CN114866202A

CN114866202A - CSI feedback method and device, storage medium, terminal and network equipment

Info

Publication number: CN114866202A
Application number: CN202110147985.0A
Authority: CN
Inventors: 陈咪咪; 周化雨
Original assignee: Spreadtrum Communications Shanghai Co Ltd
Current assignee: Spreadtrum Communications Shanghai Co Ltd
Priority date: 2021-02-03
Filing date: 2021-02-03
Publication date: 2022-08-05
Also published as: WO2022166446A1

Abstract

A CSI feedback method and device, a storage medium, a terminal and a network device are provided, wherein the method comprises the following steps: receiving first configuration signaling from a network device; and acquiring parameters of the CSI feedback information according to the first configuration signaling. Therefore, the channel information can be accurately reported, and the interference among multiple UEs can be effectively avoided.

Description

CSI feedback method and device, storage medium, terminal and network equipment

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a CSI feedback method and apparatus, a storage medium, a terminal, and a network device.

Background

The radio channel conditions are constantly changing, and if the downlink uses Quadrature Phase Shift Keying (QPSK) instead of a higher-order modulation scheme for transmission, it will reduce the utilization of the spectrum and cause a decrease in throughput, assuming that the channel quality is good. If the channel quality is poor, if the high-order modulation is used instead of the QPSK modulation, excessive retransmissions are caused, and excessive radio resources are also used. In either case, the radio resources cannot be effectively used. In order to better adapt to the variation of the radio Channel, a User Equipment (UE) may report downlink Channel quality Information to a base station (gNB) through Channel State Information (CSI), so that the gNB may select a better Modulation and Coding Scheme (MCS) or a more appropriate Precoding Matrix (PMI), and the like.

Specifically, the UE obtains the CSI by measuring a received Channel State Information-reference Signal (CSI-RS), and a process of reporting the CSI to the gNB is a CSI feedback process. The CSI feedback process includes reporting one or more of a Rank Indicator (RI), a PMI, and a Channel Quality Indicator (CQI). The reporting mode can be periodic, semi-continuous, non-periodic and the like. As is conventional for feedback of PMIs: and the UE selects the PMI considered to be suitable by the UE according to the channel state information and then informs the gNB for reference. However, this method has the disadvantage that the PMI selected by the UE is not necessarily appropriate, and may cause inter-UE interference. Another idea is: and the UE directly feeds back the channel information to the gNB, and the gNB selects a proper PMI according to the channel information. However, this method has the disadvantages of full feedback of channel information, too large overhead, and the need for compressed feedback.

Therefore, research on how to feed back the CSI has important practical value for improving communication performance.

Disclosure of Invention

The technical problem to be solved by the invention is how to provide a CSI feedback method, which can accurately report channel information and effectively avoid interference among multiple UEs.

In order to solve the above problem, an embodiment of the present invention provides a CSI feedback method, where the method includes: receiving first configuration signaling from a network device; and acquiring parameters of the CSI feedback information according to the first configuration signaling.

Optionally, the first configuration signaling includes indication information of a network type.

Optionally, the first configuration signaling includes indication information of a parameter of a network middle layer.

Optionally, the first configuration signaling includes indication information of a network type and indication information of a parameter of a network intermediate layer.

Optionally, the first configuration signaling includes indication information of a first network type and indication information of a second network type, where a network corresponding to the first network type is used to generate CSI feedback information of the first-stage feedback, and a network corresponding to the second network type is used to generate CSI feedback information of the second-stage feedback.

Optionally, the first configuration signaling includes indication information of a parameter of a first network intermediate layer and indication information of a parameter of a second network intermediate layer, where a network corresponding to the first network type is used to generate CSI feedback information of first-stage feedback, and a network corresponding to the second network type is used to generate CSI feedback information of second-stage feedback.

Optionally, the first configuration signaling includes a first cycle and a second cycle.

Optionally, the first configuration signaling is carried by radio resource control signaling and/or downlink control signaling.

The embodiment of the invention also provides a CSI feedback method, which comprises the following steps: receiving second configuration signaling from the network equipment, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports; and acquiring parameters of the CSI feedback information according to the number of the CSI-RS ports.

Optionally, the parameter of the CSI feedback information includes a parameter of a network type.

Optionally, the parameter of the CSI feedback information includes a parameter of a network intermediate output layer.

The embodiment of the invention also provides a CSI feedback method, which further comprises the following steps: receiving second configuration signaling and third configuration signaling from a network device, wherein the second configuration signaling comprises first indication information, the first indication information is used for indicating the number of CSI-RS ports, the third configuration signaling comprises second indication information, and the second indication information is used for indicating the number of receiving antennas; and acquiring parameters of CSI feedback information according to the number of the CSI-RS ports and the number of the receiving antennas.

Optionally, the method further includes: and carrying out quantization processing on the output of the network middle layer.

Optionally, the performing quantization processing on the output of the network intermediate layer includes: and carrying out mu-law quantization processing on the output of the network intermediate layer.

Optionally, the performing quantization processing on the output of the network intermediate layer includes: and carrying out phase quantization processing on the output of the network intermediate layer.

Optionally, the performing phase quantization processing on the output of the network intermediate layer includes: and performing phase quantization processing on the output of the network middle layer according to a table look-up method.

Optionally, the performing phase quantization processing on the output of the network intermediate layer includes: and performing PSK quantization processing on the output of the network middle layer.

Optionally, the performing quantization processing on the output of the network intermediate layer includes: and carrying out amplitude quantization processing on the output of the network middle layer.

Optionally, the performing quantization processing on the output of the network intermediate layer includes: and carrying out amplitude quantization processing and phase quantization processing on the output of the network intermediate layer.

Optionally, the performing amplitude quantization processing on the output of the network intermediate layer includes: and carrying out normalization processing on the output of the network intermediate layer.

The embodiment of the invention also provides a CSI feedback method, which comprises the following steps: generating a first configuration signaling, wherein the configuration signaling is used for configuring parameters of CSI feedback information; and sending the first configuration signaling to the UE.

The embodiment of the invention also provides a CSI feedback method, which comprises the following steps: generating second configuration signaling, wherein the second configuration signaling comprises first indication information, the first indication information is used for indicating the number of CSI-RS ports, and the number of the CSI-RS ports is used for configuring parameters of CSI feedback information; and sending the second configuration signaling to the UE.

The embodiment of the invention also provides a CSI feedback method, which comprises the following steps: generating second configuration signaling, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports; generating third configuration signaling, wherein the third configuration signaling comprises second indication information, and the second indication information is used for indicating the number of receiving antennas; and sending the second configuration signaling and the third configuration signaling to the UE, wherein the number of the CSI-RS ports and the number of the receiving antennas are used for configuring parameters of CSI feedback information.

An embodiment of the present invention further provides a CSI feedback apparatus, where the apparatus includes: a first configuration signaling receiving module, configured to receive a first configuration signaling from a network device; and the first parameter acquisition module is used for acquiring the parameters of the CSI feedback information according to the first configuration signaling.

An embodiment of the present invention further provides a CSI feedback apparatus, where the apparatus includes: a first configuration signaling generation module, configured to generate a first configuration signaling, where the configuration signaling is used to configure parameters of CSI feedback information; and the first configuration signaling sending module is used for sending the first configuration signaling to the UE.

An embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform any one of the methods.

An embodiment of the present invention further provides a terminal, including the apparatus, or including a memory and a processor, where the memory stores a computer program executable on the processor, and the terminal is characterized in that the processor executes the computer program to perform any of the steps of the method.

An embodiment of the present invention further provides a network device, which includes the apparatus described above, or includes a memory and a processor, where the memory stores a computer program executable on the processor, and is characterized in that the processor executes the computer program to perform any one of the steps of the method.

Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:

the embodiment of the invention provides a CSI feedback method, which comprises the following steps: receiving first configuration signaling from a network device; and acquiring parameters of the CSI feedback information according to the first configuration signaling. Compared with the prior art, in the scheme of the embodiment of the invention, the network equipment indicates the UE to use the corresponding network to process the CSI (such as encryption, compression and the like) through the configuration signaling, and then reports the CSI to the network equipment. The encryption processing can improve the security of CSI feedback, and the compression processing can reduce the data volume of transmission and save transmission resources. And the accuracy of CSI transmission can be ensured.

Furthermore, the AI-based CSI feedback mechanism provided by the invention can enable the network equipment to obtain the full channel information of the CSI-RS position, the selected PMI, MCS and the like are more reliable, more reasonable time-frequency resources can be allocated to the UE, the resource utilization rate is favorably improved, the communication reliability is improved, and the interference between the UE is reduced.

Drawings

Fig. 1 is a flowchart illustrating a first CSI feedback method according to an embodiment of the present invention;

fig. 2 is a flowchart illustrating a second CSI feedback method according to an embodiment of the present invention;

fig. 3 is a flowchart illustrating a third CSI feedback method according to an embodiment of the present invention;

fig. 4 is a flowchart illustrating a fourth CSI feedback method according to an embodiment of the invention;

fig. 5 is a schematic diagram of a CSI feedback method on a UE side according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a CSI feedback method at a base station (gNB) side according to an embodiment of the present invention;

fig. 7 is a flowchart illustrating a fifth CSI feedback method according to an embodiment of the present invention;

fig. 8 is a flowchart illustrating a sixth CSI feedback method according to an embodiment of the present invention;

fig. 9 is a flowchart illustrating a seventh CSI feedback method according to an embodiment of the present invention;

fig. 10 is a flowchart illustrating an eighth CSI feedback method according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of a first CSI feedback apparatus according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of a second CSI feedback apparatus according to an embodiment of the invention;

fig. 13 is a schematic structural diagram of a third CSI feedback apparatus according to an embodiment of the invention;

fig. 14 is a schematic structural diagram of a fourth CSI feedback apparatus according to an embodiment of the invention;

fig. 15 is a schematic structural diagram of a fifth CSI feedback apparatus according to an embodiment of the invention;

fig. 16 is a schematic structural diagram of a sixth CSI feedback apparatus according to an embodiment of the present invention.

Detailed Description

As known in the background art, the CSI feedback mechanism in the prior art cannot accurately report channel information or avoid interference between multiple UEs.

To solve the above problem, an embodiment of the present invention provides a CSI feedback method, where the method includes: receiving first configuration signaling from a network device; and acquiring parameters of the CSI feedback information according to the first configuration signaling. By the scheme, the channel information can be accurately reported, and the interference among multiple UEs can be effectively avoided.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.

Referring to fig. 1, fig. 1 is a flowchart illustrating a first CSI feedback method according to an embodiment of the present invention, where the method may be executed by a terminal, and the terminal may be User Equipment (UE), which is described below by taking the UE as an example.

AI (Artificial Intelligence) is applied more and more widely in the field of communications, and a CSI feedback mechanism based on AI is also being researched more. The process of measuring the received CSI-RS by the UE to obtain CSI feedback information and reporting the CSI feedback information to the network device is referred to as a CSI feedback process. The network device may be an Access Point (AP) or a base station (e.g., a gNB, an eNB, etc.).

The CSI feedback process can be analogized to a compression and recovery process, and the UE side compresses channel information at the CSI-RS position by using a deep learning network (or referred to as a neural network, and hereinafter, referred to as a network) to generate feedback information, which can be denoted as CSI-code and fed back to the network device. And the network equipment decompresses the CSI feedback information by using the corresponding deep learning network to recover the CSI (channel information on the CSI-RS position). There are some limitations to the application of deep learning algorithms to channel estimation.

The parameters of the CSI feedback information fed back by the UE and the accuracy of the channel information recovered by the network equipment are mutually restricted, and the parameters of the CSI feedback information reported by the UE may be different under different configurations or different scene requirements; the networks for decoding different CSI feedback information are different, and the network for generating CSI feedback information on the UE side and the network for decoding CSI feedback information by the network device to recover the channel information are corresponding, and both need to be consistent.

The CSI feedback method comprises the following steps:

step S101, receiving a first configuration signaling from a network device;

step S102, obtaining parameters of the CSI feedback information according to the first configuration signaling.

The first configuration signaling is a signaling sent by a network side/a base station to a terminal, and the configuration signaling is used for indicating the UE to acquire parameters of CSI feedback information. Or the configuration signaling may further instruct the UE to send the parameters of the obtained CSI feedback information to the network device. And the parameters of the CSI feedback information correspond to the networks for generating the CSI feedback information one by one. The UE is thus able to determine from the configuration signaling which network to locally employ to generate the CSI feedback information.

The first configuration signaling carries information related to parameters of the CSI feedback information, so that the UE determines the parameters of the obtained CSI feedback information to determine a network for locally generating the CSI feedback information. And processing (such as compression, encryption and the like) the CSI by using the local network at the UE to generate CSI feedback information, reporting the CSI feedback information to the network equipment, and finishing CSI feedback. The network device may also perform inverse processing (such as decompression, decryption, and the like) on the CSI feedback information according to the inverse processing network corresponding to the parameter of the CSI feedback information, so as to obtain the CSI reported by the UE. Optionally, the CSI includes a channel matrix of CSI-RS locations.

Specifically, referring to fig. 2, fig. 2 is a schematic flowchart of a second CSI feedback method according to an embodiment of the present invention, where the method includes:

step S201, receiving a first configuration signaling from a network device, and acquiring parameters of CSI feedback information according to the first configuration signaling;

step S202, selecting a network according to the parameters of the CSI feedback information, and generating the CSI feedback information by using the selected network to process the CSI;

step S203, reporting the CSI feedback information to the network equipment so that the network equipment performs inverse processing on the CSI feedback information to obtain the CSI;

and the parameters of the CSI feedback information correspond to the networks one to one.

In one embodiment, the first configuration signaling includes indication information of a network type, or the first configuration signaling includes indication information of a parameter output by a network middle layer, or the configuration signaling includes indication information of a network type and indication information of a parameter output by a network middle layer.

The indication information of the network type is used for indicating the corresponding network type, and the indication information of the parameter of the network middle layer is used for indicating the parameter of the corresponding network middle layer. Optionally, if the network includes a plurality of intermediate layers, the indication information of the parameters of the intermediate layers of the network may indicate a specific intermediate layer.

The UE may determine the network that locally generates the CSI feedback information according to the network type and/or parameters output by the network intermediate layer. Further, the lengths of the CSI feedback information output by different networks on the UE side are different, so that the parameter output by the network intermediate layer may correspond to the length (length code) of the CSI feedback information, and the like.

If the first configuration signaling comprises indication information of a network type, the network equipment sends the first configuration signaling to the UE through RRC signaling to indicate the network type for acquiring the CSI feedback information, and if the UE and the network equipment are respectively provided with a plurality of networks, the network equipment directly indicates the network for acquiring the CSI feedback information by the UE.

If the RRC signaling includes indication information of a network type and indication information of a parameter output by the network intermediate layer, the RRC configuration signaling indicates a network type, such as TypeNet, for obtaining CSI feedback information; the RRC configuration signaling indicates parameters output by a middle layer of the network for acquiring the CSI feedback information, such as NetOutptIndex;

such as: the UE side and the network equipment side are provided with a plurality of networks, and the network equipment directly indicates the network used by the UE through first configuration signaling. The UE may obtain CSI feedback information in the middle layer by using the network, where different middle layers correspond to different CSI feedback information lengths, and a correspondence between a middle layer index (index) and the CSI feedback information lengths is shown in table 1:

TABLE 1

Intermediate layer Index	CSI feedback information length
		1	5bits
2	10bits
		3	20bits
4	30bits

Optionally, the first configuration signaling is carried by Radio Resource Control (RRC) signaling and/or Downlink Control Information (DCI). Compared with the RRC signaling, the real-time performance of the DCI bearer configuration signaling is better, but the design of each indication domain of the original DCI is greatly changed.

Optionally, the network device may use a Physical Uplink Control Channel (PUCCH) bearer or may use a Physical Uplink Shared Channel (PUSCH) bearer to carry RRC signaling and/or DCI, so as to send the first configuration signaling to the UE.

In this embodiment, the network device instructs, through the configuration signaling, the UE to process (e.g., encrypt, compress, etc.) the CSI using the corresponding network, and then report the CSI to the network device. The encryption processing can improve the security of CSI feedback, and the compression processing can reduce the data volume of transmission and save transmission resources. And the accuracy of CSI transmission can be ensured.

In one embodiment, the first configuration signaling includes indication information of a first network type and indication information of a second network type, the network corresponding to the first network type is used for generating CSI feedback information of first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of second-stage feedback.

The indication information of the first network type is used for indicating the network type of the first network, and the indication information of the second network type is used for indicating the network type of the second network.

In another embodiment, the first configuration signaling includes indication information of a parameter of a first network interlayer and indication information of a parameter of a second network interlayer, the network corresponding to the first network type is used for generating CSI feedback information of first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of second-stage feedback.

The indication information of the parameters of the first network middle layer is used for indicating the parameters of the network middle layer of the first network, and the indication information of the parameters of the second network middle layer is used for indicating the parameters of the network middle layer of the second network.

Optionally, the first configuration signaling includes a first cycle and a second cycle. The first period is a reporting period of the CSI feedback information generated by the first network, and the second period is a reporting period of the CSI feedback information generated by the second network. The first and second periods may be represented in the first configuration signaling as Period1 and Period2, respectively.

In order to save the bit number, the CSI feedback in this embodiment is two-stage feedback, and the number of bits of the first-stage feedback is more, that is, the CSI included in the first-stage feedback is more; the number of bits of the second-stage feedback is smaller, i.e. the second-stage feedback contains less CSI information. The UE uses the first network to generate the CSI feedback information of the first-stage feedback, and the UE uses the second network to generate the CSI feedback information of the second-stage feedback. Both stages of feedback may be performed periodically, with the first stage of feedback being performed for a period greater than the second stage of feedback. For example, the period (i.e., the first period) for executing the first-stage feedback is 1 hour, and the period (i.e., the second period) for executing the second-stage feedback is 10 minutes.

Specifically, the first configuration signaling (e.g., RRC signaling) indicates a first network type and a second network type for acquiring CSI feedback information, which are denoted by TypeNet1 and TypeNet2, respectively.

Or, the first configuration signaling includes indication information of a parameter output by the first network intermediate layer and indication information of a parameter output by the second network intermediate layer, which are respectively represented by NetOutptIndex1 and NetOutptIndex 2. The UE uses the network corresponding to the parameter output by the first network intermediate layer to generate the CSI feedback information of the first-stage feedback, and uses the network corresponding to the parameter output by the second network intermediate layer to generate the CSI feedback information of the second-stage feedback.

In an embodiment, referring to fig. 3, a third CSI feedback method is further provided in an embodiment of the present invention, where the method includes:

step S301, receiving a second configuration signaling from a network device, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports;

step S302, obtaining parameters of the CSI feedback information according to the number of the CSI-RS ports.

Optionally, a second configuration signaling for indicating the number of CSI-RS ports already exists in the existing protocol, and the UE obtains parameters of the CSI feedback information according to the number of CSI-RS ports configured by the network. A first corresponding relation exists between the number of ports of the CSI-RS and the parameters of the CSI feedback information, and the first corresponding relation is used for determining the parameters of the CSI feedback information according to the number of ports of the CSI-RS.

Wherein the port number of the CSI-RS is determined by the value of the RRC configured nroflorts. Optionally, the correspondence between the values of nrofPorts and the parameters of the CSI feedback information, i.e. the first correspondence, is defined by a protocol or preconfigured by the network side. At this time, the configuration signaling only indicates the UE to report the CSI feedback information, and the UE determines a parameter (e.g., NetOutptIndex) of the CSI feedback information according to the port number (e.g., nrofPorts parameter value) of the CSI-RS and the first corresponding relationship, so as to determine the used network.

Optionally, the parameter of the CSI feedback information includes a parameter of a network type, or the parameter of the CSI feedback information includes a parameter of a network intermediate output layer. And the UE determines the network type (TypeNet) and/or the parameter (NetOutptIndex) of the network intermediate output layer according to the number of the CSI-RS ports. Specifically, if the first configuration signaling only indicates that the UE reports the CSI feedback information, the base station implicitly indicates the parameter of the CSI feedback information through the number of CSI-RS ports.

For example, nrofPorts takes a value { p1, p2, p4, p8, p12, p16, p24, p32}, and corresponds to 8 or more parameters of CSI feedback information, for example, when the parameter of CSI feedback information is the length of CSI feedback information, the length of CSI feedback information corresponding to p1 to p4 may be L1, the length of CSI feedback information corresponding to p8 value p16 may be L2, and the length of CSI feedback information corresponding to p24 to p32 may be L3. And if the configured nroflorts of the UE is p4, reporting the CSI feedback information with the length of L1 by the UE.

In an embodiment, referring to fig. 4, a third CSI feedback method is further provided in the embodiment of the present invention, where the method further includes:

step S401, receiving a second configuration signaling and a third configuration signaling from a network device, where the second configuration signaling includes first indication information, the first indication information is used to indicate the number of CSI-RS ports, the third configuration signaling includes second indication information, and the second indication information is used to indicate the number of receiving antennas;

and step S402, acquiring parameters of CSI feedback information according to the number of the CSI-RS ports and the number of the receiving antennas.

Optionally, the parameter of the CSI feedback information includes a parameter of a network type, or the parameter of the CSI feedback information includes a parameter of a network intermediate output layer.

For the details of the second configuration signaling and the second indication information, please refer to the related description in fig. 3. Optionally, a third configuration signaling for indicating the number of receiving antennas already exists in the existing protocol, and the UE determines the network type (TypeNet) and/or the parameter (NetOutptIndex) of the network intermediate output layer according to the number of CSI-RS ports configured by the network and the number of receiving antennas. Specifically, if the configuration signaling only indicates that the UE reports the CSI feedback information, the base station implicitly indicates the parameters of the CSI feedback information through the number of CSI-RS ports and the number of receiving antennas.

Optionally, a second corresponding relationship exists between a combination of the number of ports of the CSI-RS and the number of receive antennas of the terminal and the parameter of the feedback information, and the second corresponding relationship is used to determine the parameter of the feedback information according to the number of ports of the CSI-RS and the number of ports of the terminal. The number of receiving antennas may also be configured to the UE by RRC signaling, and the second correspondence relationship is defined by a protocol or preconfigured by the network side.

For example, the parameter of the CSI feedback information is the length of the CSI feedback information, and may be divided into ranges according to the number of receiving antennas, so as to obtain ranges of n1 to n2, n2 to n3, n3 to n4, and ═ n 4. The second correspondence may be expressed as:

when nroflorts are p1 to p 4: when the number of the receiving antennas is n 1-n 2, the length of the CSI feedback information is L1; when the number of the receiving antennas is n 2-n 3, the length of the CSI feedback information is L2; when the number of the receiving antennas is n 3-n 4, the length of the CSI feedback information is L3; when the number of the receiving antennas is > n4, the length of the CSI feedback information is L4;

when nroflorts are p8 to p 16: when the number of the receiving antennas is n 1-n 2, the length of the CSI feedback information is L2; when the number of the receiving antennas is n 2-n 3, the length of the CSI feedback information is L3; when the number of the receiving antennas is n 3-n 4, the length of the CSI feedback information is L4; when the number of the receiving antennas is > n4, the length of the CSI feedback information is L4;

when nroflorts are p24 to p 32: when the number of the receiving antennas is n 1-n 2, the length of the CSI feedback information is L3; when the number of the receiving antennas is n 2-n 3, the length of the CSI feedback information is L4; when the number of the receiving antennas is n 3-n 4, the length of the CSI feedback information is L4; when the number of the receiving antennas is > n4, the length of the CSI feedback information is L4;

it should be noted that the second corresponding relationship between the parameters of the CSI feedback information and the nrofPorts and the number of receiving antennas may be set as required, including but not limited to the above relationship.

In one embodiment, the method further comprises: and quantizing the output of the network middle layer.

Specifically, the information output and acquired by the UE from the network intermediate layer is a floating point number, and the information needs to be quantized to obtain the final CSI feedback information.

Optionally, the quantization includes quantization modes such as μ law quantization, amplitude quantization, and phase quantization, and a quantization mode combining amplitude quantization and phase quantization may also be used. Wherein the phase quantization comprises a table look-up method or a PSK quantization; the amplitude quantization includes a normalization process.

In a specific application, CSI feedback is implemented based on AI, and an application scenario of the embodiment of the present invention is described with an example of a length of CSI feedback information. The CSI feedback process is analogized to a compression and recovery process, and the UE side compresses channel information on the CSI-RS position by using a network to generate CSI feedback information and feeds the CSI feedback information back to the gNB. And the gNB decompresses the CSI feedback information by using the corresponding network to recover the channel information on the CSI-RS position. As shown in fig. 5 and fig. 6, fig. 5 is a schematic diagram of a CSI feedback method on a UE side in an embodiment of the present invention, and fig. 6 is a schematic diagram of a CSI feedback method on a gbb side.

For the UE-side network in fig. 5, a channel matrix (denoted as H) with CSI-RS as Input is Input (Input), and the H is processed by a compression step S501 and a quantization step S503 to obtain CSI feedback information (CSI-coded).

The compression step S501 is adapted to perform compression processing, and includes the following specific procedures: h is subjected to convolution calculation through a neural network (Conv2D), and a compression result is obtained through full connection layer (Dense) processing.

The quantization step S503 may be implemented by a Quantizer (Quantizer).

Further, after the UE performs step S301, the UE may also perform a decompression step S502 to obtain a channel matrix H, i.e., an Output (Output), of the recovered CSI-RS. The operation process of the decompression step S502 is opposite to the operation process of the compression step S501, that is, the compressed result is subjected to inverse processing by the full connection layer (density) and then to inverse convolution calculation by the neural network (Conv2D), so as to restore the compressed result to the channel matrix H.

Wherein, the quantization can be uniform quantization or non-uniform quantization.

For the network on the side of the gNB in fig. 6, CSI feedback information (CSI-code) received by the gNB and having a quantization error (Dequantizer) removed is Input (Input), and a channel matrix H of the recovered CSI-RS is Output (Output), where the recovery operation mainly refers to decompressing the CSI feedback information, that is, performing inverse processing on the CSI feedback information having the quantization error removed through a full connection layer (Dense), and then performing inverse convolution calculation through the network (Conv 2D). It can be seen that, in this example, the network where the UE acquires the CSI feedback information and the network where the gNB recovers the channel information are in one-to-one correspondence.

Based on the above method, the simulation parameters for simulation verification are shown in table 2, and the simulation results obtained by different port numbers are shown in tables 3 to 5:

TABLE 2 simulation parameters

The simulation results are as follows:

80000 training set, 10000 verification set, 5000 test set.

TABLE 3 simulation results for Port number 4

TABLE 4 simulation results for Port number of 16

Length of feedback information	NMSE
		5	-28.478
10	-32.417
		20	-33.954
25	-34.932
		50	-35.167

TABLE 5 simulation results for Port number 32

Length of feedback information	NMSE
		5	-25.964
10	-29.966
		20	-31.328
25	-31.851
		50	-34.788

As can be seen from the simulation results in tables 3 to 5, the longer the length of the CSI feedback information is, the more accurate the channel information recovered by the gNB is under the same configuration (i.e., the same port number); under the same feedback information length, the smaller the port number is, the more accurate the channel information recovered by the gNB is. The accuracy of the channel information recovered by the gNB is related to the CSI feedback information length and the number of ports and other configurations (e.g., the number of receive antennas).

For the AI-based CSI feedback method, experiments show that: the length and configuration condition of the CSI feedback information fed back by the UE and the accuracy of the channel information recovered by the gNB are mutually restricted, and the lengths of the CSI feedback information reported by the UE may be different under different configurations or different scene requirements; different lengths of the CSI feedback information and different networks are used, and the network for generating the CSI feedback information at the UE side and the network for recovering the channel information at the gNB side are corresponding to each other, so that the two networks need to be consistent. The base station can indicate the length of the CSI feedback information through the configuration signaling so as to use the AI-based CSI feedback mechanism in an actual communication system, so that the UE determines the length of the CSI feedback information.

Compared with the traditional method, the AI-based CSI feedback mechanism provided by the invention has the advantages that the network equipment can acquire the full-channel information of the CSI-RS position, the selected PMI, MCS and the like are more reliable, more reasonable time-frequency resources can be distributed for the UE, the resource utilization rate is favorably improved, the communication reliability is improved, and the interference among the UE is reduced.

Referring to fig. 7, fig. 7 is a schematic flowchart of a fifth CSI feedback method according to an embodiment of the present invention, where the method includes:

step S701, generating a first configuration signaling, wherein the configuration signaling is used for configuring parameters of CSI feedback information;

step S702, sending the first configuration signaling to the UE.

In an embodiment, referring to fig. 8, a sixth CSI feedback method according to the embodiment of the present invention includes:

step S801, sending a first configuration signaling to UE (user equipment) so that the UE can acquire parameters of CSI feedback information according to the first configuration signaling, and selecting a network according to the parameters of the CSI feedback information so as to process the CSI to generate the CSI feedback information;

step S802, receiving CSI feedback information reported by the UE;

step S803, the CSI feedback information is inversely processed to obtain the CSI;

Optionally, the first configuration signaling includes indication information of a parameter of a network intermediate layer.

Optionally, the configuration signaling is carried by RRC signaling and/or DCI.

The CSI feedback methods in fig. 7 and 8 may be performed on the network device (AP or base station, etc.) side, corresponding to the UE side. More contents of the working principle and the working mode of the method may refer to the description related to the network device in fig. 1 and fig. 2, and are not described herein again.

Referring to fig. 9, fig. 9 is a schematic flowchart of a seventh CSI feedback method according to an embodiment of the present invention, where the method includes:

step S901, generating a second configuration signaling, wherein the second configuration signaling comprises first indication information, the first indication information is used for indicating the number of CSI-RS ports, and the number of the CSI-RS ports is used for configuring parameters of CSI feedback information;

step S902, sending the second configuration signaling to the UE.

The CSI feedback method in fig. 9 may be performed on the network device side, corresponding to the UE side. More contents of the working principle and the working mode of the method may refer to the description related to the network device in fig. 3, and are not described herein again.

Referring to fig. 10, fig. 10 is a schematic flowchart of an eighth CSI feedback method according to an embodiment of the present invention, where the method includes:

step S1001, generating a second configuration signaling, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports;

step S1002, generating a third configuration signaling, where the third configuration signaling includes second indication information, and the second indication information is used for indicating the number of receiving antennas;

step S1003, the second configuration signaling and the third configuration signaling are sent to the UE, and the number of the CSI-RS ports and the number of the receiving antennas are used for configuring parameters of the CSI feedback information.

The CSI feedback method in fig. 10 may be performed by a network device, corresponding to the UE side. More contents of the working principle and the working mode of the method may refer to the related description about the network device in fig. 4, and are not described herein again.

Referring to fig. 11, a first CSI feedback apparatus 11 according to an embodiment of the present invention includes:

a first configuration signaling receiving module 1101, configured to receive a first configuration signaling from a network device;

a first parameter obtaining module 1102, configured to obtain a parameter of the CSI feedback information according to the first configuration signaling.

For more contents of the operation principle and the operation mode of the CSI feedback apparatus 11, reference may be made to fig. 1 and fig. 2 for related description of the CSI feedback method, which is not repeated herein.

Referring to fig. 12, an embodiment of the present invention provides a second CSI feedback apparatus 12, including:

a second configuration signaling receiving module 1201, configured to receive second configuration signaling from a network device, where the second configuration signaling includes first indication information, and the first indication information is used to indicate the number of CSI-RS ports;

a second parameter obtaining module 1202, configured to obtain a parameter of the CSI feedback information according to the number of CSI-RS ports.

For more details on the operation principle and the operation mode of the CSI feedback apparatus 12, reference may be made to the description of the CSI feedback method in fig. 3, which is not described herein again.

Referring to fig. 13, a third CSI feedback apparatus 13 according to an embodiment of the present invention includes:

a configuration signaling receiving module 1301, configured to receive a second configuration signaling and a third configuration signaling from a network device, where the second configuration signaling includes first indication information, the first indication information is used to indicate the number of CSI-RS ports, the third configuration signaling includes second indication information, and the second indication information is used to indicate the number of receiving antennas;

a third parameter obtaining module 1302, configured to obtain a parameter of the CSI feedback information according to the number of CSI-RS ports and the number of receiving antennas.

For more contents of the operation principle and the operation manner of the CSI feedback apparatus 13, reference may be made to the description about the CSI feedback method in fig. 4, which is not described herein again.

In a specific implementation, the CSI feedback devices 11 to 13 may correspond to a Chip having a CSI feedback function in the UE, or correspond to a Chip having a data processing function, such as a System-On-a-Chip (SOC), a baseband Chip, or the like; or the chip module is corresponding to the UE and comprises a chip with a CSI feedback function; or to a chip module having a chip with data processing function, or to a UE.

Referring to fig. 14, a fourth CSI feedback apparatus 14 according to an embodiment of the present invention includes:

a first configuration signaling generating module 1401, configured to generate a first configuration signaling, where the configuration signaling is used to configure parameters of CSI feedback information;

a first configuration signaling sending module 1402, configured to send the first configuration signaling to the UE.

For more details on the operation principle and the operation mode of the CSI feedback apparatus 14, reference may be made to fig. 7 and fig. 8 for the description of the CSI feedback method, which is not repeated here.

Referring to fig. 15, a fifth CSI feedback apparatus 15 according to an embodiment of the present invention includes:

a second configuration signaling generation module 1501, configured to generate second configuration signaling, where the second configuration signaling includes first indication information, the first indication information is used to indicate the number of CSI-RS ports, and the number of CSI-RS ports is used to configure parameters of CSI feedback information;

a second configuration signaling sending module 1502, configured to send the second configuration signaling to the UE.

For more details of the operation principle and the operation mode of the CSI feedback apparatus 15, reference may be made to the description of the CSI feedback method in fig. 9, and details are not repeated here.

Referring to fig. 16, a sixth CSI feedback apparatus 16 according to an embodiment of the present invention includes:

a second configuration signaling generation module 1601, configured to generate second configuration signaling, where the second configuration signaling includes first indication information, and the first indication information is used to indicate a CSI-RS port number;

a third configuration signaling generating module 1602, configured to generate a third configuration signaling, where the third configuration signaling includes second indication information, and the second indication information is used to indicate the number of receiving antennas;

a configuration signaling sending module 1603, configured to send the second configuration signaling and the third configuration signaling to the UE, where the number of CSI-RS ports and the number of receiving antennas are used to configure parameters of CSI feedback information.

For more details on the operation principle and the operation mode of the CSI feedback apparatus 16, reference may be made to the description of the CSI feedback method in fig. 10, and details are not repeated here.

In a specific implementation, the CSI feedback devices 14 to 16 may correspond to a Chip having a CSI feedback function in a network device, or correspond to a Chip having a data processing function, such as a System-On-a-Chip (SOC), a baseband Chip, or the like; or the chip module is corresponding to the network equipment and comprises a chip with a CSI feedback function; or to a chip module having a chip with data processing function, or to a network device, such as a base station.

In specific implementation, regarding each module/unit included in each apparatus and product described in the foregoing embodiments, it may be a software module/unit, or may also be a hardware module/unit, or may also be a part of the software module/unit and a part of the hardware module/unit. For example, for each device or product applied to or integrated into a chip, each module/unit included in the device or product may be implemented by hardware such as a circuit, or at least a part of the module/unit may be implemented by a software program running on a processor integrated within the chip, and the rest (if any) part of the module/unit may be implemented by hardware such as a circuit; for each device or product applied to or integrated with the chip module, each module/unit included in the device or product may be implemented by using hardware such as a circuit, and different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the chip module, or at least some of the modules/units may be implemented by using a software program running on a processor integrated within the chip module, and the rest (if any) of the modules/units may be implemented by using hardware such as a circuit; for each device and product applied to or integrated in the terminal, each module/unit included in the device and product may be implemented by hardware such as a circuit, different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) or different components in the terminal, or at least part of the modules/units may be implemented by a software program running on a processor integrated in the terminal, and the rest (if any) part of the modules/units may be implemented by hardware such as a circuit.

An embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to execute the steps of the method in any one of fig. 1 to 4 or any one of fig. 7 to 10. The storage medium may be a computer-readable storage medium, and may include, for example, a non-volatile (non-volatile) or non-transitory (non-transitory) memory, and may further include an optical disc, a mechanical hard disk, a solid state hard disk, and the like.

The embodiment of the invention also provides a terminal which can be UE. The terminal includes the apparatus shown in any one of fig. 11 to 13, or may include a memory and a processor, where the memory stores a computer program executable on the processor, and the processor executes the computer program to perform the steps of the method shown in fig. 1 to 4.

An embodiment of the present invention further provides a network device, which includes the apparatus shown in any one of fig. 14 to fig. 16, or includes a memory and a processor, where the memory stores a computer program executable on the processor, and the processor executes the steps of the method shown in fig. 7 to fig. 10 when executing the computer program.

Specifically, in the embodiment of the present invention, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will also be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example and not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (enhanced SDRAM), SDRAM (SLDRAM), synchlink DRAM (SLDRAM), and direct bus RAM (DR RAM).

It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document indicates that the former and latter related objects are in an "or" relationship.

The "plurality" appearing in the embodiments of the present application means two or more.

The descriptions of the first, second, etc. appearing in the embodiments of the present application are only for illustrating and differentiating the objects, and do not represent the order or the particular limitation of the number of the devices in the embodiments of the present application, and do not constitute any limitation to the embodiments of the present application.

The term "connect" in the embodiments of the present application refers to various connection manners, such as direct connection or indirect connection, to implement communication between devices, which is not limited in this embodiment of the present application.

Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A CSI feedback method, characterized in that the method comprises:

receiving first configuration signaling from a network device;

and acquiring parameters of the CSI feedback information according to the first configuration signaling.

2. The method of claim 1, wherein the first configuration signaling comprises indication information of a network type.

3. The method of claim 1, wherein the first configuration signaling comprises indication information of a parameter of a network middle layer.

4. The method of claim 1, wherein the first configuration signaling comprises indication information of a network type and indication information of a parameter of a network middle layer.

5. The method of claim 1, wherein the first configuration signaling comprises indication information of a first network type and indication information of a second network type, the network corresponding to the first network type is used for generating CSI feedback information of first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of second-stage feedback.

6. The method of claim 1, wherein the first configuration signaling comprises indication information of a parameter of a first network middle layer and indication information of a parameter of a second network middle layer, the network corresponding to the first network type is used for generating CSI feedback information of first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of second-stage feedback.

7. The method of claim 5 or 6, wherein the first configuration signaling comprises a first periodicity and a second periodicity.

8. The method according to any of claims 1 to 6, wherein the first configuration signaling is carried by radio resource control signaling and/or downlink control signaling.

9. A CSI feedback method, characterized in that the method comprises:

receiving second configuration signaling from the network equipment, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports;

and acquiring parameters of the CSI feedback information according to the number of the CSI-RS ports.

10. The method of claim 9, wherein the parameters of the CSI feedback information comprise parameters of a network type.

11. The method according to claim 9 or 10, wherein the parameters of the CSI feedback information comprise parameters of a network intermediate output layer.

12. A CSI feedback method, the method further comprising:

receiving second configuration signaling and third configuration signaling from a network device, wherein the second configuration signaling comprises first indication information, the first indication information is used for indicating the number of CSI-RS ports, the third configuration signaling comprises second indication information, and the second indication information is used for indicating the number of receiving antennas;

and acquiring parameters of CSI feedback information according to the number of the CSI-RS ports and the number of the receiving antennas.

13. The method of claim 12, wherein the parameters of the CSI feedback information comprise parameters of a network type.

14. The method according to claim 12 or 13, wherein the parameters of the CSI feedback information comprise parameters of a network intermediate output layer.

15. The method of claim 1, 9 or 12, further comprising:

and carrying out quantization processing on the output of the network middle layer.

16. The method of claim 15, wherein quantizing the output of the network intermediate layer comprises:

and carrying out mu-law quantization processing on the output of the network intermediate layer.

17. The method of claim 15, wherein quantizing the output of the network intermediate layer comprises:

and carrying out phase quantization processing on the output of the network intermediate layer.

18. The method of claim 17, wherein the performing phase quantization processing on the output of the network intermediate layer comprises:

and performing phase quantization processing on the output of the network middle layer according to a table look-up method.

19. The method of claim 17, wherein the performing phase quantization processing on the output of the network intermediate layer comprises:

and performing PSK quantization processing on the output of the network middle layer.

20. The method of claim 15, wherein quantizing the output of the network intermediate layer comprises:

and carrying out amplitude quantization processing on the output of the network middle layer.

21. The method of claim 15, wherein quantizing the output of the network intermediate layer comprises:

and carrying out amplitude quantization processing and phase quantization processing on the output of the network intermediate layer.

22. The method according to claim 20 or 21, wherein the amplitude quantization processing of the output of the network intermediate layer comprises:

and carrying out normalization processing on the output of the network intermediate layer.

23. A CSI feedback method, characterized in that the method comprises:

generating a first configuration signaling, wherein the configuration signaling is used for configuring parameters of CSI feedback information;

and sending the first configuration signaling to the UE.

24. The method of claim 23, wherein the first configuration signaling comprises indication information of a network type.

25. The method of claim 23, wherein the first configuration signaling comprises indication information of a parameter of a network middle layer.

26. The method of claim 23, wherein the first configuration signaling comprises indication information of a network type and indication information of a parameter of a network middle layer.

27. The method of claim 23, wherein the first configuration signaling comprises indication information of a first network type and indication information of a second network type, the network corresponding to the first network type is used for generating CSI feedback information of first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of second-stage feedback.

28. The method of claim 23, wherein the first configuration signaling comprises indication information of a parameter of a first network interlayer and indication information of a parameter of a second network interlayer, and wherein the network corresponding to the first network type is used for generating CSI feedback information of a first-stage feedback, and the network corresponding to the second network type is used for generating CSI feedback information of a second-stage feedback.

29. The method according to claim 27 or 28, wherein the first configuration signaling comprises a first periodicity and a second periodicity.

30. A CSI feedback method, characterized in that the method comprises:

generating second configuration signaling, wherein the second configuration signaling comprises first indication information, the first indication information is used for indicating the number of CSI-RS ports, and the number of the CSI-RS ports is used for configuring parameters of CSI feedback information;

and sending the second configuration signaling to the UE.

31. A CSI feedback method, characterized in that the method comprises:

generating second configuration signaling, wherein the second configuration signaling comprises first indication information, and the first indication information is used for indicating the number of CSI-RS ports;

generating third configuration signaling, wherein the third configuration signaling comprises second indication information, and the second indication information is used for indicating the number of receiving antennas;

and sending the second configuration signaling and the third configuration signaling to the UE, wherein the number of the CSI-RS ports and the number of the receiving antennas are used for configuring parameters of CSI feedback information.

32. A CSI feedback apparatus, wherein the apparatus comprises:

a first configuration signaling receiving module, configured to receive a first configuration signaling from a network device;

and the first parameter acquisition module is used for acquiring the parameters of the CSI feedback information according to the first configuration signaling.

33. A CSI feedback apparatus, wherein the apparatus comprises:

a first configuration signaling generation module, configured to generate a first configuration signaling, where the configuration signaling is used to configure parameters of CSI feedback information;

and the first configuration signaling sending module is used for sending the first configuration signaling to the UE.

34. A storage medium having a computer program stored thereon, the computer program, when executed by a processor, performing the method of any of claims 1 to 22 or the steps of the method of any of claims 23 to 31.

35. A terminal comprising an apparatus as claimed in claim 32, or comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of any of claims 1 to 22.

36. A network device comprising the apparatus of claim 33 or comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of any of claims 23 to 31.