WO2022151084A1 - 信息量化方法、装置、通信设备及存储介质 - Google Patents

信息量化方法、装置、通信设备及存储介质 Download PDF

Info

Publication number
WO2022151084A1
WO2022151084A1 PCT/CN2021/071575 CN2021071575W WO2022151084A1 WO 2022151084 A1 WO2022151084 A1 WO 2022151084A1 CN 2021071575 W CN2021071575 W CN 2021071575W WO 2022151084 A1 WO2022151084 A1 WO 2022151084A1
Authority
WO
WIPO (PCT)
Prior art keywords
quantization
information
indication signaling
grouping
target
Prior art date
Application number
PCT/CN2021/071575
Other languages
English (en)
French (fr)
Inventor
田文强
张治�
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to PCT/CN2021/071575 priority Critical patent/WO2022151084A1/zh
Priority to CN202180089646.XA priority patent/CN116711237A/zh
Priority to EP21918299.5A priority patent/EP4274299A4/en
Publication of WO2022151084A1 publication Critical patent/WO2022151084A1/zh
Priority to US18/349,669 priority patent/US20230354081A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/20—Monitoring; Testing of receivers
    • H04B17/24—Monitoring; Testing of receivers with feedback of measurements to the transmitter
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
    • H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
    • H04L1/0026—Transmission of channel quality indication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
    • H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
    • H04L1/0028—Formatting
    • H04L1/0029—Reduction of the amount of signalling, e.g. retention of useful signalling or differential signalling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0621—Feedback content
    • H04B7/0626—Channel coefficients, e.g. channel state information [CSI]

Definitions

  • the present application relates to the field of communication technologies, and in particular, to an information quantification method, apparatus, communication device and storage medium.
  • the terminal device generally generates CSI feedback information through channel state information (Channel State Information, CSI) measurement.
  • CSI Channel State Information
  • the terminal device Before reporting the CSI feedback information, the terminal device generally needs to quantize the CSI feedback information.
  • a unified quantization quantization strategy is adopted, that is, the terminal equipment uses the same quantization method to quantize the CSI feedback information to be fed back.
  • the embodiments of the present application provide an information quantization method, apparatus, communication device, and storage medium.
  • a target grouping quantization scheme is negotiated between a terminal device and a network device.
  • the target grouping quantization scheme there are at least two groups corresponding to different quantization methods. So that the terminal device performs packet quantization on the CSI feedback information based on the target packet quantization scheme.
  • the technical solution is as follows:
  • an information quantification method which is applied to a terminal device, and the method includes:
  • an information quantification method applied to a network device, the method includes:
  • the target grouping quantization scheme is used for the terminal equipment to group the CSI feedback information, and quantize the CSI feedback information in the group according to the quantization method corresponding to the group; there are at least two groups corresponding to in different quantification methods.
  • an information quantization apparatus which is applied in a terminal device, and the apparatus includes: a determination module and a quantization module;
  • the determining module is used to interact with the network device to determine the target grouping quantization scheme
  • the quantization module is configured to group the CSI feedback information based on the target grouping quantization scheme, and quantize the CSI feedback information in the grouping according to the quantization mode corresponding to the grouping;
  • an information quantification apparatus which is applied to a network device, and the apparatus includes: a determination module;
  • the determining module is used to interact with the terminal device to determine the target grouping quantization scheme
  • the target grouping quantization scheme is used for the terminal equipment to group the CSI feedback information, and quantize the CSI feedback information in the group according to the quantization method corresponding to the group; there are at least two groups corresponding to in different quantification methods.
  • a terminal device comprising: a processor and a transceiver connected to the processor; wherein,
  • the transceiver for interacting with the network device to determine the target packet quantization scheme
  • the processor configured to group the CSI feedback information based on the target grouping quantization scheme, and quantize the CSI feedback information in the grouping according to a quantization manner corresponding to the grouping;
  • a network device comprising: a processor and a transceiver connected to the processor; wherein,
  • the transceiver for interacting with the terminal device to determine the target packet quantization scheme
  • the target grouping quantization scheme is used for the terminal equipment to group the CSI feedback information, and quantize the CSI feedback information in the group according to the quantization method corresponding to the group; there are at least two groups corresponding to in different quantification methods.
  • a computer-readable storage medium is provided, and executable instructions are stored in the readable storage medium, and the executable instructions are loaded and executed by a processor to realize the information described in the above-mentioned aspects. quantification method.
  • a chip is provided, the chip includes a programmable logic circuit and/or program instructions, and when the chip runs on a computer device, it is used to implement the information quantification described in the above aspect method.
  • a computer program product which, when running on a processor of a computer device, enables the computer device to execute the information quantification method described in the above aspects.
  • a target grouping quantization scheme is negotiated between the terminal equipment and the network equipment, so that the terminal equipment groups the CSI feedback information based on the target grouping quantization scheme, and quantizes the CSI feedback information according to the quantization method corresponding to the grouping.
  • this grouping quantization method makes full use of the distribution characteristics of the CSI feedback information, and quantizes the CSI feedback information with different distribution characteristics through different groups, thereby Under the condition of ensuring the quantization accuracy, the number of bits required for quantization is reduced as much as possible, thereby reducing the feedback overhead of the CSI feedback information.
  • FIG. 1 is a schematic diagram of a process of generating and indicating channel state information provided by an exemplary embodiment of the present application
  • FIG. 2 is a schematic diagram of a neural network provided by an exemplary embodiment of the present application.
  • FIG. 3 is a schematic diagram of a convolutional neural network provided by an exemplary embodiment of the present application.
  • FIG. 4 is a schematic diagram of a network architecture using a neural network model for channel state information indication provided by an exemplary embodiment of the present application
  • FIG. 5 is a block diagram of a communication system provided by an exemplary embodiment of the present application.
  • FIG. 6 is a flowchart of an information quantification method provided by an exemplary embodiment of the present application.
  • FIG. 7 is a flowchart of an information quantification method provided by an exemplary embodiment of the present application.
  • FIG. 8 is a schematic diagram of an information quantization process provided by an exemplary embodiment of the present application.
  • FIG. 9 is a flowchart of an information quantification method provided by an exemplary embodiment of the present application.
  • FIG. 10 is a schematic diagram of an information quantization process provided by an exemplary embodiment of the present application.
  • FIG. 11 is a schematic diagram of an information quantization process provided by an exemplary embodiment of the present application.
  • FIG. 12 is a structural block diagram of an information quantization apparatus provided by an exemplary embodiment of the present application.
  • FIG. 13 is a structural block diagram of an information quantization apparatus provided by an exemplary embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of a communication device provided by an exemplary embodiment of the present application.
  • CSI Channel State Information
  • CSI is information for describing channel properties of a communication link.
  • the indication of CSI is very important in a communication system, which determines the performance of multiple-input multiple-output (Multiple-Input Multiple-Output, MIMO) transmission.
  • MIMO Multiple-Input Multiple-Output
  • the CSI indication in a communication system may include an indication of information such as a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), and a Rank Indicator (RI).
  • CQI Channel Quality Indicator
  • PMI Precoding Matrix Indicator
  • RI Rank Indicator
  • the network device can configure the terminal device with indication parameter information for CSI indication, for example, which information in the CQI, PMI, RI and other information the terminal device needs to indicate; at the same time, the network device can configure some information for the terminal device A reference signal used for CSI measurement, such as a synchronization signal block (Synchronization Signal Block, SSB) and/or a channel state information reference signal (Channel State Information-Reference Signal, CSI-RS).
  • the terminal device determines the current channel state information by measuring the above reference signal, and indicates the current CSI feedback information to the network device according to the indication parameter information configured by the network device, so that the network device can configure reasonable and efficient data based on the current channel situation. transfer method.
  • FIG. 2 shows a schematic diagram of a neural network provided by an embodiment of the present application.
  • the basic structure of a simple neural network includes: input layer, hidden layer and output layer. Among them, the input layer is responsible for receiving data, the hidden layer is responsible for processing data, and the final result is generated in the output layer.
  • each node represents a processing unit, which can also be considered to simulate a neuron, and multiple neurons form a layer of neural network, and the multi-layer information transmission and processing constructs an overall neural network.
  • neural network deep learning algorithms have been proposed, more hidden layers have been introduced, and feature learning is performed layer by layer through multi-hidden layer neural network training, which greatly improves neural network learning. It is widely used in pattern recognition, signal processing, optimal combination, anomaly detection, etc.
  • FIG. 3 shows a schematic diagram of a convolutional neural network provided by an embodiment of the present application.
  • a convolutional neural network its basic structure includes: an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer and an output layer.
  • the introduction of the convolutional layer and the pooling layer effectively controls the sharp increase of network parameters, limits the number of parameters and exploits the characteristics of local structures, and improves the robustness of the algorithm.
  • FIG. 4 shows a schematic diagram of a network architecture using a neural network model for channel state information indication provided by an embodiment of the present application.
  • the encoding end first calls the encoding end neural network to encode the channel information to be fed back to generate first channel information, which is also the CSI feedback information; after receiving the first channel information, the decoding end calls The neural network at the decoding end decodes the first channel information to obtain feedback channel information.
  • the size of the feedback first channel information is directly related to the feedback performance.
  • the feedback overhead required for transmitting the first channel information needs to be as small as possible; on the other hand, from the perspective of the transmission performance gain of the communication system, the recovery of the channel information to be fed back at the decoding end
  • the quantization scheme for the CSI feedback information adopts a unified quantization scheme, such as uniform quantization, ⁇ -rate quantization, etc.
  • the above quantization method is effective when there is no clear rule for the CSI feedback information.
  • an embodiment of the present application proposes an information quantization method, which is mainly used in the CSI feedback process based on artificial intelligence, so as to minimize the feedback overhead while ensuring the quantization accuracy.
  • FIG. 5 shows a block diagram of a communication system provided by an exemplary embodiment of the present application.
  • the communication system may include: an access network 12 and a terminal device 14 .
  • the access network 12 includes several network devices 120 .
  • the network device 120 may be a base station, which is a device deployed in an access network to provide a wireless communication function for a terminal.
  • the base station may include various forms of macro base station, micro base station, relay station, access point and so on.
  • the names of devices with base station functions may be different.
  • eNodeBs or eNBs In LTE systems, they are called eNodeBs or eNBs; in 5G NR-U systems, they are called gNodeBs or gNBs.
  • the description of "base station” may change.
  • the above-mentioned apparatuses for providing a wireless communication function for the terminal device 14 are collectively referred to as network devices.
  • the terminal device 14 may include various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems, as well as various forms of user equipment, mobile stations (Mobile Station, MS) , terminal device, etc.
  • the network device 120 and the terminal device 14 communicate with each other through a certain air interface technology, such as a Uu interface.
  • GSM Global System of Mobile Communication
  • CDMA Code Division Multiple Access
  • CDMA wideband Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • FDD Frequency Division Duplex
  • TDD Time Division Duplex
  • LTE-A Advanced Long Term Evolution
  • NR New Radio
  • evolution systems of NR systems LTE on unlicensed frequency bands (LTE-based access to Unlicensed spectrum, LTE-U) system, NR-U system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), 6-Generation (6G) systems, next-generation
  • WiMAX Wireless Local Area Networks
  • WLAN Wireless Fidelity
  • 6G 6-Generation
  • D2D Device to Device
  • M2M Machine to Machine
  • MTC Machine Type Communication
  • V2V Vehicle to Vehicle
  • V2X Vehicle to Everything
  • FIG. 6 shows a flowchart of an information quantification method provided by an exemplary embodiment of the present application.
  • the method can be applied to the communication system as shown in Figure 5, and the method includes:
  • step 610 the terminal device and the network device interact to determine the target packet quantization scheme.
  • both the terminal device and the network device determine the same target packet quantization scheme.
  • at least one interaction is performed between the terminal device and the network device, so that the terminal device and the network device determine the target packet quantization scheme.
  • Step 620 The terminal device groups the CSI feedback information based on the target grouping quantization scheme, and quantizes the CSI feedback information in the grouping according to the quantization method corresponding to the grouping.
  • the target grouping quantization scheme is a quantization scheme for quantizing the CSI feedback information in the form of groups.
  • groups there are at least two groups corresponding to different quantization methods.
  • the target grouping quantization scheme it is supported to divide the CSI feedback information into n groups for feedback, where n is a positive integer not less than 2, and each of the n groups corresponds to each of the n quantization methods.
  • the n quantization methods are different from each other.
  • at least two of the n quantization methods are different.
  • the target grouping quantization scheme includes 3 groups: a first grouping, a second grouping and a third grouping, the first grouping corresponds to the first quantization method, the second grouping corresponds to the second quantization method, and the third grouping corresponds to in the third quantification method.
  • the first to third quantization methods are different from each other.
  • the terminal equipment groups the CSI feedback information according to the indication of the target grouping quantization scheme, and then quantizes the CSI feedback information of each group according to the quantization method corresponding to the grouping.
  • the above-mentioned grouping quantization can also be understood as a kind of classification quantization.
  • the CSI feedback information of different distribution characteristics is classified to enter different groups, and then quantization in different quantization modes is performed according to the target grouping quantization scheme.
  • the target grouping quantization scheme includes 3 groups: a first grouping, a second grouping and a third grouping, the first grouping corresponds to the first quantization method, the second grouping corresponds to the second quantization method, and the third grouping corresponds to in the third quantification method.
  • the terminal equipment classifies a part of the CSI feedback information into the first group, uses the first quantization method for quantization, classifies the other part of the CSI feedback information into the second group, uses the second quantization method for quantization, and classifies the other part of the CSI feedback information into the first group.
  • the third quantization method is used for quantization.
  • the CSI feedback information corresponding to different groups has its own distribution characteristics, for example, in different size ranges or in different amplitude ranges.
  • different quantization methods for different groups can be used to avoid different distribution characteristics.
  • Unified quantization is performed between the CSI feedback information.
  • the CSI feedback information is generated based on a neural network model.
  • a neural network model there is a coding-end neural network on the terminal device side, the terminal device generates channel information to be fed back through CSI measurement, and passes the channel information to be fed back through the coding-end neural network to generate first channel information (ie, CSI feedback). information).
  • the terminal device obtains the quantized CSI feedback information after quantizing the CSI feedback information in groups, and sends the quantized CSI feedback information to the network device, and the network device correspondingly receives the quantized CSI feedback information, and according to the target
  • the packet quantization scheme performs dequantization to obtain CSI feedback information.
  • a target grouping quantization scheme is negotiated between the terminal equipment and the network equipment, so that the terminal equipment groups the CSI feedback information based on the target grouping quantization scheme, and feeds back the CSI according to the quantization method corresponding to the grouping.
  • the information is quantized. Since there are at least two groups corresponding to different quantization methods, compared with the unified quantization scheme used in the prior art, this grouping quantization method makes full use of the distribution characteristics of the CSI feedback information.
  • the CSI feedback information is quantized separately by different groups, so that the number of bits required for quantization can be reduced as much as possible under the condition of ensuring the quantization accuracy, thereby reducing the feedback overhead of the CSI feedback information.
  • the target packet quantization scheme is determined through interaction between the terminal device and the network device, and there are two different schemes as follows.
  • the network device indicates a target packet quantization scheme to the terminal device.
  • the network device indicates to the terminal device multiple candidate target grouping quantization schemes, where the target grouping quantization scheme is one of the multiple candidate target grouping quantization schemes.
  • a target packet quantization scheme among a plurality of candidate target packet quantization schemes is indicated by the network device.
  • a target packet quantization scheme among a plurality of candidate target packet quantization schemes is indicated by the terminal device.
  • the network device indicates a target packet quantization scheme to the terminal device.
  • FIG. 7 shows a flowchart of an information quantization method provided by an exemplary embodiment of the present application.
  • the method can be applied to the communication system as shown in Figure 5, and the method includes:
  • Step 710 The network device sends first indication signaling, where the first indication signaling is used to indicate the target packet quantization scheme.
  • the network device After determining the target packet quantization scheme, the network device configures the target packet quantization scheme to the terminal device through the first indication signaling. Optionally, the network device determines the target packet quantization scheme based on the current channel characteristics.
  • the first indication signaling includes at least one of the following: a broadcast message, a system information block (System Information Block, SIB), a radio resource control (Radio Resource Control, RRC) message, RRC reconfiguration signaling, downlink Control Information (Downlink Control Information, DCI), Medium Access Control (Medium Access Control, MAC) Control Element (Control Element, CE), Physical Downlink Control Channel (Physical Downlink Control Channel, PDCCH) Command (order), data information .
  • SIB System Information Block
  • RRC Radio Resource Control
  • RRC Radio Resource Control
  • RRC Radio Resource Control
  • the SIB is a possible implementation form of the broadcast message
  • the RRC reconfiguration signaling is a possible implementation form of the RRC message. That is, the first indication signaling includes at least one of the following: broadcast message, RRC message, DCI, MAC CE, PDCCH order, and data information; the broadcast message includes SIB, and the RRC message includes RRC reconfiguration signaling.
  • Step 720 The terminal device receives the first indication signaling sent by the network device.
  • Step 730 the terminal device acquires the target packet quantization division based on the first indication signaling.
  • the terminal device After receiving the first indication signaling, the terminal device obtains the target packet quantization scheme configured by the network device through the first indication signaling.
  • Step 740 The terminal device groups the CSI feedback information based on the target grouping quantization scheme, and quantizes the CSI feedback information in the grouping according to the quantization method corresponding to the grouping.
  • the target grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback method information is used to describe the quantization method corresponding to the group, and the feedback parameter information is used to describe the parameters corresponding to the quantization method.
  • the feedback mode information and the feedback parameter information together indicate the quantization mode corresponding to the packet.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • uniform quantization refers to a quantization method for quantizing CSI feedback information with the same quantization granularity
  • non-uniform quantization refers to a method for quantizing CSI feedback information with different quantization granularities in different intervals quantification method.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • quantization bits refer to the number of bits used to quantize a piece of data in the CSI feedback information
  • quantization granularity refers to the interval between adjacent quantization values
  • quantization range refers to the range of data that supports quantization.
  • the feedback mode information is uniform quantization; the corresponding feedback parameter information includes: the quantization bit is 2 bits, the quantization granularity is 1, and the quantization range is 0-3. For data 0, the quantized data is 00; for data 1, the quantized data is 01; for data 2, the quantized data is 10; for data 3, the quantized data is 11.
  • the feedback mode information is non-uniform quantization;
  • the corresponding feedback parameter information includes: the quantization bit is 2 bits, the quantization granularity corresponding to the quantization range 0-1 is 0.5, and the quantization granularity corresponding to the quantization range 1-2 is 1. Then, for data 0, the quantized data is 00; for data 0.5, the quantized data is 01; for data 1, the quantized data is 10; for data 2, the quantized data is 11.
  • the network device configures the terminal device to use feedback mode 1 as the target packet quantization scheme in the first indication signaling, and the feedback mode 1 includes: the number of feedback bits is 256 bits, wherein 256 bits are divided into 4 groups, and the first group 64 bits are obtained by the first quantization method, 64 bits of the second group are obtained by the second quantization method, 64 bits of the third group are obtained by the third quantization method, and 64 bits of the fourth group are obtained by the fourth quantization method.
  • the quantization granularity is the first quantization granularity
  • the quantization bit is the first quantization bit
  • the quantization range is the first quantization range.
  • the first quantization granularity is 1/(2 ⁇ 4)
  • the first quantization bit is 4, and the first quantization range is 0 to 1
  • the first quantization method will quantize the number between 0 and 1 by 4 bits
  • the quantization granularity is kept at 1/(2 ⁇ 4). 16 real numbers can be fed back through the above method.
  • the quantization granularity is the second quantization granularity
  • the quantization bit is the second quantization bit
  • the quantization range is the second quantization range.
  • the second quantization granularity is 1/(2 ⁇ 4)
  • the second quantization bit is 2
  • the second quantization range is 0 to 0.25
  • the second quantization method will quantize the numbers between 0 and 0.25 with 2 bits
  • the quantization granularity is kept at 1/(2 ⁇ 4).
  • the quantization granularity is the third quantization granularity
  • the quantization bit is the third quantization bit
  • the quantization range is the third quantization range.
  • the third quantization granularity is 1/(2 ⁇ 3)
  • the third quantization bit is 4, and the third quantization range is 0 to 2
  • the third quantization method will quantize the numbers between 0 and 2 by 4 bits
  • the quantization granularity remains at 1/(2 ⁇ 3). 16 real numbers can be fed back through the above method.
  • the quantization granularity is the fourth quantization granularity
  • the quantization bit is the fourth quantization bit
  • the quantization range is the fourth quantization range.
  • the fourth quantization granularity is 1/(2 ⁇ 2)
  • the fourth quantization bit is 4, and the fourth quantization range is 0 to 4
  • the third quantization method will quantize the numbers between 0 and 4 with 4 bits
  • the quantization granularity remains at 1/(2 ⁇ 2). 16 real numbers can be fed back through the above method.
  • the network device indicates the target packet quantization scheme to the terminal device by sending the first indication signaling, and realizes the communication between the network device and the terminal device about the quantization scheme with a relatively simple interaction process. Unification to avoid errors during both quantization and dequantization.
  • the method includes the following steps:
  • the network device configures the target packet quantization scheme for the terminal device.
  • the network device configures the terminal device through at least one of broadcast messages, SIBs, RRC messages, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • the terminal device performs corresponding packet quantization according to the target packet quantization scheme.
  • the terminal device receives the target packet quantization scheme configured by the network device, and performs packet quantization on the CSI feedback information according to the target packet quantization scheme.
  • the terminal device transmits the quantized CSI feedback information to the network device.
  • the network device performs corresponding dequantization according to the target packet quantization scheme.
  • the network device After receiving the quantized CSI feedback information, the network device dequantizes the quantized CSI feedback information according to the target packet quantization scheme.
  • the network device indicates to the terminal device multiple candidate target grouping quantization schemes, where the target grouping quantization scheme is one of the multiple candidate target grouping quantization schemes.
  • FIG. 9 shows a flowchart of an information quantification method provided by an exemplary embodiment of the present application.
  • the method can be applied to the communication system as shown in Figure 5, and the method includes:
  • Step 910 The network device sends second indication signaling to the terminal device, where the second indication signaling is used to indicate n candidate packet quantization schemes.
  • n is a positive integer greater than 1. That is, there are multiple candidate packet quantization schemes.
  • the network device determines n candidate packet quantization schemes, and configures the n candidate packet quantization schemes to the terminal device through the second indication signaling.
  • the n candidate grouping quantization schemes are different from each other.
  • the second indication signaling includes at least one of the following: broadcast message, SIB, RRC message, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • This embodiment of the present application does not limit the specific type of the second indication signaling.
  • the SIB is a possible implementation form of the broadcast message
  • the RRC reconfiguration signaling is a possible implementation form of the RRC message. That is, the second indication signaling includes at least one of the following: broadcast message, RRC message, DCI, MAC CE, PDCCH order, and data information; the broadcast message includes SIB, and the RRC message includes RRC reconfiguration signaling.
  • Step 920 The terminal device receives the second indication signaling sent by the network device.
  • Step 930 the terminal device acquires n candidate packet quantization schemes based on the second indication signaling.
  • the network device configures, in the second indication signaling, to the terminal device feedback mode 1 to feedback mode 3 as candidate packet quantization schemes. That is, n is 3.
  • Feedback mode 1 includes: the number of feedback bits is 256 bits, of which 256 bits are divided into 4 groups, the 64 bits of the first group are obtained by the first quantization method, the 64 bits of the second group are obtained by the second quantization method, and the 64 bits of the third group are obtained by using the second quantization method. The third quantization method is used, and the fourth group of 64 bits is obtained by the fourth quantization method.
  • the feedback mode 2 includes: the number of feedback bits is 128 bits, wherein the 128 bits are divided into 2 groups, the 64 bits of the first group are obtained by the fifth quantization method, and the 64 bits of the second group are obtained by the sixth quantization method.
  • the feedback mode 3 includes: the number of feedback bits is 128 bits, wherein the 128 bits are divided into 1 group, and this group of 128 bits is obtained by adopting the seventh quantization method.
  • Step 940 the terminal device determines a target packet quantization scheme from the n candidate packet quantization schemes.
  • the target packet quantization scheme among the multiple candidate target packet quantization schemes is indicated by the network device.
  • step 940 is alternatively implemented as: the network device sends the third indication signaling, and the third indication signaling is used to indicate the target packet quantization scheme among the n candidate packet quantization schemes; the terminal device receives the third indication signal sent by the network device. Command; the terminal device determines the target packet quantization scheme from the n candidate packet quantization schemes based on the third indication signaling.
  • the third indication signaling includes at least one of the following: broadcast message, SIB, RRC message, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • This embodiment of the present application does not limit the specific type of the third indication signaling.
  • the SIB is a possible implementation form of the broadcast message
  • the RRC reconfiguration signaling is a possible implementation form of the RRC message. That is, the third indication signaling includes at least one of the following: broadcast message, RRC message, DCI, MAC CE, PDCCH order, and data information; the broadcast message includes SIB, and the RRC message includes RRC reconfiguration signaling.
  • the network device indicates through the DCI that the currently adopted target packet quantization scheme is the xth candidate packet quantization scheme among the pre-configured n candidate packet quantization schemes, where x is a positive integer not greater than n.
  • the network device determines the target packet quantization scheme based on the current channel characteristics.
  • the target packet quantization scheme among the multiple candidate target packet quantization schemes is indicated by the terminal device.
  • the terminal device sends fourth indication signaling to the network device, and the fourth indication signaling is used to indicate the target packet quantization scheme among the n candidate packet quantization schemes; the network device receives the fourth indication signal sent by the terminal device. Indication signaling; the network device determines the target packet quantization scheme from the n candidate packet quantization schemes based on the fourth instruction.
  • the fourth indication signaling includes at least one of the following: uplink control information (Uplink Control Information, UCI), physical uplink control channel (Physical Uplink Control Channel, PUCCH), RRC message, data information.
  • uplink control information Uplink Control Information, UCI
  • physical uplink control channel Physical Uplink Control Channel, PUCCH
  • RRC message data information.
  • the RRC message here is a kind of message sent by the terminal device to the network device, and the RRC message can be supported in the subsequently evolved mobile communication system.
  • the terminal device indicates through the UCI that the currently adopted target packet quantization scheme is the xth candidate packet quantization scheme among the pre-configured n candidate packet quantization schemes, where x is a positive integer not greater than n.
  • the terminal device determines the target packet quantization scheme based on the current channel characteristics.
  • Step 950 The terminal device groups the CSI feedback information based on the target grouping quantization scheme, and quantizes the CSI feedback information in the grouping according to the quantization method corresponding to the grouping.
  • the target grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback method information is used to describe the quantization method corresponding to the group, and the feedback parameter information is used to describe the parameters corresponding to the quantization method.
  • the feedback mode information and the feedback parameter information together indicate the quantization mode corresponding to the packet.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • uniform quantization refers to a quantization method for quantizing CSI feedback information with the same quantization granularity
  • non-uniform quantization refers to a method for quantizing CSI feedback information with different quantization granularities in different intervals quantification method.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • quantization bits refer to the number of bits used to quantize a piece of data in the CSI feedback information; the quantization granularity refers to the interval between adjacent quantized values; and the quantization range refers to the range of data that supports quantization.
  • the network device in the case where the network device pre-configures multiple candidate packet quantization schemes for the terminal device, it only needs to select among the multiple candidate target packet quantization schemes according to the instructions of the network device or the terminal device.
  • the target packet quantization scheme is selected. Since the instruction does not need to carry the specific information of the target packet quantization scheme, the unification of the quantization scheme between the network device and the terminal device is realized with less overhead, and the quantization and dequantization processes on both sides are avoided. error in .
  • the method includes the following steps:
  • the network device configures multiple candidate packet quantization schemes for the terminal device.
  • the network device pre-configures the terminal device through at least one of broadcast messages, SIBs, RRC messages, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • the candidate grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • the network device indicates a target packet quantization scheme to the terminal device.
  • the network device instructs the terminal device to adopt one of the multiple candidate packet quantization schemes through at least one of broadcast messages, SIBs, RRC messages, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • the candidate packet quantization scheme serves as the target packet quantization scheme.
  • the terminal device performs corresponding packet quantization according to the target packet quantization scheme.
  • the terminal device receives the instruction of the network device to determine the target packet quantization scheme, and performs packet quantization on the CSI feedback information according to the target packet quantization scheme.
  • the terminal device transmits the quantized CSI feedback information to the network device.
  • the network device performs corresponding dequantization according to the target packet quantization scheme.
  • the network device After receiving the quantized CSI feedback information, the network device dequantizes the quantized CSI feedback information according to the target packet quantization scheme.
  • the method includes the following steps:
  • the network device configures multiple candidate packet quantization schemes for the terminal device.
  • the network device pre-configures the terminal device through at least one of broadcast messages, SIBs, RRC messages, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, and data information.
  • the candidate grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • the terminal device indicates a target packet quantization scheme to the network device.
  • the terminal device instructs the network device to use one candidate packet quantization scheme among multiple candidate packet quantization schemes as the target packet quantization scheme through at least one of UCI, PUCCH, RRC message, and data information.
  • the terminal device performs corresponding packet quantization according to the target packet quantization scheme.
  • the terminal device performs packet quantization on the CSI feedback information according to the target packet quantization scheme selected by itself.
  • the terminal device transmits the quantized CSI feedback information to the network device.
  • the network device performs corresponding dequantization according to the target packet quantization scheme.
  • the network device After receiving the quantized CSI feedback information, the network device dequantizes the quantized CSI feedback information according to the target packet quantization scheme indicated by the terminal device.
  • the steps performed by the terminal device can be independently implemented as an information quantization method on the terminal device side
  • the steps performed by the network device can be independently implemented as an information quantization method on the network device side
  • FIG. 12 shows a structural block diagram of an information quantization apparatus provided by an exemplary embodiment of the present application.
  • the apparatus may be implemented as a terminal device, or may be implemented as a part of the terminal device.
  • the apparatus includes: a determination module 1201 and a quantization module 1202 ;
  • the determining module 1201 is configured to interact with the network device to determine the target packet quantization scheme
  • the quantization module 1202 is configured to group the CSI feedback information based on the target grouping quantization scheme, and quantize the CSI feedback information in the grouping according to the quantization method corresponding to the grouping;
  • the determining module 1201 is configured to receive a first indication signaling sent by the network device; and obtain the target packet quantization division based on the first indication signaling.
  • the determining module 1201 is configured to receive a second indication signaling sent by the network device; and obtain n candidate packet quantization schemes based on the second indication signaling, where the n is a positive integer greater than 1; the target packet quantization scheme is determined from the n candidate packet quantization schemes.
  • the determining module 1201 is configured to receive a third indication signaling sent by the network device; based on the third indication signaling, select from the n candidate packet quantization schemes The target packet quantization scheme is determined.
  • the indication signaling sent by the network device includes at least one of the following: broadcast message, SIB, RRC message, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, data information .
  • the determining module 1201 is configured to send fourth indication signaling to the network device, where the fourth indication signaling is used to indicate the n candidate packet quantization schemes Describe the target grouping quantification scheme.
  • the fourth indication signaling includes at least one of the following: UCI, PUCCH, RRC message, and data information.
  • the target grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • the CSI feedback information is generated based on a neural network model.
  • FIG. 13 shows a structural block diagram of an information quantification apparatus provided by an exemplary embodiment of the present application.
  • the apparatus may be implemented as a network device, or may be implemented as a part of a network device, and the device includes: a determining module 1301;
  • the determining module 1301 is configured to interact with the terminal device to determine the target grouping quantization scheme
  • the target grouping quantization scheme is used for the terminal equipment to group the CSI feedback information, and quantize the CSI feedback information in the group according to the quantization method corresponding to the group; there are at least two groups corresponding to in different quantification methods.
  • the determining module 1301 is configured to send first indication signaling to the terminal device, where the first indication signaling is used to indicate the target packet quantization division.
  • the determining module 1301 is configured to send a second indication signaling to the terminal device, where the second indication signaling is used to indicate n candidate packet quantization schemes, the n is a positive integer greater than 1; the target packet quantization scheme is determined from the n candidate packet quantization schemes.
  • the determining module 1301 is configured to send a third indication signaling to the terminal device, where the third indication signaling is used to indicate that the n candidate packet quantization schemes are Describe the target grouping quantification scheme.
  • the indication signaling sent by the network device includes at least one of the following: broadcast message, SIB, RRC message, RRC reconfiguration signaling, DCI, MAC CE, PDCCH order, data information .
  • the determining module 1301 is configured to receive a fourth indication signaling sent by the terminal device; based on the fourth instruction, determine from the n candidate packet quantization schemes The target grouping quantization scheme.
  • the fourth indication signaling includes at least one of the following: UCI, PUCCH, RRC message, and data information.
  • the target grouping quantization scheme includes at least one of the following information: feedback mode information for each group, feedback parameter information for each group.
  • the feedback mode information includes at least one of the following information: uniform quantization and non-uniform quantization.
  • the feedback parameter information includes at least one of the following information: quantization bit, quantization granularity, and quantization range.
  • the CSI feedback information is generated based on a neural network model.
  • FIG. 14 shows a schematic structural diagram of a communication device (terminal device or network device) provided by an exemplary embodiment of the present application.
  • the communication device includes: a processor 101 , a receiver 102 , a transmitter 103 , a memory 104 and a bus 105 .
  • the processor 101 includes one or more processing cores, and the processor 101 executes various functional applications and information processing by running software programs and modules.
  • the receiver 102 and the transmitter 103 may be implemented as a communication component, and the communication component may be a communication chip, denoted as a transceiver.
  • the memory 104 is connected to the processor 101 through the bus 105 .
  • the memory 104 may be configured to store at least one instruction, and the processor 101 may be configured to execute the at least one instruction, so as to implement various steps in the foregoing method embodiments.
  • memory 104 may be implemented by any type or combination of volatile or non-volatile storage devices including, but not limited to, magnetic or optical disks, electrically erasable programmable Read Only Memory (Electrically-Erasable Programmable Read Only Memory, EEPROM), Erasable Programmable Read Only Memory (EPROM), Static Random Access Memory (SRAM), Read Only Memory (Read-Only Memory, ROM), magnetic memory, flash memory, programmable read-only memory (Programmable Read-Only Memory, PROM).
  • volatile or non-volatile storage devices including, but not limited to, magnetic or optical disks, electrically erasable programmable Read Only Memory (Electrically-Erasable Programmable Read Only Memory, EEPROM), Erasable Programmable Read Only Memory (EPROM), Static Random Access Memory (SRAM), Read Only Memory (Read-Only Memory, ROM), magnetic memory, flash memory, programmable read-only memory (Programmable Read-Only Memory, PROM).
  • the processor and transceiver in the communication device involved in the embodiments of the present application may perform the steps performed by the terminal device in any of the above-mentioned methods shown in FIG. 6 to FIG. 11 , It will not be repeated here.
  • the communication device when the communication device is implemented as a terminal device,
  • the transceiver for interacting with the network device to determine the target packet quantization scheme
  • the processor configured to group the CSI feedback information based on the target grouping quantization scheme, and quantize the CSI feedback information in the grouping according to a quantization manner corresponding to the grouping;
  • the processor and transceiver in the communication device involved in the embodiments of the present application may perform the steps performed by the network device in any of the methods shown in the above-mentioned FIG. 6 to FIG. 11 , It will not be repeated here.
  • the communication device when the communication device is implemented as a network device,
  • the transceiver for interacting with the terminal device to determine the target packet quantization scheme
  • the target grouping quantization scheme is used for the terminal equipment to group the CSI feedback information, and quantize the CSI feedback information in the group according to the quantization method corresponding to the group; there are at least two groups corresponding to in different quantification methods.
  • a computer-readable storage medium stores at least one instruction, at least one piece of program, code set or instruction set, the at least one instruction, the At least one piece of the program, the code set or the instruction set is loaded and executed by the processor to implement the information quantization method executed by the communication device provided by each of the above method embodiments.
  • a chip is also provided, the chip includes a programmable logic circuit and/or program instructions, when the chip runs on a computer device, for implementing the information quantification method described in the above aspects .
  • a computer program product which, when run on a processor of the computer device, causes the computer device to perform the information quantification method described in the above aspects.

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种信息量化方法、装置、通信设备及存储介质，涉及通信技术领域。该方法应用于终端设备中，该方法包括：与网络设备之间进行交互以确定目标分组量化方案；基于所述目标分组量化方案，对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；其中，存在至少所述两个分组对应于不同的量化方式。

Description

信息量化方法、装置、通信设备及存储介质 技术领域
本申请涉及通信技术领域，特别涉及一种信息量化方法、装置、通信设备及存储介质。
背景技术
终端设备一般通过信道状态信息(Channel State Information，CSI)测量，生成CSI反馈信息。
在进行CSI反馈信息上报之前，终端设备一般要对CSI反馈信息进行量化。相关技术中，采用统一量化的量化策略，即：终端设备对于待反馈的CSI反馈信息采用相同的量化方式进行量化。
发明内容
本申请实施例提供了一种信息量化方法、装置、通信设备及存储介质，终端设备与网络设备之间商定目标分组量化方案，目标分组量化方案中存在至少两个分组对应于不同的量化方式，以使得终端设备基于目标分组量化方案对CSI反馈信息进行分组量化。所述技术方案如下：
根据本申请的一个方面，提供了一种信息量化方法，应用于终端设备中，所述方法包括：
与网络设备之间进行交互以确定目标分组量化方案；
基于所述目标分组量化方案对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行；
其中，存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种信息量化方法，应用于网络设备中，所述方法包括：
与终端设备之间进行交互以确定目标分组量化方案；
其中，所述目标分组量化方案用于供所述终端设备对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种信息量化装置，应用于终端设备中，所述装置包括：确定模块以及量化模块；
所述确定模块，用于与网络设备之间进行交互以确定目标分组量化方案；
所述量化模块，用于基于所述目标分组量化方案，对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
其中，存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种信息量化装置，应用于网络设备中，所述装置包括：确定模块；
所述确定模块，用于与终端设备之间进行交互以确定目标分组量化方案；
其中，所述目标分组量化方案用于供所述终端设备对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种终端设备，所述终端设备包括：处理器和与所述处理器相连的收发器；其中，
所述收发器，用于与网络设备之间进行交互以确定目标分组量化方案；
所述处理器，用于基于所述目标分组量化方案，对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
其中，存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种网络设备，所述网络设备包括：处理器和与所述处理器相连的收发器；其中，
所述收发器，用于与终端设备之间进行交互以确定目标分组量化方案；
其中，所述目标分组量化方案用于供所述终端设备对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
根据本申请的一个方面，提供了一种计算机可读存储介质，所述可读存储介质中存储有可执行指令，所述可执行指令由处理器加载并执行以实现如上述方面所述的信息量化方法。
根据本申请实施例的一个方面，提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片在计算机设备上运行时，用于实现上述方面所述的信息量化方法。
根据本申请的一个方面，提供了一种计算机程序产品，该计算机程序产品在计算机设备的处理器上运行时，使得计算机设备执行上述方面所述的信息量化方法。
本申请实施例提供的技术方案至少包括如下有益效果：
终端设备与网络设备之间商定目标分组量化方案，以使得终端设备基于目标分组量化方案对CSI反馈信息进行分组，按照分组对应的量化方式对CSI反馈信息进行量化，由于存在至少两个分组对应于不同的量化方式，相比于现有技术中使用的统一量化方案，这种分组量化的方法充分利用了CSI反馈信息的分布特征，对不同分布特征的CSI反馈信息通过不同分组分别进行量化，从而在保证量化精度的情况下，尽可能地降低量化所需的比特数，进而降低CSI反馈信息的反馈开销。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一个示例性实施例提供的信道状态信息的生成与指示过程的示意图；
图2是本申请一个示例性实施例提供的神经网络的示意图；
图3是本申请一个示例性实施例提供的卷积神经网络的示意图；
图4是本申请一个示例性实施例提供的利用神经网络模型做信道状态信息指示的网络架构的示意图；
图5是本申请一个示例性实施例提供的通信系统的框图；
图6是本申请一个示例性实施例提供的信息量化方法的流程图；
图7是本申请一个示例性实施例提供的信息量化方法的流程图；
图8是本申请一个示例性实施例提供的信息量化过程的示意图；
图9是本申请一个示例性实施例提供的信息量化方法的流程图；
图10是本申请一个示例性实施例提供的信息量化过程的示意图；
图11是本申请一个示例性实施例提供的信息量化过程的示意图；
图12是本申请一个示例性实施例提供的信息量化装置的结构框图；
图13是本申请一个示例性实施例提供的信息量化装置的结构框图；
图14是本申请一个示例性实施例提供的通信设备的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
首先，对本申请实施例中涉及的名词进行简单介绍：
信道状态信息(Channel State Information，CSI)：
CSI是用于描述通信链路的信道属性的信息。CSI的指示在通信系统中非常重要，其决定了多入多出(Multiple-Input Multiple-Output，MIMO)传输的性能。一般来说，通信系统中的CSI指示可以包括对信道质量指示(Channel Quality Indicator，CQI)、预编码矩阵指示(Precoding Matrix Indicator，PMI)、秩指示(Rank indicator，RI)等信息的指示。
结合参考图1，对CSI的生成与指示方式进行示例性的说明。如图1所示，网络设备可以为终端设备配置用于CSI指示的指示参数信息，例如：终端设备需要指示CQI、PMI、RI等信息中的哪些信息；同时，网络设备可以为终端设备配置一些供CSI测量用的参考信号，例如：同步信号块(Synchronization Signal Block，SSB)和/或信道状态信息参考信号(Channel State Information-Reference Signal，CSI-RS)。终端设备通过对上述参考信号的测量，确定当前信道状态信息情况，并根据网络设备配置的指示参数信息向网络设备指示当前的CSI反馈信息，从而供网络设备基于当前信道情况配置出合理高效的数据传输方式。
人工智能(Artificial Intelligence，AI)：
近年来，以神经网络为代表的人工智能研究在很多领域都取得了非常大的成果，其也将在未来很长的一段时间内，对人们的生产生活起到重要的影响。
请参考图2，其示出了本申请一个实施例提供的神经网络的示意图。如图2所示，一个简单的神经网络的基本结构包括：输入层、隐藏层和输出层。其中，输入层负责接收数据，隐藏层负责处理数据，而最后的结果在输出层产生。如图3所示，各个节点代表一个处理单元，也可以认为是模拟了一个神经元，多个神经元组成一层神经网络，多层的信息传递与处理构造出了一个整体的神经网络。
随着神经网络研究的不断发展，近年来，神经网络深度学习算法被提出，较多的隐藏层被引入，通过多隐藏层的神经网络逐层训练进行特征学习，极大地提升了神经网络的学习和处理能力，并在模式识别、信号处理、优化组合、异常探测等方面被广泛应用。
同时，随着深度学习的发展，卷积神经网络也被进一步地研究。请参考图3，其示出了本申请一个实施例提供的卷积神经网络的示意图。如图3所示，在一个卷积神经网络中，其基本结构包括：输入层、多个卷积层、多个池化层、全连接层及输出层。卷积层和池化层的引入，有效地控制了网络参数的剧增，限制了参数的个数并挖掘了局部结构的特点，提高了算法的鲁棒性。
信道状态信息指示与人工智能的结合
相关技术中，无线通信系统的基础原理大多还是基于对实际通信环境的理论建模与参数选取来完成的。随着对无线通信系统灵活性、适应性、速率以及容量等要求的进一步增强，传统的基于经典模型理论的无线通信系统工作方式所能带来的增益正在逐渐弱化。目前，已有一些新的研究针对上述问题逐步开展，利用人工智能的方式做CSI的获取与指示就是其中之一。
请参考图4，其示出了本申请一个实施例提供的利用神经网络模型做信道状态信息指示的网络架构的示意图。如图4所示，编码端先调用编码端神经网络对待反馈信道信息进行编码，以生成第一信道信息，第一信道信息也即CSI反馈信息；解码端在接收到第一信道信息之后，调用解码端神经网络对第一信道信息进行解码，得到反馈信道信息。
在上述基于人工智能的CSI反馈方式中，所反馈的第一信道信息的大小与反馈性能有直接的关联关系，反馈的第一信道信息的信息量越多，编码端对应的反馈信道信息对解码端对应的待反馈信道信息的恢复程度也就越高。在这种情况下，第一信道信息的反馈开销与待反馈信道信息的恢复增益之间是存在矛盾的。一方面，从通信系统的开销角度来看，传输第一信道信息所需的反馈开销需要越小越好，另一方面，从通信系统的传输性能增益来看，待反馈信道信息在解码端的恢复程度越高，对通信系统的性能增益越有利。
综上，有必要在基于人工智能的CSI反馈研究中，设计一种CSI反馈信息的量化方案，保证传输性能增益的条件下，尽可能地降低反馈开销。
相关技术中，针对CSI反馈信息的量化方案是采用统一量化方案，比如均匀量化，μ率量化等，上述量化方式对于CSI反馈信息没有明确规律时是有效的。
但是，通过实验分析可以发现，对于特定的信道特征来说，CSI反馈信息中的有些数据明显偏小，有些数据又明显偏大，且差距较大，这时候如果用统一的均匀量化或者其他统一量化作为量化策略的话是有缺陷的。例如：如果用统一的均匀量化，在同样比特数下，为了保证较大数据能够反馈而采用相对较大的量化粒度，而相对较大的量化粒度会导致较小数据的反馈误差增大。例如：为了保证较小数据的反馈精度而采用相对较小的量化粒度，则会导致反馈较大数据时需要相对更多的比特数。
针对上述问题，本申请实施例提出一种信息量化方法，主要用于基于人工智能的CSI反馈过程当中，以在保证量化精度的情况下，最大程度地降低反馈开销。下面，结合如下实施例对本申请的技术方案进行介绍说明。
图5示出了本申请一个示例性实施例提供的通信系统的框图，该通信系统可以包括：接入网12和终端设备14。
接入网12中包括若干个网络设备120。网络设备120可以是基站，所述基站是一种部署在接入网中用以为终端提供无线通信功能的装置。基站可以包括各种形式的宏基站，微基站，中继站，接入点等等。在采用不同的无线接入技术的系统中，具备基站功能的设备的名称可能会有所不同，例如在LTE系统中，称为eNodeB或者eNB；在5G NR-U系统中，称为gNodeB或者gNB。随着通信技术的演进，“基站”这一描述可能会变化。为方便本申请实施例中，上述为终端设备14提供无线通信功能的装置统称为网络设备。
终端设备14可以包括各种具有无线通信功能的手持设备、车载设备、可穿戴设备、计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备，移动台(Mobile  Station，MS)，终端(terminal device)等等。为方便描述，上面提到的设备统称为终端。网络设备120与终端设备14之间通过某种空口技术互相通信，例如Uu接口。
本申请实施例的技术方案可以应用于各种通信系统，例如：全球移动通讯(Global System of Mobile Communication，GSM)系统、码分多址(Code Division Multiple Access，CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)系统、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)系统、LTE频分双工(Frequency Division Duplex，FDD)系统、LTE时分双工(Time Division Duplex，TDD)系统、先进的长期演进(Advanced Long Term Evolution，LTE-A)系统、新无线(New Radio，NR)系统、NR系统的演进系统、非授权频段上的LTE(LTE-based access to Unlicensed spectrum，LTE-U)系统、NR-U系统、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、全球互联微波接入(Worldwide Interoperability for Microwave Access，WiMAX)通信系统、无线局域网(Wireless Local Area Networks，WLAN)、无线保真(Wireless Fidelity，WiFi)、第6代移动通信技术(6-Generation，6G)系统、下一代通信系统或其他通信系统等。
通常来说，传统的通信系统支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信系统将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信以及车联网(Vehicle to Everything，V2X)系统等。本申请实施例也可以应用于这些通信系统。
图6示出了本申请一个示例性实施例提供的信息量化方法的流程图。该方法可以应用于如图5示出的通信系统中，该方法包括：
步骤610，终端设备与网络设备之间进行交互以确定目标分组量化方案。
终端设备与网络设备之间进行交互，以使得终端设备和网络设备确定目标分组量化方案。
由于终端设备与网络设备两侧需要统一量化方案，使得终端设备在对CSI反馈信息使用量化方案进行量化后，网络设备能够基于相同的量化方案获取正确的CSI反馈信息。所以，在步骤610中，终端设备与网络设备两侧确定相同的目标分组量化方案。可选的，终端设备与网络设备之间通过执行至少一次交互，以使得终端设备与网络设备确定目标分组量化方案。
步骤620，终端设备基于目标分组量化方案对CSI反馈信息进行分组，按照分组对应的量化方式对分组中的CSI反馈信息进行量化。
在本申请实施例中，目标分组量化方案是采用分组的形式对CSI反馈信息进行量化的一种量化方案。其中，存在至少两个分组对应于不同的量化方式。
也即，在目标分组量化方案中，支持将CSI反馈信息划分为n个分组进行反馈，n为不小于2的正整数，n个分组分别一一对应n种量化方式。可选的，n种量化方式互不相同。可选的，n种量化方式存在至少两种量化方式不相同。
示例性的，目标分组量化方案中包括3个分组：第一分组、第二分组以及第三分组，第一分组对应于第一量化方式，第二分组对应于第二量化方式，第三分组对应于第三量化方式。第一量化方式至第三量化方式互不相同。
终端设备在确定好目标分组量化方案后，根据目标分组量化方案的指示，对CSI反馈信息进行分组，再将每一分组的CSI反馈信息按照该分组对应的量化方式进行量化。上述分组量化也可以理解为是一种分类量化，通过对不同分布特征的CSI反馈信息加以分类从而进入不同的分组，再根据目标分组量化方案进行不同量化方式下的量化。
示例性的，目标分组量化方案中包括3个分组：第一分组、第二分组以及第三分组，第一分组对应于第一量化方式，第二分组对应于第二量化方式，第三分组对应于第三量化方式。终端设备将一部分CSI反馈信息分类至第一分组，采用第一量化方式进行量化，将另一部分CSI反馈信息分类至第二分组，采用第二量化方式进行量化，将另一部分CSI反馈信息分类至第三分组，采用第三量化方式进行量化。
可以理解的是，不同分组所对应的CSI反馈信息具有各自的分布特征，例如处于不同的大小范围，或者处于不同的幅值范围，此时可以通过不同分组的不同量化方式，来避免不同分布特征的CSI反馈信息之间做统一量化。
可选的，CSI反馈信息是基于神经网络模型生成的。示例性的，结合参考图4，终端设备侧存在一个编码端神经网络，终端设备通过CSI测量，生成待反馈信道信息，将待反馈信道信息经过编码端神经网络生成第一信道信息(即CSI反馈信息)。
可选的，终端设备在对CSI反馈信息进行分组量化后，得到量化后的CSI反馈信息，将量化后的CSI反馈信息发送给网络设备，网络设备相应接收量化后的CSI反馈信息，并根据目标分组量化方案进行解量化，得到CSI反馈信息。
综上所述，本实施例提供的方法，终端设备与网络设备之间商定目标分组量化方案，以使得终端设备基于目标分组量化方案对CSI反馈信息进行分组，按照分组对应的量化方式对CSI反馈信息进行量化，由于存在至少两个分组对应于不同的量化方式，相比于现有技术中使用的统一量化方案，这种分组量化的方法充分利用了CSI反馈信息的分布特征，对不同分布特征的CSI反馈信息通过不同分组分别进行量化，从而在保证量化精度的情况下，尽可能地降低量化所需的比特数，进而降低CSI反馈信息的反馈开销。
在基于图6的可选实施例中，终端设备与网络设备之间通过交互确定目标分组量化方案，存在如下2种不同的方案。
一、网络设备向终端设备指示一个目标分组量化方案。
二、网络设备向终端设备指示多个候选目标分组量化方案，目标分组量化方案为多个候选目标分组量化方案中的一个方案。
1)由网络设备指示多个候选目标分组量化方案中的目标分组量化方案。
2)由终端设备指示多个候选目标分组量化方案中的目标分组量化方案。
下面，针对上述方案分别进行示例性的说明。
一、网络设备向终端设备指示一个目标分组量化方案。
图7示出了本申请一个示例性实施例提供的信息量化方法的流程图。该方法可以应用于如图5示出的通信系统中，该方法包括：
步骤710，网络设备发送第一指示信令，第一指示信令用于指示目标分组量化方案。
在确定目标分组量化方案后，网络设备通过第一指示信令将目标分组量化方案配置给终端设备。可选的，网络设备基于当前的信道特征，确定目标分组量化方案。
可选的，第一指示信令包括如下中的至少一种：广播消息、系统信息块(System Information Block，SIB)、无线资源控制(Radio Resource Control，RRC)消息、RRC重配置信令、下行控制信息(Downlink Control Information，DCI)、媒体接入控制(Medium Access Control，MAC)控制信元(Control Element，CE)、物理下行控制信道(Physical Downlink Control Channel，PDCCH)命令(order)、数据信息。本申请实施例对第一指示信令的具体类 型不进行限定。
可以理解的是，SIB是广播消息一种可能的实现形式，RRC重配置信令是RRC消息一种可能的实现形式。也即，第一指示信令包括如下中的至少一种：广播消息、RRC消息、DCI、MAC CE、PDCCH order、数据信息；广播消息包括SIB，RRC消息包括RRC重配置信令。
步骤720，终端设备接收网络设备发送的第一指示信令。
步骤730，终端设备基于第一指示信令获取目标分组量化分案。
终端设备在接收第一指示信令后，通过第一指示信令得到网络设备配置的目标分组量化方案。
步骤740，终端设备基于目标分组量化方案对CSI反馈信息进行分组，按照分组对应的量化方式对分组中的CSI反馈信息进行量化。
可选的，目标分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。其中，反馈方式信息用于描述该分组对应的量化方法，反馈参数信息用于描述该量化方法对应的参数。反馈方式信息和反馈参数信息共同指示了分组对应的量化方式。
可选的，反馈方式信息包括如下信息中的至少一种：均匀量化、非均匀量化。其中，均匀量化指的是以相同的量化粒度来对CSI反馈信息进行量化的一种量化方法；非均匀量化指的是在不同的区间以不同的量化粒度来对CSI反馈信息进行量化的一种量化方法。
可选的，反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。本申请实施例对反馈方式信息以及反馈参数信息的具体内容不进行限定。其中，量化比特指的是对CSI反馈信息中的一个数据进行量化所用的比特数；量化粒度指的是相邻量化值之间的间隔；量化范围指的是支持进行量化的数据的区间范围。
示例性的，反馈方式信息为均匀量化；相应的反馈参数信息包括：量化比特为2比特，量化粒度为1，量化范围为0-3。则对于数据0，量化后的该数据为00；对于数据1，量化后的该数据为01；对于数据2，量化后的该数据为10；对于数据3，量化后的该数据为11。
示例性的，反馈方式信息为非均匀量化；相应的反馈参数信息包括：量化比特为2比特，量化范围0-1对应的量化粒度为0.5，量化范围1-2对应的量化粒度为1。则对于数据0，量化后的该数据为00；对于数据0.5，量化后的该数据为01；对于数据1，量化后的该数据为10；对于数据2，量化后的该数据为11。
示例性的，网络设备在第一指示信令中配置终端设备采用反馈方式1作为目标分组量化方案，反馈方式1包括：反馈比特数为256比特，其中，256比特分为4组，第一分组64比特采用第一量化方式得到，第二分组64比特采用第二量化方式得到，第三分组64比特采用第三量化方式得到，第四分组64比特采用第四量化方式得到。
在第一分组对应的第一量化方式中，采用均匀量化，量化粒度是第一量化粒度，量化比特为第一量化比特，量化范围为第一量化范围。例如：第一量化粒度是1/(2^4)，第一量化比特为4，第一量化范围为0至1，则第一量化方式会将0至1之间的数字通过4比特量化，并且量化粒度保持在1/(2^4)。通过上述方式可以反馈16个实数。
在第二分组对应的第二量化方式中，采用均匀量化，量化粒度是第二量化粒度，量化比特为第二量化比特，量化范围为第二量化范围。例如：第二量化粒度是1/(2^4)，第二量化比特为2，第二量化范围为0至0.25，则第二量化方式会将0至0.25之间的数字通过2比特量化，并且量化粒度保持在1/(2^4)。通过上述方式可以反馈32个实数。
在第三分组对应的第三量化方式中，采用均匀量化，量化粒度是第三量化粒度，量化比 特为第三量化比特，量化范围为第三量化范围。例如：第三量化粒度是1/(2^3)，第三量化比特为4，第三量化范围为0至2，则第三量化方式会将0至2之间的数字通过4比特量化，并且量化粒度保持在1/(2^3)。通过上述方式可以反馈16个实数。
在第四分组对应的第四量化方式中，采用均匀量化，量化粒度是第四量化粒度，量化比特为第四量化比特，量化范围为第四量化范围。例如：第四量化粒度是1/(2^2)，第四量化比特为4，第四量化范围为0至4，则第三量化方式会将0至4之间的数字通过4比特量化，并且量化粒度保持在1/(2^2)。通过上述方式可以反馈16个实数。
综上所述，本实施例提供的方法，网络设备通过发送第一指示信令，指示目标分组量化方案给终端设备，以较简单的交互流程实现了网络设备与终端设备之间关于量化方案的统一，避免两侧量化以及解量化过程中出错。
示例性的，结合参考图8，对上述实施例进行示例性的说明。该方法包括如下步骤：
S11，网络设备为终端设备配置目标分组量化方案。
可选的，网络设备通过广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息中的至少一种为终端设备进行配置。
S12，终端设备根据目标分组量化方案做对应分组量化。
终端设备接收网络设备配置的目标分组量化方案，并根据目标分组量化方案对CSI反馈信息进行分组量化。
S13，终端设备向网络设备传输量化后的CSI反馈信息。
S14，网络设备根据目标分组量化方案做对应解量化。
网络设备在接收到量化后的CSI反馈信息后，根据目标分组量化方案对量化后的CSI反馈信息进行解量化。
二、网络设备向终端设备指示多个候选目标分组量化方案，目标分组量化方案为多个候选目标分组量化方案中的一个方案。
图9示出了本申请一个示例性实施例提供的信息量化方法的流程图。该方法可以应用于如图5示出的通信系统中，该方法包括：
步骤910，网络设备向终端设备发送第二指示信令，第二指示信令用于指示n个候选分组量化方案。
其中，n为大于1的正整数。也即，存在多个候选分组量化方案。
网络设备确定n个候选分组量化方案，并通过第二指示信令，将n个候选分组量化方案配置给终端设备。可选的，n个候选分组量化方案互不相同。可选的，n个候选分组量化方案存在至少两个候选分组量化方案不相同。
可选的，第二指示信令包括如下中的至少一种：广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息。本申请实施例对第二指示信令的具体类型不进行限定。
可以理解的是，SIB是广播消息一种可能的实现形式，RRC重配置信令是RRC消息一种可能的实现形式。也即，第二指示信令包括如下中的至少一种：广播消息、RRC消息、DCI、MAC CE、PDCCH order、数据信息；广播消息包括SIB，RRC消息包括RRC重配置信令。
步骤920，终端设备接收网络设备发送的第二指示信令。
步骤930，终端设备基于第二指示信令获取n个候选分组量化方案。
示例性的，网络设备在第二指示信令中配置给终端设备反馈方式1至反馈方式3作为候选分组量化方案。也即，n为3。
反馈方式1包括：反馈比特数为256比特，其中256比特分为4组，第一分组64比特采用第一量化方式得到，第二分组64比特采用第二量化方式得到，第三分组64比特采用第三量化方式得到，第四分组64比特采用第四量化方式得到。
反馈方式2包括：反馈比特数为128比特，其中128比特分为2组，第一分组64比特采用第五量化方式得到，第二分组64比特采用第六量化方式得到。
反馈方式3包括：反馈比特数为128比特，其中128比特分为1组，这一分组128比特采用第七量化方式得到。
可以理解的是，如反馈方式3所示，在网络设备配置多个候选分组量化方案的情况下，可以存在候选分组量化方案只包括1个分组。
步骤940，终端设备从n个候选分组量化方案中确定出目标分组量化方案。
在一种可能的实现方式中，由网络设备指示多个候选目标分组量化方案中的目标分组量化方案。
也即，步骤940替换实现为：网络设备发送第三指示信令，第三指示信令用于在n个候选分组量化方案中指示目标分组量化方案；终端设备接收网络设备发送的第三指示信令；终端设备基于第三指示信令，从n个候选分组量化方案中确定出目标分组量化方案。
可选的，第三指示信令包括如下中的至少一种：广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息。本申请实施例对第三指示信令的具体类型不进行限定。
可以理解的是，SIB是广播消息一种可能的实现形式，RRC重配置信令是RRC消息一种可能的实现形式。也即，第三指示信令包括如下中的至少一种：广播消息、RRC消息、DCI、MAC CE、PDCCH order、数据信息；广播消息包括SIB，RRC消息包括RRC重配置信令。
示例性的，网络设备通过DCI指示当前采用的目标分组量化方案为预先配置的n个候选分组量化方案中的第x个候选分组量化方案，x为不大于n的正整数。
可选的，网络设备基于当前的信道特征，确定目标分组量化方案。
在另一种可能的实现方式中，由终端设备指示多个候选目标分组量化方案中的目标分组量化方案。
也即，在步骤940之后，终端设备向网络设备发送第四指示信令，第四指示信令用于在n个候选分组量化方案中指示目标分组量化方案；网络设备接收终端设备发送的第四指示信令；网络设备基于第四指令，从n个候选分组量化方案中确定出目标分组量化方案。
可选的，第四指示信令包括如下中的至少一种：上行控制信息(Uplink Control Information，UCI)、物理上行控制信道(Physical Uplink Control Channel，PUCCH)、RRC消息、数据信息。可以理解的是，这里的RRC消息是终端设备向网络设备发送的一种消息，该RRC消息可以在后续演进的移动通信系统中得到支持。
示例性的，终端设备通过UCI指示当前采用的目标分组量化方案为预先配置的n个候选分组量化方案中的第x个候选分组量化方案，x为不大于n的正整数。
可选的，终端设备基于当前的信道特征，确定目标分组量化方案。
步骤950，终端设备基于目标分组量化方案对CSI反馈信息进行分组，按照分组对应的量化方式对分组中的CSI反馈信息进行量化。
可选的，目标分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、 针对每个分组的反馈参数信息。其中，反馈方式信息用于描述该分组对应的量化方法，反馈参数信息用于描述该量化方法对应的参数。反馈方式信息和反馈参数信息共同指示了分组对应的量化方式。
可选的，反馈方式信息包括如下信息中的至少一种：均匀量化、非均匀量化。其中，均匀量化指的是以相同的量化粒度来对CSI反馈信息进行量化的一种量化方法；非均匀量化指的是在不同的区间以不同的量化粒度来对CSI反馈信息进行量化的一种量化方法。
可选的，反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。其中，量化比特指的是对CSI反馈信息中的一个数据进行量化所用的比特数；量化粒度指的是相邻量化值之间的间隔；量化范围指的是支持进行量化的数据的区间范围。
综上所述，本实施例提供的方法，在网络设备为终端设备预先配置多个候选分组量化方案的情况下，只需要根据网络设备或终端设备的指示，在多个候选目标分组量化方案中选择出目标分组量化方案，由于该指示不需要携带目标分组量化方案的具体信息，从而以较少的开销实现了网络设备与终端设备之间关于量化方案的统一，避免两侧量化以及解量化过程中出错。
示例性的，结合参考图10，对上述实施例进行示例性的说明。该方法包括如下步骤：
S21，网络设备为终端设备配置多个候选分组量化方案。
可选的，网络设备通过广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息中的至少一种为终端设备进行预配置。
可选的，针对任一候选分组量化方案，候选分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。可选的，反馈方式信息包括如下信息中的至少一种：均匀量化、非均匀量化。可选的，反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。
S22，网络设备向终端设备指示一个目标分组量化方案。
可选的，网络设备通过广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息中的至少一种，指示终端设备采用多个候选分组量化方案中的一个候选分组量化方案作为目标分组量化方案。
S23，终端设备根据目标分组量化方案做对应分组量化。
终端设备接收网络设备的指示从而确定目标分组量化方案，并根据目标分组量化方案对CSI反馈信息进行分组量化。
S24，终端设备向网络设备传输量化后的CSI反馈信息。
S25，网络设备根据目标分组量化方案做对应解量化。
网络设备在接收到量化后的CSI反馈信息后，根据目标分组量化方案对量化后的CSI反馈信息进行解量化。
示例性的，结合参考图11，对上述实施例进行示例性的说明。该方法包括如下步骤：
S31，网络设备为终端设备配置多个候选分组量化方案。
可选的，网络设备通过广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息中的至少一种为终端设备进行预配置。
可选的，针对任一候选分组量化方案，候选分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。可选的，反馈方式信息包括 如下信息中的至少一种：均匀量化、非均匀量化。可选的，反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。
S32，终端设备向网络设备指示一个目标分组量化方案。
可选的，终端设备通过UCI、PUCCH、RRC消息、数据信息中的至少一种，指示网络设备采用多个候选分组量化方案中的一个候选分组量化方案作为目标分组量化方案。
S33，终端设备根据目标分组量化方案做对应分组量化。
终端设备根据自身选择的目标分组量化方案对CSI反馈信息进行分组量化。
S34，终端设备向网络设备传输量化后的CSI反馈信息。
S35，网络设备根据目标分组量化方案做对应解量化。
网络设备在接收到量化后的CSI反馈信息后，根据终端设备指示的目标分组量化方案对量化后的CSI反馈信息进行解量化。
需要说明的是，上述方法实施例可以分别单独实施，也可以组合实施，本申请对此不进行限制。
在上述各个实施例中，由终端设备执行的步骤可以单独实现成为终端设备一侧的信息量化方法，由网络设备执行的步骤可以单独实现成为网络设备一侧的信息量化方法。
图12示出了本申请一个示例性实施例提供的信息量化装置的结构框图，该装置可以实现成为终端设备，或者，实现成为终端设备中的一部分，该装置包括：确定模块1201以及量化模块1202；
所述确定模块1201，用于与网络设备之间进行交互以确定目标分组量化方案；
所述量化模块1202，用于基于所述目标分组量化方案，对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
其中，存在至少两个所述分组对应于不同的量化方式。
在一个可选的实施例中，所述确定模块1201，用于，接收所述网络设备发送的第一指示信令；基于所述第一指示信令获取所述目标分组量化分案。
在一个可选的实施例中，所述确定模块1201，用于，接收所述网络设备发送的第二指示信令；基于所述第二指示信令获取n个候选分组量化方案，所述n为大于1的正整数；从所述n个候选分组量化方案中确定出所述目标分组量化方案。
在一个可选的实施例中，所述确定模块1201，用于，接收所述网络设备发送的第三指示信令；基于所述第三指示信令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
在一个可选的实施例中，所述网络设备发送的指示信令包括如下中的至少一种：广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息。
在一个可选的实施例中，所述确定模块1201，用于向所述网络设备发送第四指示信令，所述第四指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
在一个可选的实施例中，所述第四指示信令包括如下中的至少一种：UCI、PUCCH、RRC消息、数据信息。
在一个可选的实施例中，所述目标分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
在一个可选的实施例中，所述反馈方式信息包括如下信息中的至少一种：均匀量化、非 均匀量化。
在一个可选的实施例中，所述反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。
在一个可选的实施例中，所述CSI反馈信息是基于神经网络模型生成的。
图13示出了本申请一个示例性实施例提供的信息量化装置的结构框图，该装置可以实现成为网络设备，或者，实现成为网络设备中的一部分，该装置包括：确定模块1301；
所述确定模块1301，用于与终端设备之间进行交互以确定目标分组量化方案；
其中，所述目标分组量化方案用于供所述终端设备对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
在一个可选的实施例中，所述确定模块1301，用于向所述终端设备发送第一指示信令，所述第一指示信令用于指示所述目标分组量化分案。
在一个可选的实施例中，所述确定模块1301，用于，向所述终端设备发送第二指示信令，所述第二指示信令用于指示n个候选分组量化方案，所述n为大于1的正整数；从所述n个候选分组量化方案中确定出所述目标分组量化方案。
在一个可选的实施例中，所述确定模块1301，用于向所述终端设备发送第三指示信令，所述第三指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
在一个可选的实施例中，所述网络设备发送的指示信令包括如下中的至少一种：广播消息、SIB、RRC消息、RRC重配置信令、DCI、MAC CE、PDCCH order、数据信息。
在一个可选的实施例中，所述确定模块1301，用于，接收所述终端设备发送的第四指示信令；基于所述第四指令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
在一个可选的实施例中，所述第四指示信令包括如下中的至少一种：UCI、PUCCH、RRC消息、数据信息。
在一个可选的实施例中，所述目标分组量化方案包括如下信息中的至少一种：针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
在一个可选的实施例中，所述反馈方式信息包括如下信息中的至少一种：均匀量化、非均匀量化。
在一个可选的实施例中，所述反馈参数信息包括如下信息中的至少一种：量化比特、量化粒度、量化范围。
在一个可选的实施例中，所述CSI反馈信息是基于神经网络模型生成的。
图14示出了本申请一个示例性实施例提供的通信设备(终端设备或网络设备)的结构示意图，该通信设备包括：处理器101、接收器102、发射器103、存储器104和总线105。
处理器101包括一个或者一个以上处理核心，处理器101通过运行软件程序以及模块，从而执行各种功能应用以及信息处理。
接收器102和发射器103可以实现为一个通信组件，该通信组件可以是一块通信芯片，记为收发器。
存储器104通过总线105与处理器101相连。
存储器104可用于存储至少一个指令，处理器101用于执行该至少一个指令，以实现上述方法实施例中的各个步骤。
此外，存储器104可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，易失性或非易失性存储设备包括但不限于：磁盘或光盘，电可擦除可编程只读存储器(Electrically-Erasable Programmable Read Only Memory,EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read Only Memory,EPROM)，静态随时存取存储器(Static Random Access Memory，SRAM)，只读存储器(Read-Only Memory,ROM)，磁存储器，快闪存储器，可编程只读存储器(Programmable Read-Only Memory，PROM)。
其中，当通信设备实现为终端设备时，本申请实施例涉及的通信设备中的处理器和收发器，可以执行上述图6至图11任一所示的方法中，由终端设备执行的步骤，此处不再赘述。
在一种可能的实现方式中，当通信设备实现为终端设备时，
所述收发器，用于与网络设备之间进行交互以确定目标分组量化方案；
所述处理器，用于基于所述目标分组量化方案对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
其中，存在至少两个所述分组对应于不同的量化方式。
其中，当通信设备实现为网络设备时，本申请实施例涉及的通信设备中的处理器和收发器，可以执行上述图6至图11任一所示的方法中，由网络设备执行的步骤，此处不再赘述。
在一种可能的实现方式中，当通信设备实现为网络设备时，
所述收发器，用于与终端设备之间进行交互以确定目标分组量化方案；
其中，所述目标分组量化方案用于供所述终端设备对CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
在示例性实施例中，还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由处理器加载并执行以实现上述各个方法实施例提供的由通信设备执行的信息量化方法。
在示例性实施例中，还提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片在计算机设备上运行时，用于实现上述方面所述的信息量化方法。
在示例性实施例中，还提供了一种计算机程序产品，该计算机程序产品在计算机设备的处理器上运行时，使得计算机设备执行上述方面所述的信息量化方法。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (47)

  1. 一种信息量化方法，其特征在于，应用于终端设备中，所述方法包括：
    与网络设备之间进行交互以确定目标分组量化方案；
    基于所述目标分组量化方案对信道状态信息CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
    其中，存在至少两个所述分组对应于不同的量化方式。
  2. 根据权利要求1所述的方法，其特征在于，所述与网络设备之间进行交互以确定目标分组量化方案，包括：
    接收所述网络设备发送的第一指示信令；
    基于所述第一指示信令获取所述目标分组量化分案。
  3. 根据权利要求1所述的方法，其特征在于，所述与网络设备之间进行交互以确定目标分组量化方案，包括：
    接收所述网络设备发送的第二指示信令；
    基于所述第二指示信令获取n个候选分组量化方案，所述n为大于1的正整数；
    从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  4. 根据权利要求3所述的方法，其特征在于，所述从所述n个候选分组量化方案中确定出所述目标分组量化方案，包括：
    接收所述网络设备发送的第三指示信令；
    基于所述第三指示信令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  5. 根据权利要求2至4任一所述的方法，其特征在于，所述网络设备发送的指示信令包括如下中的至少一种：
    广播消息、系统信息块SIB、无线资源控制RRC消息、RRC重配置信令、下行控制信息DCI、媒体接入控制控制信元MAC CE、物理下行控制信道命令PDCCH order、数据信息。
  6. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    向所述网络设备发送第四指示信令，所述第四指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
  7. 根据权利要求6所述的方法，其特征在于，所述第四指示信令包括如下中的至少一种：
    上行控制信息UCI、物理上行控制信道PUCCH、RRC消息、数据信息。
  8. 根据权利要求1至7任一所述的方法，其特征在于，所述目标分组量化方案包括如下信息中的至少一种：
    针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
  9. 根据权利要求8所述的方法，其特征在于，所述反馈方式信息包括如下信息中的至少一种：
    均匀量化、非均匀量化。
  10. 根据权利要求8所述的方法，其特征在于，所述反馈参数信息包括如下信息中的至少一种：
    量化比特、量化粒度、量化范围。
  11. 根据权利要求1至11任一所述的方法，其特征在于，
    所述CSI反馈信息是基于神经网络模型生成的。
  12. 一种信息量化方法，其特征在于，应用于网络设备中，所述方法包括：
    与终端设备之间进行交互以确定目标分组量化方案；
    其中，所述目标分组量化方案用于供所述终端设备对信道状态信息CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
  13. 根据权利要求12所述的方法，其特征在于，所述与终端设备之间进行交互以确定目标分组量化方案，包括：
    向所述终端设备发送第一指示信令，所述第一指示信令用于指示所述目标分组量化分案。
  14. 根据权利要求12所述的方法，其特征在于，所述与终端设备之间进行交互以确定目标分组量化方案，包括：
    向所述终端设备发送第二指示信令，所述第二指示信令用于指示n个候选分组量化方案，所述n为大于1的正整数；
    从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  15. 根据权利要求14所述的方法，其特征在于，所述方法还包括：
    向所述终端设备发送第三指示信令，所述第三指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
  16. 根据权利要求13至15任一所述的方法，其特征在于，所述向所述终端设备发送的指示信令包括如下中的至少一种：
    广播消息、系统信息块SIB、无线资源控制RRC消息、RRC重配置信令、下行控制信息DCI、媒体接入控制控制信元MAC CE、物理下行控制信道命令PDCCH order、数据信息。
  17. 根据权利要求14所述的方法，其特征在于，所述从所述n个候选分组量化方案中确定出所述目标分组量化方案，包括：
    接收所述终端设备发送的第四指示信令；
    基于所述第四指令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  18. 根据权利要求17所述的方法，其特征在于，所述第四指示信令包括如下中的至少一种：
    上行控制信息UCI、物理上行控制信道PUCCH、RRC消息、数据信息。
  19. 根据权利要求12至18任一所述的方法，其特征在于，所述目标分组量化方案包括如下信息中的至少一种：
    针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
  20. 根据权利要求19所述的方法，其特征在于，所述反馈方式信息包括如下信息中的至少一种：
    均匀量化、非均匀量化。
  21. 根据权利要求19所述的方法，其特征在于，所述反馈参数信息包括如下信息中的至少一种：
    量化比特、量化粒度、量化范围。
  22. 根据权利要求12至21任一所述的方法，其特征在于，
    所述CSI反馈信息是基于神经网络模型生成的。
  23. 一种信息量化装置，其特征在于，应用于终端设备中，所述装置包括：确定模块以及量化模块；
    所述确定模块，用于与网络设备之间进行交互以确定目标分组量化方案；
    所述量化模块，用于基于所述目标分组量化方案对信道状态信息CSI反馈信息进行分组， 按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
    其中，存在至少两个所述分组对应于不同的量化方式。
  24. 根据权利要求23所述的装置，其特征在于，所述确定模块，用于，
    接收所述网络设备发送的第一指示信令；
    基于所述第一指示信令获取所述目标分组量化分案。
  25. 根据权利要求23所述的装置，其特征在于，所述确定模块，用于，
    接收所述网络设备发送的第二指示信令；
    基于所述第二指示信令获取n个候选分组量化方案，所述n为大于1的正整数；
    从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  26. 根据权利要求25所述的装置，其特征在于，所述确定模块，用于，
    接收所述网络设备发送的第三指示信令；
    基于所述第三指示信令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  27. 根据权利要求26所述的装置，其特征在于，所述网络设备发送的指示信令包括如下中的至少一种：
    广播消息、系统信息块SIB、无线资源控制RRC消息、RRC重配置信令、下行控制信息DCI、媒体接入控制控制信元MAC CE、物理下行控制信道命令PDCCH order、数据信息。
  28. 根据权利要求25所述的装置，其特征在于，
    所述确定模块，用于向所述网络设备发送第四指示信令，所述第四指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
  29. 根据权利要求28所述的装置，其特征在于，所述第四指示信令包括如下中的至少一种：
    上行控制信息UCI、物理上行控制信道PUCCH、RRC消息、数据信息。
  30. 根据权利要求23至29任一所述的装置，其特征在于，所述目标分组量化方案包括如下信息中的至少一种：
    针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
  31. 根据权利要求30所述的装置，其特征在于，所述反馈方式信息包括如下信息中的至少一种：
    均匀量化、非均匀量化。
  32. 根据权利要求30所述的装置，其特征在于，所述反馈参数信息包括如下信息中的至少一种：
    量化比特、量化粒度、量化范围。
  33. 根据权利要求23至32任一所述的装置，其特征在于，
    所述CSI反馈信息是基于神经网络模型生成的。
  34. 一种信息量化装置，其特征在于，应用于网络设备中，所述装置包括：确定模块；
    所述确定模块，用于与终端设备之间进行交互以确定目标分组量化方案；
    其中，所述目标分组量化方案用于供所述终端设备对信道状态信息CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
  35. 根据权利要求34所述的装置，其特征在于，
    所述确定模块，用于向所述终端设备发送第一指示信令，所述第一指示信令用于指示所述目标分组量化分案。
  36. 根据权利要求34所述的装置，其特征在于，所述确定模块，用于，
    向所述终端设备发送第二指示信令，所述第二指示信令用于指示n个候选分组量化方案，所述n为大于1的正整数；
    从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  37. 根据权利要求36所述的装置，其特征在于，
    所述确定模块，用于向所述终端设备发送第三指示信令，所述第三指示信令用于在所述n个候选分组量化方案中指示所述目标分组量化方案。
  38. 根据权利要求35至37任一所述的装置，其特征在于，所述向所述终端设备发送的指示信令包括如下中的至少一种：
    广播消息、系统信息块SIB、无线资源控制RRC消息、RRC重配置信令、下行控制信息DCI、媒体接入控制控制信元MAC CE、物理下行控制信道命令PDCCH order、数据信息。
  39. 根据权利要求36所述的装置，其特征在于，所述确定模块，用于，
    接收所述终端设备发送的第四指示信令；
    基于所述第四指令，从所述n个候选分组量化方案中确定出所述目标分组量化方案。
  40. 根据权利要求39所述的装置，其特征在于，所述第四指示信令包括如下中的至少一种：
    上行控制信息UCI、物理上行控制信道PUCCH、RRC消息、数据信息。
  41. 根据权利要求34至40任一所述的装置，其特征在于，所述目标分组量化方案包括如下信息中的至少一种：
    针对每个分组的反馈方式信息、针对每个分组的反馈参数信息。
  42. 根据权利要求41所述的装置，其特征在于，所述反馈方式信息包括如下信息中的至少一种：
    均匀量化、非均匀量化。
  43. 根据权利要求41所述的装置，其特征在于，所述反馈参数信息包括如下信息中的至少一种：
    量化比特、量化粒度、量化范围。
  44. 根据权利要求34至43任一所述的装置，其特征在于，
    所述CSI反馈信息是基于神经网络模型生成的。
  45. 一种终端设备，其特征在于，所述终端设备包括：处理器和与所述处理器相连的收发器；其中，
    所述收发器，用于与网络设备之间进行交互以确定目标分组量化方案；
    所述处理器，用于基于所述目标分组量化方案对信道状态信息CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；
    其中，存在至少两个所述分组对应于不同的量化方式。
  46. 一种网络设备，其特征在于，所述网络设备包括：处理器和与所述处理器相连的收发器；其中，
    所述收发器，用于与终端设备之间进行交互以确定目标分组量化方案；
    其中，所述目标分组量化方案用于供所述终端设备对信道状态信息CSI反馈信息进行分组，按照所述分组对应的量化方式对所述分组中的CSI反馈信息进行量化；存在至少两个所述分组对应于不同的量化方式。
  47. 一种计算机可读存储介质，其特征在于，所述可读存储介质中存储有可执行指令， 所述可执行指令由处理器加载并执行以实现如权利要求1至22任一所述的信息量化方法。
PCT/CN2021/071575 2021-01-13 2021-01-13 信息量化方法、装置、通信设备及存储介质 WO2022151084A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/CN2021/071575 WO2022151084A1 (zh) 2021-01-13 2021-01-13 信息量化方法、装置、通信设备及存储介质
CN202180089646.XA CN116711237A (zh) 2021-01-13 2021-01-13 信息量化方法、装置、通信设备及存储介质
EP21918299.5A EP4274299A4 (en) 2021-01-13 2021-01-13 INFORMATION QUANTIZATION METHOD AND DEVICE AS WELL AS COMMUNICATION DEVICE AND STORAGE MEDIUM
US18/349,669 US20230354081A1 (en) 2021-01-13 2023-07-10 Information quantization method, terminal device, and network device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/071575 WO2022151084A1 (zh) 2021-01-13 2021-01-13 信息量化方法、装置、通信设备及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/349,669 Continuation US20230354081A1 (en) 2021-01-13 2023-07-10 Information quantization method, terminal device, and network device

Publications (1)

Publication Number Publication Date
WO2022151084A1 true WO2022151084A1 (zh) 2022-07-21

Family

ID=82446714

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/071575 WO2022151084A1 (zh) 2021-01-13 2021-01-13 信息量化方法、装置、通信设备及存储介质

Country Status (4)

Country Link
US (1) US20230354081A1 (zh)
EP (1) EP4274299A4 (zh)
CN (1) CN116711237A (zh)
WO (1) WO2022151084A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024065800A1 (zh) * 2022-09-30 2024-04-04 富士通株式会社 信道状态信息的反馈方法和装置
WO2024104126A1 (zh) * 2022-11-14 2024-05-23 维沃移动通信有限公司 更新ai网络模型的方法、装置和通信设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100093361A1 (en) * 2008-10-13 2010-04-15 Sohn Iii Soo Apparatus and method for transmission of dynamic feedback channel information in a mimo system
US20110237282A1 (en) * 2009-10-01 2011-09-29 Qualcomm Incorporated Scalable channel feedback for wireless communication
CN111435862A (zh) * 2019-02-22 2020-07-21 维沃移动通信有限公司 信道状态信息csi报告的传输方法、终端及网络设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020147104A1 (en) * 2019-01-18 2020-07-23 Qualcomm Incorporated Layer-specific coefficient quantity and/or quantization scheme reporting for type ii channel state information compression
WO2020150936A1 (en) * 2019-01-23 2020-07-30 Qualcomm Incorporated Precoder matrix quantization for compressed csi feedback

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100093361A1 (en) * 2008-10-13 2010-04-15 Sohn Iii Soo Apparatus and method for transmission of dynamic feedback channel information in a mimo system
US20110237282A1 (en) * 2009-10-01 2011-09-29 Qualcomm Incorporated Scalable channel feedback for wireless communication
CN111435862A (zh) * 2019-02-22 2020-07-21 维沃移动通信有限公司 信道状态信息csi报告的传输方法、终端及网络设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HUAWEI, HISILICON: "Non-linear Precoding for Downlink Multiuser MIMO", 3GPP DRAFT; R1-1700053, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG1, no. Spokane, USA; 20170116 - 20170120, 16 January 2017 (2017-01-16), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051207595 *
See also references of EP4274299A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024065800A1 (zh) * 2022-09-30 2024-04-04 富士通株式会社 信道状态信息的反馈方法和装置
WO2024104126A1 (zh) * 2022-11-14 2024-05-23 维沃移动通信有限公司 更新ai网络模型的方法、装置和通信设备

Also Published As

Publication number Publication date
CN116711237A (zh) 2023-09-05
US20230354081A1 (en) 2023-11-02
EP4274299A1 (en) 2023-11-08
EP4274299A4 (en) 2024-03-06

Similar Documents

Publication Publication Date Title
US9344159B2 (en) Dynamic multi-cell clustering for downlink comp in a wireless communication network
US10097247B2 (en) Including feedback information regarding an individual subband of a wireless channel
US20230354081A1 (en) Information quantization method, terminal device, and network device
US20230353283A1 (en) Method for information transmission, second node, and first node
WO2021035492A1 (zh) 一种信道状态信息处理方法、电子设备及存储介质
CN115053469A (zh) 关于多个发送/接收点的信道状态信息的增强
WO2017076220A1 (zh) 一种信道状态信息csi反馈方法、终端及基站
US20240048207A1 (en) Method and apparatus for transmitting and receiving feedback information based on artificial neural network
US20230353214A1 (en) Method for feedback mode determination and device
CN106936486B (zh) 一种csi反馈方法及装置
CN116260552A (zh) 一种csi发送和接收方法及装置
WO2022151063A1 (zh) 信息发送方法、信息接收方法、装置、设备及介质
US20230353216A1 (en) Channel data transmission method and apparatus, communication device, and storage medium
WO2023201492A1 (zh) 基于ai的csi上报方法、接收方法、装置及存储介质
US20230370885A1 (en) Apparatus and method for transmission and reception of channel state information based on artificial intelligence
WO2024149042A1 (zh) 通信方法和通信装置
WO2024017057A1 (zh) 传输方法、通信节点及存储介质
WO2024031502A1 (en) Determining quantization information
KR20240019022A (ko) 통신 시스템에서 인공 신경망 기반 피드백 정보 송수신 방법 및 장치
CN117042179A (zh) Csi上报的方法、终端、网络设备、装置及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21918299

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202180089646.X

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 2021918299

Country of ref document: EP

Effective date: 20230804

NENP Non-entry into the national phase

Ref country code: DE