Electronic equipment on the user side for wireless communication, electronic equipment on the base station side for wireless communication, and method on the user side for wireless communication.

Abstract

The present invention provides electronic equipment and methods for user-side and base station-side wireless communication, as well as a computer-readable storage medium. The user-side electronic equipment for wireless communication includes a processing circuit configured to match a first artificial intelligence model for performing spatial-domain beam prediction with a second artificial intelligence model for performing time-domain beam prediction, and, if the matching is successful, to reuse beam measurement results between the first and second artificial intelligence models.

Description

Technical Field

[0001] This application claims the priority of a Chinese patent application filed with the China National Intellectual Property Administration on April 3, 2023, with the application number 202310354826.7 and the invention title "Electronic Devices and Methods on the User Equipment Side and the Base Station Side for Wireless Communication", and incorporates the entire content thereof by reference into this application.

[0002] This application relates to the field of wireless communication, specifically to beam management technology based on artificial intelligence (AI) in wireless communication. More specifically, it relates to an electronic device and method on the user equipment side for wireless communication, an electronic device and method on the base station side for wireless communication, and a computer-readable storage medium.

Background Art

[0003] At the RAN#94e plenary meeting, it was discussed and approved to add a new SID to Rel-18 and introduce artificial intelligence / machine learning (AI / ML) to wireless interface access. Beam management based on AI has become one of the main research directions. By using an AI / ML model for beam management, the conventional beam scanning process can be replaced to reduce overhead. Specifically, the AI / ML model can be trained with historical data, and the trained AI / ML model can be used to predict beam-related information.

[0004] Recently, various companies have evaluated the performance of AI-based beam management solutions and also discussed the impacts they have on the physical layer and potential problems and solutions. At the RAN#98e plenary meeting, it has become clear that at the current stage, the RAN1 topics for AI-based beam management only focus on two functional types: time-domain beam prediction and spatial-domain beam prediction. Due to factors such as the application environment, the size of the input / output set, and the differences in input / output parameter properties, there are many types of AI models in each functional type. The input / output relationship of the AI model is also within the scope of discussion of 3GPP (registered trademark).

Summary of the Invention

[0005] The following provides a brief overview of the Disclosure to offer a basic understanding of certain aspects of it. It should be understood that this overview is not exhaustive. It is not intended to identify any essential or important parts of the Disclosure, nor to limit its scope. Its purpose is, in a simplified form, to provide concepts that precede the more detailed descriptions that follow.

[0006] According to one aspect of this disclosure, the present invention provides an electronic device for a user device for wireless communication, which includes a processing circuit configured to match a first artificial intelligence model for performing spatial domain beam prediction with a second artificial intelligence model for performing time domain beam prediction, and, if the matching is successful, to reuse beam measurement results between the first and second artificial intelligence models.

[0007] In another aspect of this disclosure, a user-device-side method for wireless communication is provided, which includes matching a first artificial intelligence model for performing spatial-domain beam prediction with a second artificial intelligence model for performing time-domain beam prediction, and, if the matching is successful, reusing beam measurement results between the first and second artificial intelligence models.

[0008] According to one aspect of this disclosure, the present invention provides electronic equipment for a base station for wireless communication, which includes a processing circuit configured to match a first artificial intelligence model for performing spatial domain beam prediction with a second artificial intelligence model for performing time domain beam prediction, and, if the matching is successful, to reuse beam measurement results between the first and second artificial intelligence models.

[0009] In another aspect of this disclosure, a base station-side method for wireless communication is provided, which includes matching a first artificial intelligence model for performing spatial-domain beam prediction with a second artificial intelligence model for performing time-domain beam prediction, and, if the matching is successful, reusing beam measurement results between the first and second artificial intelligence models.

[0010] Other aspects of this disclosure further provide computer program code for implementing the above-mentioned wireless communication method, a computer program product, and a computer-readable storage medium on which the computer program code for implementing the above-mentioned wireless communication method is recorded.

[0011] The electronic device and method according to the embodiments of this application can reuse beam measurement results by matching two functional types of AI models used for beam prediction, and can further reduce the overhead of beam measurement.

[0012] The above and other advantages of this disclosure will become more apparent below by combining the drawings and describing in detail preferred embodiments of this disclosure. [Brief explanation of the drawing]

[0013] To further illustrate the above and other advantages and features of this disclosure, specific embodiments of this disclosure will be described in more detail below, with reference to the drawings. The drawings are incorporated herein and form part of this specification together with the following detailed description. Components having the same function and configuration are indicated by the same reference numerals. These drawings illustrate typical examples of this disclosure and should not be considered as limitations on the scope of this disclosure.

[0014] [Figure 1] This is a block diagram showing a functional module of an electronic device on the user equipment side for wireless communication according to one embodiment of the present application. [Figure 2] A schematic diagram of AI-based beam management is shown. [Figure 3] This diagram shows an example of the information flow between user equipment and a base station according to an embodiment of this application. [Figure 4] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 5] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 6] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 7] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 8] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 9] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 10] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 11] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 12] This is a block diagram showing a functional module of a base station-side electronic device for wireless communication according to another embodiment of the present application. [Figure 13] A schematic diagram of another example of the information flow between user equipment and a base station according to the embodiment of this application is shown. [Figure 14] A flowchart of a user device-side method for wireless communication according to one embodiment of this application is shown. [Figure 15] A flowchart of a base station-side method for wireless communication according to another embodiment of this application is shown. [Figure 16] This block diagram shows a first example of a schematic configuration of an eNB or gNB to which the technology described herein can be applied. [Figure 17] This block diagram shows a second example of a schematic configuration of an eNB or gNB to which the technology described herein can be applied. [Figure 18] It is a block diagram showing an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied. [Figure 19] It is a block diagram showing an example of a schematic configuration of a car navigation device to which the technology of the present disclosure can be applied. [Figure 20] It is a block diagram showing a schematic configuration of a general-purpose personal computer that can implement a method and / or apparatus and / or system according to an embodiment of the present disclosure.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, exemplary embodiments of the present disclosure will be described in conjunction with the drawings. For clarity and brevity, not all features of the actual embodiments are described in the specification. For example, it should be understood that in the process of developing such actual embodiments, decisions must be made to specify the embodiments so as to achieve the specific goals of the developer, which are subject to system and business constraints and these constraints may vary depending on the embodiments. Also, although the development work may be very complex and time-consuming, it should also be understood that for those skilled in the art who benefit from the present disclosure, such development work is only an everyday task.

[0016] Here, it should also be noted that in order to avoid obscuring the present disclosure with unnecessary details, only the device configurations and / or processing steps closely related to the solutions of the present disclosure are shown in the drawings, and other details that have little relation to the present disclosure are omitted.

[0017] <First Embodiment> As described above, there are many types of AI models used for beam prediction due to factors such as differences in the application environment, input / output set size, and input / output parameter properties. When both AI models using spatial domain beam prediction and AI models using time domain beam prediction are running, there may be overlapping parts in the inputs of the two AI models, and overlapping measurements result in unnecessary measurement overhead. In this embodiment, in order to reduce measurement overhead, a frame structure is provided that performs beam management by matching two functional types of AI models. The configuration and operation of the electronic equipment that realizes this frame structure will be described in detail below with reference to the drawings.

[0018] Figure 1 is a block diagram showing the functional module of the user device-side electronic equipment 100 for wireless communication according to this embodiment. As shown in Figure 1, the electronic equipment 100 includes a matching unit 101 configured to match a first AI model for performing spatial-domain beam prediction with a second AI model for performing time-domain beam prediction, and a reuse unit 102 configured to reuse beam measurement results between the first AI model and the second AI model if the matching is successful.

[0019] The matching unit 101 and the reuse unit 102 may be implemented by one or more processing circuits, and these processing circuits may be implemented, for example, as a chip or processor. Furthermore, each functional unit in the electronic device shown in Figure 1 is merely a logic module partitioned based on the specific function it implements, and should be understood as not limiting the specific implementation form. Here, "first" and "second" are used only for distinction and do not indicate any order or priority.

[0020] The electronic device 100 may be located, for example, on the user equipment (UE) side, and the UE may be various wireless communication terminals or communication terminals such as mobile base stations. The electronic device 100 may be implemented at the chip level or at the device level. For example, the electronic device 100 may operate as the UE itself and may further include external devices such as memory and transceivers (not shown). The memory is used to store programs executed by the UE to realize various functions and related data information. The transceiver may include one or more communication interfaces to support communication between different devices (e.g., other UEs, base stations, core networks, etc.), but the implementation of the transceiver is not specifically limited here.

[0021] To facilitate understanding, Figure 2 shows a schematic diagram of AI-based beam management. Figure 2 shows both spatial-domain beam prediction and time-domain beam prediction. The numbers 1 to 6 in Figure 2 represent different beams, and Nn, N-n+1, ​​..., N+1 represent different time points. Note that the quantities represented by these numbers and letters are approximate and not limited. In spatial-domain beam prediction, a set of measurement beams, such as beam {1, 3, 6}, is measured in each measurement cycle, and the beam information obtained from the measurements is input into a pre-trained AI model for spatial-domain beam prediction (i.e., the first AI model, hereinafter also called AI-S) to predict the beam information for beams 2, 4, and 5. In time-domain beam prediction, beam information acquired at multiple historical time points (e.g., Nn, N-n+1, ​​..., N, etc.) is collected as input to a pre-trained AI model for time-domain beam prediction (i.e., the second AI model, hereinafter also called AI-T) to predict the beam information at time point N+1.

[0022] For example, matching is successful if the input beamset for the first AI model includes the input beamset for the second AI model, and the input parameter properties of the first AI model include the input parameter properties of the second AI model. The input beamset indicates which beam measurements the AI ​​model requires as input. The input parameter properties indicate the content nature of the input to the AI ​​model and may include, for example, at least one of the following: reference signal received power (RSRP) and channel impulse response (CIR). Here, "included" can be understood as, for example, the latter being a subset of the former, or both being the same. For example, matching is successful if the input beamset for the first AI model includes beams 1-6, the beam input beamset for the second AI model includes beams 1, 3, and 5, and both input parameter properties are RSRP.

[0023] In other words, at least a portion of the beam measurement results of the first AI model can be used for predictions in the second AI model, thereby achieving matching. Specifically, the reused beam measurement results include at least a portion of the beam measurement results in the input beamset for the first AI model. If matching is successful, the inputs of the first AI can be saved during the operating cycle of the second AI, and predictions can be made using these saved inputs, eliminating the need for duplicate measurements. In this way, the results of a single measurement can be shared between the two AI models, reducing measurement overhead.

[0024] If a switch occurs between the first and / or second AI models after a successful match, the matching unit 101 is configured to re-execute the matching. This is because when an AI model is switched, its model parameters may change, and in this case, the conditions for a successful match may no longer be met.

[0025] In short, the electronic device 100 according to this embodiment can reuse beam measurement results between two functional types of AI models by matching two functional types of AI models for beam prediction, and further reduces the overhead of beam measurement.

[0026] The following describes in detail an embodiment in which the first AI model and the second AI model are placed in different locations, but it should be noted that this is not an exhaustive description. Furthermore, the features and operations in the various embodiments described herein can be combined with each other if they do not conflict, and such combinations are not necessarily explicitly indicated.

[0027] <Second Example> In this embodiment, both the first AI model and the second AI model are located on the UE side. The matching unit 101 is configured to perform matching based on the model parameters of the first AI model and the model parameters of the second AI model, and to determine whether the matching was successful or not. The model parameters of the first AI model include, for example, one or more of the input parameter size and input / output parameter properties. The input parameter size may indicate the number of beams to be measured, or it may indicate information about the beamset to be measured. The input / output parameter properties include, for example, at least one of the RSRP and CIR mentioned above. The model parameters of the second AI model include, for example, one or more of the input time window length and output time window length, input parameter size, input / output parameter properties, and the minimum number of measurements of the historical data to be used. The input time window length refers to the size of the time range of the measured beam information used for prediction, the output time window length refers to the size of the time range of the predicted beam information, the input parameter size refers to the number of measured beams in each measurement, or the information of the beamset to be measured in each measurement, the input / output parameter properties include, for example, at least one of the above RSRP and CIR, and the minimum number of historical data measurements used refers to the minimum number of historical data groups on which each prediction is based, i.e., the minimum number of measurements required within the input time window length.

[0028] As shown in the dotted box in Figure 1, the electronic device 100 further includes a communication unit 103. For example, the communication unit 103 is configured to send a message to a base station indicating whether the matching was successful or unsuccessful. The message may occupy, for example, one bit. If the matching is successful, for example, assigning a 1 to the bit notifies the base station, such as a gNB, that the AI ​​model currently performing beam management includes a first AI model and a second AI model of two functional types, and that the matching between the first AI model and the second AI model was successful. Conversely, if the matching fails, assigning a 0 to the bit notifies the base station that the matching failed. It should be understood that the correspondence between the value of one bit and its meaning is not limited and can be changed in reverse. Alternatively, the communication unit 103 may send an instruction message to the base station only if the matching is successful.

[0029] If matching is successful, the UE may treat the first AI model and the second AI model as a single unit, and the communication unit 103 may also notify the base station which AI model will be used for prediction by transmitting the model parameters or model index of the second AI to the base station. Here, the model parameters include one or more of the following, for example, the length of the input time window and the length of the output time window, the input parameter size, and the input / output parameter properties. Furthermore, once the base station and the UE have reached an agreement on all AI models, signaling overhead can be reduced by replacing the model parameters of each AI model with the model index. The above 1-bit instruction information, and the model parameters or model index herefor, can be transmitted via a control channel, and both may be included in the same signaling or transmitted using different signaling.

[0030] If matching fails, the matching unit 101 may be further configured to determine whether to use one of the first AI model and the second AI model, or to use a non-AI beam management mechanism without using an AI model. If it is decided to use one of the first AI model and the second AI model, the communication unit 103 is configured to transmit the model parameters or model index of the AI ​​model to be used to the base station. If it is decided to use a non-AI beam management mechanism, the communication unit 103 does not need to transmit instruction information to the base station. Similarly, the model parameters or model index may be transmitted via a control channel.

[0031] For ease of understanding, Figure 3 shows a schematic diagram of the information flow between the UE and gNB in ​​this embodiment. First, the UE matches the first AI model (AI-S) with the second AI model (AI-T). If the matching is successful, it sends a message to the gNB indicating that the matching was successful, and may also send the model parameters or model index of the second AI model to the gNB. Here, two arrows are shown to represent the signaling for transmission, but this does not mean that two signaling signals are required to transmit the instruction message and the model parameters or model index; it is also possible to transmit them with one signaling signal. This is just one example. Similar situations exist in various information flows that will be illustrated later. For example, one arrow does not necessarily represent one signaling signal.

[0032] The UE then performs AI-S and AI-T and reports the prediction results, or a portion thereof, to the gNB, for example, via a data channel. The UE can also report measurement results to the gNB as needed. Figure 3 primarily illustrates the case where matching is successful. If matching fails, as shown in the dotted box in Figure 3, the UE optionally sends a message to the gNB indicating that matching failed and either the AI-S or AI-T model parameters or model index to be used, or it does not send a message and uses a non-AI beam management mechanism.

[0033] After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0034] After successful matching, if the first AI model and / or the second AI model trigger the monitoring mechanism, the communication unit 103 is configured to acquire the execution cycle of the monitoring mechanism, and the matching unit 101 is configured to keep unmonitored AI models silent during the execution cycle. When monitoring is performed on the UE side, the communication unit 103 can locally acquire information on the execution cycle, and when monitoring is performed on the base station side, the communication unit 103 can acquire information on the execution cycle through specific signaling or calculate the parameter values ​​of the execution cycle.

[0035] Furthermore, if matching is re-executed after a successful match by switching between the first AI model and / or the second AI model, and the matching fails, the communication unit 103 must notify the gNB of a message indicating that the matching failed.

[0036] <Third Example> In this embodiment, the first AI model is located on either the UE side or the base station side, and the second AI model is located on the other side. The matching unit 101 is configured to perform matching by interacting with the base station via the communication unit 103. The matching is initiated by the UE.

[0037] For example, the matching unit 101 determines the AI ​​model to be used on the UE side, and the communication unit 103 sends a matching request to the base station, causing the base station to determine the AI ​​model to be used on the base station side based on the matching request, and can receive a message from the base station indicating whether the matching was successful or unsuccessful. Based on this message, the matching unit 101 determines whether the matching was successful or unsuccessful. The matching request may include model parameters or model indices of the AI ​​model to be used on the UE side.

[0038] If matching is successful, the communication unit 103 is further configured to receive model parameters or model indexes of the AI ​​model used by the base station from the base station. After successful matching, the reuse unit 102 reuses the beam measurement results between the first AI model and the second AI model via the communication unit 103. After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0039] On the other hand, if matching fails, the communication unit 103 may be further configured to send a message to the base station indicating whether to select the first AI model or the second AI model. Alternatively, the communication unit 103 may not send a message and use a non-AI beam management mechanism, or it may send a message to the base station indicating that a non-AI beam management mechanism is being used.

[0040] In the first example, the first AI model is located on the UE side, and the second AI model is located on the base station side. In this case, the matching request may include the model parameters of the first AI model used on the UE side, for example, the input parameter size and input / output parameter properties of the first AI model, or it may include the model index of the first AI model. After receiving the matching request, the base station can select the best second AI model that satisfies the requirements. If such a second AI model can be found, the base station sends a message to the UE indicating that the matching was successful, for example, a 1-bit message, and sends the model parameters or model index of the selected second AI model to the UE. The model parameters of the second AI model received from the base station may include, for example, at least the length of the input time window and the length of the output time window, and the minimum number of measurements of the historical data used. Based on this minimum number of measurements, the UE can determine how many times to schedule the first AI model to run.

[0041] If matching fails, and the UE selects a first AI model, the message sent from the communication unit 103 to the base station includes the model parameters or model index of the selected first AI model. If the UE selects a second AI model, the message sent from the communication unit 103 to the base station includes one bit of notification information informing the base station to perform beam prediction using the second AI model.

[0042] For ease of understanding, Figures 4 and 5 show schematic diagrams of the information flow between the UE and gNB in ​​the first example. Note that Figure 4 shows the case where matching is successful, and Figure 5 shows the case where matching is unsuccessful. The UE initiates matching by first determining the first AI model to use, i.e., AI-S, and then sending a matching request to the gNB, which may include the model parameters or model index of AI-S. After receiving the matching request, the gNB selects the best AI-T to match AI-S, and determines that matching is successful if it can find such an AI-T. The gNB sends an instruction message to the UE indicating that matching was successful, along with the model parameters or model index of AI-T. Subsequently, after successful matching, the UE runs AI-S and reports the AI-S prediction results and beam measurement results to the gNB, for example, via a data channel. The gNB stores the measurement results reported by the UE within the length of the input time window as input to AI-T and runs AI-T to instruct the UE on the optimal beam. Furthermore, the UE's communication unit 103 can report the beam measurement results within the length of the AI-T's input time window to the base station once or multiple times, thereby allowing the AI-T to perform beam prediction using these beam measurement results.

[0043] Referring to Figure 5, if matching fails, the gNB sends an instruction message to the UE indicating that matching failed. The UE then selects either AI-S or AI-T. If AI-S is selected, it sends the AI-S model parameters or model index to the gNB. If AI-T is selected, it sends a 1-bit notification to the gNB.

[0044] In the second example, the second AI model is located on the UE side, and the first AI model is located on the base station side. In this case, the matching request may include the model parameters of the second AI model used on the UE side, such as the input time window length and output time window length of the second AI model, the input parameter size, and input / output parameter properties, or it may include the model index of the second AI model. After receiving the matching request, the base station can select the best first AI model that satisfies the requirements. If such a first AI model can be found, the base station sends a message to the UE indicating that the matching was successful, for example, a 1-bit message. Also, if the input of the first AI model requires further augmentation information, for example, if the input parameter size of the first AI model is larger than that of the second AI model, the base station must also send this information to the UE. For example, the base station can send the model parameters or model index of the selected first AI model to the UE. The model parameters of the first AI model received from the base station include, for example, the input parameter size of the first AI model.

[0045] If matching fails, and the UE selects a second AI model, the message sent from the communication unit 103 to the base station includes the model parameters or model index of the selected second AI model. If the UE selects a first AI model, the message sent from the communication unit 103 to the base station includes one bit of notification information instructing the base station to perform beam prediction using the first AI model.

[0046] For ease of understanding, Figures 6 and 7 show schematic diagrams of the information flow between the UE and gNB in ​​the second example. Note that Figure 6 shows the case where matching is successful, and Figure 7 shows the case where matching is unsuccessful. The UE initiates matching by first determining the second AI model to use, i.e., AI-T, and then sending a matching request to the gNB, which may include the model parameters or model index of AI-T. After receiving the matching request, the gNB selects the best AI-S to match AI-T, and determines that matching is successful if it can find such an AI-S. The gNB sends an instruction message to the UE indicating that matching was successful, and also sends the model parameters of AI-S, such as the input parameter size and model index, if the input parameter size of AI-S is larger. After successful matching, the UE can then report the beam measurement results to the gNB, for example, via a data channel, and the gNB uses these beam measurement results to run AI-S and instructs the UE on the optimal beam. The UE (User Environment) holds the measurement results within the input time window as input for AI-T, which is then used to run AI-T and report the AI-T prediction results to gNB (Ground Neural Network).

[0047] Referring to Figure 7, if matching fails, the gNB sends an instruction message to the UE indicating that matching failed. The UE then selects either AI-S or AI-T. If AI-T is selected, it sends the AI-T model parameters or model index to the gNB. If AI-S is selected, it sends a 1-bit notification message to the gNB.

[0048] Furthermore, after successful matching, if the first AI model and the second AI model trigger the monitoring mechanism, when the monitoring mechanism is executed by the UE, the communication unit 103 provides the base station with the execution cycle of the monitoring mechanism, and when the monitoring mechanism is executed by the base station, the communication unit 103 obtains the execution cycle of the monitoring mechanism from the base station. In addition, if the base station's AI model triggers the monitoring mechanism, the matching unit 101 is configured to keep the UE's AI model silent during the execution cycle.

[0049] Similarly, if a switch occurs between the first and / or second AI models after successful matching, the matching operation described above must be re-executed between the UE and the base station.

[0050] <Fourth Example> In this embodiment, similar to the third embodiment, the first AI model is located on either the UE side or the base station side, and the second AI model is located on the other side. The matching unit 101 is configured to perform matching by interacting with the base station via the communication unit 103. Unlike the third embodiment, the matching is initiated by the base station.

[0051] For example, the base station determines the AI ​​model to be used for matching and sends the model parameters or model index of the determined AI model to the UE in a matching request. The UE's communication unit 103 is configured to receive this matching request from the base station. The matching unit 101 is configured to determine the AI ​​model that the UE will use for matching based on the received matching request, and the communication unit 103 is configured to send a message to the base station indicating whether the matching was successful or unsuccessful.

[0052] If matching is successful, the communication unit 103 is further configured to transmit the model parameters or model index of the AI ​​model on the UE side to the base station. After successful matching, the reuse unit 102 reuses the beam measurement results between the first AI model and the second AI model via the communication unit 103. After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0053] On the other hand, if matching fails, the communication unit 103 may be further configured to receive a message from the base station indicating whether to select the first AI model or the second AI model. Alternatively, the communication unit 103 may not receive a message and use a non-AI beam management mechanism, or it may receive a message from the base station indicating that it will use a non-AI beam management mechanism.

[0054] In the first example, the first AI model is located on the UE side, and the second AI model is located on the base station side. In this case, the matching request may include one or more of the model parameters of the second AI model used on the base station side, such as the length of the input time window and the length of the output time window, the input parameter size, the input / output parameter properties, and the minimum number of measurements of historical data used, or it may include the model index of the second AI model. After receiving the matching request, the UE can select the best first AI model that satisfies the requirements. If such a first AI model can be found, the communication unit 103 sends a message to the base station indicating that the matching was successful, for example, a 1-bit message, and also sends the model parameters of the first AI model, for example, the input parameter size and the model index, if the input parameter size of the first AI model is larger.

[0055] If matching fails, and the base station selects a first AI model, the message received by the communication unit 103 from the base station includes one bit of notification information instructing the UE to perform beam prediction using the first AI model. If the base station selects a second AI model, the message received by the communication unit 103 from the base station includes the model parameters or model index of the selected second AI model.

[0056] For ease of understanding, Figures 8 and 9 show schematic diagrams of the information flow between the UE and gNB in ​​the first example. Note that Figure 8 shows the case where matching is successful, and Figure 9 shows the case where matching is unsuccessful. The gNB initiates matching, first determining the second AI model to use, i.e., AI-T, and then sending a matching request to the UE. This matching request may include the model parameters or model index of AI-T. After receiving the matching request, the UE selects the best AI-S to match AI-T, and if such an AI-S can be found, it determines that the matching was successful. The UE sends an instruction message to the gNB indicating that the matching was successful, and also sends the model parameters of the AI-S, such as the input parameter size and model index, if the input parameter size of the AI-S is larger. Subsequently, after successful matching, the UE runs the AI-S and reports the AI-S prediction results and beam measurement results to the gNB, for example, via a data channel. The gNB stores the measurement results reported by the UE within the length of the input time window as input to the AI-T, and runs the AI-T to instruct the UE on the optimal beam. The communication unit 103 on the UE side can report the beam measurement results within the length of the AI-T input time window to the base station once or multiple times, allowing the AI-T to perform beam prediction using these beam measurement results.

[0057] Referring to Figure 9, if matching fails, the UE sends an instruction message to the gNB indicating that matching failed. The gNB then selects either AI-S or AI-T. If AI-T is selected, it sends the AI-T model parameters or model index to the UE. If AI-S is selected, it sends a 1-bit notification to the UE.

[0058] In the second example, the second AI model is located on the UE side, and the first AI model is located on the base station side. In this case, the matching request may include the model parameters of the first AI model used on the base station side, for example, the input parameter size and input / output parameter properties of the first AI model, or it may include the model index of the first AI model. After receiving the matching request, the UE can select the best second AI model that satisfies the requirements. If such a second AI model can be found, the communication unit 103 sends a message to the base station indicating that the matching was successful, for example, a 1-bit message. The communication unit 103 also needs to send the model parameters or model index of the selected second AI model to the base station. The model parameters of the second AI model may include, for example, at least the input time window length and the output time window length.

[0059] If matching fails, and the base station selects a first AI model, the message received by the communication unit 103 from the base station includes the model parameters or model index of the selected first AI model. If the base station selects a second AI model, the message received by the communication unit 103 from the base station includes one bit of notification information informing the UE to perform beam prediction using the second AI model.

[0060] For ease of understanding, Figures 10 and 11 show schematic diagrams of the information flow between the UE and gNB in ​​the second example. Figure 10 shows the case where matching is successful, and Figure 11 shows the case where matching fails. The gNB initiates matching, first determining the first AI model to use, i.e., AI-S, and then sending a matching request to the UE. This matching request may include the model parameters or model index of AI-S. After receiving the matching request, the UE selects the best AI-T to match AI-S, and if it can find such an AI-T, it determines that the matching is successful. The UE sends an instruction message to the gNB indicating that the matching was successful, along with the model parameters or model index of AI-T. Subsequently, after successful matching, the UE reports the beam measurement results to the gNB, for example, via a data channel, and the gNB uses these beam measurement results to run AI-S and instructs the UE on the optimal beam. On the UE side, the measurement results within the length of the input time window are saved as input to AI-T, which is then used to run AI-T and report the AI-T prediction results to gNB.

[0061] Referring to Figure 11, if matching fails, the UE sends an instruction message to the gNB indicating that matching failed. The gNB then selects either AI-S or AI-T. If AI-S is selected, it sends the AI-S model parameters or model index to the UE. If AI-T is selected, it sends a 1-bit notification to the UE.

[0062] Furthermore, after successful matching, if the first AI model and the second AI model trigger the monitoring mechanism, when the monitoring mechanism is executed by the UE, the communication unit 103 provides the base station with the execution cycle of the monitoring mechanism, and when the monitoring mechanism is executed by the base station, the communication unit 103 obtains the execution cycle of the monitoring mechanism from the base station. In addition, if the base station's AI model triggers the monitoring mechanism, the matching unit 101 is configured to keep the UE's AI model silent during the execution cycle.

[0063] Similarly, if a switch occurs between the first and / or second AI models after successful matching, the matching operation described above must be re-executed between the UE and the base station.

[0064] <Fifth Example> From the above description of the matching frame structure based on the AI ​​model, it can be said that according to the embodiment of the present application, a base station-side electronic device 200 for wireless communication is further provided. As shown in Figure 12, the electronic device 200 includes a matching unit 201 configured to match a first AI model for performing spatial domain beam prediction with a second AI model for performing time domain beam prediction, and a reuse unit 202 configured to reuse beam measurement results between the first AI model and the second AI model if the matching is successful.

[0065] The matching unit 201 and the reuse unit 202 may be implemented by one or more processing circuits, and these processing circuits may be implemented, for example, as a chip or processor. Furthermore, each functional unit in the electronic device shown in Figure 12 is merely a logic module partitioned based on the specific function it implements, and should be understood as not limiting the specific implementation form. Here, "first" and "second" are used only for distinction and do not indicate any order or priority.

[0066] The electronic equipment 200 can be located on the base station side or the wireless transceiver node side. The electronic equipment 200 may be implemented at the chip level or at the device level. For example, the management electronic equipment 200 may operate as the base station itself and may further include external devices such as memory and transceivers (not shown). The memory is used to store programs executed by the base station to perform various functions and related data information. The transceiver may include one or more communication interfaces to support communication between different devices (e.g., other base stations, UEs, etc.), but the implementation of the transceiver is not specifically limited here.

[0067] The AI-based beam management described above with reference to Figure 2 in the first embodiment is also applicable to this embodiment. Furthermore, the model parameters, definitions of model parameters, matching rules, and signaling flows compatible with this embodiment, as described in the first to fourth embodiments, are also applicable to this embodiment and subsequent embodiments, and will be simplified or omitted as appropriate in the following description.

[0068] For example, matching is successful if the input beamset for the first AI model includes the input beamset for the second AI model, and the input parameter properties of the first AI model include the input parameter properties of the second AI model. The input beamset indicates which beam measurements the AI ​​model requires as input. The input parameter properties indicate the nature of the content of the AI ​​model's input and can include, for example, at least one of RSRP and CIR. Here, "included" can be understood, for example, as the latter being a subset of the former.

[0069] In other words, at least a portion of the beam measurement results from the first AI model can be used in the predictions of the second AI model, thereby achieving matching. In this way, it is possible to share a single measurement result between the two AI models, reducing measurement overhead.

[0070] If a switch occurs between the first and / or second AI models after a successful match, the matching unit 101 is configured to re-execute the matching. This is because when an AI model is switched, its model parameters may change, and in this case, the conditions for a successful match may no longer be met.

[0071] In short, the electronic device 200 according to this embodiment can reuse beam measurement results between two functional types of AI models by matching two functional types of AI models for beam prediction, and further reduces the overhead of beam measurement.

[0072] The following describes an implementation in which the first AI model and the second AI model are deployed in different locations, from the perspective of base stations, but please note that this is not an exhaustive example.

[0073] <Sixth Example> In this embodiment, both the first AI model and the second AI model are located on the base station side. The matching unit 201 is configured to perform matching based on the model parameters of the first AI model and the model parameters of the second AI model, and to determine whether the matching is successful or not. The model parameters of the first AI model include, for example, one or more of the input parameter size and input / output parameter properties. The model parameters of the second AI model include, for example, one or more of the input time window length and output time window length, input parameter size, input / output parameter properties, and the minimum number of measurements of the historical data used.

[0074] As shown in the dotted box in Figure 12, the electronic equipment 200 further includes a communication unit 203. For example, if matching is successful, the communication unit 203 is configured to transmit the input time window length (T1) and output time window length (T2) of the second AI model to the UE. The UE measures the beam within the input time window length and reports the measurement results, and the base station stores the beam measurement results within the input time window length as input to the second AI model.

[0075] To facilitate understanding, Figure 13 shows a schematic diagram of the information flow between the UE and gNB in ​​this embodiment. First, the gNB matches the first AI model (AI-S) and the second AI model (AI-T). If the matching is successful, it transmits T1 and T2 of the second AI model to the UE. After the matching is successful, the UE transmits the beam measurement results in T1 to the gNB, for example, via a data channel.

[0076] In the example above, the base station does not send an instruction message to the UE indicating whether the matching was successful or not. However, this is not limited to this case, and the base station can also send this instruction message to the UE.

[0077] After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0078] After successful matching, if the first AI model and / or the second AI model trigger the monitoring mechanism, when the monitoring mechanism is executed by the base station, the communication unit 203 is configured to provide the execution cycle of the monitoring mechanism to the UE, and when the monitoring mechanism is executed by the UE, the communication unit 203 is configured to obtain the execution cycle of the monitoring mechanism from the UE. The matching unit 201 is configured to keep unmonitored AI models silent during the execution cycle.

[0079] <Seventh Example> In this embodiment, the first AI model is located on either the UE side or the base station side, and the second AI model is located on the other side. The matching unit 201 is configured to perform matching by interacting with the UE via the communication unit 203. The matching is initiated by the UE.

[0080] For example, the UE determines the AI ​​model to be used on the UE side and sends a matching request to the base station. This matching request includes the model parameters or model index of the AI ​​model to be used on the UE side. The communication unit 203 receives the matching request from the UE, and the matching unit 201 determines the AI ​​model to be used on the base station side based on this matching request. The communication unit 203 sends a message to the UE indicating whether the matching was successful or unsuccessful.

[0081] If matching is successful, the communication unit 203 is further configured to transmit the model parameters or model index of the AI ​​model used on the base station side to the UE. After successful matching, the reuse unit 202 reuses the beam measurement results between the first AI model and the second AI model via the communication unit 203. After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0082] On the other hand, if matching fails, the communication unit 203 may be further configured to receive a message from the UE indicating whether to select the first AI model or the second AI model. Alternatively, the communication unit 203 may not receive a message and use a non-AI beam management mechanism, or it may receive a message from the UE indicating that a non-AI beam management mechanism will be used.

[0083] In the first example, the first AI model is located on the UE side, and the second AI model is located on the base station side. In this case, the matching request may include the model parameters of the first AI model used on the UE side, for example, the input parameter size and input / output parameter properties of the first AI model, or it may include the model index of the first AI model. After receiving the matching request, the base station can select the best second AI model that satisfies the requirements. If such a second AI model can be found, the communication unit 203 on the base station side sends a message to the UE indicating that the matching was successful, for example, a 1-bit message, and sends the model parameters or model index of the selected second AI model to the UE. The model parameters of the second AI model sent may include, for example, at least the length of the input time window and the length of the output time window, and the minimum number of measurements of the historical data to be used. Based on this minimum number of measurements, the UE side can determine the number of times to schedule the first AI model.

[0084] If matching fails, and the UE selects a first AI model, the message received by the communication unit 203 includes the model parameters or model index of the selected first AI model. If the UE selects a second AI model, the message received by the communication unit 203 includes one bit of notification information informing the base station to perform beam prediction using the second AI model.

[0085] After successful matching, the UE performs spatial domain beam prediction using the first AI model, and the communication unit 203 is further configured to cause the second AI model to perform beam prediction using these beam measurement results by receiving beam measurement results from the UE one or more times within the length of the input time window of the second AI model. The communication unit 203 can receive beam measurement results and prediction results from the first AI model via a data channel.

[0086] A schematic diagram of the information flow example between the UE and gNB in ​​the first example can be found in Figures 4 and 5, so it will not be repeated here.

[0087] In the second example, the second AI model is located on the UE side, and the first AI model is located on the base station side. In this case, the matching request may include the model parameters of the second AI model used on the UE side, such as the input time window length and output time window length of the second AI model, the input parameter size, and input / output parameter properties, or it may include the model index of the second AI model. After receiving the matching request, the base station can select the best first AI model that satisfies the requirements. If such a first AI model can be found, the communication unit 203 on the base station side sends a message to the UE indicating that the matching was successful, for example, a 1-bit message. Furthermore, if the input of the first AI model requires further augmentation information, for example, if the input parameter size of the first AI model is larger than the input parameter size of the second AI model, the communication unit 203 must also send this information to the UE. For example, the communication unit 203 can send the model parameters or model index of the first AI model used on the base station side to the UE. The model parameters of the first AI model include, for example, the input parameter size of the first AI model.

[0088] If matching fails, and the UE selects a second AI model, the message received by the communication unit 203 from the UE includes the model parameters or model index of the selected second AI model. If the UE selects a first AI model, the message received by the communication unit 103 from the UE includes one bit of notification information informing the base station to perform beam prediction using the first AI model.

[0089] A schematic diagram of the information flow example between the UE and gNB in ​​the second example can be found in Figures 6 and 7, so it will not be repeated here.

[0090] Furthermore, after successful matching, if the first AI model and the second AI model trigger the monitoring mechanism, when the monitoring mechanism is executed by the UE, the communication unit 203 obtains the execution cycle of the monitoring mechanism from the UE, and when the monitoring mechanism is executed by the base station, the communication unit 203 provides the execution cycle of the monitoring mechanism to the UE. In addition, if the AI ​​model on the UE side triggers the monitoring mechanism, the matching unit 201 is configured to keep the AI ​​model on the base station side silent during the execution cycle.

[0091] Similarly, if a switch occurs between the first and / or second AI models after successful matching, the matching operation described above must be re-executed between the UE and the base station.

[0092] <Eighth Example> In this embodiment, similar to the seventh embodiment, the first AI model is located on either the UE side or the base station side, and the second AI model is located on the other side. The matching unit 201 is configured to perform matching by interacting with the UE via the communication unit 203. Unlike the seventh embodiment, the matching is initiated by the base station.

[0093] For example, the base station determines the AI ​​model to be used for matching, the communication unit 203 includes the model parameters or model index of the determined AI model in the matching request and sends it to the UE, and the UE determines the AI ​​model to be used on the UE side based on these model parameters or model index. The communication unit 203 is further configured to receive a message from the UE indicating whether the matching was successful or unsuccessful.

[0094] If matching is successful, the communication unit 203 is further configured to receive model parameters or model indexes of the AI ​​model on the UE side from the UE. After successful matching, the reuse unit 202 reuses the beam measurement results between the first AI model and the second AI model via the communication unit 203. After successful matching, the first AI model can be kept silent within the output time window of the second AI model.

[0095] On the other hand, if matching fails, the communication unit 203 is further configured to send a message to the UE indicating whether to select the first AI model or the second AI model. Alternatively, the communication unit 203 may not send a message and use a non-AI beam management mechanism, or it may send a message to the UE indicating that a non-AI beam management mechanism is being used.

[0096] In the first example, the first AI model is located on the UE side, and the second AI model is located on the base station side. In this case, the matching request may include one or more of the model parameters of the second AI model used on the base station side, such as the length of the input time window and the length of the output time window, the input parameter size, the input / output parameter properties, and the minimum number of historical data measurements used, or it may include the model index of the second AI model. After receiving the matching request, the UE can select the best first AI model that satisfies the requirements. If such a first AI model can be found, the UE sends a message to the base station indicating that the matching was successful, for example, a 1-bit message. In response, the communication unit 203 receives a message from the UE indicating that the matching was successful. Also, if the input parameter size of the first AI model is larger, the communication unit 203 also receives the model parameters of the first AI model from the UE, for example, the input parameter size and the model index.

[0097] If matching fails, and the base station selects a first AI model, the message sent from the communication unit 203 to the UE includes one bit of notification information instructing the UE to perform beam prediction using the first AI model. If the base station selects a second AI model, the message sent from the communication unit 203 to the UE includes the model parameters or model index of the selected second AI model.

[0098] After successful matching, the UE performs spatial domain beam prediction using the first AI model, and the communication unit 203 is further configured to cause the second AI model to perform beam prediction using these beam measurement results by receiving beam measurement results from the UE one or more times within the length of the input time window of the second AI model. The communication unit 203 can receive beam measurement results and prediction results from the first AI model via a data channel.

[0099] A schematic diagram of the information flow example between the UE and gNB in ​​the first example can be found in Figures 8 and 9, so it will not be repeated here.

[0100] In the second example, the second AI model is located on the UE side, and the first AI model is located on the base station side. In this case, the matching request may include the model parameters of the first AI model used on the base station side, for example, the input parameter size and input / output parameter properties of the first AI model, or it may include the model index of the first AI model. After receiving the matching request, the UE can select the best second AI model that satisfies the requirements. If such a second AI model can be found, the UE sends a message to the base station indicating that the matching was successful, for example, a 1-bit message. In response, the communication unit 203 receives a message from the UE indicating that the matching was successful. The communication unit 203 also receives from the UE the model parameters or model index of the second AI model selected by the UE. The model parameters of the second AI model may include, for example, at least the length of the input time window and the length of the output time window.

[0101] If matching fails, and the base station selects a first AI model, the message sent from the communication unit 203 to the UE includes the model parameters or model index of the selected first AI model. If the base station selects a second AI model, the message sent from the communication unit 203 to the UE includes one bit of notification information informing the UE to perform beam prediction using the second AI model.

[0102] A schematic diagram of the information flow example between the UE and gNB in ​​the second example can be found in Figures 10 and 11, so it will not be repeated here.

[0103] Furthermore, in this embodiment, after successful matching, if the first AI model and the second AI model trigger the monitoring mechanism, when the monitoring mechanism is executed by the UE, the communication unit 203 obtains the execution cycle of the monitoring mechanism from the UE, and when the monitoring mechanism is executed by the base station, the communication unit 203 provides the execution cycle of the monitoring mechanism to the UE. In addition, if the AI ​​model on the UE side triggers the monitoring mechanism, the matching unit 201 is configured to keep the AI ​​model on the base station side silent during the execution cycle.

[0104] Similarly, if a switch occurs between the first and / or second AI models after successful matching, the matching operation described above must be re-executed between the UE and the base station.

[0105] <Ninth Example> In describing the electronic devices for wireless communication in the embodiments described above, several processes or methods have obviously been disclosed. The following outlines these methods without repeating some of the details already discussed in the preamble. While these methods were disclosed in the process of describing the electronic devices for wireless communication, they do not necessarily utilize or be implemented by the components described. For example, embodiments of electronic devices for wireless communication may be implemented partially or entirely by hardware and / or firmware, while the following methods for wireless communication may be implemented entirely by computer-executable programs. Of course, these methods may also utilize the hardware and / or firmware of the electronic devices for wireless communication.

[0106] Figure 14 shows a flowchart of a user equipment-side method for wireless communication according to one embodiment of the present invention. This method includes matching a first AI model for performing spatial-domain beam prediction with a second AI model for performing time-domain beam prediction (S11), and, if the matching is successful, reusing the beam measurement results between the first AI model and the second AI model (S12). This method can be performed, for example, on the UE side.

[0107] For example, matching is successful if the input beamset for the first AI model includes the input beamset for the second AI model, and the input parameter properties of the first AI model include the input parameter properties of the second AI model. The input parameter properties include at least one of the reference signal received power and the channel impulse response. The reused beam measurement results include, for example, at least a portion of the beam measurement results in the input beamset for the first AI model.

[0108] If a switch occurs between the first and / or second AI models after a successful match, the matching process will be rerun.

[0109] Depending on the placement of the first and second AI models and the initiator of the matching process, there are four scenarios. In the first scenario, both the first and second AI models are placed on the UE side. In the second scenario, the first AI model is placed on either the UE side or the base station side, and the second AI model is placed on the other side, and the matching is initiated by the UE. In the third scenario, the first AI model is placed on either the UE side or the base station side, and the second AI model is placed on the other side, and the matching is initiated by the base station. In the fourth scenario, both the first and second AI models are placed on the base station side.

[0110] In the first scenario, step S11 performs matching based on the model parameters of the first AI model and the model parameters of the second AI model to determine whether the matching was successful or not. Although not shown, the method further includes sending a message to the base station indicating whether the matching was successful or unsuccessful. If the matching is successful, the method further includes sending the model parameters or model index of the second AI model to the base station. The transmitted model parameters of the second AI model include one or more of the input time window length and output time window length of the second AI model, the input parameter size, and input / output parameter properties. If the matching fails, the method further includes deciding to use one of the first and second AI models and sending the model parameters or model index of the AI ​​model to be used to the base station.

[0111] If, after successful matching, the first AI model and / or the second AI model trigger the monitoring mechanism, this method further includes obtaining the execution cycle of the monitoring mechanism and keeping the unmonitored AI models silent during the execution cycle.

[0112] The method described above in the first scenario corresponds to the electronic device 100 in the second embodiment. Relevant specific details are not repeated here, as they can be found in the second embodiment.

[0113] In the second scenario, matching is performed in step S11 by interacting with the base station. For example, step S11 includes determining the AI ​​model to be used on the UE side, sending a matching request to the base station to cause the base station to determine a second AI model to be used on the base station side based on the matching request, and receiving a message from the base station indicating whether the matching was successful or unsuccessful, and determining whether the matching was successful or unsuccessful based on this message.

[0114] The matching request includes, for example, the model parameters of the AI ​​model used on the UE side. If the first AI model is located on the UE side, the matching request includes the input parameter size and input / output parameter properties of the first AI model. If the second AI model is located on the UE side, the matching request may include the input time window length and output time window length, input parameter size, and input / output parameter properties of the second AI model. Alternatively, the matching request may further include the model index of the AI ​​model used on the UE side.

[0115] If matching is successful, the method further includes receiving the model parameters of the AI ​​model used by the base station from the base station. If the first AI model is located on the base station side, the received model parameters include the input parameter size of the first AI model. If the second AI model is located on the base station side, the received model parameters include at least the length of the input time window and the length of the output time window, and the minimum number of historical data measurements used. Alternatively, the model index of the AI ​​model used by the base station may also be received from the base station.

[0116] If matching fails, the method further includes sending a message to the base station indicating whether to select a first artificial intelligence model or a second artificial intelligence model. If the first AI model is located on the UE side, and the first AI model is selected, the message includes model parameters or model index of the selected first AI model; if the second AI model is selected, the message includes 1 bit of notification information. If the second AI model is located on the UE side, and the second AI model is selected, the message includes model parameters or model index of the selected second AI model; if the first AI model is selected, the message includes 1 bit of notification information.

[0117] The method described above in the second scenario corresponds to the electronic device 100 in the third embodiment. Relevant specific details can be found in the third embodiment and are therefore not repeated here.

[0118] In the third scenario, step S11 includes, for example, receiving a matching request from a base station that includes model parameters or model indexes of an AI model to be used for matching determined by the base station; determining which AI model the UE will use for matching based on the received model parameters or model indexes; and sending a message to the base station indicating whether the matching was successful or unsuccessful.

[0119] If the first AI model is located on the UE side, the received model parameters include one or more of the model parameters of the second AI model, such as the input time window length and output time window length, input parameter size, input / output parameter properties, and the minimum number of historical data measurements used. If the second AI model is located on the UE side, the received model parameters include at least the input parameter size and input / output parameter properties of the first AI model.

[0120] If matching is successful, the method further includes transmitting the model parameters or model index of the AI ​​model determined to be used on the UE side to the base station. If the first AI model is located on the UE side, the input parameter size of the first AI model may be transmitted to the base station. If the second AI model is located on the UE side, the input time window length and output time window length of the second AI model may be transmitted to the base station.

[0121] If matching fails, the method further includes receiving a message from the base station indicating whether to select a first AI model or a second AI model. If the first AI model is located on the UE side and the first AI model is selected, the message includes one bit of notification information; if the first AI model is located on the UE side and the second AI model is selected, the message includes the model parameters or model index of the selected second AI model; if the second AI model is located on the UE side and the first AI model is selected, the message includes the model parameters or model index of the selected first AI model; and if the second AI model is located on the UE side and the second AI model is selected, the message includes one bit of notification information.

[0122] The method described above in the third scenario corresponds to the electronic device 100 in the fourth embodiment. Relevant specific details can be found in the fourth embodiment and are therefore not repeated here.

[0123] Furthermore, in the second and third scenarios, if the first AI model is located on the UE side and the second AI model is located on the base station side, after successful matching, the method further includes causing the second AI model to perform beam prediction using the beam measurement results by reporting the beam measurement results within the length of the input time window of the second AI model to the base station one or more times. For example, the beam measurement results and the prediction results of the first AI model can be reported via a data channel. After successful matching, if the first AI model and / or the second AI model trigger a monitoring mechanism, the method provides the base station with the execution cycle of the monitoring mechanism when the monitoring mechanism is executed by the UE, and obtains the execution cycle of the monitoring mechanism from the base station when the monitoring mechanism is executed by the base station. If the base station-side AI model triggers the monitoring mechanism, the method further includes keeping the UE-side AI model silent during the execution cycle.

[0124] Figure 15 shows a flowchart of a base station-side method for wireless communication according to another embodiment of the present invention. This method includes matching a first AI model for performing spatial-domain beam prediction with a second AI model for performing time-domain beam prediction (S21), and, if the matching is successful, reusing the beam measurement results between the first AI model and the second AI model (S22). This method can be performed, for example, on the base station side.

[0125] Similarly, matching is successful if, for example, the input beamset for the first AI model includes the input beamset for the second AI model, and the input parameter properties of the first AI model include the input parameter properties of the second AI model. The input parameter properties include at least one of the reference signal received power and the channel impulse response. The reused beam measurement results include, for example, at least a portion of the beam measurement results in the input beamset for the first AI model.

[0126] If a switch occurs between the first and / or second AI models after a successful match, the matching process is rerun. Further details can be found in the description of the fifth embodiment and will not be repeated here.

[0127] The method will be explained using the first to fourth scenarios defined above as examples.

[0128] In the fourth scenario, step S21 performs matching based on the model parameters of the first AI model and the model parameters of the second AI model to determine whether the matching was successful or not.

[0129] If matching is successful, the method further includes sending the input time window length and output time window length of the second AI model to the UE. After matching is successful, if the first AI model and / or the second AI model trigger a monitoring mechanism, the method provides the UE with the execution cycle of the monitoring mechanism when the monitoring mechanism is executed by the base station, and obtains the execution cycle of the monitoring mechanism from the UE when the monitoring mechanism is executed by the UE.

[0130] The method described above in the fourth scenario corresponds to the electronic device 200 in the sixth embodiment. Relevant specific details can be found in the sixth embodiment and are therefore not repeated here.

[0131] In the second scenario, step S21 performs matching by interacting with the UE. For example, step S21 includes receiving a matching request from the UE that includes the model parameters or model index of the AI ​​model to be used on the UE side, determining the AI ​​model to be used on the base station side based on this matching request, and sending a message to the UE indicating whether the matching was successful or unsuccessful.

[0132] If the first AI model is located on the UE side, the matching request may include the input parameter size and input / output parameter properties of the first AI model. If the second AI model is located on the UE side, the matching request may include the input time window length and output time window length, input parameter size, and input / output parameter properties of the second AI model.

[0133] If matching is successful, the method further includes sending the model parameters of the AI ​​model used on the base station side to the UE. If the first AI model is located on the base station side, the sent model parameters include the input parameter size of the first AI model. If the second AI model is located on the base station side, the sent model parameters include at least the length of the input time window and the length of the output time window, and the minimum number of historical data measurements used. Alternatively, the method may further include sending the model index of the AI ​​model used on the base station side to the UE.

[0134] If matching fails, the method further includes receiving a message from the UE indicating whether to select a first AI model or a second AI model. If the first AI model is located on the UE side and the first AI model is selected, the message includes the model parameters or model index of the selected first AI model; if the first AI model is located on the UE side and the second AI model is selected, the message includes one bit of notification information; if the second AI model is located on the UE side and the first AI model is selected, the message includes one bit of notification information; and if the second AI model is located on the UE side and the second AI model is selected, the message includes the model parameters or model index of the selected second AI model.

[0135] The method described above in the second scenario corresponds to the electronic device 200 in the seventh embodiment. Relevant specific details can be found in the seventh embodiment and are therefore not repeated here.

[0136] In the third scenario, step S21 performs matching by interacting with the UE. For example, step S21 may include the base station determining the AI ​​model to be used for matching, sending the model parameters or model index of the determined AI model to the UE in a matching request so that the UE can determine the AI ​​model to be used on the UE side based on the model parameters or model index, and receiving a message from the UE indicating whether the matching was successful or unsuccessful.

[0137] If the first AI model is located on the UE side, the transmitted model parameters include one or more of the second AI model's model parameters, such as the input time window length and output time window length, input parameter size, input / output parameter properties, and the minimum number of historical data measurements used. If the second AI model is located on the UE side, the transmitted model parameters include at least the input parameter size and input / output parameter properties of the first AI model.

[0138] If matching is successful, the method further includes receiving model parameters or model indices of the AI ​​model used by the UE from the UE. If the first AI model is located on the UE side, the received model parameters may include the input parameter size of the first AI model, and if the second AI model is located on the UE side, the received model parameters may include the input time window length and the output time window length of the second AI model.

[0139] If matching fails, the method further includes sending a message to the UE indicating whether to select a first AI model or a second AI model. If the first AI model is located on the UE side and the first AI model is selected, the message includes one bit of notification information; if the first AI model is located on the UE side and the second AI model is selected, the message includes the model parameters or model index of the selected second AI model; if the second AI model is located on the UE side and the first AI model is selected, the message includes the model parameters or model index of the selected first AI model; if the second AI model is located on the UE side and the second AI model is selected, the message includes one bit of notification information.

[0140] The method described above in the third scenario corresponds to the electronic device 200 in the eighth embodiment. Relevant specific details can be found in the eighth embodiment and are therefore not repeated here.

[0141] Furthermore, in the second and third scenarios, if the first AI model is located on the UE side and the second AI model is located on the base station side, after successful matching, the method further includes causing the second AI model to perform beam prediction using the beam measurement results by receiving beam measurement results from the UE one or more times within the length of the input time window of the second AI model. For example, the beam measurement results and the prediction results of the first AI model can be received via a data channel.

[0142] If, after successful matching, the first AI model and / or the second AI model trigger a monitoring mechanism, the method obtains the execution cycle of the monitoring mechanism from the UE when the monitoring mechanism is executed by the UE, and provides the execution cycle of the monitoring mechanism to the UE when the monitoring mechanism is executed by the base station. Furthermore, if the AI ​​model on the UE side triggers the monitoring mechanism, the method further includes keeping the AI ​​model on the base station side silent during the execution cycle.

[0143] The above methods may be used in combination or individually.

[0144] The technology described in this disclosure is applicable to a variety of products.

[0145] For example, the electronic device 100 may be implemented as various user devices. The user device may be implemented as a mobile terminal (e.g., a smartphone, tablet personal computer (PC), notebook PC, portable game console, portable / dongle mobile router, and digital imaging device) or an in-vehicle terminal (e.g., a car navigation system). The user device may further be implemented as a terminal that performs machine-to-machine (M2M) communication (also called a machine-type communication (MTC) terminal). Alternatively, the user device may be a wireless communication module (e.g., an integrated circuit module including a single chip) mounted on each of these terminals.

[0146] Electronic equipment 200 may be implemented as various types of base stations. A base station can be implemented as any type of eNBB (evolved Node B) or gNB (5G base station). eNBs include, for example, macro eNBs and small eNBs. Small eNBs may be eNBs that cover cells smaller than macrocells, such as pico eNBs, micro eNBs, and home (femto) eNBs. The same may be true for gNBs. Alternatively, a base station can be implemented as any other type of base station, such as a Node B or a base station transceiver (BTS). A base station may include an entity (also called a base station device) configured to control radio communication and one or more remote radio heads (RRHs) located separately from the entity. Also, various types of user equipment can operate as base stations by temporarily or semi-permanently performing base station functions.

[0147] (Application examples for base stations) (First application example) Figure 16 is a block diagram showing a first example of a schematic configuration of an eNB or gNB to which the technology described herein can be applied. The following description uses an eNB as an example, but is similarly applicable to a gNB. The eNB 800 has one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 may be connected to each other via an RF cable.

[0148] Each of the antennas 810 includes one or more antenna elements (for example, multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving radio signals by the base station equipment 820. The eNB800 may include multiple antennas 810, as shown in Figure 16. Multiple antennas 810 may be compatible with multiple frequency bands used by the eNB800, for example. Although Figure 16 shows an example in which the eNB800 includes multiple antennas 810, the eNB800 may also include a single antenna 810.

[0149] The base station device 820 includes a controller 821, a memory 822, a network interface 823, and a wireless communication interface 825.

[0150] The controller 821 may be, for example, a CPU or a DSP, and operates various functions of the upper layer of the base station equipment 820. For example, the controller 821 generates data packets from data in signals processed by the wireless communication interface 825 and forwards the generated packets via the network interface 823. The controller 821 can generate bundle packets by bundling data from multiple baseband processors and forward the generated bundle packets. The controller 821 may also have logical functions to perform controls such as radio resource control, radio bearer control, mobility management, admission control, or scheduling. Furthermore, these controls can be performed in cooperation with surrounding eNBs or core network nodes. The memory 822 includes RAM and ROM and stores programs executed by the controller 821, as well as various control data (e.g., terminal list, transmit power data, and scheduling data).

[0151] Network interface 823 is a communication interface for connecting base station equipment 820 to core network 824. Controller 821 can communicate with core network nodes or other eNBs via network interface 823. In this case, eNB 800 and the core network nodes or other eNBs are connected to each other by logical interfaces (e.g., S1 interface and X2 interface). Network interface 823 may be a wired communication interface or a wireless communication interface for a wireless backhaul line. If network interface 823 is a wireless communication interface, it can use a higher frequency band for wireless communication than the frequency band used by wireless communication interface 825.

[0152] The wireless communication interface 825 supports any cellular communication scheme (e.g., Long Term Evolution (LTE) and LTE-Advanced) and provides wireless connectivity to terminals located in the cells of the eNB800 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, for example, coding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and can perform signal processing of various layers (e.g., L1, Media Access Control (MAC), Radio Link Control (RLC), Packet Data Aggregation Protocol (PDCP)). The BB processor 826 may have some or all of the above logical functions instead of the controller 821. The BB processor 826 may be a memory that stores a communication control program, or it may be a module that includes a processor and associated circuitry configured to execute the program. Program updates can change the functionality of the BB processor 826. This module may be a card or blade inserted into a slot in the base station equipment 820. Alternatively, this module may be a chip mounted on a card or blade. At the same time, the RF circuit 827 may include, for example, a mixer, a filter, and an amplifier, and may transmit and receive radio signals via the antenna 810.

[0153] As shown in Figure 16, 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 eNB800. As shown in Figure 16, the wireless communication interface 825 may include multiple RF circuits 827. For example, multiple RF circuits 827 may be compatible with multiple antenna elements. Although Figure 16 shows 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 include a single BB processor 826 or a single RF circuit 827.

[0154] In the eNB800 shown in Figure 16, the communication unit 203 and transceiver of the electronic equipment 200 may be implemented by a wireless communication interface 825. At least some of the functions may be implemented by a controller 821. For example, the controller 821 matches two functional types of AI models used for beam prediction by performing the functions of the matching unit 201, the reuse unit 202, and the communication unit 203, thereby enabling the reuse of beam measurement results and further reducing the overhead of beam measurement.

[0155] (Second application example) Figure 17 is a block diagram showing a second example of a schematic configuration of an eNB or gNB to which the technology described herein can be applied. Similarly, although the following description uses an eNB as an example, it is also applicable to a gNB. The eNB 830 includes one or more antennas 840, a base station device 850, and an RRH 860. The RRH 860 and each antenna 840 may be connected to each other via an RF cable. The base station device 850 and the RRH 860 may also be connected to each other via a high-speed line such as an optical fiber cable.

[0156] Each of the antennas 840 includes one or more antenna elements (for example, multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving radio signals by the RRH860. The eNB830 may include multiple antennas 840, as shown in Figure 17. Multiple antennas 840 may be compatible with multiple frequency bands used by the eNB830, for example. Although Figure 17 shows an example in which the eNB830 includes multiple antennas 840, the eNB830 may also include a single antenna 840.

[0157] 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, memory 852, and network interface 853 are the same as the controller 821, memory 822, and network interface 823 described with reference to Figure 16.

[0158] The wireless communication interface 855 supports any cellular communication scheme (e.g., LTE and LTE-Advanced) and provides wireless connectivity to terminals located within the sector corresponding to the RRH860 via the RRH860 and antenna 840. The wireless communication interface 855 may typically include, for example, a BB processor 856. The BB processor 856 is similar to the BB processor 826 described with reference to Figure 16, except that it is connected to the RF circuit 864 of the RRH860 via a connection interface 857. The wireless communication interface 855 may include multiple BB processors 856, as shown in Figure 17. Multiple BB processors 856 may be compatible with multiple frequency bands used by, for example, the eNB830. Although Figure 17 shows an example in which the wireless communication interface 855 includes multiple BB processors 856, the wireless communication interface 855 may include a single BB processor 856.

[0159] The connection interface 857 is an interface for connecting the base station device 850 (wireless communication interface 855) to the RRH860. The connection interface 857 may also be a communication module for communication on the high-speed line described above for connecting the base station device 850 (wireless communication interface 855) to the RRH860.

[0160] The RRH860 includes a connection interface 861 and a wireless communication interface 863.

[0161] The connection interface 861 is an interface for connecting the RRH860 (wireless communication interface 863) to the base station device 850. The connection interface 861 may also be a communication module for communication on the high-speed line described above.

[0162] The wireless communication interface 863 transmits and receives radio signals via the antenna 840. The wireless communication interface 863 may typically include, for example, an RF circuit 864. The RF circuit 864 may include, for example, a mixer, a filter, and an amplifier, and may transmit and receive radio signals via the antenna 840. The wireless communication interface 863 may include multiple RF circuits 864, as shown in Figure 17. Multiple RF circuits 864 can support multiple antenna elements. Although Figure 17 shows an example in which the wireless communication interface 863 includes multiple RF circuits 864, the wireless communication interface 863 may include a single RF circuit 864.

[0163] In the eNB830 shown in Figure 17, the communication unit 203 and transceiver of the electronic equipment 200 may be implemented by wireless communication interfaces 855 and / or 863. At least some of the functions may be implemented by the controller 851. For example, the controller 851 matches two functional types of AI models used for beam prediction by performing the functions of the matching unit 201, the reuse unit 202, and the communication unit 203, thereby enabling the reuse of beam measurement results and further reducing the overhead of beam measurement.

[0164] (Application examples for user equipment) (First application example) Figure 18 is a block diagram showing an example of a schematic configuration of a smartphone 900 to which the technology described herein can be applied. The smartphone 900 includes a processor 901, memory 902, storage device 903, external connection interface 904, imaging device 906, sensor 907, microphone 908, input device 909, display device 910, speaker 911, wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, bus 917, battery 918, and auxiliary controller 919.

[0165] The processor 901 is, for example, a CPU or a system-on-a-chip (SoC) and can control 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 can include, for example, semiconductor memory and storage media such as a hard disk. The external connection interface 904 is an interface for connecting external devices (e.g., memory cards and Universal Serial Bus (USB) devices) to the smartphone 900.

[0166] The imaging device 906 includes an image sensor (e.g., a charge-coupled device (CCD) and a complementary metal-oxide-semiconductor (CMOS)) and generates an image. Sensor 907 may include a set of sensors such as a measuring sensor, a gyroscope, a geomagnetic sensor, and an accelerometer. Microphone 908 converts sound input to the smartphone 900 into an audio signal. Input device 909 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect touches on the screen of the display device 910 and receives operations or information input from the user. Display device 910 includes a screen (e.g., a liquid crystal display (LCD), an organic light-emitting diode (OLED) display) and displays the output image from the smartphone 900. Speaker 911 converts the audio signal output from the smartphone 900 into sound.

[0167] The wireless communication interface 912 supports any cellular communication method (e.g., LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 912 typically includes, for example, a broadband processor 913 and an RF circuit 914. The broadband processor 913 can perform various types of signal processing for wireless communication, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing. Simultaneously, the RF circuit 914 includes, for example, a mixer, filter, and amplifier, and can transmit and receive wireless signals via the antenna 916. Note that the figure shows a case where one RF link is connected to one antenna, but this is merely an example; a single RF link can also be connected to multiple antennas via multiple phase shifters. The wireless communication interface 912 can be a single chip module on which the broadband processor 913 and RF circuit 914 are integrated. As shown in Figure 18, the wireless communication interface 912 can include multiple broadband processors 913 and multiple RF circuits 914. Figure 18 shows an example in which the wireless communication interface 912 includes multiple BB processors 913 and multiple RF circuits 914, but the wireless communication interface 912 may include a single BB processor 913 or a single RF circuit 914.

[0168] In addition to the cellular communication method, the wireless communication interface 912 can support other types of wireless communication methods, such as short-range wireless communication, proximity communication, and wireless local network (LAN) methods. In this case, the wireless communication interface 912 may include a BB processor 913 and an RF circuit 914 for various wireless communication methods.

[0169] Each of the antenna switches 915 switches the destination of the antenna 916 among multiple circuits included in the wireless communication interface 912 (for example, circuits used for different wireless communication methods).

[0170] Each of the antennas 916 includes one or more antenna elements (for example, multiple antenna elements included in a MIMO antenna) and is used to transmit and receive radio signals via the wireless communication interface 912. As shown in Figure 18, the smartphone 900 may include multiple antennas 916. Although Figure 18 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0171] The smartphone 900 may include an antenna 916 for various wireless communication methods. In this case, the antenna switch 915 can be omitted from the configuration of the smartphone 900.

[0172] Bus 917 connects the processor 901, memory 902, storage device 903, external connection interface 904, imaging device 906, sensor 907, microphone 908, input device 909, display device 910, speaker 911, wireless communication interface 912, and auxiliary controller 919 to each other. Battery 918 supplies power to each block of the smartphone 900 shown in Figure 18 via power lines, which are represented as partially dotted lines in the drawing. The auxiliary controller 919 operates the minimum necessary functions of the smartphone 900, for example, in sleep mode.

[0173] In the smartphone 900 shown in Figure 18, the communication unit 103 and transceiver of the electronic device 100 may be implemented by a wireless communication interface 912. At least some of the functions may be implemented by a processor 901 or an auxiliary controller 919. For example, the processor 901 or auxiliary controller 919 matches two functional types of AI models used for beam prediction by performing the functions of the matching unit 101, the reuse unit 102, and the communication unit 103, thereby enabling the reuse of beam measurement results and further reducing the overhead of beam measurement.

[0174] (Second application example) Figure 19 is a block diagram showing an example of a schematic configuration of a car navigation device 920 to which the technology described herein can be applied. The car navigation device 920 includes a processor 921, memory 922, global positioning system (GPS) module 924, sensor 925, data interface 926, content player 927, storage medium interface 928, input device 929, display device 930, speaker 931, wireless communication interface 933, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0175] The processor 921 is, for example, a CPU or SoC, and can control the navigation and other functions of the car navigation device 920. The memory 922 includes RAM and ROM and stores data and programs executed by the processor 921.

[0176] The GPS module 924 measures the position (e.g., latitude, longitude, altitude) of the car navigation device 920 using GPS signals received from GPS satellites. The sensor 925 may include a set of sensors, such as a gyro sensor, a geomagnetic sensor, and a barometric pressure sensor. The data interface 926 is connected to, for example, an in-vehicle network 941 via a terminal (not shown) to acquire data generated by the vehicle (e.g., vehicle speed data).

[0177] The content player 927 plays content stored on a storage medium (e.g., CD and DVD) inserted into the storage medium interface 928. The input device 929 includes, for example, a touch sensor, button, or switch configured to detect touches on the screen of the display device 930, and receives operations or information input from the user. The display device 930 includes, for example, an LCD or OLED display screen, and displays images of the navigation function or the played content. The speaker 931 outputs sounds of the navigation function or the played content.

[0178] The wireless communication interface 933 supports any cellular communication scheme (e.g., LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 933 typically includes, for example, a broadband processor 934 and an RF circuit 935. The broadband processor 934 can perform various types of signal processing for wireless communication, such as coding / decoding, modulation / demodulation, and multiplexing / demultiplexing. Simultaneously, the RF circuit 935 includes, for example, a mixer, filter, and amplifier, and can transmit and receive wireless signals via the antenna 937. The wireless communication interface 933 can also be a single chip module with the broadband processor 934 and RF circuit 935 integrated on it. As shown in Figure 19, the wireless communication interface 933 can include multiple broadband processors 934 and multiple RF circuits 935. While Figure 19 shows an example where the wireless communication interface 933 includes multiple broadband processors 934 and multiple RF circuits 935, the wireless communication interface 933 may include a single broadband processor 934 or a single RF circuit 935.

[0179] In addition to cellular communication, the wireless communication interface 933 can support other types of wireless communication, such as short-range wireless communication, proximity communication, and wireless LAN. In this case, the wireless communication interface 933 can include a BB processor 934 and an RF circuit 935 for each type of wireless communication.

[0180] Each of the antenna switches 936 switches the destination of the antenna 937 among multiple circuits included in the wireless communication interface 933 (for example, circuits used for different wireless communication methods).

[0181] Each of the antennas 937 includes one or more antenna elements (for example, multiple antenna elements included in a MIMO antenna) and is used to transmit and receive radio signals via the wireless communication interface 933. As shown in Figure 16, the car navigation device 920 may include multiple antennas 937. Although Figure 16 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.

[0182] The car navigation system 920 may include an antenna 937 for various wireless communication methods. In this case, the antenna switch 936 can be omitted from the configuration of the car navigation system 920.

[0183] Battery 938 supplies power to each block of the car navigation system 920 shown in Figure 19 via power lines, which are partially represented as dotted lines in the drawing. Battery 938 stores power supplied from the vehicle.

[0184] In the car navigation device 920 shown in Figure 19, the communication unit 103 and transceiver of the electronic device 100 may be implemented by a wireless communication interface 933. At least part of the functions may be implemented by a processor 921. For example, the processor 921 matches two functional types of AI models used for beam prediction by performing the functions of the matching unit 101, the reuse unit 102, and the communication unit 103, thereby enabling the reuse of beam measurement results and further reducing the overhead of beam measurement.

[0185] The technology described herein may be implemented as an in-vehicle system (or vehicle) 940 including one or more blocks of a car navigation device 920, an in-vehicle network 941, and a vehicle module 942. The vehicle module 942 generates vehicle data (e.g., vehicle speed, engine speed, fault information) and outputs the generated data to the in-vehicle network 941.

[0186] The above has described the basic principles of the disclosure by combining specific embodiments, but a person skilled in the art will understand that all or any step or component of the methods and apparatus of the disclosure can be implemented in any computer device (including processors, storage media, etc.) or network of computer devices by hardware, firmware, software, or a combination thereof, and that a person skilled in the art can implement this by reading the description of the disclosure and using their basic circuit design knowledge or basic programming skills.

[0187] Furthermore, the Disclosure provides a program product that stores machine-readable instruction codes. When these instruction codes are read and executed by a device, they perform the method according to the embodiments of the Disclosure described above.

[0188] Accordingly, the disclosure also includes storage media for storing program products containing the above-mentioned machine-readable instruction codes. These storage media include, but are not limited to, flexible disks, optical disks, magneto-optical disks, memory cards, memory sticks, and the like.

[0189] When this disclosure is implemented by software or firmware, the programs constituting the software are installed from a storage medium or network to a computer having a dedicated hardware configuration (for example, the general-purpose computer 2000 shown in Figure 20), and once the various programs are installed, the computer can perform various functions.

[0190] In Figure 20, the central processing unit (CPU) 2001 executes various processes based on programs stored in read-only memory (ROM) 2002, or programs loaded from memory section 2008 into random access memory (RAM) 2003. RAM 2003 stores data necessary for the CPU 2001 to execute various processes as needed. CPU 2001, ROM 2002, and RAM 2003 are connected to each other via bus 2004. The input / output interface 2005 is also connected to bus 2004.

[0191] The input section 2006 (including keyboard, mouse, etc.), output section 2007 (including displays such as cathode ray tubes (CRTs), liquid crystal displays (LCDs), etc., and speakers, etc.), storage section 2008 (including hard disks, etc.), and communication section 2009 (including network interface cards such as LAN cards and modulators / demodulators) are connected to the input / output interface 2005. The communication section 2009 performs communication processing over a network, such as the Internet. If necessary, a drive 2010 may be connected to the input / output interface 2005. Removable media 2011, such as magnetic disks, optical disks, magneto-optical disks, and semiconductor memory, are mounted on the drive 2010 if necessary, so that computer programs read from them are installed on the storage section 2008 if necessary.

[0192] When the above series of processes are implemented using software, the programs that make up the software are installed from a network such as the internet, or from a storage medium such as removable media 2011.

[0193] Those skilled in the art should understand that such storage media are not limited to removable media 2011, which stores the program shown in Figure 20 and provides the program to the user by being distributed separately from the device. Examples of removable media 2011 include magnetic disks (including Flexible Disks®), optical disks (including Optical Disk Read-Only Memory (CD-ROM) and Digital General Purpose Disks (DVD)), magneto-optical disks (including MiniDisc (MD)®), and semiconductor memory. Alternatively, the storage medium may be a hard disk contained in ROM 2002 or storage section 2008, which stores the program and is distributed to the user together with the device containing them.

[0194] In the apparatus, methods, and systems of this disclosure, each component or step is disassembled and / or reassembled. These disassemblies and / or reassemblies should also be considered equivalent solutions of this disclosure. The execution steps of the above series of processes can be performed in the order described and in chronological order, but do not necessarily have to be performed in chronological order. Some steps may be performed in parallel or independently of each other.

[0195] Finally, the terms “include,” “incorporate,” or any other variation thereof are intended to include non-exclusive inclusion, thereby including not only those elements but also other elements not explicitly listed, or the inherent elements of such process, method, product, or device. Furthermore, unless otherwise specified, the elements limited by the phrase “include one…” do not preclude the presence of other identical elements in the process, method, product, or device that includes the aforementioned elements.

[0196] Although embodiments of the present disclosure have been described in detail above with reference to the drawings, it should be understood that the embodiments described above are for illustrative purposes only and do not limit the present disclosure. Those skilled in the art will be able to make various modifications and changes to the embodiments described above without departing from the substance and scope of the present disclosure. Therefore, the scope of the present disclosure is limited only to the appended claims and their equivalents.

Claims

1. Electronic equipment on the user side for wireless communication, A first artificial intelligence model for performing spatial-domain beam prediction and a second artificial intelligence model for performing time-domain beam prediction are matched. If matching is successful, the beam measurement results are reused between the first artificial intelligence model and the second artificial intelligence model. Includes a processing circuit configured as follows electronic equipment.

2. Matching is successful if the input beamset for the first artificial intelligence model includes the input beamset for the second artificial intelligence model, and the input parameter properties of the first artificial intelligence model include the input parameter properties of the second artificial intelligence model. The electronic device according to claim 1.

3. The aforementioned input parameter properties include at least one of the reference signal received power and the channel impulse response. The electronic device according to claim 2.

4. The beam measurement results include at least a portion of the beam measurement results in the input beamset for the first artificial intelligence model. The electronic device according to claim 2.

5. Both the first artificial intelligence model and the second artificial intelligence model are located on the user device side. The processing circuit is configured to perform matching based on the model parameters of the first artificial intelligence model and the model parameters of the second artificial intelligence model, and to determine whether the matching was successful or not. The electronic device according to claim 1.

6. The processing circuit is further configured to send a message to the base station indicating whether the matching was successful or unsuccessful. The electronic device according to claim 5.

7. If matching is successful, the processing circuit is further configured to transmit the model parameters or model index of the second artificial intelligence model to the base station. The electronic device according to claim 6.

8. The model parameters of the second artificial intelligence model include one or more of the input time window length and output time window length of the second artificial intelligence model, the input parameter size, and the input / output parameter properties. The electronic device according to claim 7.

9. If matching fails, the processing circuit is further configured to decide to use one of the first artificial intelligence model and the second artificial intelligence model, and to transmit the model parameters or model index of the artificial intelligence model to be used to the base station. The electronic device according to claim 6.

10. After a successful match, if the first artificial intelligence model and / or the second artificial intelligence model trigger the monitoring mechanism, the processing circuit obtains the execution cycle of the monitoring mechanism and is configured to keep the unmonitored artificial intelligence models silent during that execution cycle. The electronic device according to claim 5.

11. If, after successful matching, a switch occurs between the first artificial intelligence model and / or the second artificial intelligence model, the processing circuit is configured to re-execute the matching process. The electronic device according to claim 1.

12. The first artificial intelligence model is located on either the user device side or the base station side, and the second artificial intelligence model is located on the other side of the user device side or the base station side. The processing circuit is configured to perform matching by interacting with the base station. The electronic device according to claim 1.

13. The aforementioned processing circuit is Determine the artificial intelligence model to be used on the user device side. A matching request is sent to the base station, causing the base station to determine the artificial intelligence model to be used on the base station side based on the matching request. The system is configured to receive a message from the base station indicating whether the matching was successful or unsuccessful, and to perform matching in such a way that it determines whether the matching was successful or unsuccessful based on that message. The electronic device according to claim 12.

14. The matching request includes model parameters or model index of the artificial intelligence model used on the user device side. If the first artificial intelligence model is located on the user device side, the matching request includes the input parameter size and input / output parameter properties of the first artificial intelligence model. If the second artificial intelligence model is located on the user device side, the matching request includes the length of the input time window and the length of the output time window of the second artificial intelligence model, the input parameter size, and the input / output parameter properties. The electronic device according to claim 13.

15. The matching request includes the model index of the artificial intelligence model used on the user device. The electronic device according to claim 13.

16. If matching is successful, the processing circuit is further configured to receive the model parameters of the artificial intelligence model used by the base station from the base station. If the first artificial intelligence model is located on the base station side, the received model parameters include the input parameter size of the first artificial intelligence model. If the second artificial intelligence model is located on the base station side, the received model parameters include at least the length of the input time window and the length of the output time window, and the minimum number of historical data measurements used. The electronic device according to claim 13.

17. If matching is successful, the processing circuit is further configured to receive the model index of the artificial intelligence model used by the base station from the base station. The electronic device according to claim 13.

18. If matching fails, the processing circuit is further configured to send a message to the base station indicating whether to select the first artificial intelligence model or the second artificial intelligence model. The electronic device according to claim 13.

19. If the first artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes the model parameters or model index of the selected first artificial intelligence model. If the first artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes 1 bit of notification information. If the second artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes 1 bit of notification information. If the second artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes the model parameters or model index of the selected second artificial intelligence model. The electronic device according to claim 18.

20. The aforementioned processing circuit is The base station receives a matching request that includes the model parameters or model index of the artificial intelligence model used for matching determined by the base station. Based on the received model parameters or model index, the user device determines the artificial intelligence model to be used for matching. The system is configured to perform matching in such a way that it sends a message to the base station indicating whether the matching was successful or unsuccessful. The electronic device according to claim 12.

21. If the first artificial intelligence model is located on the user device side, the received model parameters include one or more of the model parameters of the second artificial intelligence model, such as the length of the input time window and the length of the output time window, the input parameter size, the input / output parameter properties, and the minimum number of measurements of historical data used. If the second artificial intelligence model is located on the user device side, the received model parameters include at least the input parameter size and input / output parameter properties of the first artificial intelligence model. The electronic device according to claim 20.

22. If the match is successful, If the first artificial intelligence model is located on the user device side, the processing circuit is further configured to transmit the input parameter size of the first artificial intelligence model to the base station. If the second artificial intelligence model is located on the user device side, the processing circuit is further configured to transmit the length of the input time window and the length of the output time window of the second artificial intelligence model to the base station. The electronic device according to claim 20.

23. If matching fails, the processing circuit is further configured to receive a message from the base station indicating whether to select the first artificial intelligence model or the second artificial intelligence model. The electronic device according to claim 20.

24. If the first artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes 1 bit of notification information. If the first artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes the model parameters or model index of the selected second artificial intelligence model. If the second artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes the model parameters or model index of the selected first artificial intelligence model. If the second artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes 1 bit of notification information. The electronic device according to claim 23.

25. If the first artificial intelligence model is located on the user equipment side and the second artificial intelligence model is located on the base station side, after successful matching, the processing circuit is further configured to cause the second artificial intelligence model to perform beam prediction using the beam measurement results by reporting the beam measurement results within the length of the input time window of the second artificial intelligence model to the base station once or multiple times. The electronic device according to claim 12.

26. The processing circuit is configured to report the beam measurement results and the prediction results of the first artificial intelligence model via a data channel. The electronic device according to claim 25.

27. After a successful match, When the first artificial intelligence model and / or the second artificial intelligence model triggers a monitoring mechanism, and the monitoring mechanism is executed by the user device, the processing circuit is configured to provide the base station with the execution cycle of the monitoring mechanism, and when the monitoring mechanism is executed by the base station, the processing circuit is configured to obtain the execution cycle of the monitoring mechanism from the base station. If the artificial intelligence model on the base station side triggers the monitoring mechanism, the processing circuit is further configured to keep the artificial intelligence model on the user device side silent during the execution cycle. The electronic device according to claim 12.

28. Electronic equipment on the base station side for wireless communication, A first artificial intelligence model for performing spatial-domain beam prediction and a second artificial intelligence model for performing time-domain beam prediction are matched. If matching is successful, the beam measurement results are reused between the first artificial intelligence model and the second artificial intelligence model. Includes a processing circuit configured as follows electronic equipment.

29. Both the first artificial intelligence model and the second artificial intelligence model are located on the base station side, and the processing circuit is configured to perform matching based on the model parameters of the first artificial intelligence model and the model parameters of the second artificial intelligence model, and to determine whether the matching was successful or not. The electronic device according to claim 20.

30. If matching is successful, the processing circuit is configured to transmit the length of the input time window and the length of the output time window of the second artificial intelligence model to the user device. The electronic device according to claim 29.

31. After successful matching, if the first artificial intelligence model and / or the second artificial intelligence model trigger a monitoring mechanism, the processing circuit is configured to provide the execution cycle of the monitoring mechanism to the user device when the monitoring mechanism is executed by the base station, and to obtain the execution cycle of the monitoring mechanism from the user device when the monitoring mechanism is executed by the user device. The electronic device according to claim 29.

32. If, after successful matching, a switch occurs between the first artificial intelligence model and / or the second artificial intelligence model, the processing circuit is configured to re-execute the matching process. The electronic device according to claim 29.

33. The first artificial intelligence model is located on either the user device side or the base station side, and the second artificial intelligence model is located on the other side of the user device side or the base station side. The processing circuit is configured to perform matching by interacting with the user device. The electronic device according to claim 28.

34. The aforementioned processing circuit is The system receives a matching request from the user device that includes the model parameters or model index of the artificial intelligence model used on the user device side, which was determined by the user device. Based on the matching request, the artificial intelligence model to be used on the base station side is determined. The system is configured to perform matching so that a message indicating whether the matching was successful or unsuccessful is sent to the user device. The electronic device according to claim 33.

35. If the first artificial intelligence model is located on the user device side, the matching request includes the input parameter size and input / output parameter properties of the first artificial intelligence model. If the second artificial intelligence model is located on the user device side, the matching request includes the length of the input time window and the length of the output time window of the second artificial intelligence model, the input parameter size, and the input / output parameter properties. The electronic device according to claim 34.

36. If matching is successful, the processing circuit is further configured to transmit the model parameters of the artificial intelligence model used on the base station side to the user device. If the first artificial intelligence model is located on the base station side, the transmitted model parameters include the input parameter size of the first artificial intelligence model. If the second artificial intelligence model is located on the base station side, the transmitted model parameters include at least the length of the input time window and the length of the output time window, and the minimum number of historical data measurements to be used. The electronic device according to claim 34.

37. If matching is successful, the processing circuit is further configured to transmit the model index of the artificial intelligence model used on the base station side to the user device. The electronic device according to claim 34.

38. If matching fails, the processing circuit is further configured to receive a message from the user device indicating whether to select the first artificial intelligence model or the second artificial intelligence model. The electronic device according to claim 34.

39. If the first artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes the model parameters or model index of the selected first artificial intelligence model. If the first artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes 1 bit of notification information. If the second artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes 1 bit of notification information. If the second artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes the model parameters or model index of the selected second artificial intelligence model. The electronic device according to claim 38.

40. The aforementioned processing circuit is The base station determines the artificial intelligence model to be used for matching. The model parameters or model index of the determined artificial intelligence model are included in the matching request and sent to the user device, causing the user device to determine the artificial intelligence model to be used on the user device side based on the model parameters or model index. The system is configured to perform matching so that a message indicating whether the matching was successful or unsuccessful is received from the user device. The electronic device according to claim 33.

41. If the first artificial intelligence model is located on the user device side, the transmitted model parameters include one or more of the model parameters of the second artificial intelligence model, such as the length of the input time window and the length of the output time window, the input parameter size, the input / output parameter properties, and the minimum number of measurements of historical data used. If the second artificial intelligence model is located on the user device side, the transmitted model parameters include at least the input parameter size and input / output parameter properties of the first artificial intelligence model. The electronic device according to claim 40.

42. If the match is successful, If the first artificial intelligence model is located on the user device side, the processing circuit is further configured to receive the input parameter size of the first artificial intelligence model from the user device. If the second artificial intelligence model is located on the user device side, the processing circuit is further configured to receive the length of the input time window and the length of the output time window of the second artificial intelligence model from the user device. The electronic device according to claim 40.

43. If matching fails, the processing circuit is further configured to send a message to the user device indicating whether to select the first artificial intelligence model or the second artificial intelligence model. The electronic device according to claim 40.

44. If the first artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes 1 bit of notification information. If the first artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes the model parameters or model index of the selected second artificial intelligence model. If the second artificial intelligence model is located on the user device side and the first artificial intelligence model is selected, the message includes the model parameters or model index of the selected first artificial intelligence model. If the second artificial intelligence model is located on the user device side and the second artificial intelligence model is selected, the message includes 1 bit of notification information. The electronic device according to claim 43.

45. If the first artificial intelligence model is located on the user equipment side and the second artificial intelligence model is located on the base station side, after successful matching, the processing circuit is further configured to receive beam measurement results from the user equipment one or more times within the length of the input time window of the second artificial intelligence model, thereby causing the second artificial intelligence model to perform beam prediction using the beam measurement results. The electronic device according to claim 33.

46. The processing circuit is configured to receive the beam measurement results and the prediction results of the first artificial intelligence model via a data channel. The electronic device according to claim 45.

47. After a successful match, When the first artificial intelligence model and / or the second artificial intelligence model triggers a monitoring mechanism, and the monitoring mechanism is executed by the user device, the processing circuit is configured to obtain the execution cycle of the monitoring mechanism from the user device, and when the monitoring mechanism is executed by the base station, the processing circuit is configured to provide the execution cycle of the monitoring mechanism to the user device. If the artificial intelligence model on the user device side triggers the monitoring mechanism, the processing circuit is further configured to keep the artificial intelligence model on the base station side silent during the execution cycle. The electronic device according to claim 33.

48. A method on the user equipment side for wireless communication, Matching a first artificial intelligence model for performing spatial-domain beam prediction with a second artificial intelligence model for performing time-domain beam prediction, If matching is successful, the method includes reusing the beam measurement results between the first artificial intelligence model and the second artificial intelligence model. method.

49. A method on the base station side for wireless communication, Matching a first artificial intelligence model for performing spatial-domain beam prediction with a second artificial intelligence model for performing time-domain beam prediction, If matching is successful, the method includes reusing the beam measurement results between the first artificial intelligence model and the second artificial intelligence model. method.

50. When executed by a processor, a computer-executable instruction is stored which causes the processor to perform the method according to claim 48 or 49. A computer-readable storage medium.

Images