of each beam included in a first monitoring beam set.

[0288] S502. The terminal reports the L1_RSRP of each beam in the first monitoring beam set.

[0289] S503: The base station defines the beam with the largest L1_RSRP as the measured optimal beam.

[0290] S504: The base station performs beam prediction using the current beam prediction model, and analyzes the performance difference between the predicted optimal beam and the measured optimal beam.

[0291] This performance difference is the prediction error value introduced in the above embodiment. The method of calculating the prediction error value can refer to the relevant description in the above embodiment and will not be repeated here.

[0292] S505: The base station decides to switch the model or fall back to the non-AI mode.

[0293] The method for the base station to determine whether to switch models and whether to fall back to AI mode based on the specified threshold value can be referred to the relevant description in the above terminal side embodiment and will not be repeated here.

[0294] S506: The base station sends configuration information of a new measurement beam set to the terminal.

[0295] If the base station decides to switch the model, it sends the configuration information of the monitoring beam set and the measurement beam set corresponding to the switched beam prediction model to the terminal.

[0296] If the base station decides to fall back to non-AI mode, it sends the configuration information of the full beam set to the terminal.

[0297] Using this method, when a beam measurement model is configured on the base station side, by setting filtering factors and specifying thresholds, it is possible to dynamically adjust the balance between air interface measurement overhead and beam prediction performance, switching to the appropriate beam prediction model in a timely manner to meet the needs of different scenarios. Furthermore, if the performance of all beam prediction models deteriorates, it can quickly fall back to non-AI mode to prevent terminal disconnection.

[0298] Based on the same concept, an embodiment of the present application provides a beam prediction model switching device, which is applied to a terminal. The terminal includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the terminal is the first beam prediction model. As shown in FIG6 , the device includes:

[0299] The measurement module 601 is configured to measure the pilot signal of each beam included in the first monitoring beam set to obtain the signal quality corresponding to each beam included in the first monitoring beam set, and select the signal quality with the largest value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0300] Prediction module 602 is configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into a first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0301] A calculation module 603 is configured to calculate a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0302] The switching module 604 is used to select a target beam prediction model from multiple second beam prediction models if the first prediction error value is greater than or equal to the specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0303] Optionally, the switching module 604 is specifically configured to:

[0304] Perform the following traversal operations on each second beam prediction model in turn:

[0305] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0306] Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0307] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0308] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

[0309] Optionally, the prediction module 602 is further configured to deactivate the first beam prediction model and perform beam prediction using the full beam set if the first prediction error value and the second prediction error values ​​of multiple second beam prediction models are both greater than or equal to a specified threshold value.

[0310] Optionally, the calculation module 603 is specifically configured to:

[0311] The difference between the measured signal quality and the first predicted signal quality is used as the first prediction error value; or,

[0312] Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0313] Obtain a historical prediction error value, where the historical prediction error value is the difference between the measured signal quality obtained in the previous measurement period and the predicted signal quality output by the first beam prediction model in the previous measurement period;

[0314] The first prediction error value is calculated using the following formula:

[0315] First prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0316] Among them, α is the filtering factor.

[0317] Optionally, the device further includes:

[0318] A receiving module is used to receive configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station; and to receive a first RRC message sent by the base station, where the first RRC message includes an identifier of a first measurement beam set, an identifier of a first monitoring beam set, a specified threshold value, and a filter factor. The first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and to perform beam prediction using the first measurement beam set.

[0319] Optionally, the device further includes a sending module;

[0320] A sending module, configured to send UCI to a base station. The UCI includes beam indices and signal qualities of multiple beams, where the signal qualities of the multiple beams are all minimum signal qualities.

[0321] The receiving module is also used to receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use the configuration information of the full beam set to perform beam measurement and beam prediction.

[0322] Optionally, the sending module is further configured to send a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set;

[0323] The receiving module is further used to receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

[0324] In another embodiment of the present application, a beam prediction model switching device is provided, which is applied to a base station. The base station includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the base station is the first beam prediction model. As shown in FIG7 , the device includes:

[0325] An acquisition module 701 is configured to acquire signal qualities corresponding to respective beams included in a first monitoring beam set reported by a terminal, and select a signal quality with a maximum value from the signal qualities corresponding to respective beams included in the first monitoring beam set as the measured signal quality;

[0326] Prediction module 702 is configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into a first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0327] A calculation module 703 is configured to calculate a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0328] The switching module 704 is used to select a target beam prediction model from multiple second beam prediction models if the first prediction error value is greater than or equal to the specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0329] Optionally, the switching module 704 is specifically configured to:

[0330] Perform the following traversal operations on each second beam prediction model in turn:

[0331] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0332] Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0333] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0334] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

[0335] Optionally, the prediction module 702 is further configured to deactivate the first beam prediction model and perform beam prediction using the full beam set if the first prediction error value and the prediction error values ​​of multiple second beam prediction models are both greater than or equal to a specified threshold value.

[0336] Optionally, the calculation module 703 is specifically configured to:

[0337] The difference between the measured signal quality and the first predicted signal quality is used as the first prediction error value; or,

[0338] Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0339] Obtain a historical prediction error value, where the historical prediction error value is the difference between the measured signal quality obtained in the previous measurement period and the predicted signal quality output by the first beam prediction model in the previous measurement period;

[0340] The first prediction error value is calculated using the following formula:

[0341] First prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0342] Among them, α is the filtering factor.

[0343] Based on the same concept, an embodiment of the present application provides a terminal, which includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the terminal is the first beam prediction model. As shown in FIG8 , the terminal includes:

[0344] Processor 801; transceiver 804;

[0345] A machine-readable storage medium 802 stores machine-executable instructions that can be executed by the processor 801; the machine-executable instructions prompt the processor 801 to perform the following steps:

[0346] measuring a pilot signal of each beam included in the first monitoring beam set to obtain a signal quality corresponding to each beam included in the first monitoring beam set, and selecting a signal quality with a maximum value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0347] Obtaining the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0348] Calculating a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0349] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0350] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0351] Perform the following traversal operations on each second beam prediction model in turn:

[0352] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0353] Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0354] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0355] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

[0356] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0357] If the first prediction error value and the second prediction error values ​​of the plurality of second beam prediction models are both greater than or equal to a specified threshold value, the first beam prediction model is disabled, and beam prediction is performed using the full beam set.

[0358] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0359] The difference between the measured signal quality and the first predicted signal quality is used as the first prediction error value; or,

[0360] Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0361] Obtaining a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a signal quality of a predicted beam output by a first beam prediction model in the previous measurement period;

[0362] The first prediction error value is calculated using the following formula:

[0363] First prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0364] Among them, α is the filtering factor.

[0365] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0366] receiving configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station;

[0367] Receive a first RRC message sent by the base station, where the first RRC message includes an identifier of a first measurement beam set, an identifier of a first monitoring beam set, a specified threshold value, and a filter factor. The first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and to perform beam prediction using the first measurement beam set.

[0368] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0369] Sending UCI to the base station. The UCI includes the beam index and signal quality of multiple beams. The signal quality of multiple beams is the minimum signal quality value.

[0370] A first indication message sent by a base station is received, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use configuration information of the full beam set to perform beam measurement and beam prediction.

[0371] Optionally, the machine executable instructions further cause the processor 801 to perform the following steps:

[0372] Sending a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set;

[0373] A second indication message sent by the base station is received, where the second indication message is used to instruct the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

[0374] In Figure 8 , a communication bus 803 may also be included. The processor 801, the machine-readable storage medium 802, and the transceiver 804 communicate with each other via the communication bus 803. The communication bus 803 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, and the like.

[0375] The transceiver 804 may be a wireless communication module. Under the control of the processor 801 , the transceiver 804 exchanges data with other devices.

[0376] The machine-readable storage medium 802 may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Alternatively, the machine-readable storage medium 802 may be at least one storage device located remote from the processor.

[0377] The processor 801 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0378] An embodiment of the present application further provides a base station, which includes a first beam prediction model and multiple second beam prediction models. The effective beam prediction model of the base station is the first beam prediction model. As shown in FIG9 , the base station includes:

[0379] Processor 901; transceiver 904;

[0380] A machine-readable storage medium 902 stores machine-executable instructions that can be executed by the processor 901; the machine-executable instructions prompt the processor 901 to perform the following steps:

[0381] Obtaining signal qualities corresponding to the beams included in the first monitoring beam set reported by the terminal, and selecting the signal quality with the largest value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality;

[0382] Obtaining the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and inputting the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model;

[0383] Calculating a first prediction error value of a first beam prediction model based on the first predicted signal quality and the measured signal quality;

[0384] If the first prediction error value is greater than or equal to the specified threshold value, a target beam prediction model is selected from multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

[0385] Optionally, the machine executable instructions further cause the processor 901 to perform the following steps:

[0386] Perform the following traversal operations on each second beam prediction model in turn:

[0387] For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model;

[0388] Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model;

[0389] If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated;

[0390] If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

[0391] Optionally, the machine executable instructions further cause the processor 901 to perform the following steps:

[0392] If the first prediction error value and the prediction error values ​​of the plurality of second beam prediction models are both greater than or equal to a specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

[0393] Optionally, the machine executable instructions further cause the processor 901 to perform the following steps:

[0394] The difference between the measured signal quality and the first predicted signal quality is used as the first prediction error value; or,

[0395] Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value;

[0396] Obtain a historical prediction error value, where the historical prediction error value is the difference between the measured signal quality obtained in the previous measurement period and the predicted signal quality output by the first beam prediction model in the previous measurement period;

[0397] The first prediction error value is calculated using the following formula:

[0398] First prediction error value = |α*current prediction error value + (1-α)*historical prediction error value|;

[0399] Among them, α is the filtering factor.

[0400] In Figure 9 , a communication bus 903 may also be included. The processor 901, the machine-readable storage medium 902, and the transceiver 904 communicate with each other via the communication bus 903. The communication bus 903 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, and the like.

[0401] The transceiver 904 may be a wireless communication module. Under the control of the processor 901 , the transceiver 904 exchanges data with other devices.

[0402] The machine-readable storage medium 902 may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Alternatively, the machine-readable storage medium 902 may be at least one storage device located remotely from the processor.

[0403] The processor 901 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0404] In another embodiment provided in the present application, a computer-readable storage medium is further provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned beam prediction model switching methods are implemented.

[0405] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the beam prediction model switching methods in the above embodiments.

[0406] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated 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 instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. 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 includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0407] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0408] Each embodiment in this specification is described in a related manner. Similar portions between the embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so their description is relatively simple. For related portions, refer to the description of the method embodiments.

[0409] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A beam prediction model switching method, characterized in that: Applied to a terminal, the terminal includes a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the terminal is the first beam prediction model, and the method includes: Measuring the pilot signal of each beam included in the first monitoring beam set to obtain the signal quality corresponding to each beam included in the first monitoring beam set, and selecting the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality; Acquire the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; Calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; If the first prediction error value is greater than or equal to a specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

2. The method according to claim 1, characterized in that The selecting a target beam prediction model from the plurality of second beam prediction models comprises: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

3. The method according to claim 1 or 2, characterized in that: After calculating the first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality, the method further includes: If the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

4. The method according to claim 3, characterized in that: The calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality includes: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

5. The method according to claim 4, characterized in that Before measuring the pilot signal of each beam included in the first monitoring beam set, the method further includes: Receive the configuration information of the full beam set, the configuration information of at least one measurement beam set, and the configuration information of at least one monitoring beam set sent by the base station Configuration information; Receive a first RRC message sent by the base station, where the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor, and the first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and perform beam prediction using the first measurement beam set.

6. The method according to claim 5, characterized in that After deactivating the first beam prediction model, the method further includes: Sending UCI to the base station, where the UCI includes beam indexes and signal qualities of multiple beams, and the signal qualities of the multiple beams are all minimum signal qualities; Receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use configuration information of the full beam set to perform beam measurement and beam prediction.

7. The method according to claim 5, characterized in that After selecting the target beam prediction model from the plurality of second beam prediction models, the method further includes: Sending a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set; Receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

8. A beam prediction model switching method, characterized in that: Applied to a base station, the base station includes a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the base station is the first beam prediction model, and the method includes: Acquire the signal quality corresponding to each beam included in the first monitoring beam set reported by the terminal, and select the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality; Acquire the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; Calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; If the first prediction error value is greater than or equal to a specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

9. The method according to claim 8, characterized in that The selecting a target beam prediction model from the plurality of second beam prediction models comprises: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

10. The method according to claim 8 or 9, characterized in that: After calculating the first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality, the method further includes: If the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and the full beam set is used to perform beam prediction.

11. The method according to claim 8, characterized in that The calculating a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality includes: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

12. A beam prediction model switching device, characterized in that: Applied to a terminal, the terminal includes a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the terminal is the first beam prediction model, and the device includes: a measurement module, configured to measure the pilot signal of each beam included in the first monitoring beam set, obtain the signal quality corresponding to each beam included in the first monitoring beam set, and select the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality; a prediction module, configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; A calculation module, configured to calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; A switching module is used to select a target beam prediction model from the multiple second beam prediction models if the first prediction error value is greater than or equal to a specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

13. The device according to claim 12, characterized in that The switching module is specifically used for: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

14. The device according to claim 12 or 13, characterized in that The prediction module is also used to disable the first beam prediction model and use the full beam set to perform beam prediction if the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value.

15. The device according to claim 14, characterized in that The computing module is specifically used for: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

16. The device according to claim 15, characterized in that The device also includes: A receiving module is used to receive configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station; and to receive a first RRC message sent by the base station, wherein the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor, and the first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and perform beam prediction using the first measurement beam set.

17. The device according to claim 16, characterized in that The device also includes a sending module; The sending module is configured to send UCI to the base station, where the UCI includes beam indexes and signal qualities of multiple beams, and the signal qualities of the multiple beams are all minimum signal qualities; The receiving module is also used to receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use the configuration information of the full beam set to perform beam measurement and beam prediction.

18. The device according to claim 16, characterized in that The sending module is further used to send a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set; The receiving module is further used to receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

19. A beam prediction model switching device, characterized in that: Applied to a base station, the base station includes a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the base station is the first beam prediction model, and the device includes: an acquisition module, configured to acquire signal qualities corresponding to the beams included in the first monitoring beam set reported by the terminal, and select a signal quality with the largest value from the signal qualities corresponding to the beams included in the first monitoring beam set as the measured signal quality; a prediction module, configured to obtain the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; A calculation module, configured to calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; A switching module is used to select a target beam prediction model from the multiple second beam prediction models if the first prediction error value is greater than or equal to a specified threshold value, and switch the effective beam prediction model to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

20. The device according to claim 19, characterized in that The switching module is specifically used for: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model. And end the traversal operation; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

21. The device according to claim 19 or 20, characterized in that The prediction module is further used to disable the first beam prediction model and use the full beam set to perform beam prediction if the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value.

22. The device according to claim 19, characterized in that The computing module is specifically used for: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

23. A terminal, characterized in that: The terminal includes a first beam prediction model and a plurality of second beam prediction models, an effective beam prediction model of the terminal is the first beam prediction model, and the terminal includes: processor; Transceiver; A machine-readable storage medium storing machine-executable instructions that can be executed by the processor; the machine-executable instructions prompt the processor to perform the following steps: Measuring the pilot signal of each beam included in the first monitoring beam set to obtain the signal quality corresponding to each beam included in the first monitoring beam set, and selecting the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality; Acquire the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; Calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; If the first prediction error value is greater than or equal to a specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

24. The terminal according to claim 23, characterized in that The machine executable instructions further cause the processor to perform the following steps: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

25. The terminal according to claim 23 or 24, characterized in that: The machine executable instructions further cause the processor to perform the following steps: If the first prediction error value and the second prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and beam prediction is performed using the full beam set.

26. The terminal according to claim 25, characterized in that The machine executable instructions further cause the processor to perform the following steps: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

27. The terminal according to claim 26, characterized in that The machine executable instructions further cause the processor to perform the following steps: receiving configuration information of a full beam set, configuration information of at least one measurement beam set, and configuration information of at least one monitoring beam set sent by a base station; Receive a first RRC message sent by the base station, where the first RRC message includes an identifier of the first measurement beam set, an identifier of the first monitoring beam set, the specified threshold value, and the filter factor, and the first RRC message is used to instruct the terminal to perform beam measurement using the first monitoring beam set and perform beam prediction using the first measurement beam set.

28. The terminal according to claim 27, characterized in that The machine executable instructions further cause the processor to perform the following steps: Sending UCI to the base station, where the UCI includes beam indexes and signal qualities of multiple beams, and the signal qualities of the multiple beams are all minimum signal qualities; Receive a first indication message sent by the base station, where the first indication message includes an identifier of the full beam set, and the first indication message is used to instruct the terminal to use configuration information of the full beam set to perform beam measurement and beam prediction.

29. The terminal according to claim 27, characterized in that The machine executable instructions further cause the processor to perform the following steps: Sending a second RRC message to the base station, where the second RRC message includes an identifier of a third measurement beam set corresponding to the target beam prediction model and an identifier of a third monitoring beam set; Receive a second indication message sent by the base station, where the second indication message is used to instruct the terminal to perform beam measurement using the third monitoring beam set and to perform beam prediction using the third measurement beam set.

30. A base station, characterized in that: The base station includes a first beam prediction model and multiple second beam prediction models, the effective beam prediction model of the base station is the first beam prediction model, and the base station includes: processor; Transceiver; A machine-readable storage medium storing machine-executable instructions that can be executed by the processor; the machine-executable instructions prompt the processor to perform the following steps: Acquire the signal quality corresponding to each beam included in the first monitoring beam set reported by the terminal, and select the signal quality with the largest value from the signal qualities corresponding to each beam included in the first monitoring beam set as the measured signal quality; Acquire the signal quality of each beam included in the first measurement beam set from the signal quality corresponding to each beam included in the first monitoring beam set, and input the signal quality of each beam included in the first measurement beam set into the first beam prediction model to obtain a first predicted signal quality of the predicted beam output by the first beam prediction model; Calculate a first prediction error value of the first beam prediction model based on the first predicted signal quality and the measured signal quality; If the first prediction error value is greater than or equal to a specified threshold value, a target beam prediction model is selected from the multiple second beam prediction models, and the effective beam prediction model is switched to the target beam prediction model, and the prediction error value of the target beam prediction model is less than the specified threshold value.

31. The base station according to claim 30, characterized in that The machine executable instructions further cause the processor to perform the following steps: Perform the following traversal operations on each second beam prediction model in turn: For the second beam prediction model, inputting the signal quality of each beam included in the measurement beam set corresponding to the second beam prediction model into the second beam prediction model to obtain a second predicted signal quality of the predicted beam output by the second beam prediction model; Using the difference between the measured signal quality and the second predicted signal quality as a second prediction error value of the second beam prediction model; If the second prediction error value is less than the specified threshold value, the second beam prediction model is used as the target beam prediction model, and the traversal operation is terminated; If the second prediction error value is greater than or equal to the specified threshold value, the traversal operation continues.

32. The base station according to claim 30 or 31, characterized in that: The machine executable instructions further cause the processor to perform the following steps: If the first prediction error value and the prediction error values ​​of the multiple second beam prediction models are both greater than or equal to the specified threshold value, the first beam prediction model is disabled and the full beam set is used to perform beam prediction.

33. The base station according to claim 30, characterized in that The machine executable instructions further cause the processor to perform the following steps: using the difference between the measured signal quality and the first predicted signal quality as the first prediction error value; or, Calculating the difference between the measured signal quality and the first predicted signal quality to obtain a current prediction error value; Acquire a historical prediction error value, where the historical prediction error value is a difference between a measured signal quality obtained in a previous measurement period and a predicted signal quality output by the first beam prediction model in the previous measurement period; The first prediction error value is calculated by the following formula: The first prediction error value=|α*current prediction error value+(1-α)*historical prediction error value|; Among them, α is the filtering factor.

34. A machine-readable storage medium, characterized in that Machine executable instructions are stored, and when called and executed by a processor, the machine executable instructions prompt the processor to implement any method described in claims 1-11.

35. A computer program product, characterized in that The computer program product causes the processor to implement the method according to any one of claims 1 to 11.

Images