Channel state information feedback method, communication apparatus, storage medium, and program product

Abstract

Provided in the present application are a channel state information (CSI) feedback method, a communication apparatus, a storage medium, and a program product. The method comprises: before performing compression processing on CSI, performing standardization processing on the CSI. That is, the CSI is converted into CSI in a target format. In this way, for CSI of different types of channels, characteristics or formats of the CSI may be different, but after standardization processing is performed on the SCI, CSI in a unified format can be obtained. Alternatively, a module for standardization processing can be added before a CSI compression and recovery network, so as to facilitate compression processing on the CSI of different types of channels, thereby facilitating an improvement in the compression efficiency of the CSI and in the generalization performance of the CSI compression and recovery network.

Description

Channel state information feedback method, communication apparatus, storage medium and program product TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a channel state information feedback method, a communication apparatus, a storage medium and a program product. BACKGROUND

[0002] In a wireless communication system, in order to guarantee that the transmitted signal matches the channel state, the network device needs to obtain channel state information (CSI) when performing scheduling and precoding. In different duplex mode networks, the CSI acquisition method is different. For example, in a time division duplex (TDD) system, the network device can obtain the CSI from the network device to the terminal by measuring the uplink sounding reference signal (SRS) sent by the terminal, using channel reciprocity; in a frequency division duplex (FDD) system, since the uplink and downlink channels use different frequency domain resources, channel reciprocity cannot be used to obtain CSI, and channel estimation is performed by the terminal and the CSI is fed back. The amount of CSI data is large, and direct transmission will occupy a large amount of resources, therefore, in order to reduce the amount of transmitted CSI data, CSI compression can be performed, and the terminal feeds back the compressed CSI.

[0003] At present, a possible design is to merge data sets of multiple types of channels, and then use the merged data set to train a CSI compression recovery network, so as to obtain a trained CSI compression recovery network, and based on the CSI compression recovery network, the measured CSI is compressed and recovered. However, the above-mentioned CSI compression recovery network cannot be applied to the CSI of the channel not in the data set, and thus the generalization performance of the above-mentioned CSI compression recovery network is poor.

[0004] SUMMARY

[0005] The present application provides a channel state information feedback method, a communication apparatus, a storage medium and a program product, in order to improve the generalization performance of the CSI compression recovery network.

[0006] In a first aspect, the present application provides a channel state information feedback method, which can be executed by a communication apparatus. The communication apparatus can be a terminal, or a component (such as a chip, a chip system, a processor, etc.) configured in the terminal, or a logic module or software capable of realizing all or part of the terminal functions, and the present application does not make any limitation in this regard.

[0007] Exemplarily, the method comprises: performing standardization processing on the first CSI to obtain the second CSI, the first CSI being obtained based on measurement of the downlink signal, and the standardization processing being used to convert the first CSI into CSI in a target format; and performing compression on the second CSI to obtain the third CSI.

[0008] In this application, the compression processing of the CSI can also be considered as encoding of the CSI by an encoder, and correspondingly, the recovery processing of the CSI can also be considered as decoding of the CSI by a decoder. The CSI compression network and the CSI recovery network can be regarded as a CSI compression and recovery network, that is, the CSI compression and recovery network comprises an encoding end and a decoding end, the encoding end is used for compression processing of the CSI, and the decoding end is used for recovery processing of the CSI. The recovery can also be referred to as reconstruction, reconstruction, etc. This application does not limit it.

[0009] In the above technical solution, the CSI is standardized before the compression processing of the CSI, that is, the CSI is converted into CSI in a target format. In this way, for the CSI of different types of channels, the characteristics or formats thereof can be different. After the standardization processing, CSI in a unified format can be obtained, or a module for standardization processing can be added before the CSI compression and recovery network. In this way, it is helpful to compress the CSI of different types of channels, and further to improve the efficiency of CSI compression and the generalization performance of the CSI compression and recovery network.

[0010] In combination with the first aspect, in a possible implementation manner of the first aspect, the target format is predefined, the first CSI is based on a channel matrix representation, the CSI in the target format is based on a reference matrix representation, and the second CSI is based on a target matrix representation. The standardization processing of the first CSI to obtain the second CSI comprises: determining a precoding matrix based on the channel matrix; and performing row transformation and / or column transformation on the precoding matrix based on the reference matrix to obtain the target matrix.

[0011] The precoding matrix can be obtained based on eigenvector decomposition.

[0012] By introducing the predefined reference matrix in the target format, the channel matrices of different types of channels can be converted into channel matrices in a unified format, thereby adapting to different channel environments. Compared with model training based on a large amount of data, it is helpful to reduce the training cost and deployment cost. It can be understood that the reference matrix indicates that the CSI in a unified format is obtained by converting CSI in different formats, but the values of the CSI obtained by the standardization processing are different.

[0013] It can be understood that the target format can be predefined by a protocol or indicated by a network device.

[0014] In an example, the method further includes receiving a first parameter, the first parameter being a parameter in the target formula, and different target formulas represented by different first parameters correspond to different target formats.

[0015] That is, different target formulas represented by different first parameters correspond to different target formats, and the target formula can be used to convert the first CSI into CSI in the corresponding target format. In other words, the terminal can determine the corresponding target formula based on the first parameter, and determine the corresponding target format based on the target formula. For example, the terminal can obtain second CSI in the same format as the target format based on the first CSI and the target formula corresponding to the first parameter.

[0016] In another example, the method further includes receiving a second parameter, the second parameter being a parameter for constructing a calculation network, and different calculation networks constructed by different second parameters correspond to different target formats.

[0017] That is, different calculation networks constructed by different second parameters correspond to different target formats, and the calculation network can be used to convert the first CSI into CSI in the corresponding target format. In other words, the terminal can determine the corresponding calculation network based on the second parameter, and determine the corresponding target format based on the calculation network. For example, the terminal can obtain second CSI in the same format as the target format based on the first CSI and the calculation network corresponding to the second parameter.

[0018] With reference to the first aspect, in a possible implementation manner of the first aspect, the method further includes: obtaining a fourth CSI based on the first CSI, the fourth CSI being different from the first CSI in sparsity; and performing standardization processing on the fourth CSI to obtain the second CSI.

[0019] The fourth CSI is different from the first CSI in sparsity, for example, the data amount of the fourth CSI can be different from that of the first CSI. The fourth CSI is obtained based on the first CSI, including performing sparsification processing on the first CSI to obtain the fourth CSI (i.e., the first CSI after sparsification). Further, the terminal can perform standardization processing on the fourth CSI to obtain the second CSI.

[0020] By performing sparsification processing on the CSI before standardization processing, the sparsity of the data can be improved, and the efficiency of code word compression can be improved.

[0021] With reference to the first aspect, in a possible implementation manner of the first aspect, the method further includes: sending a third parameter, the third parameter being related to the standardization processing.

[0022] The third parameter is related to the standardization processing, which can be understood as that the third parameter can indicate the process of the standardization processing, or in other words, the third parameter can help the decoding end to restore the standardized CSI to the original CSI. The terminal feeds back the third parameter, which is greatly reduced compared to the parameters that need to be fed back by the existing CSI compression and recovery network, thereby helping to improve the transmission efficiency.

[0023] In a second aspect, the present application provides a channel state information feedback method, which can be executed by a communication device. The communication device can be a network device, a component (such as a chip, a chip system, a processor, etc.) configured in the network device, or a logic module or software capable of realizing all or part of the functions of the network device, and the present application does not limit this.

[0024] Exemplarily, the method includes: receiving a third CSI and a third parameter, the third parameter being related to a standardization processing, the standardization processing being used to convert a first CSI into a CSI in a target format, the first CSI being obtained based on a measurement on a downlink signal; decompressing the third CSI to obtain a fifth CSI; and obtaining a sixth CSI based on the third parameter and the fifth CSI.

[0025] The third parameter is related to the standardization processing, or in other words, the third parameter can indicate the process of the standardization processing, and the decoding end can restore the standardized CSI to the original CSI based on the third parameter.

[0026] The fifth CSI can be considered as a reconstructed or reestablished second CSI, and the fifth CSI and the second CSI are generally different. Similarly, the sixth CSI can be considered as a CSI obtained by performing an inverse process of the standardization on the fifth CSI, and the sixth CSI and the first CSI are generally different.

[0027] In the above technical solution, for the CSI of different types of channels, the characteristics or formats thereof can be different, and after the standardization processing, the CSI in a unified format can be obtained, which helps to improve the channel reconstruction accuracy for the decoding end. Moreover, the CSI of different types of channels can be recovered, which helps to improve the generalization performance of the CSI compression and recovery network.

[0028] With reference to the second aspect, in some possible implementation of the second aspect, the target format is predefined, and the fifth CSI is obtained based on the target matrix and the third parameter and the fifth CSI, including: performing inverse transformation of row transformation and / or inverse transformation of column transformation on the target matrix based on the third parameter to obtain a precoding matrix.

[0029] It can be understood that the target format can be predefined by a protocol or indicated by a network device.

[0030] In an example, the method further includes: sending the first parameter, the first parameter being a parameter in the target formula, and different target formulas represented by different first parameters corresponding to different target formats.

[0031] That is, different target formulas represented by different first parameters correspond to different target formats, and the target formula can be used to convert the first CSI into CSI in the corresponding target format, in other words, the terminal can determine the corresponding target formula based on the first parameter, and determine the corresponding target format based on the target formula. For example, the terminal can obtain the second CSI in the same CSI format as the target format based on the first CSI and the target formula corresponding to the first parameter.

[0032] In another example, the method further includes: sending the second parameter, the second parameter being a parameter for constructing a calculation network, and different calculation networks constructed by different second parameters corresponding to different target formats.

[0033] That is, different calculation networks constructed by different second parameters correspond to different target formats, and the calculation network can be used to convert the first CSI into CSI in the corresponding target format, in other words, the terminal can determine the corresponding calculation network based on the second parameter, and determine the corresponding target format based on the calculation network. For example, the terminal can obtain the second CSI in the same CSI format as the target format based on the first CSI and the calculation network corresponding to the second parameter.

[0034] With reference to the second aspect, in some possible implementation of the second aspect, the obtaining of the sixth CSI based on the third parameter and the fifth CSI includes: performing inverse process of standardization processing on the fifth CSI based on the third parameter to obtain a seventh CSI; and obtaining the sixth CSI based on the seventh CSI, the seventh CSI and the sixth CSI being different in sparsity.

[0035] The sixth CSI is obtained based on the seventh CSI, for example, inverse processing of sparsification can be performed on the seventh CSI to obtain the sixth CSI.

[0036] By introducing the sparsification processing, the sparsity of data can be improved, and the efficiency of code word compression can be improved.

[0037] In a third aspect, the present application provides a communication apparatus, which can implement the method in the first aspect and any possible implementation of the first aspect, or implement the method in the second aspect and any possible implementation of the second aspect. The apparatus includes corresponding units for performing the above method. The units included in the apparatus can be implemented by software and / or hardware.

[0038] In a fourth aspect, the present application provides a communication apparatus, which includes a processor. The processor is coupled with a memory and can be used to execute a computer program in the memory to implement the method in the first aspect and any possible implementation of the first aspect, or implement the method in the second aspect and any possible implementation of the second aspect.

[0039] Optionally, the apparatus further includes a communication interface, and the processor is coupled with the communication interface. The communication interface is configured to receive a signal from another communication device outside the apparatus and transmit the signal to the processor, or send a signal from the processor to another communication device outside the apparatus. Exemplarily, the communication interface can be a transceiver, a circuit, a bus, a module or another type of communication interface.

[0040] Optionally, the apparatus further includes a memory. The memory is configured to store program instructions and data.

[0041] In a fifth aspect, the present application provides a computer readable storage medium, which stores a computer program or instructions, and when the computer program or instructions are executed, the method in the first aspect and any possible implementation of the first aspect is implemented, or the method in the second aspect and any possible implementation of the second aspect is implemented.

[0042] In a sixth aspect, the present application provides a computer program product, which includes instructions, and when the instructions are executed, the method in the first aspect and any possible implementation of the first aspect is implemented, or the method in the second aspect and any possible implementation of the second aspect is implemented.

[0043] In a seventh aspect, the present application provides a chip system, which includes at least one processor, and is configured to support the functions in the above first aspect and any possible implementation of the first aspect, or support the functions in the above second aspect and any possible implementation of the second aspect, such as receiving or processing data involved in the above method.

[0044] In a possible design, the chip system further includes a memory, which is configured to store program instructions and data, and the memory is located in the processor or outside the processor.

[0045] The chip system can be composed of chips, or can contain chips and other discrete devices.

[0046] In an eighth aspect, the present application provides a communication system, comprising a terminal device for implementing the method in the first aspect and any possible implementation manner of the first aspect, and a network device for implementing the method in the second aspect and any possible implementation manner of the second aspect.

[0047] It should be understood that the third aspect to the eighth aspect of the present application correspond to the technical solutions of the first aspect and the second aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding possible implementation manners are similar, which will not be described again. BRIEF DESCRIPTION OF DRAWINGS

[0048] FIG. 1 is a schematic diagram of an architecture of a communication system suitable for the method provided by the present application;

[0049] FIG. 2 is a schematic diagram of an existing CSI compression and recovery network provided by an embodiment of the present application;

[0050] FIG. 3 is a schematic flowchart of a CSI feedback method provided by an embodiment of the present application;

[0051] FIG. 4 is a schematic diagram of a CSI compression and recovery process provided by an embodiment of the present application;

[0052] FIG. 5 is a schematic block diagram of a communication device provided by an embodiment of the present application;

[0053] FIG. 6 is another schematic block diagram of a communication device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0054] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0055] The technical solutions provided in the present application can be applied to various communication systems, for example, a long term evolution (LTE) system, an FDD system, a TDD system, a sidelink communication system, a universal mobile telecommunication system (UMTS), a worldwide interoperability for microwave access (WiMAX) communication system, a 5th generation (5G) mobile communication system or a new radio access technology (NR). The 5G mobile communication system can include non-standalone (NSA) and / or standalone (SA).

[0056] The technical solutions provided in the present application can also be applied to future communication systems. The present application does not limit this.

[0057] In order to facilitate understanding of the method provided in the present application, the following points are first explained.

[0058] First, in order to facilitate clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", etc. For example, the first CSI and the second CSI are only used to distinguish different CSIs, and the order is not limited. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not necessarily mean different.

[0059] Second, in the embodiments shown in the present application, each term and English abbreviation, such as channel state information (CSI), is an example for convenient description, and should not constitute any limitation on the present application. The present application does not exclude the possibility of defining other terms capable of achieving the same or similar functions in the existing or future protocols.

[0060] Third, the "protocol" involved in the embodiments of the present application can refer to a standard protocol in the communication field, for example, can include an LTE protocol, an NR protocol and a related protocol applied to a future communication system, and the present application does not limit this.

[0061] Fourthly, "at least one" means one or more, "multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c, where a, b and c can be single or multiple.

[0062] Fifthly, in this application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to a terminal" can be understood as the destination of the information being the terminal, which can include direct transmission through the air interface, or indirect transmission through the air interface by other units or modules. "Receiving configuration information from a network device" can be understood as the source of the configuration information being the network device, which can include receiving directly from the network device through the air interface, or indirectly receiving from the network device through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0063] In other words, sending and receiving can be between devices, such as between a network device and a terminal; or within a device, such as between components, modules, chips, software modules or hardware modules within a device through a bus, wire or interface.

[0064] It can be understood that the information may be processed as necessary before being sent from the source to the destination, such as encoding, modulation, etc. The destination can also perform corresponding processing after receiving the information from the source, such as decoding, demodulation, etc., so as to interpret the valid information from the source. Similar expressions in this application can be similarly understood and will not be repeated.

[0065] Sixthly, in this application, "when", "in the case of", "if" and other descriptions all refer to the device (such as a network device or a terminal) making corresponding processing under certain objective circumstances, not limited to time, and does not require the device (such as a network device or a terminal) to have a judgment action when implemented, nor does it mean that there are other limitations.

[0066] Seventhly, in this application, "predefined" can also be understood as: defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, fixed, or pre-burned.

[0067] Eighth, in this application, the terminal as the encoding end and the network device as the decoding end are only examples and should not constitute any limitation on this application. For example, in actual applications, the network device can also be the encoding end and the terminal can also be the decoding end. In addition, the encoding end can also be regarded as the sending end and the decoding end can also be regarded as the receiving end.

[0068] The communication system to which the method provided in this application is applicable will be described in detail below with reference to the accompanying drawings.

[0069] FIG. 1 is a schematic diagram of the architecture of a communication system applicable to the method provided in this application. FIG. 1 shows a schematic diagram of a possible, non-limiting system architecture.

[0070] As shown in FIG. 1, the communication system 1000 includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (such as 110a and 110b in FIG. 1, collectively referred to as 110) and at least one terminal (such as 120a-120j in FIG. 1, collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in FIG. 1), etc., can also be included in the RAN 100. The terminal 120 is connected to the RAN node 110 in a wireless manner. The RAN node 110 is connected to the core network 200 in a wireless or wired manner. The core network device in the core network 200 and the RAN node 110 in the RAN 100 can be different physical devices respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the radio access network.

[0071] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolved system (such as a future communication system). The RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (Wi-Fi) system. The RAN 100 can also be a communication system that combines two or more of the above systems.

[0072] The RAN node 110, which can also be referred to as a network device, an access network device, a RAN entity, or an access node, etc., is a part of a communication system to help terminals to access the network wirelessly. The RAN nodes 110 in the communication system 1000 can be of the same type or of different types. In some scenarios, the roles of the RAN node 110 and the terminal 120 are relative, for example, the network element 120i in Figure 1 can be a helicopter or a drone, which can be configured to be a mobile base station, for the terminal 120j accessing to the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN node 110 and the terminal 120 are sometimes both referred to as communication apparatuses, for example, the network elements 110a and 110b in Figure 1 can be understood as communication apparatuses with base station functions, and the network elements 120a-120j can be understood as communication apparatuses with terminal functions.

[0073] In a possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a base station in a future communication system, or an access node in a Wi-Fi system, etc. The RAN node can be a macro base station (such as 110a in Figure 1), a micro base station or an indoor station (such as 110b in Figure 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU).

[0074] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a control unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0075] A terminal can also be referred to as user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal device, a wireless communication device, a user agent, or a user apparatus.

[0076] The terminal can be a device that provides voice / data connectivity to a user, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. Currently, some examples of terminals can be: a mobile phone, a pad, a computer (such as a notebook computer, a palm computer, etc.) with wireless transceiver function, a mobile internet device (MID), a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a drone, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal in a 5G network, or a terminal in a future evolved public land mobile network (PLMN), etc.

[0077] In addition, the terminal can also be a terminal in an internet of things (IoT) system. IoT is an important part of the future development of information technology, and its main technical feature is to connect objects through communication technology and network, so as to realize the intelligent network of man-machine interconnection and object-object interconnection. IoT technology can achieve mass connection, deep coverage and terminal power saving through, for example, narrow band (NB) technology.

[0078] In addition, the terminal can also include smart printers, train detectors, gas station sensors, and the main functions include collecting data (part of the terminal), receiving control information and downlink data of network equipment, and sending electromagnetic waves to transmit uplink data to network equipment.

[0079] In the embodiments of the present application, the network device may, for example, be the RAN node 110 shown in FIG. 1, and the terminal may, for example, be the terminal 120 shown in FIG. 1. The type of the network device and the terminal is not specifically limited in the present application.

[0080] In addition, the terminal and the network device may be hardware devices, or software functions running on special-purpose hardware, software functions running on general-purpose hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special-purpose or general-purpose hardware devices and software functions. The specific form of the terminal and the network device is not limited in the present application.

[0081] CSI can be used to reflect the channel state. When scheduling and precoding, CSI needs to be obtained to match the transmitted signal to the channel state. In networks of different duplex modes, the way of obtaining CSI is different.

[0082] For example, in a TDD system, the network device can obtain the CSI from the network device to the terminal by measuring the uplink SRS sent by the terminal, by using the uplink-downlink channel reciprocity in the TDD system. In an FDD system, since the uplink and downlink channels use different frequency resources, the channel reciprocity cannot be used to obtain CSI, so the terminal performs channel estimation and feeds back CSI. The feedback accuracy and the feedback amount of CSI are important performance indicators. The more accurate the CSI feedback is, the more suitable the scheduling and precoding are to the channel, and the better the transmission performance is. The greater the CSI feedback amount is, the more accurate it is. Therefore, directly transmitting the CSI feedback amount may occupy a large amount of resources. To reduce the amount of CSI data transmitted, CSI compression can be performed, and the terminal feeds back the compressed CSI.

[0083] The existing CSI compression feedback scheme will be described below in conjunction with FIG. 2.

[0084] FIG. 2 is a schematic diagram of an existing CSI compression recovery network provided by an embodiment of the present application. In the CSI compression recovery network shown in FIG. 2, the CSI compression recovery network includes an encoding end and a decoding end. The encoding end is configured to perform encoding processing on CSI, and the decoding end is configured to perform recovery processing on the CSI.

[0085] One scheme is that, as shown in a) of FIG. 2, in the face of multiple channels, the data sets (that is, subtask 1-data set, subtask 2-data set, subtask 3-data set, and subtask 4-data set in the figure) of the multiple channels can be merged (or mixed), the CSI compression recovery network is trained using the merged data set, so as to obtain a trained CSI compression recovery network, and the CSI is compressed and recovered based on the trained CSI compression recovery network.

[0086] In the above scheme, if the channel distribution is not in the data set, that is, if the data set does not include the type of channel distribution, the CSI feedback accuracy can be low, in other words, the generalization performance of the above network is poor.

[0087] Another solution is, as shown in b) of FIG. 2, in the face of multiple channels, the data set of multiple channels is respectively trained to obtain a corresponding CSI compression and recovery network (as shown in the figure, four CSI compression and recovery networks are shown), in use, first determine which CSI compression and recovery network should be used for compression and recovery, and then use the CSI compression and recovery network for compression and recovery.

[0088] In the above scheme, if a new channel with different distribution is encountered, the corresponding CSI compression and recovery network cannot be found, that is, in the above scheme, the generalization performance of the CSI compression and recovery network is poor.

[0089] To this end, the CSI feedback method provided by the present application normalizes the CSI before compression, which can convert the CSI of different types of channels (or channels with different distributions) into a target format, and then compress the normalized CSI, so that the CSI compression and recovery network can be applicable to different types of channels, and even if a new channel is encountered, the CSI of the new channel can be normalized and then compressed, which helps to improve the generalization performance of the CSI compression and recovery network.

[0090] The CSI feedback method provided by the present application will be described in detail below with reference to the accompanying drawings. The method is described below by taking the interaction between a network device and a terminal as an example, but should not constitute any limitation on the present application. The network device can also be replaced by a component (such as a chip, a chip system, a processor, etc.) configured in the network device, or a logic module or software capable of realizing all or part of the functions of the network device. The terminal can also be replaced by a component (such as a chip, a chip system, a processor, etc.) configured in the terminal, or a logic module or software capable of realizing all or part of the functions of the terminal.

[0091] FIG. 3 is a schematic flowchart of a CSI feedback method 300 provided by an embodiment of the present application. The steps in the method 300 will be described in detail below.

[0092] In step 310, the terminal normalizes the first CSI to obtain the second CSI.

[0093] The first CSI is obtained based on measurement of a downlink signal. The downlink signal includes, but is not limited to, a channel state information reference signal (CSI-RS), a synchronization signal block (SSB), a cell-specific reference signal (CRS), a demodulation reference signal (DM-RS), or the like. The type of the downlink signal is not limited in the present application, as long as the downlink signal can be used for measurement by the terminal. For example, the downlink signal can also be a pilot signal of another type.

[0094] The standardization processing can be used to convert the first CSI into CSI of a target format. The target format can be predefined. That is, the standardization processing can convert CSI of different types of channels into CSI of a predefined format. Different types of channels can refer to channels with different distributions. For example, channels can be classified into line-of-sight (LOS) and non-line-of-sight (NLOS) channels based on the propagation characteristics of the channels. In the LOS channel, there is a direct, unobstructed line-of-sight path between the transmitting end and the receiving end, that is, the signal can be directly transmitted from the transmitting end to the receiving end without being blocked by an intermediate obstacle. In the NLOS channel, there is no direct line-of-sight path between the transmitting end and the receiving end, and the signal is affected by obstacles, reflection, refraction, scattering, and the like during propagation. It can be understood that in actual applications, the types (or distributions) of channels are various, and the types are not limited in the present application.

[0095] By standardizing the CSI, CSI of different types of channels can be converted into CSI of a predefined format, so that the format of the CSI can be unified, and the generalization performance of the CSI compression and recovery network can be improved.

[0096] Exemplarily, before encoding, the terminal standardizes the first CSI to obtain second CSI, which conforms to a predefined format.

[0097] It can be understood that the target format can be predefined or indicated by the network device.

[0098] One possible implementation is that the network device sends a first parameter, which is a parameter in the target formula. Different first parameters represent different target formulas corresponding to different target formats.

[0099] That is, different target formulas represented by different first parameters correspond to different target formats, and the target formulas can be used to convert the first CSI into CSI in the corresponding target format. In other words, the terminal can determine the corresponding target formula based on the first parameter, and determine the corresponding target format based on the target formula. For example, the terminal can obtain second CSI in the same format as the CSI in the target format based on the first CSI and the target formula corresponding to the first parameter.

[0100] Another possible implementation is that the network device sends a second parameter, which is a parameter for constructing a calculation network, and different calculation networks constructed by different second parameters correspond to different target formats.

[0101] That is, different calculation networks constructed by different second parameters correspond to different target formats, and the calculation network can be used to convert the first CSI into CSI in the corresponding target format. In other words, the terminal can determine the corresponding calculation network based on the second parameter, and determine the corresponding target format based on the calculation network. For example, the terminal can obtain second CSI in the same format as the CSI in the target format based on the first CSI and the calculation network corresponding to the second parameter.

[0102] In step 320, the terminal compresses the second CSI to obtain third CSI.

[0103] For example, after the terminal obtains the second CSI by standardizing the first CSI, the terminal compresses the second CSI by an encoder to obtain the third CSI.

[0104] In step 330, the terminal sends the third CSI and the third parameter. Correspondingly, the network device receives the third CSI and the third parameter.

[0105] The third parameter can also be referred to as a change parameter, and the name thereof is not limited in the present application.

[0106] The third parameter is related to the standardization process, or the third parameter can indicate the standardization process, or the third parameter can be used to restore the standardized CSI to the original CSI at the decoding end.

[0107] For example, the terminal standardizes the first CSI to obtain the second CSI and the third parameter for indicating the standardization process, further compresses the second CSI to obtain the third CSI, and sends the third CSI and the third parameter. Correspondingly, the network device receives the third CSI and the third parameter.

[0108] It can be understood that the third parameter and the third CSI can be carried in the same signaling or in different signaling, and the present application does not limit this.

[0109] In step 340, the network device decompresses the third CSI to obtain a fifth CSI.

[0110] Decompressing the third CSI can also be understood as decoding the third CSI, or reconstructing (or referred to as rebuilding or restoring) the third CSI, etc.

[0111] Exemplarily, the network device decompresses the third CSI by a decoder to obtain the fifth CSI. The fifth CSI can be considered as a reconstructed or rebuilt second CSI, and the fifth CSI and the second CSI are generally different.

[0112] In step 350, the network device obtains a sixth CSI based on the third parameter and the fifth CSI.

[0113] The sixth CSI can be considered as a CSI obtained by performing an inverse process of standardization on the fifth CSI, and the sixth CSI and the first CSI are generally different.

[0114] As mentioned above, the third parameter is used to indicate a process of converting the first CSI into the second CSI, and the network device obtains the sixth CSI by performing an inverse process of standardization on the fifth CSI based on the third parameter.

[0115] In the present application, the CSI compression and recovery network includes an encoding end and a decoding end, the encoding end is used for encoding processing of CSI, and the decoding end is used for recovery processing of CSI. Wherein, the recovery can also be referred to as rebuilding, reconstruction, etc. In addition, in the present application, a preprocessing module (such as a standardization processing module or a distribution normalization module) is introduced before the encoding end (such as an encoder) to normalize the input CSI to a unified distribution, and the module outputs the CSI after standardization processing and the third parameter. A post-processing module is introduced after the decoding end (such as a decoder) to perform an inverse process of standardization processing on the decoded CSI to recover to the original CSI (such as the sixth CSI), and it can be understood that the sixth CSI is a recovered CSI, and the first CSI is generally different.

[0116] In the technical solution, the terminal performs standardization processing on the CSI before compression, which can convert the CSI of different types of channels (or channels with different distributions) into a target format, and then compress the CSI after standardization processing. Therefore, the CSI compression and recovery network can be applied to different types of channels, and even when a new channel is encountered, the CSI of the new channel can be standardized and compressed, which helps to improve the generalization performance of the CSI compression and recovery network.

[0117] It can be understood that the CSI is generally represented based on a channel matrix. The standardization process of the CSI will be explained in detail from the perspective of the channel matrix.

[0118] In one possible design, the first CSI is represented based on a channel matrix, the CSI of the predefined format is represented based on a reference matrix, and the second CSI is represented based on a target matrix. The standardization processing on the first CSI to obtain the second CSI includes determining a precoding matrix based on the channel matrix, and performing row transformation and / or column transformation on the precoding matrix based on the reference matrix to obtain the target matrix.

[0119] The standardization processing is exemplarily described by taking row transformation and / or column transformation on the precoding matrix, but the present application should not be limited thereto. For example, the standardization processing can also be other processing on the precoding matrix. The precoding matrix can be obtained by normalizing a eigenvector corresponding to a maximum eigenvalue of the channel matrix.

[0120] The reference matrix includes, but is not limited to, an upper triangular matrix, a lower triangular matrix, a diagonal matrix, a unit matrix, and the like. It can be understood that the reference matrix only needs to have a specific structure, and the present application does not limit the specific form of the reference matrix.

[0121] Correspondingly, the network device performs step 350 (the network device obtains the sixth CSI based on the third parameter and the fifth CSI), which includes performing inverse row transformation and / or inverse column transformation on the target matrix based on the third parameter to obtain the precoding matrix. The third parameter can be the number of rows of the row transformation and / or the number of columns of the column transformation. The network device performs inverse row transformation and / or inverse column transformation on the target matrix based on the third parameter to obtain the precoding matrix.

[0122] Optionally, the standardization processing on the first CSI to obtain the second CSI includes: the terminal obtains a fourth CSI based on the first CSI, the fourth CSI and the first CSI have different sparsity degrees; and the standardization processing on the fourth CSI to obtain the second CSI.

[0123] The different sparsity degrees of the fourth CSI and the first CSI can be understood as different data amounts of the two. The fourth CSI is obtained based on the first CSI, including: performing sparse processing on the first CSI to obtain the fourth CSI (i.e., the first CSI after sparse processing), and further, the terminal can perform standardization processing on the fourth CSI to obtain the second CSI.

[0124] Exemplarily, the first CSI is based on a channel matrix representation, a feature vector corresponding to a maximum eigenvalue of the channel matrix is normalized to obtain a precoding matrix, sparse processing is performed on the precoding matrix to obtain a precoding matrix after sparse processing, and then based on a reference matrix, row transformation and / or column transformation is performed on the precoding matrix after sparse processing to obtain a target matrix (corresponding to the second CSI).

[0125] Correspondingly, the network device performs an inverse process of the standardization processing on the fifth CSI based on the third parameter to obtain the sixth CSI, including: performing an inverse process of the standardization processing on the fifth CSI based on the third parameter to obtain a seventh CSI; and performing an inverse process of the sparse processing on the seventh CSI to obtain the sixth CSI.

[0126] Exemplarily, the fifth CSI is based on a target matrix representation, the network device performs an inverse process of the row transformation and / or the inverse process of the column transformation on the target matrix based on the third parameter to obtain a first matrix (corresponding to the seventh CSI), and performs an inverse process of the sparse processing on the first matrix to obtain a precoding matrix.

[0127] Optionally, before step 310, the method 300 further includes: the network device sends a downlink signal, and correspondingly, the terminal receives the downlink signal and performs measurement based on the downlink signal, or in other words, performs channel estimation based on the downlink signal to obtain the first CSI.

[0128] Optionally, before step 310, the method 300 further includes: the network device sends a configuration parameter about a CSI compression network in a CSI compression recovery network to the terminal, where the configuration parameter can include a number of layers of the network and weights in the network. Correspondingly, the terminal receives the configuration parameter and generates the CSI compression network based on the configuration parameter.

[0129] The encoding part in the CSI compression recovery network can be referred to as a CSI compression network, and correspondingly, the decoding part can be referred to as a CSI recovery network.

[0130] Optionally, the configuration parameter of the CSI compression recovery network can also be predefined, in other words, the terminal can generate the CSI compression network based on the predefined configuration parameter.

[0131] FIG. 4 is a schematic diagram of a CSI compression recovery process according to an embodiment of the present application.

[0132] As shown in FIG. 4, a pre-processing module is introduced before the CSI compression recovery network, which includes, for example, a sparsification process and a normalization process. A post-processing module is introduced after the CSI compression recovery network, which is the inverse process of the pre-processing module, for example, including the inverse process of the normalization process and the inverse process of the sparsification process.

[0133] For example, at the compression end, the original channel state information (corresponding to the original channel matrix, denoted as matrix 1) is input, the original channel matrix is subjected to eigenvalue decomposition to obtain a precoding matrix (denoted as matrix 2), the precoding matrix is subjected to a sparsification process, for example, by a sparse transformation function, to obtain a matrix after sparsification (denoted as matrix 3), and further, the matrix 3 is subjected to a normalization process to obtain a matrix 4 (corresponding to new channel state information with uniform distribution), which is the same as the reference matrix in format or distribution. The output after the normalization process is the matrix 4 and a third parameter indicating the normalization process. Further, the encoder is used for encoding, and the encoded matrix (denoted as matrix 5, i.e., compressed data of the new channel state information) and the third parameter are output and sent, and thus, the air interface outputs the change index and the data of the matrix 5.

[0134] At the recovery end, the compressed data of the new channel state information is received by the recovery end and recovered into reconstructed new channel state information by the decoder. According to the third parameter, the inverse process of the normalization process is performed, and further, the inverse process of the sparsification process is performed to obtain the reconstructed original channel state information, i.e., the output is the reconstructed original channel state information.

[0135] The network device can perform scheduling, precoding, etc. according to the reconstructed original channel state information.

[0136] In the technical solution shown in FIG. 4, the terminal performs normalization processing on the CSI before compressing the CSI, which can convert the CSI of different types of channels (or channels with different distributions) into CSI in a predefined format, and then compress the CSI after the normalization processing, so that the CSI compression recovery network can be applicable to different types of channels, and even when a new channel is encountered, the CSI of the new channel can be normalized and then compressed, which helps to improve the generalization performance of the CSI compression recovery network. In addition, by performing the sparsification process on the CSI before the normalization processing, the sparseness of the data can be improved, and thus the efficiency of the code word compression can be improved. Furthermore, the terminal feeds back the third parameter, which is greatly reduced compared to the parameters that need to be fed back using the existing CSI compression recovery network, and thus helps to improve the transmission efficiency.

[0137] The following will give the specific process of the standardization processing and the sparsification processing by examples. In the following, the CSI is represented based on a channel matrix (or a channel state matrix). For example, taking a channel matrix with rank 1 as an example. Wherein, the channel matrix with rank 1 means that the maximum number of linearly independent rows or columns in the channel matrix is 1, in other words, all the rows or all the columns of the channel matrix are linearly dependent. It can be understood that the rank 1 of the above channel matrix is only an example, and should not constitute any limitation to the present application. For example, the rank of the channel matrix can also be other values. When the rank of the channel matrix is not 1, the CSI compression recovery can also be realized based on the following steps.

[0138] Step one: the terminal performs channel estimation based on the received pilot signals to obtain a channel matrix (downlink).

[0139] Firstly, the following assumptions are made:

[0140] 1. The base station (an example of a network device) has N t transmission antennas, N h represents the number of horizontal antennas, and N v represents the number of vertical antennas.

[0141] 2. The terminal has N h transmission antennas (here specifically can be transmit antennas).

[0142] 3. The total number of subbands is K, each subband includes one or more subcarriers, and the channel state information of each subband can be represented by a feedback amount. Wherein, the feedback amount can be the average value of the CSI of the subcarriers in the subband, or the weighted average value of the CSI of the subcarriers in the subband, or the CSI of a certain specific subcarrier in the subband, which is not limited by the present application. K is a positive integer.

[0143] The channel matrix is represented as: H' = [H1, H2, …, H v K], wherein, H r k represents the downlink channel state information of the kth subband, and k takes a value in the range of 1 to K.

[0144] Assuming that the channel estimation at the terminal side is accurate, through eigenvalue decomposition: we get the normalized eigenvector corresponding to the maximum eigenvalue of the kth subband w K k, which ensures that ||w k k|| = 1. Wherein, λ 2 k is the maximum eigenvalue of H k k, H k k represents the transpose of H K k. As the precoding vector corresponding to the kth subband, similarly, the precoding vector corresponding to each subband in the K subbands can be obtained, and then the precoding matrix W = [w1, w2, …, wK] is obtained. K ].

[0145] The terminal reports the precoding matrix to the base station. Exemplarily, the terminal compresses the precoding matrix and reports the compressed precoding matrix, and the base station reconstructs the compressed precoding matrix to obtain the reconstructed precoding matrix. In the present application, before the precoding matrix is compressed, a standardization process is introduced, and correspondingly, the base station introduces the inverse process of the standardization process after reconstruction. Compared with the adaptive model switching based on the environment to improve the neural network model, the present application reduces the need for model adjustment and switching by matching the format identified by the pre-trained CSI compression and recovery network model with the standardized (or normalized, or normalized, etc.) CSI format, and improves the generalization performance of the model.

[0146] Optionally, a sparsification process can also be introduced, and the sparseness of the precoding matrix, so as to improve the efficiency of the codeword compression.

[0147] The process of sparsification and standardization of the precoding matrix will be described in detail below.

[0148] I. Sparseness processing

[0149] A possible implementation is to convert the precoding matrix W into a domain that presents enhanced sparseness by 2-dimensional (D) discrete fourier transformation (DFT). More specifically, the precoding matrix W is converted into W = F K N W, where F K and F N are K × K and N × N normalized DFT matrices, respectively, and Ψ(·) represents a sparsification function. The 2D DFT is selected because of the inherent sparseness of the precoding matrix in the angular delay domain. Further, the phase and amplitude of the above matrix are decoupled by: Spar where F d and F h represent the K × K and N t × N t normalized DFT matrices, respectively, and Ψ(·) represents a sparsification function. The 2D DFT is selected because of the inherent sparseness of the precoding matrix in the angular delay domain. Further, the phase and amplitude of the above matrix are decoupled by: where ⊙ represents the Hadamard product. The element at position (i, j) in W Spar is represented as

[0150] II. Standardization processing

[0151] f en (·) and f de ​(·) respectively represent encoding function and decoding function, the CSI compression recovery network comprises f en (·) and f de (·), wherein s = f en (W), represents the reconstructed W, i.e., the recovered W at the decoding end. It can be understood that the higher the reconstruction accuracy, the higher the coincidence degree of W and . In the present application, before the precoding matrix is input into the CSI compression recovery network, it is first converted into a predetermined format. The standardization process and its inverse process are formalized as follows:

[0152] W std , b = S(W); (standardization), wherein b represents a third parameter.

[0153] s = f en (W std ); (encoding)

[0154] (decoding)

[0155] (standardization inverse process)

[0156] wherein W std represents the standardized precoding matrix. The standardization process will be described below.

[0157] First, a reference matrix W Ben is determined. As an example but not limitation, in the case of considering a line-of-sight (LoS) channel, first, a sample is randomly selected from a pre-defined LoS channel model, which should contain various parameters of the channel, such as path gain, angle of arrival (AoA), angle of departure (AoD) and path delay, etc. Second, according to the selected LoS channel sample, the expected average angle of departure perpendicular to the antenna array is calculated. Third, all angle information (such as AoA and AoD) in the LoS channel sample is adjusted so that the expected average angle of departure is centered in the angle domain. In addition, the main component (usually the path with the largest gain) is identified in the delay domain and is aligned. For example, the delay domain can be standardized by adjusting the delay so that the delay of the main component is zero or a fixed value (such as ). Finally, the reference matrix W Ben is generated according to the above-processed LoS channel sample. The reference matrix W Ben is usually a complex matrix representing the gain and phase information of the channel.

[0158] As mentioned above, the precoding matrix W is sparsified to obtain W Spar, the following can be cyclically shifted by a function f sh (·,m,n), to align W Spar with the reference matrix W Ben . Where m and n represent the shift steps in rows and columns, respectively. The precoding matrix W shift after cyclic shift is denoted as: W shift = f sh (W Spar ,m,n) = A m W Spar [A T ] n , where W shift has the same format as the reference matrix W Ben . Where, is a cyclic permutation matrix, indicates that A is an N t ×N t real matrix. A can be, for example, A is a cyclic row permutation matrix, A T is the transpose of A, and A T is a cyclic column permutation matrix.

[0159] It can be understood that the above cyclic row permutation matrix is only an example in the present application and should not constitute any limitation on the embodiments of the present application. In actual applications, other forms of matrices can also be used.

[0160] It can be understood that determining the optimal shift steps m* and n* for the optimal alignment of W Spar and the reference matrix W Ben helps to reduce the shift and reduce the amount of calculation. A way of independently solving m* and n* is given below.

[0161] The row and column vectors are defined as: and W Ben Similarly, the reference matrix r Ben of the above row and column vectors r is defined. The optimal shift cyclic shift m* that maximizes the correlation between r and r m can be determined by the correlation function C(m) = r Ben ·r Ben . Where r m is the result of r cyclically shifted by m steps. By maximizing C(m), the optimal shift can be found: A similar process is also applicable to determining the optimal column shift n*. The column and row vectors are defined as and W Ben Similarly, the reference matrix c Ben of the above row and column vectors c is defined. The optimal shift cyclic shift n* that maximizes the correlation between c and c n can be determined by the correlation function C(n) = c Ben, to determine the optimal shift cyclic shift n* that maximizes the correlation between c and c Ben . Where c n is the result of c cyclically shifted n steps. By maximizing C(n), the optimal shift n* is found: and the offset c Ben that maximizes the correlation defined by the reference matrix W std .

[0162] After the terminal determines m* and n*, it determines the precoding matrix W std in the manner described above, based on the standardized precoding matrix W , where {m*, n*} is the optimal shift step, i.e., the third parameter to be sent to the base station. For example, the terminal can encode this third parameter in 2 bits.

[0163] After the terminal determines the above-mentioned W std , it encodes the above-mentioned W en based on s = f std (W std ) to obtain s.

[0164] Exemplarily, the terminal sends the above-mentioned s and {m*, n*} to the base station, and correspondingly, the base station receives the above-mentioned s and {m*, n*}.

[0165] After the base station receives the above-mentioned s and {m*, n*}, it performs the decoding process , where denotes the reconstructed W std . Further, the base station performs the inverse process of standardization , where denotes the reconstructed W Spar . Finally, the base station performs the inverse process of sparsification , where denotes the reconstructed W, and Ψ -1 (·) denotes the inverse sparse transform function, such as the inverse 2D DFT, so as to recover to the original precoding matrix format.

[0166] Optionally, in the present application, the CSI feedback and the reconstruction accuracy on the kth subband can be evaluated based on the squared generalized cosine similarity (SGCS) : , where is the reconstructed eigenvector of the kth subband. The overall CSI feedback and recovery performance is determined by the average SGCS: ​The closer the value is to 1, the higher the feedback and recovery efficiency of the CSI. Therefore, the optimization goal of the CSI feedback is defined as: wherein, denotes a set of CSI feedback schemes, including Type I feedback based on a codebook, Type II feedback based on a codebook, and a downlink-based auto-encoder method.

[0167] The above describes in detail the method provided by the embodiments of the present application in combination with the drawings. The following describes in detail the apparatus provided by the embodiments of the present application in combination with the drawings.

[0168] FIG. 5 is a schematic block diagram of a communication apparatus 500 provided by the embodiments of the present application.

[0169] In FIG. 5, the transceiver module 520 can implement corresponding communication functions, and the transceiver module 520 can also be referred to as an input / output interface or a communication unit. The processing module 510 can be used to perform processing operations. It should be understood that if the apparatus 500 is a component, such as a chip, configured in a network device or a terminal, the transceiver module 520 can be an input / output interface.

[0170] Optionally, the transceiver module 520 can include a sending module and a receiving module. The sending module is used to perform the sending operations of the network device or the terminal in FIG. 3 described above, and the receiving module is used to perform the receiving operations of the network device or the terminal in FIG. 3 described above.

[0171] It should be understood that if the apparatus 500 is a component, such as a chip, configured in a network device or a terminal, the sending module can be an output interface, and the sending operations involved in the embodiments of the present application can be performed by the output interface; the receiving module can be an input interface, and the receiving operations involved in the embodiments of the present application can be performed by the input interface.

[0172] Optionally, the apparatus 500 can further include a storage module, which can be used to store instructions and / or data. The processing module 510 can read the instructions and / or data in the storage module, so that the apparatus implements the method embodiments shown in the preceding FIG. 3.

[0173] In a possible design, the apparatus 500 described above can be used to implement the functions of the terminal in the method embodiments shown in FIG. 3 described above, or the apparatus 500 can include a unit for implementing any function or operation of the terminal in the method embodiments shown in FIG. 3 described above, and the unit can be implemented by software, hardware, firmware, or any combination thereof, in whole or in part.

[0174] When the apparatus 500 is configured to implement the function of the terminal in the method embodiment shown in FIG. 3, the processing module 510 can be configured to perform step 310 in FIG. 3, and perform standardization processing on the first CSI to obtain the second CSI, the first CSI being obtained based on measurement on the downlink signal, and the standardization processing being configured to convert the first CSI into CSI in a target format; and the processing module 510 is further configured to perform step 320, and perform compression on the second CSI to obtain the third CSI.

[0175] Optionally, the transceiver module 520 can be configured to send a third parameter, the third parameter being related to the standardization processing.

[0176] Optionally, the target format is predefined, the first CSI is based on a channel matrix representation, the CSI in the target format is based on a reference matrix representation, the second CSI is based on a target matrix representation, and the processing module 510 is specifically configured to determine a precoding matrix based on the channel matrix, and perform row transformation and / or column transformation on the precoding matrix based on the reference matrix to obtain the target matrix.

[0177] Optionally, the transceiver module 520 can be further configured to receive a first parameter, the first parameter being a parameter in a target formula, and different target formulas represented by different first parameters correspond to different target formats.

[0178] Optionally, the transceiver module 520 can be further configured to receive a second parameter, the second parameter being a parameter for constructing a calculation network, and different calculation networks constructed by different second parameters correspond to different target formats.

[0179] Optionally, the processing module 510 is specifically configured to obtain a fourth CSI based on the first CSI, the fourth CSI and the first CSI being different in sparsity, and perform standardization processing on the fourth CSI to obtain the second CSI.

[0180] In another possible design, the apparatus 500 can be configured to implement the function of the network device in the method embodiment shown in FIG. 3, or the apparatus 500 can include a unit for implementing any function or operation of the network device in the method embodiment shown in FIG. 3, and the unit can be implemented by software, hardware, firmware or any combination thereof, in whole or in part.

[0181] When the apparatus 500 is configured to implement the function of the network device in the method embodiment shown in FIG. 3, the transceiver module 520 (specifically, the receiving module) can be configured to perform step 330 in FIG. 3, receiving the third CSI and the third parameter, the third parameter being related to a standardization process for converting the first CSI into the CSI in the target format, the first CSI being obtained based on the measurement on the downlink signal; the processing module 510 is configured to decompress the third CSI to obtain the fifth CSI; and the processing module 510 is further configured to obtain the sixth CSI based on the third parameter and the fifth CSI.

[0182] Optionally, the transceiver module 520 is further configured to send the first parameter, the first parameter being a parameter in the target formula, and different parameters representing different target formulas corresponding to different target formats.

[0183] Optionally, the transceiver module 520 is further configured to send the second parameter, the second parameter being a parameter for constructing a computing network, and different parameters constructing different computing networks corresponding to different target formats.

[0184] Optionally, the target format is predefined, and the fifth CSI is based on a target matrix, and the processing module 510 is specifically configured to perform inverse transformation of row transformation and / or inverse transformation of column transformation on the target matrix based on the third parameter to obtain a precoding matrix.

[0185] Optionally, the processing module 510 is specifically configured to perform an inverse process of the standardization process on the fifth CSI based on the third parameter to obtain a seventh CSI, and obtain the sixth CSI based on the seventh CSI, the sparsity degrees of the seventh CSI and the sixth CSI being different.

[0186] For more detailed description of the processing module 510 and the transceiver module 520, please refer to the relevant description in the method embodiment shown in FIG. 3.

[0187] It should be noted that the transceiver module can also be referred to as a transceiver unit, a transceiver, a transceiver, or a transceiver device, etc. The processing module can also be referred to as a processor, a processing board, a processing unit, or a processing device, etc. Optionally, the transceiver module is configured to perform the sending operation and the receiving operation of the terminal device or the network device in the above method, and the device in the communication module for realizing the receiving function can be regarded as a receiving module, and the device in the communication module for realizing the sending function can be regarded as a sending module, that is, the transceiver module includes the receiving module and the sending module.

[0188] In addition, in a possible design, the foregoing transceiver module and / or processing module can be implemented by a virtual module, for example, the processing module can be implemented by a software function module or a virtual device, and the transceiver module can be implemented by a software function module or a virtual device. In another possible design, the processing module or the transceiver module can also be implemented by an entity device, for example, if the device is implemented by a chip / chip circuit, the transceiver module can be an input / output circuit and / or a communication interface, and is used for performing an input operation (corresponding to the foregoing receiving operation) and an output operation (corresponding to the foregoing sending operation); and the processing module is an integrated processor or a microprocessor or an integrated circuit.

[0189] It should be understood that the division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division, and another division manner can be used in actual implementation. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software function module.

[0190] FIG. 6 is another schematic block diagram of a communication device 600 provided by an embodiment of the present application. The device 600 can be a chip system, or can also be a device configured with a chip system and used for implementing the method embodiments. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0191] As shown in FIG. 6, the device 600 can include a processor 610, which can be used to execute a computer program or instruction in a memory, so as to implement the steps performed by a terminal or the steps performed by a network device in the method embodiments shown in FIG. 4.

[0192] Optionally, the device 600 further includes a communication interface 620. The communication interface 620 can be used for communicating with other devices through a transmission medium, so that the device 600 can communicate with other devices. The communication interface 620 can be, for example, a transceiver, an interface, a bus, a circuit or a device capable of realizing a transceiving function. The processor 610 can input and output data by using the communication interface 620, and is used for implementing the method in the embodiments shown in FIG. 3. Specifically, the device 600 can be used to implement the functions of the network device or the terminal in the method embodiments.

[0193] For example, when the device 600 is used to implement the method shown in FIG. 3, the processor 610 is used to implement the functions of the processing module 510, for example, to perform the steps 310 and 320 in FIG. 3, and the communication interface 620 is used to implement the functions of the transceiver module 520, for example, to perform the step 330 in FIG. 3.

[0194] Optionally, the apparatus 600 further includes at least one memory 630 for storing program instructions and / or data. The memory 630 is coupled to the processor 610. The coupling in the embodiments of the present application is indirect coupling or communication connection between apparatuses, units or modules, which can be electrical, mechanical or other forms, for information interaction between apparatuses, units or modules. The processor 610 can operate in cooperation with the memory 630. The processor 610 can execute program instructions stored in the memory 630. At least one of the at least one memory can be included in the processor.

[0195] It should be understood that the coupling in the embodiments of the present application is indirect coupling or communication connection between apparatuses, units or modules, which can be electrical, mechanical or other forms, for information interaction between apparatuses, units or modules. The processor 610 can operate in cooperation with the memory 630. The specific connection medium between the processor 610, the communication interface 620 and the memory 630 is not limited in the embodiments of the present application. In FIG. 6, the processor 610, the communication interface 620 and the memory 630 are connected through a bus 640. The connection mode between other components is only schematically illustrated, and is not limited. The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, only one thick line is used to represent the bus in FIG. 6, but it does not mean that there is only one bus or only one type of bus.

[0196] It should be understood that when the above communication apparatus 600 is a chip applied to a terminal, the chip implements the functions of the terminal in the above method embodiments. The chip of the terminal receives a signal from other modules (such as a radio frequency module or an antenna) in the terminal, and the signal can be sent by a network device to the terminal; or the chip of the terminal sends a signal to other modules (such as a radio frequency module or an antenna) in the terminal, and the signal can be sent by the terminal to the network.

[0197] When the above communication apparatus 600 is a chip applied to a network device, the chip implements the functions of the network device in the above method embodiments. The chip of the network device receives a signal from other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by a terminal to the network device; or the chip of the network device sends a signal to other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by the network device to the terminal.

[0198] It should be noted that when the communication apparatus 600 is a terminal or a network device, the communication interface 620 can be a transceiver, which can specifically include a transmitter and a receiver, the transmitter being configured to send signals, and the receiver being configured to receive signals. When the communication apparatus 600 is a chip applied to a terminal or a network device, the communication interface 620 can be an input / output circuit, a bus, a module, a pin, or other types of communication interface input / output circuits, wherein the input circuit in the input / output circuit can be configured to receive, and the output interface can be configured to send.

[0199] The present application also provides a computer program product, which comprises a computer program (also referred to as code or instructions), which, when executed, can implement the method described in the embodiment shown in FIG. 3 or FIG. 4.

[0200] The present application also provides a computer readable storage medium, which stores a computer program (also referred to as code or instructions). When the computer program is executed, the method described in the embodiment shown in FIG. 3 or FIG. 4 can be implemented.

[0201] The present application provides a communication system, which comprises a terminal and a network device as described above.

[0202] It should be understood that the processor in the embodiments of the present application can be an integrated circuit chip with a processing capability of signals. In the implementation process, each step of the above method embodiments can be completed by integrated logic circuits or instruction in the form of software in the processor. The processor described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the storage, and the processor reads the information in the storage, and combines the hardware to complete the steps of the above method.

[0203] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the system and method described herein is intended to include, but not be limited to, these and any other suitable types of memory.

[0204] The terms "unit", "module" and the like used in the specification can be used to represent a computer-related entity, hardware, firmware, a combination of hardware and software, software, or software in execution. The units and modules in the embodiments of the present application have the same meaning and can be used interchangeably.

[0205] Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. The choice of hardware or software, or combinations of both, would be dependent on the specific application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. In several embodiments provided in the present application, it will be apparent that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the described device embodiments are merely illustrative, and the division into units is merely a logical function division, and actual implementation can have another division, for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0206] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. can be located in one place or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0207] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit.

[0208] In the above embodiments, the functions of the various functional units can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, the software can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, digital video disc (DVD)), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0209] The functions, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make a contribution to the technology or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0210] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A channel state information feedback method, characterized by, The method comprises: standardizing first channel state information (CSI) to obtain second CSI, the first CSI being obtained based on measurement of a downlink signal, the standardization being used to convert the first CSI into CSI of a target format; compressing the second CSI to obtain third CSI.

2. The method of claim 1, wherein, The target format is predefined, the first CSI is based on a channel matrix representation, the CSI of the target format is based on a reference matrix representation, and the second CSI is based on a target matrix representation, the standardizing the first CSI to obtain second CSI comprising: determining a precoding matrix based on the channel matrix; performing row transformation and / or column transformation on the precoding matrix based on the reference matrix to obtain the target matrix.

3. The method of claim 1, wherein, The method further comprises: receiving first parameters, the first parameters being parameters in a target formula, different first parameters representing different target formulas corresponding to different target formats.

4. The method of claim 1, wherein, The method further comprises: receiving second parameters, the second parameters being parameters used to construct a calculation network, different second parameters constructing different calculation networks corresponding to different target formats.

5. The method of any one of claims 1 to 4, wherein, The standardizing the first CSI to obtain second CSI comprises: obtaining fourth CSI based on the first CSI, the fourth CSI and the first CSI being different in sparsity; standardizing the fourth CSI to obtain the second CSI.

6. The method of any one of claims 1 to 5, wherein, The method further comprises: sending third parameters, the third parameters being related to the standardization.

7. A channel state information feedback method, characterized by, The method comprises: receiving third channel state information (CSI) and third parameters, the third parameters being related to standardization used to convert first CSI into CSI of a target format, the first CSI being obtained based on measurement of a downlink signal; decompressing the third CSI to obtain fifth CSI; obtaining sixth CSI based on the third parameters and the fifth CSI.

8. The method of claim 7, wherein, The target format is predefined, the fifth CSI being based on a target matrix representation, and the obtaining sixth CSI based on the third parameters and the fifth CSI comprising: performing inverse row transformation and / or inverse column transformation on the target matrix based on the third parameters to obtain a precoding matrix.

9. The method of claim 7, wherein, The method further comprises: sending first parameters, the first parameters being parameters in a target formula, different parameters representing different target formulas corresponding to different target formats.

10. The method of claim 7, wherein, The method further comprises: sending second parameters, the second parameters being parameters used to construct a calculation network, different parameters constructing different calculation networks corresponding to different target formats.

11. The method of any one of claims 7 to 10, wherein, The obtaining sixth CSI based on the third parameters and the fifth CSI comprises: performing an inverse process of standardization on the fifth CSI based on the third parameters to obtain seventh CSI; obtaining the sixth CSI based on the seventh CSI, the seventh CSI and the sixth CSI being different in sparsity.

12. A communications device, characterized by comprising means for implementing the method of any one of claims 1 to 6, or comprising means for implementing the method of any one of claims 7 to 11.

13. A communications device, characterized by comprising a processor configured to invoke a computer program in a memory to cause the apparatus to implement the method of any one of claims 1 to 6, or to implement the method of any one of claims 7 to 11.

14. A computer-readable storage medium, characterized in that, The storage medium has stored therein a computer program or instructions, which, when executed by a computer, implement the method of any one of claims 1 to 6, or implement the method of any one of claims 7 to 11.

15. A computer program product, characterised in that, The computer program product comprises instructions, which, when executed by a computer, implement the method of any one of claims 1 to 6, or implement the method of any one of claims 7 to 11.

Images