Method for evaluating CSI feedback performance, network device, and terminal device
By using encoder and decoder to decode and encode CSI in network devices and terminal devices, the CSI feedback performance is directly evaluated, and the problem of CSI feedback performance evaluation in FDD mode is solved, and high accuracy and low transmission overhead are achieved. Evaluate the effect.
Patent Information
- Application Number
- PCT/CN2023/095152
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-18
- Publication Date
- 2024-11-21
AI Technical Summary
In FDD mode, it is difficult to directly evaluate the CSI feedback performance because the network equipment and terminal equipment are located on both sides of the base station and the UE, and cannot be directly compared. In addition, traditional methods require frequent transmission of CSI, resulting in large transmission overhead and increased delay.
By setting the encoder and decoder in network devices and terminal devices, the received CSI is decoded and encoded, and the CSI feedback performance is directly evaluated, frequent transmission of CSI, and the information difference between the encoder and the decoder is utilized. Evaluate CSI feedback performance.
The CSI feedback performance evaluation with high accuracy and low transmission overhead is achieved, reducing the computing power and power consumption requirements of terminal devices, avoiding frequent transmission of CSI, and improving the real-time and accuracy of evaluation.
Smart Images

Figure CN2023095152_21112024_PF_FP_ABST
Abstract
Description
CSI feedback performance evaluation method, network equipment, and terminal equipment Technical Field
[0001] The present application relates to the field of communications, and more specifically, to a method for evaluating CSI (Channel-State Information) feedback performance, a network device, a terminal device, a chip, a computer-readable storage medium, a computer program product, a computer program, and a communication system. Background Art
[0002] MIMO (multiple-in, multiple-out) technology plays a crucial role in both LTE (Long Term Evolution) and NR (New Radio) systems, and will continue to be a key enabling technology in future next-generation wireless communication systems. However, MIMO signal transmission performance depends heavily on the accuracy of CSI acquisition at the transmitter.
[0003] The use of autoencoder models to achieve high-precision CSI feedback in FDD (Frequency-division Duplex) mode has received widespread attention in academia in recent years and has begun to be studied and discussed within wireless standardization organizations. In this type of method, the UE (User Equipment) can use a pre-trained neural network encoder to convert the obtained CSI into indication information (bitstream) that can be fed back via the uplink channel. After receiving this indication information, the network device can use the corresponding trained neural network decoder to restore the indication information to CSI information. The closer the CSI recovered by the network device is to the CSI obtained by the UE, the better the performance of the neural network model. However, because the CSI recovered by the network device and the CSI obtained by the UE are located on the base station and UE sides respectively, a direct comparison cannot be made. It is necessary to consider how to evaluate the performance of CSI feedback without introducing significant transmission overhead.
[0004] Summary of the Invention
[0005] This embodiment of the present application provides a method for evaluating CSI feedback performance, including:
[0006] The network device processes the first CSI based on the first encoder to obtain first CSI feedback information; the first CSI is obtained by the network device processing second CSI feedback information received from the terminal device based on the first decoder; the second CSI feedback information is obtained by the terminal device processing the second CSI obtained by measurement based on the reference signal based on the first encoder;
[0007] The network device evaluates CSI feedback performance based on the first CSI feedback information.
[0008] This embodiment of the present application provides a method for evaluating CSI feedback performance, including:
[0009] The terminal device processes, based on the first encoder, the second CSI obtained by measuring the reference signal to obtain second CSI feedback information;
[0010] The terminal device sends second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder, so as to process the first CSI based on the first encoder to obtain the first CSI feedback information, and then evaluate the CSI feedback performance based on the first CSI feedback information.
[0011] An embodiment of the present application provides a network device, including:
[0012] a first processing module, configured to process the first CSI based on the first encoder to obtain first CSI feedback information; the first CSI is obtained based on the first decoder processing second CSI feedback information received from the terminal device; the second CSI feedback information is obtained by the terminal device processing the second CSI obtained by measurement based on the reference signal based on the first encoder;
[0013] The first processing module is further configured to evaluate CSI feedback performance based on the first CSI feedback information.
[0014] An embodiment of the present application provides a terminal device, including:
[0015] A second processing module, configured to process, based on the first encoder, second CSI obtained by measuring the reference signal to obtain second CSI feedback information;
[0016] The seventh communication module is used to send second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder and evaluate the CSI feedback performance based on the first CSI feedback information.
[0017] An embodiment of the present application provides a network device, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and execute the computer program stored in the memory to enable the network device to perform the above-mentioned CSI feedback performance evaluation method.
[0018] An embodiment of the present application provides a terminal device, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and execute the computer program stored in the memory to enable the network device to perform the above-mentioned CSI feedback performance evaluation method.
[0019] An embodiment of the present application provides a chip for implementing the above-mentioned CSI feedback performance evaluation method.
[0020] Specifically, the chip includes: a processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned CSI feedback performance evaluation method.
[0021] An embodiment of the present application provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a device, the device executes the above-mentioned CSI feedback performance evaluation method.
[0022] An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned CSI feedback performance evaluation method.
[0023] An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned CSI feedback performance evaluation method.
[0024] In an embodiment of the present application, a first encoder is provided in the network device, which performs at least one decoding and encoding process on the received second CSI, and evaluates the CSI feedback performance based on the information generated by the complete decoding and encoding process. Since the evaluation is performed directly based on the relevant information obtained by the encoder and decoder, rather than indirectly using the system transmission performance, it has higher accuracy. At the same time, since the network device and the terminal device do not need to transmit CSI during each performance evaluation, the transmission overhead can be effectively controlled. In addition, there is no need for the terminal device to consume excessive computing power and power consumption for model performance evaluation, thereby avoiding increasing the capability requirements of the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application.
[0026] FIG2 is a schematic diagram of the basic process of CSI acquisition under frequency division duplexing.
[0027] FIG3 is a basic architecture diagram of a CSI feedback method based on an autoencoder model.
[0028] FIG4 is a schematic flowchart of a method for evaluating CSI feedback performance according to an embodiment of the present application.
[0029] FIG5 is a schematic flowchart of a method for evaluating CSI feedback performance according to another embodiment of the present application.
[0030] FIG6 is a schematic flowchart of a method for evaluating CSI feedback performance according to yet another embodiment of the present application.
[0031] FIG7 is a schematic flowchart of a method for evaluating CSI feedback performance according to yet another embodiment of the present application.
[0032] FIG8 is a schematic diagram of a first method for triggering CSI feedback model performance monitoring in the first application example of the present application.
[0033] FIG9 is a schematic diagram of a second method for triggering CSI feedback model performance monitoring in the first application example of the present application.
[0034] FIG10 is a schematic diagram of implementing CSI feedback model performance monitoring in Application Example 1 of the present application.
[0035] FIG11 is a schematic diagram of a first processing method based on performance monitoring results in the first application example of the present application.
[0036] FIG12 is a schematic diagram of a second processing method based on performance monitoring results in the first application example of the present application.
[0037] FIG13 is a schematic diagram of a first method for triggering CSI feedback model performance monitoring in the second application example of the present application.
[0038] FIG14 is a schematic diagram of a second method for triggering CSI feedback model performance monitoring in the second application example of the present application.
[0039] FIG15A is a schematic diagram of a first method for implementing CSI feedback model performance monitoring in the second application example of the present application.
[0040] FIG15B is a schematic diagram of a second method for implementing CSI feedback model performance monitoring in the second application example of the present application.
[0041] FIG16 is a schematic block diagram of a network device according to an embodiment of the present application.
[0042] FIG17 is a schematic block diagram of a network device according to another embodiment of the present application.
[0043] FIG18 is a schematic block diagram of a network device according to yet another embodiment of the present application.
[0044] FIG19 is a schematic block diagram of a network device according to another embodiment of the present application.
[0045] FIG20 is a schematic block diagram of a network device according to another embodiment of the present application.
[0046] FIG21 is a schematic block diagram of a network device according to another embodiment of the present application.
[0047] FIG22 is a schematic block diagram of a network device according to another embodiment of the present application.
[0048] Figure 23 is a schematic block diagram of a terminal device according to an embodiment of the present application.
[0049] Figure 24 is a schematic block diagram of a communication device according to an embodiment of the present application.
[0050] Figure 25 is a schematic block diagram of a chip according to an embodiment of the present application.
[0051] Figure 26 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION
[0052] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0053] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.
[0054] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) and other terminal-to-terminal direct communications, and the embodiments of the present application can also be applied to these communication systems.
[0055] In one embodiment, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.
[0056] In one embodiment, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.
[0057] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
[0058] The terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.
[0059] In the embodiments of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.) or underwater (such as submarines, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).
[0060] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a terminal device in the personal internet of things (PIoT), a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
[0061] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.
[0062] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.
[0063] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.
[0064] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
[0065] FIG1 exemplarily illustrates a communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one possible implementation, the communication system 100 may include multiple network devices 110, and each network device 110 may include a different number of terminal devices 120 within its coverage area, which is not limited in this embodiment of the present application.
[0066] In one possible implementation, the communication system 100 may further include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which is not limited in this embodiment of the present application.
[0067] Among them, the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment. The access network equipment can be an evolutionary base station (evolutional node B, abbreviated as eNB or e-NodeB) macro base station, micro base station (also called "small base station"), pico base station, access point (AP), transmission point (TP) or new generation base station (new generation Node B, gNodeB), etc. in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.
[0068] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system shown in Figure 1 as an example, the communication device may include a network device and a terminal device having a communication function. The network device and the terminal device may be specific devices in the embodiments of the present application and will not be described in detail here. The communication device may also include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.
[0069] To facilitate understanding of the embodiments of the present application, the following briefly describes the basic processes and basic concepts involved in the embodiments of the present application. It should be understood that the basic processes and basic concepts introduced below do not limit the embodiments of the present application.
[0070] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.
[0071] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.
[0072] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.
[0073] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.
[0074] (1) CSI Feedback Mechanism in Cellular Communication Systems
[0075] In a cellular communication system, the specific way in which a network device (taking a base station as an example) obtains CSI varies depending on the duplex communication mode adopted. Specifically, in the TDD (Time-division Duplex) mode, since both the uplink and downlink links operate on the same frequency, the base station can use the channel reciprocity between the uplink and downlink channels to obtain CSI, that is, the base station can directly estimate the CSI that can be used to guide downlink data transmission based on the uplink RS (Reference Signal) sent by the UE. The uplink RS is, for example, the SRS (Sounding Reference Signal). In comparison, in the FDD (Frequency-division Duplex) mode, since the uplink and downlink links operate on different frequencies, the base station cannot use channel reciprocity to directly estimate the downlink CSI based on the uplink RS, so the acquisition of CSI will be much more complicated. First, the base station will configure and send some RSs for the UE to complete CSI measurement, such as SSB (Synchronization Signal Block) or CSI-RS (Channel-State Information Reference Signal). The UE then completes channel estimation by measuring the RS and feeds back CSI information to the base station, allowing the base station to configure a reasonable and efficient data transmission method based on the current channel conditions.
[0076] In the NR system, multiple codebooks are standardized to enable the UE to feed back CSI to the base station, such as Type 1, Type 2, and enhanced Type 2. The UE finds the codeword in the codebook that best matches the CSI to be fed back and feeds the corresponding index back to the base station via the uplink. The base station then uses the same codebook to recover the CSI using the index. Figure 2 shows the basic CSI acquisition process in FDD.
[0077] (2) Autoencoder model
[0078] An autoencoder is a type of artificial neural network model that learns the implicit features of input data, known as encoding, and uses these learned features to reconstruct the original input data, known as decoding. More intuitively, an autoencoder typically consists of an encoder and decoder pair. The encoder compresses the input information, producing robust and concise compressed information; the decoder, based on this compressed information, restores the input information as accurately as possible.
[0079] The optimization and training process of an autoencoder aims to ensure that the decoder model's output is as consistent as possible with the encoder model's input, while constraining the size of the compressed information. Unlike traditional approaches, the compressed information output by the encoder model lacks explicit meaning and is difficult to interpret outside of the decoder model.
[0080] (3) CSI feedback method based on AI (Artificial Intelligence) technology
[0081] In the related art, it is proposed to use an autoencoder model to achieve high-precision CSI feedback in FDD mode. Figure 3 shows the basic architecture diagram of the CSI feedback method based on the autoencoder model. Among them, the UE can use a pre-trained neural network encoder to convert the obtained CSI information into indication information (also called CSI feedback information, specifically a bit stream) that can be fed back through the uplink channel. After the base station receives the indication information, it can use the corresponding trained neural network decoder to restore the indication information to CSI information. The closer the CSI recovered by the base station is to the CSI obtained by the UE, the better the performance of the neural network model.
[0082] For traditional CSI feedback schemes in FDD modes, current wireless communication systems primarily rely on theoretical modeling of actual communication environments to construct sufficiently sophisticated codebooks. However, as requirements for wireless communication system flexibility, adaptability, and system capacity continue to increase, the gains offered by wireless communication system design and optimization approaches based on classical mathematical models are gradually diminishing. It is necessary to adopt new approaches and methods, such as data-driven AI technology, combined with traditional theories and system design methods, to overcome existing bottlenecks and further enhance wireless system performance.
[0083] The AI-based CSI feedback solution has higher feedback accuracy and lower feedback overhead compared to traditional CSI acquisition solutions because it utilizes the powerful nonlinear fitting, compression, and recovery capabilities of neural networks. However, since AI-based CSI feedback is essentially a data-driven black box technology, its generalization and interpretability are not as good as traditional solutions. Specifically, the AI model will achieve good performance for familiar scenarios (i.e., scenarios that have been encountered or similar during the training phase), but it cannot guarantee performance for unfamiliar scenarios, and the feedback accuracy may even be significantly weaker than traditional solutions. Therefore, it is particularly important to monitor and evaluate the feedback performance of the CSI feedback solution based on the AI model.
[0084] Due to the particularity of the CSI feedback problem, the most direct way to evaluate feedback performance is to compare the difference between the CSI obtained by feedback and the ideal CSI. However, since the two are located on the base station and UE sides respectively, direct comparison cannot be performed. In related technologies, two types of solutions are proposed:
[0085] Monitoring through intermediate results (intermediate KPIs): For example, using indicators such as cosine similarity and normalized mean square error between the feedback-recovered CSI and the ideal CSI. The advantage of this type of method is that it can accurately and intuitively monitor the performance of the CSI feedback model, but it also comes at a high cost. If the performance monitoring is completed by the base station, the UE needs to upload the ideal CSI required for each monitoring to the base station as losslessly as possible in some way. Each monitoring will occupy a large amount of uplink transmission resources and introduce delays. If the performance monitoring is completed on the UE side, the base station needs to send the feedback CSI itself or the decoder model to the UE in some way. The former will introduce downlink transmission resource loss and delays for each monitoring. The latter places higher demands on the UE's capabilities and will result in greater power consumption because the complexity of the decoder model is much higher than that of the encoder model.
[0086] Monitoring system performance indicators (eventual KPIs) such as data transmission rate and packet reception success rate. This approach suffers from significant latency, making it difficult to immediately detect performance issues with the CSI feedback model, which can negatively impact network communication performance. It also suffers from difficulty locating the problem. Many factors can potentially impact indirect communication metrics, and degradation of the CSI feedback model is just one of them. If the cause is misdiagnosed, updating or replacing the CSI feedback model, or reverting to traditional solutions, will be ineffective.
[0087] The technical solutions of the embodiments of the present application are mainly intended to solve at least one of the above technical problems.
[0088] FIG4 is a schematic flowchart of a method for evaluating CSI feedback performance according to an embodiment of the present application. The method may optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.
[0089] S410. The network device processes the first CSI based on the first encoder to obtain first CSI feedback information. The first CSI is obtained by the network device processing second CSI feedback information received from the terminal device based on the first decoder; the second CSI feedback information is obtained by the terminal device processing second CSI obtained by measurement based on a reference signal based on the first encoder, i.e., the first encoder is used in the terminal device to process the second CSI to obtain the second CSI feedback information.
[0090] S420: The network device evaluates CSI feedback performance based on the first CSI feedback information.
[0091] In practical applications, the first encoder and the first decoder constitute an auto-encoding model. The first encoder can be deployed in a terminal device. After the terminal device obtains the CSI based on the measurement of the reference signal, the terminal device can use the first encoder to encode the CSI to obtain CSI feedback information. The first decoder can be deployed in a network device, and is used by the network device to decode the CSI feedback information sent by the terminal device to recover the corresponding CSI. According to an embodiment of the present application, the network device also includes a first encoder. The first encoder in the network device can be pre-configured or determined based on information related to the first encoder reported by the terminal device.
[0092] In the embodiment of the present application, the second CSI is CSI obtained by the terminal device based on measurement of a reference signal. For example, the reference signal may include an SSB, a CSI-RS, or another RS, i.e., the second CSI may be CSI determined by the terminal device by measuring the SSB, CSI-RS, or another RS.
[0093] In an embodiment of the present application, the second CSI feedback information is obtained by the terminal device processing the second CSI based on the first encoder, that is, the second CSI feedback information is the encoding result of the second CSI. Optionally, the second CSI feedback information is a bit stream (bitmap, which may also be referred to as a bitmap, bitmap, etc.). In actual applications, the terminal device may send the second CSI feedback information to the network device. It can be understood that the second CSI feedback information is an indication information for feedback on the second CSI, which is used to enable the network device to be aware of the current channel conditions in order to configure a reasonable and efficient data transmission method.
[0094] In the embodiment of the present application, the first CSI is obtained by the network device processing the second CSI feedback information based on the first decoder, that is, the first CSI is the decoding result of the second CSI feedback information. It can be understood that the first CSI and the second CSI have the same data structure, and the better the CSI feedback performance (that is, the better the performance of the autoencoder model), the closer the first CSI is to the second CSI. In actual applications, the network device can configure the data transmission method based on the decoded first CSI.
[0095] In an embodiment of the present application, the network device processes the first CSI based on the first encoder to obtain the first CSI feedback information. That is, the first CSI feedback information is the encoding result of the first CSI. Specifically, the first CSI feedback information can be understood as the result of decoding and re-encoding the second CSI feedback information. Therefore, the first CSI feedback information and the second CSI feedback information have the same data structure. For example, both can be bitstreams. It is understandable that the better the CSI feedback performance (that is, the better the performance of the autoencoding model), the closer the first CSI feedback information is to the second CSI feedback information.
[0096] It should be noted that, in some embodiments, the step of the network device decoding the second CSI feedback information into the first CSI and the step of encoding the first CSI into the first CSI feedback information may be interrelated. Exemplarily, each time the network device decodes and obtains the first CSI, it encodes the first CSI into the first CSI feedback information to perform real-time evaluation of the CSI feedback performance. In other embodiments, the step of the network device decoding the second CSI feedback information into the first CSI and the step of encoding the first CSI into the first CSI feedback information may be decoupled. Exemplarily, each time the network device decodes and obtains the first CSI, it uses the first CSI to configure the data transmission mode and stores the first CSI; when certain conditions are met to trigger the CSI feedback performance evaluation, the first CSI is encoded into the first CSI feedback information for use in evaluating the CSI feedback performance.
[0097] It can be understood that in the embodiment of the present application, the CSI feedback performance is related to the performance of the first encoder and the performance of the first decoder. Evaluating the CSI feedback performance can also be understood as evaluating the performance of the first encoder and / or evaluating the performance of the first decoder.
[0098] Optionally, in the embodiments of the present application, evaluating CSI feedback performance may include performing a qualitative or quantitative evaluation of CSI feedback performance. For example, the network device may evaluate whether CSI feedback meets requirements or determine relevant indicators used to characterize CSI feedback performance. In other words, CSI feedback performance in the embodiments of the present application may refer to whether CSI feedback meets requirements or to relevant indicators of CSI feedback.
[0099] It can be seen that in the above-mentioned CSI feedback performance evaluation method, in the embodiment of the present application, a first encoder is provided in the network device, which completes at least one decoding and encoding process for the received second CSI, and evaluates the CSI feedback performance based on the information output by the complete decoding and encoding process. Since the evaluation is performed directly based on the relevant information obtained by the encoder and decoder, rather than indirectly evaluated with the help of the system transmission performance, it has higher accuracy. At the same time, since there is no need for the network device and the terminal device to transmit CSI during each performance evaluation, the transmission overhead can be effectively controlled. In addition, there is no need for the terminal device to consume excessive computing power and power consumption for model performance evaluation, thereby avoiding increasing the capability requirements of the terminal device.
[0100] In some embodiments, step S420, wherein the network device evaluates CSI feedback performance based on the first CSI feedback information, may include: the network device determining a first indicator based on the first CSI feedback information and the second CSI feedback information, where the first indicator is used to characterize the CSI feedback performance. According to this embodiment, the indicator can be calculated based on the first CSI feedback information and the second CSI feedback information to quantitatively and accurately reflect the CSI feedback performance.
[0101] Optionally, the first indicator is related to the difference and / or similarity between the first CSI feedback information and the second CSI feedback information. In other words, the first indicator may reflect a comparison result between the first CSI feedback information and the second CSI feedback information.
[0102] Figure 5 shows a schematic flow chart of the method for evaluating the CSI feedback performance in this embodiment. According to the process shown in Figure 5, when the CSI feedback model (including the first encoder and the first decoder) has high feedback accuracy, the first CSI recovered by the network side is highly consistent with the original CSI (i.e., the second CSI) fed back by the UE side. Therefore, the first CSI is re-encoded using the encoder model, and the first CSI feedback information obtained should be highly consistent with the second CSI feedback information received by the network side. When the feedback accuracy of the CSI feedback model is poor, the first CSI recovered by the network side is greatly different from the second CSI fed back by the UE side. Therefore, the first CSI recovered by the network side is re-encoded using the first encoder, and the first CSI feedback information obtained should be greatly different from the second CSI feedback information received by the network side. By adopting a first indicator related to the difference and / or similarity between the first CSI feedback information and the second CSI feedback information, the CSI feedback performance can be accurately reflected.
[0103] Optionally, the first indicator includes at least one of the following:
[0104] A ratio between the number of error bits in the N bits of the first CSI feedback information and N; wherein the error bit is a bit corresponding to the same bit position but having different values in the first CSI feedback information and the second CSI feedback information;
[0105] The number of error bits;
[0106] a mean square error between the first CSI feedback information and the second CSI feedback information;
[0107] a normalized mean square error between the first CSI feedback information and the second CSI feedback information;
[0108] a Euclidean distance between the first CSI feedback information and the second CSI feedback information;
[0109] a Hamming distance between the first CSI feedback information and the second CSI feedback information;
[0110] The cosine similarity between the first CSI feedback information and the second CSI feedback information.
[0111] Exemplarily, the first indicator may include the number of error bits or the ratio of the number of error bits to N, thereby directly reflecting the difference between the first feedback information and the second feedback information. If the value of the i-th bit in the first CSI feedback information is different from the value of the i-th bit in the second CSI feedback information, then the i-th bit in the first CSI feedback information is an error bit.
[0112] For example, the first CSI feedback information and the second CSI feedback information both contain 8 bits, where the first CSI feedback information is 11101110 and the second CSI information is 11101111. Then, the value of the 8th bit in the first CSI feedback information and the value of the 8th bit in the second CSI feedback information are different. The 8th bit is an error bit, the number of error bits is 1, and the ratio of the number of error bits to the number of bits N in the first feedback information is 1 / 8. It can be understood that this ratio can also be called the error bit rate.
[0113] For example, the first indicator may include a mean square error (MSE) or a normalized mean square error (NMEE) between the first CSI feedback information and the second CSI feedback information, reflecting the overall difference between the first feedback information and the second feedback information. Errors may be calculated for each bit in the first CSI feedback information and each bit in the second CSI feedback information, thereby obtaining a set of errors. The MSE or the normalized error is determined based on the set of errors.
[0114] Exemplarily, the first indicator may include the Euclidean distance, the Hamming distance, or the cosine similarity between the first feedback information and the second feedback information, reflecting the similarity between the first feedback information and the second feedback information.
[0115] For example, the first metric may include the number of error bits, mean squared error, and Euclidean distance, combining different types of metrics to comprehensively evaluate CSI feedback performance. It is understood that in actual applications, the first metric may be implemented in other ways, specifically based on different application scenarios or according to protocol or system specifications.
[0116] Optionally, in this embodiment of the present application, the network device may evaluate CSI feedback performance based on a set of CSI feedback information corresponding to a single received CSI (a set of CSI feedback information includes the received CSI feedback information and CSI feedback information obtained through decoding and re-encoding), or may evaluate CSI feedback performance based on multiple sets of CSI feedback information corresponding to multiple CSIs. When evaluating CSI feedback performance based on multiple sets of CSI feedback information, a first indicator may be determined based on each set of CSI feedback information, and then an average of the first indicators corresponding to each set may be taken to evaluate CSI feedback performance.
[0117] Optionally, the network device may also evaluate CSI feedback performance by comparing CSI. Specifically, in some embodiments, step S420, in which the network device evaluates CSI feedback performance based on the first CSI feedback information, may include: the network device processing the first CSI feedback information based on the first decoder to obtain third CSI; and the network device determining a second indicator based on the first CSI and the third CSI, where the second indicator is used to characterize the CSI feedback performance.
[0118] Figure 6 shows a schematic flow chart of the method for evaluating CSI feedback performance in this embodiment. According to the process shown in Figure 6, it can be understood that when the CSI feedback model (including the first encoder and the first decoder) has high feedback accuracy, the third CSI recovered by the network side is highly consistent with the first CSI recovered for the first time. When the feedback accuracy of the CSI feedback model is poor, the third CSI recovered by the network side is significantly different from the first CSI recovered for the first time. Therefore, the second indicator determined based on the first CSI and the third CSI can accurately reflect the CSI feedback performance.
[0119] Optionally, this embodiment and the aforementioned embodiment of determining the first indicator may be implemented independently or in combination, that is, the CSI feedback performance may be evaluated based on a single indicator or in combination with multiple indicators.
[0120] Similarly, the setting of the second indicator may refer to the setting of the first indicator in the aforementioned embodiment. For example, the second indicator may be related to the difference and / or similarity between the first CSI and the third CSI. Furthermore, the second indicator may also include at least one of the mean square error, normalized mean square error, Euclidean distance, Hamming distance, and cosine distance between the first CSI and the third CSI, which is not limited in this application.
[0121] According to the concept of the above embodiment, re-encoding and / or re-decoding may also be performed based on the third CSI, and the information obtained by the re-encoding and / or re-decoding may be used to evaluate the CSI feedback performance. It is understood that the technical solutions obtained by configuring re-encoding and / or re-decoding are all variations or replacements of the above embodiments of the present application and should be covered by the scope of protection of this application.
[0122] Corresponding to the above method, FIG7 is a schematic flowchart of a method for evaluating CSI feedback performance according to another embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes:
[0123] S710. The terminal device processes, based on the first encoder, second CSI obtained by measuring the reference signal to obtain second CSI feedback information.
[0124] S720. The terminal device sends second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder, so as to process the first CSI based on the first encoder to obtain the first CSI feedback information, and then evaluate the CSI feedback performance based on the first CSI feedback information.
[0125] It can be understood that the terminal device can send second CSI feedback information to the network device when the second CSI is obtained based on the measurement of the reference signal. The second CSI feedback information can be used by the network device to understand the current channel situation and can also be used by the network device to evaluate the CSI feedback performance.
[0126] Optionally, after evaluating the CSI feedback performance, the network device may adopt one or more further processing methods.
[0127] Exemplarily, in some embodiments, the above method may further include: the network device sends first indication information to the terminal device; wherein the first indication information is used to indicate CSI feedback performance.
[0128] According to this embodiment, the network device may indicate the CSI feedback performance by sending the first indication information, and the terminal device may determine whether to take action.
[0129] Correspondingly, from the perspective of the terminal device, the above method may further include: the terminal device receives first indication information from the network device; wherein the first indication information is used to indicate CSI feedback performance.
[0130] Optionally, the first indication information is used to indicate a third indicator, which is used to characterize CSI feedback performance. Exemplarily, the third indicator may include the first indicator and / or the second indicator. That is, the network device may send specific values of the relevant indicators to the terminal device, which then determines whether the CSI feedback performance meets requirements and whether to take action.
[0131] Optionally, the first indication information is used to indicate whether the CSI feedback performance meets a preset condition. In any embodiment of the present application, the preset condition may be that the first CSI feedback information is the same as the second CSI feedback information, or that the first CSI is the same as the third CSI, etc. The preset condition may also be related to a third indicator and a corresponding threshold, wherein the third indicator may include the above-mentioned first indicator and / or second indicator. For example, the preset condition may be that an indicator of the similarity class in the third indicator is greater than or equal to a first threshold, or an indicator of the error class in the third indicator is less than or equal to a second threshold, etc.
[0132] It should be noted that the first indication information may also simultaneously indicate whether the third indicator and the CSI feedback performance meet the preset conditions, so that the terminal device can directly obtain comprehensive information related to the CSI feedback performance.
[0133] In some embodiments, the above method may further include:
[0134] When the CSI feedback performance does not meet the preset conditions, the network device sends second indication information to the terminal device; wherein the second indication information is used to instruct the terminal device to perform predetermined processing on the first encoder.
[0135] Optionally, when the CSI feedback performance does not meet the preset condition, the network device may send only the second indication information, or send both the first indication information and the second indication information.
[0136] Accordingly, from the perspective of the terminal device, the above method may further include:
[0137] When the terminal device receives the second indication information from the network device, it determines that the CSI feedback performance does not meet the preset conditions and performs predetermined processing on the first encoder.
[0138] Optionally, the predetermined processing includes one of the following:
[0139] Switching to use other encoders except the first encoder among Z encoders of the terminal device, where Z is an integer greater than 1;
[0140] updating the first encoder;
[0141] Fine-tune the first encoder; fine-tuning means training it on a new dataset to get better performance.
[0142] The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
[0143] The Z encoders may be all or part of the encoders configured in the terminal device. For example, the terminal device may have K encoders, and the network device may configure the terminal device to switch among the Z encoders, or in other words, the network device may activate Z encoders, i.e., Z may be less than or equal to K.
[0144] Optionally, the fifth CSI may be the CSI obtained by the terminal device based on the measurement of the reference signal after receiving the second indication information, that is, the network device instructs the terminal device to fall back to using the codebook to process the CSI obtained subsequently based on the measurement of the reference signal.
[0145] In some embodiments, the above method further includes: the network device continues to use the first encoder when the CSI feedback performance meets the preset conditions. That is, the network device may not perform any related processing on the first encoder. Optionally, the network device may send the first indication information to the terminal device, or may not send the first indication information to the terminal device, that is, take no action. It is understood that the network device can continuously monitor and evaluate the CSI feedback performance, and indicate the terminal device when the assessment determines that the CSI feedback performance does not meet the conditions, and not indicate the terminal device when the assessment determines that the CSI feedback performance meets the conditions.
[0146] The following is an exemplary description of the implementation of configuring the first encoder and the first decoder in the embodiment of the present application.
[0147] In one embodiment, the first encoder and the first decoder may be configured by a network device. Accordingly, the above method may further include: the network device sending fourth indication information to the terminal device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
[0148] Correspondingly, from the perspective of the terminal device, the above method may further include: the terminal device receives fourth indication information from the network device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
[0149] As an example but not a limitation, the fourth indication information may be carried by an RRC (Radio Resource Control) message, broadcast configuration information, MAC CE (MAC Control Element) or DCI (Downlink Control Information).
[0150] Exemplarily, the relevant information of the first encoder may include information such as an ID (Identifier) and parameters of the first encoder, so that the terminal device can configure the first encoder in the terminal device based on the relevant information.
[0151] According to this embodiment, the first encoder and the first decoder are both provided by the network device, and the network device sends and configures the encoder to the terminal device, thereby ensuring alignment of model information in the terminal device and the network device.
[0152] In one embodiment, the first encoder is pre-configured in the terminal device, and the first decoder is pre-configured in the network device. The terminal device and the network device can align the model information by transmitting information. That is, for the terminal device, the first encoder is pre-configured, and the terminal device can send relevant information of the first encoder to the network device. For the network device, the first decoder is pre-configured, and the first encoder can be determined based on the relevant information sent by the terminal device. In actual applications, the first encoder and / or the first decoder can be pre-defined or obtained through third-party channels or protocols. This application does not limit the pre-configuration method of the first encoder and / or the first decoder.
[0153] The following is an exemplary description of the implementation method of triggering the evaluation of CSI feedback performance in the embodiment of the present application.
[0154] In one embodiment, the CSI feedback performance evaluation is triggered by a network device. Specifically, before the network device processes the first channel state information (CSI) based on the encoder to obtain the first CSI feedback information, the CSI feedback performance evaluation method further includes: the network device sending third indication information to the terminal device; wherein the third indication information is used to trigger the CSI feedback performance evaluation. In other words, the third indication information is used to request or notify the CSI feedback performance evaluation.
[0155] Optionally, the third indication information can also be used to instruct the terminal device to send information related to evaluating CSI feedback performance. For example, when the network device is not configured with the first encoder, the third indication information can also be used to instruct the terminal device to report relevant information of the first encoder.
[0156] Optionally, the method may further include: upon receiving third indication information from the network device, the terminal device sends first reporting information to the network device. Accordingly, after the network device sends the first indication information to the terminal device, the method may further include: the network device receives the first reporting information from the terminal device.
[0157] The first reporting information is used to indicate at least one of the following:
[0158] Whether to agree to evaluate the CSI feedback performance;
[0159] Information about the first encoder;
[0160] First assessment cycle;
[0161] a type of a fourth indicator, the fourth indicator being used to characterize CSI feedback performance;
[0162] The first indicator threshold.
[0163] The first evaluation period may be a period for evaluating CSI feedback performance that the terminal device expects. In practical applications, this period may be greater than or equal to the CSI feedback period. For example, CSI may be fed back every 10 ms (milliseconds), and CSI feedback performance may be evaluated every 100 ms based on ten CSI feedbacks within that 100 ms.
[0164] Exemplarily, the type of the fourth indicator is the type of indicator desired by the terminal device for characterizing CSI feedback performance. The fourth indicator may be the same as or different from the third indicator in the aforementioned embodiment. Optionally, the type of the fourth indicator includes at least one of bit error rate, number of error bits, mean square error, normalized mean square error, Euclidean distance, Hamming distance, and cosine similarity.
[0165] Exemplarily, the first indicator threshold may be a threshold expected by the terminal device for determining whether the CSI feedback performance meets a preset condition. The first indicator threshold may be related to an indicator used to characterize the CSI feedback performance, for example, the first indicator threshold may be a threshold for an error bit rate, a threshold for a mean square error, or the like.
[0166] Exemplarily, the first reporting information may include whether the evaluation of CSI feedback performance is agreed to and related information of the first encoder. For example, if the first encoder is pre-configured in the terminal device, and the network device needs to request the evaluation of CSI feedback performance through the third indication information, the terminal device may accordingly indicate in the first reporting information whether it agrees to evaluate the CSI feedback performance. If the evaluation of the CSI feedback performance is agreed to, the terminal device may further indicate related information of the first encoder in the first reporting information, so that the network device can configure the first encoder in the network device.
[0167] Exemplarily, the first reporting information may include the first evaluation period, the type of the fourth indicator, or the first indicator threshold value desired by the terminal device. For example, the terminal device reports the first evaluation period, the type of the fourth indicator, or the first indicator threshold value based on its own capabilities. The network device evaluates the CSI feedback performance based on the first reporting information, thereby adjusting the evaluation results based on the terminal device capabilities. Specifically, the frequency of switching, updating, and fine-tuning the encoder model may be coordinated based on the terminal device capabilities.
[0168] Optionally, the first reporting information may be carried by a first RRC message, UCI (Uplink Control Information) or PUSCH (Physical Uplink Shared Channel).
[0169] Optionally, the third indication information may be carried by a second RRC message, MAC CE or DCI.
[0170] In one embodiment, the CSI feedback performance evaluation is triggered by the terminal device. Specifically, the above method may further include: the terminal device sending second reporting information to the network device; wherein the second reporting information is used to trigger the CSI feedback performance evaluation.
[0171] Accordingly, from the perspective of the network device, before the network device processes the first channel state information CSI based on the encoder to obtain the first CSI feedback information, the above method may also include the network device receiving second reporting information from the terminal device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
[0172] Exemplarily, the second reporting information is used to indicate at least one of the following:
[0173] Information about the first encoder;
[0174] Second assessment cycle;
[0175] The type of the fifth indicator, which is used to characterize the CSI feedback performance;
[0176] Second indicator threshold.
[0177] The configuration of the second reporting information may refer to the configuration of the first reporting information in the aforementioned embodiment. For example, the second evaluation period may be the period for evaluating CSI feedback performance that the terminal device expects, the type of the fourth indicator may be the type of indicator that the terminal device expects to be used to characterize CSI feedback performance, and the second indicator threshold may be the threshold that the terminal device expects to be used to determine whether the CSI feedback performance meets a preset condition. The difference between the second reporting information and the first reporting information is that the second reporting information initiated by the terminal device does not need to carry whether it agrees to evaluate the CSI feedback performance. The relevant technical details of other information can be referred to the aforementioned description and will not be repeated here.
[0178] Optionally, the second reporting information may be carried by an RRC message, UCI or PUSCH.
[0179] It should be noted that, in the embodiment of the present application, triggering the evaluation of CSI feedback performance may refer to triggering one or more evaluations of CSI feedback performance. For example, after the network device triggers the evaluation of CSI feedback performance and causes the terminal device to report relevant information of the first encoder, or after the terminal device actively reports relevant information of the first encoder, the network device may periodically perform multiple evaluations of CSI feedback performance. That is, the terminal device only uploads the encoder model once, and can support an unlimited number of subsequent CSI feedback performance monitoring and evaluations. Compared with each evaluation requiring the terminal device or network device to transmit CSI to the opposite side, the embodiment of the present application can significantly reduce the occupancy of transmission resources.
[0180] Optionally, the embodiment of the present application also supports feedback performance evaluation of each encoder / decoder in the case of multiple encoders and / or multiple decoders.
[0181] In some embodiments, when multiple decoders are deployed, the above-described method can be used to evaluate the feedback performance of each decoder. Specifically, the above-described first decoder is the i-th decoder among M decoders, where M is an integer greater than 1 and i is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the i-th decoder. That is, when M decoders are deployed, for the performance evaluation of the i-th decoder among the M decoders, the network device processes the received second CSI feedback information based on the i-th decoder to obtain the first CSI, then processes the first CSI based on the first encoder to obtain the first CSI feedback information, and evaluates the CSI feedback performance of the i-th decoder based on the first CSI feedback information.
[0182] Optionally, the CSI feedback performance of each of the M decoders may be evaluated in the above manner, that is, i may take any value from 1 to M. It should be noted that different decoders may process the same received CSI feedback information or may process different CSI feedback information.
[0183] The CSI feedback performance of each of the M decoders can be used to select / switch the encoder subsequently used by the network device. Specifically, the method further includes: the network device determining a second decoder among the M decoders based on the CSI feedback performance of each of the M decoders; wherein the second decoder is used by the network device to process third CSI feedback information from the terminal device. Exemplarily, the third CSI feedback information may refer to CSI feedback information received from the terminal device after the second decoder is determined.
[0184] Optionally, the network device may select a decoder with the best performance from the M decoders as the second decoder according to relevant indicators.
[0185] In some embodiments, when there are multiple encoders, the above method can be used to evaluate the feedback performance of each encoder. Specifically, the above-mentioned first encoder is the j-th encoder among the K encoders, K is an integer greater than 1, and j is a positive integer not greater than K. Accordingly, the first CSI feedback information is used to evaluate the CSI feedback performance of the j-th encoder. That is, when K encoders are deployed, for the performance evaluation of the j-th encoder, the network device processes the received second CSI feedback information based on the first decoder to obtain the first CSI, then processes the first CSI based on the j-th encoder to obtain the first CSI feedback information, and evaluates the CSI feedback performance of the j-th encoder based on the first CSI feedback information.
[0186] Optionally, the CSI feedback performance of each of the K encoders may be evaluated using the above method, that is, j may take any value from 1 to K. The evaluation of the jth encoder may be performed based on a decoding and re-encoding process of the second CSI feedback information obtained by encoding the encoder.
[0187] The CSI feedback performance of each of the K encoders can be used to select / switch the encoder subsequently used by the terminal device. Specifically, the CSI feedback performance of each of the K encoders is used to determine a second encoder among the K encoders, and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal. Exemplarily, the fourth CSI may refer to the CSI obtained based on the measurement of the reference signal after the second encoder is determined.
[0188] Optionally, the network device may determine the second encoder from the K encoders and indicate relevant information of the second encoder, such as an ID, through the first indication information in the aforementioned embodiment. Alternatively, the network device may indicate the CSI feedback performance of each encoder through the first indication information, and the terminal device may determine the second encoder from the K encoders.
[0189] According to the foregoing description, the evaluation of the j-th encoder can be performed based on the decoding and re-encoding process of the second CSI feedback information obtained by encoding the encoder. The following provides an exemplary method for a network device to determine the encoder corresponding to the received CSI feedback information. Exemplarily, before the network device processes the first channel state information CSI based on the first encoder to obtain the first CSI feedback information, the method further includes: the network device sends first configuration information to the terminal device; wherein the first configuration information is used to instruct the terminal device to process the second CSI based on the j-th encoder.
[0190] Accordingly, before the terminal device processes the second CSI obtained based on the measurement of the reference signal based on the first encoder to obtain second CSI feedback information, the above method also includes: the terminal device receives first configuration information from the network device; the terminal device determines the first encoder among K encoders based on the first configuration information; wherein K is an integer greater than 1.
[0191] That is, the network device sends the first configuration information to enable the terminal device to use the jth encoder to process the CSI obtained based on the reference signal measurement to obtain corresponding CSI feedback information. In this way, the network device can determine that the CSI feedback information subsequently received includes the encoding result corresponding to the jth encoder.
[0192] Optionally, the first configuration information includes an encoder ID sequence, which includes the IDs of X encoders. The encoder ID sequence is used to instruct the terminal device to sequentially process the second CSI obtained based on the reference signal measurement using the X encoders to obtain multiple CSI feedback information, including CSI feedback information corresponding to each of the X encoders; where the X encoders include the jth encoder, and X is an integer greater than 1. In other words, the network device sends the first configuration information to configure the terminal device to subsequently use each of the X encoders to sequentially process the CSI obtained based on the reference signal measurement to obtain CSI feedback information corresponding to each of the X encoders. For example, if the multiple encoders configured in the terminal device and the network device include encoder 1, encoder 2, encoder 3, and encoder 4, the network device may send the first configuration information to the terminal device, which includes the sequence {1, 3, 4}, to instruct the terminal device to sequentially use encoder 1, encoder 3, and encoder 4 to obtain the corresponding CSI feedback information. Optionally, the encoder ID sequence may include repeated or identical IDs. For example, the encoder ID sequence carried by the network device in the first configuration information is {1, 2, 3, 1}, and the X encoders include repeated encoder 1. The terminal device needs to use encoder 1 twice to encode CSI in the next four CSI encodings.
[0193] Accordingly, the above method may further include: the terminal device sequentially sending the multiple CSI feedback information to the network device. The multiple CSI feedback information is used by the network device to determine the second CSI feedback information corresponding to the first encoder based on the encoder ID sequence.
[0194] That is, the network device can determine, based on the encoder ID sequence, the correspondence between subsequently received CSI feedback information and each encoder indicated by the encoder ID sequence. Specifically, the network device can determine the CSI feedback information corresponding to a specific encoder from among the multiple pieces of received feedback information, and then evaluate the CSI feedback performance of that encoder. Specifically, the above method may further include: the network device receiving multiple pieces of CSI feedback information from the terminal device, and determining, based on the encoder ID sequence, the second CSI feedback information corresponding to the j-th encoder from among the multiple pieces of CSI feedback information.
[0195] It should be noted that the number X of encoders indicated by the above-mentioned encoder ID sequence may be the same as or different from the number K of encoders in the terminal device. Specifically, X may be less than, equal to, or greater than K. For example, the encoder ID sequence needs to include the IDs of all encoders and does not include repeated or identical encoder IDs. The sequence is mainly used to indicate the order of the encoders, then X is equal to K. For another example, the encoder ID sequence may include the IDs of some encoders, that is, the encoder ID sequence is used to indicate both the IDs of the encoders subsequently adopted by the terminal device and the order between the encoders, then X may be different from K. Furthermore, if the encoder ID sequence can include repeated encoder IDs, then X may be greater than K; if the encoder ID sequence cannot include repeated encoder IDs, then X is less than K.
[0196] In some embodiments, when there are multiple encoders and multiple decoders, the above method can be used to perform feedback performance evaluation on the combination of each encoder and each decoder.
[0197] Optionally, the first encoder is the j-th encoder among K encoders, K is an integer greater than 1, and j is a positive integer not greater than K; the first decoder is the i-th decoder among M decoders, M is an integer greater than 1, and i is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the combination of the j-th encoder and the i-th decoder.
[0198] Accordingly, the above method also includes: the network device determines the second encoder and the second decoder based on the CSI feedback performance of each encoder among the K encoders and the combination of each decoder among the M decoders; wherein the second decoder is used by the network device to process the third CSI feedback information from the terminal device; and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
[0199] Among them, the specific processing method for the i-th decoder and the j-th encoder can be set with reference to the aforementioned embodiment and will not be described in detail here. Exemplarily, the network device can combine each encoder and each decoder to obtain a combination of multiple encoders and decoders, and evaluate the CSI feedback performance for each combination. Optionally, the network device can adopt the processing method for multiple encoders in the aforementioned embodiment (for example, a method of indicating the order of encoders by an encoder ID sequence), obtain the CSI feedback information corresponding to the j-th encoder, and use multiple decoders to process the CSI feedback information separately to achieve the evaluation of the CSI feedback performance of the combination of the j-th encoder and each decoder. Similarly, the evaluation of the CSI feedback performance of each encoder and each decoder combination can be achieved.
[0200] To facilitate understanding of the above technical solution, two specific application examples are provided below.
[0201] Application Example 1
[0202] In this application example, a single encoder and a single decoder are deployed in the terminal device (UE) and the network equipment (taking the base station as an example). The evaluation of the CSI feedback performance is used to determine whether to update / fine-tune the encoder and decoder models, or fall back to using the codebook for CSI feedback.
[0203] This application example includes:
[0204] (1) Triggering CSI feedback model performance monitoring
[0205] As a basic condition for implementing AI-based CSI feedback, the UE and base station need to maintain matching encoder and decoder models respectively. The models can be obtained in the following ways:
[0206] Base station provision: The base station itself retains the trained model and sends and configures the model encoder to the UE (for example, through RRC messages, broadcast configuration, MAC CE or DCI indication, etc.).
[0207] Manufacturer predefined: UE and base station manufacturers have each predefined the encoder and decoder models that can be used for CSI feedback. In this case, the UE needs to report the retained model information and corresponding ID to the base station (for example, through RRC messages, UCI, PUSCH indication, etc.) to achieve alignment of the model information between the base station and the UE.
[0208] Obtained through third-party channels or agreements.
[0209] During the operation of the CSI feedback model, the performance of the CSI feedback model often fluctuates due to factors such as UE mobility and changes in the wireless communication environment. Therefore, model performance monitoring needs to be triggered by the UE or base station.
[0210] Specifically, if the base station triggers CSI feedback model performance monitoring, the trigger signaling can be sent to the UE via RRC, MAC CE, DCI, etc. As corresponding feedback, the information that the UE potentially needs to report to the base station includes but is not limited to:
[0211] a) Whether you agree to conduct performance monitoring
[0212] b) CSI encoder model and / or model ID used by the UE;
[0213] c) the monitoring period or monitoring trigger condition expected by the UE;
[0214] d) Monitoring indicators expected by UE;
[0215] e) UE expected monitoring threshold;
[0216] The UE may report information to the base station through RRC, UCI, PUSCH, etc. The triggering process is shown in FIG8 .
[0217] If the UE triggers CSI feedback model performance monitoring, the trigger signaling can be reported to the base station via RRC, UCI, PUSCH, etc. The information that the UE can report to the base station in the trigger information includes but is not limited to:
[0218] a) The CSI encoder model and / or model ID used by the UE;
[0219] b) the monitoring period or monitoring trigger condition expected by the UE;
[0220] c) Monitoring indicators expected by UE;
[0221] d) The monitoring threshold expected by the UE.
[0222] The trigger information can be implemented through RRC, UCI, PUSCH, etc. The trigger process is shown in Figure 9.
[0223] (2) Implement CSI feedback model performance monitoring
[0224] Through the previous steps, the base station has obtained or learned the encoder model that is consistent with the UE. The base station uses this encoder model to re-encode the output of the decoder model (the CSI recovered by the base station). The base station then monitors and evaluates the model's performance by comparing the compressed information output by the encoder model with the feedback information input by the decoder model, as shown in Figure 10.
[0225] Here, the indicators for judging the performance of the CSI feedback model, i.e., the similarity evaluation criteria between the feedback bitstream and the recompressed bitstream, may include but are not limited to:
[0226] a) Bit error rate (i.e., the ratio of the number of different bits to the total number of bits);
[0227] b) the total number of error bits;
[0228] c) mean square error or normalized mean square error;
[0229] d) Euclidean distance between two encoded vectors;
[0230] e) Hamming distance between two encoding vectors;
[0231] f) Cosine similarity of two encoded vectors.
[0232] The above indicators can be calculated for a single CSI sample or can be obtained by counting a number of CSI samples over a period of time. The selection of the evaluation criteria can be performed by the base station or realized through UE reporting.
[0233] (3) Triggering the next action based on performance monitoring results
[0234] The base station can continuously monitor the CSI model performance and determine whether it meets the monitoring threshold (the threshold can be set by the base station or reported by the UE). The potential actions that the base station can trigger are listed as follows:
[0235] a) Send the monitoring results to the UE, allowing the UE to decide whether to take action, as shown in Figure 11. The content sent can be whether the monitoring indicator meets the threshold (which can be specified by 1 bit) or the specific value of the monitoring indicator.
[0236] b) The base station determines that the CSI model performance is normal and no action is required.
[0237] c) The base station determines that the CSI model performance does not meet the requirements and sends information to the UE to trigger CSI model switching / update / fine-tuning, fallback to the traditional feedback solution, etc., as shown in Figure 12.
[0238] Application Example 2
[0239] In this application example, multiple encoders and / or multiple decoders are deployed in a terminal device (UE) and a network device (taking a base station as an example), and the evaluation of CSI feedback performance is used to determine whether to perform model selection / switching on the encoder and / or decoder.
[0240] Specifically, this application example is applicable to the following three situations:
[0241] a) The UE maintains an encoder model, and the base station maintains multiple decoder models that can work in conjunction with the encoder model.
[0242] b) The UE maintains multiple encoder models, and the base station also maintains multiple decoder models that can be used in conjunction with the UE encoder model.
[0243] c) The UE holds multiple encoder models, and the base station holds a decoder model that can work in conjunction with the encoder models.
[0244] (1) Triggering CSI feedback model performance monitoring
[0245] During the operation of the CSI feedback model, the performance of the CSI feedback model often fluctuates due to factors such as UE mobility and changes in the wireless communication environment. The currently used CSI feedback model may no longer be the most suitable, so model selection / switching needs to be triggered by the UE or base station.
[0246] If the base station triggers the CSI feedback model selection / switching for some reason, the trigger signaling can be sent to the UE via RRC, MAC CE, DCI, etc. In response, the information that the UE potentially needs to report to the base station includes but is not limited to:
[0247] a) Whether you agree to select / switch the model;
[0248] b) The CSI encoder model and / or model ID used by the UE (if the UE has multiple available encoder models, multiple models and / or model IDs can be reported);
[0249] c) UE's desired model selection / switching cycle or triggering condition;
[0250] d) UE expected model selection / switching reference indicators.
[0251] The UE may report information to the base station through RRC, UCI, PUSCH, etc. The triggering process is shown in FIG13 .
[0252] If the base station triggers the CSI feedback model selection / switching, the trigger signaling can be reported to the base station via RRC, UCI, PUSCH, etc. The information that the UE can report to the base station in the trigger information includes but is not limited to:
[0253] e) The CSI encoder model and / or model ID used by the UE (if the UE has multiple available encoder models, multiple models and / or model IDs can be reported);
[0254] f) UE's desired model selection / switching cycle or triggering condition;
[0255] g) UE's desired model selection / switching reference indicators.
[0256] The trigger information can be implemented through RRC, UCI, PUSCH, etc. The trigger process is shown in Figure 14.
[0257] (2) Implement CSI feedback model performance monitoring
[0258] Through the previous steps, the base station side has obtained or learned the encoder model that is consistent with the UE side (there may be a single or multiple encoder models). For the case where the UE side can only use a single encoder model, the base station side needs to follow the performance evaluation method described in Example 1 to perform performance evaluation on the multiple decoder models available on the base station side, as shown in Figure 15A. For the case where the UE side has multiple encoder models available at the same time, the base station needs to send down configuration information to specify the encoder ID used by the UE for the next feedback or the next several feedbacks (the configuration information can be a sequence, specifying the encoder model ID corresponding to the next several feedbacks). After receiving the feedback information, the base station can test the performance of different encoder-decoder model combinations by using different decoder models, as shown in Figure 15B.
[0259] Here, the indicators for comparing model performance, i.e., the similarity evaluation criteria between the feedback bitstream and the recompressed bitstream corresponding to different models, may include but are not limited to:
[0260] g) bit error rate (i.e., the ratio of the number of different bits to the total number of bits);
[0261] h) the total number of error bits;
[0262] i) mean square error or normalized mean square error;
[0263] j) Euclidean distance between two encoding vectors;
[0264] k) Hamming distance between two encoding vectors;
[0265] l) Cosine similarity of two encoding vectors.
[0266] The above indicators can be calculated for a single CSI sample or can be obtained by counting a number of CSI samples over a period of time. The selection of the evaluation criteria can be performed by the base station or realized through UE reporting.
[0267] After completing the model performance evaluation, the base station can select / switch the model based on the evaluation results. In the case of UE-side encoder model switching, the base station needs to send signaling to inform the UE to switch.
[0268] As you can see, the above application example has the following advantages:
[0269] No significant additional overhead is introduced: If the encoder model has not been updated or switched, the UE only needs to upload the encoder model once to support an unlimited number of subsequent CSI feedback sample performance monitoring and evaluation, thus avoiding transmission overhead.
[0270] No additional burden on the UE: The UE only needs to upload or instruct the encoder model, without consuming additional computing power and power for model performance evaluation.
[0271] High evaluation accuracy: It can directly reflect the accuracy of the CSI feedback at that time rather than through indirect indicators.
[0272] Flexible and highly real-time evaluation: Evaluation can be performed immediately after each CSI feedback is completed, without the delay caused by the base station or UE transmitting the CSI itself or auxiliary information to the other side.
[0273] Based on the above advantages, this solution can enable base stations and UEs to achieve accurate, reliable, and real-time evaluation of CSI feedback model performance, thereby providing a strong basis for triggering CSI feedback scheme fallback, model switching, etc., thereby ensuring overall wireless communication performance.
[0274] FIG16 is a schematic block diagram of a network device 1600 according to an embodiment of the present application. The network device 1600 may include:
[0275] A first processing module 1610 is configured to process first CSI based on a first encoder to obtain first CSI feedback information; the first CSI is obtained by processing second CSI feedback information from a terminal device based on a first decoder; and the second CSI feedback information is obtained by processing second CSI obtained by the terminal device based on a measurement of a reference signal based on the first encoder.
[0276] The first processing module 1610 is further configured to evaluate CSI feedback performance based on the first CSI feedback information.
[0277] In one embodiment, the first processing module 1610 is further configured to:
[0278] A first indicator is determined based on the first CSI feedback information and the second CSI feedback information, where the first indicator is used to characterize CSI feedback performance.
[0279] In one implementation, the first indicator is related to the difference and / or similarity between the first CSI feedback information and the second CSI feedback information.
[0280] In one embodiment, the first indicator includes at least one of the following:
[0281] A ratio between the number of error bits in the N bits of the first CSI feedback information and N; wherein the error bit is a bit corresponding to the same bit position but having different values in the first CSI feedback information and the second CSI feedback information;
[0282] The number of error bits;
[0283] a mean square error between the first CSI feedback information and the second CSI feedback information;
[0284] a normalized mean square error between the first CSI feedback information and the second CSI feedback information;
[0285] a Euclidean distance between the first CSI feedback information and the second CSI feedback information;
[0286] a Hamming distance between the first CSI feedback information and the second CSI feedback information;
[0287] The cosine similarity between the first CSI feedback information and the second CSI feedback information.
[0288] In one embodiment, the first processing module 1610 is further configured to:
[0289] Processing the first CSI feedback information based on the first decoder to obtain third CSI;
[0290] A second indicator is determined based on the first CSI and the third CSI, where the second indicator is used to characterize CSI feedback performance.
[0291] In one embodiment, the first decoder is the i-th decoder among M decoders, where M is an integer greater than 1, and i is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the i-th decoder;
[0292] The first processing module 1610 is further configured to:
[0293] Based on the CSI feedback performance of each decoder among the M decoders, a second decoder is determined among the M decoders; wherein the second decoder is used to process the third CSI feedback information from the terminal device.
[0294] In one embodiment, the first encoder is the j-th encoder among K encoders, where K is an integer greater than 1 and j is a positive integer not greater than K; the first CSI feedback information is used to evaluate the CSI feedback performance of the j-th encoder; the CSI feedback performance of each encoder among the K encoders is used to determine a second encoder among the K encoders, and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
[0295] In one embodiment, as shown in FIG17 , the network device 1600 further includes a first communication module 1710 configured to:
[0296] Send first configuration information to the terminal device; wherein the first configuration information is used to instruct the terminal device to process the second CSI based on the j-th encoder.
[0297] In one embodiment, the first configuration information includes an encoder ID sequence, where the encoder ID sequence includes IDs of X encoders. The encoder ID sequence is used to instruct the terminal device to process, in sequence, the second CSI obtained based on the measurement of the reference signal based on the X encoders to obtain multiple CSI feedback information, where the multiple CSI feedback information includes CSI feedback information corresponding to each of the X encoders; wherein the X encoders include the j-th encoder, and X is an integer greater than 1.
[0298] Correspondingly, the first communication module 1710 is also used to receive multiple CSI feedback information from the terminal device; the first processing module 1610 is also used to determine the second CSI feedback information corresponding to the j-th encoder in the multiple CSI feedback information based on the encoder ID sequence.
[0299] In one embodiment, the first encoder is the jth encoder among K encoders, where K is an integer greater than 1 and j is a positive integer not greater than K; the first decoder is the ith decoder among M decoders, where M is an integer greater than 1 and j is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the jth encoder and the ith decoder combination;
[0300] The first processing module 1610 is further configured to:
[0301] Based on the CSI feedback performance of each encoder among the K encoders and each decoder combination among the M decoders, a second encoder and a second decoder are determined; wherein the second decoder is used to process the third CSI feedback information from the terminal device; the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
[0302] In one embodiment, as shown in FIG18 , the network device 1600 further includes a second communication module 1810 configured to:
[0303] Sending first indication information to the terminal device; wherein the first indication information is used to indicate CSI feedback performance.
[0304] In one implementation, the first indication information is used to indicate a third indicator, and the third indicator is used to characterize CSI feedback performance.
[0305] In one implementation, the first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
[0306] In one embodiment, as shown in FIG19 , the network device 1600 further includes a third communication module 1910 configured to:
[0307] When the CSI feedback performance does not meet the preset conditions, second indication information is sent to the terminal device; wherein the second indication information is used to instruct the terminal device to perform predetermined processing on the first encoder.
[0308] In one embodiment, the predetermined process includes one of the following:
[0309] Switching to use other encoders except the first encoder among Z encoders of the terminal device, where Z is an integer greater than 1;
[0310] updating the first encoder;
[0311] Fine-tuning the first encoder;
[0312] The codebook is used to process the fourth CSI obtained based on the measurement of the reference signal.
[0313] In one embodiment, the first processing module 1610 is further configured to:
[0314] If it is determined that the CSI feedback performance meets the preset condition, the first encoder is kept in use.
[0315] In one embodiment, as shown in FIG20 , the network device 1600 further includes a fourth communication module 2010 configured to:
[0316] Sending third indication information to the terminal device; wherein the third indication information is used to trigger CSI feedback performance evaluation.
[0317] In one embodiment, the fourth communication module 2010 is further configured to:
[0318] Receive first reporting information from a terminal device; wherein the first reporting information is used to indicate at least one of the following:
[0319] Whether to agree to evaluate CSI feedback performance;
[0320] Information about the first encoder;
[0321] First assessment cycle;
[0322] a type of a fourth indicator, the fourth indicator being used to characterize CSI feedback performance;
[0323] The first indicator threshold.
[0324] In one implementation, the first reporting information is carried by a first RRC message, UCI, or PUSCH.
[0325] In one implementation, the third indication information is carried by a second RRC message, MAC CE, or DCI.
[0326] In one embodiment, as shown in FIG21 , the network device 1600 further includes a fifth communication module 2110 configured to:
[0327] Receive second reporting information from the terminal device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
[0328] In one embodiment, the second reporting information is used to indicate at least one of the following:
[0329] Information about the first encoder;
[0330] Second assessment cycle;
[0331] The type of the fifth indicator, which is used to characterize the CSI feedback performance;
[0332] Second indicator threshold.
[0333] In one implementation, the second reporting information is carried by an RRC message, UCI, or PUSCH.
[0334] In one embodiment, the first encoder and the first decoder are configured in a network device. As shown in FIG22 , the network device 1600 further includes a sixth communication module 2210 for:
[0335] Send fourth indication information to the terminal device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
[0336] In one embodiment, the first decoder is preconfigured; and the first encoder is determined based on relevant information sent by the terminal device.
[0337] The network device 1600 of the embodiment of the present application can implement the corresponding functions of the network device in the aforementioned method embodiment. The corresponding processes, functions, implementation methods and beneficial effects of each module (sub-module, unit or component, etc.) in the network device 1600 can be found in the corresponding description in the above method embodiment, and will not be repeated here. It should be noted that the functions described in the various modules (sub-module, unit or component, etc.) in the network device 1600 of the embodiment of the application can be implemented by different modules (sub-module, unit or component, etc.) or by the same module (sub-module, unit or component, etc.).
[0338] FIG23 is a schematic block diagram of a terminal device 2300 according to an embodiment of the present application. The terminal device 2300 may include:
[0339] A second processing module 2310 is configured to process, based on the first encoder, second CSI obtained by measuring the reference signal to obtain second CSI feedback information;
[0340] The seventh communication module 2320 is configured to send second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder and evaluate the CSI feedback performance based on the first CSI feedback information.
[0341] In one embodiment, the seventh communication module 2320 is further configured to:
[0342] receiving first configuration information from a network device;
[0343] The second processing module 2310 is further configured to:
[0344] Based on the first configuration information, a first encoder is determined among K encoders; wherein K is an integer greater than 1.
[0345] In one embodiment, the first configuration information includes an encoder ID sequence, which includes the IDs of X encoders. The encoder ID sequence is used to instruct the terminal device 2300 to process the second CSI obtained based on the measurement of the reference signal based on the X encoders in sequence; wherein the X encoders include the first encoder, and X is an integer greater than 1.
[0346] Correspondingly, the seventh communication module 2320 is further used to send the multiple CSI feedback information to the network device in sequence; wherein, the multiple CSI feedback information is used by the network device to determine the second CSI feedback information corresponding to the first encoder based on the encoder ID sequence.
[0347] In one embodiment, the seventh communication module 2320 is further configured to:
[0348] Receive first indication information from a network device; wherein the first indication information is used to indicate CSI feedback performance.
[0349] In one implementation, the first indication information is used to indicate a third indicator, and the third indicator is used to characterize CSI feedback performance.
[0350] In one implementation, the first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
[0351] In one embodiment, the second processing module 2310 is further configured to:
[0352] In a case where the second indication information is received from the network device, it is determined that the CSI feedback performance does not meet the preset condition, and a predetermined process is performed on the first encoder.
[0353] In one embodiment, the predetermined process includes one of the following:
[0354] Switching to other encoders except the first encoder among the Z encoders used, where Z is an integer greater than 1;
[0355] updating the first encoder;
[0356] Fine-tuning the first encoder;
[0357] The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
[0358] In one embodiment, the seventh communication module 2320 is further configured to:
[0359] Upon receiving third indication information from the network device, sending first reporting information to the network device; wherein the third indication information is used to trigger CSI feedback performance evaluation; and the first reporting information is used to indicate at least one of the following:
[0360] Whether to agree to evaluate the CSI feedback performance;
[0361] Information about the first encoder;
[0362] First assessment cycle;
[0363] a type of a fourth indicator, the fourth indicator being used to characterize CSI feedback performance;
[0364] The first indicator threshold.
[0365] In one implementation, the first reporting information is carried by RRC, UCI, or PUSCH.
[0366] In one implementation, the third indication information is carried by RRC, MAC CE or DCI.
[0367] In one embodiment, the seventh communication module 2320 is further configured to:
[0368] Sending second reporting information to the network device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
[0369] In one embodiment, the second reporting information is used to indicate at least one of the following:
[0370] Information about the first encoder;
[0371] Second assessment cycle;
[0372] The type of the fifth indicator, which is used to characterize the CSI feedback performance;
[0373] Second indicator threshold.
[0374] In one implementation, the second reporting information is carried by RRC, UCI, or PUSCH.
[0375] In one embodiment, the first encoder and the first decoder are configured by a network device, and the seventh communication module 2320 is further configured to:
[0376] Receive fourth indication information from the network device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
[0377] The terminal device 2300 of the embodiment of the present application can implement the corresponding functions of the terminal device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the terminal device 2300 can be found in the corresponding descriptions in the above-mentioned method embodiments, which will not be repeated here. It should be noted that the functions described by the various modules (sub-modules, units or components, etc.) in the terminal device 2300 of the application embodiment can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).
[0378] Figure 24 is a schematic block diagram of a communication device 2400 according to an embodiment of the present application. The communication device 2400 includes a processor 2410, which can call and execute a computer program from a memory to enable the communication device 2400 to implement the method in the embodiment of the present application.
[0379] In one embodiment, the communication device 2400 may further include a memory 2420. The processor 2410 may call and execute a computer program from the memory 2420 to enable the communication device 2400 to implement the method in the embodiment of the present application.
[0380] The memory 2420 may be a separate device independent of the processor 2410 , or may be integrated into the processor 2410 .
[0381] In one embodiment, the communication device 2400 may further include a transceiver 2430 , and the processor 2410 may control the transceiver 2430 to communicate with other devices. Specifically, the transceiver 2430 may send information or data to other devices, or receive information or data sent by other devices.
[0382] The transceiver 2430 may include a transmitter and a receiver. The transceiver 2430 may further include an antenna, and the number of antennas may be one or more.
[0383] In one embodiment, the communication device 2400 may be a network device of an embodiment of the present application, and the communication device 2400 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.
[0384] In one embodiment, the communication device 2400 may be a terminal device of an embodiment of the present application, and the communication device 2400 may implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.
[0385] 25 is a schematic structural diagram of a chip 2500 according to an embodiment of the present application. The chip 2500 includes a processor 2510, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.
[0386] In one embodiment, the chip 2500 may further include a memory 2520. The processor 2510 may call and execute a computer program from the memory 2520 to implement the method executed by the terminal device in the embodiment of the present application.
[0387] The memory 2520 may be a separate device independent of the processor 2510 or may be integrated into the processor 2510 .
[0388] In one embodiment, the chip 2500 may further include an input interface 2530. The processor 2510 may control the input interface 2530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
[0389] In one embodiment, the chip 2500 may further include an output interface 2540. The processor 2510 may control the output interface 2540 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
[0390] In one embodiment, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
[0391] In one embodiment, the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
[0392] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0393] The processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.
[0394] The memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM).
[0395] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.
[0396] FIG26 is a schematic block diagram of a communication system 2600 according to an embodiment of the present application. The communication system 2600 includes a network device 1600 and a terminal device 2300 .
[0397] Among them, the terminal device 2300 is used for the network device 1600 to process the second CSI obtained based on the measurement of the reference signal based on the first encoder, obtain the second CSI feedback information, and send the second CSI feedback information to the network device 1600.
[0398] The network device 1600 is used to process the first CSI based on the first encoder to obtain first CSI feedback information, wherein the first CSI is obtained by the network device processing the received second CSI feedback information based on the first decoder; and is also used to evaluate CSI feedback performance based on the first CSI feedback information.
[0399] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it 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. When the computer program instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. 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 transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).
[0400] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0401] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0402] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A method for evaluating channel state information (CSI) feedback performance, comprising: The network device processes the first CSI based on the first encoder to obtain first CSI feedback information; the first CSI is obtained by the network device processing the second CSI feedback information from the terminal device based on the first decoder; the second CSI feedback information is obtained by the terminal device processing the second CSI obtained based on the measurement of the reference signal based on the first encoder; The network device evaluates CSI feedback performance based on the first CSI feedback information.
2. The method according to claim 1, wherein: The network device evaluating CSI feedback performance based on the first CSI feedback information includes: The network device determines a first indicator based on the first CSI feedback information and the second CSI feedback information, where the first indicator is used to characterize the CSI feedback performance.
3. The method according to claim 2, wherein: The first indicator is related to the difference and / or similarity between the first CSI feedback information and the second CSI feedback information.
4. The method according to claim 2 or 3, wherein: The first indicator includes at least one of the following: a ratio between the number of error bits in the N bits of the first CSI feedback information and N; wherein the error bit is a bit corresponding to the same bit position but having different values in the first CSI feedback information and the second CSI feedback information; the number of error bits; A mean square error between the first CSI feedback information and the second CSI feedback information; a normalized mean square error between the first CSI feedback information and the second CSI feedback information; A Euclidean distance between the first CSI feedback information and the second CSI feedback information; A Hamming distance between the first CSI feedback information and the second CSI feedback information; The cosine similarity between the first CSI feedback information and the second CSI feedback information.
5. The method according to any one of claims 1 to 4, wherein: The network device evaluating CSI feedback performance based on the first CSI feedback information includes: The network device processes the first CSI feedback information based on the first decoder to obtain a third CSI; The network device determines a second indicator based on the first CSI and the third CSI, where the second indicator is used to characterize the CSI feedback performance.
6. The method according to any one of claims 1 to 5, wherein: The first decoder is the i-th decoder among M decoders, M is an integer greater than 1, and i is a positive integer not greater than M; The first CSI feedback information is used to evaluate the CSI feedback performance of the i-th decoder; The method further comprises: The network device determines a second decoder among the M decoders based on the CSI feedback performance of each decoder among the M decoders; wherein the second decoder is used by the network device to process the third CSI feedback information from the terminal device.
7. The method according to any one of claims 1 to 5, wherein: The first encoder is the j-th encoder among K encoders, K is an integer greater than 1, and j is a positive integer not greater than K; the first CSI feedback information is used to evaluate the CSI feedback performance of the j-th encoder; the CSI feedback performance of each encoder among the K encoders is used to determine a second encoder among the K encoders, and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
8. The method according to claim 7, wherein: Before the network device processes the first CSI based on the first encoder to obtain the first CSI feedback information, the method further includes: The network device sends first configuration information to the terminal device; wherein the first configuration information is used to instruct the terminal device to process the second CSI based on the jth encoder.
9. The method according to claim 8, wherein: The first configuration information includes an encoder identification ID sequence, the encoder ID sequence includes IDs of X encoders, and the encoder ID sequence is used to instruct the terminal device to process the second CSI based on the X encoders in sequence to obtain multiple CSI feedback information, and the multiple CSI feedback information includes CSI feedback information corresponding to each encoder of the X encoders; wherein the X encoders include the j-th encoder, and X is an integer greater than 1; The method further comprises: The network device receives multiple CSI feedback information from the terminal device, and determines the second CSI feedback information corresponding to the jth encoder in the multiple CSI feedback information based on the encoder ID sequence.
10. The method according to any one of claims 1 to 5, wherein: The first encoder is the jth encoder among K encoders, K is an integer greater than 1, and j is a positive integer not greater than K; the first decoder is the i-th decoder among M decoders, M is an integer greater than 1, and i is a positive integer not greater than M; The first CSI feedback information is used to evaluate the CSI feedback performance of the j-th encoder and the i-th decoder combination; The method further comprises: The network device determines a second encoder and a second decoder based on the CSI feedback performance of each encoder among the K encoders and each decoder combination among the M decoders; wherein the second decoder is used by the network device to process the third CSI feedback information from the terminal device; and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
11. The method according to any one of claims 1 to 10, wherein: The method further comprises: The network device sends first indication information to the terminal device; wherein the first indication information is used to indicate the CSI feedback performance.
12. The method according to claim 11, wherein: The first indication information is used to indicate a third indicator, and the third indicator is used to characterize the CSI feedback performance.
13. The method according to claim 11 or 12, wherein: The first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
14. The method according to any one of claims 1 to 13, wherein: The method further comprises: When determining that the CSI feedback performance does not meet a preset condition, the network device sends second indication information to the terminal device; wherein the second indication information is used to instruct the terminal device to perform predetermined processing on the first encoder.
15. The method according to claim 14, wherein: The predetermined processing includes one of the following: Switching to use other encoders except the first encoder among Z encoders of the terminal device, where Z is an integer greater than 1; Updating the first encoder; Fine-tuning the first encoder; The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
16. The method according to any one of claims 1 to 15, wherein: The method further comprises: When the CSI feedback performance meets a preset condition, the network device keeps using the first encoder.
17. The method according to any one of claims 1 to 16, wherein: Before the network device processes the first CSI based on the first encoder to obtain the first CSI feedback information, the method further includes: The network device sends third indication information to the terminal device; wherein the third indication information is used to trigger CSI feedback performance evaluation.
18. The method according to claim 17, wherein: The method further comprises: The network device receives first reporting information from the terminal device; wherein the first reporting information is used to indicate at least one of the following: Do you agree to evaluate the CSI feedback performance? relevant information of the first encoder; First evaluation cycle; a type of a fourth indicator, the fourth indicator being used to characterize the CSI feedback performance; The first indicator threshold.
19. The method according to claim 18, wherein: The first reporting information is carried by a first radio resource control RRC message, uplink control information UCI or a physical uplink shared channel PUSCH.
20. The method according to any one of claims 17 to 19, wherein: The third indication information is carried by the second RRC message, the media access control control element MAC CE or the downlink control information DCI.
21. The method according to any one of claims 1 to 16, wherein: Before the network device processes the first channel state information CSI based on the encoder to obtain the first CSI feedback information, the method further includes: The network device receives second reporting information from the terminal device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
22. The method according to claim 21, wherein: The second reporting information is used to indicate at least one of the following: relevant information of the first encoder; Second evaluation cycle; a type of a fifth indicator, the fifth indicator being used to characterize the CSI feedback performance; The second indicator threshold.
23. The method according to claim 22, wherein: The second reporting information is carried by an RRC message, UCI or PUSCH.
24. The method according to any one of claims 1 to 23, wherein: The first encoder and the first decoder are configured by the network device, and the method further includes: The network device sends fourth indication information to the terminal device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
25. The method according to any one of claims 1 to 23, wherein: The first decoder is preconfigured; the first encoder is determined based on relevant information sent by the terminal device.
26. A method for evaluating CSI feedback performance, comprising: The terminal device processes, based on the first encoder, the second CSI obtained by measuring the reference signal to obtain second CSI feedback information; The terminal device sends the second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder, so as to evaluate the CSI feedback performance based on the first CSI feedback information after processing the first CSI based on the first encoder to obtain the first CSI feedback information.
27. The method according to claim 26, wherein: Before the terminal device processes the second CSI obtained based on the measurement of the reference signal based on the first encoder to obtain the second CSI feedback information, the method further includes: The terminal device receives first configuration information from the network device; The terminal device determines the first encoder among K encoders based on the first configuration information; wherein K is an integer greater than 1.
28. The method according to claim 27, wherein: The first configuration information includes an encoder ID sequence, the encoder ID sequence includes IDs of X encoders, and the encoder ID sequence is used to instruct the terminal device to process the measured second CSI based on the X encoders in sequence to obtain multiple CSI feedback information, and the multiple CSI feedback information includes CSI feedback information corresponding to each encoder of the X encoders; wherein the X encoders include the first encoder, and X is an integer greater than 1; The method further comprises: The terminal device sends the multiple CSI feedback information to the network device in sequence; wherein the multiple CSI feedback information is used by the network device to determine the second CSI feedback information corresponding to the first encoder based on the encoder ID sequence.
29. The method according to any one of claims 26 to 28, wherein: The method further comprises: The terminal device receives first indication information from the network device; wherein the first indication information is used to indicate the CSI feedback performance.
30. The method of claim 29, wherein: The first indication information is used to indicate a third indicator, and the third indicator is used to characterize the CSI feedback performance.
31. The method according to claim 29 or 30, wherein: The first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
32. The method according to any one of claims 26 to 31, wherein: The method further comprises: When receiving the second indication information from the network device, the terminal device determines that the CSI feedback performance does not meet a preset condition, and performs predetermined processing on the first encoder.
33. The method of claim 32, wherein: The predetermined processing includes one of the following: Switching to use other encoders except the first encoder among Z encoders of the terminal device, where Z is an integer greater than 1; Updating the first encoder; Fine-tuning the first encoder; The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
34. The method according to any one of claims 26 to 33, wherein: The method further comprises: The terminal device sends first reporting information to the network device when receiving third indication information from the network device; wherein the third indication information is used to trigger CSI feedback performance evaluation; and the first reporting information is used to indicate at least one of the following: Do you agree to evaluate the CSI feedback performance? relevant information of the first encoder; First evaluation cycle; a type of a fourth indicator, the fourth indicator being used to characterize the CSI feedback performance; The first indicator threshold.
35. The method of claim 34, wherein: The first reporting information is carried by a first RRC message, UCI or PUSCH.
36. The method according to claim 34 or 35, wherein: The third indication information is carried by a second RRC message, MAC CE or DCI.
37. The method according to any one of claims 26 to 33, wherein: The method further comprises: The terminal device sends second reporting information to the network device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
38. The method of claim 37, wherein: The second reporting information is used to indicate at least one of the following: relevant information of the first encoder; Second evaluation cycle; a type of a fifth indicator, the fifth indicator being used to characterize the CSI feedback performance; The second indicator threshold.
39. The method of claim 38, wherein: The second reporting information is carried by an RRC message, UCI or PUSCH.
40. The method according to any one of claims 26 to 39, wherein: The first encoder and the first decoder are configured by the network device, and the method further includes: The terminal device receives fourth indication information from the network device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
41. A network device comprising: A first processing module, configured to process the first CSI based on the first encoder to obtain first CSI feedback information; the first CSI is obtained by processing the second CSI feedback information from the terminal device based on the first decoder; the second CSI feedback information is obtained by the terminal device processing the second CSI obtained based on the measurement of the reference signal based on the first encoder; The first processing module is further used to evaluate CSI feedback performance based on the first CSI feedback information.
42. The network device according to claim 41, wherein: The first processing module is also used for: A first indicator is determined based on the first CSI feedback information and the second CSI feedback information, where the first indicator is used to characterize the CSI feedback performance.
43. The network device according to claim 42, wherein: The first indicator is related to the difference and / or similarity between the first CSI feedback information and the second CSI feedback information.
44. The network device according to claim 42 or 43, wherein: The first indicator includes at least one of the following: a ratio between the number of error bits in the N bits of the first CSI feedback information and N; wherein the error bit is a bit corresponding to the same bit position but having different values in the first CSI feedback information and the second CSI feedback information; the number of error bits; A mean square error between the first CSI feedback information and the second CSI feedback information; a normalized mean square error between the first CSI feedback information and the second CSI feedback information; A Euclidean distance between the first CSI feedback information and the second CSI feedback information; A Hamming distance between the first CSI feedback information and the second CSI feedback information; The cosine similarity between the first CSI feedback information and the second CSI feedback information.
45. The network device according to claim 41, wherein: The first processing module is also used for: Processing the first CSI feedback information based on the first decoder to obtain third CSI; A second indicator is determined based on the first CSI and the third CSI, where the second indicator is used to characterize the CSI feedback performance.
46. The network device according to any one of claims 41 to 45, wherein: The first decoder is the i-th decoder among M decoders, where M is an integer greater than 1, and i is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the i-th decoder; The first processing module is also used for: Based on the CSI feedback performance of each decoder in the M decoders, a second decoder is determined in the M decoders; wherein the second decoder is used to process the third CSI feedback information from the terminal device.
47. The network device according to any one of claims 41 to 45, wherein: The first encoder is the j-th encoder among K encoders, K is an integer greater than 1, and j is a positive integer not greater than K; the first CSI feedback information is used to evaluate the CSI feedback performance of the j-th encoder; the CSI feedback performance of each encoder among the K encoders is used to determine a second encoder among the K encoders, and the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
48. The network device according to claim 47, wherein: The network device further includes a first communication module, configured to: Sending first configuration information to the terminal device; wherein the first configuration information is used to instruct the terminal device to process the second CSI based on the j-th encoder.
49. The network device according to claim 48, wherein: The first configuration information includes an encoder ID sequence, the encoder ID sequence includes IDs of X encoders, and the encoder ID sequence is used to instruct the terminal device to process the second CSI based on the X encoders in sequence to obtain multiple CSI feedback information, and the multiple CSI feedback information includes CSI feedback information corresponding to each encoder of the X encoders; wherein the X encoders include the j-th encoder, and X is an integer greater than 1; The first communication module is further used to receive multiple CSI feedback information from the terminal device; The first processing module is further configured to determine, from among the plurality of CSI feedback information, the second CSI feedback information corresponding to the j-th encoder based on the encoder ID sequence.
50. The network device according to any one of claims 41 to 45, wherein: The first encoder is the jth encoder among K encoders, K is an integer greater than 1, and j is a positive integer not greater than K; the first decoder is the i-th decoder among M decoders, M is an integer greater than 1, and i is a positive integer not greater than M; the first CSI feedback information is used to evaluate the CSI feedback performance of the combination of the j-th encoder and the i-th decoder; The first processing module is also used for: Based on the CSI feedback performance of each encoder among the K encoders and each decoder combination among the M decoders, a second encoder and a second decoder are determined; wherein the second decoder is used to process the third CSI feedback information from the terminal device; the second encoder is used by the terminal device to process the fourth CSI obtained based on the measurement of the reference signal.
51. The network device according to any one of claims 41 to 50, wherein: The network device further includes a second communication module, configured to: Sending first indication information to the terminal device; wherein the first indication information is used to indicate the CSI feedback performance.
52. The network device according to claim 51, wherein: The first indication information is used to indicate a third indicator, and the third indicator is used to characterize the CSI feedback performance.
53. The network device according to claim 51 or 52, wherein: The first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
54. The network device according to any one of claims 41 to 53, wherein: The network device further includes a third communication module, configured to: When it is determined that the CSI feedback performance does not meet a preset condition, second indication information is sent to the terminal device; wherein the second indication information is used to instruct the terminal device to perform predetermined processing on the first encoder.
55. The network device according to claim 54, wherein: The predetermined processing includes one of the following: Switching to use other encoders except the first encoder among Z encoders of the terminal device, where Z is an integer greater than 1; Updating the first encoder; Fine-tuning the first encoder; The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
56. The network device according to any one of claims 41 to 55, wherein: The first processing module is also used for: When the CSI feedback performance meets a preset condition, keep using the first encoder.
57. The network device according to any one of claims 41 to 56, wherein: The network device further includes a fourth communication module, configured to: Sending third indication information to the terminal device; wherein the third indication information is used to trigger CSI feedback performance evaluation.
58. The network device according to claim 57, wherein: The fourth communication module is also used for: Receive first reporting information from the terminal device; wherein the first reporting information is used to indicate at least one of the following: Do you agree to evaluate the CSI feedback performance? relevant information of the first encoder; First evaluation cycle; a type of a fourth indicator, the fourth indicator being used to characterize the CSI feedback performance; The first indicator threshold.
59. The network device according to claim 58, wherein: The first reporting information is carried by a first RRC message, UCI or PUSCH.
60. The network device according to any one of claims 57 to 59, wherein: The third indication information is carried by a second RRC message, MAC CE or DCI.
61. The network device according to any one of claims 41 to 56, wherein: The network device further includes a fifth communication module, configured to: Receive second reporting information from the terminal device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
62. The network device according to claim 61, wherein: The second reporting information is used to indicate at least one of the following: relevant information of the first encoder; Second evaluation cycle; a type of a fifth indicator, the fifth indicator being used to characterize the CSI feedback performance; The second indicator threshold.
63. The network device according to claim 62, wherein: The second reporting information is carried by an RRC message, UCI or PUSCH.
64. The network device according to any one of claims 41 to 63, wherein: The first encoder and the first decoder are configured by the network device, and the network device further includes a sixth communication module, which is used to: Send fourth indication information to the terminal device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
65. The network device according to any one of claims 41 to 63, wherein: The first decoder is preconfigured; the first encoder is determined based on relevant information sent by the terminal device.
66. A terminal device, comprising: The second processing module is configured to process, based on the first encoder, a second CSI obtained by measuring the reference signal to obtain a second CSI feedback information; A seventh communication module is used to send the second CSI feedback information to the network device; wherein the second CSI feedback information is used by the network device to obtain the first CSI based on the first decoder, and to evaluate the CSI feedback performance based on the first CSI feedback information.
67. The terminal device according to claim 66, wherein: The seventh communication module is also used for: Receiving first configuration information from a network device; The second processing module is also used for: Based on the first configuration information, the first encoder is determined among K encoders; wherein K is an integer greater than 1.
68. The terminal device according to claim 67, wherein: The first configuration information includes an encoder ID sequence, the encoder ID sequence includes IDs of X encoders, and the encoder ID sequence is used to instruct the terminal device to process the second CSI based on the X encoders in sequence; wherein the X encoders include the first encoder, and X is an integer greater than 1; The seventh communication module is further used to send the multiple CSI feedback information to the network device in sequence; wherein the multiple CSI feedback information is used by the network device to determine the second CSI feedback information corresponding to the first encoder based on the encoder ID sequence.
69. The terminal device according to any one of claims 66-68, wherein: The seventh communication module is also used for: Receive first indication information from the network device; wherein the first indication information is used to indicate the CSI feedback performance.
70. The terminal device according to claim 69, wherein: The first indication information is used to indicate a third indicator, and the third indicator is used to characterize the CSI feedback performance.
71. The terminal device according to claim 69 or 70, wherein: The first indication information is used to indicate whether the CSI feedback performance meets a preset condition.
72. The terminal device according to any one of claims 66 to 71, wherein: The second processing module is also used for: In case of receiving second indication information from the network device, it is determined that the CSI feedback performance does not meet a preset condition, and a predetermined process is performed on the first encoder.
73. The terminal device according to claim 72, wherein: The predetermined processing includes one of the following: Switching to use other encoders except the first encoder among the Z encoders, where Z is an integer greater than 1; Updating the first encoder; Fine-tuning the first encoder; The fifth CSI obtained based on the measurement of the reference signal is processed based on the codebook.
74. The terminal device according to any one of claims 66 to 73, wherein: The seventh communication module is also used for: In the case of receiving third indication information from the network device, sending first reporting information to the network device; wherein the third indication information is used to trigger CSI feedback performance evaluation; and the first reporting information is used to indicate at least one of the following: Do you agree to evaluate the CSI feedback performance? relevant information of the first encoder; First evaluation cycle; a type of a fourth indicator, the fourth indicator being used to characterize the CSI feedback performance; The first indicator threshold.
75. The terminal device according to claim 74, wherein: The first reporting information is carried by a first RRC message, UCI or PUSCH.
76. The terminal device according to claim 74 or 75, wherein: The third indication information is carried by a second RRC message, MAC CE or DCI.
77. The terminal device according to any one of claims 66 to 73, wherein: The seventh communication module is also used for: Sending second reporting information to the network device; wherein the second reporting information is used to trigger CSI feedback performance evaluation.
78. The terminal device according to claim 77, wherein: The second reporting information is used to indicate at least one of the following: relevant information of the first encoder; Second evaluation cycle; a type of a fifth indicator, the fifth indicator being used to characterize the CSI feedback performance; The second indicator threshold.
79. The terminal device according to claim 78, wherein: The second reporting information is carried by an RRC message, UCI or PUSCH.
80. The terminal device according to any one of claims 66-79, wherein: The first encoder and the first decoder are configured by the network device, and the seventh communication module is further used for: Receive fourth indication information from the network device; wherein the fourth indication information is used to indicate relevant information of the first encoder.
81. A network device comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory so that the network device executes the method as claimed in any one of claims 1 to 25.
82. A terminal device, comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory so that the terminal device executes the method as claimed in any one of claims 26 to 40.
83. A chip, comprising: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 40.
84. A computer-readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 1 to 40.
85. A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 1 to 40.
86. A computer program causing a computer to execute the method of any one of claims 1 to 40.
87. A communication system comprising: A network device, configured to perform the method according to any one of claims 1 to 25; A terminal device, configured to execute the method as claimed in any one of claims 26 to 40.
Citation Information
Patent Citations
System and method for determining channel state information
CN114402560A
Qualifying machine learning-based CSI prediction
US20210376895A1
Channel state information feedback based on full channel estimation
US20230103220A1
Communication method and communication apparatus
WO2022012257A1
Model evaluation method and apparatus
WO2022073207A1
Cited By
Monitoring methods, terminal devices and network devices
WO2026156803A1
