Electronic device and communication method

Abstract

The invention relates to electronic equipment and a communication method. An electronic device includes: a processing circuit configured to: acquire first channel quality measurement information based on a non-AI mode and second channel quality measurement information based on an AI mode; providing the first channel quality measurement information as an input to a first prediction model, and obtaining first channel quality prediction information predicted for a future moment from an output of the first prediction model; providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future moment from the output of the second prediction model; and comparing the first channel quality prediction information with the second channel quality prediction information to determine whether to use a non-AI mode or an AI mode at the future time.

Description

Electronic device and communication method

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202211649370.9 filed on December 21, 2022, the entirety of which is incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of communications, and more particularly, to beam management. Background Art

[0004] In a wireless communication system using Multiple-Input Multi-Output (MIMO) technology, a base station (as an example of a network-side communication device or communication node in the system) and a user equipment (UE) (also referred to as a terminal device, as an example of a user-side communication device or communication node in the system) have multiple antennas that support MIMO technology. The base station antenna and the UE antenna can form spatial beams with narrow directivity to provide strong power coverage in a specific direction, thereby counteracting the large path loss in high-frequency band (such as millimeter wave) channels. However, due to the strong directivity and narrow coverage of these spatial beams, it is necessary to select appropriate transmit beams and receive beams from the multiple transmit beams and receive beams of the base station and the UE to transmit data and / or control signals on the uplink and downlink channels.

[0005] Summary of the Invention

[0006] A brief overview of the present disclosure is provided below to provide a basic understanding of some aspects of the present disclosure. However, it should be understood that this overview is not an exhaustive overview of the present disclosure. It is not intended to identify key or important parts of the present disclosure, nor is it intended to limit the scope of the present disclosure. Its purpose is simply to present certain concepts of the present disclosure in a simplified form as a prelude to the more detailed description that will be given later.

[0007] This paper proposes a technology that uses beam management to establish and maintain an appropriate beam pair between a transmitter (base station or user equipment) and a receiver (user equipment or base station). The receiver selects an appropriate receive beam, and the transmitter selects an appropriate transmit beam, which together maintain a good wireless connection.

[0008] A beam management solution based on channel measurement can be adopted. Specifically, by performing downlink beam scanning from the base station to the UE, downlink reference signals are transmitted on multiple transmit beams of the base station, and received using multiple receive beams of the UE. By measuring the downlink reference signals, the strongest transmit beam of the base station and the strongest receive beam of the UE can be selected for transmission of data and / or control signals on the downlink channel. Similarly, by performing uplink beam scanning from the UE to the base station and measuring the uplink reference signals, the strongest receive beam of the base station and the strongest transmit beam of the UE can be selected for transmission of data and / or control signals on the uplink channel.

[0009] Furthermore, with the development of artificial intelligence (AI) technology, AI-based beam management solutions have been proposed. Specifically, an AI-based beam management model can be established to use the transmit and receive beams used for past information transmission to predict the transmit and receive beams used for future information transmission.

[0010] Compared with the channel measurement-based beam management in non-AI mode, the AI-based beam management in AI mode can reduce the measurement overhead on the base station / UE side and improve the efficiency of beam management. However, the inventors of the present disclosure have found that in some cases, compared with the beam management in non-AI mode, the beam management in AI mode may not necessarily bring good channel quality. For example, due to the influence of the wireless environment, there is an obstruction between the UE and the base station, resulting in poor signal quality, which may affect the channel quality obtained by the beam management in AI mode.

[0011] In view of one or more of the above problems, the present disclosure provides a prediction mechanism for beam management mode, which can predict whether AI mode or non-AI mode will be used for beam management at a future moment.

[0012] According to one aspect of the present disclosure, an electronic device is provided. The electronic device may include a processing circuit, the processing circuit being configured to: obtain first channel quality measurement information based on a non-AI mode and second channel quality measurement information based on an AI mode, wherein in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, a beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam; provide the first channel quality measurement information as input to a first prediction model, and obtain first channel quality prediction information predicted for a future time from an output of the first prediction model, the first prediction model being trained using past first channel quality measurement information in the non-AI mode; provide the second channel quality measurement information as input to a second prediction model, and obtain second channel quality prediction information predicted for the future time from an output of the second prediction model, the second prediction model being trained using past second channel quality measurement information in the AI ​​mode; and compare the first channel quality prediction information with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time.

[0013] According to another aspect of the present disclosure, a communication method is provided. The method may include: obtaining first channel quality measurement information based on a non-AI mode and second channel quality measurement information based on an AI mode, wherein in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, the beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam; providing the first channel quality measurement information as input to a first prediction model, and obtaining first channel quality prediction information predicted for a future time from an output of the first prediction model, the first prediction model being trained using past first channel quality measurement information in the non-AI mode; providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future time from an output of the second prediction model, the second prediction model being trained using past second channel quality measurement information in the AI ​​mode; and comparing the first channel quality prediction information with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time.

[0014] According to another aspect of the present disclosure, a computer-readable storage medium is provided, comprising executable instructions. When the executable instructions are executed by an information processing device, the information processing device is caused to perform the communication method according to the present disclosure.

[0015] According to yet another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the communication method according to the present disclosure.

[0016] According to one or more embodiments of the present disclosure, it is possible to predict whether AI mode or non-AI mode will be used for beam management in the future, thereby improving the efficiency of beam management and reducing the system overhead of beam management while ensuring the channel quality that beam management can bring. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0018] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0019] FIG1 is a schematic diagram illustrating beam management based on channel measurement in a non-AI mode;

[0020] FIG2 is a block diagram illustrating an exemplary configuration of an electronic device for performing prediction of a beam management mode according to an embodiment of the present disclosure;

[0021] FIG3 is an exemplary flow chart illustrating a communication method for predicting a beam management mode according to an embodiment of the present disclosure;

[0022] FIG4 is a schematic diagram illustrating data flow in a communication method for predicting a beam management mode according to an embodiment of the present disclosure;

[0023] FIG5 is an exemplary signaling flow diagram illustrating AI beam management according to an embodiment of the present disclosure;

[0024] FIG6 is a block diagram illustrating a first example of a schematic configuration of a gNB according to an embodiment of the present disclosure;

[0025] FIG7 is a block diagram illustrating a second example of a schematic configuration of a gNB according to an embodiment of the present disclosure;

[0026] FIG8 is a block diagram illustrating an example of a schematic configuration of a smartphone according to an embodiment of the present disclosure; and

[0027] FIG. 9 is a block diagram illustrating an example of a schematic configuration of a car navigation device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0029] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0030] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0031] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0032] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0033] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0034] FIG1 shows a schematic diagram of beam management based on channel measurement in a non-AI mode.

[0035] The rightward arrow in FIG1 represents the downlink direction from the base station 1000 to the UE 1004, and the leftward arrow represents the uplink direction from the UE 1004 to the base station 1000. As shown in FIG1 , the base station 1000 includes n t_DL Downlink transmit beams (n t_DL is a natural number greater than or equal to 1, and is shown as n in Figure 1 t_DL =9), UE 1004 includes n r_DL Downlink receive beams (n r_DL is a natural number greater than or equal to 1, and is shown as n in Figure 1 r_DL =5).

[0036] As shown in FIG1 , during the downlink beam scanning process, the n t_DL One of the downlink transmission beams (e.g., beam 1002) sends n r_DL downlink reference signals, UE 1004 uses n r_DL The downlink receiving beams receive the nr_DL The downlink reference signal may be, for example, a synchronization signal block (SSB) or a channel state information reference signal (CSI-RS), or other reference signals that can be used for channel quality measurement. r_DL The downlink reference signals are measured (for example, the received signal power (such as reference signal received power RSRP) and channel quality (such as channel quality indicator CQI) of the downlink reference signals), thereby determining the strongest downlink receiving beam of UE 1004. Next, the n t_DL For example, n beams other than beam 1002 t_DL -1 downlink transmission beam sends n to UE 1004 respectively t_DL -1 downlink reference signal, UE 1004 uses the determined strongest downlink receiving beam to receive these n t_DL -1 downlink reference signal and perform measurements to determine the strongest downlink transmit beam of base station 1000.

[0037] The uplink beam scanning process is similar to the downlink beam scanning process, using the n t_UL Uplink transmission beams and base station 1000's n r_UL The uplink receiving beams are scanned for uplink beams, thereby determining the strongest uplink transmitting beam of UE 1004 and the strongest uplink receiving beam of base station 1000.

[0038] After the downlink beam scanning and uplink beam scanning processes are completed, the determined strongest transceiver beam of the base station and the strongest transceiver beam of the UE are used to transmit the subsequent information (such as data and / or control signals).

[0039] The above describes non-AI mode channel measurement-based beam management (hereinafter sometimes referred to as "non-AI mode beam measurement"). With the development of AI technology, AI-based beam management in AI mode has been proposed. Specifically, an AI beam management model can be established to use the transmit and receive beams used for past information transmission to predict the transmit and receive beams used for future information transmission.

[0040] As an example, the following briefly describes the training phase and prediction phase of the AI ​​beam management model.

[0041] During the training phase of the AI ​​beam management model, the transmit beam and receive beam (e.g., beam ID) actually used in past information transmission are used as training data to train the AI ​​beam management model. In some embodiments, the training data may be a continuous time series data, such as time series data obtained by collecting a predetermined number of beam IDs (e.g., 500 times, 5 milliseconds each time) at predetermined time intervals over a continuous period of time in the past. In the training data, for example, the transmit beam and receive beam at time 0 to t0-N in the past (N is the time step, such as the sampling period of the training data, which can be set arbitrarily) can be used as the input of the AI ​​beam management model, and the transmit beam and receive beam at time t0 in the past can be used as the true value. The output of the AI ​​beam management model and the true value are compared, and the parameters of the AI ​​beam management model are modified in a way that reduces the difference between the output of the AI ​​beam management model and the true value, so as to complete the training phase of the AI ​​beam management model.

[0042] During the prediction phase of the AI ​​beam management model, the actual transmit beam and receive beam at the current time t are input as the input to the AI ​​beam management model, and the predicted transmit beam and receive beam at the future time t+N can be obtained through the output of the AI ​​beam management model. In addition, the future time that the AI ​​beam management model can predict is not limited to the time t+N, but can also be any time within a predetermined time period from the current time. The granularity of the future time that the AI ​​beam management model can predict can be appropriately set and adjusted as needed. In addition, the sampling frequency of the training data can also be appropriately determined based on this granularity.

[0043] It should be understood that the AI ​​beam management model described in this article can be any AI-based model, for example, including but not limited to deep learning neural network (such as convolutional neural network CNN, recurrent neural network RNN, long short-term memory network LSTM) model.

[0044] Compared with the beam management in the non-AI mode, the beam management in the AI ​​mode can reduce the measurement overhead on the base station / UE side and improve the efficiency of beam management, etc., because there is no need to perform beam scanning and channel measurement. However, the inventors of the present disclosure found that in some cases, compared with the beam management in the non-AI mode, the beam management in the AI ​​mode may not necessarily bring good channel quality. For example, due to the influence of the wireless environment, there is an obstruction between the UE and the base station, resulting in poor signal quality, which may affect the channel quality obtained by the beam management in the AI ​​mode. Therefore, the present disclosure proposes a prediction mechanism for the beam management mode, which can predict whether the AI ​​mode or the non-AI mode will be used for beam management in the future.

[0045] The prediction mechanism of the beam management mode according to the present disclosure will be described in detail below with reference to FIG. 2 to FIG. 4 .

[0046] 2 shows an exemplary configuration block diagram of an electronic device 2000 according to an embodiment of the present disclosure. The electronic device 2000 may be used, for example, to perform prediction of a beam management mode according to the present disclosure.

[0047] In some embodiments, the electronic device 2000 may include a processing circuit 2010. The processing circuit 2010 of the electronic device 2000 provides various functions of the electronic device 2000. In some embodiments, the processing circuit 2010 of the electronic device 2000 may be configured to execute a communication method for the electronic device 2000.

[0048] Processing circuitry 2010 may refer to various implementations of digital circuitry, analog circuitry, or mixed-signal (a combination of analog and digital) circuitry that performs functions in a computing system. Processing circuitry may include, for example, circuits such as integrated circuits (ICs), application-specific integrated circuits (ASICs), portions or circuits of a separate processor core, an entire processor core, a separate processor, a programmable hardware device such as a field programmable gate array (FPGA), and / or a system including multiple processors.

[0049] In some embodiments, the processing circuit 2010 may include a data acquisition unit 2020 , a data processing unit 2030 , and a comparison unit 2040 , configured to execute corresponding steps in the communication method shown in FIG. 3 described later.

[0050] In some embodiments, the electronic device 2000 may further include a memory (not shown). The memory of the electronic device 2000 may store information generated by the processing circuit 2010 as well as programs and data used for the operation of the electronic device 2010. The memory may be a volatile memory and / or a non-volatile memory. For example, the memory may include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), and a flash memory.

[0051] In addition, the electronic device 2000 can be implemented at the chip level, or can also be implemented at the device level by including other external components. In some embodiments, the electronic device 2000 can be implemented as a first communication device as a whole device, and can also include multiple antennas. In addition, the electronic device 2000 can be deployed in the cloud, on the base station side, or on the UE side.

[0052] It should be understood that the above-mentioned units are merely logical modules divided according to the specific functions they implement, and are not intended to limit the specific implementation methods. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.).

[0053] FIG3 shows an exemplary flowchart of a communication method for predicting a beam management mode according to an embodiment of the present disclosure. The communication method may be implemented by the electronic device 2000 shown in FIG2 , for example.

[0054] As shown in FIG. 3 , in S3000 , the data acquiring unit 2020 acquires first channel quality measurement information based on a non-AI mode and second channel quality measurement information based on an AI mode.

[0055] The non-AI mode is, for example, the non-AI mode based on channel measurement described above with reference to FIG1 . In the non-AI mode, beam measurement, for example, as shown in FIG1 , is performed to determine the beam used for information transmission. In addition, the first channel quality measurement information may include channel quality measurement information for the beam used for information transmission determined in the non-AI mode. The channel quality measurement information may include, for example, one or more of RSRP, CQI, bit error rate (BER), signal-to-interference-plus-noise ratio (SINR), and beam azimuth (degree), but is not limited thereto. Other channel quality measurement information may also be included, as long as it is information that can reflect channel quality.

[0056] The AI ​​mode is based on the AI ​​beam management model described above. In the AI ​​mode, the AI ​​beam management model is used to predict the beam used for information transmission. In addition, the second channel quality measurement information includes channel quality measurement information for the beam used for information transmission predicted by the AI ​​beam management model.

[0057] In the case of downlink communication, the UE performs downlink channel quality measurement and provides first channel quality measurement information and second channel quality measurement information to the data acquisition unit 2020. Similarly, in the case of uplink communication, the base station performs uplink channel quality measurement and provides first channel quality measurement information and second channel quality measurement information to the data acquisition unit 2020.

[0058] Next, in S3010 , the data processing unit 2030 provides the first channel quality measurement information as input to the first prediction model, and obtains first channel quality prediction information predicted for a future time from the output of the first prediction model.

[0059] In S3020, the data processing unit 2030 provides the second channel quality measurement information as input to the second prediction model, and obtains second channel quality prediction information predicted for the future time from the output of the second prediction model.

[0060] Figure 4 illustrates a schematic diagram of data flow in a communication method for predicting a beam management mode according to an embodiment of the present disclosure. As shown in Figure 4 , first channel quality measurement information 4010 and second channel quality measurement information 4040 acquired in step S3000 are provided to a first prediction model 4020 and a second prediction model 4050, respectively, in step S3020.

[0061] The first prediction model 4020 is trained using past first channel quality measurement information in the non-AI mode.

[0062] During the training phase of the first prediction model 4020, past first channel quality measurement information is used as training data to train the first prediction model 4020. The past first channel quality measurement information is obtained by measuring beams used for information transmission in the past in the non-AI mode. In some embodiments, the past first channel quality measurement information can be a continuous time series data, such as time series data obtained by collecting channel measurement information a predetermined number of times (e.g., 500 times, each 5 milliseconds) at predetermined time intervals over a continuous period of time in the past. In the training data, for example, the first channel quality measurement information from time 0 to t0-N (N is the time step, such as the sampling period, which can be arbitrarily set) can be used as the input of the first prediction model 4020, and the first channel quality measurement information at time t0 in the past can be used as the true value. The output of the first prediction model 4020 and the true value are compared, and the parameters of the first prediction model 4020 are modified in a manner that reduces the difference between the output of the first prediction model 4020 and the true value, thereby completing the training phase of the first prediction model 4020.

[0063] During the prediction phase of the first prediction model 4020, the first channel quality measurement information 4010 at the current time t is input as the first prediction model 4020 input. The first channel quality prediction information 4030 for a future time (e.g., time t+N) can be obtained using the output of the AI ​​beam management model. The first channel quality prediction information 4030 can also be a segment of time series data (e.g., time series data at time t+N), whose data type corresponds to the first channel quality measurement information 4010 at the current time. For example, if the first channel quality measurement information 4010 at the current time t is RSRP, the output of the first prediction model 4020 can be RSRP at the future time t+N, which serves as the first channel quality prediction information 4030 at the future time t+N.

[0064] The second prediction model 4050 is trained using past second channel quality measurement information in the AI ​​mode.

[0065] During the training phase of the second prediction model 4050, past second channel quality measurement information is used as training data to train the second prediction model 4050. The past second channel quality measurement information is obtained by measuring beams used for information transmission in the AI ​​mode in the past. In some embodiments, the past second channel quality measurement information can be a continuous time series data, such as time series data obtained by collecting channel measurement information a predetermined number of times (e.g., 500 times, each 5 milliseconds) at predetermined time intervals over a continuous period of time in the past. In the training data, for example, the second channel quality measurement information from time 0 to t0-N (N is the time step, such as the sampling period of the training data, which can be set arbitrarily) can be used as the input of the second prediction model 4050, and the second channel quality measurement information at time t0 in the past can be used as the true value. The output of the second prediction model 4050 is compared with the true value, and the parameters of the second prediction model 4050 are modified in a manner that reduces the difference between the output of the second prediction model 4050 and the true value, thereby completing the training phase of the second prediction model 4050.

[0066] During the prediction phase of the second prediction model 4050, the second channel quality measurement information 4040 at the current time t is input as the input of the second prediction model 4050. The second channel quality prediction information 4060 for a future time (e.g., time t+N) can be obtained through the output of the AI ​​beam management model. The second channel quality prediction information 4060 can also be a piece of time series data (e.g., time series data at time t+N), whose data type corresponds to the actual second channel quality measurement information 4040 input at the current time. For example, if the actual second channel quality measurement information 4040 input at the current time t is RSRP, the output of the second prediction model 4050 can be the RSRP at the future time t+N, which serves as the second channel quality prediction information 4060 at the future time t+N.

[0067] It should be understood that, similar to the AI ​​beam management model described above, the first prediction model 4010 and the second prediction model 4020 described herein can be any AI-based model, for example, including but not limited to deep learning neural network (e.g., convolutional neural network CNN, recurrent neural network RNN, long short-term memory network LSTM) models.

[0068] In addition, LSTM is a time-recurrent neural network. Compared with ordinary RNN, LSTM can perform better in longer sequences. The LSTM network has an input layer, a hidden layer, a fully connected layer and a regression layer (output layer), wherein the role of the hidden layer is to enable the network to achieve the effect of "forgetting the unimportant and remembering the important" during the training process, so that during the test process, the regression layer (output layer) can make predictions with a higher accuracy. The optimization function in the LSTM network training process adopts Adam (a first-order optimization algorithm that can replace the traditional stochastic gradient descent process, which can iteratively update the neural network weights based on training data). Therefore, in the present disclosure, it is preferred to use LSTM to predict future beam selection, thereby reducing the overhead of beam measurement, etc. In addition, for the AI ​​beam management model, since it also has time dependence, LSTM is also preferably used.

[0069] Referring back to FIG3 , in S3030 , the comparison unit 2040 compares the first channel quality prediction information with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future moment. For example, referring to FIG4 , the first channel quality prediction information 4030 and the second channel quality prediction information 4060 are input into a comparison model 4070 (corresponding to the comparison unit 2040 in FIG2 ) to determine a comparison result 4080. For example, if the first channel quality prediction information 4030 and the second channel quality prediction information 4060 include RSRP, the two RSRPs may be compared to determine the comparison result 4080.

[0070] In some embodiments, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is below a first predetermined threshold, the comparison model 4070 may determine that the comparison result 4080 indicates that the AI ​​mode will be used at the future time. Alternatively, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is greater than the first predetermined threshold, the comparison model 4070 may determine that the comparison result 4080 indicates that the non-AI mode will be used at the future time.

[0071] The first predetermined threshold value can be, for example, an empirical value determined based on the actual network environment, and can be adjusted according to changes in the network environment. In the present disclosure, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is relatively small (below the first predetermined threshold value), it can be considered that the prediction results in the AI ​​mode and the non-AI mode are similar, so the AI ​​mode can be used in the future to improve the efficiency of beam management and reduce the system overhead of beam management while ensuring channel quality. In addition, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is relatively large (greater than the first threshold value), it can be considered that the prediction result in the AI ​​mode may have a large deviation, so the non-AI mode is used in the future to ensure channel quality.

[0072] In some embodiments, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is greater than the second predetermined threshold, the second prediction model 4050 may be retrained. The second predetermined threshold may be, for example, an empirical value determined based on the actual network environment, and may be adjusted according to changes in the network environment. In the present disclosure, when the difference between the first channel quality prediction information 4030 and the second channel quality prediction information 4060 is greater than the second predetermined threshold, it may be considered that a large deviation has occurred in the prediction result under the AI ​​mode. This may be because the prediction under the AI ​​mode is a further prediction of the prediction result of the AI ​​beam management model, which is prone to cumulative errors, thereby requiring the second prediction model 4050 to be retrained. In some embodiments, the second predetermined threshold and the first predetermined threshold described above may be set independently of each other. In other embodiments, the second predetermined threshold may be set to be greater than or equal to the first predetermined threshold.

[0073] In some embodiments, when it is determined that the comparison result 4080 is to use the AI ​​mode at a future moment, the base station can activate the AI ​​mode, so that the AI ​​mode is used at the future moment. In addition, when it is determined that the comparison result 4080 is to use the non-AI mode at a future moment, the base station can deactivate the AI ​​mode, so that the non-AI mode is used at the future moment. In addition, in some embodiments, when the AI ​​beam management model based on the AI ​​mode is deployed on the UE side, the base station can activate or deactivate the AI ​​mode by sending control signaling such as medium access control-control element (MAC CE) or downlink control information (DCI) to the UE, or carry information for activating or deactivating the AI ​​mode in the PDSCH. In some embodiments, when the electronic device 2000 is deployed on the UE side, the UE can feedback the comparison result 4080 to the base station through control signaling such as uplink control information (UCI) or physical uplink data channel (PUSCH), so that the base station activates or deactivates the AI ​​mode.

[0074] In addition, in some embodiments, taking into account the cumulative error of the second prediction model 4050 described above, the base station can periodically deactivate the AI ​​mode and adjust or retrain the second prediction model 4050 to reduce the cumulative error of the second prediction model 4050 and improve the prediction accuracy of the second prediction model 4050.

[0075] Next, an exemplary signaling process of AI beam management according to an embodiment of the present disclosure is described with reference to FIG. 5 .

[0076] In order to describe an exemplary signaling process of AI beam management according to the present disclosure, some concepts related to the signaling process are first introduced below.

[0077] In beam management, the base station configures the transmission configuration indication (TCI) state through radio resource control (RRC) signaling and MAC CE, and activates different TCI states with DCI to inform the UE which downlink transmit beam the base station has activated for the UE's information transmission, so that the UE can accordingly select the optimal downlink receive beam corresponding to the downlink transmit beam.

[0078] The TCI status is defined as follows:

[0079] To receive a reference signal, the UE must derive the required large-scale parameters from one or more quasi-co-located (QCL) source signals. Therefore, before receiving the target reference signal, the base station must configure the UE's QCL source signal and the QCL type between the target reference signal and the source signal through signaling. To configure the QCL relationship between reference signals, TCI states are introduced.

[0080] The structure of the TCI state is, for example, {RS1|QCL-Type 1, RS2|QCL-Type 2} or {RS1|QCL-Type 1}, where RS1 and RS2 are identification information of the downlink reference signal, and QCL-Type 1 and QCL-Type 2 are QCL types. Each TCI state may include, for example, one or two downlink reference signals and their corresponding QCL types. The downlink reference signal configured in the TCI state may be, for example, an SSB or CSI-RS. If a TCI state is configured for a reference signal, its QCL source signal and QCL type can be determined from the TCI state configuration.

[0081] The following is an example configuration procedure for the TCI state.

[0082] The configuration of the TCI state depends on the type of reference signal and there are several ways.

[0083] Configuration via RRC signaling: For example, the TCI state of the periodic CSI-RS / Tracking Reference Signal (TRS) is configured via RRC signaling.

[0084] Configured through RRC signaling and activated by MAC-CE (referred to as MAC-CE indication): For example, semi-persistent CSI-RS / TRS or the demodulation reference signal (DM-RS) of the physical downlink control channel (PDCCH) are configured through RRC signaling and then indicated by MAC-CE.

[0085] Configured through RRC signaling, activated by MAC-CE, and then indicated by DCI (referred to as DCI indication): For example, aperiodic CSI-RS / TRS or DM-RS of the physical downlink shared channel (PDSCH) is configured through RRC signaling, activated by MAC-CE, and then indicated by DCI.

[0086] Next, an exemplary signaling process for AI beam management according to the present disclosure will be described in detail with reference to FIG5 . It should be understood that the signaling process shown in FIG5 is for beam management of downlink transmit / receive beams. The signaling process for beam management of uplink transmit / receive beams can also be implemented similarly and will not be described in detail here.

[0087] As shown in Figure 5, T1 and T2 show the period of configuring the TCI state by RRC signaling. The TCI state can, for example, indicate multiple transmit beam groups, each of which includes multiple available transmit beams. For example, multiple transmit beam groups B1, B2, and B3 can be expressed as B1=1-8, B2=9-16, and B3=17-24, where the numbers in each beam group indicate the IDs of the available transmit beams. In each period T (for example, T1 and T2), multiple TCI state SSB ID update periods are included. In Figure 5, the example of period T1 includes two update periods t1 and t2, and period T2 includes two update periods t3 and t4. The SSB ID is used to indicate the activated TCI state, for example, activated by MAC CE. The activated TCI state includes a transmit beam group activated from multiple transmit beam groups, indicating the ID of a group of currently available transmit beams (for example, B1, B2, or B3). In addition, each update period t (eg, t1, t2, t3, t4) includes multiple DCI signaling periods, which are used for the base station to send DCI signaling to the UE.

[0088] In the t1 time slot, at S11, based on the beam measurement results reported by the UE, the base station uses DCI to control the transmit / receive (TX / RX) beam selection. This process can be completed, for example, by the beam scanning process shown in Figure 1. For example, the UE can measure the downlink beam (for example, measure the SSB or CSI-RS) and report a measurement report. The measurement report can include, for example, the best beams in the downlink transmit beam and the best receive beam corresponding to each downlink transmit beam. For example, the measurement report can include the first four beams with the largest RSRP and arrange them in order from best to worst, or it can include the RSRP of the strongest beam in the downlink transmit beam and the difference between the RSRP of the remaining best beams and the strongest beam. Based on the beam measurement results reported by the UE, the base station uses DCI to indicate the TX beam to the UE, and the UE determines the RX beam based on the TX beam indicated by the base station.

[0089] In S12, the AI ​​beam management model selects the optimal TX / RX beam for time slot t2 based on the TX / RX beam pair obtained in S11, and the UE reports it to the base station.

[0090] The AI ​​beam management model described in the present disclosure can be deployed on the cloud, base station or UE side. In some embodiments, when the AI ​​beam management model is deployed on the cloud, the AI ​​beam management model obtains the beam measurement result of the t1 time slot from the base station or UE, predicts the best beam or best beam group of the t2 time slot, and provides it to the base station and UE. In some embodiments, when the AI ​​beam management model is deployed on the base station side, the AI ​​beam management model predicts the best beam or best beam group of the t2 time slot based on the beam measurement result of the t1 time slot reported by the UE, and provides it to the UE. In some embodiments, when the AI ​​beam management model is deployed on the UE side, the AI ​​beam management model predicts the best beam or best beam group of the t2 time slot based on the beam measurement result of the t1 time slot measured by the UE, and provides it to the base station. The case illustrated in S12 is the case where the AI ​​beam management model is deployed on the UE side.

[0091] The optimal TX / RX beam for time slot t2 predicted by the AI ​​beam management model in time slot t1 can be used in time slot t2, so that beam measurement is not required in time slot t2, thereby reducing the transmission of base station reference signals and UE measurements, and reducing power consumption.

[0092] The predicted optimal TX / RX beam described in the present disclosure can be not only the optimal TX / RX beam pair, but also a group of possible optimal TX beams, a group of possible optimal RX beams, or a group of possible optimal TX / RX beam pairs. Even if the predicted optimal TX / RX beam pair is not the optimal TX / RX beam pair, but a group of possible optimal TX beams, a group of possible optimal RX beams, or a group of possible optimal TX / RX beam pairs, the UE can measure only this group of beams / beam pairs during the t2 time slot instead of measuring all beams, thereby reducing measurement overhead.

[0093] In S13, the UE reports the measurement results based on the TX / RX beam pair selected in S11 and marks it as non-AI mode. Since the selection of the TX / RX beam pair in S11 is obtained through channel measurement in non-AI mode, the measurement result is marked as non-AI mode. The measurement results reported in this step correspond to the first channel quality measurement information described above, which can be used as the past first channel quality measurement information to train the first prediction model 4020 based on the non-AI mode, or can be used as the current first channel quality measurement information to input into the first prediction model 4020 to obtain the first channel quality prediction information at the future moment.

[0094] Next, in time slot t2, in S21, based on the UE's reported measurement results of the optimal TX / RX beam (e.g., the optimal TX / RX beam pair) for time slot t2 predicted in S12, the base station controls TX / RX beam pair selection using DCI. Furthermore, if the UE reports to the base station in S12 not the optimal TX / RX beam pair, but rather the optimal TX beam group, the optimal RX beam group, or a group of TX / RX beam pairs, the UE performs beam measurement within the optimal TX beam group, the optimal RX beam group, or the group of TX / RX beam pairs, and reports the measurement results to the base station for the base station to control beam selection.

[0095] In S22, the UE reports the measurement result based on the TX / RX beam pair selected in S21 and marks the AI ​​mode. Since the selection of the TX / RX beam pair in S21 is predicted by the AI ​​beam management model in the AI ​​mode, the measurement result is marked with the AI ​​mode. The measurement result reported in this step corresponds to the second channel quality measurement information described above, and can be used as the past second channel quality measurement information to train the second prediction model 4050 based on the non-AI mode, or it can be used as the current second channel quality measurement information to input into the second prediction model 4050 to obtain the second channel quality prediction information at the future moment.

[0096] Through the signaling process of AI beam management in time slots t1 and t2, the AI ​​beam management model can be used to predict the best beam pair, the best downlink beam group, the best uplink beam group or the best beam pair group in future time slots, thereby reducing or avoiding beam measurements, reducing the transmission of base station reference signals and UE measurements, and thus reducing power consumption.

[0097] In communications in higher frequency bands (e.g., the 52.6-71 GHz band), narrower beams are used to compensate for greater path loss, resulting in a much greater number of beams than in lower frequency bands (e.g., the 5 / 6 GHz band). However, the maximum number of TCI states supported by each bandwidth partial (BWP) is fixed and limited (e.g., 128). The QCL source reference signal SSB ID in each TCI state has a fixed one-to-one correspondence with the actual SSB ID. For example, 128 TCI states can only support the indication of a maximum of 64 beams. Therefore, the maximum number of 128 TCI states may not be able to match the significantly increased number of beams in higher frequency bands (e.g., the 52.6-71 GHz band).

[0098] If no additional beam indication is added, the beams included in the activated TCI state can be updated. These beams are from a subset of all beams, such as beam groups B1, B2, or B3 described above. However, according to the signaling time slot relationship in Figure 5, it can be found that the TCI state update period is the SSB ID update period t (t1, t2, t3, t4) shown in Figure 5, which requires a long process and may cause system delays.

[0099] In light of the above issues, this disclosure investigates a solution for coping with the increase in the number of beams without adding additional beam indicators. This solution utilizes an AI-based beam management model to predict the beam groups in future TCI states, enabling preemptive updates of the beams in those states. This solution is described in detail below, with reference to time slots t3 and t4 in Figure 5.

[0100] In the time slot t3, the processing of S31, S32, and S34 corresponds to S11, S12, and S13 in the time slot t1, respectively, and will not be repeated here.

[0101] In some embodiments, when the activated TCI state does not include the beam predicted in the AI ​​mode, processing is performed to modify the activated TCI state to include the predicted beam. Specifically, in S33, the UE finds that the best TX / RX beam (e.g., TX beam) at time t4 predicted in S32 is not included in the activated TCI state, and notifies the base station to modify the activated TCI state at time t4 to include the predicted best TX / RX beam (e.g., TX beam). In addition, S33 describes the case where the AI ​​beam management model is deployed on the UE side. In some embodiments, when the AI ​​beam management model is deployed on the base station side, the activated TCI state at time t4 is directly modified by the base station. In other embodiments, when the AI ​​beam management model is deployed on the cloud, the base station is notified from the cloud to modify the activated TCI state at time t4, or the UE is notified from the cloud, and the UE notifies the base station to modify the activated TCI state at time t4.

[0102] At time slot t4, in S41, the base station uses DCI to control TX / RX beam pair selection based on the UE's reported measurement results of the best TX / RX beam at time t4, as predicted in S32. At this point, because the base station has already modified the active TCI state at time t4 to include the measurement results of the best TX / RX beam at time t4 predicted in S32, there is no need to wait for the time to reconfigure the active TCI state.

[0103] The processing of S42 is the same as that of S22 in the time slot t2, and will not be repeated here.

[0104] Through the signaling process of AI beam management in time slots t3 and t4, the solution of increasing the number of beams can be coped with without adding additional beam indications. The AI ​​beam management model is used to predict the beam group in the future TCI state to update the beam in the TCI state in advance.

[0105] Next, the transmission timing and contents of the first channel quality information 4010 and the second channel quality information 4040 will be discussed.

[0106] Since the first channel quality information 4010 and the second channel quality information 4040 respectively indicate channel quality information based on a non-AI mode and channel quality information based on an AI mode, measures need to be taken to distinguish between the two.

[0107] In some embodiments, the first channel quality measurement information 4010 and the second channel quality measurement information 4040 can be obtained in different time slots. For example, the base station can configure different reporting time slots for the first channel quality measurement information 4010 and the second channel quality measurement information 4040, so that the UE reports the first channel quality measurement information 4010 and the second channel quality measurement information 4040 in corresponding time slots. This configuration can be implemented, for example, via control signaling such as MAC CE or DCI. Based on the different reporting time slots, the base station can identify whether the UE is reporting the first channel quality measurement information 4010 or the second channel quality measurement information 4040.

[0108] In some embodiments, the first channel quality measurement information 4010 and the second channel quality measurement information 4040 may be obtained at different periods. For example, the base station may configure different reporting periods for the first channel quality measurement information 4010 and the second channel quality measurement information 4040, so that the UE reports the first channel quality measurement information 4010 and the second channel quality measurement information 4040 according to the corresponding periods. This configuration may be implemented, for example, via control signaling such as MAC CE or DCI. Based on the different reporting periods, the base station can identify whether the UE is reporting the first channel quality measurement information 4010 or the second channel quality measurement information 4040.

[0109] In some embodiments, the first channel quality measurement information 4010 and the second channel quality measurement information 4040 may also be obtained using the same period plus different time slot offsets. For example, the base station may configure the first channel quality measurement information 4010 and the second channel quality measurement information 4040 with the same reporting period T, but with different reporting time slot offsets. For example, the first channel quality measurement information 4010 is reported in the first time slot with the reporting period T, while the second channel quality measurement information 4040 is reported in the second time slot with the reporting period T. This allows the base station to identify whether the UE is reporting the first channel quality measurement information 4010 or the second channel quality measurement information 4040 based on the reporting period and the different time slot offsets. This configuration may also be implemented, for example, through control signaling such as MAC CE or DCI.

[0110] In some embodiments, the reporting period of the first / second channel quality measurement information described above can also be used to define the prediction time window of the first / second prediction model of the present disclosure. For example, when the reporting period is T and the current time is t, the prediction model can predict the channel quality prediction information at the future time t+T, and then determine whether to use the non-AI mode or the AI ​​mode at the future time t+T.

[0111] In some embodiments, the first channel quality measurement information 4010 may carry identification information indicating non-AI mode, and the second channel quality measurement information 4040 may carry identification information indicating AI mode, for identification by the base station. In this case, there is no need to distinguish the reporting timing of the first channel quality measurement information 4010 and the second channel quality measurement information 4040. In addition, if the base station configures different reporting periods for the first channel quality measurement information 4010 and the second channel quality measurement information 4040, the information may carry indication information to distinguish between AI mode and non-AI mode only when the two reporting periods are integer multiples in time slots and the reporting time slots of the first channel quality measurement information 4010 and the second channel quality measurement information 4040 overlap.

[0112] In some embodiments, different UEs may use different AI beam management models to obtain the second channel quality measurement information based on the AI ​​mode. Different AI beam management models may have different model parameters depending on the area where the UE is located, the performance of the UE, etc. Therefore, the second channel quality measurement information 4040 may carry model information of the AI ​​beam management model. In this case, in some embodiments, the second prediction model 4050 may include multiple second prediction models corresponding to different AI beam management models, and each second prediction model is used to train the second channel quality measurement information of an AI beam management model. In addition, in the prediction stage, the corresponding second prediction model can also be selected from multiple second prediction models according to the model information of the AI ​​beam management model carried by the second channel quality measurement information to obtain the corresponding second channel quality prediction information.

[0113] In some embodiments, the first channel quality measurement information 4010 and the second channel quality measurement information 4040 may also carry auxiliary information, such as the UE's location and moving speed. Depending on the UE's location and moving speed, the channel quality measurement information obtained by the UE may be different. By carrying the UE's location, moving speed, etc. as auxiliary information in the channel quality measurement information, the channel quality measurement information can be classified according to the UE's location, moving speed, etc. Accordingly, the first prediction model 4020 may include one or more prediction models corresponding to the UE's location and / or moving speed, and the one or more prediction models are trained based on the first channel quality measurement information of the UE at different locations and moving speeds. The second prediction model 4050 may include one or more prediction models corresponding to the UE's location and / or moving speed, and the one or more prediction models are trained based on the second channel quality measurement information of the UE at different locations and moving speeds. This makes the trained first prediction model 4020 and second prediction model 4050 more accurate. Furthermore, during the prediction phase, first prediction model 4020 and second prediction model 4050 are selected based on the location and movement speed carried in first channel quality measurement information 4010 and second channel quality measurement information 4040, thereby making the prediction results more accurate. It should be understood that auxiliary information is not limited to the location and movement speed of the UE, and other auxiliary information can be selected based on actual needs, as long as it improves the prediction accuracy of first prediction model 4020 and second prediction model 4050.

[0114] As described above, the electronic device 2000 described herein for predicting the beam management mode can be deployed on the cloud, on the base station side, or on the UE side. When the electronic device 2000 is deployed on the cloud, the electronic device 2000 obtains corresponding information from the base station side or the UE side, trains the first prediction model 4020 and the second prediction model 4050, and uses the first prediction model 4020 and the second prediction model 4050 to make predictions, obtains a comparison result 4080, and provides it to the base station side / UE side. When the electronic device 2000 is deployed on the base station side, the electronic device 2000 obtains corresponding information from the UE side, trains the first prediction model 4020 and the second prediction model 4050, and uses the first prediction model 4020 and the second prediction model 4050 to make predictions, obtains a comparison result 4080, and provides it to the UE side. When the electronic device 2000 is deployed on the UE side, the electronic device 2000 obtains the corresponding information from the base station side, trains the first prediction model 4020 and the second prediction model 4050, and uses the first prediction model 4020 and the second prediction model 4050 to make predictions, obtains the comparison result 4080 and provides it to the base station side. In addition, the electronic device 2000 can also be deployed in a distributed manner, with part deployed on the cloud / base station side and part deployed on the UE side. In addition, since the training of the first prediction model 4020 and the second prediction model 4050 usually requires a large amount of training data and requires a large amount of computing and processing power, it is preferred to train the first prediction model 4020 and the second prediction model 4050 on the cloud or base station side, and send the trained first prediction model 4020 and the second prediction model 4050 to the UE side for prediction.

[0115] Application examples according to the present disclosure will be described below.

[0116] The technology of the present disclosure can be applied to various products.

[0117] For example, a base station can be implemented as any type of evolved NodeB (eNB) or gNodeB (gNB) in next-generation radio access technology, such as macro eNB / gNB and small eNB / gNB. A small eNB / gNB may be an eNB / gNB that covers a cell smaller than a macro cell, such as a pico eNB / gNB, micro eNB / gNB, and home (femto) eNB / gNB. Alternatively, a base station can be implemented as any other type of base station, such as one or both of a base transceiver station (BTS) and a base station controller (BSC) in a GSM system, one or both of a radio network controller (RNC) and a NodeB in a WCDMA system, or a corresponding network node in a future communication system. A base station may include: a main body configured to control wireless communications (also referred to as a base station device); and one or more remote radio heads (RRHs) located at a location different from the main body. In addition, the various types of terminals described below can each operate as a base station by temporarily or semi-permanently performing base station functions.

[0118] For example, the terminal device (UE) can be implemented as a mobile terminal (such as a smartphone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or an in-vehicle terminal (such as a car navigation device). The terminal device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also known as a machine-type communication (MTC) terminal). In addition, the terminal device can be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above-mentioned terminals.

[0119] [Application examples for base stations]

[0120] (First application example)

[0121] 6 is a block diagram illustrating a first example of a schematic configuration of a gNB to which the present disclosure can be applied. The gNB 800 includes one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 can be connected to each other via an RF cable.

[0122] Each antenna 810 includes a single or multiple antenna elements (such as the multiple antenna elements included in a multiple-input, multiple-output (MIMO) antenna) and is used for base station device 820 to transmit and receive wireless signals. As shown in Figure 6, gNB 800 may include multiple antennas 810. For example, multiple antennas 810 may be compatible with multiple frequency bands used by gNB 800. Base station device 820 includes a controller 821, a memory 822, a network interface 823, and a wireless communication interface 825.

[0123] The controller 821 may be, for example, a CPU or DSP, and operates various higher-layer functions of the base station device 820. For example, the controller 821 generates data packets based on data in signals processed by the wireless communication interface 825 and transmits the generated packets via the network interface 823. The controller 821 may bundle data from multiple baseband processors to generate bundled packets and transmit the generated bundled packets. The controller 821 may have logic functions for performing control such as radio resource control, radio bearer control, mobility management, admission control, and scheduling. This control may be performed in conjunction with a nearby gNB, eNB, or core network node (e.g., the Access and Mobility Management Function (AMF)). The memory 822 includes RAM and ROM and stores programs executed by the controller 821 and various types of control data (such as terminal lists, transmission power data, and scheduling data).

[0124] The network interface 823 is a communication interface for connecting the base station device 820 to the core network 824. The controller 821 can communicate with the core network node or another gNB / eNB via the network interface 823. In this case, the gNB 800 and the core network node or other gNB / eNB can be connected to each other through logical interfaces (such as the N2 interface with the AMF and the Xn interface with the gNB). The network interface 823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 823 is a wireless communication interface, the network interface 823 can use a higher frequency band for wireless communication than the frequency band used by the wireless communication interface 825.

[0125] The wireless communication interface 825 supports any cellular communication scheme (such as LTE, LTE-Advanced, and NR (New Radio)) and provides wireless connectivity to terminals located in the cell of the gNB 800 via the antenna 810. The wireless communication interface 825 may typically include, for example, a baseband (BB) processor 826 and RF circuitry 827. The BB processor 826 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for layers such as Layer 1 (L1), Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 821, the BB processor 826 may perform some or all of the aforementioned logical functions. The BB processor 826 may be a memory that stores communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 826. This module may be a card or blade inserted into a slot in the base station device 820. Alternatively, it may be a chip mounted on the card or blade. Meanwhile, the RF circuit 827 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via the antenna 810 .

[0126] As shown in Figure 6 , the wireless communication interface 825 may include multiple BB processors 826. For example, multiple BB processors 826 may be compatible with multiple frequency bands used by the gNB 800. As shown in Figure 6 , the wireless communication interface 825 may include multiple RF circuits 827. For example, multiple RF circuits 827 may be compatible with multiple antenna elements. While Figure 6 illustrates an example in which the wireless communication interface 825 includes multiple BB processors 826 and multiple RF circuits 827, the wireless communication interface 825 may also include a single BB processor 826 or a single RF circuit 827.

[0127] (Second application example)

[0128] FIG7 is a block diagram illustrating a second example of a schematic configuration of a gNB to which the techniques of this disclosure can be applied. A gNB 830 includes one or more antennas 840, a base station device 850, and an RRH 860. The RRH 860 and each antenna 840 can be connected to each other via an RF cable. The base station device 850 and the RRH 860 can also be connected to each other via a high-speed line such as a fiber optic cable.

[0129] Each of the antennas 840 includes a single or multiple antenna elements (such as the multiple antenna elements included in a MIMO antenna) and is used for the RRH 860 to transmit and receive wireless signals. As shown in FIG7 , the gNB 830 may include multiple antennas 840. For example, the multiple antennas 840 may be compatible with the multiple frequency bands used by the gNB 830. The base station device 850 includes a controller 851, a memory 852, a network interface 853, a wireless communication interface 855, and a connection interface 857. The controller 851, the memory 852, and the network interface 853 are the same as the controller 821, the memory 822, and the network interface 823 described with reference to FIG6 .

[0130] The wireless communication interface 855 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 860 via the RRH 860 and the antenna 840. The wireless communication interface 855 may generally include, for example, a BB processor 856. The BB processor 856 is identical to the BB processor 826 described with reference to FIG6 , except that the BB processor 856 is connected to the RF circuit 864 of the RRH 860 via the connection interface 857. As shown in FIG7 , the wireless communication interface 855 may include multiple BB processors 856. For example, multiple BB processors 856 may be compatible with multiple frequency bands used by the gNB 830. Although FIG7 shows an example in which the wireless communication interface 855 includes multiple BB processors 856, the wireless communication interface 855 may also include a single BB processor 856.

[0131] The connection interface 857 is an interface for connecting the base station device 850 (wireless communication interface 855) to the RRH 860. The connection interface 857 may also be a communication module for connecting the base station device 850 (wireless communication interface 855) to the RRH 860 for communication in the high-speed line.

[0132] The RRH 860 includes a connection interface 861 and a wireless communication interface 863 .

[0133] The connection interface 861 is an interface for connecting the RRH 860 (wireless communication interface 863) to the base station device 850. The connection interface 861 may also be a communication module for communication in the above-mentioned high-speed line.

[0134] The wireless communication interface 863 transmits and receives wireless signals via the antenna 840. The wireless communication interface 863 may generally include, for example, an RF circuit 864. The RF circuit 864 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 840. As shown in FIG7 , the wireless communication interface 863 may include multiple RF circuits 864. For example, the multiple RF circuits 864 may support multiple antenna elements. Although FIG7 shows an example in which the wireless communication interface 863 includes multiple RF circuits 864, the wireless communication interface 863 may also include a single RF circuit 864.

[0135] In gNB 800 and gNB 830 shown in Figures 6 and 7 , one or more components included in the processing circuit 2010 described with reference to Figure 2 may be implemented in the wireless communication interface 912. Alternatively, at least some of these components may also be implemented by the controller 821 and the controller 851.

[0136] [Application examples for terminal devices]

[0137] (First application example)

[0138] 8 is a block diagram showing an example of a schematic configuration of a smartphone 900 to which the technology of the present disclosure can be applied. The smartphone 900 includes a processor 901, a memory 902, a storage device 903, an external connection interface 904, a camera 906, a sensor 907, a microphone 908, an input device 909, a display device 910, a speaker 911, a wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, a bus 917, a battery 918, and an auxiliary controller 919.

[0139] The processor 901 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 900. The memory 902 includes RAM and ROM, and stores data and programs executed by the processor 901. The storage device 903 may include storage media such as semiconductor memories and hard disks. The external connection interface 904 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 900.

[0140] The camera 906 includes an image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) and generates a captured image. The sensor 907 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 908 converts the sound input to the smartphone 900 into an audio signal. The input device 909 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 910, and receives an operation or information input from the user. The display device 910 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display and displays an output image of the smartphone 900. The speaker 911 converts the audio signal output from the smartphone 900 into sound.

[0141] The wireless communication interface 912 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 912 may generally include, for example, a BB processor 913 and an RF circuit 914. The BB processor 913 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 914 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 916. The wireless communication interface 912 may be a chip module on which the BB processor 913 and the RF circuit 914 are integrated. As shown in FIG8 , the wireless communication interface 912 may include multiple BB processors 913 and multiple RF circuits 914. Although FIG8 shows an example in which the wireless communication interface 912 includes multiple BB processors 913 and multiple RF circuits 914, the wireless communication interface 912 may also include a single BB processor 913 or a single RF circuit 914.

[0142] In addition, in addition to the cellular communication scheme, the wireless communication interface 912 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near-field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 912 may include a BB processor 913 and an RF circuit 914 for each wireless communication scheme.

[0143] Each of the antenna switches 915 switches a connection destination of the antenna 916 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 912 .

[0144] Each of the antennas 916 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 912. As shown in FIG8 , the smartphone 900 may include multiple antennas 916. Although FIG8 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0145] In addition, the smartphone 900 may include an antenna 916 for each wireless communication scheme. In this case, the antenna switch 915 may be omitted from the configuration of the smartphone 900.

[0146] The bus 917 connects the processor 901, the memory 902, the storage device 903, the external connection interface 904, the camera 906, the sensor 907, the microphone 908, the input device 909, the display device 910, the speaker 911, the wireless communication interface 912, and the auxiliary controller 919. The battery 918 supplies power to the various blocks of the smartphone 900 shown in FIG8 via feeders, which are partially shown as dotted lines in the figure. The auxiliary controller 919 operates the minimum necessary functions of the smartphone 900, for example, in sleep mode.

[0147] 8 , one or more components included in the processing circuit 2010 described with reference to FIG2 may be implemented in the wireless communication interface 912. Alternatively, at least part of these components may also be implemented by the processor 901 or the auxiliary controller 919.

[0148] (Second application example)

[0149] 9 is a block diagram showing an example of a schematic configuration of a car navigation device 920 to which the technology of the present disclosure can be applied. The car navigation device 920 includes a processor 921, a memory 922, a global positioning system (GPS) module 924, a sensor 925, a data interface 926, a content player 927, a storage medium interface 928, an input device 929, a display device 930, a speaker 931, a wireless communication interface 933, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0150] The processor 921 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation apparatus 920. The memory 922 includes a RAM and a ROM, and stores data and programs executed by the processor 921.

[0151] The GPS module 924 measures the position (such as latitude, longitude, and altitude) of the car navigation device 920 using GPS signals received from GPS satellites. The sensor 925 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 926 is connected to, for example, the in-vehicle network 941 via an unillustrated terminal and acquires data generated by the vehicle (such as vehicle speed data).

[0152] The content player 927 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 928. The input device 929 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 930, and receives an operation or information input from the user. The display device 930 includes a screen such as an LCD or OLED display and displays an image of a navigation function or reproduced content. The speaker 931 outputs the sound of the navigation function or the reproduced content.

[0153] The wireless communication interface 933 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 933 may generally include, for example, a BB processor 934 and an RF circuit 935. The BB processor 934 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 935 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 937. The wireless communication interface 933 may also be a chip module on which the BB processor 934 and the RF circuit 935 are integrated. As shown in Figure 9, the wireless communication interface 933 may include multiple BB processors 934 and multiple RF circuits 935. Although Figure 9 shows an example in which the wireless communication interface 933 includes multiple BB processors 934 and multiple RF circuits 935, the wireless communication interface 933 may also include a single BB processor 934 or a single RF circuit 935.

[0154] In addition, in addition to the cellular communication scheme, the wireless communication interface 933 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 933 can include a BB processor 934 and an RF circuit 935.

[0155] Each of the antenna switches 936 switches a connection destination of the antenna 937 between a plurality of circuits included in the wireless communication interface 933 , such as circuits for different wireless communication schemes.

[0156] Each of the antennas 937 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 933. As shown in FIG9, the car navigation device 920 may include multiple antennas 937. Although FIG9 shows an example in which the car navigation device 920 includes multiple antennas 937, the car navigation device 920 may also include a single antenna 937.

[0157] Furthermore, the car navigation device 920 may include an antenna 937 for each wireless communication scheme. In this case, the antenna switch 936 may be omitted from the configuration of the car navigation device 920.

[0158] The battery 938 supplies power to the respective blocks of the car navigation device 920 shown in Fig. 9 via a feeder line, which is partially shown as a dotted line in the figure. The battery 938 accumulates the power supplied from the vehicle.

[0159] 9 , one or more components included in the processing circuit 2010 described with reference to FIG2 may be implemented in the wireless communication interface 912 . Alternatively, at least a portion of these components may also be implemented by the processor 921 .

[0160] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 940 including a car navigation device 920, an in-vehicle network 941, and one or more blocks of a vehicle module 942. The vehicle module 942 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 941.

[0161] It should be understood that references to "an embodiment" or similar expressions throughout this specification mean that the specific features, structures, or characteristics described in connection with that embodiment are included in at least one specific embodiment of the present disclosure. Therefore, the appearance of phrases such as "in an embodiment of the present disclosure" or similar expressions throughout this specification does not necessarily refer to the same embodiment.

[0162] Those skilled in the art will appreciate that the present disclosure is implemented as a system, apparatus, method, or computer-readable storage medium (e.g., a non-transitory storage medium) as a computer program product. Thus, the present disclosure may be implemented in various forms, such as a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microprogram code, etc.), or a combination of software and hardware, hereinafter referred to as a "circuit," "module," or "system." Furthermore, the present disclosure may also be implemented as a computer program product in any tangible media form having computer-usable program code stored thereon.

[0163] The relevant description of the present disclosure is described with reference to the flowcharts and / or block diagrams of the systems, devices, methods and computer program products according to specific embodiments of the present disclosure. It is understood that each block in each flowchart and / or block diagram, as well as any combination of blocks in the flowchart and / or block diagram, can be implemented using computer program instructions. These computer program instructions can be executed by a machine composed of a processor of a general-purpose computer or a special computer or other programmable data processing device, and the instructions are processed by the computer or other programmable data processing device to implement the functions or operations described in the flowchart and / or block diagram.

[0164] The accompanying drawings show flowcharts and block diagrams of the architecture, functions and operations that can be implemented by the systems, devices, methods and computer program products according to various embodiments of the present disclosure. Therefore, each block in the flowchart or block diagram can represent a module, segment, or portion of program code, which includes one or more executable instructions to implement the specified logical function. It should also be noted that in certain other embodiments, the functions described by the blocks may not be performed in the order shown in the figures. For example, two blocks connected in the figures can actually be executed simultaneously, or in some cases can be executed in the opposite order of the icons depending on the functions involved. It should also be noted that each block of the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a system based on dedicated hardware, or by a combination of dedicated hardware and computer instructions to perform specific functions or operations.

[0165] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technical improvements to marketed technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

[0166] Note that the technology disclosed in this specification can have the following configurations.

[0167] (1) An electronic device, comprising:

[0168] a processing circuit, the processing circuit being configured to:

[0169] Obtaining first channel quality measurement information based on a non-artificial intelligence (AI) mode and second channel quality measurement information based on the AI ​​mode, wherein, in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, the beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam;

[0170] providing the first channel quality measurement information as input to a first prediction model, and obtaining first channel quality prediction information predicted for a future time from an output of the first prediction model, wherein the first prediction model is trained using past first channel quality measurement information in the non-AI mode;

[0171] providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future time instant from an output of the second prediction model, wherein the second prediction model is trained using past second channel quality measurement information in an AI mode; and

[0172] The first channel quality prediction information is compared with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time.

[0173] (2) The electronic device according to (1), wherein

[0174] The first channel quality measurement information and the second channel quality measurement information are acquired in different time slots.

[0175] (3) The electronic device according to (1), wherein

[0176] The first channel quality measurement information and the second channel quality measurement information are acquired in different periods.

[0177] (4) The electronic device according to (1), wherein

[0178] The first channel quality measurement information carries identification information for indicating the non-AI mode, and the second channel quality measurement information carries identification information for indicating the AI ​​mode.

[0179] (5) The electronic device according to (1), wherein

[0180] The second channel quality measurement information carries model information of the AI ​​beam management model.

[0181] (6) The electronic device according to (1), wherein

[0182] The first channel quality measurement information and the second channel quality measurement information are obtained from a terminal device and carry a position and / or a moving speed of the terminal device.

[0183] The first prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device, and the second prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device.

[0184] (7) The electronic device according to (1), wherein the processing circuit is further configured to:

[0185] In a case where an activated transmission configuration indication (TCI) state does not include the beam predicted in the AI ​​mode, processing is performed to modify the activated TCI state to include the predicted beam.

[0186] (8) The electronic device according to (1), wherein the processing circuit is further configured to:

[0187] When the difference between the first channel quality prediction information and the second channel quality prediction information is below a first predetermined threshold, determining to use the AI ​​mode at the future time;

[0188] When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than the first predetermined threshold, it is determined to use the non-AI mode at the future moment.

[0189] (9) The electronic device according to (8), wherein the processing circuit is further configured to:

[0190] When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than a second predetermined threshold, the second prediction model is retrained.

[0191] (10) A communication method comprising:

[0192] Obtaining first channel quality measurement information based on a non-artificial intelligence (AI) mode and second channel quality measurement information based on the AI ​​mode, wherein, in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, the beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam;

[0193] providing the first channel quality measurement information as input to a first prediction model, and obtaining first channel quality prediction information predicted for a future time from an output of the first prediction model, wherein the first prediction model is trained using past first channel quality measurement information in the non-AI mode;

[0194] providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future time instant from an output of the second prediction model, wherein the second prediction model is trained using past second channel quality measurement information in an AI mode; and

[0195] The first channel quality prediction information is compared with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time.

[0196] (11) The communication method according to (10), wherein:

[0197] The first channel quality measurement information and the second channel quality measurement information are acquired in different time slots.

[0198] (12) The communication method according to (10), wherein:

[0199] The first channel quality measurement information and the second channel quality measurement information are acquired in different periods.

[0200] (13) The communication method according to (10), wherein:

[0201] The first channel quality measurement information carries identification information for indicating the non-AI mode, and the second channel quality measurement information carries identification information for indicating the AI ​​mode.

[0202] (14) The communication method according to (10), wherein:

[0203] The second channel quality measurement information carries model information of the AI ​​beam management model.

[0204] (15) The communication method according to (10), wherein:

[0205] The first channel quality measurement information and the second channel quality measurement information are obtained from a terminal device and carry a position and / or a moving speed of the terminal device.

[0206] The first prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device, and the second prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device.

[0207] (16) The communication method according to (10), further comprising:

[0208] In a case where an activated transmission configuration indication (TCI) state does not include the beam predicted in the AI ​​mode, processing is performed to modify the activated TCI state to include the predicted beam.

[0209] (17) The communication method according to (10), further comprising:

[0210] When the difference between the first channel quality prediction information and the second channel quality prediction information is below a first predetermined threshold, determining to use the AI ​​mode at the future time;

[0211] When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than the first predetermined threshold, it is determined to use the non-AI mode at the future moment.

[0212] (18) The communication method according to (10), further comprising:

[0213] When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than a second predetermined threshold, the second prediction model is retrained.

[0214] (19) A computer-readable storage medium comprising executable instructions, which, when executed by an information processing device, causes the information processing device to execute the communication method described in any one of (10) to (18).

[0215] (20) A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the processor is caused to execute the communication method described in any one of (10) to (18).

Claims

1. An electronic device, comprising: a processing circuit, the processing circuit being configured to: Obtaining first channel quality measurement information based on a non-artificial intelligence (AI) mode and second channel quality measurement information based on the AI ​​mode, wherein, in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, the beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam; providing the first channel quality measurement information as input to a first prediction model, and obtaining first channel quality prediction information predicted for a future time from an output of the first prediction model, wherein the first prediction model is trained using past first channel quality measurement information in the non-AI mode; providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future time instant from an output of the second prediction model, wherein the second prediction model is trained using past second channel quality measurement information in an AI mode; and The first channel quality prediction information is compared with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time.

2. The electronic device according to claim 1, wherein The first channel quality measurement information and the second channel quality measurement information are acquired in different time slots.

3. The electronic device according to claim 1, wherein The first channel quality measurement information and the second channel quality measurement information are acquired in different periods.

4. The electronic device according to claim 1, wherein The first channel quality measurement information carries identification information for indicating the non-AI mode, and the second channel quality measurement information carries identification information for indicating the AI ​​mode.

5. The electronic device according to claim 1, wherein The second channel quality measurement information carries model information of the AI ​​beam management model. The electronic device according to claim 1 , wherein: The first channel quality measurement information and the second channel quality measurement information are obtained from a terminal device and carry a position and / or a moving speed of the terminal device. The first prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device, and the second prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device.

7. The electronic device according to claim 1, wherein The processing circuit is further configured to: In a case where an activated transmission configuration indication (TCI) state does not include the beam predicted in the AI ​​mode, processing is performed to modify the activated TCI state to include the predicted beam.

8. The electronic device according to claim 1, wherein The processing circuit is further configured to: When the difference between the first channel quality prediction information and the second channel quality prediction information is below a first predetermined threshold, determining to use the AI ​​mode at the future time; When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than the first predetermined threshold, it is determined to use the non-AI mode at the future moment.

9. The electronic device according to claim 8, wherein: The processing circuit is further configured to: When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than a second predetermined threshold, the second prediction model is retrained.

10. A communication method, comprising: Obtaining first channel quality measurement information based on a non-artificial intelligence (AI) mode and second channel quality measurement information based on the AI ​​mode, wherein, in the non-AI mode, beam measurement is performed to determine a beam for information transmission, and the first channel quality measurement information includes channel quality measurement information for the determined beam; in the AI ​​mode, the beam for information transmission is predicted using an AI beam management model, and the second channel quality measurement information includes channel quality measurement information for the predicted beam; providing the first channel quality measurement information as input to a first prediction model, and obtaining first channel quality prediction information predicted for a future time from an output of the first prediction model, wherein the first prediction model is trained using past first channel quality measurement information in the non-AI mode; providing the second channel quality measurement information as input to a second prediction model, and obtaining second channel quality prediction information predicted for the future time instant from an output of the second prediction model, wherein the second prediction model is trained using past second channel quality measurement information in an AI mode; and The first channel quality prediction information is compared with the second channel quality prediction information to determine whether to use the non-AI mode or the AI ​​mode at the future time. The communication method according to claim 10 , wherein: The first channel quality measurement information and the second channel quality measurement information are acquired in different time slots.

12. The communication method according to claim 10, wherein: The first channel quality measurement information and the second channel quality measurement information are acquired in different periods.

13. The communication method according to claim 10, wherein: The first channel quality measurement information carries identification information for indicating the non-AI mode, and the second channel quality measurement information carries identification information for indicating the AI ​​mode. The communication method according to claim 10 , wherein: The second channel quality measurement information carries model information of the AI ​​beam management model.

15. The communication method according to claim 10, wherein: The first channel quality measurement information and the second channel quality measurement information are obtained from a terminal device and carry a position and / or a moving speed of the terminal device. The first prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device, and the second prediction model includes one or more prediction models corresponding to the position and / or moving speed of the terminal device.

16. The communication method according to claim 10, further comprising: The situation in which the beam predicted in the AI ​​mode is not included in the activated transmission configuration indication (TCI) state In this case, processing is performed to modify the activated TCI state to include the predicted beam.

17. The communication method according to claim 10, further comprising: When the difference between the first channel quality prediction information and the second channel quality prediction information is below a first predetermined threshold, determining to use the AI ​​mode at the future time; When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than the first predetermined threshold, it is determined to use the non-AI mode at the future moment.

18. The communication method according to claim 10, further comprising: When the difference between the first channel quality prediction information and the second channel quality prediction information is greater than a second predetermined threshold, the second prediction model is retrained. 19 . A computer-readable storage medium comprising executable instructions, which, when executed by an information processing device, causes the information processing device to execute the communication method according to claim 10 .

20. A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the communication method according to any one of claims 10 to 18.

Images