Monitoring data processing model for channel information recovery
By performing parallel measurements and difference comparisons on uplink and downlink channels, and monitoring the data processing model, the problem of difficulty in updating the channel information recovery model in the prior art is solved, achieving efficient channel information recovery and reducing the computational burden of the communication system.
Patent Information
- Application Number
- CN202080106315.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-16
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2040-10-16
AI Technical Summary
Existing technologies struggle to effectively monitor and update channel information recovery models in wireless communication, leading to increased computational overhead and complexity in communication systems, and making it difficult to obtain accurate channel state information in real-world environments.
By performing parallel measurements on the uplink and downlink channels, the data processing model monitors channel information to recover the model, reducing the need for additional feedback. The reference signal and feedback signal are used to compare the differences in channel information and update the model.
It significantly reduces overhead and computational workload in communication systems, improves the efficiency and accuracy of channel information recovery, and reduces the implementation complexity of terminal equipment.
Smart Images

Figure CN116325872B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate generally to the field of telecommunications, and in particular to methods, devices, apparatuses, and computer-readable storage media for monitoring a data processing model for channel information recovery. Background Art
[0002] In wireless communications, channel information, such as channel state information (CSI), refers to known channel characteristics of a communication link. This information describes how the signal propagates from the transmitter to the receiver and represents the combined effects of, for example, scattering, fading, and power attenuation over distance. CSI makes it possible to adapt the transmission to the current channel conditions, which is crucial for reliable communication at high data rates in multi-antenna systems. Several solutions for obtaining CSI have been proposed. Therefore, it is very important to monitor whether a solution for obtaining CSI is available. Summary of the invention
[0003] In general, example embodiments of the present disclosure provide a solution for monitoring a data processing model for channel information recovery.
[0004] In a first aspect, a first device is provided. The first device includes: at least one processor; and at least one memory including computer program code; the at least one memory and the computer program code are configured to, together with the at least one processor, enable the first device to: receive a first reference signal from at least one second device on an uplink channel. The first device is also caused to use a data processing model to determine first channel information about an uplink channel based at least in part on the reference signal. The first device is also caused to determine the difference between the first channel information and the second channel information estimated based on the reference signal. The first device is also caused to use the data processing model to recover third channel information about a downlink channel from a feedback signal from at least one second device. The first device is also caused to update the data processing model based on the above difference and the third channel information.
[0005] In a second aspect, a second device is provided. The second device includes: at least one processor; and at least one memory including computer program code; the at least one memory and the computer program code are configured to, together with the at least one processor, cause the second device to: send a first reference signal to the first device on an uplink channel, the first reference signal being used to determine first channel information and second channel information about the uplink channel, and the first channel information being used to determine a data processing model to be used to recover channel information about a downlink channel between the first device and the second device. The second device is also caused to send a feedback signal to the first device, the feedback signal being used to recover third channel information about the downlink channel between the first device and the second device.
[0006] In a third aspect, a method is provided. The method includes receiving a first reference signal from at least one second device on an uplink channel at a first device. The method also includes determining first channel information about the uplink channel based at least in part on the reference signal using a data processing model. The method also includes determining a difference between the first channel information and second channel information estimated based on the reference signal. The method also includes recovering third channel information about the downlink channel from a feedback signal from at least one second device using the data processing model. The method also includes updating the data processing model based on the difference and the third channel information.
[0007] In a fourth aspect, a method is provided. The method includes sending a first reference signal to a first device on an uplink channel at a second device, the first reference signal being used to determine first channel information and second channel information about the uplink channel, and the first channel information being used to determine a data processing model to be used to recover channel information about a downlink channel between the first device and the second device. The method also includes sending a feedback signal to the first device, the feedback signal being used to recover third channel information about the downlink channel between the first device and the second device.
[0008] In a fifth aspect, an apparatus is provided. The apparatus includes a component for receiving a first reference signal from at least one second device on an uplink channel at a first device; a component for determining first channel information about the uplink channel based at least in part on the reference signal using a data processing model; a component for determining a difference between the first channel information and second channel information estimated based on the reference signal; a component for recovering third channel information about the downlink channel from a feedback signal from at least one second device using the data processing model; and a component for updating the data processing model based on the difference and the third channel information.
[0009] In a sixth aspect, an apparatus is provided. The apparatus includes a component for sending a first reference signal to a first device on an uplink channel at a second device, the first reference signal being used to determine first channel information and second channel information about the uplink channel, and the first channel information being used to determine a data processing model to be used to recover channel information about a downlink channel between the first device and the second device; and a component for sending a feedback signal to the first device, the feedback signal being used to recover third channel information about the downlink channel between the first device and the second device.
[0010] In a seventh aspect, a computer-readable medium is provided, wherein the computer-readable medium includes program instructions for causing an apparatus to at least execute the method according to any one of the third aspect and the fourth aspect.
[0011] It should be understood that the invention summary is not intended to determine the key or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Some example embodiments will now be described with reference to the accompanying drawings, in which:
[0013] Figure 1 An example communication environment is shown in which example embodiments of the present disclosure may be implemented;
[0014] Figure 2 shows a simplified block diagram of a training model according to some example embodiments of the present disclosure;
[0015] Figure 3 shows a signaling flow for applying uplink channel information to determine a data processing model deployed for downlink use according to some example embodiments of the present disclosure;
[0016] Figure 4 A schematic diagram showing a subframe structure according to some example embodiments of the present disclosure;
[0017] Figure 5 A flowchart showing a method implemented at a first device according to some example embodiments of the present disclosure is shown;
[0018] Figure 6 A flowchart showing a method implemented at a second device according to some other example embodiments of the present disclosure is shown;
[0019] Figure 7 shows a simplified block diagram of an apparatus suitable for implementing an example embodiment of the present disclosure; and
[0020] Figure 8 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.
[0021] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION
[0022] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described only to illustrate and help those skilled in the art to understand and implement the present disclosure, and do not represent any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various other ways except for the way described below.
[0023] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
[0024] In this disclosure, references to "one embodiment," "an embodiment," and "an example embodiment" indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include the particular feature, structure, or characteristic. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, those skilled in the art believe that it is within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.
[0025] It should be understood that although the terms "first" and "second" etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.
[0026] The terms used herein are only used to describe specific embodiments and are not intended to limit the example embodiments. As used herein, the singular forms "a", "an", and "the" also include the plural forms, unless the context clearly indicates otherwise. It is further understood that the terms "comprises", "comprising", "has", "having", "includes", and / or "including" when used herein specify the presence of the features, elements, and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.
[0027] As used in this application, the term "circuitry" may refer to one, more, or all of the following:
[0028] (a) a pure hardware circuit implementation (such as an implementation using only analog and / or digital circuitry), and
[0029] (b) a combination of hardware circuitry and software such as (where applicable):
[0030] (i) a combination of analog and / or digital hardware circuits and software / firmware, and
[0031] (ii) any portion of a hardware processor(s) with software, including digital signal processor(s), software and memory(s), which work together to enable a device (such as a mobile phone or server) to perform various functions, and
[0032] (c) Hardware circuits and / or processor(s), such as microprocessor(s) or portions of microprocessor(s), that require software (e.g., firmware) to operate, but which may not be present when the software is not required for operation.
[0033] This definition of circuitry applies to all uses of the term in this application, including in any claims. As another example, as used in this application, the term circuitry also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its accompanying software and / or firmware. For example, if applicable to a particular claim element, the term circuitry also covers a baseband integrated circuit or processor integrated circuit for a mobile device, or a similar integrated circuit in a server, cellular network device, or other computing or network device.
[0034] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, such as Long Term Evolution (LTE), Advanced LTE (LTE-a), Wideband Code Division Multiple Access (WCDMA), High Speed Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. In addition, the communication between the terminal device and the network device in the communication network can be performed according to any suitable generation of communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, future fifth generation (5G) communication protocol, and / or any other protocol currently known or to be developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communication, there will certainly be future types of communication technologies and systems that can embody the present disclosure. The scope of the present disclosure should not be limited to the above-mentioned systems.
[0035] As used herein, the term "network device" refers to a node in a communication network through which a terminal device accesses the network and receives services from the network. A network device may refer to a base station (BS) or an access point (AP), for example, a NodeB (NodeB or NB), an evolved NodeB (eNodeB or eNB), a NR NB (also known as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, an integrated and access backhaul (IAB) node, a low power node (such as a femto, a pico, etc.), a non-terrestrial network (NTN) or a non-terrestrial network device (such as a satellite network device, a low earth orbit (LEO) satellite, and a geosynchronous orbit (GEO) satellite), an aircraft network device, etc., depending on the terminology and technology applied.
[0036] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not limitation, a terminal device may also be referred to as a communication device, a user equipment (UE), a subscriber station (SS), a portable subscriber station, a mobile station (MS), or an access terminal (AT). The terminal device may include, but is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet computer, a wearable terminal device, a personal digital assistant (PDA), a portable computer, a desktop computer, an image capture terminal device (such as a digital camera), a game terminal device, a music storage and playback device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded device (LEE), a laptop vehicle-mounted device (LME), a USB dongle, a smart device, a wireless customer premises equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical equipment and applications (e.g., remote surgery), industrial equipment and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automated processing chain), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.
[0037] As mentioned above, how to obtain CSI is very important for communication performance. Multiple-input multiple-output (MIMO) based on machine learning (ML) has attracted great attention and shown its advantages, especially in physical layer solutions such as beamforming and channel state information (CSI) acquisition. ML-based massive MIMO solutions can provide performance enhancement and reduce computational complexity, overhead, and latency.
[0038] Many ML schemes for CSI acquisition (e.g., including channel estimation, feedback, etc.) and beamforming can use statistical channel models, ray tracing generated data, or measured data to train neural networks (NNs) offline for analysis. Since the data set used in pre-training cannot fully represent the real environment, when such a NN is deployed in practice, further training is required to update the weights of the pre-trained NN. In some other cases, the NN can also be trained directly in the real scenario of the deployment. For example, in CSI feedback and channel estimation applications, the training of the NN requires paired data sets (e.g., real or "reference" CSI and compressed CSI), however, it is difficult to obtain real CSI in practice. Some conventional techniques only assume that accurate CSI can be obtained to train or update the NN in deployment.
[0039] During the implementation of NN, one problem is that during the NN operation phase, the NN may not always work. Therefore, a monitoring mechanism is needed to detect errors or failures of the NN.
[0040] According to an embodiment of the present disclosure, a solution for monitoring a data processing model to obtain channel information is proposed. Two parallel measurements made by the data processing model for both the uplink channel and the downlink channel are used to determine whether the data processing model is usable. In this way, it does not require additional feedback, which significantly reduces the overhead and computational workload in the communication system.
[0041] Figure 1 A schematic diagram of a communication environment 100 in which embodiments of the present disclosure may be implemented is shown. The communication environment 100 includes a first device 110. The communication environment 100, as part of a communication network, also includes devices 120-1, 120-2, ..., 120-N, which may be collectively referred to as "second device(s) 120". The first device 110 and the second device 120 may communicate with each other.
[0042] The communication environment 100 may include any suitable number of devices and cells. In the communication environment 100, the first device 110 and the second device 120 may transmit data and control information to each other. In the case where the first device 110 is a network device and the second device 120 is a terminal device, the link from the second device 120 to the first device 110 is called an uplink (UL), and the link from the first device 110 to the second device 120 is called a downlink (DL). The second device 120 and the first device 110 are interchangeable.
[0043] It should be understood that Figure 1 The number of first devices and cells and their connections shown is given for illustrative purposes and does not suggest any limitation. Communication environment 100 may include any suitable number of devices and networks suitable for implementing embodiments of the present disclosure.
[0044] The communication in the communication environment 100 can be implemented according to any appropriate communication protocol(s), including but not limited to cellular communication protocols of the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G) and fifth generation (5G), wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or to be developed in the future. In addition, the communication can utilize any appropriate wireless communication technology, including but not limited to: code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplex (FDD), time division duplex (TDD), multiple input multiple output (MIMO), orthogonal frequency division multiplexing (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM), and / or any other technology currently known or to be developed in the future.
[0045] Figure 2 A simplified block diagram of an apparatus 200 for training a model according to some example embodiments of the present disclosure is shown. The apparatus 200 may be implemented at the first device 110. Alternatively, the apparatus 200 may be implemented at the second device 120. It should be noted that the embodiments of the present disclosure are not limited thereto.
[0046] The apparatus 200 may include a module 220, which may be used to recover uplink information and downlink information using a data processing model. For example, the module 220 may recover downlink channel information from processed downlink information, and recover uplink channel information from processed uplink information. Compare the recovered downlink channel information with the processed channel downlink information, and compare the recovered uplink channel information with the processed channel uplink information. The data processing model will be updated based on the comparison. The apparatus 200 may be implemented in the first device 110. In addition, it does not require additional CSI feedback, which significantly reduces overhead. Since complex CSI processing is not required, it also reduces the implementation workload on the terminal device side.
[0047] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Figure 3 , Figure 3 A signaling flow 300 for training a downlink data processing model using uplink channel information according to an example embodiment of the present disclosure is shown. For discussion purposes, reference will be made to Figure 1 The signaling flow 300 is described. The signaling flow 300 may involve the first device 110 and the second device 120-1. Figure 3As shown, the signaling flow 300 has two parts 310 and 320. It should be noted that these two parts 310 and 320 can occur in any suitable order. For example, the steps in part 310 and the steps in part 320 can be performed in parallel. In other embodiments, the steps in part 310 can be performed before or after part 320.
[0048] The second device 120-1 sends 3005 a first reference signal to the first device 110 on an uplink channel. The first reference signal may be any suitable signal that may be used for channel estimation. For example, the first reference signal may be a sounding reference signal (SRS). Alternatively, a demodulation reference signal may be used.
[0049] In some example embodiments, the second device 120-1 may compensate the reference signal before transmission. For example, the compensation parameter may be determined based on the frequency of the uplink channel (hereinafter referred to as the "first frequency") and the frequency of the downlink channel (hereinafter referred to as the "second frequency"). The second device 120-1 may apply the compensation parameter to the reference signal. For example, the phase of the reference signal may be compensated based on the compensation parameter. From the perspective of the antenna: the response of the antenna array depends on the carrier frequency.
[0050] For example, the reference signal to be sent at the second device 120-1 may be represented as s. Therefore, the compensated reference signal may be represented as The transmission compensation matrix at the second device 120-1 is:
[0051] In some example embodiments, the first device 110 may also compensate the received reference signal. For example, a compensation parameter may be determined based on the first frequency and the second frequency and may be applied to the received reference signal. The first device 110 may compensate the phase of the received reference signal based on the compensation parameter. In some example embodiments, the received reference signal may be represented as:
[0052]
[0053] Where s represents the original reference signal, represents the uplink CSI, and n is additive white Gaussian noise.
[0054] The first device 110 determines 3010 first channel information based on a reference signal on an uplink channel using a data processing model. In some embodiments, the processed channel information may have less information than the original channel information. In some example embodiments, the processed channel information may be generated by compressing the original channel information. Alternatively or additionally, the original channel information may be quantized to obtain the processed channel information. In other embodiments, the processed channel information may be codebook-based information. The processed channel information may be able to represent the original channel information, but is more concise than the first channel information. It should be noted that the processed channel information may be obtained using any suitable processing. The embodiments of the present disclosure are not limited thereto. In some example embodiments, the processed channel information may be obtained in a manner similar to that in which the UE generates the processed UL-CSI. For example, the first device 110 and the second device 120-1 may utilize the same processing to obtain the second channel information and the processed UL-CSI, respectively.
[0055] For example, the first device 110 may determine an original reference signal (e.g., represented as "s" in formula (1)) sent by the second device 120-1. Since the uplink channel between the first device 110 and the second device 120-1 is not an ideal channel, the reference signal sent at the second device 120-1 and the reference signal received at the first device 110 may not be the same. The original reference signal refers to a reference signal without any attenuation, interference, or noise. In some example embodiments, the original reference signal may be predetermined so that the first device 110 can acquire the original reference signal. In some example embodiments, the original channel information may be represented as:
[0056]
[0057] in A is the receiving compensation matrix at the first device 110, which is composed of A T,DL =P T A T,UL accomplish, Indicates uplink CSI.
[0058] Alternatively, the first device 110 may monitor the uplink channel during a predetermined period to receive the reference signal. The first device 110 may receive any suitable number of reference signals. The first channel information may be determined based on the reference signals received during the predetermined period. For example, the first device 110 may receive one or more reference signals within a predetermined duration. Alternatively, if the number of data bursts received by the first device 110 is below a threshold number, the first device 110 may continue to monitor the uplink channel and receive (multiple) reference signals.
[0059] The first device 110 may estimate second channel information about the uplink channel based on the reference signal. For example, the first device 110 may extract uplink CSI from the reference signal. The second channel information may be determined based on the extracted uplink CSI.
[0060] The first device 110 determines 3015 a difference between the first channel information and the second channel information. For example only, the first device 110 may determine a normalized mean square error (NMSE) between the first channel information and the second channel information. The NMSE may be obtained as follows:
[0061]
[0062] where || || F represents the Frobinius norm of the matrix, HUL represents the uplink CSI, represents the recovered CSI (ie, the first information). It should be noted that the difference between the first channel information and the second channel information may be determined using any suitable method. Similarly, the individual NMSE of the channel of the k-th second device may be calculated and represented as M (k) 1.
[0063] In some embodiments, the first device 110 may send 3025 a second reference signal to the second device 120-1 on a downlink channel. For example, the further reference signal may be a CSI reference signal. Alternatively, a demodulation reference signal may be sent.
[0064] The second device 120-1 may determine 3030 channel information about the downlink channel based on the additional reference signal. For example, the second device 120-1 may estimate the channel information about the downlink channel. The second device 120 may further extract the channel information about the downlink channel. For example, the channel information may be compressed. Alternatively, the second device 120-1 may quantize the channel information about the downlink channel.
[0065] The second device 120 - 1 may generate 3035 a feedback signal for the second reference signal. The feedback signal may include the extracted channel information about the downlink channel. The second device 120 - 1 may send 3040 the feedback signal to the first device 110 .
[0066] The first device 110 recovers 3045 third channel information about the downlink channel from the feedback signal using the trained data processing model. In this way, the downlink channel information can be recovered without additional overhead. For example only, the third channel information can be represented as:
[0067]
[0068] in represents the mapping from a to the achievable rate, and || represents the determination (product of eigenvalues). The covariance matrix of the effective channel is represents the expected signal power, where F is based on The precoding matrix is designed. ∈ K ...
[0069] The first device 110 updates 3050 the data processing model based on the above difference and the third channel information. For example, the first device 110 may update a certain layer(s) of the data processing model based on the above difference and the third channel information. In this way, the data processing model may be monitored based on the uplink channel information and the downlink channel information. It does not require additional channel state information feedback, which significantly reduces overhead and computational burden.
[0070] In some embodiments, the first device 110 may determine whether the above difference exceeds a threshold difference. For example, the threshold difference may be determined based on previous training performance. The first device 110 may also determine whether the channel quality of the downlink channel exceeds a threshold quality based on the third information. The threshold quality may be determined based on the performance experience of a conventional system. If the above difference of most second devices is lower than the threshold difference, the measurement of the uplink may be considered normal. Similarly, if the channel quality of most second devices exceeds the threshold quality, the measurement of the downlink may be considered normal.
[0071] If the difference is lower than the threshold difference and the channel quality exceeds the threshold quality, then for each second device 120, the first device 110 may further determine whether the difference exceeds the threshold difference and whether the channel quality exceeds the threshold quality. For example, for the k-th second device 120-k, if the difference is lower than the threshold difference and the channel quality exceeds the threshold quality, the data processing model may be maintained. The k-th second device 120-k may be scheduled by the first device 110. Alternatively, for the k-th second device 120-k, if the difference is lower than the threshold difference and the channel quality is lower than the threshold quality, the data processing model may be maintained. The k-th second device 120-k may not be scheduled by the first device 110.
[0072] In other embodiments, for the kth second device 120-k, if the above difference exceeds the threshold difference and the channel quality exceeds the threshold quality, the data processing model can be maintained. The first device 110 can trigger the kth second device 120-k to send a third reference signal on the uplink channel. For example, the first device 110 can send an indication for triggering the transmission of the third reference signal. The kth second device 120-k can send a third reference signal. The first device 110 can re-evaluate the above difference based on the third reference signal. The third reference signal can be any suitable signal that can be used for channel estimation. For example, the third reference signal can be an SRS. Alternatively, a demodulation reference signal can be used. In some example embodiments, the first device 110 can re-evaluate the channel quality based on the feedback signal. Alternatively, the channel quality can be re-evaluated based on another feedback signal received from the kth second device 120-k. In some embodiments, if the re-evaluated difference is lower than the threshold difference, the data processing model may not be updated. Alternatively, the data processing model can be updated based on the third reference signal. For example, if the re-evaluated difference exceeds a threshold difference and the re-evaluated channel quality is lower than a threshold quality, the data processing model needs to be updated. The k-th second device 120-k may be scheduled by the first device 110. Alternatively, for the k-th second device 120-k, if the above difference is lower than a threshold difference and the channel quality is lower than a threshold quality, the data processing model may be maintained. The first device 110 may collect uplink data from the k-th second device 120-k. The k-th second device 120-k may not be scheduled by the first device 110.
[0073] In some embodiments, if the above difference exceeds the threshold difference and the channel quality exceeds the threshold quality, the data processing model may be active. The first device 110 may trigger the second device 120 to send a fourth reference signal on the uplink channel. For example, the first device 110 may send an indication for triggering the transmission of the fourth reference signal. The second device 120 may send a fourth reference signal. The first device 110 may re-evaluate the above difference based on the fourth reference signal. In some example embodiments, the first device 110 may re-evaluate the channel quality based on the feedback signal. Alternatively, the channel quality may be re-evaluated based on another feedback signal received from the k-th second device 120-k. In some embodiments, if the re-evaluated difference is lower than the threshold difference, the data processing model may not be updated. Alternatively, the data processing model may be updated based on the fourth reference signal. If the re-evaluated difference still exceeds the threshold difference and the re-evaluated channel quality is lower than the threshold quality, the data processing model may be updated. The fourth reference signal may be any suitable signal that can be used for channel estimation. For example, the fourth reference signal may be an SRS. Alternatively, a demodulation reference signal may be used.
[0074] In other embodiments, when the measurement of the downlink channel (M2) is abnormal, this indicates that the data processing model has failed, and the first device 110 can switch to a non-NN mode. For example, if the above difference is lower than a threshold difference and the channel quality is lower than a threshold quality, the data processing model may be inactive. The first device 110 may switch to a non-NN processing model. In other embodiments, if the above difference exceeds a threshold difference and the channel quality is lower than a threshold quality, the data processing model may be inactive. The first device 110 may switch to a non-NN processing model, and may update the data processing model based on the first reference signal. Table 1 below shows example criteria and decisions for monitoring the data processing model. It should be noted that Table 1 is only an example and not a limitation.
[0075] Table 1
[0076]
[0077]
[0078]
[0079] In order to accurately monitor the data processing model, the uplink and downlink channels can be in the same situation without too much delay and mismatch. Therefore, the downlink subframe that sends CSI-RS to measure downlink CSI and the uplink subframe that sends uplink training RS should be close. Figure 4 A schematic diagram of a subframe structure is shown. Figure 4 As shown, the uplink reference signal may be transmitted in the uplink subframe 420, and the downlink reference signal may be transmitted in the downlink subframe 430. In other words, the uplink reference signal and the downlink reference signal may be transmitted in consecutive uplink / downlink subframes.
[0080] Figure 5 A flow chart of an example method 500 implemented at a first device 110 according to some example embodiments of the present disclosure is shown. For discussion purposes, the method 500 will be described from the perspective of the first device 110.
[0081] At block 510, the first device 110 receives a first reference signal from the second device 120-1 on an uplink channel. The reference signal may be any suitable signal that may be used for channel estimation. For example, the reference signal may be a sounding reference signal (SRS). Alternatively, a demodulation reference signal may be used.
[0082] In some example embodiments, first device 110 may also compensate the received reference signal. For example, a compensation parameter may be determined based on the first frequency and the second frequency and may be applied to the received reference signal. First device 110 may compensate the phase of the received reference signal based on the compensation parameter.
[0083] In block 520, the first device 110 determines first channel information based on a reference signal on an uplink channel using a data processing model. In some embodiments, the processed channel information may have less information than the original channel information. In some example embodiments, the processed channel information may be generated by compressing the original channel information. Alternatively or additionally, the original channel information may be quantized to obtain the processed channel information. In other embodiments, the processed channel information may be codebook-based information. The processed channel information may be able to represent the original channel information, but is more concise than the first channel information. It should be noted that the processed channel information may be obtained using any suitable processing. The embodiments of the present disclosure are not limited thereto. In some example embodiments, the processed channel information may be obtained in a manner similar to that in which the UE generates the processed UL-CSI. For example, the first device 110 and the second device 120-1 may utilize the same processing to obtain the second channel information and the processed UL-CSI, respectively.
[0084] In some embodiments, the first device 110 may estimate second channel information about the uplink channel based on the reference signal. For example, the first device 110 may extract uplink CSI from the reference signal. The second channel information may be determined based on the extracted uplink CSI.
[0085] At block 530, the first device 110 determines a difference between the first channel information and the second channel information. For example only, the first device 110 may determine a normalized mean square error (NMSE) between the first channel information and the second channel information.
[0086] In some embodiments, the first device 110 may send 3025 a second reference signal to the second device 120-1 on a downlink channel. For example, the further reference signal may be a CSI reference signal. Alternatively, a demodulation reference signal may be sent.
[0087] At block 540, the first device 110 recovers 3045 third channel information about the downlink channel from the feedback signal using the trained data processing model. In this way, the downlink channel information may be recovered without additional overhead.
[0088] In block 550, the first device 110 updates the data processing model based on the above difference and the third channel information. In this way, the data processing model can be monitored based on the uplink channel information and the downlink channel information. It does not require additional channel state information feedback, which significantly reduces overhead and computational burden.
[0089] In some embodiments, the first device 110 may determine whether the above difference exceeds a threshold difference. For example, the threshold difference may be determined based on previous training performance. The first device 110 may also determine whether the channel quality of the downlink channel exceeds a threshold quality based on the third information. The threshold quality may be determined based on the performance experience of a conventional system. If the above difference of most second devices is lower than the threshold difference, the measurement of the uplink may be considered normal. Similarly, if the channel quality of most second devices exceeds the threshold quality, the measurement of the downlink may be considered normal.
[0090] If the difference is lower than the threshold difference and the channel quality exceeds the threshold quality, then for each second device 120, the first device 110 may further determine whether the difference exceeds the threshold difference and whether the channel quality exceeds the threshold quality. For example, for the k-th second device 120-k, if the difference is lower than the threshold difference and the channel quality exceeds the threshold quality, the data processing model may be maintained. The k-th second device 120-k may be scheduled by the first device 110. Alternatively, for the k-th second device 120-k, if the difference is lower than the threshold difference and the channel quality is lower than the threshold quality, the data processing model may be maintained. The k-th second device 120-k may not be scheduled by the first device 110.
[0091] In other embodiments, for the kth second device 120-k, if the above difference exceeds the threshold difference and the channel quality exceeds the threshold quality, the data processing model can be maintained. The first device 110 can trigger the kth second device 120-k to send a third reference signal and re-evaluate the above difference based on the third reference signal. In some example embodiments, the first device 110 can re-evaluate the third channel information based on the feedback signal. Alternatively, the third channel information can be re-evaluated based on another feedback signal received from the kth second device 120-k. In some embodiments, if the re-evaluated difference is lower than the threshold difference, the data processing model may not be updated. Alternatively, the data processing model can be updated based on the third reference signal. For example, if the re-evaluated difference exceeds the threshold difference and the re-evaluated channel quality is lower than the threshold quality, the data processing model needs to be updated. The kth second device 120-k can be scheduled by the first device 110. Alternatively, for the kth second device 120-k, if the above difference is lower than the threshold difference and the channel quality is lower than the threshold quality, the data processing model can be maintained. The first device 110 may collect uplink data from the kth second device 120 - k. The first device 110 may update the processing data model based on the first reference signal. The kth second device 120 - k may not be scheduled by the first device 110.
[0092] In some embodiments, if the above difference exceeds a threshold difference and the channel quality exceeds a threshold quality, the data processing model may be active. The first device 110 may trigger the second device 120 to send a fourth reference signal on the uplink channel and re-evaluate the above difference based on the fourth reference signal. In some example embodiments, the first device 110 may re-evaluate the third channel information based on the feedback signal. Alternatively, the third channel information may be re-evaluated based on another feedback signal received from the kth second device 120-k. In some embodiments, if the re-evaluated difference is lower than the threshold difference, the data processing model may not be updated. Alternatively, the data processing model may be updated based on the fourth reference signal. If the re-evaluated difference still exceeds the threshold difference and the re-evaluated channel quality is lower than the threshold quality, the data processing model may be updated.
[0093] In other embodiments, when the measurement of the downlink channel (M2) is abnormal, this indicates that the data processing model fails, and the first device 110 can switch to a non-NN mode. For example, if the above difference is lower than a threshold difference and the channel quality is lower than a threshold quality, the data processing model can be inactive. The first device 110 can switch to a non-NN processing model. In other embodiments, if the above difference exceeds a threshold difference and the channel quality is lower than a threshold quality, the data processing model can be inactive. The first device 110 can switch to a non-NN processing model and can update the data processing model based on the first reference signal.
[0094] Figure 6 A flow chart of an example method 600 implemented at the second device 120 according to some example embodiments of the present disclosure is shown. For discussion purposes, the method 600 will be described from the perspective of the second device 120. It should be noted that the dashed boxes are optional.
[0095] At block 610, the second device 120-1 sends 3005 a first reference signal to the first device 110 on an uplink channel. The reference signal may be any suitable signal that may be used for channel estimation. For example, the reference signal may be a sounding reference signal (SRS). Alternatively, a demodulation reference signal may be used.
[0096] In some example embodiments, the second device 120-1 may compensate the reference signal before transmission. For example, the compensation parameter may be determined based on the frequency of the uplink channel (hereinafter referred to as the "first frequency") and the frequency of the downlink channel (hereinafter referred to as the "second frequency"). The second device 120-1 may apply the compensation parameter to the reference signal. For example, the phase of the reference signal may be compensated based on the compensation parameter. From the perspective of the antenna: the response of the antenna array depends on the carrier frequency.
[0097] In some embodiments, the second device 120 may receive a second reference signal on a downlink channel from the first device 110. For example, the additional reference signal may be a CSI reference signal. Alternatively, a demodulation reference signal may be sent.
[0098] The second device 120-1 may determine channel information about the downlink channel based on the additional reference signal. For example, the second device 120-1 may estimate the channel information about the downlink channel. The second device 120 may further extract the channel information about the downlink channel. For example, the channel information may be compressed. Alternatively, the second device 120-1 may quantize the channel information about the downlink channel.
[0099] The second device 120-1 may generate 3035 a feedback signal for the second reference signal. The feedback signal may include the extracted channel information about the downlink channel.
[0100] At block 620, the second device 120-1 transmits a feedback signal to the first device 110. The feedback signal is used to recover third channel information about a downlink channel between the first device and the second device.
[0101] In some example embodiments, a first device (e.g., first device 110) capable of performing any method 500 may include a component for performing the corresponding operation of method 500. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The first device may be implemented as a first device 110 or included in the first device 110. In some example embodiments, the component may include at least one processor and at least one memory including computer program code. The at least one memory and the computer program code are configured to cause the execution of the device together with the at least one processor.
[0102] In some embodiments, the apparatus includes a component for receiving a first reference signal from at least one second device on an uplink channel at a first device; a component for determining first channel information about the uplink channel based at least in part on the reference signal using a data processing model; a component for determining a difference between the first channel information and second channel information estimated based on the reference signal; a component for recovering third channel information about the downlink channel from a feedback signal from at least one second device using the data processing model; and a component for updating the data processing model based on the difference and the third channel information.
[0103] In some embodiments, the apparatus further comprises means for sending a second reference signal to at least one second device on a downlink channel; and means for receiving a feedback signal for the second reference signal from at least one second device, the feedback signal comprising the extracted channel information about the downlink channel.
[0104] In some embodiments, the component for determining the first channel information includes: a component for determining an original reference signal sent by at least one second device; a component for determining the original channel information based on the original reference signal and the received reference signal; and a component for recovering the first channel information from the original channel information using a data processing model.
[0105] In some embodiments, the component for updating the processing model includes: a component for determining whether the above-mentioned difference exceeds a threshold difference; a component for determining whether the channel quality of the downlink channel exceeds a threshold quality based on third information; and a component for maintaining the data processing model based on the determination that the above-mentioned difference is lower than the threshold difference and the channel quality exceeds the threshold quality.
[0106] In some embodiments, the apparatus further includes: for a target second device in at least one second device, a component for determining whether the above-mentioned difference exceeds a threshold difference; a component for determining whether the channel quality of a downlink channel between the first device and the target second device exceeds a threshold quality based on third information; and a component for causing scheduling of the target second device to be skipped based on a determination that the above-mentioned difference is lower than the threshold difference and the channel quality is lower than the threshold quality.
[0107] In some embodiments, the apparatus further includes a component for performing the following operations on a target second device in at least one second device: determining whether the above-mentioned difference exceeds a threshold difference; determining whether the channel quality of a downlink channel between the first device and the target second device exceeds a threshold quality based on third information; receiving a third reference signal from the target second device on an uplink channel based on a determination that the above-mentioned difference exceeds the threshold difference and the channel quality exceeds the threshold quality; re-evaluating the above-mentioned difference based on the third reference signal; and re-evaluating the channel quality based on a feedback signal or an additional feedback signal received from at least one second device.
[0108] In some example embodiments, the apparatus further comprises means for updating the data processing model based on the third reference signal.
[0109] In some embodiments, the apparatus further includes a component for performing the following operations on a target second device in at least one second device: determining whether the above-mentioned difference exceeds a threshold difference; determining whether the channel quality of a downlink channel between the first device and the target second device exceeds a threshold quality based on third information; skipping the scheduling of the target second device based on the determination that the above-mentioned difference exceeds the threshold difference and the channel quality is lower than the threshold quality; and updating the data processing model based on the first reference signal.
[0110] In some embodiments, the component for updating the processing model includes: a component for determining whether the above-mentioned difference exceeds a threshold difference; a component for determining whether the channel quality of the downlink channel between the first device and the target second device exceeds the threshold quality based on third information; a component for receiving a fourth reference signal from at least one second device on an uplink channel based on the determination that the above-mentioned difference exceeds the threshold difference and the channel quality exceeds the threshold quality; a component for re-evaluating the above-mentioned difference based on the fourth reference signal; and a component for re-evaluating the channel quality based on the feedback signal or an additional feedback signal received from at least one second device.
[0111] In some example embodiments, the apparatus further comprises means for updating the data processing model based on the fourth reference signal.
[0112] In some embodiments, the component for updating the processing model includes: a component for determining whether the above-mentioned difference exceeds a threshold difference; a component for determining whether the channel quality of the downlink channel exceeds a threshold quality based on third information; a component for making the data processing model inactive based on a determination that the above-mentioned difference is lower than the threshold difference and the channel quality is lower than the threshold quality; and a component for switching to a non-neural network processing mode.
[0113] In some embodiments, the component for updating the processing model includes: a component for determining whether the above-mentioned difference exceeds a threshold difference; a component for determining whether the channel quality of the downlink channel exceeds a threshold quality based on third information; a component for making the data processing model inactive based on the determination that the above-mentioned difference is higher than the threshold difference and the channel quality is lower than the threshold quality; a component for switching to a non-neural network processing mode; and a component for updating the data processing model based on a first reference signal.
[0114] In some example embodiments, a second device (e.g., second device 120) capable of performing any method 600 may include a component for performing the corresponding operation of method 600. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The second device may be implemented as a second device 120 or included in the second device 120. In some example embodiments, the component may include at least one processor and at least one memory including computer program code. The at least one memory and the computer program code are configured to cause the execution of the device together with the at least one processor.
[0115] In some embodiments, the apparatus includes a component for sending a first reference signal to a first device on an uplink channel at a second device, the first reference signal being used to determine first channel information and second channel information about the uplink channel, and the first channel information being used to determine a data processing model to be used to recover channel information about a downlink channel between the first device and the second device; and a component for sending a feedback signal to the first device, the feedback signal being used to recover third channel information about the downlink channel between the first device and the second device.
[0116] In some embodiments, the apparatus further comprises means for receiving a second reference signal from the first device on a downlink channel; and wherein the means for sending the feedback signal comprises means for sending the feedback signal including the extracted channel information on the downlink channel.
[0117] In some embodiments, the apparatus further comprises means for receiving an indication from the first device to trigger transmission of an additional reference signal; and means for sending the additional reference signal to the first device on an uplink channel.
[0118] Figure 7 700 is a simplified block diagram of a device 700 suitable for implementing an example embodiment of the present disclosure. The device 700 may be provided to implement a communication device, such as Figure 1 The first device 110 or the second device 120 is shown. As shown in the figure, the device 700 includes one or more processors 710, one or more memories 720 coupled to the processor 710, and one or more communication modules 740 coupled to the processor 710.
[0119] The communication module 740 is used for two-way communication. The communication module 740 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface necessary for communicating with other network elements. In some example embodiments, the communication module 740 may include at least one antenna.
[0120] Processor 710 may be of any type suitable for the local technology network, and may include, as non-limiting examples, one or more of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 700 may have multiple processors, such as application specific integrated circuit chips that are time slaved to a clock synchronized with a main processor.
[0121] The memory 720 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 724, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 722 and other volatile memories that do not persist during power outages.
[0122] The computer program 730 includes computer executable instructions that are executed by the associated processor 710. The program 730 may be stored in a memory, such as in the ROM 724. The processor 710 may perform any suitable actions and processes by loading the program 730 into the RAM 722.
[0123] The exemplary embodiments of the present disclosure may be implemented by a program 730 so that the device 700 may execute a reference Figures 3 to 6 Any process of the present disclosure discussed. The exemplary embodiments of the present disclosure may also be implemented by hardware or a combination of software and hardware.
[0124] In some example embodiments, the program 730 may be tangibly embodied in a computer-readable medium that may be included in the device 700 (such as in the memory 720) or in other storage devices accessible to the device 700. The device 700 may load the program 730 from the computer-readable medium to the RAM 722 for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, and other magnetic storage and / or optical storage devices. Figure 8 An example of a computer readable medium 800 in the form of an optical storage disk is shown. The computer readable medium has a program 730 stored thereon.
[0125] Generally, various embodiments of the present disclosure may be implemented using hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented using hardware, while other aspects may be implemented using firmware or software that may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the blocks, devices, systems, techniques, or methods described herein may be implemented using hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.
[0126] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer executable instructions, such as instructions included in a program module, which are executed in a device on a target real or virtual processor to perform the above referenced Figures 3 to 8 Any method described herein. Typically, a program module includes a routine, program, library, object, class, component, data structure, etc. that performs a specific task or implements a specific abstract data type. In various embodiments, the functions of the program modules can be combined or split between program modules as needed. The machine executable instructions of the program modules can be executed in a local or distributed device. In a distributed device, the program modules can be located in both local and remote storage media.
[0127] The program code for executing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device so that the program code is implemented when executed by the processor or controller in the flow chart and / or the block diagram. The program code can be executed completely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or completely on a remote machine or server.
[0128] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform various processes and operations as described above. Examples of carriers include signals, computer readable media, etc.
[0129] The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a computer readable storage medium will include an electrical connection with one or more wires, a portable computer floppy disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0130] In addition, although the operations are described in a particular order, this should not be understood as requiring such operations to be performed in the particular order shown or in order or performing all the operations shown to obtain the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limitations on the scope of the present disclosure, but rather descriptions of features that may be specific to a particular embodiment. Certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination.
[0131] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it should be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Instead, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1. A first device, comprising: at least one processor; as well as at least one memory including computer program code; The at least one memory and the computer program code are configured to, together with the at least one processor, cause the first device to: receiving, on an uplink channel, a first reference signal from at least one second device; determining, using a data processing model, first channel information about the uplink channel based at least in part on the first reference signal; determining a difference between the first channel information and second channel information estimated based on the first reference signal; sending, on a downlink channel, a second reference signal to the at least one second device; as well as receiving a feedback signal for the second reference signal from the at least one second device, the feedback signal comprising the extracted channel information about the downlink channel; recovering third channel information about a downlink channel from the feedback signal from the at least one second device using the data processing model; as well as The data processing model is updated based on the difference and the third channel information.
2. The first device according to claim 1, wherein the first device is caused to determine the first channel information by: determining an original reference signal sent by the at least one second device; Determining original channel information based on the original reference signal and the received first reference signal; as well as The first channel information is restored from the original channel information using the data processing model.
3. The first device of claim 1 , wherein the first device is caused to determine to update the processing model by: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; and Based on determining that the difference is below the threshold difference and the channel quality exceeds the threshold quality, the data processing model is maintained.
4. The first device according to claim 3, wherein the first device is further configured to: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; and Based on determining that the difference is lower than the threshold difference and the channel quality is lower than the threshold quality, scheduling of the target second device is skipped.
5. The first device according to claim 3, wherein the first device is further configured to: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; receiving, on the uplink channel, a third reference signal from the target second device based on determining that the difference exceeds the threshold difference and the channel quality exceeds the threshold quality; re-evaluating the difference based on the third reference signal; as well as The channel quality is re-evaluated based on the feedback signal or a further feedback signal received from the at least one second device.
6. The first device according to claim 5, wherein the first device is further configured to: Based on the third reference signal, the data processing model is updated.
7. The first device according to claim 3, wherein the first device is further configured to: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; causing scheduling of the target second device to be skipped based on determining that the difference exceeds the threshold difference and the channel quality is below the threshold quality; as well as Based on the first reference signal, the data processing model is updated.
8. The first device of claim 1 , wherein the first device is caused to update the processing model by: determining whether the difference exceeds a threshold difference; determining, based on third information, whether a channel quality of the downlink channel between the first device and the second device exceeds a threshold quality; receiving, on the uplink channel, a fourth reference signal from the at least one second device based on determining that the difference exceeds the threshold difference and the channel quality exceeds the threshold quality; re-evaluating the difference based on the fourth reference signal; as well as The channel quality is re-evaluated based on the feedback signal or a further feedback signal received from the at least one second device.
9. The first device according to claim 8, wherein the first device is further configured to: Based on the fourth reference signal, the data processing model is updated.
10. The first device of claim 1, wherein the first device is caused to update the processing model by: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; inactivating the data processing model based on determining that the difference is below the threshold difference and the channel quality is below the threshold quality; and Switch to non-neural network processing mode.
11. The first device of claim 1 , wherein the first device is caused to update the processing model by: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; inactivating the data processing model based on determining that the difference is above the threshold difference and the channel quality is below the threshold quality; Switching to non-neural network processing mode; and Based on the first reference signal, the data processing model is updated. 12 . The first device according to claim 1 , wherein the first device is a network device, and the at least one second device is at least one terminal device.
13. A second device, comprising: at least one processor; as well as at least one memory including computer program code; The at least one memory and the computer program code are configured to, together with the at least one processor, cause the second device to: sending a first reference signal to a first device on an uplink channel, the first reference signal being used to determine first channel information and second channel information about the uplink channel, wherein the first channel information is determined based on the first reference signal by using a data processing model, and a difference between the first channel information and the second channel information and third channel information about a downlink channel are used to update the data processing model; receiving a second reference signal from the first device on a downlink channel; as well as A feedback signal including the extracted channel information about the downlink channel is sent to the first device, wherein the data processing model is further used to recover third channel information about the downlink channel from the feedback signal.
14. The second device according to claim 13, wherein the second device is further caused to: receiving, from the first device, an indication for triggering transmission of a further reference signal; and The further reference signal is sent on the uplink channel to the first device. 15 . The second device according to claim 13 , wherein the first device is a network device, and the second device is a terminal device.
16. A method comprising: receiving, at the first device, a first reference signal from at least one second device on an uplink channel; determining, using a data processing model, first channel information about the uplink channel based at least in part on the first reference signal; determining a difference between the first channel information and second channel information estimated based on the first reference signal; sending, on a downlink channel, a second reference signal to the at least one second device; as well as receiving a feedback signal for the second reference signal from the at least one second device, the feedback signal comprising the extracted channel information about the downlink channel; recovering third channel information about a downlink channel from the feedback signal from the at least one second device using the data processing model; as well as The data processing model is updated based on the difference and the third channel information.
17. The method of claim 16, wherein determining the first channel information comprises: determining an original reference signal sent by the at least one second device; Determining original channel information based on the original reference signal and the received first reference signal; as well as The first channel information is restored from the original channel information using the data processing model.
18. The method of claim 16, wherein updating the process model comprises: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; as well as Based on determining that the difference is below the threshold difference and the channel quality exceeds the threshold quality, the data processing model is maintained.
19. The method according to claim 18, further comprising: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; as well as Based on determining that the difference is lower than the threshold difference and the channel quality is lower than the threshold quality, scheduling of the target second device is skipped.
20. The method according to claim 19, further comprising: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; receiving, on the uplink channel, a third reference signal from the target second device based on determining that the difference exceeds the threshold difference and the channel quality exceeds the threshold quality; re-evaluating the difference based on the third reference signal; as well as The channel quality is re-evaluated based on the feedback signal or a further feedback signal received from the at least one second device.
21. The method according to claim 20, further comprising: Based on the third reference signal, the data processing model is updated.
22. The method of claim 18, further comprising: For a target second device in the at least one second device, determining whether the difference exceeds a threshold difference; determining, based on the third information, whether the channel quality of the downlink channel between the first device and the target second device exceeds a threshold quality; causing scheduling of the target second device to be skipped based on determining that the difference exceeds the threshold difference and the channel quality is below the threshold quality; as well as Based on the first reference signal, the data processing model is updated.
23. The method of claim 18, wherein updating the process model comprises: determining whether the difference exceeds a threshold difference; determining, based on third information, whether a channel quality of the downlink channel between the first device and the second device exceeds a threshold quality; receiving, on the uplink channel, a fourth reference signal from the at least one second device based on determining that the difference exceeds the threshold difference and the channel quality exceeds the threshold quality; re-evaluating the difference based on the fourth reference signal; as well as The channel quality is re-evaluated based on the feedback signal or a further feedback signal received from the at least one second device.
24. The method according to claim 23, further comprising: Based on the fourth reference signal, the data processing model is updated.
25. The method of claim 16, wherein updating the process model comprises: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; inactivating the data processing model based on determining that the difference is below the threshold difference and the channel quality is below the threshold quality; and Switch to non-neural network processing mode.
26. The method of claim 16, wherein updating the process model comprises: determining whether the difference exceeds a threshold difference; determining, based on the third information, whether a channel quality of the downlink channel exceeds a threshold quality; inactivating the data processing model based on determining that the difference is above the threshold difference and the channel quality is below the threshold quality; Switching to non-neural network processing mode; and Based on the first reference signal, the data processing model is updated.
27. The method according to any one of claims 16 to 26, wherein the first device is a network device, and the at least one second device is at least one terminal device.
28. A method comprising: At the second device, sending a first reference signal to the first device on an uplink channel, the first reference signal being used to determine first channel information and second channel information about the uplink channel, wherein the first channel information is determined based on the first reference signal by using a data processing model, and a difference between the first channel information and the second channel information and third channel information about a downlink channel are used to update the data processing model; receiving a second reference signal from the first device on a downlink channel; as well as A feedback signal including the extracted channel information about the downlink channel is sent to the first device, wherein the data processing model is further used to recover third channel information about the downlink channel from the feedback signal.
29. The method according to claim 28, further comprising: receiving, from the first device, an indication for triggering transmission of a further reference signal; as well as The further reference signal is sent on the uplink channel to the first device.
30. The method according to any one of claims 28 to 29, wherein the first device is a network device, and the second device is a terminal device.
31. An apparatus comprising: means for receiving, at a first device, a first reference signal from at least one second device on an uplink channel; means for determining, using a data processing model, first channel information about the uplink channel based at least in part on the first reference signal; means for determining a difference between the first channel information and second channel information estimated based on the first reference signal; means for sending a second reference signal to the at least one second device on a downlink channel; as well as means for receiving a feedback signal for the second reference signal from the at least one second device, the feedback signal comprising the extracted channel information about the downlink channel; means for recovering third channel information about a downlink channel from said feedback signal from said at least one second device using said data processing model; as well as Means for updating the data processing model based on the difference and the third channel information.
32. An apparatus comprising: means for sending a first reference signal to a first device on an uplink channel, the first reference signal being used to determine first channel information and second channel information about the uplink channel, wherein the first channel information is determined based on the first reference signal by using a data processing model, and a difference between the first channel information and the second channel information and third channel information about a downlink channel are used to update the data processing model; means for receiving a second reference signal from said first device on a downlink channel; as well as means for sending a feedback signal comprising the extracted channel information about the downlink channel to the first device, wherein the data processing model is further used to recover third channel information about the downlink channel from the feedback signal.
33. A computer readable medium comprising program instructions, the program instructions being used to cause an apparatus to perform the method according to any one of claims 16 to 27, or to perform the method according to any one of claims 28 to 30.
