Communication device and determination method for channel state information report based on artificial intelligence / machine learning

Abstract

The invention discloses a communication device and a method for determining a channel state information (CSI) report on the basis of artificial intelligence (AI) / machine learning (ML), and relates to the technical field of communication devices, in particular to a communication device and a method for determining the channel state information (CSI) report on the basis of the AI (artificial intelligence) / ML (machine learning). The method is performed by a communication device, determining one or more CSI reports based on CSI feedback of AI / ML, where each of the CSI reports comprises at least one of: an output from an autoencoder, a compression ratio, a rank indicator, a quantization level, a true value of enhanced CSI feedback, and / or an ML model monitoring result; and determining a priority rule of the CSI report according to the CSI feedback of the AI / ML.

Description

Technical Field

[0001] The present application relates to the field of wireless communication systems, and more specifically to a communication device and a determination method for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML). For example, the present application relates to a study item description (SID) on AI / ML for a new radio (NR) air interface, which is part of Release 18 developed by the 3rd Generation Partnership Project (3GPP) Radio Access Network (RAN) at the 94e plenary meeting in December 2022. In particular, the present application relates to the determination of priority rules for CSI reports. Background Art

[0002] AI / ML technology is applied in 3GPP RAN1, and multiple application scenarios are identified as research objects, namely CSI feedback enhancement, beam management and positioning. As stated in the new 3GPP SID, although specific AI / ML algorithms and models can be studied for evaluation purposes, these algorithms and models are implementation-specific and do not require standardization.

[0003] Therefore, there is an urgent need for a communication device and method based on artificial intelligence (AI) / machine learning (ML) for determining a channel state information (CSI) report that can solve the problems in the prior art, specifically including a new CSI report based on AI / ML model compression CSI output, solving the problem of overlapping multiple (new) CSI reports on a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH), solving the problem of overlapping data collection and / or model monitoring information with (new) CSI reports, reducing system overhead, providing good communication performance, and / or providing high reliability. Summary of the invention

[0004] The purpose of this application is to provide a communication device and determination method for channel state information (CSI) reporting based on artificial intelligence (AI) / machine learning (ML), which can solve the problems in the prior art, provide auxiliary information for the normal operation of the AI / ML model, reduce system overhead, provide good communication performance, and / or provide high reliability.

[0005] In a first aspect of the present application, a method for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) is performed by a communication device, including determining, by the communication device, one or more CSI reports based on AI / ML-based CSI feedback, wherein each of the CSI reports includes at least one of the following: an output from an autoencoder, a compression ratio, a rank indicator, a quantization level, a true value of enhanced CSI feedback, and / or an ML model monitoring result, and determining, by the communication device, a priority rule for the CSI report based on the AI / ML-based CSI feedback.

[0006] In a second aspect of the present application, a user equipment (UE) includes a memory, a transceiver, and a processor coupled to the memory and the transceiver. The processor is configured to execute the above method.

[0007] In a third aspect of the present application, a base station includes a memory, a transceiver, and a processor coupled to the memory and the transceiver. The processor is configured to execute the above method.

[0008] In a fourth aspect of the present application, a non-transitory machine-readable storage medium stores instructions thereon, and when a computer executes the instructions, the instructions cause the computer to execute the above method.

[0009] In a fifth aspect of the present application, a chip includes a processor configured to call and run a computer program stored in a memory so that a device equipped with the chip executes the above method.

[0010] In a sixth aspect of the present application, a computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the above method.

[0011] In a seventh aspect of the present application, a computer program product comprises a computer program, wherein the computer program enables a computer to execute the above method.

[0012] In an eighth aspect of the present application, a computer program is provided, wherein the computer program enables a computer to execute the above method. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or related technologies, the following briefly introduces the drawings to be described in the embodiments. Obviously, the drawings are only some embodiments of the present application, and ordinary technicians in this field can obtain other drawings based on these drawings without paying any price.

[0014] Figure 1 is a schematic diagram showing a basic autoencoder model for enhancing CSI feedback according to an embodiment of the present application.

[0015] Figure 2 It is a block diagram showing one or more user equipment (UE) and a base station (such as a gNB) in a communication network system according to an embodiment of the present application.

[0016] Figure 3 It is a wireless communication flow chart showing a wireless communication performed by a UE for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) according to an embodiment of the present application.

[0017] Figure 4 It is a wireless communication flow chart showing a wireless communication process performed by a first base station for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) according to an embodiment of the present application.

[0018] Figure 5 is a schematic diagram showing a basic autoencoder model for enhancing CSI feedback according to an embodiment of the present application.

[0019] Figure 6 is a block diagram of a system for wireless communication according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The technical content, structural features, objectives and effects of the present application are described in detail below in conjunction with the accompanying drawings. Specifically, the terms in the embodiments of the present application are only used to describe the purpose of specific embodiments, and are not intended to limit the present application.

[0021] The terms used in this application are used to discuss channel state information (CSI) reporting based on artificial intelligence (AI) / machine learning (ML). The description of the terms is shown in Table 1.

[0022] Table 1:

[0023]

[0024]

[0025] AI / ML technology has been applied in 3GPP RAN1, and several research application scenarios have been identified, namely CSI feedback enhancement, beam management, and positioning. In the current technology, the following are discussed: Spatial-frequency domain CSI compression using bilateral AI model is selected as a representative sub-use case, and the research of other sub-use cases is not excluded. All pre-processing / post-processing, quantization / dequantization are within the scope of this sub-use case. The discussion conclusions include: 1. After the discussion of the evaluation method, the spatial-temporal-frequency domain CSI compression using bilateral model is further explored as a possible sub-use case of CSI feedback enhancement. 2. After the discussion of the evaluation method, the CSI accuracy improvement based on traditional codebook design is further explored using unilateral model as a possible sub-use case of CSI feedback enhancement. 3. After the discussion of the evaluation method, CSI prediction using unilateral model is further explored as a possible sub-use case of CSI feedback enhancement. 4. After the discussion of the evaluation method, CSI-RS configuration and overhead reduction are further explored as possible sub-use cases of CSI feedback enhancement. 5. After the discussion of the evaluation method, resource allocation and scheduling are further explored as possible sub-use cases of CSI feedback enhancement. 6. After the discussion of the evaluation method, joint CSI prediction and compression are further explored as a possible sub-use case of CSI feedback enhancement.

[0026] Some embodiments of the present application discuss cases of CSI feedback enhancement. Figure 1 It is a schematic diagram of a basic autoencoder model for enhancing CSI feedback, which illustrates the basic autoencoder model in an embodiment of the present application. Figure 1 It is illustrated that in some embodiments, the autoencoder compresses the raw CSI-RS value (referred to as raw CSI) / maximum eigenvector and reports its output to the gNB, which decompresses it. The new CSI report includes enhanced CSI feedback generated by the AI / ML model.

[0027] Figure 2It is illustrated that in some embodiments, the communication network system 40 includes one or more user equipment (UE) 10 and a base station (e.g., gNB) 20. In an embodiment of the present application, the communication network system 40 includes one or more UEs 10 and a base station 20 (e.g., a first base station or a second base station). One or more UEs 10 may include a memory 12, a transceiver 13, and a processor 11 coupled to the memory 12 and the transceiver 13. The base station 20 may include a memory 22, a transceiver 23, and a processor 21 coupled to the memory 22 and the transceiver 23. The processor 11 or 21 may be configured to implement the functions, procedures, and / or methods proposed in this description. The various layers of the wireless interface protocol may be implemented in the processor 11 or 21. The memory 12 or 22 is operatively coupled to the processor 11 or 21 to store various information required to operate the processor 11 or 21. The transceiver 13 or 23 is operatively coupled to the processor 11 or 21, and the transceiver 13 or 23 is used to send and / or receive wireless signals.

[0028] The processor 11 or 21 may include an application-specific integrated circuit (ASIC), other chipsets, logic circuits and / or data processing devices. The memory 12 or 22 may include a read-only memory (ROM), a random access memory (RAM), a flash memory, a memory card, a storage medium and / or other storage devices. The transceiver 13 or 23 may include a baseband circuit for processing radio frequency signals. When these embodiments are implemented in software form, the techniques described in this application may be implemented by modules (such as programs, functions, etc.) to perform the functions described herein. The modules may be stored in the memory 12 or 22 and executed by the processor 11 or 21. The memory 12 or 22 may be integrated inside the processor 11 or 21, or may be implemented outside the processor 11 or 21, in which case it may be connected to the processor 11 or 21 by various known communication methods.

[0029] In some embodiments, a method for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) performed by a communication device includes the communication device determining one or more CSI reports based on CSI feedback based on AI / ML, wherein each of the CSI reports includes at least one of the following: an output of an autoencoder, a compression ratio, a rank indicator, a quantization level, a true value of enhanced CSI feedback, and / or an ML model monitoring result; and the communication device determines a priority rule for the CSI report based on the CSI feedback of AI / ML. The communication device may be a UE 10 or a base station 20.

[0030] In some embodiments, the processor 11 is configured to determine one or more CSI reports based on AI / ML-based CSI feedback, wherein each of the CSI reports includes at least one of the following: output of an autoencoder, compression ratio, rank indicator, quantization level, true value of enhanced CSI feedback, and / or ML model monitoring results, and the processor 11 is also configured to determine the priority rules of the CSI report based on the AI / ML CSI feedback. This can solve the problems in the prior art, explicitly including new CSI reports based on AI / ML model compressed CSI output, solving the problem of overlapping multiple (new) CSI reports transmitted on PUSCH or PUCCH, solving the problem of overlapping data collection and / or model monitoring information with (new) CSI reports, reducing system overhead, providing good communication performance, and / or providing high reliability.

[0031] In some embodiments, the processor 21 is configured to determine one or more CSI reports based on AI / ML-based CSI feedback, wherein each of the CSI reports includes at least one of the following: output of an autoencoder, compression ratio, rank indicator, quantization level, true value of enhanced CSI feedback, and / or ML model monitoring results, and the processor 21 is also configured to determine the priority rules of the CSI report based on the AI / ML CSI feedback. This can solve the problems in the prior art, explicitly including new CSI reports based on AI / ML model compressed CSI output, solving the problem of overlapping multiple (new) CSI reports transmitted on PUSCH or PUCCH, solving the problem of overlapping data collection and / or model monitoring information with (new) CSI reports, reducing system overhead, providing good communication performance, and / or providing high reliability.

[0032] Figure 3An example of a wireless communication method 300 for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) performed by a UE is provided, according to an embodiment of the present application. In some embodiments, the method 300 includes: step 302, the UE determines one or more CSI reports based on CSI feedback based on AI / ML, wherein each of the CSI reports includes at least one of the following: an output of an autoencoder, a compression ratio, a rank indicator, a quantization level, a true value of enhanced CSI feedback, and / or an ML model monitoring result; and step 304, the UE determines a priority rule for CSI reports based on the CSI feedback of AI / ML. This can solve the problems in the prior art, explicitly including a new CSI report based on AI / ML model compression CSI output, solving the problem of overlapping of multiple (new) CSI reports when transmitted on PUSCH or PUCCH, solving the problem of overlapping of data collection and / or model monitoring information with (new) CSI reports, reducing system overhead, providing good communication performance, and / or providing high reliability.

[0033] Figure 4 An example of a wireless communication method 400 performed by a base station for determining a channel state information (CSI) report based on artificial intelligence (AI) / machine learning (ML) is provided, according to an embodiment of the present application. In some embodiments, the method 400 includes: step 402, the base station determines one or more CSI reports based on CSI feedback based on AI / ML, wherein each of the CSI reports includes at least one of the following: the output of the autoencoder, the compression ratio, the rank indicator, the quantization level, the true value of the enhanced CSI feedback and / or the ML model monitoring result; and step 404, the base station determines the priority rule of the CSI report based on the CSI feedback of AI / ML. This can solve the problems in the prior art, explicitly include new CSI reports based on AI / ML model compression CSI output, solve the problem of overlapping of multiple (new) CSI reports when transmitted on PUSCH or PUCCH, solve the problem of overlapping of data collection and / or model monitoring information with (new) CSI reports, reduce system overhead, provide good communication performance, and / or provide high reliability.

[0034] In some embodiments, each of the CSI reports includes a single CSI report or a part 1 CSI report and a part 2 CSI report, a configurable CSI report and / or an unbalanced CSI report. In some embodiments, when each of the CSI reports includes the single CSI report or the part 1 CSI report, the output of the autoencoder and / or the output of the AI / ML model is included in the single CSI report or the part 1 CSI report. In some embodiments, when each of the CSI reports includes the part 2 CSI report, the output of the compressed CSI from the AI / ML model is included in the part 2 CSI report. In some embodiments, when each of the CSI reports is the configurable CSI report, whether the configurable CSI report includes the single CSI report or the part 1 CSI report and the part 2 CSI report, and the configurable CSI report is determined by the CSI size of the base station or each of the CSI reports. In some embodiments, when each of the CSI reports is the unbalanced CSI report, if the unbalanced CSI report includes the part 2 CSI report, it is configured not to report the part 2 CSI report to the base station. In some embodiments, when each of the CSI reports is the unbalanced CSI report including the single CSI report or the part 1 CSI report and the part 2 CSI report, the single CSI report or the part 1 CSI report and the part 2 CSI report are individually configured whether to report.

[0035] In some embodiments, the priority rule of the CSI report based on the AI / ML-based CSI feedback is related to an aperiodic CSI report to be carried on a physical uplink shared channel (PUSCH), a semi-persistent CSI report to be carried on the PUSCH, a semi-persistent CSI report to be carried on a physical uplink control channel (PUCCH), and / or a periodic CSI report to be carried on the PUCCH. In some embodiments, the priority rule of the CSI report refers to a priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M sc+s, where: y=0 indicates the aperiodic CSI report to be carried on the PUSCH, y=1 indicates the semi-persistent CSI report to be carried on the PUSCH, y=2 indicates the semi-persistent CSI report to be carried on the PUCCH, and y=3 indicates the periodic CSI report to be carried on the PUCCH; k=0 indicates that the CSI report carries layer 1 reference signal received power (L1-RSRP) or layer 1 signal-to-noise and interference ratio (L1-SINR), and k=1 indicates that the CSI report does not carry the L1-RSRP or the L1-SINR; c indicates a serving cell index, N cells is the value of the high-level parameter maxNrofServingCells; s is the report configuration ID, M s is the value of the high-level parameter maxNrofCSI-ReportConfigurations. In some embodiments, k is also associated with data collection and / or model monitoring. In addition, in this technical solution, parameters k=2 and / or k=3 are associated with data collection and / or model monitoring, and the details will be described in the following examples.

[0036] In some embodiments, the priority rule of the CSI report refers to the priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s l+M s c+s or Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s k+N cells ·M s l+M sc+s, where: y=0 indicates the aperiodic CSI report to be carried on the PUSCH, y=1 indicates the semi-persistent CSI report to be carried on the PUSCH, y=2 indicates the semi-persistent CSI report to be carried on the PUCCH, and y=3 indicates the periodic CSI report to be carried on the PUCCH; k=0 indicates that the CSI report carries layer 1 reference signal received power (L1-RSRP) or layer 1 signal-to-noise and interference ratio (L1-SINR), and k=1 indicates that the CSI report does not carry the L1-RSRP or the L1-SINR; l=0 indicates that the CSI report carries or does not carry data collection (Data_Col) or model monitoring (Model_Monitor) of the AI / ML model; c is the serving cell index, N cells is the value of the high-level parameter maxNrofServingCells; s is the report configuration ID, M s It is the value of the higher-level parameter maxNrofCSI-ReportConfigurations.

[0037] Figure 5 It is a schematic diagram of an example of a basic autoencoder model for enhancing CSI feedback according to an embodiment of the present application. Figure 5 Some embodiments are illustrated to focus on the case of a CSI report, especially about part 2 in a new CSI report. Usually, the CSI of part 1 is included. In some examples, the UE provides the CSI of part 2, while in other examples, the CSI of part 2 is not included in the processing output of the UE.

[0038] Figure 5 As an example, in some embodiments, the autoencoder model has two designs depending on the input. The input is the original CSI (original CSI-RS value) or the eigenvector corresponding to the maximum eigenvalue after channel matrix decomposition. In some embodiments, the eigenvector is called the maximum eigenvector. For the sub-use case of multiple CSI, examples with or without CSI prediction may be added to the description.

[0039] Example:

[0040] CSI report containing part 2:

[0041] In some examples, the new CSI report includes the CSI of Part 2. The new CSI report includes the CSI output compressed by the AI / ML model. The CSI composition of Part 2 is explained as follows. In some examples, the input of the AI / ML model (encoder of the autoencoder) is the (maximum) eigenvector on the UE side, and the output of the AI / ML model on the UE side is the compressed (maximum) eigenvector. This output is included in the new CSI report. As an option, the CSI of Part 2 includes the compressed (maximum) eigenvector. The size of the compressed (maximum) eigenvector is indicated by the RI (rank indicator) and / or quantization level and / or compression ratio contained in the CSI of Part 1. The CSI of Part 1 and the CSI of Part 2 are encoded separately.

[0042] An example description is: "For AI / ML enhanced CSI feedback, Part 1 contains RI, CQI and / or compression ratio indication, and / or quantization level indication, for AI / ML compressed CSI across layers. The fields of Part 1 - RI, CQI, compression ratio indication and / or quantization level - are encoded separately. Part 2 contains the compressed maximum eigenvector of the AI / ML compressed CSI. Part 1 and Part 2 are encoded separately." Another example description is: "For AI / ML enhanced CSI feedback, Part 1 contains RI, CQI and / or quantization level indication, for AI / ML compressed CSI across layers. The fields of Part 1 - RI, CQI, compression ratio indication and / or quantization level - are encoded separately. Part 2 contains the compressed maximum eigenvector and / or compression ratio indication of the AI / ML-assisted CSI. Part 1 and Part 2 are encoded separately." The compression ratio is generally defined as the ratio of the input data size to the output data size in an autoencoder.

[0043] In some examples, data collection (true value) reports are included in the new CSI report. For example, "DataColCSI" as a report type (similar to RI) indicates true value data collection for enhanced CSI feedback, where the original value of the maximum eigenvector is reported. "PreVector" indicates that the input of the AI / ML model or the UE-side autoencoder model is the maximum eigenvector. "DataColCSI" and / or "PreVector" is a report type used as RRC signaling. In some examples, "DataColCSI_PreVector" is a report type and RRC signaling, indicating that both true values ​​and compressed (maximum) eigenvectors are reported simultaneously. Please note that "DataColCSI", "PreVector" and "DataColCSI_PreVector" are not necessarily exactly the same.

[0044] If the report configuration is "DataColCSI_PreVector", the CSI report contains the original value of the maximum eigenvector and the compressed (maximum) eigenvector output by the UE-side AI / ML model. "DataColCSI_PreVector" means that both the true value and the compressed (maximum) eigenvector are reported. Both the original value of the maximum eigenvector and the compressed (maximum) eigenvector are included in Part 2 of the CSI. As an alternative, these original values ​​and compressed eigenvectors can also be included in Part 1 of the CSI.

[0045] If the reporting configuration is "DataColCSI", the UE reports the raw value (i.e., the true value) of the largest eigenvector to the gNB. "DataColCSI" is just a symbolic representation and does not necessarily have a strict form. In some examples, the raw value of the largest eigenvector is included in part 1 of the CSI; in other examples, these raw values ​​are included in part 2 of the CSI; in some examples, the raw values ​​are included in the MAC-CE. In some examples, data collection is a mode that can be activated or deactivated by RRC signaling, MAC-CE, DCI, or pre-configured by RRC / MAC-CE and activated or deactivated by DCI. In some examples, if data collection is activated, the raw value (i.e., the true value) of the largest eigenvector is included in part 1 of the CSI; in other examples, it is included in part 2 or MAC-CE. In some examples, the raw CSI is the encoder input of the UE-side autoencoder / AI / ML model. At the gNB side, the compressed CSI is decompressed. In this use case, it is called AI / ML enhanced CSI feedback. If the input of the UE-side autoencoder / AI / ML model is the original CSI, the output of the model is called AI / ML compressed CSI.

[0046] If the reporting configuration is "DataColCSI", the UE reports the raw value (i.e., the true value) of the largest eigenvector to the gNB. "DataColCSI" is just a symbolic representation and does not necessarily have a strict form. In some examples, the raw value of the largest eigenvector is included in part 1 of the CSI; in other examples, these raw values ​​are included in part 2 of the CSI; in some examples, the raw values ​​are included in the MAC-CE. In some examples, data collection is a mode that can be activated or deactivated by RRC signaling, MAC-CE, DCI, or pre-configured by RRC / MAC-CE and activated or deactivated by DCI. In some examples, if data collection is activated, the raw value (i.e., the true value) of the largest eigenvector is included in part 1 of the CSI; in other examples, it is included in part 2 or MAC-CE. In some examples, the raw CSI is the encoder input of the UE-side autoencoder / AI / ML model. At the gNB side, the compressed CSI is decompressed. In this use case, it is called AI / ML enhanced CSI feedback. If the input of the UE-side autoencoder / AI / ML model is the original CSI, the output of the model is called AI / ML compressed CSI.

[0047] An example may be described as: "For AI / ML enhanced CSI feedback, Part 1 contains cross-layer RI and / or CQI, and / or compression ratio indication, and / or quantization level of AI / ML compressed CSI. The fields of Part 1 – RI, CQI and / or quantization level – are encoded separately. Part 2 contains compressed original CSI and / or compression ratio indication of AI / ML assisted CSI. Part 1 and Part 2 are encoded separately."

[0048] An example may be described as: “For AI / ML enhanced CSI feedback, Part 1 contains the cross-layer compression ratio indication and / or quantization level of the AI / ML compressed CSI. The fields of Part 1 – compression ratio indication and / or quantization level – are coded separately. Part 2 contains the compressed original CSI of the AI / ML assisted CSI. Part 1 and Part 2 are coded separately.

[0049] An example may be described as: "For AI / ML enhanced CSI feedback, Part 1 contains the cross-layer compression ratio indication and / or quantization level of the AI / ML compressed CSI. The fields of Part 1 – compression ratio indication and / or quantization level – are encoded separately. Part 2 contains the compressed original CSI and / or compression ratio indication of the AI / ML assisted CSI. Part 1 and Part 2 are encoded separately."

[0050] In some examples, the data collection (true value) report is included in the new CSI report. If the report configuration is "DataColCSI_PreVector", the CSI report contains the compressed raw CSI and the true value data collection of the raw CSI. Note that the compressed raw CSI and the true value data collection of the raw CSI can be different raw CSI. In some examples, both the true value CSI and the compressed raw CSI are included in part 2 of the CSI. In other examples, these values ​​are included in part 1 of the CSI. "DataColCSI_PreVector" means that the true value of the raw CSI and the compressed raw CSI are reported simultaneously.

[0051] If the reporting configuration is "DataColCSI", data collection (true value CSI) is reported. In some examples, the true value raw CSI is included in part 1 of the CSI; in other examples, it is included in part 2 of the CSI; in other examples, it is included in the MAC-CE. In some examples, the true value raw CSI is quantized before reporting and dequantized at the gNB.

[0052] In some examples, data collection is a mode that can be activated or deactivated. Activation or deactivation can be performed via RRC signaling / MAC-CE / DCI, or pre-configured via RRC / MAC-CE and activated or deactivated by DCI. In some examples, if data collection is activated, the true value raw CSI is included in part 1 of the CSI; in other examples, in part 2; or in the MAC-CE. In some examples, the quantization level is a property or hyperparameter of the ML model / autoencoder model and can be implicitly known to the UE and gNB during the model deployment phase. In some examples, part 2 CSI contains quantized compressed raw CSI or (maximum) eigenvectors. These compressed raw CSI or (maximum) eigenvectors are the output of the UE-side AI / ML model encoder.

[0053] Included in a single CSI report or Part 1 CSI report:

[0054] In some examples, the ML model output of the UE-side autoencoder is included in a single CSI report or a Part 1 CSI report. The composition of Part 1 CSI is as follows. The input to the AI / ML model for enhanced CSI feedback is the original CSI on the UE side, or the input to the autoencoder is the original CSI. The original CSI is compressed by the AI / ML model, transmitted over the air interface, and decompressed at the gNB side. The gNB can calculate the rank, so there is no RI (rank indicator) in the CSI report. The quantization level of the UE-side encoder output is included in the CSI report, indicating the size of the compressed original CSI. In some examples, the quantization level is an attribute or hyperparameter of the ML model / autoencoder model, which can be implicitly known to the UE and gNB during the model deployment phase. In some examples, Part 1 CSI contains quantized compressed original CSI, which is the output of the UE-side AI / ML model encoder.

[0055] One example may be described as: “For AI / ML assisted CSI feedback, part 1 CSI contains RI and / or CQI, and compression ratio indication and / or quantization level, for cross-layer feedback of AI / ML assisted CSI. The fields of part 1 – RI and / or CQI, and compression ratio indication, quantization level, and compressed original CSI – are separately encoded.” Another example may be described as: “For AI / ML assisted CSI feedback, part 1 CSI contains RI and / or CQI, and compression ratio indication and / or quantization level, for cross-layer feedback of AI / ML assisted CSI. The fields of part 1 – RI, CQI, compression ratio indication and quantization level, and compressed original CSI – are jointly encoded.” The input of the AI / ML model at the UE side is the maximum eigenvector, or the input of the autoencoder at the UE side is the maximum eigenvector. The maximum eigenvector is compressed by the AI / ML model, transmitted over the air interface and decompressed at the gNB side. The UE shall calculate the rank and report the RI (rank indicator) in the CSI report. The quantization level is included in the CSI report to indicate the size of the compressed original CSI. In some examples, the quantization level is a property or hyperparameter of the ML model / autoencoder model and can be implicitly known to the UE and gNB during the model deployment phase.

[0056] One example may be described as: “For AI / ML assisted CSI feedback, Part 1 CSI contains RI and / or CQI, as well as compression ratio indication and / or quantization level, for cross-layer feedback of AI / ML assisted CSI. The fields of Part 1 – RI, CQI, compression ratio indication, quantization level, and maximum compressed eigenvector – are encoded separately.” Another example may be described as: “For AI / ML assisted CSI feedback, Part 1 CSI contains RI and / or CQI, as well as compression ratio indication and / or quantization level, for cross-layer feedback of AI / ML assisted CSI. The fields of Part 1 – RI, CQI, compression ratio indication, quantization level, and maximum compressed eigenvector – are jointly encoded.”

[0057] Configurable CSI reporting:

[0058] When at least one of {encoder output of the autoencoder, real data collected by data, model monitoring data} is reported, whether the report of CSI feedback consists of a single part, or consists of Part 1 CSI and Part 2 CSI, is determined by at least one of the following methods. In some examples, if the size of the CSI exceeds a threshold, Part 2 CSI includes the autoencoder output in the above example. The threshold is set by RRC signaling / MAC-CE / DCI. The threshold can be configured by the gNB or reported by the UE. Otherwise, it will be included in Part 1 CSI, and the CSI feedback will consist of only one part. In some examples, whether the autoencoder output on the UE side is included in Part 2 CSI, or the report of CSI feedback consists of a single part or Part 1 CSI and Part 2 CSI, is configured by the gNB through RRC signaling / DCI / MAC-CE.

[0059] For example, the configuration is a signaling in a higher layer parameter reportQuantity indicating that the report contains at least one of {encoder output of the autoencoder, collected data for data collection for enhanced CSI feedback (e.g., raw CSI or maximum eigenvector), model monitoring data of the autoencoder model} so that the CSI feedback consists of a single part.

[0060] As an example, CSI being a single part is not limited to CSI feedback enhanced by ML, and the configuration is signaling in a higher layer parameter reportQuantity, indicating that the report contains at least one of {data collection data for time domain or spatial domain beam prediction, model monitoring data for time domain or spatial domain beam prediction, data collection data for positioning, model monitoring data for positioning}, so that the CSI feedback consists of a single part.

[0061] Unbalanced CSI Report:

[0062] In some examples, if Part 2 CSI reports are present, they are intentionally not reported to the gNB. Reporting of Part 1 CSI and Part 2 CSI is separately configurable. Since Part 1 CSI has low time dependency, the gNB can predict or interpolate this information from historical Part 1 CSI. Part 2 CSI is reported at every configured reporting occasion. Part 1 CSI is reported every few reporting occasions. The relevant signaling here is the separate reporting of Part 2 CSI, which can be RRC signaling / DCI field or MAC CE.

[0063] CSI report priority rules:

[0064] When multiple CSI reports overlap, there should be rules to decide which CSI report should be transmitted first. iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s c+s correlation, where:

[0065] y=0 indicates an aperiodic CSI report to be transmitted on PUSCH, y=1 indicates a semi-persistent CSI report to be transmitted on PUSCH, y=2 indicates a semi-persistent CSI report to be transmitted on PUCCH, and y=3 indicates a periodic CSI report to be transmitted on PUCCH; k=0 indicates a CSI report including L1-RSRP or L1-SINR, k=1 indicates a CSI report not including L1-RSRP or L1-SINR; c is the index of the serving cell, N cells is the value of the higher-level parameter maxNrofServingCells; s is reportConfigID, M s is the value of the higher-level parameter maxNrofCSI-ReportConfigurations. It can be understood that the parameter definitions here are y=0,y=1,y=2,y=3,k=0,k=1,c,N cells ,S,Ms are defined the same as in the previous embodiment.

[0066] Example 1: Mixed Instructions

[0067] In some examples, "Data_Col" is used to indicate data collection for an AI / ML model or use case. Additionally, "Model_Monitor" is used to indicate model monitoring for an AI / ML model.

[0068] CSI report and priority value Pri iCSI (u,k,c,s)=2·N cells ·Ms y+N cells ·M s ·k+M s c+s correlation, where:

[0069] y=0 indicates aperiodic CSI report transmitted on PUSCH, y=1 indicates semi-persistent CSI report transmitted on PUSCH, y=2 indicates semi-persistent CSI report transmitted on PUCCH, and y=3 indicates periodic CSI report transmitted on PUCCH;

[0070] k = 0 indicates a CSI report including L1-RSRP or L1-SINR, k = 1 indicates a CSI report not including L1-RSRP or L1-SINR; c is the index of the serving cell, N cells is the value of the higher-level parameter maxNrofServingCells; s is reportConfigID, M s is the value of the higher-level parameter maxNrofCSI-ReportConfigurations. It can be understood that the parameter definitions here (such as y=0,y=1,y=2,y=3,k=0,k=1,c,N cells ,S,Ms) are consistent with the definitions in the above embodiments.

[0071] In some examples, k=2 is used for CSI reports carrying model monitoring information, and k=3 is used for CSI reports carrying data collection data. "k=0 is used for CSI reports carrying L1-RSRP or L1-SINR and not carrying Data_Col or Model_Monitor, k=1 is used for CSI reports not carrying L1-RSRP, L1-SINR, Data_Col, or Model_Monitor, k=2 is used for CSI reports carrying data collection information, and k=3 is used for CSI reports carrying Model_Monitor." Data collection information refers to data and / or information required for data collection.

[0072] In some examples, k=2 is used for CSI reports that carry data collection information, and k=3 is used for CSI reports that carry model monitoring information. "k=0 is used for CSI reports that carry L1-RSRP or L1-SINR and do not carry Data_Col or Model_Monitor, k=1 is used for CSI reports that do not carry L1-RSRP, L1-SINR, Data_Col, or Model_Monitor, k=2 is used for CSI reports that carry Model_Monitor data collection, and k=3 is used for CSI reports that carry Data_Col."

[0073] In some examples, k=2 is used for CSI reports that carry data collection and / or model monitoring information. "k=0 is used for CSI reports that carry L1-RSRP or L1-SINR and do not carry Data_Col or Model_Monitor, k=1 is used for CSI reports that do not carry L1-RSRP, L1-SINR, Data_Col or Model_Monitor, and k=2 is used for CSI reports that carry Model_Monitor data collection and / or carry Data_Col."

[0074] In some examples, k=0 is used for CSI reports that carry data collection and / or model monitoring information. "k=0 is used for CSI reports that carry Data_Col or Model_Monitor, k=1 is used for CSI reports that carry L1-RSRP or L1-SINR and do not carry Data_Col or Model_Monitor, and k=2 is used for CSI reports that do not carry L1-RSRP, L1-SINR or Model_Monitor data collection and / or Data_Col."

[0075] In some examples, k=0 is used for CSI reports that carry data collection information, and k=1 is used for CSI reports that carry model monitoring information. "k=0 is used for CSI reports that carry Data_Col, k=1 is used for CSI reports that carry Model_Monitor, k=1 is used for CSI reports that carry L1-RSRP or L1-SINR and do not carry Data_Col or Model_Monitor, and k=2 is used for CSI reports that do not carry L1-RSRP, L1-SINR or Model_Monitor data collection and / or Data_Col."

[0076] In some examples, k=0 is used for CSI reports that carry model monitoring information, and k=1 is used for CSI reports that carry data collection information. "k=0 is used for CSI reports that carry Model_Monitor, k=1 is used for CSI reports that carry Data_Col, k=1 is used for CSI reports that carry L1-RSRP or L1-SINR and do not carry Data_Col or Model_Monitor, and k=2 is used for CSI reports that do not carry L1-RSRP, L1-SINR or Model_Monitor data collection and / or Data_Col."

[0077] Example 2: Single indication for ML

[0078] In some examples, "Data_Col" represents data collection for AI / ML models / use cases. In addition, "Model_Monitor" represents model monitoring for AI / ML models.

[0079] In some examples, the priority equation can be one of the following: CSI report and priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s ·l+M s c+s related, or CSI report with priority value Pri iCSI (y,k,c,a)=2·N cells ·M s y+N cells ·M s k+N cells ·M s ·l+M s c+s correlation, where:

[0080] y=0 indicates an aperiodic CSI report to be transmitted via PUSCH, y=1 indicates a semi-persistent CSI report to be transmitted via PUSCH, y=2 indicates a semi-persistent CSI report to be transmitted via PUCCH, and y=3 indicates a periodic CSI report to be transmitted via PUCCH; k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, k=1 indicates a CSI report not carrying L1-RSRP or L1-SINR; c is the index of the serving cell, N cells is the value of the high-level parameter maxNrofServingCells; s is reportConfigID, M s It is the value of the higher-level parameter maxNrofCSI-ReportConfigurations.

[0081] In some examples, l=0 indicates that the CSI report does not carry Model_Monitor, or carries Data_Col; otherwise, l=1. In some examples, l=1 indicates that the CSI report carries Model_Monitor, or carries Data_Col; otherwise, l=0. In some examples, l=0 indicates that the CSI report carries Model_Monitor, and l=1 indicates that the CSI report carries Data_Col; otherwise, l=2. In some examples, l=0 indicates that the CSI report carries Model_Monitor, and l=1 indicates that the CSI report does not carry Model_Monitor and Data_Col; otherwise, l=2 indicates that the CSI report carries Data_Col. In some examples, l=0 indicates that the CSI report carries Data_Col, and l=1 indicates that the CSI report carries Model_Monitor; otherwise, l=2.

[0082] Example 3: Improved mode indication

[0083] In some examples, "Data_Col" is used to represent data collection for AI / ML models / use cases. In addition, "Model_Monitor" is used to represent model monitoring for AI / ML models.

[0084] CSI report and priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s c+s correlation, where:

[0085] y=0 indicates aperiodic CSI reporting via PUSCH, y=1 indicates semi-persistent CSI reporting via PUSCH, y=2 indicates semi-persistent CSI reporting via PUCCH, and y=3 indicates periodic CSI reporting via PUCCH;

[0086] k = 0 indicates a CSI report carrying L1-RSRP or L1-SINR, k = 1 indicates a CSI report not carrying L1-RSRP or L1-SINR; c is the index of the serving cell, N cells is the value of the high-level parameter maxNrofServingCells; s is reportConfigID, M s It is the value of the higher-level parameter maxNrofCSI-ReportConfigurations.

[0087] Machine learning generally provides better performance, and reports involving ML have higher priority. Reports the probabilities associated with "k".

[0088] In some examples, if in model monitoring mode and / or data collection mode, k=0 indicates a CSI report carrying a report related to model monitoring or data collection, and k=1 indicates a CSI report that does not carry this information. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, positioning information. Otherwise, k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0089] In some examples, if in model monitoring mode and / or data collection mode, k=0 indicates a CSI report carrying a report related to data collection, k=1 indicates a CSI report carrying a report related to model monitoring, and k=2 indicates a CSI report that does not carry any information. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, positioning information. Otherwise, k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0090] In some examples, if in model monitoring mode and / or data collection mode and / or at least one ML model is activated, k=0 indicates a CSI report carrying a report related to model monitoring, k=1 indicates a CSI report carrying a report related to data collection, and k=2 indicates a CSI report that does not carry any information. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, positioning information. Otherwise, k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0091] In some examples, if in model monitoring mode and / or data collection mode, and / or at least one ML model is activated, k=0 indicates a CSI report carrying a report related to data collection, and k=1 indicates a CSI report that does not carry any information. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, positioning information, and k=2 indicates a CSI report carrying a report related to model monitoring. Otherwise, k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0092] In some examples, if in model monitoring mode and / or data collection mode, and / or at least one ML model is activated, k=0 indicates a CSI report carrying a report related to model monitoring, and k=1 indicates a CSI report that does not carry any information. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, positioning information, and k=2 indicates a CSI report carrying a report related to data collection.

[0093] In another example, the machine learning model has higher complexity and requires higher UE capabilities. Reports related to machine learning have lower priority. iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s ·l+M s c+s associated, or CSI report with priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s k+N cells ·M s ·l+M s c+s is associated, where:

[0094] y=0 indicates an aperiodic CSI report to be transmitted on PUSCH, y=1 indicates a semi-persistent CSI report to be transmitted on PUSCH, y=2 indicates a semi-persistent CSI report to be transmitted on PUCCH, and y=3 indicates a periodic CSI report to be transmitted on PUCCH; k=0 indicates a CSI report carrying L1-RSRP or L1-SINR, k=1 indicates a CSI report not carrying L1-RSRP or L1-SINR; c is the serving cell index, N cells is the value of the higher-layer parameter maxNrofServingCells; s is the reporting configuration ID, M s It is the value of the higher layer parameter maxNrofCSI-ReportConfigurations.

[0095] In some examples, if in model monitoring mode and / or data collection mode, k=0 indicates a CSI report that does not carry information related to model monitoring and / or data collection, and k=1 indicates a CSI report that carries information related to model monitoring or data collection. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, and positioning information. Otherwise, k=0 indicates a CSI report that carries L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0096] In some examples, if in model monitoring mode and / or data collection mode, and / or at least one machine learning model is activated, k=0 indicates a CSI report that does not carry information related to model monitoring and / or data collection, and k=1 indicates a CSI report that carries information related to model monitoring or data collection. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, and positioning information. Otherwise, k=0 indicates a CSI report that carries L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0097] In some examples, if in model monitoring mode and / or data collection mode, and / or at least one machine learning model is activated, k=0 indicates a CSI report that does not carry information related to model monitoring and / or data collection, k=1 indicates a CSI report that carries information related to model monitoring, and k=2 indicates a CSI report that carries information related to model monitoring data collection. Reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by an autoencoder, and positioning information. Otherwise, k=0 indicates a CSI report that carries L1-RSRP or L1-SINR, and k=1 indicates a CSI report that does not carry L1-RSRP or L1-SINR.

[0098] In some examples, if in model monitoring mode and / or data collection mode, and / or at least one machine learning model is activated, k=0 indicates a CSI report that does not carry information related to model monitoring and / or data collection, k=1 indicates a CSI report that carries information related to data collection, and k=2 indicates a CSI report that carries information related to model monitoring; reports related to model monitoring or data collection may include at least one of the following: L1-RSRP, L1-SINR, original CSI / maximum eigenvector, CSI / eigenvector compressed by the autoencoder, and positioning information.

[0099] In summary, some embodiments of the present application relate to determining priority rules for CSI reports based on AI / ML-based CSI feedback. First, it is discussed whether Part 2CSI is needed to constitute a new CSI report. Afterwards, priority rules for new CSI reports are proposed. New CSI features (i.e., the output of the autoencoder) are taken into account. The effects of the present invention include at least one of the following: 1. The new CSI report containing compressed AI / ML output is clarified to clarify its reporting method. 2. When overlapping with the current CSI report (such as CSI before Rel.18, Rel.17, Rel.16, Rel.15, etc.), priority rules are provided to solve the overlapping problem. 3. Priority rules are provided for non-periodic, semi-persistent and periodic CSI with data collection and monitoring. When these CSI reports overlap, a CSI report is selected.

[0100] Figure 6 7 is a block diagram of an exemplary wireless communication system 700 according to an embodiment of the present application. The embodiments described herein may be implemented into a system using any appropriately configured hardware and / or software. Figure 6A system 700 is shown, which includes a radio frequency (RF) circuit 710, a baseband circuit 720, an application circuit 730, a memory / storage device 740, a display 750, a camera 760, a sensor 770, and an input / output (I / O) interface 780, which are coupled to each other at least as shown. The application circuit 730 may include circuits, such as but not limited to one or more single-core or multi-core processors. The processor may include any combination of general-purpose processors and special-purpose processors, such as a graphics processor, an application processor. The processor may be coupled to a memory / storage device and configured to execute instructions stored in the memory / storage device to enable various applications and / or operating systems to run on the system.

[0101] While the present disclosure has been described in connection with what is considered to be the most practical and preferred embodiment, it is to be understood that the present disclosure is not limited to the disclosed embodiment, but is intended to cover various arrangements made without departing from the scope of the broadest interpretation of the appended claims.

Claims

1. A method for determining a channel state information (CSI) report based on artificial intelligence machine learning (AI / ML), executed by a communication device, characterized in that: include: The communication device determines one or more CSI reports based on the AI / ML-based CSI feedback, wherein each of the CSI reports includes at least one of the following: an output from an autoencoder, a compression ratio, a rank indicator, a quantization level, a true value of enhanced CSI feedback, and / or an ML model monitoring result; and The communication device determines a priority rule for the CSI report according to the AI / ML-based CSI feedback.

2. The method according to claim 1, characterized in that Each of the CSI reports includes a single CSI report or a part 1 CSI report and a part 2 CSI report, a configurable CSI report and / or an unbalanced CSI report.

3. The method according to claim 2, characterized in that When each of the CSI reports includes the single CSI report or the part 1 CSI report, the output of the autoencoder and / or the output of the AI / ML model is included in the single CSI report or the part 1 CSI report.

4. The method according to claim 2, characterized in that: When each of the CSI reports includes the part 2 CSI report, the output of the compressed CSI from the AI / ML model is included in the part 2 CSI report.

5. The method according to claim 2, characterized in that: When each of the CSI reports is the configurable CSI report, whether the configurable CSI report includes the single CSI report or the part 1 CSI report and the part 2 CSI report, and the configurable CSI report is determined by the CSI size of the base station or each of the CSI reports.

6. The method according to claim 2, characterized in that When each of the CSI reports is the unbalanced CSI report, if the unbalanced CSI report includes the part 2 CSI report, it is configured not to report the part 2 CSI report to the base station.

7. The method according to claim 2, characterized in that When each of the CSI reports is the unbalanced CSI report including the single CSI report or the part 1 CSI report and the part 2 CSI report, the single CSI report or the part 1 CSI report and the part 2 CSI report are individually configured whether to be reported.

8. The method according to any one of claims 1 to 7, characterized in that The priority rule of the CSI report according to the AI / ML-based CSI feedback is related to the non-periodic CSI report to be carried on the physical uplink shared channel PUSCH, the semi-persistent CSI report to be carried on the PUSCH, the semi-persistent CSI report to be carried on the physical uplink control channel PUCCH and / or the periodic CSI report to be carried on the PUCCH.

9. The method according to claim 8, characterized in that The priority rule of the CSI report refers to the priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s c+s, where: y=0 indicates the aperiodic CSI report to be carried on the PUSCH, y=1 indicates the semi-persistent CSI report to be carried on the PUSCH, y=2 indicates the semi-persistent CSI report to be carried on the PUCCH, and y=3 indicates the periodic CSI report to be carried on the PUCCH; k=0 indicates that the CSI report carries the layer 1 reference signal received power L1-RSRP or the layer 1 signal-to-noise ratio L1-SINR, and k=1 indicates that the CSI report does not carry the L1-RSRP or the L1-SINR; c represents the serving cell index, N cells is the value of the high-level parameter maxNrofServingCells; s is the report configuration ID, M s It is the value of the higher-level parameter maxNrofCSI-ReportConfigurations.

10. The method according to claim 9, characterized in that k is also associated with data collection and / or model monitoring.

11. The method according to claim 8, characterized in that The priority rule of the CSI report refers to the priority value Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s ·k+M s ·l+M s c+s or Pri iCSI (y,k,c,s)=2·N cells ·M s y+N cells ·M s k+N cells ·M s ·l+M s c+s, where: y=0 indicates the aperiodic CSI report to be carried on the PUSCH, y=1 indicates the semi-persistent CSI report to be carried on the PUSCH, y=2 indicates the semi-persistent CSI report to be carried on the PUCCH, and y=3 indicates the periodic CSI report to be carried on the PUCCH; k=0 indicates that the CSI report carries L1-RSRP or L1-SINR, k=1 indicates that the CSI report does not carry the L1-RSRP or the L1-SINR; l=0 indicates that the CSI report carries or does not carry data collection or model monitoring of the AI / ML model; c is the serving cell index, N cells is the value of the high-level parameter maxNrofServingCells; s is the report configuration ID, M s It is the value of the higher-level parameter maxNrofCSI-ReportConfigurations.

12. A user equipment, characterized in that: include: Memory; Transceiver; as well as a processor coupled to the memory and the transceiver; The processor is configured to execute the method of any one of claims 1 to 11.

13. A base station, characterized in that: include: Memory; Transceiver; as well as a processor coupled to the memory and the transceiver; The processor is configured to execute the method of any one of claims 1 to 11.

14. A non-transitory machine-readable storage medium, characterized in that: Instructions are stored thereon, and when a computer executes the instructions, the instructions cause the computer to perform the method of any one of claims 1 to 11.

15. A chip, characterized in that: include: A processor configured to call and run a computer program stored in a memory so that a device equipped with the chip executes a method according to any one of claims 1 to 11.

16. A computer-readable storage medium, characterized in that: A computer program is stored therein, wherein the computer program causes a computer to execute the method of any one of claims 1 to 11.

17. A computer program product, characterized in that Comprising a computer program, wherein the computer program causes a computer to perform the method of any one of claims 1 to 11.

18. A computer program, characterized in that The computer program causes a computer to execute the method according to any one of claims 1 to 11.

Images