Electronic device and method for wireless communication system, and storage medium

Abstract

An electronic device and method for a wireless communication system, and a storage medium. A first electronic device for a wireless communication system, the first electronic device comprising: at least one processor and at least one memory, the at least one memory comprising a computer program code, and the at least one memory and the computer program code being configured to enable, by means of the at least one processor, the first electronic device to notify a second electronic device of data, wherein the data is notified in one of the following notification modes: a first notification mode, which is configured such that data is sent or received by means of an AI model deployed on one side of the first electronic device or a second electronic device; a second notification mode, which is configured such that data is sent and received by means of a pair of jointly trained AI models deployed on two sides of the first electronic device and the second electronic device; and a third notification mode, which is configured such that data is sent to the second electronic device by the first electronic device without using an AI model for notifying data at either of the first electronic device and the second electronic device.

Description

Electronic device, method and storage medium for wireless communication system

[0001] Cross-reference to related applications

[0002] This application is based on and claims priority from Chinese patent application No. 202311644098.X, filed on December 1, 2023, entitled “Electronic device, method and storage medium for wireless communication system,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates generally to wireless communication systems, and more particularly to techniques related to data transmission / notification in wireless communication systems. Background Art

[0004] With the development of communication scenarios and technologies, data transmission in wireless communication systems may have more flexible and variable requirements than ever before in terms of communication metrics such as data volume, latency, reliability, and resource overhead. Relying solely on communication models based on traditional source and / or channel coding techniques may not be able to meet these flexible communication metric requirements in some current wireless communication scenarios.

[0005] Therefore, new communication models need to be expanded to adapt to more flexible requirements in terms of various communication indicators. Summary of the Invention

[0006] The present disclosure proposes a solution related to data transmission / notification in a wireless communication system. Specifically, the present disclosure provides an electronic device, a method, and a storage medium for a wireless communication system.

[0007] One aspect of the present disclosure relates to a first electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the first electronic device to notify a second electronic device of data, wherein the data is notified through one of the following notification modes: a first notification mode, configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode, configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and a third notification mode, configured to send the data by the first electronic device to the second device without utilizing the AI ​​model for notifying the data at both the first electronic device and the second electronic device.

[0008] Another aspect of the present disclosure relates to a second electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the second electronic device to obtain data to be notified by the first electronic device, wherein the data is notified through one of the following notification modes: a first notification mode, configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode, configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and a third notification mode, configured to send the data by the first electronic device to the second device without utilizing the AI ​​model for notifying the data at both the first electronic device and the second electronic device.

[0009] Another aspect of the present disclosure relates to a method for a first electronic device of a wireless communication system, comprising notifying a second electronic device of data, wherein the data is notified through one of the following notification modes: a first notification mode, configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode, configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and a third notification mode, configured to send the data by the first electronic device to the second device without utilizing an AI model for notifying the data at both the first electronic device and the second electronic device.

[0010] Another aspect of the present disclosure relates to a method for a second electronic device of a wireless communication system, comprising obtaining data to be notified by a first electronic device, wherein the data is notified through one of the following notification modes: a first notification mode, configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode, configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and a third notification mode, configured to send the data by the first electronic device to the second device without utilizing the AI ​​model for notifying the data at both the first electronic device and the second electronic device.

[0011] Another aspect of the present disclosure relates to a first electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the first electronic device to send data to a second electronic device as one of a group of sending devices, the group of sending devices including one or more sending devices, wherein a plurality of jointly trained artificial intelligence (AI) model pairs are deployed on both sides of each sending device and the second electronic device, and wherein the at least one memory and the computer program code are further configured to, through the at least one processor, enable the first electronic device to process the data using a first AI model in a first AI model pair selected from the plurality of AI model pairs and send the processed data to the second electronic device, so that the second electronic device uses the second AI model in the first AI model pair to reconstruct the data based on the processed data received from the first electronic device.

[0012] Another aspect of the present disclosure relates to a second electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the second electronic device to receive data from each transmitting device in a group of transmitting devices, the group of transmitting devices including one or more transmitting devices, wherein a plurality of jointly trained artificial intelligence (AI) model pairs are deployed on both sides of each transmitting device and the second electronic device, and wherein the at least one memory and the computer program code are further configured to, through the at least one processor, enable the second electronic device to receive processed data obtained by processing the data using a first AI model in a corresponding AI model pair selected from the multiple AI model pairs from each transmitting device, and reconstruct the data based on the received processed data using a second AI model in the corresponding AI model pair.

[0013] Another aspect of the present disclosure relates to a method for a first electronic device of a wireless communication system, comprising the first electronic device sending data to a second electronic device as one of a group of transmitting devices, the group of transmitting devices including one or more transmitting devices, wherein a plurality of jointly trained artificial intelligence (AI) model pairs are deployed on both sides of each transmitting device and the second electronic device, and wherein the method further comprises processing the data using a first AI model in a first AI model pair selected from the plurality of AI model pairs and sending the processed data to the second electronic device, so that the second electronic device reconstructs the data based on the processed data received from the first electronic device using a second AI model in the first AI model pair.

[0014] Another aspect of the present disclosure relates to a method for a second electronic device of a wireless communication system, comprising receiving data from each transmitting device in a group of transmitting devices, the group of transmitting devices including one or more transmitting devices, wherein a plurality of jointly trained artificial intelligence (AI) model pairs are deployed on both sides of each transmitting device and the second electronic device, and wherein the method further comprises receiving processed data obtained by processing the data using a first AI model in a corresponding AI model pair selected from the multiple AI model pairs from each transmitting device, and reconstructing the data based on the received processed data using a second AI model in the corresponding AI model pair.

[0015] Another aspect of the present disclosure relates to a non-transitory computer-readable storage medium storing executable instructions, which, when executed, implement the method as described in the above aspect.

[0016] Another aspect of the present disclosure relates to a computer program product comprising executable instructions, which, when executed, implement the method according to the above aspect.

[0017] The above summary is provided to summarize some exemplary embodiments in order to provide a basic understanding of various aspects of the subject matter described herein. Therefore, the above features are merely examples and should not be construed as narrowing the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become apparent from the detailed description described below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] A better understanding of the present disclosure may be obtained when the following detailed description of the embodiments is considered in conjunction with the accompanying drawings. The same or similar reference numerals are used in the various drawings to represent the same or similar components. The accompanying drawings, together with the following detailed description, are incorporated into and form a part of this specification and are used to illustrate the embodiments of the present disclosure and to explain the principles and advantages of the present disclosure. In particular:

[0019] FIG1 schematically illustrates a conventional notification mode in a wireless communication system;

[0020] FIG2 is a conceptual configuration of an electronic device on the transmitting end side according to the first embodiment of the present disclosure;

[0021] FIG3 schematically shows a conceptual operation flow of the transmitting end side according to the first embodiment of the present disclosure;

[0022] FIG4 schematically shows a schematic representation of a second notification mode according to the first embodiment of the present disclosure;

[0023] FIG5 schematically shows a conceptual configuration of an electronic device on the receiving end side according to the first embodiment of the present disclosure;

[0024] FIG6 schematically shows a conceptual operation flow of the receiving end side according to the first embodiment of the present disclosure;

[0025] FIG7 schematically illustrates the interaction between a transmitting end and a receiving end according to a first exemplary implementation of the first embodiment of the present disclosure;

[0026] FIG8A schematically shows a schematic representation of a first notification mode according to a first example implementation of the first embodiment of the present disclosure;

[0027] FIG8B schematically illustrates interaction between a transmitting end and a receiving end using a first notification mode according to a first example implementation of the first embodiment of the present disclosure;

[0028] FIG9A schematically shows a schematic representation of a second notification mode according to a first example implementation of the first embodiment of the present disclosure;

[0029] FIG9B schematically illustrates interaction between a transmitting end and a receiving end using a second notification mode according to a first example implementation of the first embodiment of the present disclosure;

[0030] FIG10A schematically illustrates a schematic representation of a third notification mode according to a first example implementation of the first embodiment of the present disclosure;

[0031] FIG10B schematically illustrates interaction between a first example transmitting end and a receiving end using a third notification mode according to the first embodiment of the present disclosure;

[0032] FIG11 schematically illustrates the interaction between a transmitting end and a receiving end according to a second exemplary implementation of the first embodiment of the present disclosure;

[0033] 12A and 12B schematically illustrate an application scenario according to the second embodiment of the present disclosure;

[0034] FIG13 schematically shows a conceptual configuration of an electronic device on the transmitting end side according to the second embodiment of the present disclosure;

[0035] FIG14 schematically shows a conceptual operation flow of the transmitting end side according to the second embodiment of the present disclosure;

[0036] FIG15 schematically shows a conceptual configuration of an electronic device on the receiving end side according to the second embodiment of the present disclosure;

[0037] FIG16 schematically shows a conceptual operation flow of a receiving end side according to the second embodiment of the present disclosure;

[0038] FIG17 schematically illustrates the interaction between a transmitting end and a receiving end according to a first exemplary implementation of the second embodiment of the present disclosure;

[0039] FIG18 schematically illustrates the interaction between a transmitting end and a receiving end according to a second example implementation of the second embodiment of the present disclosure;

[0040] FIG19 schematically illustrates the interaction between the transmitting end and the receiving end during the training of the AI ​​model according to the second embodiment of the present disclosure;

[0041] 20 is a block diagram of an example structure of a personal computer as an information processing device that can be employed in an embodiment of the present disclosure;

[0042] FIG21 is a block diagram illustrating a first example of a schematic configuration of a gNB to which the technology of the present disclosure may be applied;

[0043] FIG22 is a block diagram illustrating a second example of a schematic configuration of a gNB to which the technology of the present disclosure may be applied;

[0044] FIG23 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; and

[0045] FIG. 24 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.

[0046] While the embodiments described in this disclosure may be susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are herein described in detail. However, it should be understood that the drawings and detailed description thereof are not intended to limit the embodiments to the particular forms disclosed, but on the contrary, the intent is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the claims. DETAILED DESCRIPTION

[0047] The following describes representative applications of various aspects of the apparatus and method of the present disclosure. The description of these examples is only to add context and help understand the described embodiments. Therefore, it is clear to those skilled in the art that the embodiments described below can be implemented without some or all of the specific details. In other cases, well-known process steps are not described in detail to avoid unnecessarily obscuring the described embodiments. Other applications are also possible, and the solutions of the present disclosure are not limited to these examples.

[0048] Typically, a wireless communication system includes at least a transmitting device (hereinafter referred to as the transmitting end) and a receiving device (hereinafter referred to as the transmitting end). In the present disclosure, both the transmitting end and the receiving end can be a control device or a terminal device. For example, the control device can act as a transmitting end to notify data to a terminal device, or the terminal device can act as a transmitting end to notify data to the control device, or the terminal device can act as a transmitting end to notify data to another terminal device acting as a receiving end. The control device can provide communication services for one or more terminal devices.

[0049] In this disclosure, the terms "base station" or "control device" have their full breadth of common meaning and include at least a wireless communication station that facilitates communication as part of a wireless communication system or radio system. For example, a base station may be an eNB for the 4G communication standard, a gNB for the 5G NR communication standard, a remote radio head, a wireless access point, a drone control tower, or a communication device that performs similar functions. In this disclosure, "base station" and "control device" may be used interchangeably, or a "control device" may be implemented as part of a "base station." Below, using a base station as an example, an application example of a base station / terminal device will be described in detail with reference to the accompanying drawings.

[0050] In the present disclosure, the term "terminal device" or "user equipment (UE)" has the full breadth of its usual meaning and includes at least a terminal device that is part of a wireless communication system or radio system to facilitate communication. As an example, the terminal device may be a terminal device such as a mobile phone, a laptop, a tablet computer, an in-vehicle communication device, a wearable device, a sensor, or the like, or an element thereof. In the present disclosure, "terminal device" and "user equipment" (hereinafter referred to as "UE") may be used interchangeably, or a "terminal device" may be implemented as a part of a "user equipment".

[0051] In this disclosure, the term "transmitter side" / "transmitter device side" has its full breadth of ordinary meaning and generally refers to the side that transmits or notifies data to the other party. Similarly, the term "terminal device side" / "user device side" has its full breadth of ordinary meaning and can accordingly refer to the side that receives or obtains data from the other party.

[0052] In this disclosure, the term "AI model" has the full breadth of its usual meaning, and generally refers to any applicable machine learning model, deep learning model, rule model, weak artificial intelligence model, strong artificial intelligence model, etc. that has been trained to implement the functions defined in this disclosure.

[0053] In a wireless communication system, when a transmitter needs to notify a receiver of data, according to a traditional communication model, as shown in Figure 1, the transmitter can encode the data to be notified to the receiver (for example, using source coding and channel coding), modulate the encoded data, and transmit the modulated data to the receiver, for example, over a noisy channel. The receiver then demodulates and decodes the received data (for example, using channel decoding and source decoding) to obtain the data that the transmitter wishes to notify.

[0054] When some communication scenarios require sending large amounts of data, or when the noise and interference in the wireless communication system are large, the use of this traditional data transmission method may result in a delay that is difficult to meet the needs of both communicating parties. Alternatively, the use of this traditional data transmission method may result in a large resource overhead (for example, communication resources in terms of time, frequency, space, etc.). Alternatively, in some special circumstances (for example, special channel conditions), the use of this traditional data transmission method may also lead to a decrease in data transmission reliability.

[0055] In addition, as introduced in the background technology, with the development of communication scenarios and communication technologies, different communication scenarios may have more flexible and changing requirements for communication indicators such as data volume, latency, reliability, and resource overhead than before.

[0056] Therefore, new communication models need to be expanded to adapt to more flexible requirements in terms of various communication indicators.

[0057] With the development of wireless communications and artificial intelligence, the present disclosure considers introducing AI into wireless communication systems as a new communication mode for transmission / notification of data.

[0058] For example, this new communication mode can consider deploying AI models at the transmitting and / or receiving ends. Such AI models can be configured to perform any one or more operations of source coding, channel coding, and modulation on the data, any one or more operations of source decoding, channel decoding, and demodulation on the data, or any additional processing required for the current communication, such as compression or decompression of the data, prediction of the currently required data based on other data (e.g., historical data), etc.

[0059] First embodiment

[0060] According to a first embodiment of the present disclosure, data can be notified from a transmitting end to a receiving end using one of the following three notification modes: a first notification mode, configured to use an artificial intelligence (AI) model deployed on one side of the transmitting end or the receiving end to send or receive the data; a second notification mode, configured to use a pair of jointly trained AI models deployed on both sides of the transmitting end and the receiving end to send and receive the data; and a third notification mode, configured to send the data from the transmitting end to the receiving end when neither the transmitting end nor the receiving end uses the AI ​​model for notifying the data.

[0061] The first embodiment will be described in detail below with reference to FIG. 2 to FIG. 11 .

[0062] The structure and operation flow of the transmitting end according to the first embodiment of the present disclosure

[0063] First, the conceptual structure of the electronic device 20 for the transmitting end according to an embodiment of the present disclosure will be described with reference to Figure 2. The electronic device 20 shown in Figure 2 may include various units to implement the corresponding operations according to the first embodiment of the present disclosure. In this example, the electronic device 20 includes a communication unit 202 and a control unit 204. According to the present disclosure, the electronic device 20 may be a control device or a terminal device serving as a transmitting end. In one embodiment, the electronic device 20 is implemented as the control device or the terminal device serving as the transmitting end itself or a part thereof, or is implemented as a device or a part of the device for controlling the control device or the terminal device serving as the transmitting end or otherwise related thereto. The various operations described below in conjunction with the transmitting end may be implemented by units 202, 204 or other possible units of the electronic device 20.

[0064] As shown in FIG2 , the electronic device 20 may include a communication unit 202. The communication unit 202 may be configured to notify data to another electronic device. For example, the data to be notified may be any data that needs to be notified from the transmitting end to the receiving end according to the corresponding communication scenario, such as, but not limited to, channel state information (CSI), video data, sensor data, etc. More generally, the communication unit 202 may be configured to send signals to or receive signals from other electronic devices (such as service data, control signaling, and any other signals that need to be sent between electronic devices).

[0065] The electronic device 20 may also include a control unit 204. The control unit 204 may be configured to control the communication unit 202 to use one of the following notification modes to notify data: a first notification mode configured to use an AI model deployed on one side of the electronic device 20 or the receiving electronic device to send or receive the data; a second notification mode configured to use a pair of jointly trained AI models deployed on both the electronic device 20 and the receiving electronic device to send and receive the data; and a third notification mode configured to send the data from the electronic device 20 to the receiving electronic device when neither the electronic device 20 nor the receiving electronic device uses an AI model for notifying the data. For example, the control unit 204 may be configured to select a notification model and / or AI model and control the communication unit 202 to notify the receiving electronic device of the notification model and / or AI model to be used. Alternatively, the control unit 204 may be configured to determine the notification model and / or AI model to be used based on indication information received via the communication unit 202. More generally, the control unit 204 may be configured to perform any appropriate control on the electronic device required to enable it to complete the corresponding operation.

[0066] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, rather than being used to limit specific implementation methods, for example, they can be implemented in software, hardware or a combination of software and hardware. The functions of the units disclosed herein can be implemented using circuits or processing circuits. Processing circuits can refer to various implementations of digital circuit systems, analog circuit systems or mixed signal (a combination of analog and digital) circuit systems that perform functions in a computing system. Processing circuits can include, for example, circuits such as integrated circuits (ICs), application specific integrated circuits (ASICs), parts or circuits of separate processor cores, entire processor cores, separate processors, programmable hardware devices such as field programmable gate arrays (FPGAs), and / or systems including multiple processors. Processors are considered to be processing circuits or circuits because they include transistors and other circuits therein.

[0067] In the present disclosure, a circuit, unit, device or apparatus is hardware that performs or is programmed to perform the function. The hardware can be any hardware disclosed herein or otherwise known to be programmed or configured to perform the function. When the hardware is a processor that can be considered as a type of circuit, the circuit, device or unit is a combination of hardware and software, and the software is used to configure the hardware and / or processor. In the implementation of hardware, the hardware can be programmed or configured to perform the function. In the implementation of software or a combination of software and hardware, the software can be used to configure the hardware and / or processor. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.).

[0068] Hereinafter, various operations performed by the electronic device 20 as the transmitting end will be described in detail with reference to the conceptual operation flow 30 of the transmitting end shown in FIG. 3 .

[0069] The operation of the sending end starts at S302.

[0070] At S304, the transmitting end notifies the receiving end of data, where the data is notified through one of the following notification modes: a first notification mode, configured to use an artificial intelligence (AI) model deployed on one side of the transmitting end or the receiving end to send or receive the data; a second notification mode, configured to use a pair of jointly trained AI models deployed on both sides of the transmitting end and the receiving end to send and receive the data; and a third notification mode, configured to send the data from the transmitting end to the receiving end without using the AI ​​model for notifying the data at both the transmitting end and the receiving end. For example, the data to be notified can be any data that needs to be notified by the transmitting end to the receiving end according to the corresponding communication scenario, such as but not limited to channel state information (CSI), video data, sensor data, etc.

[0071] In S304, specifically, the transmitting end may first determine which notification mode to use to notify the receiving end of data. For example, the transmitting end may select one of the three notification modes mentioned above based at least on communication indicators. The communication indicators may, for example, include at least one or more of the following indicators: the transmission delay on the communication link between the transmitting end and the receiving end (for example, it may be the actual delay and / or the expected delay), the data transmission accuracy requirement, the communication resource overhead, the transmission rate between the transmitting end and the receiving end, the queue length of the data that the transmitting end is ready to send to the receiving end, and the computing power of the transmitting end and / or the receiving end. For another example, the transmitting end may receive information from the receiving end indicating which notification mode to use. In this case, the receiving end may select the notification mode to be used based at least on the above-mentioned communication indicators.

[0072] For example, in the first notification mode and the second notification mode, due to the introduction of the AI ​​model for joint encoding / compression / decompression / prediction of the data to be sent and / or received, the data transmission accuracy may be lower than the accuracy of data transmission using traditional encoding and decoding and modulation and demodulation methods under the same channel conditions, that is, lower than the data transmission accuracy of the third notification mode. In addition, since the first notification mode only deploys the AI ​​model on the transmitting end or the receiving end, due to the lack of a joint training process for data on both the transmitting end and the receiving end, some correlation information between the transmitting end and the receiving end is lost when the AI ​​model is generated, and / or since this unilaterally deployed AI model usually performs some data prediction processing, resulting in prediction errors, the data transmission accuracy of the first notification mode may be lower than the data transmission accuracy of the second notification mode.

[0073] However, the use of AI models can reduce the total data processing time, thereby reducing transmission latency and increasing transmission rate. After the original data is processed by the AI ​​model, a very small amount of output data for transmission can be generated, thereby saving communication resources (such as time, frequency or space resources). Therefore, the sender or receiver can select the most appropriate notification mode to notify data based on the requirements for data transmission accuracy and the trade-offs in transmission latency, transmission rate, and communication resource overhead.

[0074] In particular, in some special scenarios, such as the case of CSI feedback as detailed below, the amount of data to be transmitted between the transmitter and receiver may affect the required data transmission accuracy. Therefore, the amount of data transmitted between the transmitter and receiver (for example, the length of the queue of data to be transmitted) can also be considered to determine the required data transmission accuracy, and then the most appropriate notification mode can be selected to notify the data based on the required data transmission accuracy.

[0075] Furthermore, deploying AI models may require computing power on the sender / receiver side. Therefore, some sender / receiver devices with limited computing power may not be suitable for deploying AI models. Therefore, the most appropriate notification mode for data notification can also be selected based on the computing power of the sender / receiver side.

[0076] For another example, the receiving end may select the notification mode to use. In this case, before notifying the data, the sending end may also receive indication information from the receiving end indicating the notification mode to be used next. For another example, the notification mode to be used may be a default, for example, based on a pre-agreed agreement between the two parties, or based on a predetermined association between a specific communication scenario and a notification mode.

[0077] Preferably, the notification mode to be adopted can be determined dynamically. For example, the notification mode to be adopted can be determined and adjusted in real time based on the real-time changes in the communication indicators described above. For another example, the communication indicators described above can also be determined periodically and the notification mode to be adopted adjusted accordingly.

[0078] The sending end may also deploy at least one AI model for the first notification mode and / or the second notification mode before S304.

[0079] Specifically, according to the present disclosure, the first notification mode can be configured as any one of the following modes: sub-mode (1) deploying an AI model at the sending end, and the sending end uses the deployed AI model to process the data to be notified to the receiving end and sends the processed data to the receiving end, sub-mode (2) deploying an AI model at the receiving end, and the receiving end uses the deployed AI model to receive the data to be notified to the receiving end from the sending end, and sub-mode (3) deploying an AI model at the receiving end, and the receiving end uses the deployed AI model to predict the data based on historical data related to the data to be notified to the receiving end.

[0080] In the first notification mode, the AI ​​model deployed at the transmitting or receiving end can be any appropriate AI model that pre-processes the data to be notified or performs additional processing on the received data. For example, the AI ​​model deployed at the transmitting end can compress the data to be notified, extract key information, reduce redundant information, add additional information relevant to the scenario, and so on. In this case, the input of the AI ​​model deployed at the transmitting end can be the raw data to be notified, and the output can be the processed data after processing the data to be notified. As another example, the AI ​​model deployed at the transmitting end can also be a model that encodes and modulates the data to be notified using an AI method. In this case, the input of the AI ​​model deployed at the transmitting end can be the raw data to be notified, and the output can be a modulated signal to be transmitted over the channel. For example, the AI ​​model deployed at the receiving end can decompress the data received from the transmitting end, extract key information, and make predictions about the complete data to be notified based on the data received from the transmitting end. In this case, the input of the AI ​​model deployed at the receiving end can be the data received from the transmitting end, and the output can be the complete data generated by the AI ​​model after processing to be notified by the transmitting end to the receiving end. For another example, the AI ​​model deployed at the receiving end can also be a model that decodes and demodulates the data to be notified in an AI manner. In this case, the input of the AI ​​model deployed at the receiving end can be a modulated signal received from the transmitting end that has been traditionally encoded and modulated, and the output can be data demodulated and decoded by the AI ​​model.

[0081] In particular, the AI ​​model deployed at the receiving end may also be a prediction model for predicting data. In this case, the input of the AI ​​model deployed at the receiving end may be historical data related to the data to be predicted and, optionally, any data used to assist in the prediction, and the output may be the predicted data to be notified by the sending end to the receiving end.

[0082] In the case where the transmitting end determines at S304 that the first notification mode is to be used, the transmitting end may further determine which of the three sub-modes to use to notify the data. For example, the transmitting end may make the determination based on at least the communication scenario and the deployment of the AI ​​models of the transmitting end and the receiving end. For example, in the case where only the transmitting end has the ability to deploy AI, or in the case where the communication scenario involved is suitable for using AI to pre-process the data to be notified to the receiving end (for example, compression, extraction of key information, addition of additional information related to the scenario, etc.), sub-mode (1) may be used to notify the data. For another example, in the case where only the receiving end has the ability to deploy AI, or in the case where the communication scenario involved is suitable for using AI to perform additional processing on the data received from the transmitting end (for example, decompression, extraction of key information, prediction of the complete data to be notified based on the data received from the transmitting end, etc.), sub-mode (2) may be used to notify the data. For example, in some special cases (e.g., the CSI feedback scenario described in detail below), the transmitter may not even send any data to be notified to the receiver, but only notify the receiver to use the AI ​​deployed at the receiver to predict the data to be notified based on the historical data previously received from the transmitter. In these special cases, the transmitter may determine to use sub-mode (3) to notify the data.

[0083] For another example, the sub-mode to be used may also be selected by the receiving end. In this case, before notifying the data, the sending end may also receive indication information from the receiving end indicating the specific sub-mode to be used next. For another example, which sub-mode to use may also be a default or preset based on the communication scenario and / or the AI ​​model deployment status of the sending end and the receiving end (for example, in previous communications, the sending end and the receiving end have already understood each other's AI model deployment status).

[0084] According to the present disclosure, the second notification mode can be configured as the sending end uses the first AI model in a pair of jointly trained AI models to process the data to be notified to the receiving end and sends the processed data to the receiving end, and the receiving end uses the second AI model in the pair of AI models to reconstruct the data based on the processed data received from the sending end.

[0085] FIG4 shows a schematic representation of the second notification mode. As shown in FIG4, in this mode, the data x1 to be notified from the sending end to the receiving end is first processed by the first AI model deployed at the sending end to obtain the processed data z1 (for example, the data z1 can be in a complex form). Subsequently, via the transmission of the wireless channel, the data z1 becomes Due to the presence of noise and interference in wireless channels, Not necessarily identical to z1. It is input into the second AI model, and after being processed by the model, the receiving end can obtain reconstructed data Typically, using a well-trained AI model pair, the resulting data is reconstructed It is basically the same as the original data x1 to be notified.

[0086] As shown in Figure 4, the first AI model and the second AI model deployed on both sides of the transmitter and the receiver respectively are a pair of jointly trained AI models. In this notification mode, the transmitter and the receiver together with the wireless channel passing therebetween can be regarded as an N-layer neural network as a whole. In this neural network, the wireless channel is also a part of it. The wireless channel can be modeled as a non-training layer in the neural network according to the channel characteristics, that is, a neural network layer with fixed parameters, which will not change during model training. During the training of the AI ​​model pair, the first AI model at the transmitter and the second AI model at the receiver need to be jointly learned (for example, the training data is paired data, the training parameters are jointly adjusted, etc.) to obtain the parameters of the entire neural network.

[0087] According to the second notification mode, the jointly trained AI model pair can be particularly suitable for performing paired operations on the data to be notified, such as encoding and decoding, modulation and demodulation, compression and decompression, etc. In particular, the jointly trained AI model pair can be particularly suitable for performing joint source-channel coding (JSCC) on the data to be notified. It is known to those skilled in the art that the purpose of source coding is to remove redundant information in the data to be transmitted in order to improve the effectiveness of data transmission, while the purpose of channel coding is to add redundant information to the data to be transmitted to realize functions such as detection and error correction, thereby improving the reliability of data transmission. However, the design ideas of these two codings are to remove redundant information and add redundant information, respectively, and are therefore opposite. If the source coding and channel coding are designed separately in the traditional way, it is difficult to obtain the optimal solution. Therefore, a joint coding scheme called JSCC is proposed. In JSCC, the AI ​​model can be used to jointly design at least the source coding and channel coding, so that the end-to-end transmission performance of the wireless communication system is optimized. In some JSCC schemes, the AI ​​model can also jointly design source coding, channel coding, and modulation, so that the transmitter can use the AI ​​model to output a modulated signal that can be directly sent, and the receiver can use the AI ​​model to directly decode the data that the transmitter wants to notify from the received signal.

[0088] Returning to FIG. 3 again, after the sending end notifies the receiving end of data using one of the determined notification modes at S304 , the operation of the sending end ends at S306 .

[0089] It should be noted that the operation steps of the transmitting end shown in Figure 3 are merely schematic. In practice, the operation of the transmitting end may also include some additional or alternative steps. For example, as mentioned in the above description, before S304, the transmitting end may deploy at least one AI model for subsequent notification data use. For another example, before S304, the transmitting end may determine which notification mode to use and determine which AI model to use. In some cases, the transmitting end may also signal the receiving end to notify the notification mode and / or AI model to be used for data notification, or the transmitting end may receive information from the receiving end notifying the notification mode and / or AI model to be used for data notification.

[0090] The structure and operation flow of the receiving end according to the first embodiment of the present disclosure

[0091] The above describes in detail the exemplary structure and exemplary operation of the transmitting end according to the present disclosure. Next, the exemplary structure and exemplary operation flow of the receiving end device according to the present disclosure will be described in conjunction with Figures 5 and 6.

[0092] The electronic device 50 shown in Figure 5 may include various units to implement the corresponding operations according to the first embodiment of the present disclosure. In this example, the electronic device 50 includes a communication unit 502 and a control unit 504. According to the present disclosure, the electronic device 50 may be a control device or a terminal device serving as a receiving end. In one embodiment, the electronic device 50 is implemented as a control device or a terminal device serving as a receiving end, or as a part thereof, or is implemented as a device or a part of a device for controlling a control device or a terminal device serving as a receiving end or otherwise related thereto. The various operations described below in conjunction with the transmitting end may be implemented by units 502, 504 or other possible units of the electronic device 50.

[0093] As shown in FIG5 , the electronic device 50 may include a communication unit 502. The communication unit 502 may be configured to receive data from another electronic device. For example, the received data may be any data notified by the transmitting end to the receiving end according to the corresponding communication scenario, such as, but not limited to, channel state information (CSI), video data, sensor data, etc. More generally, the communication unit 502 may be configured to send signals to or receive signals from other electronic devices (such as service data, control signaling, and any other signals that need to be sent between electronic devices).

[0094] The electronic device 50 may also include a control unit 504. The control unit 504 may be configured to control the communication unit 502 to adopt one of the following notification modes to obtain data to be notified by the transmitting electronic device: a first notification mode configured to transmit or receive the data using an AI model deployed on one side of the electronic device 50 or the transmitting electronic device; a second notification mode configured to transmit and receive the data using a pair of jointly trained AI models deployed on both the electronic device 50 and the transmitting electronic device; and a third notification mode configured to transmit the data from the transmitting electronic device to the electronic device 50 when neither the electronic device 50 nor the transmitting electronic device utilizes an AI model for notifying the data. For example, the control unit 504 may be configured to determine the notification model and / or AI model to be used based on indication information received via the communication unit 502. Alternatively, the control unit 504 may be configured to select a notification model and / or AI model and control the communication unit 502 to notify the transmitting electronic device of the notification model and / or AI model to be used. More generally, the control unit 204 may be configured to perform any appropriate control on the electronic device required to enable it to complete the corresponding operation.

[0095] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, rather than being used to limit specific implementation methods, for example, they can be implemented in software, hardware or a combination of software and hardware. The functions of the units disclosed herein can be implemented using circuits or processing circuits. Processing circuits can refer to various implementations of digital circuit systems, analog circuit systems or mixed signal (a combination of analog and digital) circuit systems that perform functions in a computing system. Processing circuits can include, for example, circuits such as integrated circuits (ICs), application specific integrated circuits (ASICs), parts or circuits of separate processor cores, entire processor cores, separate processors, programmable hardware devices such as field programmable gate arrays (FPGAs), and / or systems including multiple processors. Processors are considered to be processing circuits or circuits because they include transistors and other circuits therein.

[0096] In the present disclosure, a circuit, unit, device or apparatus is hardware that performs or is programmed to perform the function. The hardware can be any hardware disclosed herein or otherwise known to be programmed or configured to perform the function. When the hardware is a processor that can be considered as a type of circuit, the circuit, device or unit is a combination of hardware and software, and the software is used to configure the hardware and / or processor. In the implementation of hardware, the hardware can be programmed or configured to perform the function. In the implementation of software or a combination of software and hardware, the software can be used to configure the hardware and / or processor. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.).

[0097] Next, various operations performed by the electronic device 50 as the receiving end will be described in detail with reference to the conceptual operation flow 60 of the transmitting end shown in FIG. 6 .

[0098] The operation of the receiving end starts at S602.

[0099] At S604, the receiving end obtains data to be notified by the sending end, and the data is notified through one of the following notification modes: a first notification mode, configured to use an AI model deployed on one side of the receiving end or the sending end to send or receive the data; a second notification mode, configured to use a pair of jointly trained AI models deployed on both sides of the receiving end and the sending end to send and receive the data; and a third notification mode, configured to send the data from the sending end to the receiving end when neither the receiving end nor the sending end uses the AI ​​model for notifying the data.

[0100] In S604, specifically, the receiving end may first determine which notification mode to use to obtain the data to be notified by the sending end. For example, the receiving end may receive indication information from the sending end indicating the notification mode to be used next. In this case, the sending end selects one of the notification modes from the above three notification modes based at least on the communication indicator, as described above with reference to FIG3 , and notifies the receiving end of the selected notification mode. For another example, the notification mode to be used may also be selected by the receiving end. For example, the receiving end may select the notification mode to be used based at least on the communication indicator in a similar manner as described above with reference to FIG3 , and notify the sending end of its selected notification mode. The specific method for selecting the notification mode has been described in detail above and will not be repeated here. For another example, the notification mode to be used may also be a default one, for example, based on a pre-agreed agreement between the two parties, or based on a predetermined association between a specific communication scenario and a notification mode.

[0101] The receiving end may also deploy at least one AI model for the first notification mode and / or the second notification mode before S604.

[0102] As explained above, the first notification mode can be configured as any one of the following modes: mode (1) deploying the AI ​​model at the sending end, the sending end using the deployed AI model to process the data to be notified to the receiving end and sending the processed data to the receiving end, mode (2) deploying the AI ​​model at the receiving end, the receiving end using the deployed AI model to receive the data to be notified to the receiving end from the sending end, and (3) deploying the AI ​​model at the receiving end, the receiving end using the deployed AI model to predict the data based on historical data related to the data to be notified to the receiving end.

[0103] In the case where the receiving end determines at S604 that the first notification mode is to be used, the receiving end may further determine which of the three sub-modes to use to obtain the data to be notified by the transmitting end. For example, the receiving end may receive indication information from the transmitting end indicating which sub-mode to use. As described in detail above, which sub-mode to use may be determined at least based on the communication scenario and the AI ​​model deployment situation of the transmitting end and the receiving end. For another example, the receiving end may also use a similar method to determine which sub-mode to use and send indication information to the transmitting end. For another example, which sub-mode to use may also be a default or preset according to the communication scenario and / or the AI ​​model deployment situation of the transmitting end and the receiving end (for example, in previous communications, the transmitting end and the receiving end have already understood each other's AI model deployment situation).

[0104] As described in detail above, the second notification mode can be configured such that the transmitting end uses the first AI model of a pair of jointly trained AI models to process the data to be notified to the receiving end and transmits the processed data to the receiving end, and the receiving end uses the second AI model of the pair of AI models to reconstruct the data based on the processed data received from the transmitting end. The AI ​​model to be deployed by the receiving end in the second notification mode has been described above and will not be repeated here.

[0105] After the receiving end obtains the data to be notified by the transmitting end using one of the determined notification modes at S604 , the operation of the receiving end ends at S606 .

[0106] It should be noted that the operating steps of the receiving end shown in Figure 6 are merely schematic. In practice, the operation of the receiving end may also include some additional or alternative steps. For example, as mentioned in the above description, before S604, the receiving end may deploy at least one AI model for subsequent notification data use. For another example, before S604, the sending end may determine which notification mode to use and determine which AI model to use. In some cases, the receiving end may also signal the sending end to notify the notification mode and / or AI model to be used for data notification, or the receiving end may receive information from the sending end notifying the notification mode and / or AI model to be used for data notification.

[0107] A first exemplary implementation of the first embodiment of the present disclosure

[0108] Below, a first example implementation of applying the solution of the first embodiment to a CSI feedback scenario will be described with reference to FIG. 7 to FIG. 10 .

[0109] In a first exemplary implementation, the data that the transmitting end wants to notify the receiving end may be channel state information (CSI) feedback. In this first exemplary implementation, for example, the transmitting end may be a user equipment UE, and the receiving end may be a base station BS.

[0110] As shown in FIG7 , first, the transmitter and receiver can determine the queue length of communication data to be sent to the receiver. For example, the transmitter determines the queue length of communication data waiting to be sent to the receiver. In some cases (e.g., when the receiver, i.e., the base station, determines which notification mode to use based on the queue length), the transmitter can send the determined queue length of communication data to the receiver. For example, any suitable channel / signaling / message can be used to send information indicating the queue length, such as via a physical uplink control channel (PUCCH).

[0111] Next, the transmitter and / or receiver can determine the notification mode to use based on the queue length. In this example implementation, this determination can be made by either the transmitter or the receiver based on the queue length. For example, after either the transmitter or the receiver determines the notification mode, the transmitter or the receiver can send indication information indicating the determined notification mode to the other. Specifically, for example, after determining the queue length of communication data to be sent to the receiver, the transmitter can determine which notification mode to use for CSI feedback based on the queue length and send indication information indicating which notification mode to use for CSI feedback to the receiver. Alternatively, the transmitter can send information indicating the queue length to the receiver and receive indication information from the receiver indicating which notification mode to use for CSI feedback. In the latter case, the indication information is determined based on the queue length. For example, the indication information indicating the notification mode can be sent using any applicable channel / signaling / message, such as via a physical uplink control channel (PUCCH) or downlink control information (DCI).

[0112] The following describes in detail the process of determining the notification mode in the first exemplary implementation of the first embodiment.

[0113] In wireless communications, especially for communication scenarios that require low latency and high energy efficiency (such as XR scenarios), scheduling across the application layer, data layer, and physical layer is usually considered to minimize the average queuing delay of data when the average data transmission power consumption is limited. In cross-layer scheduling, there are already scheduling algorithms that compromise between latency and power consumption. For example, this algorithm will use higher power for transmission when the channel conditions are poor and lower power for transmission when the channel conditions are good. It will also use low power for transmission and adopt a coding and modulation scheme with low transmission rate and high packet loss tolerance when the queue length of communication data waiting to be sent is short, and use high power for transmission and adopt a coding and modulation scheme with high transmission rate and low packet loss tolerance when the queue length of communication data waiting to be sent is long.

[0114] For example, in this cross-layer scheduling, the longer the queue of communication data waiting to be sent, the more data packets are sent within a transmission time slot. Therefore, a more accurate estimation of the wireless channel state is required within the transmission time slot to ensure data transmission performance (for example, the trade-off between latency and power consumption). In wireless communications, channel state estimation is generally performed by user equipment (UE) providing CSI feedback. However, providing high-precision channel state estimation requires the UE to feedback a large amount of information, resulting in high communication overhead. Therefore, it is necessary to reasonably and dynamically adjust the accuracy of the channel state information estimation to minimize communication overhead.

[0115] In view of the above, the present disclosure proposes that the longer the queue length of communication data waiting to be sent, the higher the accuracy of channel estimation is adopted, and the shorter the queue length, the lower the accuracy of channel estimation is adopted, thereby controlling the overhead brought by channel estimation as a whole.

[0116] In this first exemplary implementation of the first embodiment of the present disclosure, it is considered to control the accuracy of channel estimation by notifying CSI feedback in different notification modes.

[0117] Specifically, in this example implementation, in the first notification mode, for example, an AI model for estimating the channel state data of the current transmission time slot (i.e., current CSI feedback) based at least on the channel state data for historical transmission time slots (i.e., historical CSI feedback) can be deployed at the receiving end. Figures 8A and 8B respectively illustrate the first notification mode of this first example implementation and the interaction between the transmitting end and the receiving end using the first notification mode.

[0118] For example, such an AI model can predict the current CSI feedback based only on the historical CSI feedback data. As shown in FIG8A , assuming that the current transmission time slot is n, and the CSI feedback data is represented as The input of this AI model deployed at the receiving end can be a series of historical CSI feedback data: Where T can represent the number of CSI feedbacks in the historical transmission time slot to be used, and the output of the AI ​​model can be the CSI feedback data of the current transmission time slot predicted by the model. In this case, the communication overhead introduced by channel estimation in the current transmission time slot can be zero. This situation can also be considered as the CSI feedback to be notified by the transmitter to the receiver being implicitly notified based on the AI ​​model at the receiver. For another example, this AI model can also estimate the current CSI feedback based on historical CSI feedback data and a small amount of data sent by the transmitter for the current channel state. In this case, the small amount of data sent by the transmitter can be any appropriate data to assist in predicting the current CSI feedback.

[0119] Because the receiving end obtains CSI feedback based on the AI ​​model's predictions in this first notification mode, the channel estimation accuracy is low. Therefore, this first notification mode is suitable for situations where the queue length of communication data waiting to be sent is short. In other words, when the queue length is less than or equal to the first threshold, the receiving end obtains CSI feedback based on the first notification mode.

[0120] As shown in Figure 8B, in the first notification mode, for example, the transmitter can send information to the receiver indicating the queue length of the communication data it has determined to be sent to the receiver, so that the receiver can determine whether to use the first notification mode based on the queue length and enable the corresponding AI model to predict CSI feedback. In this case, the first threshold used to determine whether to enable the first notification mode based on the queue length can be predetermined or agreed upon by the transmitter and the receiver in previous communications. Alternatively, after the receiver determines to use the first notification mode based on the queue length, it can also signal the transmitter to inform it that it will use the first notification model to predict CSI feedback.

[0121] For another example, after determining the queue length, the transmitting end may determine to use the first notification mode based on the queue length, and explicitly notify the receiving end that the first notification mode is to be used, so that the receiving end enables the corresponding AI model to predict CSI feedback.

[0122] In the case where the AI ​​model deployed at the receiving end requires a small amount of channel state information for auxiliary prediction from the sending end, the receiving end can request this data from the sending end, or, based on a pre-agreed agreement or configuration, the sending end can also actively send this data to the receiving end without the receiving end's request.

[0123] In a first example implementation, in the second notification mode, for example, a pair of jointly trained AI models for determining the channel state data (i.e., current CSI feedback) for the current transmission time slot can be deployed on both the transmitting and receiving ends. Figures 9A and 9B respectively illustrate the second notification mode of the first example implementation and the interaction between the transmitting and receiving ends using the second notification mode.

[0124] For example, the first AI model in the pair of AI models may be deployed at the transmitter. The first AI model may process the CSI feedback data (e.g., compress the CSI feedback data, or perform joint coding including source coding, channel coding, and modulation on the CSI feedback data, or perform both compression and joint coding on the CSI feedback data) to generate processed feedback data. The transmitter may send the processed feedback data to the receiver via any appropriate channel / signaling (e.g., PUCCH). The receiver may deploy the second AI model in the pair of AI models. The second AI model may process the received data (e.g., decompress the CSI feedback data, or perform joint decoding including source decoding, channel decoding, and demodulation on the received data, or perform both decompression and joint decoding on the received data) to reconstruct the CSI feedback that the transmitter intends to notify the receiver.

[0125] In this example implementation, the AI ​​model pair deployed at the transmitter and receiver can be any jointly trained AI model pair suitable for CSI feedback transmission. For example, such an AI model pair can perform more complex processing on the CSI feedback data, thereby reducing the communication overhead of transmitting the processed CSI feedback data and improving the reconstruction accuracy. For example, as shown in Figure 9A, the first AI model in the pair of AI models deployed at the transmitter can take not only the CSI feedback data of the current transmission time slot as input, but also the CSI feedback data of historical transmission time slots as input. For example, assuming that the current transmission time slot is n and the CSI feedback data is represented as h[n], then the input of the first AI model deployed at the transmitter can be the CSI feedback data of the current transmission time slot together with a series of historical CSI feedback data: h[nT], h[n-T+1], ..., h[n-1], h[n], where T can represent the number of CSI feedbacks in the historical transmission time slots to be used. After being processed by the first AI model, the processed data outputted from the first AI model may be a very small amount of data, for example, only 2 or 4 bits of data. The second AI model deployed at the receiving end can process the very small amount of processed data received from the transmitting end, thereby reconstructing the CSI feedback that the transmitting end intends to notify the receiving end.

[0126] In the second notification mode, although the transmitter does not directly send the CSI feedback itself to the receiver, the actual CSI feedback of the current transmission time slot is processed using the jointly trained AI model. Therefore, the accuracy of the channel estimation is higher than that of the first notification mode, but lower than the third notification mode described below in which the actual CSI feedback is sent directly from the transmitter to the receiver. Therefore, this second notification mode is suitable for situations where the queue length of the communication data waiting to be sent is medium. In other words, when the queue length is greater than the first threshold and less than or equal to the second threshold, the transmitter uses the second notification mode to notify the receiver of the CSI feedback.

[0127] As shown in Figure 9B , in the second notification mode, first, similar to the first notification mode shown in Figure 8B , the transmitting end can send information indicating the queue length of communication data to be sent to the receiving end to the receiving end, so that the receiving end can determine whether to use the second notification mode based on the queue length and enable the corresponding AI model to process CSI feedback. Alternatively, after determining to use the second notification mode based on the queue length, the transmitting end can explicitly notify the receiving end of the use of the second notification mode, so that the receiving end can enable the corresponding AI model to process CSI feedback.

[0128] Subsequently, i.e., after determining to enable the second notification mode, the receiving end can send a channel state information reference signal (CSI-RS) to the transmitting end. The transmitting end can then estimate the channel state based on the received CSI-RS, i.e., calculate CSI feedback, and process the CSI feedback using the first AI model in the jointly trained pair of AI models.

[0129] The transmitting end may then send the processed CSI feedback data to the receiving end, and the receiving end may process the received data using the second AI model in the pair of AI models to reconstruct the CSI feedback for the current transmission time slot.

[0130] In the first example implementation, in the third notification mode, no AI model may be used, and CSI feedback may be sent from the transmitter to the receiver in a traditional manner. Figures 10A and 10B illustrate the third notification mode of the first example implementation and the interaction between the transmitter and receiver using the first notification mode, respectively.

[0131] For example, the receiving end can send a CSI-RS to the transmitting end. The transmitting end can estimate the channel state based on the received CSI-RS, that is, calculate CSI feedback. As shown in Figure 10A, assuming the current transmission time slot is n, the CSI feedback calculated by the transmitting end can be represented as a vector h[n] of length L bits. The transmitting end can directly send this vector to the receiving end via any appropriate channel / signaling (e.g., the PUCCH channel).

[0132] Because the actual CSI feedback is sent directly to the receiving end in the third notification mode, channel estimation accuracy is maximized. Therefore, this third notification mode is suitable for situations where the queue length of communication data waiting to be sent is long. In other words, when the queue length is greater than the second threshold, the transmitting end uses the third notification mode to send CSI feedback to the receiving end.

[0133] As shown in Figure 10B, in the third notification mode, first, similar to the first notification mode shown in Figure 8B and the second notification mode shown in Figure 9B, the transmitting end can send information indicating the queue length of the communication data to be sent to the receiving end to the receiving end, so that the receiving end can determine whether to use the second notification mode based on the queue length and enable the corresponding AI model to process CSI feedback. Alternatively, after determining to use the second notification mode based on the queue length, the transmitting end can explicitly notify the receiving end of the use of the second notification mode, so that the receiving end can enable the corresponding AI model to process CSI feedback.

[0134] Afterwards, that is, after determining to enable the third notification mode, the receiving end may send a CSI-RS to the transmitting end. Next, the transmitting end may estimate the channel state based on the received CSI-RS, that is, calculate CSI feedback.

[0135] Next, the transmitter can directly send the calculated CSI feedback to the receiver.

[0136] A second exemplary implementation of the first embodiment of the present disclosure

[0137] Next, a second example implementation in which the solution of the first embodiment is applied to a scenario of video data transmission will be described with reference to FIG. 11 .

[0138] In a second exemplary implementation, the data that the transmitting end wants to notify the receiving end may be video data.

[0139] As shown in Figure 11, the transmitting end and the receiving end can first determine the transmission delay of data transmitted from the transmitting end to the receiving end. For example, the transmitting end can measure the transmission delay. In another example, the receiving end can also measure the transmission delay. In the latter case, the receiving end can send the measured transmission delay to the transmitting end.

[0140] Next, the sending end and / or the receiving end may determine the notification mode to use based on the transmission delay. In this example implementation, either the sending end or the receiving end may make this determination based on the transmission delay. For example, after either the sending end or the receiving end determines the notification mode, that end may send indication information indicating the determined notification mode to the other end.

[0141] The following describes in detail the process of determining the notification mode in the second exemplary implementation of the first embodiment.

[0142] In this example implementation, in the first notification mode, for example, the AI ​​model deployed at the transmitting end may be an AI model that compresses video data, extracts key information (for example, extracts key frames or key pixels in a frame), reduces redundant information (for example, removes some frames or certain pixels in a frame), adds additional information (for example, metadata information related to video encoding and decoding), etc. For another example, the AI ​​model deployed at the transmitting end may also be a model that encodes and / or modulates the video data in an AI manner. For example, the AI ​​model deployed at the receiving end may be an AI model that decompresses the data received from the transmitting end, predicts the complete data to be notified based on the data received from the transmitting end (for example, predicts a complete frame sequence or a complete frame based on a partial frame or partial pixels in a frame sent by the transmitting end), etc. For another example, the AI ​​model deployed at the receiving end may also be a model that decodes and / or demodulates the received data in an AI manner.

[0143] In this example implementation, in the second notification mode, the jointly trained AI model pair deployed on both the transmitting and receiving ends can be an AI model pair that performs paired operations on video data, such as encoding and decoding, modulation and demodulation, compression and decompression, etc. In particular, in the second notification mode, the jointly trained AI model pair deployed on both the transmitting and receiving ends can be the AI ​​model pair for JSCC described above.

[0144] In this example implementation, in the third notification mode, the transmitting end and the receiving end transmit video data according to traditional video coding and decoding technology.

[0145] In video data transmission scenarios, traditional video codec technologies can result in significant transmission latency due to their relatively complex computations. However, traditional video codec technologies can be lossless, thus ensuring high data transmission reliability. When deploying AI models on either the transmitter or receiver to transmit video data, the AI ​​model design may not guarantee lossless encoding and decoding of the video data. In particular, when the AI ​​model is used to compress / decompress the transmitted video data, delete some information, or perform predictions on at least part of the video data, the receiver may be unable to receive or reconstruct the original video data. Therefore, deploying AI models on either the transmitter or receiver to transmit video data may reduce data transmission reliability. However, AI models can quickly generate or reconstruct video data for transmission, thereby reducing end-to-end transmission latency. In addition, when the AI ​​model is deployed only on the sending end or the receiving end, due to the lack of a joint training process for data on both the sending end and the receiving end, some related information between the sending end and the receiving end is lost when generating the AI ​​model, and / or due to the data prediction processing / redundant information deletion processing introduced by this unilaterally deployed AI model, errors may occur. Therefore, the data transmission accuracy of the first notification model in which the AI ​​model is deployed on one side may be lower than the data transmission accuracy of the second notification mode in which the AI ​​model is deployed on both the sending end and the receiving end.

[0146] Taking the above factors into consideration, in response to the transmission delay being less than or equal to the first threshold, in other words, in response to the transmission delay being relatively small, the transmitting end may use the third notification mode to send video data to the receiving end. In response to the transmission delay being greater than the first threshold and less than or equal to the second threshold, in other words, in response to the transmission delay being medium, the transmitting end may use the second notification mode to notify the receiving end of the video data. In response to the transmission delay being greater than the second threshold, in other words, in response to the transmission delay being relatively large, the receiving end may obtain the video data based on the first notification mode. For example, as described above, the receiving end may predict a complete frame sequence and / or all pixels in a frame based on a partial frame and / or a partial pixel in a frame received from the transmitting end.

[0147] The first embodiment of the present disclosure has been described with reference to Figures 2-11. With the aid of the solution of this first embodiment, the notification mode most suitable for current communication needs can be selected to notify data from the sending end to the receiving end, thereby better meeting the more flexible requirements of various communication indicators. Preferably, the notification mode to be used can be dynamically adjusted during the communication process, thereby more flexibly adapting to real-time changes in communication indicator requirements.

[0148] Second embodiment

[0149] In the description of the first embodiment above, the second notification mode is described in detail, in which a jointly trained AI model pair is deployed on both the transmitter and receiver sides to notify data. In practice, there are many communication scenarios in which a group of transmitters sends data to a single receiver. For example, the group of transmitters may include one or more transmitter devices. Below, two exemplary communication scenarios in this case are first described with reference to Figures 12A and 12B.

[0150] FIG12A shows a scenario such as a live broadcast of a sports event. In this scenario, multiple cameras can be arranged around a sports stadium, each of which captures images from a specific angle. The images captured by these cameras can first be sent to a TV station / director's studio. Subsequently, the most appropriate image can be selected from these images from different angles and sent to the user terminal. For example, the images to be selected can be images that the user may be interested in, such as images of key players with football, images of players competing against each other, close-up images of coaches / audience members, and the like.

[0151] Figure 12B shows a scenario for a smart connected car. In this scenario, the vehicle can be equipped with multiple sensors, such as image sensors, LiDAR, and mmWave radar. These sensors can act as different transmitters to send their captured information to the vehicle's control device. The vehicle's control device can then select appropriate information from this information for operations such as presenting images of the vehicle's surroundings and measuring the distance between the vehicle and other objects.

[0152] In the scenario illustrated in Figures 12A and 12B , where a group of transmitters transmit data to a receiver, the data most important to the receiver may be data sent by only one or a few of the transmitters in the group. For example, in the scenario of Figure 12A , the data most important to the receiver may be data sent by the camera that captures the most suitable image for playback to the user. In the scenario of Figure 12B , the data most important to the receiver may be data sent by the sensor that captures the most accurate information based on the current climate, lighting conditions, etc. If each transmitter in the group transmits the highest quality data (e.g., optimal image quality for video data (such as using a high frame rate (e.g., 60 FPS) and a high resolution (e.g., 4K)), or the highest numerical accuracy for sensor data) to the receiver, unnecessary resource consumption and / or latency may result.

[0153] Therefore, it is possible to consider deploying different jointly trained AI model pairs between each sender and receiver in this group of senders. These AI model pairs can be suitable for, for example, processed data with different data volumes and / or data accuracy generated by the sender, and suitable for reconstructing data with, for example, different data accuracy and / or data quality by the receiver, thereby enabling flexible control of data transmission from a group of sender devices to receiver devices.

[0154] Specifically, according to the second embodiment of the present disclosure, a group of transmitters can send data to a receiver. The group of transmitter devices may include one or more transmitter devices, and multiple jointly trained AI model pairs are deployed on both sides of each transmitter and receiver. Each transmitter can use a first AI model in a first AI model pair selected from the multiple AI model pairs to process data to be sent to the receiver and send the processed data to the receiver, so that the receiver uses a second AI model in the first AI model pair to reconstruct the data based on the processed data received from the receiver.

[0155] The second embodiment will be described in detail below with reference to FIG. 13 to FIG. 19 .

[0156] The structure and operation flow of the transmitting end according to the second embodiment of the present disclosure

[0157] First, the conceptual structure of the electronic device 130 for the transmitting end according to an embodiment of the present disclosure will be described with reference to Figure 13. The electronic device 130 shown in Figure 13 may include various units to implement the corresponding operations according to the first embodiment of the present disclosure. In this example, the electronic device 130 includes a communication unit 13002 and a control unit 13004. According to the present disclosure, the electronic device 130 may be a control device or a terminal device serving as a transmitting end. In one embodiment, the electronic device 130 is implemented as the control device or the terminal device serving as the transmitting end itself or a part thereof, or is implemented as a device or a part of the device for controlling the control device or the terminal device serving as the transmitting end or otherwise related thereto. The various operations described below in conjunction with the transmitting end may be implemented by units 13002, 13004 or other possible units of the electronic device 130.

[0158] As shown in Figure 13, similar to the first embodiment, the electronic device 130 may include a communication unit 13002. The communication unit 13002 may be configured to send data to another electronic device. For example, the data to be sent may be any data that needs to be notified by the transmitting end to the receiving end according to the corresponding communication scenario, such as but not limited to video data, sensor data, etc. For another example, the communication unit 13002 may also be configured to receive information from another electronic device indicating the priority of the electronic device 130 in a group of electronic devices serving as the transmitting end. For another example, the communication unit 13002 may also be configured to receive feedback information from another electronic device indicating the accuracy of processing and reconstructing data using a certain AI model. More generally, the communication unit 13002 may be configured to send signals to other electronic devices or receive signals from other electronic devices (such as business data, control signaling, and any other signals that need to be sent between electronic devices).

[0159] The electronic device 130 may further include a control unit 13004. The control unit 13004 may be configured to select a first AI model pair from a plurality of AI model pairs, and then control the communication unit 13004 to use the first AI model in the first AI model pair to process data to be sent to another electronic device and send the processed data to the other electronic device, so that the other electronic device uses the second AI model in the first AI model pair to reconstruct the data based on the processed data received from the electronic device 130. For example, the control unit 13004 may be configured to notify the other electronic device as the receiving end of at least the ID of the selected AI model pair and the sending parameters of the event that enables the model pair. Alternatively, the control unit 13004 may be configured to be based on the sending parameter information indicating the sending parameters received via the communication unit 13002. More generally, the control unit 13004 may be configured to perform any appropriate control on the electronic device required to enable it to complete the corresponding operation.

[0160] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, rather than being used to limit specific implementation methods, for example, they can be implemented in software, hardware or a combination of software and hardware. The functions of the units disclosed herein can be implemented using circuits or processing circuits. Processing circuits can refer to various implementations of digital circuit systems, analog circuit systems or mixed signal (a combination of analog and digital) circuit systems that perform functions in a computing system. Processing circuits can include, for example, circuits such as integrated circuits (ICs), application specific integrated circuits (ASICs), parts or circuits of separate processor cores, entire processor cores, separate processors, programmable hardware devices such as field programmable gate arrays (FPGAs), and / or systems including multiple processors. Processors are considered to be processing circuits or circuits because they include transistors and other circuits therein.

[0161] In the present disclosure, a circuit, unit, device or apparatus is hardware that performs or is programmed to perform the function. The hardware can be any hardware disclosed herein or otherwise known to be programmed or configured to perform the function. When the hardware is a processor that can be considered as a type of circuit, the circuit, device or unit is a combination of hardware and software, and the software is used to configure the hardware and / or processor. In the implementation of hardware, the hardware can be programmed or configured to perform the function. In the implementation of software or a combination of software and hardware, the software can be used to configure the hardware and / or processor. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.).

[0162] Next, various operations performed by the electronic device 130 as the transmitting end will be described in detail with reference to the conceptual operation flow 140 of the transmitting end shown in FIG. 14 .

[0163] The operation of the sending end starts at S1402.

[0164] At S1404 , the transmitting end determines which AI model pair among the multiple AI model pairs to use to transmit data.

[0165] According to one example implementation, an AI model pair may be selected based on a priority of a transmitter within a group of transmitters. For example, the priority of a transmitter may be determined based on at least one of the following: a communication scenario between a group of transmitter devices to which the transmitter belongs and a receiver, and the importance of data sent by each transmitter in the group of transmitter devices to the receiver.

[0166] For example, a priority level for each transmitter in a group of transmitter devices may be pre-assigned. For example, such a priority level may be pre-specified by the transmitter or receiver based on various factors, or pre-negotiated between the transmitter and receiver. For example, such factors may include at least the communication scenario and / or the transmitter's device attributes (e.g., data transmission performance, such as the device's inherent transmission accuracy, inherent processing speed, etc.).

[0167] For another example, the receiving end can determine the difference in importance between the data sent by each transmitting end, and then feedback the priority of the transmitting end determined based on the importance of the data to each transmitting end. For example, the receiving end can use any suitable method to determine the importance of the received data. In particular, in some application scenarios, any suitable artificial intelligence / machine learning model can be used to determine the importance of different data. For example, in the scenario of video transmission, any suitable artificial intelligence / machine learning model can be used to determine whether the data sent by a certain transmitting end indicates whether the current picture is a picture of interest to the user (such as determining whether the current picture includes a key player with football, whether it includes a player confrontation, etc.). For example, the higher the importance of the data, the higher the priority of the transmitting end. After determining the priority of the transmitting end, the receiving end can feedback the determined priority to the transmitting end. For example, the receiving end can use any suitable signaling to perform such feedback, such as via uplink control information (UCI).

[0168] Preferably, the priority of the sender can be determined dynamically, for example, in real time or regularly based on the current communication scenario and / or the importance of the data sent by each sender.

[0169] According to the above example implementation, either the transmitter or receiver can determine the AI ​​model pair to use based on the transmitter's priority. For example, a transmitter with a higher priority can use an AI model pair with better performance, while a transmitter with a lower priority can use an AI model pair with lower performance. Specifically, the performance of an AI model pair can be evaluated based on the amount of data output by the AI ​​model used at the transmitter, and / or the accuracy of the data reconstructed by the AI ​​model used at the receiver, and / or the processing speed of the AI ​​model. For example, a high-performance AI model pair allows a small amount of data to be transmitted between the transmitter and receiver, while reconstructing data that is substantially identical to the original data. For example, for video transmission, a high-performance AI model pair allows a large 60FPS, 4K video frame sequence input at the transmitter to be processed at a faster speed into a relatively small amount of data, thereby utilizing fewer communication resources for transmission and achieving shorter latency. Furthermore, the high-performance AI model allows the receiver to reconstruct a 60FPS, 4K video frame sequence based on the smaller amount of data, which is substantially lossless compared to the original 60FPS, 4K video frame sequence. For example, for sensor data transmission, a high-performance AI model pair allows the input sensor data to be processed at a faster speed at the transmitting end, and allows the sensor data to be reconstructed at the receiving end based on the received data with substantially no loss in accuracy compared to the original sensor data. Conversely, a low-performance AI model pair may generate a large amount of data at the transmitting end, or may require low-quality data input at the transmitting end (e.g., low-resolution video data or low-precision sensor data), or may reconstruct data with low accuracy at the receiving end, or may also process data at a slower speed.

[0170] It should be noted that it is not necessarily optimal for the sender to use high-performance AI models indiscriminately. For example, a high-performance AI model may consume more power, occupy more storage space, or occupy more computing power during operation. Therefore, when the priority of the sender is low, it may be more optimal to use a low-performance AI model to reduce unnecessary consumption of power, storage, and / or computing power. Therefore, the present disclosure proposes to use high-performance AI models only for senders with higher priorities.

[0171] According to another example implementation, the AI ​​model pair may be selected based on the accuracy of the reconstructed data fed back by the receiving end to the transmitting end. For example, the accuracy may include any one or a combination of the following: a verification result of the reconstructed data, and an accuracy rate calculated based on a comparison between the data sent by the transmitting end and the reconstructed data.

[0172] Specifically, each transmitting end can send data processed by the first AI model in a pair of AI models to the receiving end. After receiving the processed data, the receiving end can calculate the reconstruction accuracy of the data reconstructed using the second AI model in the pair of AI models. The data here can be data that the transmitting end wants to send to the receiving end (for example, video data, sensor data, etc.), or it can be data specifically used to determine the reconstruction accuracy of the data.

[0173] According to an example, the receiving end can simply use any appropriate verification method to verify the reconstructed data. Verification methods include, for example, cyclic redundancy check (CRC), MD5 check, hash check, etc. For example, the data sequence input by the sending end to the first AI model can be expressed as z=(z1, z2, ..., z n ), the data sequence output from the second AI model at the receiving end can be expressed as z=(`z1,`z2,…,`z n ). The receiving end can use any appropriate verification method to determine the number of data that have passed the verification and the number of data that have failed the verification in the data sequence output by the second AI model, and can calculate the ratio of the number of data that have passed the verification to the number of data in the data sequence as the reconstruction accuracy. For example, assuming that the length of the data sequence is n, and the number of data that have passed the verification in the data sequence output by the second AI model is n1, then the reconstruction accuracy can be expressed as n1 / n. In this example, the reconstruction accuracy can be obtained without sending additional data between the sending end and the receiving end, so it is advantageous to avoid adding a large overhead between the sending end and the receiving end.

[0174] According to another example, the receiving end can calculate the comparison value between the data sent by the sending end and the reconstructed data, such as the minimum mean square error (MMSE) between the data reconstructed by the AI ​​model and the original data, and use it as the reconstruction accuracy. This method can calculate the reconstruction accuracy more accurately, but it requires the sending end to send the original data directly to the receiving end without going through the AI ​​model, which may incur additional communication overhead.

[0175] According to the above example implementation, the AI ​​model pair to be used can be determined by either the transmitting end or the receiving end based on the reconstruction accuracy. After determining the reconstruction accuracy, the receiving end can feedback the determined reconstruction accuracy to the transmitting end. The transmitting end can then determine whether to select the AI ​​model pair for subsequent data transmission based on whether the accuracy meets the expected value. For another example, after determining the reconstruction accuracy, the receiving end can also determine whether the accuracy meets the expected value by itself, and either feedback to the transmitting end information indicating whether to continue using the AI ​​model pair, or implicitly indicate to the transmitting end to continue using the AI ​​model pair by not providing any feedback.

[0176] Preferably, the reconstruction accuracy can be determined dynamically. For example, the receiving end can calculate the reconstruction accuracy of the currently used AI model pair in real time or periodically, and adjust the AI ​​model pair to be used in real time or periodically accordingly.

[0177] Two example implementations for determining the AI ​​model pair to be used have been described. According to a second embodiment, these two example implementations can be implemented in combination. For example, the AI ​​model pair to be used can be first determined based on the priority of each transmitter, and then the AI ​​model pair actually used by each transmitter and receiver can be adjusted according to the reconstruction accuracy, for example, to meet the reconstruction accuracy requirements between each transmitter and receiver. For another example, multiple applicable AI model pairs can be first selected based on the reconstruction accuracy, and then an AI model pair whose performance meets its priority can be selected from these multiple AI model pairs according to the priority of the transmitter. Of course, these two example implementations can also be combined to select an AI model pair in any other appropriate manner.

[0178] Continuing to refer to FIG. 14 , at S1406 , the transmitting end may use the determined AI model to process and transmit data.

[0179] For example, during S1404 determining which AI model to use to transmit data, the transmitting end may directly use the corresponding AI model to transmit data based on the priority and / or data reconstruction accuracy fed back from the receiving end, based on a predetermined correspondence between the priority and / or data reconstruction accuracy and the AI ​​model pair. In other words, the transmitting end may directly use the predetermined corresponding AI model pair to transmit data based on the priority and / or data reconstruction accuracy without explicitly notifying the receiving end that the AI ​​model pair is to be enabled.

[0180] For another example, before S1406, the transmitting end may also send or receive transmission parameter information indicating the transmission parameters to the receiving end, and the transmission parameter information may include at least the ID of the selected AI model pair and information indicating the time when the AI ​​model pair is to be enabled, so that the indicated AI model pair is enabled at the indicated time to send data. In the case where the receiving end sends the transmission parameter information to the transmitting end, the transmission parameter information may be sent to the transmitting end together with information indicating the priority of the transmitting end determined by the receiving end and / or the data reconstruction accuracy. For example, the transmission parameter information can be sent using any appropriate signaling, such as radio resource control (RRC) signaling, uplink control information (UCI), or downlink control information (DCI).

[0181] The operation of the sending end ends at S1408.

[0182] It should be noted that the operation steps of the transmitting end shown in Figure 14 are merely schematic. In practice, the operation of the transmitting end may also include some additional or alternative steps. For example, as mentioned in the above description, between S1404 and S1406, the transmitting end may also send transmission parameter information to the receiving end or receive transmission parameter information from the receiving end. For another example, during S1406, the transmitting end may also perform operations with the receiving end for dynamically adjusting the AI ​​model pair to be used, such as the receiving end feeding back the updated transmitting end priority and / or data reconstruction accuracy to the transmitting end, and transmitting the updated transmission parameter information between the transmitting end and the receiving end to adjust the AI ​​model pair.

[0183] The structure and operation flow of the receiving end according to the second embodiment of the present disclosure

[0184] The exemplary structure and exemplary operation of the transmitting end according to the present disclosure are described in detail above. Next, the exemplary structure and exemplary operation flow of the receiving end device according to the present disclosure will be described in conjunction with Figures 15 and 16.

[0185] The electronic device 150 shown in Figure 15 may include various units to implement the corresponding operations according to the second embodiment of the present disclosure. In this example, the electronic device 150 includes a communication unit 1502 and a control unit 1504. According to the present disclosure, the electronic device 150 may be a control device or a terminal device serving as a receiving end. In one embodiment, the electronic device 150 is implemented as a control device or a terminal device serving as a receiving end, or as a part thereof, or is implemented as a device or a part of the device for controlling a control device or a terminal device serving as a receiving end or otherwise related thereto. The various operations described below in conjunction with the transmitting end may be implemented by units 1502, 1504 or other possible units of the electronic device 150.

[0186] As shown in Figure 15, similar to the first embodiment, the electronic device 150 may include a communication unit 1502. The communication unit 1502 may be configured to receive data from another electronic device. For example, the received data may be any data notified by the transmitting end to the receiving end according to the corresponding communication scenario, such as but not limited to video data, sensor data, etc. For another example, the communication unit 1502 may also be configured to send information indicating the priority of the other electronic device in a group of electronic devices serving as the transmitting end to another electronic device. For another example, the communication unit 1502 may also be configured to send feedback information indicating the accuracy of processing and reconstructing data using a certain AI model to another electronic device. More generally, the communication unit 1502 may be configured to send signals to other electronic devices or receive signals from other electronic devices (such as business data, control signaling, and any other signals that need to be sent between electronic devices).

[0187] The electronic device 150 may further include a control unit 504. The control unit 1504 may be configured to select a first AI model pair from a plurality of AI model pairs, and then control the communication unit 1504 to use the second AI model in the first AI model pair to process the data processed by the first AI model in the first AI model pair and sent from another electronic device, thereby reconstructing the data that the other electronic device intends to send to the electronic device 150. For example, the control unit 1504 may be configured to notify the other electronic device as a transmitting end of at least the sending parameters including the ID of the selected AI model pair and the event of enabling the model pair. Alternatively, the control unit 1504 may be configured to be based on the sending parameter information indicating the sending parameters received via the communication unit 1502. More generally, the control unit 1504 may be configured to perform any appropriate control on the electronic device required to enable it to complete the corresponding operation.

[0188] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, rather than being used to limit specific implementation methods, for example, they can be implemented in software, hardware or a combination of software and hardware. The functions of the units disclosed herein can be implemented using circuits or processing circuits. Processing circuits can refer to various implementations of digital circuit systems, analog circuit systems or mixed signal (a combination of analog and digital) circuit systems that perform functions in a computing system. Processing circuits can include, for example, circuits such as integrated circuits (ICs), application specific integrated circuits (ASICs), parts or circuits of separate processor cores, entire processor cores, separate processors, programmable hardware devices such as field programmable gate arrays (FPGAs), and / or systems including multiple processors. Processors are considered to be processing circuits or circuits because they include transistors and other circuits therein.

[0189] In the present disclosure, a circuit, unit, device or apparatus is hardware that performs or is programmed to perform the function. The hardware can be any hardware disclosed herein or otherwise known to be programmed or configured to perform the function. When the hardware is a processor that can be considered as a type of circuit, the circuit, device or unit is a combination of hardware and software, and the software is used to configure the hardware and / or processor. In the implementation of hardware, the hardware can be programmed or configured to perform the function. In the implementation of software or a combination of software and hardware, the software can be used to configure the hardware and / or processor. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.).

[0190] Next, various operations performed by the electronic device 150 as the receiving end will be described in detail with reference to the conceptual operation flow 160 of the receiving end shown in FIG. 16 .

[0191] The operation at the receiving end starts at S16002.

[0192] At S16004 , the receiving end determines which AI model pair among multiple AI model pairs to use to receive data.

[0193] In S16004, as described above, the AI ​​model pair may be determined based on the priority of the sender among a group of senders, and the priority of the sender may be pre-specified or fed back to the sender by the receiver. In the latter case, the receiver may determine the difference in importance between the data sent by each sender and / or determine the communication scenario between the sender and the receiver based on the data sent by each sender, and then feed back to each sender the priority of the sender determined at least based on the data importance and / or the communication scenario.

[0194] As also explained above, the AI ​​model pair can also be determined based on the accuracy of the data reconstructed by the receiving end. For example, the receiving end can send data processed by the first AI model in a pair of AI models from the transmitting end. After receiving the processed data, the receiving end can calculate the reconstruction accuracy of the data reconstructed using the second AI model in the pair of AI models. As described in detail above, the receiving end can use any appropriate verification method to verify the reconstructed data, and calculate the ratio of the number of data that pass the verification to the number of data in the data sequence as the reconstruction accuracy. For another example, the receiving end can also calculate the comparison between the data reconstructed by the AI ​​model and the original data, such as the minimum mean square error (MMSE), and use it as the reconstruction accuracy.

[0195] As also explained above, the AI ​​model pair may also be determined based on a combination of the priority of the sender and the accuracy of the reconstructed data.

[0196] As described above, the receiving end can feed back the determined priority of the sending end and / or the accuracy of the reconstructed data to the sending end. Subsequently, either the sending end or the receiving end can determine the AI ​​model pair to be used based on the priority of the sending end and / or the accuracy of the reconstructed data, and send transmission parameter information indicating the transmission parameters to the other party, except for the case where the AI ​​model pair is directly enabled by the sending end without explicit notification. The transmission parameter information can include at least the ID of the selected AI model pair and information indicating the time when the AI ​​model pair is to be enabled.

[0197] At S16006, the receiving end may use the determined AI model to process the data received from the sending end and processed by the AI ​​model of the sending end, thereby reconstructing the data that the sending end intends to send to the receiving end.

[0198] The operation at the receiving end ends at S16008.

[0199] It should be noted that the operating steps of the receiving end shown in Figure 16 are merely schematic. In practice, the operation of the receiving end may also include some additional or alternative steps. For example, as mentioned in the above description, between S16004 and S16006, the receiving end may also send transmission parameter information to the transmitting end or receive transmission parameter information from the transmitting end. For another example, during S16006, the receiving end may also perform operations with the transmitting end for dynamically adjusting the AI ​​model pair to be used, such as the receiving end feeding back the updated transmitting end priority and / or data reconstruction accuracy to the transmitting end, and transmitting the updated transmission parameter information between the transmitting end and the receiving end to adjust the AI ​​model pair.

[0200] The details of the transmitting end and the receiving end according to the second embodiment of the present disclosure have been described with reference to Figures 13 to 16. Now, exemplary interactions between the transmitting end and the receiving end according to the second embodiment of the present disclosure will be described with reference to Figures 17 to 19.

[0201] FIG17 schematically illustrates the interaction between a transmitting end and a receiving end according to a first exemplary implementation of the second embodiment of the present disclosure.

[0202] As shown in Figure 17, first, the transmitter sends data to the receiver. That is, in the current communication scenario, the data that the transmitter wants to send to the receiver, such as video data or sensor data. Here, the transmitter can use any appropriate method to send the data to the receiver. For example, the transmitter can use traditional methods to perform traditional encoding, modulation, and other operations on the data to be sent. Alternatively, the data can be sent using a default AI model pair or an AI model pair previously determined by both parties.

[0203] Subsequently, the receiving end can determine the priority of the transmitting end based on the data received from the transmitting end. As described in detail above, the receiving end can receive data from each transmitting end in a group of transmitting ends, and compare the importance differences between the data received from different transmitting ends and / or determine the current communication scenario based on the data. After determining the importance of the data of each transmitting end and / or the communication scenario, the receiving end can feedback its priority to the corresponding transmitting end accordingly. For example, a transmitting end with high data importance can correspond to a higher priority, while a transmitting end with low data importance can correspond to a lower priority. For example, the receiving end can use any suitable signaling to perform such feedback, such as via uplink control information (UCI).

[0204] Next, both the transmitter and the receiver can determine the AI ​​model pair to be used based on the priority of the transmitter. For example, for a transmitter with a higher priority, an AI model pair with better performance can be used, while for a transmitter with a lower priority, an AI model pair with worse performance can be used. For example, after the transmitter receives the priority fed back by the receiver, it can directly use the corresponding AI model to send data based on the predetermined correspondence between the priority and the AI ​​model pair. Correspondingly, the receiver can also directly use the corresponding AI model to receive data based on the predetermined correspondence between the priority of the corresponding transmitter and the AI ​​model pair.

[0205] More generally, as shown in FIG17 , either the transmitting end or the receiving end may determine the AI ​​model pair to be used based on the priority of the transmitting end, and send transmission parameter information indicating the transmission parameters to the other party. The transmission parameter information may include at least the ID of the selected AI model pair and information indicating the time when the AI ​​model pair is to be enabled, so that the indicated AI model pair is enabled at the indicated time to send data. When the receiving end sends the transmission parameter information to the transmitting end, the transmission parameter information may be sent to the transmitting end together with the priority of the transmitting end determined by the indicating end. For example, the transmission parameter information may be sent using any appropriate signaling, such as RRC signaling, UCI, or DCI.

[0206] After the AI ​​model pair / transmission parameters are determined, data may be sent from the transmitting end to the receiving end using the selected AI model pair (eg, the AI ​​model pair specified in the transmission parameters).

[0207] FIG18 schematically illustrates the interaction between a transmitting end and a receiving end according to a second example implementation of the second embodiment of the present disclosure.

[0208] First, the transmitter can send data processed by the first AI model in a pair of AI models (e.g., AI model pair x) to the receiver. This data can be data that the transmitter wants to send to the receiver (e.g., video data, sensor data, etc.), or data specifically used to determine the reconstruction accuracy of the data.

[0209] Next, the receiving end may calculate the reconstruction accuracy of the data reconstructed using the second AI model in the pair of AI models. As described in detail above, the reconstruction accuracy may be determined based on a checksum, or based on an accuracy rate (e.g., minimum mean square error (MMSE)) calculated by comparing the data reconstructed by the AI ​​model with the original data.

[0210] Next, the receiving end can feed back the calculated accuracy to the sending end.

[0211] Subsequently, both the transmitter and receiver can determine the AI ​​model pair to use based on the accuracy of the transmitter. For example, the transmitter can determine whether to select the AI ​​model pair x for subsequent data transmission based on whether the accuracy fed back by the receiver meets the expected value. For another example, after determining the reconstruction accuracy, the receiver can also determine whether the accuracy meets the expected value and either feedback to the transmitter whether to continue using the AI ​​model pair or implicitly indicate to the transmitter whether to continue using the AI ​​model pair by not providing any feedback.

[0212] More generally, as shown in FIG17 , either the transmitting end or the receiving end may determine the AI ​​model pair to be used based on the reconstruction accuracy, and send transmission parameter information indicating the transmission parameters to the other end. The transmission parameter information may include at least the ID of the selected AI model pair and information indicating the time when the AI ​​model pair is to be enabled, so that the indicated AI model pair is enabled at the indicated time to send data. When the receiving end sends the transmission parameter information to the transmitting end, the transmission parameter information may be sent to the transmitting end together with the reconstruction accuracy determined by the indicating receiving end. For example, the transmission parameter information may be sent using any appropriate signaling, such as RRC signaling, UCI, or DCI.

[0213] After the AI ​​model pair / transmission parameters are determined, data may be sent from the transmitting end to the receiving end using the selected AI model pair (eg, the AI ​​model pair specified in the transmission parameters).

[0214] FIG19 schematically illustrates the interaction between the transmitting end and the receiving end during the training of the AI ​​model according to the second embodiment of the present disclosure.

[0215] According to the present disclosure, the AI ​​model parameters can be adjusted during the training of the AI ​​model pair based on the accuracy of the data that the transmitting end intends to send to the receiving end, which is fed back by the receiving end to the transmitting end. In particular, this training method is not limited to the second embodiment of the present disclosure, but is also applicable to any situation where it is necessary to jointly train an AI model pair between the transmitting end and the receiving end. For example, this training method is also applicable to the second communication mode according to the first embodiment of the present disclosure.

[0216] As shown in Figure 19, the transmitting end can send data processed by the first AI model of a pair of AI models to the receiving end. For example, the data here can be feature data specifically used for model training.

[0217] Next, the receiving end can evaluate the AI ​​model. For example, the reconstruction accuracy of the data reconstructed using the second AI model in the pair of AI models can be calculated. Similar to the reconstruction accuracy calculation method described above, the reconstruction accuracy can be determined based on verification, that is, calculated as the ratio of the number of data that pass the verification to the number of data in the data sequence. Alternatively, the reconstruction accuracy can also be based on the minimum mean square error (MMSE) calculated between the data reconstructed by the AI ​​model and the original data. The receiving end can evaluate multiple AI models separately, for example, calculate the reconstruction accuracy of multiple AI models. For example, assuming there are m AI models, the reconstruction accuracy for the 1st AI model to the mth AI model can be expressed as a set A = [A1, A2, ..., A m For example, assuming m = 3, that is, there are 3 AI models, then the reconstruction accuracy can be expressed as A = [[0, 0.5], [0.5, 0.8], [0.8, 1]].

[0218] Next, the receiving end can feed back to the sending end the ID of the AI ​​model for which the current feedback is directed, the calculated accuracy or an indication of whether the accuracy meets the standard, and the AI ​​model parameters to be updated. For example, the AI ​​model parameters to be updated can be any applicable AI model parameters, such as the number of layers of the neural network, the number of nodes in each layer, the weight values ​​of each node, the learning rate, and so on. For example, the receiving end can use any applicable message, signaling, etc. to provide such feedback to the sending end. In particular, when the receiving end is a user equipment and the sending end is a base station, the receiving end can feedback an indication of whether the accuracy meets the standard through a positive acknowledgment (ACK) or a negative acknowledgment (NACK), and transmit the specific AI model parameters to be updated in the PUCCH or PUSCH that transmits the ACK / NACK.

[0219] Subsequently, the transmitting end can update the first AI model in the currently training AI model pair (i.e., the AI ​​model used by the transmitting end) based on the feedback information received from the receiving end. For example, the model parameters of the first AI model can be adjusted according to the feedback from the receiving end. At the same time, the receiving end can also update the second AI model in the currently training AI model pair (i.e., the AI ​​model used by the receiving end). For example, the second AI model can be reconfigured according to the determined model parameters.

[0220] During the training process, the interactions and operations shown in FIG19 may be performed iteratively until the desired reconstruction accuracy is achieved.

[0221] It should be noted that in the present disclosure, the AI ​​model pair can be jointly trained between any appropriate sending end and receiving end. For example, a wireless channel under various communication conditions can be established between the sending end and the receiving end for model training by any appropriate means, or the model training process can be used to make the jointly trained AI model pair widely applicable to wireless channels under various communication conditions. The trained AI model pair can be used for any sending end and receiving end. In other words, the sending end and receiving end for jointly training the AI ​​model pair do not necessarily have to be the sending end and receiving end that use the AI ​​model pair for data transmission. Of course, the sending end and receiving end that use the AI ​​model pair for data transmission can be the sending end and receiving end that jointly train the AI ​​model pair.

[0222] The second embodiment of the present disclosure has been described in detail above with reference to Figures 13 to 19. According to the second embodiment of the present disclosure, it is advantageous to select the most appropriate pair of AI models between each transmitter and receiver in a group of transmitters for data transmission, thereby flexibly controlling the transmission of data from a group of transmitter devices to a receiver device. For example, using the second embodiment of the present disclosure, it is possible to ensure the accurate and / or timely transmission of important data while avoiding unnecessary resource consumption and / or delay in the transmission of non-important data.

[0223] In particular, the first embodiment and the second embodiment can be implemented in combination. For example, each transmitting end in a group of transmitting ends can notify the receiving end of data according to the first notification mode, the second notification mode, and the third notification mode described in the first embodiment. In the case of determining to use the second notification mode for notification in the manner described in the first embodiment, the corresponding transmitting end can determine which AI model pair of the multiple deployed AI model pairs to use to notify the data in the manner described in the second embodiment. For example, in the case of combined implementation, each transmitting end in a group of transmitting ends can separately determine the notification mode to be adopted, or the group of transmitting ends can uniformly adopt one notification mode.

[0224] It should be understood that the machine-executable instructions in the machine-readable storage medium or program product according to the embodiments of the present disclosure can be configured to perform operations corresponding to the above-mentioned device and method embodiments. When referring to the above-mentioned device and method embodiments, the embodiments of the machine-readable storage medium or program product are clear to those skilled in the art and are therefore not described again. Machine-readable storage media and program products for carrying or including the above-mentioned machine-executable instructions also fall within the scope of the present disclosure. Such storage media may include, but are not limited to, floppy disks, optical disks, magneto-optical disks, memory cards, memory sticks, and the like.

[0225] In addition, it should be understood that the above series of processing and devices can also be implemented by software and / or firmware. In the case of being implemented by software and / or firmware, the program constituting the software is installed from a storage medium or a network to a computer with a dedicated hardware structure, such as the general-purpose personal computer 1300 shown in Figure 20. When various programs are installed, the computer can perform various functions, etc. Figure 20 is a block diagram showing an example structure of a personal computer as an information processing device that can be used in an embodiment of the present disclosure. In one example, the personal computer can correspond to the above-mentioned exemplary transmitting end or receiving end according to the present disclosure.

[0226] 20 , a central processing unit (CPU) 1301 executes various processes according to a program stored in a read-only memory (ROM) 1302 or a program loaded from a storage section 1308 to a random access memory (RAM) 1303. In the RAM 1303, data required when the CPU 1301 executes various processes and the like is also stored as needed.

[0227] The CPU 1301, the ROM 1302, and the RAM 1303 are connected to one another via a bus 1304. An input / output interface 1305 is also connected to the bus 1304.

[0228] The following components are connected to the input / output interface 1305: an input section 1306 including a keyboard, a mouse, etc.; an output section 1307 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1308 including a hard disk, etc.; and a communication section 1309 including a network interface card such as a LAN card, a modem, etc. The communication section 1309 performs communication processing via a network such as the Internet.

[0229] A drive 1310 is also connected to the input / output interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1310 as needed so that a computer program read therefrom is installed in the storage section 1308 as needed.

[0230] In the case of realizing the above-described series of processing by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the removable medium 1311 .

[0231] Those skilled in the art will appreciate that such storage media are not limited to the removable media 1311 shown in FIG. 20 , which stores programs therein and is distributed separately from the device to provide the programs to users. Examples of the removable media 1311 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disk read-only memories (CD-ROMs) and digital versatile disks (DVDs)), magneto-optical disks (including minidiscs (MDs) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be a ROM 1302, a hard disk included in the storage section 1308, or the like, in which the programs are stored and distributed to users together with the device containing them.

[0232] The technology disclosed herein can be applied to various products.

[0233] As explained above, the transmitting end and the receiving end of the present disclosure can both be control devices or terminal devices. For example, the electronic device 20, the electronic device 50, the electronic device 130, and the electronic device 150 according to the embodiments of the present disclosure can be implemented as various control devices / base stations or included in various control devices / base stations, and the methods shown in Figures 3, 6, 14, and 16 can also be implemented by various control devices / base stations. For example, the electronic device 20, the electronic device 50, the electronic device 130, and the electronic device 150 according to the embodiments of the present disclosure can also be implemented as various terminal devices / user devices or included in various terminal devices / user devices, and the methods shown in Figures 3, 6, 14, and 16 can also be implemented by various terminal devices / user devices.

[0234] For example, the control device / base station mentioned in the present disclosure can be implemented as any type of base station, such as an evolved Node B (gNB), such as a macro gNB and a small gNB. A small gNB can be a gNB that covers a cell smaller than a macro cell, such as a pico gNB, a micro gNB, and a home (femto) gNB. Alternatively, the base station can be implemented as any other type of base station, such as a NodeB and a base transceiver station (BTS). A base station may include: a main body (also called a base station device) configured to control wireless communication; and one or more remote radio heads (RRHs) located at a location different from the main body. In addition, the various types of terminals described below can all operate as a base station by temporarily or semi-permanently performing base station functions.

[0235] For example, the terminal device mentioned in the present disclosure is also referred to as a user device in some examples, and can be implemented as a mobile terminal (such as a smart phone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or a vehicle-mounted terminal (such as a car navigation device). The user device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also referred to as a machine-type communication (MTC) terminal). In addition, the user device can be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above-mentioned terminals.

[0236] An example according to the present disclosure will be described below with reference to FIG. 21 to FIG. 24 .

[0237] [Example about base stations]

[0238] It should be understood that the term "base station" in the present disclosure has the full breadth of its usual meaning and at least includes a wireless communication station used as part of a wireless communication system or radio system to facilitate communication. Examples of base stations may include, but are not limited to, the following: a base station may be one or both of a base transceiver station (BTS) and a base station controller (BSC) in a GSM system, one or both of a radio network controller (RNC) and a Node B in a WCDMA system, an eNB in ​​an LTE and LTE-Advanced system, a gNB appearing in a 5G communication system, an eLTE eNB, etc., or a corresponding network node in a future communication system. Some of the functions in the base station of the present disclosure may also be implemented as an entity having a control function for communication in D2D, M2M, and V2V communication scenarios, or as an entity that plays a spectrum coordination role in a cognitive radio communication scenario.

[0239] First example

[0240] FIG21 is a block diagram illustrating a first example of a schematic configuration of a gNB to which the techniques of this disclosure may be applied. gNB 1400 includes multiple antennas 1410 and a base station device 1420. Base station device 1420 and each antenna 1410 may be connected to each other via an RF cable. In one implementation, gNB 1400 (or base station device 1420) herein may correspond to electronic device 10 and / or electronic device 80 described above.

[0241] Each antenna 1410 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for base station device 1420 to transmit and receive wireless signals. As shown in Figure 21, gNB 1400 may include multiple antennas 1410. For example, multiple antennas 1410 may be compatible with multiple frequency bands used by gNB 1400.

[0242] The base station device 1420 includes a controller 1421 , a memory 1422 , a network interface 1423 , and a wireless communication interface 1425 .

[0243] The controller 1421 may be, for example, a CPU or a DSP, and operates various higher-layer functions of the base station device 1420. For example, the controller 1421 generates data packets based on the data in the signal processed by the wireless communication interface 1425 and transmits the generated packets via the network interface 1423. The controller 1421 may bundle data from multiple baseband processors to generate bundled packets and transmit the generated bundled packets. The controller 1421 may have logic functions for performing control such as radio resource control, radio bearer control, mobility management, admission control, and scheduling. This control may be performed in conjunction with a nearby gNB or core network node. The memory 1422 includes RAM and ROM and stores programs executed by the controller 421 and various types of control data (such as terminal lists, transmission power data, and scheduling data).

[0244] Network interface 1423 is a communication interface for connecting base station device 1420 to core network 1424. Controller 1421 can communicate with a core network node or another gNB via network interface 1423. In this case, gNB 1420 and the core network node or other gNB can be connected to each other via logical interfaces (such as S1 and X2 interfaces). Network interface 1423 can also be a wired communication interface or a wireless communication interface for wireless backhaul. If network interface 1423 is a wireless communication interface, network interface 1423 can use a higher frequency band for wireless communication than the frequency band used by wireless communication interface 1425.

[0245] The wireless communication interface 1425 supports any cellular communication scheme, such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connectivity to terminals located in the cell of the gNB 1400 via the antenna 1410. The wireless communication interface 1425 may typically include, for example, a baseband (BB) processor 1426 and RF circuitry 1427. The BB processor 1426 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for layers such as Layer 1 (L1), Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 1421, the BB processor 1426 may perform some or all of the aforementioned logical functions. The BB processor 1426 may be a memory storing communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 1426. This module may be a card or blade inserted into a slot in the base station device 1420. Alternatively, it may be a chip mounted on the card or blade. Meanwhile, the RF circuit 1427 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 1410. Although FIG21 shows an example in which one RF circuit 1427 is connected to one antenna 1410, the present disclosure is not limited to this illustration, and one RF circuit 1427 may be connected to multiple antennas 1410 at the same time.

[0246] As shown in Figure 21 , the wireless communication interface 1425 may include multiple BB processors 1426. For example, multiple BB processors 1426 may be compatible with multiple frequency bands used by the gNB 1400. As shown in Figure 21 , the wireless communication interface 1425 may include multiple RF circuits 1427. For example, multiple RF circuits 1427 may be compatible with multiple antenna elements. While Figure 21 illustrates an example in which the wireless communication interface 1425 includes multiple BB processors 1426 and multiple RF circuits 1427, the wireless communication interface 1425 may also include a single BB processor 1426 or a single RF circuit 1427.

[0247] Second example

[0248] FIG22 is a block diagram illustrating a second example of a schematic configuration of a gNB to which the techniques of this disclosure may be applied. A gNB 1530 includes multiple antennas 1540, a base station device 1550, and an RRH 1560. The RRH 1560 and each antenna 1540 may be connected to each other via an RF cable. The base station device 1550 and the RRH 1560 may be connected to each other via a high-speed line such as an optical fiber cable. In one implementation, the gNB 1530 (or base station device 1550) herein may correspond to the electronic devices 50 and / or 100 described above.

[0249] Each antenna 1540 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for RRH 1560 to transmit and receive wireless signals. As shown in Figure 22, gNB 1530 may include multiple antennas 1540. For example, multiple antennas 1540 may be compatible with multiple frequency bands used by gNB 1530.

[0250] Base station device 1550 includes a controller 1551, a memory 1552, a network interface 1553, a wireless communication interface 1555, and a connection interface 1557. Controller 1551, memory 1552, and network interface 1553 are the same as controller 1421, memory 1422, and network interface 1423 described with reference to FIG.

[0251] The wireless communication interface 1555 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 1560 via the RRH 1560 and the antenna 1540. The wireless communication interface 1555 may generally include, for example, a BB processor 1556. The BB processor 1556 is identical to the BB processor 1426 described with reference to FIG. 21 , except that the BB processor 1556 is connected to the RF circuit 1564 of the RRH 1560 via the connection interface 1557. As shown in FIG. 22 , the wireless communication interface 1555 may include multiple BB processors 1556. For example, multiple BB processors 1556 may be compatible with multiple frequency bands used by the gNB 1530. Although FIG. 22 illustrates an example in which the wireless communication interface 1555 includes multiple BB processors 1556, the wireless communication interface 1555 may also include a single BB processor 1556.

[0252] The connection interface 1557 is an interface for connecting the base station device 1550 (wireless communication interface 1555) to the RRH 1560. The connection interface 1557 may also be a communication module for connecting the base station device 1550 (wireless communication interface 1555) to the RRH 1560 for communication in the high-speed line.

[0253] The RRH 1560 includes a connection interface 1561 and a wireless communication interface 1563 .

[0254] The connection interface 1561 is an interface for connecting the RRH 1560 (wireless communication interface 1563) to the base station device 1550. The connection interface 1561 may also be a communication module for communication in the above-mentioned high-speed line.

[0255] The wireless communication interface 1563 transmits and receives wireless signals via the antenna 1540. The wireless communication interface 1563 may generally include, for example, an RF circuit 1564. The RF circuit 1564 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 1540. Although FIG. 22 shows an example in which one RF circuit 1564 is connected to one antenna 1540, the present disclosure is not limited to this illustration, and one RF circuit 1564 may be connected to multiple antennas 1540 simultaneously.

[0256] As shown in FIG22 , the wireless communication interface 1563 may include multiple RF circuits 1564. For example, multiple RF circuits 1564 may support multiple antenna elements. Although FIG22 shows an example in which the wireless communication interface 1563 includes multiple RF circuits 1564, the wireless communication interface 1563 may also include a single RF circuit 1564.

[0257] [Example about user equipment]

[0258] First example

[0259] 23 is a block diagram illustrating an example of a schematic configuration of a smartphone 1600 to which the techniques of the present disclosure may be applied. The smartphone 1600 includes a processor 1601, a memory 1602, a storage device 1603, an external connection interface 1604, a camera 1606, a sensor 1607, a microphone 1608, an input device 1609, a display 1610, a speaker 1611, a wireless communication interface 1612, one or more antenna switches 1615, one or more antennas 1616, a bus 1617, a battery 1618, and an auxiliary controller 1619. In one implementation, the smartphone 1600 (or processor 1601) herein may correspond to the electronic device 50 and / or the electronic device 100 described above.

[0260] The processor 1601 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 1600. The memory 1602 includes RAM and ROM, and stores data and programs executed by the processor 1601. The storage device 1603 may include storage media such as semiconductor memories and hard disks. The external connection interface 1604 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 1600.

[0261] The camera 1606 includes an image sensor (such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS)) and generates a captured image. The sensor 1607 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 1608 converts the sound input to the smartphone 1600 into an audio signal. The input device 1609 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 1610, and receives an operation or information input from the user. The display device 1610 includes a screen (such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display) and displays the output image of the smartphone 1600. The speaker 1611 converts the audio signal output from the smartphone 1600 into sound.

[0262] The wireless communication interface 1612 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 1612 may generally include, for example, a BB processor 1613 and an RF circuit 1619. The BB processor 1613 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 1614 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 1616. The wireless communication interface 1612 may be a chip module on which the BB processor 1613 and the RF circuit 1614 are integrated. As shown in FIG23 , the wireless communication interface 1612 may include multiple BB processors 1613 and multiple RF circuits 1614. Although FIG23 shows an example in which the wireless communication interface 1612 includes multiple BB processors 1613 and multiple RF circuits 1614, the wireless communication interface 1612 may also include a single BB processor 1613 or a single RF circuit 1614.

[0263] In addition, in addition to the cellular communication scheme, the wireless communication interface 1612 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 1612 may include a BB processor 1613 and an RF circuit 1614 for each wireless communication scheme.

[0264] Each of the antenna switches 1615 switches the connection destination of the antenna 1616 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 1612 .

[0265] Each of the antennas 1616 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 1612. As shown in FIG23, the smartphone 1600 may include multiple antennas 1616. Although FIG23 shows an example in which the smartphone 1600 includes multiple antennas 1616, the smartphone 1600 may also include a single antenna 1616.

[0266] In addition, the smartphone 1600 may include an antenna 1616 for each wireless communication scheme. In this case, the antenna switch 1615 may be omitted from the configuration of the smartphone 1600.

[0267] The bus 1617 connects the processor 1601, the memory 1602, the storage device 1603, the external connection interface 1604, the camera 1606, the sensor 1607, the microphone 1608, the input device 1609, the display device 1610, the speaker 1611, the wireless communication interface 1612, and the auxiliary controller 1619. The battery 1618 supplies power to the various blocks of the smartphone 1600 shown in FIG. 23 via feeders, which are partially shown as dashed lines in the figure. The auxiliary controller 1619 operates the minimum necessary functions of the smartphone 1600, for example, in sleep mode.

[0268] Second example

[0269] 24 is a block diagram illustrating an example of a schematic configuration of a car navigation device 1720 to which the techniques of the present disclosure may be applied. The car navigation device 1720 includes a processor 1721, a memory 1722, a global positioning system (GPS) module 1724, a sensor 1725, a data interface 1726, a content player 1727, a storage medium interface 1728, an input device 1729, a display device 1730, a speaker 1731, a wireless communication interface 1733, one or more antenna switches 1736, one or more antennas 1737, and a battery 1738. In one implementation, the car navigation device 1720 (or processor 1721) herein may correspond to the electronic device 50 and / or the electronic device 100 described above.

[0270] The processor 1721 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation device 1720. The memory 1722 includes a RAM and a ROM, and stores data and programs executed by the processor 1721.

[0271] The GPS module 1724 uses GPS signals received from GPS satellites to measure the position (such as latitude, longitude, and altitude) of the car navigation device 1720. The sensor 1725 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 1726 is connected to, for example, the vehicle network 1741 via a terminal not shown, and obtains data generated by the vehicle (such as vehicle speed data).

[0272] The content player 1727 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 1728. The input device 1729 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 1730, and receives operations or information input from the user. The display device 1730 includes a screen such as an LCD or OLED display and displays images of the navigation function or reproduced content. The speaker 1731 outputs sounds of the navigation function or reproduced content.

[0273] The wireless communication interface 1733 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 1733 may generally include, for example, a BB processor 1734 and an RF circuit 1735. The BB processor 1734 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 1735 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 1737. The wireless communication interface 1733 may also be a chip module on which the BB processor 1734 and the RF circuit 1735 are integrated. As shown in Figure 24, the wireless communication interface 1733 may include multiple BB processors 1734 and multiple RF circuits 1735. Although Figure 24 shows an example in which the wireless communication interface 1733 includes multiple BB processors 1734 and multiple RF circuits 1735, the wireless communication interface 1733 may also include a single BB processor 1734 or a single RF circuit 1735.

[0274] In addition, in addition to the cellular communication scheme, the wireless communication interface 1733 can support other types of wireless communication schemes, such as short-range wireless communication schemes, near field communication schemes, and wireless LAN schemes. In this case, for each wireless communication scheme, the wireless communication interface 1733 can include a BB processor 1734 and an RF circuit 1735.

[0275] Each of the antenna switches 1736 switches a connection destination of the antenna 1737 between a plurality of circuits included in the wireless communication interface 1733 , such as circuits for different wireless communication schemes.

[0276] Each of the antennas 1737 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 1733. As shown in FIG24, the car navigation device 1720 may include multiple antennas 1737. Although FIG24 shows an example in which the car navigation device 1720 includes multiple antennas 1737, the car navigation device 1720 may also include a single antenna 1737.

[0277] In addition, the car navigation device 1720 may include an antenna 1737 for each wireless communication scheme. In this case, the antenna switch 1736 may be omitted from the configuration of the car navigation device 1720.

[0278] The battery 1738 supplies power to the respective blocks of the car navigation device 1720 shown in Fig. 24 via a feeder line, which is partially shown as a dotted line in the figure. The battery 1738 accumulates the power supplied from the vehicle.

[0279] The technology of the present disclosure may also be implemented as an in-vehicle system (or vehicle) 1740 including a car navigation device 1720, an in-vehicle network 1741, and one or more blocks of a vehicle module 1742. The vehicle module 1742 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 1741.

[0280] The exemplary embodiments of the present disclosure are described above with reference to the accompanying drawings, but the present disclosure is certainly not limited to the above examples. Those skilled in the art may obtain various changes and modifications within the scope of the appended claims, and it should be understood that these changes and modifications will naturally fall within the technical scope of the present disclosure.

[0281] It should be understood that the machine-executable instructions in the machine-readable storage medium or program product according to the embodiments of the present disclosure can be configured to perform operations corresponding to the above-mentioned device and method embodiments. When referring to the above-mentioned device and method embodiments, the embodiments of the machine-readable storage medium or program product are clear to those skilled in the art and are therefore not described again. Machine-readable storage media and program products for carrying or including the above-mentioned machine-executable instructions also fall within the scope of the present disclosure. Such storage media may include, but are not limited to, floppy disks, optical disks, magneto-optical disks, memory cards, memory sticks, and the like.

[0282] In addition, it should be understood that the above series of processes and devices can also be implemented by software and / or firmware. In the case of implementation by software and / or firmware, the storage medium of the relevant device stores the corresponding program constituting the corresponding software, and when the program is executed, various functions can be performed.

[0283] For example, a plurality of functions included in one unit in the above embodiments may be implemented by separate devices. Alternatively, a plurality of functions implemented by a plurality of units in the above embodiments may be implemented by separate devices, respectively. In addition, one of the above functions may be implemented by a plurality of units. Needless to say, such a configuration is included in the technical scope of the present disclosure.

[0284] In this specification, the steps described in the flowchart include not only processing executed in time series in the order described, but also processing executed in parallel or individually rather than necessarily in time series. In addition, even in the steps processed in time series, it goes without saying that the order can be changed as appropriate.

[0285] Although the present disclosure and its advantages have been described in detail, it should be understood that various changes, substitutions and transformations can be made without departing from the spirit and scope of the present disclosure as defined by the appended claims. Moreover, the terms "comprises," "comprising," or any other variations thereof in the embodiments of the present disclosure are intended to cover non-exclusive inclusions, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or device. In the absence of further restrictions, an element defined by the statement "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0286] In addition, the present disclosure may also have the following configurations:

[0287] (1) A first electronic device for a wireless communication system, comprising:

[0288] at least one processor; and

[0289] At least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to notify the second electronic device of data, wherein the data is notified through one of the following notification modes:

[0290] A first notification mode is configured to transmit or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device;

[0291] a second notification mode configured to transmit and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and

[0292] The third notification mode is configured so that the first electronic device sends the data to the second device without using an AI model for notifying the data at both the first electronic device and the second electronic device.

[0293] (2) The first electronic device according to (1), wherein:

[0294] The first notification mode is configured as any one of the following modes: (1) deploying the AI ​​model at the first electronic device, processing the data by the first electronic device using the deployed AI model and transmitting the processed data to the second electronic device, (2) deploying the AI ​​model at the second electronic device, receiving the data from the first electronic device by the second electronic device using the deployed AI model, and (3) deploying the AI ​​model at the second electronic device, predicting the data by the second electronic device using the deployed AI model based on at least historical data related to the data;

[0295] The second notification mode is configured as follows: the first electronic device processes the data using the first AI model of the pair of AI models and sends the processed data to the second electronic device, and the second electronic device reconstructs the data based on the processed data received from the first electronic device using the second AI model of the pair of AI models.

[0296] (3) The first electronic device according to (1) or (2), wherein:

[0297] The notification mode is selected based on at least a communication indicator,

[0298] The communication indicators include at least one or more of the following indicators: transmission delay on the communication link between the first electronic device and the second electronic device, data transmission accuracy requirements, communication resource overhead, transmission rate between the first electronic device and the second electronic device, queue length of data that the first electronic device is ready to send to the second electronic device, and computing power of the first electronic device and / or the second electronic device.

[0299] (4) The first electronic device according to (1) or (2), wherein the data to be notified is channel state information (CSI) feedback.

[0300] (5) The first electronic device according to (4), wherein:

[0301] The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to determine a queue length of communication data to be sent to the second electronic device, and

[0302] The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to:

[0303] determining which notification mode to use for notifying CSI feedback based on the queue length, and sending indication information indicating which notification mode to use for notifying CSI feedback to the second electronic device, or

[0304] Information indicating the queue length is sent to the second electronic device, so that the second electronic device determines which notification mode to use to notify CSI feedback based on the queue length.

[0305] (6) The first electronic device according to (5), wherein:

[0306] In response to the queue length being less than or equal to a first threshold, enabling the second electronic device to obtain CSI feedback based on the first notification mode,

[0307] In response to the queue length being greater than the first threshold and less than or equal to the second threshold, the first electronic device notifies the second electronic device of the CSI feedback using the second notification mode, or

[0308] In response to the queue length being greater than a second threshold, the first electronic device uses a third notification mode to send CSI feedback to the second electronic device.

[0309] (7) The first electronic device according to (5), wherein:

[0310] The information indicating the queue length or the indication information is transmitted through a physical uplink control channel (PUCCH).

[0311] (8) The first electronic device according to (1) or (2), wherein the data to be notified is video data.

[0312] (9) The first electronic device according to (8), wherein:

[0313] The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to determine a transmission delay for transmitting from the first electronic device to the second electronic device, and wherein

[0314] In response to the transmission delay being less than or equal to the first threshold, the first electronic device uses a third notification mode to send the video data to the second electronic device.

[0315] In response to the transmission delay being greater than the first threshold and less than or equal to the second threshold, the first electronic device notifies the second electronic device of the video data using the second notification mode, or

[0316] In response to the transmission delay being greater than a second threshold, the second electronic device is enabled to obtain the video data based on a first notification mode.

[0317] (10) The first electronic device according to (1) or (2), wherein:

[0318] The at least one memory and the computer program code are configured to, through the at least one processor, enable the first electronic device to transmit data to the second electronic device as one of a group of transmitting end devices, the group of transmitting end devices including one or more transmitting end devices.

[0319] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0320] The at least one memory and the computer program code are further configured to, through the at least one processor, enable the first electronic device to send the data to the second electronic device using a second notification mode based on a first AI model pair selected from the multiple AI model pairs.

[0321] (11) A second electronic device for a wireless communication system, comprising:

[0322] at least one processor; and

[0323] At least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the second electronic device to obtain data to be notified by the first electronic device, wherein the data is notified through one of the following notification modes:

[0324] A first notification mode is configured to transmit or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device;

[0325] a second notification mode configured to transmit and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and

[0326] The third notification mode is configured so that the first electronic device sends the data to the second device without using an AI model for notifying the data at both the first electronic device and the second electronic device.

[0327] (12) The second electronic device according to (11), wherein

[0328] The first notification mode is configured as any one of the following modes: (1) deploying the AI ​​model at the first electronic device, processing the data by the first electronic device using the deployed AI model and transmitting the processed data to the second electronic device, (2) deploying the AI ​​model at the second electronic device, receiving the data from the first electronic device by the second electronic device using the deployed AI model, and (3) deploying the AI ​​model at the second electronic device, predicting the data by the second electronic device using the deployed AI model based on at least historical data related to the data;

[0329] The second notification mode is configured as follows: the first electronic device processes the data using the first AI model of the pair of AI models and sends the processed data to the second electronic device, and the second electronic device reconstructs the data based on the processed data received from the first electronic device using the second AI model of the pair of AI models.

[0330] (13) The second electronic device according to (11) or (12), wherein:

[0331] The notification mode is selected based on at least a communication indicator,

[0332] The communication indicators include at least one or more of the following indicators: transmission delay on the communication link between the first electronic device and the second electronic device, data transmission accuracy requirements, communication resource overhead, transmission rate between the first electronic device and the second electronic device, queue length of data that the first electronic device is ready to send to the second electronic device, and computing power of the first electronic device and / or the second electronic device.

[0333] (14) The second electronic device according to (11) or (12), wherein the data to be notified is channel state information (CSI) feedback.

[0334] (15) The second electronic device according to (14), wherein:

[0335] The at least one memory and the computer program code are further configured to, through the at least one processor, cause the second electronic device to:

[0336] receiving, from the first electronic device, indication information indicating which notification mode to use for notifying CSI feedback, wherein the indication information is determined based on a queue length of communication data to be sent by the first electronic device to the second electronic device, or

[0337] Information indicating a queue length of communication data that the first electronic device is ready to send to the second electronic device is received from the first electronic device, and a notification mode to be used for notifying CSI feedback is determined based on the queue length.

[0338] (16) The second electronic device according to (15), wherein:

[0339] In response to the queue length being less than or equal to the first threshold, the second electronic device obtains CSI feedback based on the first notification mode,

[0340] In response to the queue length being greater than the first threshold and less than or equal to the second threshold, the second electronic device obtains CSI feedback from the first electronic device based on the second notification mode, or

[0341] In response to the queue length being greater than a second threshold, the second electronic device uses a third notification mode to receive CSI feedback from the first electronic device.

[0342] (17) The second electronic device according to (15), wherein

[0343] The information indicating the queue length or the indication information is transmitted through a physical uplink control channel (PUCCH).

[0344] (18) The second electronic device according to (11) or (12), wherein the data to be notified is video data.

[0345] (19) The second electronic device according to (18), wherein:

[0346] The at least one memory and the computer program code are further configured to, through the at least one processor, cause the second electronic device to determine a transmission delay for transmitting from the first electronic device to the second electronic device, and wherein

[0347] In response to the transmission delay being less than or equal to the first threshold, the second electronic device uses a third notification mode to receive the video data from the first electronic device.

[0348] In response to the transmission delay being greater than the first threshold and less than or equal to the second threshold, the second electronic device obtains the video data from the first electronic device based on the second notification mode, or

[0349] In response to the transmission delay being greater than a second threshold, the second electronic device obtains the video data based on a first notification mode.

[0350] (20) The second electronic device according to (11) or (12), wherein:

[0351] The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive data from each of a group of sender devices including the first electronic device, the group of sender devices including one or more sender devices,

[0352] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0353] Wherein, the at least one memory and computer program code are further configured to, through the at least one processor, enable the second electronic device to obtain the data from each sending device using a second communication mode based on a corresponding AI model pair selected from the multiple AI model pairs.

[0354] (21) A method for a first electronic device in a wireless communication system, comprising notifying a second electronic device of data, wherein the data is notified using one of the following notification modes:

[0355] A first notification mode is configured to transmit or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device;

[0356] a second notification mode configured to transmit and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and

[0357] The third notification mode is configured so that the first electronic device sends the data to the second device without using an AI model for notifying the data at both the first electronic device and the second electronic device.

[0358] (22) A method for a second electronic device of a wireless communication system, comprising obtaining data to be notified by a first electronic device, wherein the data is notified by one of the following notification modes:

[0359] A first notification mode is configured to transmit or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device;

[0360] a second notification mode configured to transmit and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and

[0361] The third notification mode is configured so that the first electronic device sends the data to the second device without using an AI model for notifying the data at both the first electronic device and the second electronic device.

[0362] (23) A first electronic device for a wireless communication system, comprising:

[0363] at least one processor; and

[0364] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to act as one of a group of sending devices to send data to the second electronic device, the group of sending devices including one or more sending devices.

[0365] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0366] The at least one memory and the computer program code are further configured to, through the at least one processor, enable the first electronic device to process the data using the first AI model in the first AI model pair selected from the multiple AI model pairs and send the processed data to the second electronic device, so that the second electronic device uses the second AI model in the first AI model pair to reconstruct the data based on the processed data received from the first electronic device.

[0367] (24) The first electronic device according to (23), wherein:

[0368] The first AI model pair is selected based on the priority of the first electronic device in the group of transmitting devices.

[0369] (25) The first electronic device according to (24), wherein:

[0370] The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to receive information indicating the priority from the second electronic device.

[0371] (26) The first electronic device according to (24) or (25), wherein:

[0372] The priority is determined based on at least one of the following items: a communication scenario between the group of sending devices and the second electronic device, and importance of data sent by each sending device in the group of sending devices to the second electronic device.

[0373] (27) The first electronic device according to (23) or (24), wherein:

[0374] The first AI model pair is selected based on the accuracy of reconstructing the data.

[0375] (28) The first electronic device according to (27), wherein:

[0376] The accuracy includes any one of the following items or a combination thereof: a verification result of the reconstructed data, and an accuracy rate calculated based on a comparison between the data and the reconstructed data.

[0377] (29) The first electronic device according to (23) or (24), wherein:

[0378] The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to send transmission parameter information indicating a transmission parameter to the second electronic device, or,

[0379] The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to receive transmission parameter information indicating a transmission parameter from the second electronic device,

[0380] The sending parameter information includes at least the ID of the selected AI model pair and information indicating the time to enable the AI ​​model pair.

[0381] (30) The first electronic device according to (29), wherein:

[0382] The transmission parameter information is transmitted or received via one of the following signaling: radio resource control (RRC) signaling, uplink control information (UCI), or downlink control information (DCI).

[0383] (31) The first electronic device according to (23) or (24), wherein:

[0384] During the training of the plurality of AI model pairs, AI model parameters are adjusted based on the accuracy of reconstructing the data fed back by the second electronic device to the first electronic device.

[0385] (32) A second electronic device for a wireless communication system, comprising:

[0386] at least one processor; and

[0387] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive data from each sender device in a group of sender devices, the group of sender devices including one or more sender devices,

[0388] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0389] In which, the at least one memory and computer program code are further configured to, through the at least one processor, enable the second electronic device to receive from each sending end device processed data obtained by processing the data using the first AI model in the corresponding AI model pair selected from the multiple AI model pairs, and use the second AI model in the corresponding AI model pair to reconstruct the data based on the received processed data.

[0390] (33) The second electronic device according to (32), wherein:

[0391] The corresponding AI model pairs are selected based on the priority of each transmitting end device in the group of transmitting end devices.

[0392] (34) The second electronic device according to (33), wherein:

[0393] The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to send information indicating the priority to each transmitting end device.

[0394] (35) The second electronic device as described in (33) or (34), wherein:

[0395] The priority is determined based on at least one of the following items: a communication scenario between the group of sending devices and the second electronic device, and importance of data sent by each sending device in the group of sending devices to the second electronic device.

[0396] (36) The second electronic device as described in (32) or (33), wherein:

[0397] The at least one memory and the computer program code are configured to, through the at least one processor, enable the second electronic device to feed back the accuracy of the reconstructed data to each sending end device, and

[0398] Wherein, the corresponding AI model pair is selected based on the accuracy.

[0399] (37) The second electronic device according to (36), wherein:

[0400] The accuracy includes any one of the following items or a combination thereof: a verification result of the reconstructed data, and an accuracy rate calculated based on a comparison between the data and the reconstructed data.

[0401] (38) The second electronic device as described in (32) or (33), wherein:

[0402] The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to send transmission parameter information indicating a transmission parameter to the first electronic device, or,

[0403] The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive transmission parameter information indicating a transmission parameter from the first electronic device,

[0404] The sending parameter information includes at least the ID of the selected AI model pair and information indicating the time to enable the AI ​​model pair.

[0405] (39) The second electronic device according to (38), wherein:

[0406] The transmission parameter information is transmitted or received via one of the following signaling: radio resource control (RRC) signaling, uplink control information (UCI), or downlink control information (DCI).

[0407] (40) The second electronic device as described in (32) or (33), wherein:

[0408] The at least one memory and the computer program code are configured to enable the second electronic device to feed back the reconstruction accuracy of the data through the at least one processor during the training of the multiple AI model pairs, so that the AI ​​model parameters are dynamically adjusted based on the accuracy.

[0409] (41) A method for a first electronic device in a wireless communication system, comprising the first electronic device, as one of a group of transmitting devices, transmitting data to a second electronic device, the group of transmitting devices including one or more transmitting devices,

[0410] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0411] The method further includes processing the data using a first AI model in a first AI model pair selected from the multiple AI model pairs and sending the processed data to a second electronic device, so that the second electronic device uses a second AI model in the first AI model pair to reconstruct the data based on the processed data received from the first electronic device.

[0412] (42) A method for a second electronic device of a wireless communication system, comprising receiving data from each transmitter device in a group of transmitter devices, the group of transmitter devices comprising one or more transmitter devices,

[0413] Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and,

[0414] The method further includes receiving processed data from each sending end device by processing the data using a first AI model in a corresponding AI model pair selected from the multiple AI model pairs, and reconstructing the data based on the received processed data using a second AI model in the corresponding AI model pair.

[0415] (43) A non-transitory computer-readable storage medium storing executable instructions, which, when executed, implement the method as described in any one of (21), (22), (41) and (42).

[0416] (44) A computer program product comprising executable instructions which, when executed, implement the method of any one of (21), (22), (41) and (42).

Claims

1. A first electronic device for a wireless communication system, comprising: at least one processor; and At least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to notify the second electronic device of data, wherein the data is notified through one of the following notification modes: A first notification mode configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and The third notification mode is configured such that the first electronic device sends the data to the second device when neither the first electronic device nor the second electronic device uses an AI model for notifying the data.

2. The first electronic device according to claim 1, wherein: The first notification mode is configured as any one of the following modes: (1) deploying an AI model at the first electronic device, processing the data by the first electronic device using the deployed AI model and sending the processed data to the second electronic device, (2) deploying an AI model at the second electronic device, receiving the data from the first electronic device using the deployed AI model by the second electronic device, and (3) deploying an AI model at the second electronic device, predicting the data by the second electronic device using the deployed AI model based on at least historical data related to the data; The second notification mode is configured as follows: the first electronic device uses the first AI model of the pair of AI models to process the data and sends the processed data to the second electronic device, and the second electronic device uses the second AI model of the pair of AI models to reconstruct the data based on the processed data received from the first electronic device.

3. The first electronic device according to claim 1 or 2, wherein: The notification mode is selected based on at least a communication indicator, The communication indicators include at least one or more of the following indicators: transmission delay on the communication link between the first electronic device and the second electronic device, data transmission accuracy requirements, communication resource overhead, transmission rate between the first electronic device and the second electronic device, queue length of data that the first electronic device is ready to send to the second electronic device, and computing power of the first electronic device and / or the second electronic device.

4. The first electronic device according to claim 1 or 2, wherein: The data to be notified is channel state information (CSI) feedback.

5. The first electronic device as claimed in claim 4, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to determine a queue length of communication data to be sent to the second electronic device, and The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to: determining which notification mode to use to notify CSI feedback based on the queue length, and sending indication information indicating which notification mode to use to notify CSI feedback to the second electronic device, or Information indicating the queue length is sent to the second electronic device, so that the second electronic device determines which notification mode to use to notify CSI feedback based on the queue length.

6. The first electronic device as claimed in claim 5, wherein: In response to the queue length being less than or equal to a first threshold, enabling the second electronic device to obtain CSI feedback based on a first notification mode, In response to the queue length being greater than the first threshold and less than or equal to the second threshold, the first electronic device notifies the second electronic device of the CSI feedback using the second notification mode, or In response to the queue length being greater than a second threshold, the first electronic device sends CSI feedback to the second electronic device using a third notification mode.

7. The first electronic device as claimed in claim 5, wherein: The information indicating the queue length or the indication information is transmitted through a physical uplink control channel (PUCCH).

8. The first electronic device according to claim 1 or 2, wherein: The data to be notified is video data.

9. The first electronic device as claimed in claim 8, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the first electronic device to determine a transmission delay for transmitting from the first electronic device to the second electronic device, and wherein In response to the transmission delay being less than or equal to the first threshold, the first electronic device uses a third notification mode to send the video data to the second electronic device, In response to the transmission delay being greater than the first threshold and less than or equal to the second threshold, the first electronic device notifies the second electronic device of the video data using the second notification mode, or In response to the transmission delay being greater than a second threshold, the second electronic device is enabled to obtain the video data based on a first notification mode.

10. The first electronic device according to claim 1 or 2, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, enable the first electronic device to send data to the second electronic device as one of a group of sending devices, wherein the group of sending devices includes one or more sending devices, Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting end device and the second electronic device, and, The at least one memory and the computer program code are further configured to enable the first electronic device to send the data to the second electronic device using a second notification mode based on a first AI model pair selected from the multiple AI model pairs through the at least one processor.

11. A second electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including a computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the second electronic device to obtain data to be notified by the first electronic device, wherein the data is notified through one of the following notification modes: A first notification mode configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and The third notification mode is configured such that the first electronic device sends the data to the second device when neither the first electronic device nor the second electronic device uses an AI model for notifying the data.

12. The second electronic device according to claim 11, wherein: The first notification mode is configured as any one of the following modes: (1) deploying an AI model at the first electronic device, processing the data by the first electronic device using the deployed AI model and sending the processed data to the second electronic device, (2) deploying an AI model at the second electronic device, receiving the data from the first electronic device using the deployed AI model by the second electronic device, and (3) deploying an AI model at the second electronic device, predicting the data by the second electronic device using the deployed AI model based on at least historical data related to the data; The second notification mode is configured as follows: the first electronic device uses the first AI model of the pair of AI models to process the data and sends the processed data to the second electronic device, and the second electronic device uses the second AI model of the pair of AI models to reconstruct the data based on the processed data received from the first electronic device.

13. The second electronic device according to claim 11 or 12, wherein: The notification mode is selected based on at least a communication indicator, The communication indicators include at least one or more of the following indicators: transmission delay on the communication link between the first electronic device and the second electronic device, data transmission accuracy requirements, communication resource overhead, transmission rate between the first electronic device and the second electronic device, queue length of data that the first electronic device is ready to send to the second electronic device, and computing power of the first electronic device and / or the second electronic device.

14. The second electronic device according to claim 11 or 12, wherein: The data to be notified is channel state information (CSI) feedback.

15. The second electronic device as claimed in claim 14, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the second electronic device to: receiving, from the first electronic device, indication information indicating which notification mode is to be used to notify CSI feedback, wherein the indication information is determined based on a queue length of communication data to be sent by the first electronic device to the second electronic device, or Information indicating a queue length of communication data that the first electronic device is ready to send to the second electronic device is received from the first electronic device, and a notification mode to be used to notify CSI feedback is determined based on the queue length.

16. The second electronic device as claimed in claim 15, wherein: In response to the queue length being less than or equal to the first threshold, the second electronic device obtains CSI feedback based on the first notification mode, In response to the queue length being greater than the first threshold and less than or equal to the second threshold, the second electronic device obtains CSI feedback from the first electronic device based on the second notification mode, or In response to the queue length being greater than a second threshold, the second electronic device uses a third notification mode to receive CSI feedback from the first electronic device.

17. The second electronic device as claimed in claim 15, wherein: The information indicating the queue length or the indication information is transmitted through a physical uplink control channel (PUCCH).

18. The second electronic device according to claim 11 or 12, wherein: The data to be notified is video data.

19. The second electronic device as claimed in claim 18, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the second electronic device to determine a transmission delay for transmitting from the first electronic device to the second electronic device, and wherein In response to the transmission delay being less than or equal to the first threshold, the second electronic device uses a third notification mode to receive the video data from the first electronic device, In response to the transmission delay being greater than the first threshold and less than or equal to the second threshold, the second electronic device obtains the video data from the first electronic device based on the second notification mode, or In response to the transmission delay being greater than a second threshold, the second electronic device obtains the video data based on a first notification mode.

20. The second electronic device according to claim 11 or 12, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive data from each of a group of sender devices including the first electronic device, the group of sender devices including one or more sender devices, Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting end device and the second electronic device, and, Wherein, the at least one memory and the computer program code are further configured to enable the second electronic device to obtain the data from each sending device using a second communication mode based on a corresponding AI model pair selected from the multiple AI model pairs through the at least one processor.

21. A method for a first electronic device of a wireless communication system, comprising notifying a second electronic device of data, wherein: The data is notified via one of the following notification modes: A first notification mode configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and The third notification mode is configured such that the first electronic device sends the data to the second device when neither the first electronic device nor the second electronic device uses an AI model for notifying the data.

22. A method for a second electronic device of a wireless communication system, comprising obtaining data to be notified by a first electronic device, wherein: The data is notified via one of the following notification modes: A first notification mode configured to send or receive the data using an artificial intelligence (AI) model deployed on one side of the first electronic device or the second electronic device; a second notification mode configured to send and receive the data using a pair of jointly trained AI models deployed on both sides of the first electronic device and the second electronic device; and The third notification mode is configured such that the first electronic device sends the data to the second device when neither the first electronic device nor the second electronic device uses an AI model for notifying the data.

23. A first electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to enable the first electronic device to send data to the second electronic device as one of a group of sending devices through the at least one processor, the group of sending devices including one or more sending devices, Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting end device and the second electronic device, and, Wherein, the at least one memory and the computer program code are further configured to, through the at least one processor, enable the first electronic device to process the data using a first AI model in a first AI model pair selected from the multiple AI model pairs and send the processed data to a second electronic device, so that the second electronic device uses a second AI model in the first AI model pair to reconstruct the data based on the processed data received from the first electronic device.

24. The first electronic device as claimed in claim 23, wherein: The first AI model pair is selected based on the priority of the first electronic device in the group of transmitting end devices.

25. The first electronic device as claimed in claim 24, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to receive information indicating the priority from the second electronic device.

26. The first electronic device according to claim 24 or 25, wherein: The priority is determined based on at least one of the following items: a communication scenario between the group of sending devices and the second electronic device, and importance of data sent by each sending device in the group of sending devices to the second electronic device.

27. The first electronic device according to claim 23 or 24, wherein: The first AI model pair is selected based on the accuracy of reconstructing the data.

28. The first electronic device as claimed in claim 27, wherein: The accuracy includes any one of the following items or a combination thereof: a verification result of the reconstructed data, and an accuracy rate calculated based on a comparison between the data and the reconstructed data.

29. The first electronic device according to claim 23 or 24, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to send transmission parameter information indicating a transmission parameter to the second electronic device, or, The at least one memory and the computer program code are configured to, through the at least one processor, cause the first electronic device to receive transmission parameter information indicating a transmission parameter from the second electronic device, The sending parameter information includes at least the ID of the selected AI model pair and information indicating the time to enable the AI ​​model pair.

30. The first electronic device as claimed in claim 29, wherein: The transmission parameter information is transmitted or received via one of the following signaling: radio resource control (RRC) signaling, uplink control information (UCI), or downlink control information (DCI).

31. The first electronic device according to claim 23 or 24, wherein: During the training of the plurality of AI model pairs, the AI ​​model parameters are adjusted based on the accuracy of reconstructing the data fed back by the second electronic device to the first electronic device.

32. A second electronic device for a wireless communication system, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive data from each sender device in a group of sender devices, the group of sender devices including one or more sender devices, Wherein, multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting end device and the second electronic device, and, In which, the at least one memory and the computer program code are further configured to enable the second electronic device to receive, through the at least one processor, processed data obtained by processing the data using the first AI model in the corresponding AI model pair selected from the multiple AI model pairs from each sending end device, and reconstruct the data based on the received processed data using the second AI model in the corresponding AI model pair.

33. The second electronic device as claimed in claim 32, wherein: The corresponding AI model pair is selected based on the priority of each transmitting end device in the group of transmitting end devices.

34. The second electronic device as claimed in claim 33, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to send information indicating the priority to each transmitting end device.

35. The second electronic device according to claim 33 or 34, wherein: The priority is determined based on at least one of the following items: a communication scenario between the group of sending devices and the second electronic device, and importance of data sent by each sending device in the group of sending devices to the second electronic device.

36. The second electronic device as claimed in claim 32 or 33, wherein: The at least one memory and the computer program code are configured to enable the second electronic device to feed back the accuracy of reconstructing the data to each sending end device through the at least one processor, and Wherein, the corresponding AI model pair is selected based on the accuracy.

37. The second electronic device as claimed in claim 36, wherein: The accuracy includes any one of the following items or a combination thereof: a verification result of the reconstructed data, and an accuracy rate calculated based on a comparison between the data and the reconstructed data.

38. The second electronic device according to claim 32 or 33, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to send transmission parameter information indicating a transmission parameter to the first electronic device, or, The at least one memory and the computer program code are configured to, through the at least one processor, cause the second electronic device to receive transmission parameter information indicating a transmission parameter from the first electronic device, The sending parameter information includes at least the ID of the selected AI model pair and information indicating the time to enable the AI ​​model pair.

39. The second electronic device as claimed in claim 38, wherein: The transmission parameter information is transmitted or received via one of the following signaling: radio resource control (RRC) signaling, uplink control information (UCI), or downlink control information (DCI).

40. The second electronic device according to claim 32 or 33, wherein: The at least one memory and the computer program code are configured to enable the second electronic device to feedback the reconstruction accuracy of the data through the at least one processor during the training of the multiple AI model pairs, so that the AI ​​model parameters are dynamically adjusted based on the accuracy.

41. A method for a first electronic device of a wireless communication system, comprising the first electronic device as one of a group of transmitting devices sending data to a second electronic device, the group of transmitting devices comprising one or more transmitting devices, in, Multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and, The method further includes processing the data using a first AI model in a first AI model pair selected from the multiple AI model pairs and sending the processed data to a second electronic device, so that the second electronic device uses a second AI model in the first AI model pair to reconstruct the data based on the processed data received from the first electronic device.

42. A method for a second electronic device of a wireless communication system, comprising receiving data from each sender device in a group of sender devices, the group of sender devices comprising one or more sender devices, in, Multiple artificial intelligence (AI) model pairs that have been jointly trained are deployed on both sides of each transmitting device and the second electronic device, and, The method further includes receiving processed data from each sending end device by processing the data using a first AI model in a corresponding AI model pair selected from the multiple AI model pairs, and reconstructing the data based on the received processed data using a second AI model in the corresponding AI model pair.

43. A non-transitory computer-readable storage medium storing executable instructions, which when executed implement the method of any one of claims 21, 22, 41 and 42.

44. A computer program product comprising executable instructions which, when executed, implement the method of any one of claims 21, 22, 41 and 42.

Images