Channel state information (CSI) processing method and device

Abstract

The invention provides a channel state information (CSI) processing method and device, and relates to the technical field of communication, according to the channel state information (CSI) processing method provided by the invention, terminal equipment (UE) can receive configuration information sent by network equipment, and the configuration information is used for configuring uplink resources; and when the uplink resource is not enough to be used for reporting all channel state information (CSI), reporting a first CSI in all the CSI to the network device by using a target CSI reporting mode, the target CSI reporting mode comprising an AI-based CSI reporting mode and / or a traditional CSI reporting mode, and the first CSI being obtained by discarding a second CSI in all the CSI. According to the invention, when uplink resources are insufficient, part of CSI can be reasonably discarded, and certain system performance can be ensured.

Description

Channel State Information (CSI) processing method and device Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a method and apparatus for processing channel state information (CSI). Background Art

[0002] Current research and simulation results indicate that artificial intelligence (AI) technology can reduce terminal feedback overhead or improve the accuracy of channel state information (CSI) feedback. The 3rd Generation Partnership Project (3GPP) standardization research has developed a bilateral AI / machine learning (ML) model based on a terminal-side CSI generation model and a network device-side CSI recovery model to achieve compressed CSI feedback and recovery, respectively.

[0003] For bilateral AI / ML-based CSI compression feedback, when uplink resources are insufficient, some information in the AI-based CSI feedback needs to be discarded. However, how to properly discard some CSI while ensuring sufficient system performance is an urgent problem that needs to be solved.

[0004] Summary of the Invention

[0005] The present disclosure provides a channel state information (CSI) processing method and apparatus, which can reasonably discard part of the CSI when uplink resources are insufficient and can ensure certain system performance.

[0006] A first aspect of the present disclosure provides a channel state information (CSI) processing method, which is applied to a terminal device (UE), including:

[0007] receiving configuration information sent by a network device, where the configuration information is used to configure uplink resources;

[0008] When the uplink resources are insufficient for reporting all channel state information CSI, a target CSI reporting method is used to report the first CSI among all the CSIs to the network device, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained after discarding the second CSI among all the CSIs.

[0009] According to a second aspect of the present disclosure, an embodiment provides a channel state information (CSI) processing method, which is applied to a network device and includes:

[0010] Sending configuration information to a terminal device UE, where the configuration information is used to configure uplink resources;

[0011] Receive the first CSI among all channel state information CSI reported by the UE using a target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained by the UE after discarding the second CSI from all the CSIs when the uplink resources are insufficient for reporting all the CSIs.

[0012] According to a third aspect of the present disclosure, an embodiment provides a channel state information (CSI) processing device, which is applied to a terminal device (UE), including:

[0013] A receiving module, configured to receive configuration information sent by a network device, wherein the configuration information is used to configure uplink resources;

[0014] A sending module is used to report the first CSI among all the CSIs to the network device using a target CSI reporting method when the uplink resources are insufficient for reporting all channel state information CSIs, wherein the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained after discarding the second CSI from all the CSIs.

[0015] According to a fourth aspect of the present disclosure, an embodiment provides a channel state information (CSI) processing device, which is applied to a network device and includes:

[0016] A sending module, configured to send configuration information to a terminal device UE, where the configuration information is used to configure uplink resources;

[0017] A receiving module is configured to receive a first CSI among all channel state information CSI reported by the UE using a target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained by the UE after discarding the second CSI from all the CSI when the uplink resources are insufficient for reporting all the CSI.

[0018] The fifth aspect embodiment of the present disclosure provides a communication device, which includes: a transceiver; a memory; and a processor, which is connected to the transceiver and the memory respectively, and is configured to control the wireless signal reception and transmission of the transceiver by executing computer-executable instructions on the memory, and can implement the method of the first aspect embodiment or the second aspect embodiment of the present disclosure.

[0019] The sixth aspect embodiment of the present disclosure provides a computer storage medium, wherein the computer storage medium stores computer-executable instructions; after the computer-executable instructions are executed by a processor, the method of the first aspect embodiment or the second aspect embodiment of the present disclosure can be implemented.

[0020] A seventh aspect of the present disclosure provides a communication system, including a terminal device UE and a network device, wherein:

[0021] The terminal device UE is used to perform the method according to the embodiment of the first aspect of the present disclosure;

[0022] The network device is used to execute the method of the embodiment of the second aspect of the present disclosure.

[0023] The channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure enable a terminal device (UE) to discard the second CSI from all CSIs when the uplink resources configured by the network device are unable to report all CSIs. After obtaining the remaining first CSI, the UE can report the first CSI from all CSIs to the network device using the target CSI reporting method. The technical solution of this disclosure enables reasonable discarding of some CSI information while ensuring certain system performance.

[0024] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0026] FIG1 is a schematic diagram of a flow chart of a channel state information (CSI) processing method according to an embodiment of the present disclosure;

[0027] FIG2 is a schematic flow chart of a method for processing channel state information (CSI) according to an embodiment of the present disclosure;

[0028] FIG3 is a schematic diagram of a flow chart of a channel state information (CSI) processing method according to an embodiment of the present disclosure;

[0029] FIG4 is a schematic diagram of a flow chart of a channel state information (CSI) processing method according to an embodiment of the present disclosure;

[0030] FIG5 is a schematic diagram of a flow chart of a channel state information (CSI) processing method according to an embodiment of the present disclosure;

[0031] FIG6 is a timing diagram of a channel state information (CSI) processing method according to an embodiment of the present disclosure;

[0032] FIG7 is a block diagram of a channel state information (CSI) processing apparatus according to an embodiment of the present disclosure;

[0033] FIG8 is a block diagram of a channel state information (CSI) processing apparatus according to an embodiment of the present disclosure;

[0034] FIG9 is a schematic structural diagram of a communication device according to an embodiment of the present disclosure;

[0035] FIG10 is a schematic structural diagram of a chip provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0037] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application. It should be noted that the embodiments of the present application and the features in the embodiments may be combined with each other unless there is a conflict.

[0038] The terms used in the embodiments of this application are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of this application. The singular forms "a" and "the" used in the embodiments of this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0039] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0040] To facilitate understanding, the terms involved in this embodiment are first introduced.

[0041] 1. First CSI

[0042] The first CSI is the remaining higher-priority CSI after the terminal device UE discards some lower-priority second CSI from all CSI when uplink resources are insufficient to report all channel state information (CSI), based on the CSI discard strategy corresponding to the target CSI reporting method. The size of the remaining transmitted first CSI is less than or equal to the size of the uplink resources.

[0043] 2. Second CSI

[0044] The second CSI is the CSI with a lower priority selected for discard among all CSIs by the terminal device UE based on the CSI discard strategy corresponding to the target CSI reporting mode when uplink resources cannot be used to report all channel state information CSIs.

[0045] 3. Third CSI

[0046] The third CSI is the CSI content reported based on the AI ​​reporting method when the target CSI reporting method is AI-based CSI reporting and traditional CSI reporting through one CSI reporting.

[0047] 4. The Fourth CSI

[0048] The fourth CSI is the CSI content reported based on the traditional CSI reporting method when the target CSI reporting method is AI-based CSI reporting and traditional CSI reporting through one CSI reporting method.

[0049] 5. Codeword quantization information

[0050] The codeword quantization information is a binary bit stream obtained by quantizing the codeword after the CSI generation model compresses the codeword.

[0051] Current research and simulation results demonstrate that the use of artificial intelligence (AI) technology can reduce terminal feedback overhead or improve the accuracy of Channel State Information (CSI) feedback. Furthermore, within the 3rd Generation Partnership Project (3GPP) standardization research, a bilateral AI / machine learning (ML) model based on a terminal-side CSI generation model and a network equipment-side CSI recovery model has been developed to implement compressed CSI feedback and recovery, respectively. Figure 1 below illustrates a schematic diagram of CSI compression feedback and recovery based on a bilateral AI / ML model. The UE compresses the downlink channel information H using the CSI generation model, quantizes it into a binary bit stream, and sends it to the gNB. The gNB then uses the CSI recovery model to recover H', which approximates the original downlink information.

[0052] When rank >= 1, the methods for training the bilateral model of the CSI generation part model and the CSI recovery part model include the following options:

[0053] Option 1 (rank specific): For each rank, train a bilateral model that includes a CSI generation model and a CSI recovery model.

[0054] Option 2 (rank common): For all ranks, only one bilateral model including the CSI generation model and the CSI recovery model is trained.

[0055] Option 3 (layer specific): For each layer, train a bilateral model consisting of a CSI generation model and a CSI recovery model.

[0056] Option 4 (layer common): Only one bilateral model including the CSI generation part model and the CSI recovery part model is trained for all layers.

[0057] For bilateral AI / ML-based CSI compression feedback, when uplink resources are insufficient, some information in the AI-based CSI feedback needs to be discarded. However, how to properly discard some CSI while ensuring sufficient system performance is an urgent problem that needs to be solved.

[0058] To this end, this embodiment proposes a channel state information (CSI) processing method and apparatus, which can reasonably discard part of the CSI when uplink resources are insufficient, and can ensure certain system performance.

[0059] It is understood that the solutions provided by this disclosure can be applied to terminal devices (UEs) or other executable entities. In the following embodiments of this disclosure, the technical solutions of this disclosure are described using terminal devices as examples, but this does not constitute a specific limitation. The terminal device (UE) can be a mobile phone, laptop, tablet computer, POS terminal, vehicle-mounted computer, or other communication device, and is not limited in this disclosure.

[0060] The channel state information (CSI) processing method and apparatus provided in this application are described in detail below with reference to the accompanying drawings.

[0061] Figure 2 shows a schematic flow chart of a method for processing channel state information (CSI) according to an embodiment of the present disclosure. As shown in Figure 2 , the method is applied to a terminal device (UE), and may include the following steps.

[0062] Step 101: Receive configuration information sent by a network device, where the configuration information is used to configure uplink resources.

[0063] In a specific application scenario, before the UE reports channel state information (CSI) to the network device, the network device may send configuration information indicating the availability of uplink resources to the UE. Accordingly, in the embodiments of the present disclosure, after receiving the configuration information, the UE may report CSI to the network device via the uplink channel indicated by the uplink resource.

[0064] Step 102: When uplink resources are insufficient for reporting all channel state information CSI, a first CSI among all CSIs is reported to a network device using a target CSI reporting mode, where the first CSI is obtained by discarding the second CSI among all CSIs.

[0065] In specific application scenarios, before using uplink resources to report CSI to a network device, it is possible to determine whether the uplink resources can support reporting all CSI. If it is determined that the uplink resources can support reporting all CSI, the UE can directly use the uplink resources to report all CSI to the network device. Accordingly, if it is determined that the uplink resources are insufficient to support reporting all CSI, the UE can implement the embodiments of the present disclosure to discard some CSI from all CSI, so that the size of the remaining transmitted CSI is less than or equal to the size of the uplink resources, and further use the uplink resources to report the remaining CSI to the network device.

[0066] Among them, the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method. Different CSI reporting methods can be configured with different CSI discarding strategies. The UE can specifically determine the target CSI reporting method to be adopted based on the signaling indication of the network device. Accordingly, the UE can receive indication information sent by the network device, and the indication information is used to indicate the target CSI reporting method. Accordingly, for the embodiment of the present disclosure, when the first CSI among all CSIs is reported to the network device using the target CSI reporting method: as a possible implementation method, the first CS among all CSIs can be reported to the network device based on the traditional CSI reporting method; as a possible implementation method, the first CS among all CSIs can be reported to the network device based on the AI ​​CSI reporting method; as a possible implementation method, the first CS among all CSIs can be reported to the network device based on the AI ​​CSI reporting method and the traditional CSI reporting method.

[0067] When reporting the first CS of all CSI to the network device based on the traditional CSI reporting method, the non-zero coefficients to be reported are prioritized and some non-zero coefficients are discarded based on the priority sorting results. For example, when using the Rel-16 Type II codebook or the Rel-17 Type II port selection (PS) codebook for CSI feedback, the CSI can be reported in two parts: Part 1 and Part 2. The specific contents of the report are shown in Table 1:

[0068] Table 1: CSI feedback using the Rel-16 Type II codebook or the Rel-17 Type II port selection (PS) codebook

[0069] When uplink resources cannot transmit all CSI reported content, some CSI information needs to be discarded. To achieve CSI discard, the information in Part 2 can be divided into groups G0, G1, and G2. Groups G1 and G2 contain non-zero coefficients of different priorities. The coefficient priority sorting method in the combination coefficients based on the Rel-16 Type II codebook or the Rel-17 Type II PS codebook is as follows:

[0070] Coefficient priority order of Rel-16 Type II codebook Type II codebook:

[0071] Pri(l,i,f)=2·L·υ·π(f)+υ·i+l,with with l=1,2,…,υ,i=0,1,…,2L-1,and f=0,1,…,Mυ -1. Where l is the beam, i is the spatial domain beam index, and f is the frequency domain beam index.

[0072] Or the coefficient priority order of the Rel-17 Type II PS codebook:

[0073] Pri(l,i,f)=K1·υ·f+υ·i+l,with l=1,2,…,v,i=0,1,…,K1-1 and f=0,…,M-1

[0074] The smaller the value of Pri(l,i,f), the higher the priority. Conversely, the lower the priority.

[0075] For the embodiment of the present disclosure, when the first CS in all CSIs is reported to the network device based on the AI-based CSI reporting method, the CSIs are mainly prioritized, and part of the CSIs is discarded based on the priority sorting result, that is, the second CSI is discarded. In determining the second CSI to be discarded from all CSIs: as a possible implementation, all CSIs may be reported according to Part 1 and Part 2, that is, all CSIs may be divided into CSI Part 1 and CSI Part 2, wherein the content included in CSI Part 1 may be the same as or different from the content included in CSI Part 1 divided in a traditional manner, and is not specifically limited herein; CSI Part 2 includes at least codewords or codeword quantization information, and the second CSI to be discarded is determined from the codewords or codeword quantization information included in CSI Part 2 through grouping and priority determination. For the specific implementation process, please refer to the relevant description in step 202 of the embodiment; as a possible implementation, all CSIs may be reported as a whole, that is, no longer divided into Part 1 and Part 2 for reporting, and the second CSI to be discarded is determined from all CSIs through grouping and priority determination. For the specific implementation process, please refer to the relevant description in step 202 of the embodiment. When the first CSI among all CSIs is reported to the network device together using both the AI-based CSI reporting method and the traditional CSI reporting method, the CSIs required to be reported by the two reporting methods can be comprehensively prioritized, and some CSIs, i.e., the second CSI, are discarded based on the priority ranking result. For the specific implementation process, please refer to the relevant description in step 302 of the embodiment.

[0076] In summary, according to the channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure, when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can select, based on the target CSI reporting method, a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solutions of the present disclosure enable reasonable discarding of some CSI information while ensuring certain system performance.

[0077] Figure 3 shows a flow chart of a method for processing channel state information (CSI) according to an embodiment of the present disclosure. As shown in Figure 3 , the method is applied to a terminal device (UE), and as shown in Figure 3 , the embodiment may include the following steps.

[0078] Step 201: Receive configuration information sent by a network device, where the configuration information is used to configure uplink resources.

[0079] For the embodiment of the present disclosure, the specific implementation process can be found in the relevant description of step 101 of the embodiment, which will not be repeated here.

[0080] Step 202: When uplink resources are insufficient for reporting all channel state information (CSI), in response to the target CSI reporting mode being the AI-based CSI reporting mode, determine the second CSI to be discarded among all CSIs, discard the second CSI among all CSIs, and obtain the first CSI among all CSIs.

[0081] For the embodiment of the present disclosure, in response to the target CSI reporting method being an AI-based CSI reporting method, when determining the second CSI to be discarded in all CSIs, it can be reported according to Part 1 and Part 2, that is, all CSI to be reported is divided into CSI Part 1 and CSI Part 2, and CSI Part 2 contains at least codewords or codeword quantization information; further, the second CSI to be discarded can be determined in the codewords or codeword quantization information by grouping and prioritizing the codewords or codeword quantization information in CSI Part 2.

[0082] Accordingly, by grouping and prioritizing the codewords or codeword quantization information in CSI Part 2, when determining the second CSI to be discarded in the codeword or codeword quantization information, as a possible implementation method, the codeword quantization information can be divided into N groups (codeword quantization information groups), and the priority of each group is determined according to the group index (the larger the group index, the lower the priority), and then the codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority, until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0083] When the codeword quantization information is divided into N groups:

[0084] When the model type of the bilateral model is any of Layer common, Layer specific, Rank common, and Rank specific, as a possible implementation method, The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of each transmission layer is placed in the last group of N groups, where v is the transmission rank value reported by the UE. For example, if N=2, when the codeword quantization information is divided into 2 groups, the first The codeword quantization information of the transmission layer is placed in the first group, and the others The codeword quantization information of the transmission layer is placed in the second group.

[0085] When the model type of the bilateral model is any of Layer common, Layer specific, Rank common, and Rank specific, as a possible implementation method, the length of the quantized information corresponding to each transmission layer can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L is the number of codewords output by the CSI generation model of each transmission layer or the length of the quantized information after the codeword is quantized. For example, if N=2, when the codeword quantization information is divided into 2 groups, the length of the quantization information corresponding to each transmission layer can be The codeword quantization information is placed in the first group, and the length of other quantization information is The codeword quantization information is placed in the second group.

[0086] When the model type of the bilateral model is either Rank common or Rank specific, as a possible implementation method, the length of the quantized information corresponding to each transmission layer can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where X is the number of codewords output by the CSI generation model of each transmission layer when the rank is v or the quantization information length after the codeword quantization. For example, if N=2, that is, when the codeword quantization information is divided into 2 groups, the length of the quantization information corresponding to each transmission layer can be The codeword quantization information is placed in the first group, and the length of other quantization information is The codeword quantization information is placed in the second group.

[0087] Accordingly, by grouping and prioritizing the codeword quantization information in CSI Part 2, when determining the second CSI to be discarded in the codeword quantization information, as a possible implementation method, the priority of each codeword or each codeword quantization information corresponding to each transmission layer can be determined, and the codeword or codeword quantization information can be divided into N groups (codeword groups or codeword quantization information groups) in order from high to low priority. For example, the higher the priority, the smaller the group index number; then, the priority of each codeword group or each codeword quantization information group in the N groups is determined according to the group index, and the codeword groups or codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the transmitted first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2. For example, first determine the codeword group or codeword quantization information group with the largest group index number, that is, the lowest priority, as the second CSI to be discarded and discard it, then check whether the size of the first CSI is less than or equal to the size of the uplink resource. If so, transmit the first CSI. If not, continue to determine the codeword group or codeword quantization information group with the second largest index number, that is, the second lowest priority, as the second CSI with discarding and discard it, and so on.

[0088] For example, assuming that the AI / ML model used for AI-based CSI reporting is layer common, that is, all layers use the same AI / ML model, then the number of output codewords of the CSI-based partial model is equal, or the length L of the quantization information after the codeword is quantized is equal. Assuming L = 120 bits, the transmission rank v = 2 selected by the UE, the priority of each codeword or each codeword quantization information corresponding to the first transmission layer is determined based on the transmission layer index or priority calculation formula, which is higher than the priority of each codeword or each codeword quantization information corresponding to the second transmission layer. Further, the Part2 corresponding to the first transmission layer and the second transmission layer can be divided into two groups in descending order of priority, and the codeword quantization information group corresponding to the first transmission layer contains L 1,1 and L 2,1 bits, the codeword quantization information packet corresponding to the second transmission layer contains L 1,2 and L 2,2 bits. Among them, L 1,1 =L 1,2= L / 2 = 60 bits, representing the codeword quantization information of the first half and the second half of the first transmission layer; L 2,1 =L 2,2 = L / 2 = 60 bits represents the codeword quantization information of the first half and the second half of the second transmission layer. Further, if the priority of the four groups of codeword quantization information corresponding to the two transmission layers is determined according to the group index, the order from large to small is: L 1,1 , L 2,1 , L 1,2 , L 2,2 , and then can be ordered from low to high priority (L 2,2 , L 1,2 , L 2,1 , L 1,1 ) sequentially determines the codeword quantization information groups as the second CSI to be discarded until the size of the transmitted first CSI is less than or equal to the size of the uplink resource.

[0089] Among them, when determining the priority of each codeword or each codeword quantization information corresponding to each transmission layer, as a possible implementation method, the priority of each codeword or each codeword quantization information corresponding to each transmission layer can be determined according to the transmission layer index (the larger the transmission layer index, the lower the priority); as a possible implementation method, the priority of each codeword corresponding to each transmission layer can be determined according to the codeword priority calculation formula; as a possible implementation method, the priority of each codeword quantization information corresponding to each transmission layer can be determined according to the quantization information priority calculation formula. The codeword priority calculation formula can be The Y in the codeword priority calculation formula represents the number of codewords contained in each transmission layer; the quantization information priority calculation formula can be: Y in the quantization information priority calculation formula represents the length of the quantization information included in each transmission layer.

[0090] Exemplarily, the priority of each quantization information is determined according to the defined quantization information priority calculation formula, and the priority of each quantization information is determined as shown in Table 2 below. Thereafter, the low-priority codeword quantization information can be determined as the second CSI to be discarded in order of priority (from right to left) until the size of the transmitted first CSI is less than or equal to the size of the uplink resource, where Y represents the length of the quantization information.

[0091] Table 2: Priority sorting of codeword quantization information for each transport layer, with decreasing priority from left to right

[0092] i in the table m,n Indicates the quantization information of the nth codeword in the mth transmission layer, i m,n The value of is determined according to Pri(l).

[0093] For the embodiment of the present disclosure, in response to the target CSI reporting method being the AI-based CSI reporting method, when determining the second CSI to be discarded in all CSIs, all CSIs may also be reported as a whole, that is, no longer divided into Part 1 and Part 2 for reporting. By grouping all CSIs and sorting their priorities, the second CSI to be discarded in all CSIs is determined.

[0094] Accordingly, by grouping all CSIs and sorting their priorities, when determining the second CSI to be discarded among all CSIs, as a possible implementation method, all CSIs can be divided into N groups (CSI groups), the priority of each group can be determined according to the group index, and the CSI groups can be determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0095] When all CSIs are divided into N groups, the length of the corresponding quantized information in all CSIs can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L tot is the total length of all CSI information, The value obtained by rounding it up or down.

[0096] Accordingly, by grouping all CSIs and sorting their priorities, when determining the second CSI to be discarded among all CSIs, as a possible implementation method, the codeword quantization information contained in all CSIs can be divided into N groups (codeword quantization information), the priority of each group is determined according to the group index, and the codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0097] When all codeword quantization information included in the CSI is divided into N groups:

[0098] As a possible implementation method, all CSI The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of each transmission layer is placed in the last group of N groups, where v is the transmission rank value reported by the UE. The value obtained by rounding it up or down.

[0099] As a possible implementation method, the length of the quantized information corresponding to each transmission layer in all CSIs can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L is the number of codewords output by the CSI generation model of each transmission layer or the length of the quantized information after the codeword is quantized. The value obtained by rounding it up or down.

[0100] As a possible implementation method, the length of the quantized information corresponding to each transmission layer in all CSIs can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where X is the number of codewords output by the CSI generation model of each transmission layer when the rank is v or the quantization information length after the codeword quantization. The value obtained by rounding it up or down.

[0101] Step 203: Report the first CSI among all CSIs to the network device.

[0102] In a specific application scenario, when reporting the first CSI of all CSIs to the network device, the target CSI reporting method can also be used to report the input information Input-CSI-NW of the CSI generation model to the network device. Input-CSI-NW represents the input information of the AI / ML model used to generate part of the CSI on the terminal side. If the content of the CSI report also includes Input-CSI-NW, the reported Input-CSI-NW can be reported in one CSI together with the AI-based CSI report and the traditional CSI report. When reporting in one CSI, the reported Input-CSI-NW includes a part that is independent of the above parts and is reported separately.

[0103] In summary, according to the channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure, when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can, based on the target CSI reporting method, select a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solution of the present disclosure, through grouping and priority sorting, can reasonably discard some CSI information while ensuring a certain level of system performance.

[0104] Figure 4 shows a flow chart of a method for processing channel state information (CSI) according to an embodiment of the present disclosure. As shown in Figure 4 , the method is applied to a terminal device (UE), and as shown in Figure 4 , the embodiment may include the following steps.

[0105] Step 301: Receive configuration information sent by a network device, where the configuration information is used to configure uplink resources.

[0106] For the embodiment of the present disclosure, the specific implementation process can be found in the relevant description of step 101 of the embodiment, which will not be repeated here.

[0107] Step 302: When uplink resources are insufficient for reporting all channel state information (CSI), in response to the target CSI reporting mode being the AI-based CSI reporting mode and the traditional CSI reporting mode, determine the second CSI to be discarded among all CSIs, discard the second CSI among all CSIs, and obtain the first CSI among all CSIs.

[0108] For the embodiments of the present disclosure, in response to the target CSI reporting method being an AI-based CSI reporting method and a traditional CSI reporting method, when determining the second CSI to be discarded from all CSIs, the third CSI to be reported under the AI-based CSI reporting method and the fourth CSI to be reported under the traditional CSI reporting method may be first determined; the second CSI may be further determined from the third CSI and the fourth CSI. When determining the second CSI from the third and fourth CSIs, as a possible implementation method, the fourth CSI to be reported under the traditional CSI reporting method may be directly determined as the second CSI to be discarded; as a possible implementation method, the CSI Part 2 corresponding to the third and fourth CSIs may be fused, and the second CSI may be determined from the fused CSI Part 2. That is, all CSI required to be reported by the two reporting methods may be divided into CSI Part 1 and CSI Part 2 according to Part 1 and Part 2 reporting, and the second CSI to be discarded may be further determined from the CSI included in CSI Part 2 through grouping and priority sorting. Specifically, when the second CSI to be discarded is determined in the CSI included in CSI Part2 through group division and priority determination, the fused CSI Part2 can be divided into N groups, the priority of each group can be determined according to the group index, and the CSI Part2 groups can be determined as the second CSI to be discarded in order from low to high priority until the size of the transmitted first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0109] When the third and fourth CSI are combined and all CSI required for reporting by the two reporting methods are divided into CSI Part 1 and CSI Part 2, CSI Part 1 may include RI / CQI, information about the number of codewords per transmission layer or for all transmission layers, and the number of non-zero coefficients for all transmission layers. When reporting CSI Part 1 to a network device, information about the number of codewords per transmission layer or for all transmission layers in CSI Part 1 may be reported based on the AI ​​CSI reporting method, the number of non-zero coefficients for all transmission layers in CSI Part 1 may be reported based on the traditional CSI reporting method, and the RI / CQI in Part 1 may be reported to the network device based on either the AI ​​CSI reporting method or the traditional CSI reporting method. It should be noted that RI / CQI is reported only once and can be calculated based on either the AI-based CSI or the traditional CSI. This can be determined by pre-definition, network configuration, or terminal indication of whether the RI / CQI calculation is based on AI CSI reporting or traditional CSI reporting.

[0110] As shown in Table 1, the reported information for CSI Part 2 corresponding to the fourth CSI can be divided into groups G0, G1, and G2. When fusing the reported information for CSI Part 2 corresponding to the third CSI and the fourth CSI, as a possible implementation, each group of codeword quantization information in the third CSI corresponding to CSI Part 2 can be configured before the G0 group information or after the G2 group information of the fourth CSI corresponding to CSI Part 2. For example, if the third CSI corresponding to CSI Part 2 contains two groups of codeword quantization information A1 and A2, each group of codeword quantization information in the third CSI corresponding to CSI Part 2 can be configured before the G0 group information of the fourth CSI corresponding to CSI Part 2, resulting in the following merged CSI Part 2 reporting information: A1, A2, G0, G1, G2; alternatively, each group of codeword quantization information in the third CSI corresponding to CSI Part 2 can be configured after the G2 group information of the fourth CSI corresponding to CSI Part 2, resulting in the following merged CSI Part 2 reporting information: G0, G1, G2, A1, A2. When fusing the reporting information of the third and fourth CSI corresponding to CSI Part 2, as a possible implementation method, each set of codeword quantization information in the third CSI corresponding to CSI Part 2 can be inserted into different grouping information of the fourth CSI corresponding to CSI Part 2. When the AI-based CSI reporting information is divided into two groups, these two groups of information are respectively included in two of the groups in the traditional CSI reporting Part 2. Alternatively, when the AI-based CSI reporting information is divided into three groups, these two groups of information are respectively included in the three groups in the traditional CSI reporting Part 2. For example, the third CSI corresponds to CSI Part 2 and includes two groups of codeword quantization information B1 and B2. B1 can be inserted into the G0 group information and B2 can be inserted into the G1 group information, or B1 can be inserted into the G0 group information and B2 can be inserted into the G2 group information, etc. For another example, the third CSI corresponds to CSI Part 2 and includes three groups of codeword quantization information B1, B2, and B3. B1 can be inserted into the G0 group information, B2 can be inserted into the G1 group information, and B3 can be inserted into the G2 group information, or B1 can be inserted into the G1 group information, B2 can be inserted into the G0 group information, and B3 can be inserted into the G2 group information, etc.

[0111] For example, assume that AI-based CSI reporting and traditional CSI reporting include two parts, Part 1 and Part 2, through a CSI report. The information in Part 1 is shown in Table 3 below:

[0112] Table 3: CSI information included in Part 1

[0113] Assuming the transmission rank indicated by the RI is 2, traditional CSI feedback is based on the Rel-16 Type II codebook. Assuming the quantized information length L = 120 bits output by the CSI generation model for each layer, each layer is divided into three groups, each containing 40 bits. When AI-based CSI reporting is divided into three groups, these three groups of information are included in Part 2 of the traditional CSI report, as shown in Table 4 below.

[0114] Table 4: CSI information included in Part 1

[0115] In the embodiments of the present disclosure, in response to the target CSI reporting mode being the AI-based CSI reporting mode and the traditional CSI reporting mode, all CSI required for both reporting modes can be reported together as a whole, i.e., the reporting is no longer divided into Part 1 and Part 2. As a possible implementation, the CSI reporting can be divided into three parts: CSI Part 1, CSI Part 2, and CSI Part 3. CSI Part 1 is used to report the content of Part 1 under the traditional CSI (fourth CSI) reporting mode (such as RI, CQI, and the number of non-zero coefficients of all layers), CSI Part 3 is used to report the content of Part 2 under the traditional CSI (fourth CSI) reporting mode (such as G0, G1, and G2 group information), and CSI Part 2 is used to report the content of the AI-based CSI (third CSI) reporting mode. When determining the second CSI to be discarded among all CSIs, the non-zero coefficients in CSI Part 3 that do not comply with uplink resource transmission can be determined as the second CSI. Specifically, the non-zero coefficients that need to be reported can be prioritized, and based on the priority sorting results, some non-zero coefficients can be discarded so that the size of the remaining first CSI is less than or equal to the size of the uplink resource.

[0116] As a possible implementation, CSI reporting can be divided into three parts: CSI Part 1, CSI Part 2, and CSI Part 3. CSI Part 1 is used to report the content of Part 1 under the traditional CSI (fourth CSI) reporting method (such as RI, CQI, and the number of non-zero coefficients of all layers), CSI Part 2 is used to report the content of Part 2 under the traditional CSI (fourth CSI) reporting method (such as G0, G1, and G2 group information), and CSI Part 3 is used to report the third CSI. CSI Part 3 contains at least codewords or codeword quantization information. Furthermore, CSI Part 1 can be used to report the content of Part 1 under the traditional CSI (fourth CSI) reporting method (such as RI, CQI, and the number of non-zero coefficients of all layers). The codeword quantization information in Part 3 is divided into N groups (codeword quantization information groups), and the priority of each group is determined according to the group index, and the codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2; or, the priority of each codeword or each codeword quantization information corresponding to each transmission layer can be determined, and the codeword or codeword quantization information can be divided into N groups (codeword groups or codeword quantization information groups) in order from low to high priority, for example, the higher the priority, the smaller the group index number; then the priority of each group is determined according to the group index, and the codeword groups or codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0117] When the codeword quantization information is divided into N groups:

[0118] As a possible implementation, The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of each transmission layer is placed in the last group of N groups, where v is the transmission rank value reported by the UE. For example, if N=2, when the codeword quantization information is divided into 2 groups, the first The codeword quantization information of the transmission layer is placed in the first group, and the others The codeword quantization information of the transmission layer is placed in the second group.

[0119] As a possible implementation method, the length of the quantized information corresponding to each transmission layer can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L is the number of codewords output by the CSI generation model of each transmission layer or the length of the quantized information after the codeword is quantized. For example, if N=2, when the codeword quantization information is divided into 2 groups, the length of the quantization information corresponding to each transmission layer can be The codeword quantization information is placed in the first group, and the length of other quantization information is The codeword quantization information is placed in the second group.

[0120] As a possible implementation method, the length of the quantized information corresponding to each transmission layer can be The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where X is the number of codewords output by the CSI generation model of each transmission layer when the rank is v or the quantization information length after the codeword quantization. For example, if N=2, that is, when the codeword quantization information is divided into 2 groups, the length of the quantization information corresponding to each transmission layer can be The codeword quantization information is placed in the first group, and the length of other quantization information is The codeword quantization information is placed in the second group.

[0121] When determining the priority of each codeword or each codeword quantization information corresponding to each transmission layer, as a possible implementation method, the priority of each codeword or each codeword quantization information corresponding to each transmission layer can be determined according to the transmission layer index (the larger the transmission layer index, the lower the priority); as a possible implementation method, the priority of each codeword corresponding to each transmission layer can be determined according to the codeword priority calculation formula; as a possible implementation method, the priority of each codeword quantization information corresponding to each transmission layer can be determined according to the quantization information priority calculation formula. The codeword priority calculation formula can be The Y in the codeword priority calculation formula represents the number of codewords contained in each layer; the quantitative information priority calculation formula can be Y in the quantization information priority calculation formula represents the length of the quantization information included in each transmission layer.

[0122] Step 303: Report the first CSI among all CSIs to the network device.

[0123] For the specific implementation process of the embodiment of the present disclosure, please refer to the relevant description in step 202 of the embodiment, which will not be repeated here.

[0124] In summary, according to the channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure, when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can, based on the target CSI reporting method, select a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solution of the present disclosure, through grouping and priority sorting, can reasonably discard some CSI information while ensuring a certain level of system performance.

[0125] FIG5 is a flow chart illustrating a method for processing channel state information (CSI) according to an embodiment of the present disclosure. As shown in FIG5 , the method is applied to a network device, which may be a base station, etc., and is not specifically limited herein. The embodiment may include the following steps.

[0126] Step 401: Send configuration information to the terminal device UE, where the configuration information is used to configure uplink resources.

[0127] In the embodiments of the present disclosure, to enable a UE to report channel state information (CSI) to a network device, the network device may send configuration information indicating the availability of uplink resources to the UE. After receiving the configuration information, the UE may report CSI to the network device via the uplink channel indicated by the uplink resource.

[0128] Step 402: Receive the first CSI among all channel state information CSI reported by the UE using the target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method. The first CSI is obtained by the UE after discarding the second CSI from all CSIs when the uplink resources are insufficient for reporting all CSIs.

[0129] In a specific application scenario, after the network device sends configuration information to the UE, the UE can determine whether the uplink resources can support reporting all CSI before using uplink resources to report CSI to the network device. As a possible application scenario, when the UE determines that the uplink resources can support reporting all CSI, the UE can directly use the uplink resources to report all CSI to the network device. Accordingly, the network device can receive all CSI reported by the UE. As a possible application scenario, when the UE determines that the uplink resources are insufficient to support reporting all CSI, it can discard part of the CSI in all CSIs so that the size of the remaining transmitted CSI can be less than or equal to the size of the uplink resources, and further use the uplink resources to report the remaining CSI to the network device. Accordingly, the network device can receive the first CSI among all the channel state information CSI reported by the UE. The first CSI is obtained after the UE discards the second CSI in all CSIs when the uplink resources are insufficient to report all CSIs.

[0130] Among them, the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method. Different CSI reporting methods can be configured with different CSI discarding strategies. The UE can determine the specific target CSI reporting method to be adopted based on the signaling instructions of the network device. Accordingly, the network device can send indication information to the UE, and the indication information is used to indicate the target CSI reporting method. Accordingly, for the embodiment of the present disclosure, when receiving the first CSI among all channel state information CSI reported by the UE using the target CSI reporting method: as a possible implementation method, the first CS reported by the UE based on the traditional CSI reporting method can be received; as a possible implementation method, the first CS reported by the UE based on the AI ​​CSI reporting method can be received; as a possible implementation method, the first CS reported by the UE based on the AI ​​CSI reporting method and the traditional CSI reporting method can be received. It should be noted that when the uplink resources of the UE cannot be used to report all channel state information CSI, the specific implementation process of determining the second CSI based on the target CSI reporting method and discarding the second CSI can be found in the relevant descriptions in steps 102, 202, and 302 of the embodiment, which will not be repeated here.

[0131] In a specific application scenario, when the UE reports the first CSI among all CSIs to the network device, it can also use the target CSI reporting method to report the input information Input-CSI-NW of the CSI generation part model to the network device. Input-CSI-NW represents the input information of the AI / ML model used to generate part of the CSI on the terminal side. If the content of the CSI report also includes Input-CSI-NW, the reported Input-CSI-NW can be reported in one CSI together with the AI-based CSI report and the traditional CSI report. When reporting in one CSI, the reported Input-CSI-NW includes a part that is independent of the above-mentioned parts and is reported separately. Accordingly, for the embodiment of the present disclosure, the network device can also receive the input information Input-CSI-NW of the CSI generation part model reported by the UE using the target CSI reporting method.

[0132] In summary, according to the channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure, when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can, based on the target CSI reporting method, select a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solution of the present disclosure, through grouping and priority sorting, can reasonably discard some CSI information while ensuring a certain level of system performance.

[0133] Figure 6 is a timing diagram of a channel state information CSI processing method provided according to an embodiment of the present disclosure. The method is applied to a communication system, which includes a terminal device UE and a network device. The network device sends configuration information to the terminal device UE, and the configuration information is used to configure uplink resources; when the uplink resources of the terminal device UE cannot be used to report all channel state information CSI, the terminal device UE determines the second CSI to be discarded in all CSIs based on the target CSI reporting method; the terminal device UE discards the second CSI in all CSIs and obtains the first CSI in all CSIs; the terminal device UE reports the first CSI in all CSIs to the network device.

[0134] Step 501: The network device sends configuration information to the terminal device UE, where the configuration information is used to configure uplink resources.

[0135] In the embodiments of the present disclosure, to enable a UE to report channel state information (CSI) to a network device, the network device may send configuration information indicating the availability of uplink resources to the UE. After receiving the configuration information, the UE may report CSI to the network device via the uplink channel indicated by the uplink resource.

[0136] Step 502: When uplink resources are insufficient for reporting all channel state information CSI, the terminal device UE determines a second CSI to be discarded among all CSIs based on a target CSI reporting mode.

[0137] Step 503: The terminal device UE discards the second CSI in all CSIs and obtains the first CSI in all CSIs.

[0138] For the specific implementation process of steps 502 and 503 of the embodiment, please refer to the relevant descriptions in steps 102, 202, and 302 of the embodiment, and will not be repeated here.

[0139] Step 504: The terminal device UE reports the first CSI to the network device.

[0140] In summary, according to the channel state information (CSI) processing method and apparatus provided in the embodiments of the present disclosure, when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can, based on the target CSI reporting method, select a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solution of the present disclosure, through grouping and priority sorting, can reasonably discard some CSI information while ensuring a certain level of system performance.

[0141] In the embodiments provided above, the methods provided in the embodiments of the present application are described from the perspectives of the terminal device UE and the network device. In order to implement the various functions in the methods provided in the embodiments of the present application, the terminal device UE and the network device may include a hardware structure and a software module, and implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. One of the above functions may be executed in the form of a hardware structure, a software module, or a hardware structure plus a software module.

[0142] Corresponding to the channel state information CSI processing methods provided in the above-mentioned embodiments, the present disclosure also provides a channel state information CSI processing device. Since the channel state information CSI processing device provided in the embodiment of the present disclosure corresponds to the channel state information CSI processing methods provided in the above-mentioned embodiments, the implementation method of the channel state information CSI processing method is also applicable to the channel state information CSI processing device provided in this embodiment and will not be described in detail in this embodiment.

[0143] FIG7 is a schematic structural diagram of a channel state information CSI processing apparatus 600 provided according to an embodiment of the present disclosure. The channel state information CSI processing apparatus 600 may be applied to a terminal device UE.

[0144] As shown in FIG7 , the apparatus 600 may include:

[0145] The receiving module 610 may be configured to receive configuration information sent by a network device, where the configuration information is used to configure uplink resources;

[0146] The sending module 620 can be used to report the first CSI among all CSIs to the network device using a target CSI reporting method when uplink resources are insufficient to report all channel state information CSIs. The target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method. The first CSI is obtained by discarding the second CSI from all CSIs.

[0147] In some embodiments of the present disclosure, as shown in FIG7 , the apparatus 600 may further include: a processing module 630 ;

[0148] The processing module 630 may be configured to determine, based on a target CSI reporting mode, second CSI to be discarded from among all CSIs.

[0149] In some embodiments of the present disclosure, when the target CSI reporting mode is an AI-based CSI reporting mode, the processing module 630 may be configured to divide all CSI into CSI Part 1 and CSI Part 2, where CSI Part 2 includes at least codewords or codeword quantization information; divide the codeword quantization information into N groups, determine the priority of each group according to a group index, and sequentially determine the codeword quantization information groups in descending order of priority as second CSI to be discarded until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2; or determine the priority of each codeword or each codeword quantization information corresponding to each transmission layer, divide the codeword or codeword quantization information into N groups in descending order of priority, determine the priority of each group according to a group index, and sequentially determine the codeword groups or codeword quantization information groups in descending order of priority as second CSI to be discarded until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0150] In some embodiments of the present disclosure, when the target CSI reporting method is an AI-based CSI reporting method, the processing module 630 can be used to divide all CSIs into N groups, determine the priority of each group according to the group index, and determine the CSI groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2; or divide the codeword quantization information contained in all CSIs into N groups, determine the priority of each group according to the group index, and determine the codeword quantization information groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0151] In some embodiments of the present disclosure, when all CSIs are divided into N groups, the processing module 630 may be configured to divide all CSIs corresponding to quantization information of length The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L tot is the total length of all CSI information, The value obtained by rounding it up or down.

[0152] In some embodiments of the present disclosure, when the codeword quantization information included in all CSI is divided into N groups, the processing module 630 may be configured to divide the codeword quantization information included in all CSI into N groups. The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of each transmission layer is placed in the last group of N groups, where v is the transmission rank value reported by the UE. is the value obtained by rounding up or down; or the length of the quantized information corresponding to each transmission layer in all CSI is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L is the number of codewords output by the CSI generation model of each transmission layer or the length of the quantized information after the codeword is quantized. is the value obtained by rounding up or down; or the length of the quantized information corresponding to each transmission layer in all CSI is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where X is the number of codewords output by the CSI generation model of each transmission layer when the rank is v or the quantization information length after the codeword quantization. The value obtained by rounding it up or down.

[0153] In some embodiments of the present disclosure, when the target CSI reporting method is an AI-based CSI reporting method and a traditional CSI reporting method, the processing module 630 can be used to determine the third CSI that needs to be reported under the AI-based CSI reporting method and the fourth CSI that needs to be reported under the traditional CSI reporting method; and determine the second CSI in the third CSI and the fourth CSI.

[0154] In some embodiments of the present disclosure, the processing module 630 may be configured to determine the fourth CSI as the second CSI; or to fuse the third CSI and the CSI Part 2 corresponding to the fourth CSI to determine the second CSI in the fused CSI Part 2.

[0155] In some embodiments of the present disclosure, the processing module 630 may be configured to place each set of codeword quantization information in the third CSI corresponding to CSI Part 2 before the G0 group information or after the G2 group information of the fourth CSI corresponding to CSI Part 2; or to insert each set of codeword quantization information in the third CSI corresponding to CSI Part 2 into different grouping information of the fourth CSI corresponding to CSI Part 2.

[0156] In some embodiments of the present disclosure, the processing module 630 can be used to divide the fused CSI Part 2 into N groups, determine the priority of each group according to the group index, and determine the CSI Part 2 groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, where N is greater than or equal to 2.

[0157] In some embodiments of the present disclosure, the processing module 630 can be used to divide all CSI into CSI Part 1, CSI Part 2 and CSI Part 3, CSI Part 1 and CSI Part 3 are used to report the fourth CSI, and CSI Part 2 is used to report the third CSI; the non-zero coefficients in CSI Part 3 that do not comply with uplink resource transmission are determined as the second CSI.

[0158] In some embodiments of the present disclosure, the processing module 630 may be configured to determine the second CSI in the third CSI and the fourth CSI, including: dividing all CSI reports into CSI Part 1, CSI Part 2, and CSI Part 3, wherein CSI Part 1 and CSI Part 2 are used to report the fourth CSI, CSI Part 3 is used to report the third CSI, and CSI Part 3 contains at least codewords or codeword quantization information; the codeword quantization information is divided into N groups, the priority of each group is determined according to the group index, and the codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2; or the priority of each codeword or each codeword quantization information corresponding to each transmission layer is determined, the codeword or codeword quantization information is divided into N groups in order from high to low priority, the priority of each group is determined according to the group index, and the codeword groups or codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2.

[0159] In some embodiments of the present disclosure, the processing module 630 may be used to The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of each transmission layer is placed in the last group of N groups, where v is the transmission rank value reported by the UE. is the value obtained by rounding up or down; or the length of the quantized information corresponding to each transmission layer is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where L is the number of codewords output by the CSI generation model of each transmission layer or the length of the quantized information after the codeword is quantized. is the value obtained by rounding up or down; or the length of the quantized information corresponding to each transmission layer is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of N groups, where X is the number of codewords output by the CSI generation model of each transmission layer when the rank is v or the quantization information length after the codeword quantization. The value obtained by rounding it up or down.

[0160] In some embodiments of the present disclosure, the processing module 630 may be used to determine the priority of each codeword or each codeword quantization information corresponding to each transmission layer according to the transmission layer index; or to determine the priority of each codeword corresponding to each transmission layer according to the codeword priority calculation formula; or to determine the priority of each codeword quantization information corresponding to each transmission layer according to the quantization information priority calculation formula.

[0161] In some embodiments of the present disclosure, the receiving module 610 may be configured to receive indication information sent by a network device, where the indication information is used to indicate a target CSI reporting mode.

[0162] In some embodiments of the present disclosure, the sending module 620 may be configured to report the input information Input-CSI-NW of the CSI generation model to the network device using the target CSI reporting method.

[0163] FIG8 is a schematic structural diagram of a channel state information (CSI) processing apparatus 700 according to an embodiment of the present disclosure. The channel state information (CSI) processing apparatus 700 may be applied to a network device.

[0164] As shown in FIG8 , the apparatus 700 may include:

[0165] The sending module 710 may be configured to send configuration information to the terminal device UE, where the configuration information is used to configure uplink resources;

[0166] The receiving module 720 can be used to receive the first CSI among all channel state information CSI reported by the UE using the target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method. The first CSI is obtained by the UE after discarding the second CSI in all CSIs when the uplink resources cannot be used to report all CSIs.

[0167] In some embodiments of the present disclosure, the sending module 710 may be configured to send indication information to the UE, where the indication information is used to indicate a target CSI reporting mode.

[0168] In some embodiments of the present disclosure, the receiving module 720 may be configured to receive input information Input-CSI-NW of a CSI generation model reported by a UE using a target CSI reporting method.

[0169] Please refer to Figure 9, which is a schematic diagram of the structure of a communication device 1400 provided in an embodiment of the present application. Communication device 1400 can be a network device or a user device, or a chip, chip system, or processor that supports the network device to implement the above method. It can also be a chip, chip system, or processor that supports the user device to implement the above method. This device can be used to implement the method described in the above method embodiment. For details, please refer to the description of the above method embodiment.

[0170] The communication device 1400 may include one or more processors 1401. The processor 1401 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control the communication device (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or CU, etc.), execute computer programs, and process computer program data.

[0171] Optionally, the communication device 1400 may further include one or more memories 1402, on which a computer program 1404 may be stored. The processor 1401 executes the computer program 1404 to cause the communication device 1400 to perform the method described in the above method embodiment. Optionally, the memory 1402 may also store data. The communication device 1400 and the memory 1402 may be provided separately or integrated together.

[0172] Optionally, the communication device 1400 may further include a transceiver 1405 and an antenna 1406. The transceiver 1405 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., and is configured to implement transceiver functions. The transceiver 1405 may include a receiver and a transmitter. The receiver may be referred to as a receiver or a receiving circuit, etc., and is configured to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., and is configured to implement a transmitting function.

[0173] Optionally, the communication device 1400 may further include one or more interface circuits 1407. The interface circuit 1407 is configured to receive code instructions and transmit the instructions to the processor 1401. The processor 1401 executes the code instructions to enable the communication device 1400 to perform the method described in the above method embodiment.

[0174] In one implementation, processor 1401 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or may be used for transmitting or delivering signals.

[0175] In one implementation, processor 1401 may store a computer program 1403. Computer program 1403, when executed on processor 1401, may cause communication device 1400 to perform the method described in the above method embodiment. Computer program 1403 may be embedded in processor 1401, in which case processor 1401 may be implemented by hardware.

[0176] In one implementation, the communication device 1400 may include a circuit that can implement the functions of sending, receiving, or communicating in the aforementioned method embodiments. The processor and transceiver described in this application can be implemented on an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0177] The communication device described in the above embodiments may be a network device or a user device, but the scope of the communication device described in this application is not limited thereto, and the structure of the communication device may not be limited to FIG9 . The communication device may be an independent device or may be part of a larger device. For example, the communication device may be:

[0178] (1) An independent integrated circuit (IC), or chip, or chip system or subsystem;

[0179] (2) a collection of one or more ICs, optionally including a storage component for storing data and computer programs;

[0180] (3) ASIC, such as modem;

[0181] (4) Modules that can be embedded in other devices;

[0182] (5) Receivers, terminal devices, intelligent terminal devices, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.;

[0183] (6)Others, etc.

[0184] If the communication device can be a chip or a chip system, please refer to the structural diagram of the chip shown in Figure 10. The chip shown in Figure 10 includes a processor 1501 and an interface 1502. The number of processors 1501 can be one or more, and the number of interfaces 1502 can be multiple.

[0185] Optionally, the chip further includes a memory 1503, which is used to store necessary computer programs and data.

[0186] Those skilled in the art will also appreciate that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the functions for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present application.

[0187] The present application also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.

[0188] The present application also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0189] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. Available media may be magnetic media (eg, floppy disks, hard disks, tapes), optical media (eg, high-density digital video discs (DVDs)), or semiconductor media (eg, solid state disks (SSDs)).

[0190] The present disclosure proposes a channel state information (CSI) processing and apparatus, which can reasonably discard part of the CSI when uplink resources are insufficient and can ensure certain system performance.

[0191] Based on this disclosure, examples of embodiments of this solution are as follows:

[0192] For AI-based CSI feedback, some CSI reporting methods are discarded:

[0193] Opt0: CSI is reported according to Part 1 and Part 2. Part 2 contains at least the codeword quantization information compressed based on the CSI generation model.

[0194] –Opt0-0: For Layer common / Layer specific or Rank common / Rank specific models, Part 2 is divided into at least two groups. The codeword quantization information of the transmission layer is placed in the first group, and the others The codeword quantization information of the transmission layer is placed in the second group, where v represents the rank value reported by the terminal.

[0195] Divide Part2 into N>2 groups, each layer The quantization information of bits is placed in the first N-1 groups, and the last group contains

[0196] Or, each layer The reporting information is placed in the first group, and each layer The reporting information is placed in the second group, and L represents the number of codewords output by the CSI generation model of each layer or the length of the quantized information after the codeword is quantized, in bits.

[0197] Divide Part2 into N>2 groups, each layer The quantization information of bits is placed in the first N-1 groups, and the last group contains

[0198] –Opt0-1: For Rank common or Rank specific models, Part 2 is divided into at least two groups. The codeword quantization information is placed in the first group, and the remaining The codeword quantization information is placed in the second group. Where X represents the number of codewords when the rank is v.

[0199] –Opt0-2: Define the priority of each codeword as Y represents the number of codewords contained in each layer. Or directly define the priority of quantization information Y represents the length of the quantization information contained in each layer.

[0200] For Opt0-0 and Opt0-1, the priority of the second group is lower than that of the first group. When CSI needs to be discarded, the lower priority group is discarded first.

[0201] Opt1: All contents of the CSI report are reported as a whole, that is, they are no longer reported in two parts: Part 1 and Part 2.

[0202] –Opt1-0: Divide the quantized information contained in the reported CSI into N groups, sort the indexes of the N groups from small to large, and the information length of the first N-1 groups is The last group The larger the group index, the lower the priority.

[0203] –Opt1-1: Discard the quantized information output by the AI / ML model of each layer of CSI generation contained in the CSI according to the Opt0-0 or Opt0-1 method.

[0204] AI-based CSI reporting and traditional CSI reporting are fed back to the network through one CSI report (corresponding to one CSI reporting ID):

[0205] ●Alt0: CSI is reported according to Part 1 and Part 2

[0206] – Part 1: Only one RI / CQI is reported, and the remaining information in Part 1 of both AI-based and traditional CSI reports is placed in Part 1. For example, Part 1 of AI-based CSI reports includes the number of codewords for each layer or all layers; Part 1 of traditional CSI reports includes the number of non-zero coefficients for all layers.

[0207] Whether the RI / CQI calculation is based on AI CSI reporting or traditional CSI reporting, as determined by pre-defined, network configuration, or terminal indication.

[0208] –Part 2:

[0209] Alt0-1: Place two or more groups of information reported by the AI-based CSI before G0 or after G2 in Part 2 of the traditional CSI report.

[0210] Alt0-2: When the AI-based CSI reporting information is divided into two groups, the two groups of information are respectively included in two groups of Part 2 of the traditional CSI reporting. Alternatively, when the AI-based CSI reporting information is divided into three groups, the two groups of information are respectively included in the three groups of Part 2 of the traditional CSI reporting.

[0211] The two groups of information are determined according to the two-group division method in Opt0-0 or Opt0-1 mentioned above.

[0212] ●Alt1: All contents of the CSI report are reported together as a whole, that is, they are no longer divided into Part 1 and Part 2.

[0213] – Alt1-0: CSI reporting is divided into three parts. Parts 1 and 2 contain traditional CSI reporting content, and Part 3 contains AI-based CSI reporting content. Optionally, Part 2 contains AI-based CSI reporting content, and Part 3 contains the content in Part 2 included in traditional CSI reporting.

[0214] Note 1: The RI / CQI in Part 1 is reported only once and can be calculated based on AI-based CSI or traditional CSI. Part 3 then contains at least the codeword quantization information after compression of each layer or transmission rank.

[0215] Note 2: Let Input-CSI-NW represent the input information for the AI / ML model used to generate CSI on the terminal side. If the CSI report also includes Input-CSI-NW, the reported Input-CSI-NW can be reported in the same CSI as the AI-based CSI report and the traditional CSI report. When reported in the same CSI, the reported Input-CSI-NW includes a separate part that is independent of the above parts.

[0216] Example 1 (AI-based CSI reporting):

[0217] Assuming that the AI / ML model used for AI-based CSI reporting is layer common, that is, all layers use the same AI / ML model, then the number of output codewords of the CSI generation model is equal, or the information length L after quantization of the codeword is equal. Assuming L = 120 bits and the transmission rank v = 2 selected by the UE. Divide Part2 into two groups, the first group contains L 1,1 and L 2,1 bits, the second group contains L 1,2 and L 2,2 bits. Among them, L 1,1 =L 1,2 = L / 2 = 60 bits represents the quantization information of the first half and the second half of the first layer; L 2,1 =L 2,2 = L / 2 = 60 bits represents the quantization information of the first half and the second half of the second layer. Alternatively, the priority of each quantization information is determined according to the defined priority. The priority of each quantization information may be determined as shown in Table 2 below, where Y represents the length of the quantization information.

[0218] Table 2: Priority ranking of each quantitative information at each layer, with decreasing priority from left to right

[0219] i in the table m,n Indicates the nth quantization information of the mth layer, i in the table m,n The value of is determined according to Pri(l).

[0220] Example 2 (AI-based CSI reporting and traditional CSI reporting through one CSI report):

[0221] Assume that AI-based CSI reporting and traditional CSI reporting include two parts, Part 1 and Part 2, through a CSI report. The information in Part 1 is shown in Table 3 below:

[0222] Table 3: CSI information included in Part 1

[0223] Assuming the transmission rank indicated by the RI is 2, traditional CSI feedback is based on the Rel-16 Type II codebook. Assuming the quantized information length L = 120 bits output by the CSI generation model for each layer, each layer is divided into three groups, each containing 40 bits. When AI-based CSI reporting is divided into three groups, these three groups of information are included in Part 2 of the traditional CSI report, as shown in Table 4 below.

[0224] Table 4: CSI information included in Part 1

[0225] In summary, the present disclosure has the following beneficial technical effects: when a terminal device (UE) is unable to report all channel state information (CSI) based on the uplink resources configured by the network device, it can, based on the target CSI reporting method, select a second CSI with a lower priority from all CSIs for discarding, and further report the remaining first CSI with a higher priority from all CSIs to the network device. The technical solution of the present disclosure, through grouping and priority sorting, can reasonably discard some CSI information while ensuring certain system performance.

[0226] The embodiments or examples of the present disclosure are not exhaustive, but are merely illustrations of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.

[0227] In some implementation manners or examples, the terms "in response to," "in the case of," "at the time of," "when," "if," "if," etc. in the present disclosure may be replaced with each other.

[0228] In some embodiments or examples, the description methods of the present disclosure, such as "A or B", "A and / or B", "at least one of A and B", "A in one case, B in another case", "in response to one case A, in response to another case B", etc., may include at least one of the following technical solutions according to the situation: executing A independently of B, that is, A in some embodiments or examples; executing B independently of A, that is, B in some embodiments or examples; selectively executing A and B, that is, selecting to execute from A and B in some embodiments or examples; executing both A and B, that is, A and B in some embodiments or examples.

[0229] In some embodiments or examples, “including A”, “comprising A”, “used to indicate A” and “carrying A” in the present disclosure may be interpreted as directly carrying A or indirectly indicating A.

[0230] In addition, each element, each row, or each column in the table involved in the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0231] Those skilled in the art will understand that the various numerical numbers such as first and second involved in this application are only for the convenience of description and are not used to limit the scope of the embodiments of this application, and also indicate the order of precedence.

[0232] In this application, at least one can also be described as one or more, and multiple can be two, three, four or more, which is not limited in this application. In the embodiments of this application, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", and there is no order of precedence or size between the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0233] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0234] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0235] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0236] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0237] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)", "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0238] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0239] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, it can also be called device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it can also be set as a structure in which the terminal has all or part of the functions of the access network device. In addition, language such as "uplink" and "downlink" can also be replaced by language corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0240] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0241] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0242] In some embodiments, the terms "precoding", "precoder", "weight", "precoding weight", "quasi-co-location (QCL)", "transmission configuration indication (TCI) state", "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "the number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angular degree", "antenna", "antenna element", "panel" and the like can be used interchangeably.

[0243] In some embodiments, terms such as "frame", "radio frame", "subframe", "slot", "sub-slot", "mini-slot", "symbol", "symbol", and "transmission time interval (TTI)" can be used interchangeably.

[0244] In some embodiments, "obtain", "get", "obtain", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from a protocol, obtaining by self-processing, autonomous implementation, etc.

[0245] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0246] In some embodiments, "predetermined" and "preset" can be interpreted as pre-specified in a protocol, etc., or can be interpreted as a pre-set action performed by a device, etc.

[0247] In some embodiments, determining may be interpreted as judging, calculating, computing, processing, deriving, investigating, searching, looking up, retrieving, ascertaining, receiving, transmitting, inputting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, “assuming,” “expecting,” “considering,” broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, and the like, but is not limited thereto.

[0248] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0249] Furthermore, it should be understood that the various embodiments of the present application may be implemented individually or in combination with other embodiments where the solution permits.

[0250] Those skilled in the art will appreciate that the units and algorithmic steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0251] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0252] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A channel state information (CSI) processing method, characterized in that: The method is applied to a terminal device UE, comprising: Receiving configuration information sent by a network device, where the configuration information is used to configure uplink resources; When the uplink resources are insufficient for reporting all channel state information CSI, a first CSI among all the CSIs is reported to the network device using a target CSI reporting method, wherein the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained after discarding the second CSI among all the CSIs.

2. The method according to claim 1, characterized in that The method further comprises: Based on the target CSI reporting mode, second CSI to be discarded among all the CSIs is determined.

3. The method according to claim 2, characterized in that When the target CSI reporting mode is an AI-based CSI reporting mode, determining, based on the target CSI reporting mode, the second CSI to be discarded among all the CSIs includes: Dividing all the CSI into CSI Part 1 and CSI Part 2, wherein the CSI Part 2 at least includes a codeword or codeword quantization information; Divide the codeword quantization information into N groups, determine the priority of each group according to the group index, and determine the codeword quantization information groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2; or Determine the priority of each codeword or each codeword quantization information corresponding to each transmission layer, divide the codeword or the codeword quantization information into N groups in descending order of priority, determine the priority of each group according to the group index, and determine the codeword groups or codeword quantization information groups as the second CSI to be discarded in descending order of priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2.

4. The method according to claim 2, characterized in that: When the target CSI reporting mode is an AI-based CSI reporting mode, determining, based on the target CSI reporting mode, the second CSI to be discarded among all the CSIs includes: Divide all the CSI into N groups, determine the priority of each group according to the group index, and determine the CSI groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2; or The codeword quantization information contained in all the CSIs is divided into N groups, the priority of each group is determined according to the group index, and the codeword quantization information groups are determined as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2.

5. The method according to claim 4, characterized in that The dividing all the CSI into N groups includes: The length of the corresponding quantized information in all CSIs is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of the N groups, where L tot is the total length of all CSI information, The value obtained by rounding it up or down.

6. The method according to claim 4, characterized in that Divide the codeword quantization information contained in all the CSI into N groups, including: All the CSI The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of the transmission layer is placed in the last group of the N groups, where v is the value of the transmission rank reported by the UE, is the value obtained by rounding it up or down; or The length of the quantized information corresponding to each transmission layer in all CSIs is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of the N groups, where L is the number of codewords output by the CSI generation part model of each transmission layer or the length of the quantization information after the codeword is quantized, is the value obtained by rounding it up or down; or The length of the quantized information corresponding to each transmission layer in all CSIs is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of the N groups, where X is the number of codewords output by the CSI generation part model of each transmission layer when the rank is v or the quantization information length after the codeword is quantized, The value obtained by rounding it up or down.

7. The method according to claim 2, characterized in that: When the target CSI reporting mode is an AI-based CSI reporting mode and a traditional CSI reporting mode, determining the second CSI to be discarded among all the CSIs based on the target CSI reporting mode includes: Determine a third CSI that needs to be reported in the AI-based CSI reporting method and a fourth CSI that needs to be reported in the traditional CSI reporting method; The second CSI is determined among the third CSI and the fourth CSI.

8. The method according to claim 7, characterized in that Determining the second CSI from the third CSI and the fourth CSI includes: determining the fourth CSI as the second CSI; or The third CSI and the CSI Part2 corresponding to the fourth CSI are merged, and the second CSI is determined in the merged CSI Part2.

9. The method according to claim 8, characterized in that The CSI Part 2 corresponding to the fusion of the third CSI and the fourth CSI includes: Arrange each group of codeword quantization information in the third CSI corresponding to CSI Part 2 before the G0 group information or after the G2 group information of the fourth CSI corresponding to CSI Part 2; or Each group of codeword quantization information in the third CSI corresponding to CSI Part 2 is respectively inserted into different grouping information of the fourth CSI corresponding to CSI Part 2.

10. The method according to claim 9, characterized in that The determining the second CSI in the fused CSI Part 2 includes: Divide the fused CSI Part 2 into N groups, determine the priority of each group according to the group index, and sort the groups in order of priority from low to high. The CSI Part 2 groups are determined as the second CSI to be discarded in a higher order until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2.

11. The method according to claim 7, characterized in that The determining the second CSI from the third CSI and the fourth CSI includes: dividing all the CSI into CSI Part 1, CSI Part 2 and CSI Part 3, wherein the CSI Part 1 and CSI Part 3 are used to report the fourth CSI, and the CSI Part 2 is used to report the third CSI; The non-zero coefficient in the CSI Part 3 that does not conform to the uplink resource transmission is determined as the second CSI.

12. The method according to claim 7, characterized in that The determining the second CSI from the third CSI and the fourth CSI includes: Dividing the reporting of all the CSIs into CSI Part 1, CSI Part 2 and CSI Part 3, wherein the CSI Part 1 and CSI Part 2 are used to report the fourth CSI, the CSI Part 3 is used to report the third CSI, and the CSI Part 3 at least includes a codeword or codeword quantization information; Divide the codeword quantization information into N groups, determine the priority of each group according to the group index, and determine the codeword quantization information groups as the second CSI to be discarded in order from low to high priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2; or Determine the priority of each codeword or each codeword quantization information corresponding to each transmission layer, divide the codeword or codeword quantization information into N groups in descending order of priority, determine the priority of each group according to the group index, and determine the codeword groups or codeword quantization information groups as the second CSI to be discarded in descending order of priority until the size of the first CSI is less than or equal to the size of the uplink resource, wherein N is greater than or equal to 2.

13. The method according to claim 3 or 12, characterized in that: The dividing the codeword quantization information into N groups includes: Will The codeword quantization information of each transmission layer is placed in the first N-1 groups. The codeword quantization information of the transmission layer is placed in the last group of the N groups, where v is the value of the transmission rank reported by the UE, is the value obtained by rounding it up or down; or The length of quantized information corresponding to each transmission layer is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of the N groups, where L is the number of codewords output by the CSI generation part model of each transmission layer or the length of the quantization information after the codeword is quantized, is the value obtained by rounding it up or down; or The length of quantized information corresponding to each transmission layer is The codeword quantization information is placed in the first N-1 groups, and the corresponding quantization information length is The codeword quantization information is placed in the last group of the N groups, where X is the number of codewords output by the CSI generation part model of each transmission layer when the rank is v or the quantization information length after the codeword is quantized, The value obtained by rounding it up or down.

14. The method according to claim 3 or 12, characterized in that: The determining the priority of each codeword or each codeword quantization information corresponding to each transmission layer includes: Determine the priority of each codeword or each codeword quantization information corresponding to each transmission layer according to the transmission layer index; or Determine the priority of each codeword corresponding to each transmission layer according to the codeword priority calculation formula; or The priority of each codeword quantization information corresponding to each transmission layer is determined according to the quantization information priority calculation formula.

15. The method according to any one of claims 1 to 14, characterized in that The method further comprises: Receive indication information sent by the network device, where the indication information is used to indicate the target CSI reporting mode.

16. The method according to any one of claims 1 to 14, characterized in that The method further comprises: The target CSI reporting method is used to report the input information Input-CSI-NW of the CSI generation part model to the network device.

17. A channel state information (CSI) processing method, characterized in that: The method is applied to a network device, comprising: Sending configuration information to a terminal device UE, where the configuration information is used to configure uplink resources; Receive the first CSI among all channel state information CSI reported by the UE using a target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained by the UE after discarding the second CSI among all the CSIs when the uplink resources are insufficient for reporting all the CSIs.

18. The method according to claim 17, characterized in that The method further comprises: Sending indication information to the UE, where the indication information is used to indicate the target CSI reporting mode.

19. The method according to claim 17, characterized in that The method further comprises: Receive input information Input-CSI-NW of a CSI generation part model reported by the UE using the target CSI reporting mode.

20. A channel state information (CSI) processing device, characterized in that: The device is applied to a terminal device UE, and includes: A receiving module, used to receive configuration information sent by a network device, wherein the configuration information is used to configure uplink resources; A sending module, used for reporting the first CSI among all the CSIs to the network device by using a target CSI reporting method when the uplink resources are insufficient for reporting all the channel state information CSIs, wherein the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained after discarding the second CSI among all the CSIs.

21. A channel state information (CSI) processing device, characterized in that: The device is applied to a network device, including: A sending module, used to send configuration information to a terminal device UE, where the configuration information is used to configure uplink resources; A receiving module is used to receive the first CSI among all channel state information CSI reported by the UE using a target CSI reporting method, where the target CSI reporting method includes an AI-based CSI reporting method and / or a traditional CSI reporting method, and the first CSI is obtained by the UE after discarding the second CSI among all the CSI when the uplink resources are insufficient for reporting all the CSI.

22. A communication device, wherein: include: Transceiver; Memory; A processor is connected to the transceiver and the memory, respectively, and is configured to control the wireless signal reception and transmission of the transceiver by executing computer executable instructions on the memory, and can implement any one of the methods of claims 1-19.

23. A computer storage medium, wherein: The computer storage medium stores computer executable instructions; after the computer executable instructions are executed by the processor, the method described in any one of claims 1 to 19 can be implemented.

24. A communication system, comprising a terminal device UE and a network device, wherein: The terminal device UE is used to perform the method according to any one of claims 1 to 16; The network device is used to execute the method according to any one of claims 17 to 19.

Images