Communication method and device, storage medium and program product

Abstract

The embodiment of the invention provides a communication method and device, a storage medium and a program product, relates to the technical field of communication, and is used for ensuring the performance of CSI (Channel State Information) compression feedback, and the method comprises the following steps: processing channel state information based on a first information processing mode and a second information processing mode to obtain first channel state information feedback information, and sending the first channel state information feedback information.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular, to a communication method, apparatus, storage medium, and program product. Background Art

[0002] In the field of wireless communication, artificial intelligence (AI) / machine learning (ML) technologies have begun to play an active role in fields such as the core network, network management network optimization, and access network. In recent years, significant progress has also been made in the air interface transmission technology based on AI / ML.

[0003] For most AI / ML use cases, the AI / ML model runs on one of the two ends of the communication link, that is, it runs on the base station (gNB) or the user equipment (UE). However, for the compressed feedback of channel state information (CSI), it is necessary to deploy the AI / ML model on both the UE side and the gNB side, that is, to deploy a bilateral model. The AI / ML model on the UE side is used to implement the compression of CSI, and the AI / ML model on the gNB side is used to implement the decompression of CSI. In addition, from the perspective of whether to utilize the time-domain correlation of the channel, the CSI compression / decompression model can be divided into a spatial-frequency (SF) model and a spatial-temporal-frequency (STF) model. Among them, the STF model utilizes the time-domain correlation of the channel (manifested as the model supporting the storage and use of the historical state information of the model) to compress the channel state information at the current moment, while the SF model does not utilize the time-domain correlation. When the STF model has sufficient historical state information, compared with the SF model, the STF model shows obvious performance benefits. However, when the STF model does not have sufficient historical state information, the performance of the STF model will be impaired, resulting in the performance of the STF model being lower than that of the SF model, and ultimately leading to a decline in the performance of CSI compressed feedback. Summary of the Invention

[0004] Embodiments of the present disclosure provide a communication method, apparatus, storage medium, and program product for ensuring the performance of CSI compressed feedback.

[0005] To achieve the above object, the present disclosure adopts the following technical solutions:

[0006] In a first aspect, a communication method is provided, which is applied to a first node, and the method includes:

[0007] Process the channel state information based on the first information processing method and the second information processing method to obtain first channel state information feedback information;

[0008] Send the first channel state information feedback information.

[0009] In a second aspect, a communication method is provided, which is applied to a second node. The method includes:

[0010] Receive the first channel state information feedback information, where the first channel state information feedback information is used to indicate the channel state information, and the first channel state information feedback information is obtained by processing the channel state information based on the first information processing method and the second information processing method.

[0011] In a third aspect, a communication method is provided, which is applied to a first node. The method includes:

[0012] Receive third information from the second node; the third information is used to indicate a target information processing method, and the target information processing method includes the first information processing method and / or the second information processing method;

[0013] Based on the third information, process the channel state information using the target information processing method.

[0014] In a fourth aspect, a communication method is provided, which is applied to a second node. The method includes:

[0015] Send the third information to the first node, where the third information is used to indicate a target information processing method, and the target information processing method includes the first information processing method and / or the second information processing method.

[0016] In a fifth aspect, a communication method is provided, which is applied to a first node. The method includes:

[0017] In a rank RANK adaptation scenario, send channel state information feedback information based on a specified number of data transmission layers.

[0018] In a sixth aspect, a communication method is provided, which is applied to a second node. The method includes:

[0019] In a RANK adaptation scenario, receive channel state information feedback information, where the channel state information feedback information is sent based on a specified number of data transmission layers.

[0020] In a seventh aspect, a communication device is provided, which is applied to a first node. The device includes:

[0021] A processing unit, configured to process the channel state information based on the first information processing method and the second information processing method to obtain first channel state information feedback information;

[0022] A transmitting unit, configured to transmit first channel state information feedback information.

[0023] In a eighth aspect, a communication device is provided, which is applied to a second node. The device includes:

[0024] A receiving unit, configured to receive first channel state information feedback information, where the first channel state information feedback information is used to indicate channel state information, and the first channel state information feedback information is obtained by processing the channel state information based on a first information processing method and a second information processing method.

[0025] In a ninth aspect, a communication device is provided, which is applied to a first node. The device includes:

[0026] A receiving unit, configured to receive third information from a second node; the third information is used to indicate a target information processing method, and the target information processing method includes a first information processing method and / or a second information processing method;

[0027] A processing unit, configured to process the channel state information by using the target information processing method based on the third information.

[0028] In a tenth aspect, a communication device is provided, which is applied to a second node. The device includes:

[0029] A transmitting unit, configured to send third information to a first node, where the third information is used to indicate a target information processing method, and the target information processing method includes a first information processing method and / or a second information processing method.

[0030] In an eleventh aspect, a communication device is provided, which is applied to a first node. The device includes:

[0031] A transmitting unit, configured to transmit channel state information feedback information based on a specified number of data transmission layers in a rank RANK adaptation scenario.

[0032] In a twelfth aspect, a communication device is provided, which is applied to a second node. The method includes:

[0033] A receiving unit, configured to receive channel state information feedback information in a rank RANK adaptation scenario, where the channel state information feedback information is transmitted based on a specified number of data transmission layers.

[0034] In a thirteenth aspect, a communication device is provided, including: a processor and a memory; the memory is coupled to the processor; the memory is used to store instructions executable by the processor, and the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the communication device implements the method provided in any one of the first aspect to the sixth aspect as described above.

[0035] In a fourteenth aspect, there is provided a computer-readable storage medium storing computer instructions which, when run on a computer, cause the computer to execute the method provided in any one of the first aspect to the sixth aspect.

[0036] In a fifteenth aspect, there is provided a computer program product comprising a computer program which, when run on a computer, causes the computer to execute the method provided in any one of the first aspect to the sixth aspect.

[0037] In an embodiment of the present disclosure, the first node processes channel state information based on a first information processing method and a second information processing method to obtain first channel state information feedback information, that is, compresses the channel state information by jointly using the first information processing method and the second information processing method to obtain the first channel state information feedback information, thereby ensuring the performance of CSI compression feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings are used to provide a further understanding of the technical solutions of the present invention and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the technical solutions of the present invention and do not constitute a limitation to the technical solutions of the present invention.

[0039] Figure 1 It is a schematic diagram of the processing flow of an STF model and an SF model provided in an embodiment of the present disclosure;

[0040] Figure 2 It is a schematic diagram of the structure of a communication system provided in an embodiment of the present disclosure;

[0041] Figure 3 It is a schematic diagram of the flow of a communication method provided in an embodiment of the present disclosure;

[0042] Figure 4 It is a schematic diagram of the feedback flow of channel state information feedback information provided in an embodiment of the present disclosure;

[0043] Figure 5 It is a schematic diagram of the structure of an STF model provided in an embodiment of the present disclosure;

[0044] Figure 6 It is a schematic diagram of the flow of another communication method provided in an embodiment of the present disclosure;

[0045] Figure 7 It is a schematic diagram of the flow of another communication method provided in an embodiment of the present disclosure;

[0046] Figure 8 It is a schematic diagram of the flow of another communication method provided in an embodiment of the present disclosure;

[0047] Figure 9A schematic diagram of model switching provided by an embodiment of the present disclosure;

[0048] Figure 10 Another schematic diagram of model switching provided by an embodiment of the present disclosure;

[0049] Figure 11 Another schematic diagram of model switching provided by an embodiment of the present disclosure;

[0050] Figure 12 Another schematic diagram of model switching provided by an embodiment of the present disclosure;

[0051] Figure 13 A schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0052] Figure 14 A schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0053] Figure 15 A schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0054] Figure 16 Another schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0055] Figure 17 Another schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0056] Figure 18 Another schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0057] Figure 19 Another schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0058] Figure 20 Another schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0059] Figure 21 A schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. Detailed implementation manners

[0060] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0061] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and other forms such as the third-person singular form "comprises" and the present participle form "comprising" are construed as open, inclusive meanings, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples", etc. are intended to indicate that the specific features, structures, materials or characteristics related to the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, the specific features, structures, materials or characteristics described above may be included in any one or more embodiments or examples in any appropriate manner.

[0062] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0063] In the embodiments of the present disclosure, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present disclosure should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0064] In addition, the use of "based on" means open and inclusive, because a process, step, calculation or other action "based on" one or more of the stated conditions or values may, in practice, be based on additional conditions or values beyond those stated.

[0065] In the 3GPP Rel-18 / 19 phase, the AI / ML research project for the New Radio (NR) air interface led by the Radio Access Network (RAN) 1 working group explores enhancing air interface features to support AI / ML algorithms, thereby improving performance and / or reducing complexity or overhead. The project has identified the following three promising areas for deepening the understanding of solutions and comparing performance evaluations with relevant non-AI / ML implementations and across companies:

[0066] 1) Channel state information, including compressed feedback and time-domain prediction of CSI;

[0067] 2) Beam Management (BM), including spatial / temporal beam prediction;

[0068] 3) Positioning, including direct AI / ML positioning (e.g., fingerprinting) and AI / ML-assisted positioning, where the output of the AI / ML model is a new measurement or an enhancement of existing measurements.

[0069] Among them, the performance evaluation and comparison with non-AI / ML baselines are an important part of this research project to measure the potential or benefits and complexity of AI / ML technologies. In addition, the research content of the project also includes aspects such as model Life Cycle Management (LCM), model training, data collection, model inference, performance monitoring, model transmission, and model identification.

[0070] In related technologies, the processing flows for the STF model and the SF model can be as Figure 1 shown, see Figure 1 , for the CSI compression process using the SF model, at time t, the input to the encoder only requires channel state information. However, for the CSI compression process using the STF model, in addition to the input channel state information, the historical state information of the encoder model (denoted as a t-T ) should also be used as an additional input to the encoder. Similarly, for the CSI decompression process using the SF model, at time t, the input to the decoder only requires CSI feedback information (in the form of a bitstream). However, for the CSI decompression process using the STF model, in addition to the CSI feedback information, the historical state information of the decoder model (denoted as b t-T ) should also be used as an additional input to the decoder. Where v t and v t ' respectively represent the channel state information (e.g., feature vector) at time t and the channel state information (e.g., feature vector) recovered by the decoder, and a tDenote the historical state information output by the encoder model at time t, b t Denote the historical state information output by the decoder model at time t. The historical state information includes the characteristic information of the historical channel state. In this way, the historical state information can be used to improve the performance of CSI compression feedback.

[0071] However, currently, in the case where the STF model does not have sufficient historical state information, the performance of the STF model will be impaired, and even the performance of the STF model may be lower than that of the SF model, resulting in a decline in the performance of CSI compression feedback. Therefore, in the case of insufficient historical state information, how to mitigate the performance loss of the STF model to ensure the performance of CSI compression feedback is an urgent problem to be solved.

[0072] Based on this, the embodiments of the present disclosure provide a communication method, apparatus, storage medium, and program product. The first node processes the channel state information based on the first information processing method (corresponding to the STF model) and the second information processing method (corresponding to the SF model) to obtain the first channel state information feedback information, that is, jointly compresses the channel state information using the first information processing method and the second information processing method to obtain the first channel state information feedback information, which can mitigate the performance loss of the first information processing method in the case of insufficient historical state information, thereby ensuring the performance of CSI compression feedback.

[0073] It should be noted that for a communication system adopting AI / ML technology, in the embodiments of the present disclosure, "model" is a general term used to describe that a device in a communication system can execute a processing method, function, characteristic, or group of characteristics. A "model" can be a function, function, functional module, functional module, processing method, information processing method, implementation, function, functional group, configuration, configuration set, data set (e.g., for model training), or data-driven algorithm.

[0074] The solutions of the embodiments of the present disclosure will be introduced below with reference to the accompanying drawings.

[0075] The technical solutions provided by the embodiments of the present disclosure can be applied to various mobile communication networks. For example, an NR mobile communication network adopting the fifth generation mobile networks (5G) technology, a future mobile communication network (e.g., a 6G wireless communication system), or a multi-communication fusion system, etc. The embodiments of the present disclosure do not limit this.

[0076] In the embodiments of the present disclosure, a mobile communication network (including but not limited to the third-generation 3G, fourth-generation 4G, fifth-generation 5G, and future mobile communication networks, such as the sixth-generation mobile communication network 6G) may include network-side devices (e.g., including but not limited to base stations) and receiving-side devices (e.g., including but not limited to terminals). It should be understood that, in this example, for instance, in the downlink, the first communication node (which may also be referred to as the first communication node device, the first node) may be a base station-side device, and the second communication node (which may also be referred to as the second communication node device, the second node) may be a terminal-side device. In some examples, for instance, in the uplink, the first communication node may also be a terminal-side device, and the second communication node may also be a base station-side device. In some examples, for instance, in device-to-device communication between two communication nodes, both the first communication node and the second communication node may be base stations or terminals. Therefore, whether the first node and the second node are base stations or terminals needs to be determined according to the context.

[0077] Figure 2 The following shows a schematic structural diagram of a communication system provided by an embodiment of the present disclosure. As Figure 2 shown, the communication system includes but is not limited to a first node 110 and a second node 120. Among them. Wireless signals can be transmitted, received, and related interactions can be carried out between the first node 110 and the second node 120.

[0078] In a wireless communication scenario, the first node 110 communicates with the second node 120 via a wireless channel. For example, the first node 110 is a terminal, and the second node 120 is a base station, and the terminal communicates with the base station via a wireless channel. Another example is that the first node 110 is a terminal, and the second node 120 is a wireless router, and the wireless router communicates with the terminal via a wireless channel. Another example is that the first node 110 is a first base station, and the second node 120 is a second base station, and the first base station communicates with the second base station via a wireless channel. Another example is that the first node 110 is a first terminal, and the second node 120 is a second terminal, and the first terminal communicates with the second terminal via a wireless channel. Another example is that the first node 110 is a repeater, and the second node 120 is a base station, and the base station communicates with the repeater via a wireless channel. Another example is that the first node 110 is a terminal, and the second node 120 is a repeater, and the repeater communicates with the terminal via a wireless channel. Another example is that the first node 110 is a first repeater, and the second node 120 is a second repeater, and the first repeater communicates with the second repeater via a wireless channel. Another example is that the first node 110 is a base station, and the second node 120 is a satellite, and the satellite communicates with the base station via a wireless channel. Another example is that the first node 110 is a satellite, and the second node 120 is a base station, and the base station communicates with the satellite via a wireless channel. Another example is that the first node 110 is a terminal, and the second node 120 is a satellite, and the satellite communicates with the terminal via a wireless channel. Another example is that the first node 110 is a satellite, and the second node 120 is a terminal, and the terminal communicates with the satellite via a wireless channel. Another example is that the first node 110 is a ground device, and the second node 120 is an aircraft, and the aircraft communicates with the ground device via a wireless channel. Another example is that the first node 110 is a first aircraft, and the second node 120 is a second aircraft, and the first aircraft communicates with the second aircraft via a wireless channel.

[0079] In the present disclosure, the "first" node, "second" node, "first" information processing method, "second" information processing method, "first" channel state information feedback information, "second" channel state information feedback information, unless otherwise specified, are only used for distinction in description and do not represent the front-back or precedence order.

[0080] In the present disclosure, the base station may be a base station in Long Term Evolution (LTE), Long Term Evolution Advanced (LTE-A), or an evolved Node B (eNB or eNodeB), a base station device in a 5G network, or a base station in a future communication system (such as 6G, etc.). The base station may include various macro base stations, micro base stations, home base stations, remote radio heads, reconfigurable intelligent surfaces (RISs), routers, Wireless Fidelity (WIFI) devices, or various network-side devices such as a primary cell and a secondary cell.

[0081] In the present disclosure, the terminal is a device with wireless transceiver functions, which can be deployed on land, including indoors or outdoors; it can also be deployed on water (such as a ship, etc.); it can also be deployed in the air (such as an airplane, a balloon, a satellite, etc.). The terminal may be a mobile phone, a tablet computer (Pad), a computer with wireless transceiver functions, a Virtual Reality (VR) terminal, an Augmented Reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Embodiments of the present disclosure do not limit the application scenarios. Sometimes the terminal may also be referred to as a user, a user equipment, an access terminal, a UE unit, a UE station, a mobile station, a mobile unit, a remote station, a remote terminal, a mobile device, a UE terminal, a wireless communication device, a UE agent, or a UE device, etc. Embodiments of the present disclosure do not limit this.

[0082] It should be understood that Figure 2 is an exemplary structural diagram, Figure 2 The number of devices included in the shown communication system is not limited. For example, the number of the first node and the second node is not limited. And, in addition to Figure 2 the devices shown, Figure 2 the shown communication system may further include other devices, which are not limited herein.

[0083] Next, as Figure 3 shown, an embodiment of the present disclosure provides a communication method, which is applied to a first node. The first node may be the first node 110 shown above Figure 2 . The method may include the following steps:

[0084] S101. Process the channel state information based on a first information processing method and a second information processing method to obtain first channel state information feedback information.

[0085] As an example, when the first information processing method is an empty time-frequency domain model or an empty time-frequency domain channel state information processing method, and the second information processing method is an empty frequency domain model or an empty frequency domain channel state information processing method. The first information processing method includes the first information processing method of the first node and the first information processing method of the second node, and the second information processing method includes the second information processing method of the first node and the second information processing method of the second node. The first information processing method of the first node is an empty time-frequency encoder model or an empty time-frequency domain channel state information compression method, and the second information processing method of the first node is an empty frequency encoder model or an empty frequency domain channel state information compression method. The first information processing method of the second node is an empty time-frequency decoder model or an empty time-frequency domain channel state information decompression method, and the second information processing method of the second node is an empty frequency decoder model or an empty frequency domain channel state information decompression method. The second node may be the second node 120 shown above Figure 2 . For ease of description, the following embodiments take the first node as a terminal and the second node as a base station as an example to illustrate a communication method provided by an embodiment of the present disclosure.

[0086] In some embodiments, processing the channel state information may be to compress the channel state information. The channel state information includes at least one of the following: the channel itself, a precoding vector / matrix corresponding to the channel, and an eigenvector of the channel. It should be noted that when a communication method provided by an embodiment of the present disclosure is used at the data transmission layer level, the channel state information is the channel state information corresponding to a current data transmission layer.

[0087] The channel state information feedback information refers to the compressed channel state information, and the channel state information feedback information is the output of the first information processing method / second information processing method of the first node and the input of the first information processing method / second information processing method of the second node.

[0088] It should be understood that in the related art, the channel state information is processed based on the first information processing method or the second information processing method to obtain the corresponding channel state information feedback information. However, in the embodiments of the present disclosure, the channel state information is processed based on the first information processing method and the second information processing method to obtain the first channel state information feedback information. From the above descriptions of the first information processing method and the second information processing method, it can be seen that the first information processing method is the STF model, and the second information processing method is the ST model. That is, the embodiments of the present disclosure propose to jointly process the channel state information by using the STF model and the ST model to obtain the first channel state information feedback information. Compared with the related art where the channel state information is only processed based on the STF model, in the case of insufficient historical state information, the performance loss caused by applying the STF model is reduced, thereby ensuring the performance of CSI compression feedback.

[0089] As an example, in the warm-up stage of the first information processing method, the second information processing method is enabled, that is, when the first information processing method is enabled, the second information processing method is also enabled, so that the first information processing method and the second information processing method take effect simultaneously. Then, the channel state information is processed based on the first information processing method and the second information processing method to obtain the first channel state information feedback information. Among them, the warm-up stage of the first information processing method is the initial stage after the first information processing method is enabled or the initial stage after the first state information of the first information processing method is reset. Among them, the first state information of the first information processing method can have other names, such as the historical state information of the first information processing method, and the embodiments of the present disclosure do not limit this.

[0090] It should be understood that in the initial stage after the first information processing method is enabled or the first state information of the first information processing method is reset, the first information processing method does not have sufficient first state information (for example, for the first processing in the initial stage, there is no first state information, and for the subsequent processing in the initial stage, the amount of information of the characteristic information of the historical state included in the first state information is insufficient), resulting in a decrease in the performance of the first information processing method and a decrease in the CSI compression feedback performance. Based on this, the embodiments of the present disclosure propose to enable the second information processing method in the warm-up stage of the first information processing method, that is, by enabling the SF model to utilize the advantages of the SF model being flexible enough and not relying on historical state information, the performance loss caused by simply applying the STF model is reduced, thereby ensuring the CSI compression feedback performance.

[0091] In some embodiments, the first channel state information feedback information includes a first type of channel state information feedback information and a second type of channel state information feedback information. Among them, the first type of channel state information feedback information is obtained by processing the channel state information based on a first information processing method, and the second type of channel state information feedback information is obtained by processing the channel state information based on a second information processing method. That is to say, the first node compresses the channel state information based on the first information processing method to obtain the first type of channel state information feedback information, and compresses the channel state information based on the second information processing method to obtain the second type of channel state information feedback information.

[0092] As an example, the first type of channel state information feedback information is obtained by processing the channel state information and the first state information of the first information processing method based on the first information processing method.

[0093] In some embodiments, in addition to outputting the first type of channel state information feedback information, the first information processing method of the first node also outputs updated first state information, that is, the historical state information of the updated STF model. The first state information does not need to be fed back to the second node.

[0094] In some embodiments, the duration of the warm-up phase of the first information processing method is predefined (for example, the first N feedbacks are used as the warm-up phase by default) or indicated by the network side. Taking the first information processing method as the STF encoder model and the duration of the warm-up phase being indicated by the network side as an example, the second node can carry the duration of the warm-up phase through the STF model activation information or the description information of the model or dataset. Among them, when the duration of the warm-up phase is equal to 0, it means that there is no warm-up phase. The description information of the model or dataset is used in the case where the STF encoder model of the first node is first trained by the second node and then the dataset or the STF encoder model is transmitted to the first node.

[0095] In some embodiments, the duration of the warm-up phase includes at least one feedback period or feedback count of the channel state information.

[0096] In some embodiments, the duration of the warm-up phase of the first information processing method is used for the performance monitoring of the first information processing method. In this way, it can be ensured that the minimum duration for the performance monitoring of the first information processing method is greater than the duration of the warm-up phase, thus ensuring the accuracy of the performance monitoring.

[0097] In some embodiments, the warm-up phase of the first information processing method is enabled based on one of the following methods:

[0098] Method 1: The warm-up phase is enabled by default, and the duration of the warm-up phase is always greater than 0.

[0099] Method 2: The warm-up phase is enabled by default, and the duration of the warm-up phase is greater than or equal to 0; when the duration of the warm-up phase is equal to 0, it means that the warm-up phase is not enabled.

[0100] Method 3: The warm-up phase is enabled by means of a proprietary signaling carried in the model activation information. After the warm-up phase is enabled, the duration information of the warm-up phase is valid. The model activation information is sent by the second node.

[0101] In some embodiments, when the first information processing method is enabled and / or the first status information of the first information processing method is reset at the data transmission layer level, different data transmission layers support independently enabling the first information processing method and / or resetting the first status information of the first information processing method. In other words, in the embodiments of the present disclosure, the first information processing method can be enabled and / or the first status information of the first information processing method can be reset at the data transmission layer level. That is to say, different data transmission layers enable the first information processing method or reset the first status information of the first information processing method separately. Among them, separate enabling can be that different data transmission layers all enable the first information processing method or reset the first status information of the first information processing method, or some data transmission layers enable the first information processing method or reset the first status information of the first information processing method. The embodiments of the present disclosure do not limit this.

[0102] For example, in the case of RANK adaptation, there are jumps between different RANKs. Suppose a jump from RANK-X to RANK-(X + 1) occurs and the historical state information of the STF model is newly enabled or reset for layer X + 1. At this time, after enabling the STF model or resetting the historical state information of the STF model for layer X + 1, the communication method provided by the embodiments of the present disclosure can be adopted.

[0103] Among them, RANK adaptation is a technology strongly related to wireless communication multiple-input multiple-output (MIMO) spatial division multiplexing. Based on the MIMO spatial division multiplexing technology, multiple data transmission layers (also called data streams) can transmit in parallel, thereby improving the spectral efficiency. However, under different or time-varying channel conditions, the optimal number of data transmission layers (or data streams) for the above parallel transmission (referred to as the RANK value) is different or time-varying. The RANK adaptation technology means that the terminal can measure and feedback the above RANK value to the network side or the base station based on the channel condition at the current moment; if the channel condition changes, the RANK value (referred to as the RANK feedback information) measured and feedback to the network side or the base station also changes accordingly.

[0104] In some embodiments, when enabling the first information processing mode and / or resetting the first state information of the first information processing mode at the data transmission layer level, the channel state information of the first information processing mode input to the first node or the channel state information of the second information processing mode input to the first node includes the channel state information corresponding to one data transmission layer. That is to say, the channel state information corresponding to the first information processing mode or the second information processing mode of the first node includes the channel state information corresponding to one data transmission layer.

[0105] As an example, when enabling the first information processing mode and / or resetting the first state information of the first information processing mode at the data transmission layer level, the channel state information of the first information processing mode input to the first node and the channel state information output by the first information processing mode of the second node are the channel state information corresponding to one data transmission layer, and the channel state information of the second information processing mode input to the first node and the channel state information output by the second information processing mode of the second node are the channel state information corresponding to one data transmission layer.

[0106] In some embodiments, when enabling the first information processing mode and / or resetting the first state information of the first information processing mode at the terminal level (the first information processing mode and / or the first state information of the first information processing mode cannot be independently enabled at different data transmission layers), the channel state information of the first information processing mode input to the first node or the channel state information of the second information processing mode input to the first node includes the channel state information corresponding to all data transmission layers. That is to say, the channel state information corresponding to the first information processing mode or the second information processing mode of the first node includes the channel state information corresponding to the overall all data transmission layers.

[0107] As an example, when enabling the first information processing mode and / or resetting the first state information of the first information processing mode at the terminal level, the channel state information of the first information processing mode input to the first node and the channel state information output by the first information processing mode of the second node are the channel state information corresponding to the overall all data transmission layers, and the channel state information of the second information processing mode input to the first node and the channel state information output by the second information processing mode of the second node are the channel state information corresponding to the overall all data transmission layers.

[0108] S102. Send the feedback information of the first channel state information.

[0109] In some embodiments, after obtaining the feedback information of the first channel state information, the first node sends the feedback information of the first channel state information to the second node.

[0110] In some embodiments, the first type of channel state information feedback information and the second type of channel state information feedback information are carried on the same channel state information report, or on different channel state information reports.

[0111] As an example, the first node sends a first channel state information report, and the first channel state information report includes the first type of channel state information feedback information and the second type of channel state information feedback information.

[0112] As another example, the first node sends a second channel state information report and a third channel state information report, where the second channel state information report includes the first type of channel state information feedback information, and the third channel state information report includes the second type of channel state information feedback information. Among them, when sending the second channel state information report and the third channel state information report, it may be to send the second channel state information report first and then the third channel state information report, or to send the third channel state information report first and then the second channel state information report, or to send the second channel state information report and the third channel state information report simultaneously. The embodiments of the present disclosure do not limit this.

[0113] It should be noted that the first node's choice to send the first type of channel state information feedback information and the second type of channel state information feedback information in one channel state information report, or to send them in two channel state information reports, is related to the indication information sent by the second node. For example, in the case of receiving the indication information sent by the second node for indicating to send the first type of channel state information feedback information and the second type of channel state information feedback information in one channel state information report, the first node sends the first channel state information report. Another example, in the case of receiving the indication information sent by the second node for indicating to send the first type of channel state information feedback information and the second type of channel state information feedback information in two channel state information reports, the first node sends the second channel state information report and the third channel state information report. Another example, in the case of receiving the indication information sent by the second node for indicating to send the first type of channel state information feedback information, the first node sends the second channel state information report, and in the case of receiving the indication information sent by the second node for indicating to send the second type of channel state information feedback information, the first node sends the third channel state information report.

[0114] In some embodiments, any of the above channel state information reports is carried in a high-layer signaling, such as a Radio Resource Control (RRC) message, or carried in a Media Access Control-Control Element (MAC CE).

[0115] In some embodiments, the time domain position of the second type of channel state information feedback information is before the time domain position of the first type of channel state information feedback information. That is to say, the feedback priority of the second type of channel state information feedback information is higher than that of the first type of channel state information feedback information. It should be understood that since the first type of channel state information feedback information is only used for information processing method preheating rather than for actual services, the feedback priority of the second type of channel state information feedback information is higher than that of the first type of channel state information feedback information.

[0116] Based on Figure 3 In the shown embodiment, the first node processes the channel state information based on a first information processing method (corresponding to the STF model) and a second information processing method (corresponding to the SF model) to obtain the first channel state information feedback information. That is, the channel state information is timely compressed by jointly using the first information processing method and the second information processing method to obtain the first channel state information feedback information, which can avoid or mitigate the performance loss caused by applying the first information processing method in the case of insufficient historical state information, thus ensuring the performance of CSI compression feedback.

[0117] In some embodiments, when the first information processing method of the second node is trained by the first node, after the first node finishes training the first information processing method of the second node, the first node may send the first information to the second node. The first information includes the first information processing method, or a data set for training the first information processing method of the second node; the first information further includes the duration information of the preheating stage of the first information processing method, such as the minimum duration requirement information. Taking the first information processing method as the STF model as an example, the first information includes the first information processing method, which may be that the first information includes the parameter information and structural information of the STF decoder model.

[0118] In some embodiments, after sending the first channel state information feedback information,

[0119] That is, after step S102, the first node may process the channel state information based on the first information processing method to obtain the second channel state information feedback information, and then send the second channel state information feedback information to the second node.

[0120] As an example, after the warm-up phase of the first information processing method, the channel state information is processed based on the first information processing method to obtain the second channel state information feedback information. As a possible example, the first node processes the channel state information and the first state information of the first information processing method based on the first information processing method to obtain the second channel state information feedback information.

[0121] In some embodiments, in addition to outputting the second channel state information feedback information, the first information processing method of the first node also outputs the updated first state information of the first information processing method.

[0122] That is to say, after the warm-up phase of the first information processing method, the first node turns off the second information processing method and only keeps the first information processing method effective.

[0123] The following describes this example in combination with a specific example. Exemplarily, taking the first node as the terminal, the first information processing method as the STF encoder model, and the second information processing method as the SF encoder model as an example, Figure 4 The following is a schematic diagram of the feedback process of the channel state information feedback information provided by the embodiment of the present disclosure. Refer to Figure 4 , after enabling the STF model, the first four CSI feedbacks are in the warm-up phase of the STF model. At this time, both the SF model and the STF model are effective, and the terminal feeds back two types of CSI feedback information to the base station (the CSI feedback corresponding to the output of the terminal STF encoder model and the CSI feedback corresponding to the output of the terminal SF encoder model); after the warm-up phase of the STF model ends, only the STF model is effective, and the terminal only feeds back one type of CSI feedback information to the base station (the CSI feedback information corresponding to the output of the terminal STF encoder model).

[0124] In some embodiments, after sending the first channel state information feedback information, that is, after step S102, the first node receives the second information sent by the second node. The second information is used to indicate the management decision of the warm-up phase of the first information processing method, and the management decision is used to indicate extending the warm-up phase or stopping the warm-up phase; the first node executes the management decision in response to the second information.

[0125] In some embodiments, the processing flow of the first information processing method includes the processing flow of the second information processing method. Exemplarily, taking the first information processing method as the STF encoder model and the second information processing method as the SF encoder model as an example, the structure of the STF encoder model includes the structure of the SF encoder model. For example, the structure of the STF encoder model includes the structure of the SF encoder model and the Long Short Term Memory (LSTM) structure.

[0126] That is to say, in the embodiments of the present disclosure, the structure of the STF model is composed of the structure of the SF model and the structure of the LSTM. In this way, the STF model can reuse the structure of the SF model, thereby reducing the complexity and storage overhead of jointly using the STF model and the SF model.

[0127] Exemplarily, as Figure 5 shown, it is a schematic structural diagram of an STF model provided by an embodiment of the present disclosure. Refer to Figure 5 , the terminal STF encoder structure is composed of an LSTM structure stacked on the terminal SF encoder structure, and the base station STF decoder structure is composed of an LSTM structure stacked on the base station SF decoder structure. In the terminal STF encoder structure, the dimension of the data output by the LSTM structure (module) is equal to the dimension of the data input by the terminal SF encoder structure (module); in the base station STF decoder structure, the dimension of the data output by the base station SF decoder structure (module) is equal to the dimension of the data input by the LSTM structure (module). Among them, in the above Figure 5 , v t represents the channel state information at time t, v t ' represents the channel state information recovered by the decoder at time t, a t represents the historical state information of the model output by the terminal STF encoder model at time t, b t represents the historical state information output by the base station STF decoder model at time t, a t-T represents the historical state information of the model input by the terminal STF encoder model at time t, b t-T represents the historical state information of the model input by the base station STF decoder model at time t.

[0128] In some embodiments, as Figure 6 shown, the embodiments of the present disclosure provide a communication method, which is applied to a second node. The second node may be the second node 120 shown above Figure 2 , and the method may include the following steps:

[0129] S201. Receive the first channel state information feedback information.

[0130] Among them, the first channel state information feedback information is used to indicate the channel state information, and the first information channel state information feedback information is obtained by processing the channel state information based on the first information processing method and the second information processing method. For the description of the first information processing method and the second information processing method, reference may be made to the corresponding description in the embodiments shown above Figure 3 , and details are not described herein again.

[0131] In some embodiments, the first channel state information feedback information includes a first type of channel state information feedback information and a second type of channel state information feedback information. Among them, the first type of channel state information feedback information is obtained by processing the channel state information based on a first information processing method, and the second type of channel state information feedback information is obtained by processing the channel state information based on a second information processing method. For the description of the first type of channel state information feedback information and the second type of channel state information feedback information, reference can be made to the corresponding description in the embodiments Figure 3 shown above, and details are not described herein again.

[0132] As an example, the second node receives a first channel state information report sent by the first node. The first channel state information report includes a first type of channel state information feedback information and a second type of channel state information feedback information.

[0133] As another example, the second node receives a second channel state information report and a third channel state information report sent by the first node. Among them, the second channel state information report includes a first type of channel state information feedback information, and the third channel state information report includes a second type of channel state information feedback information.

[0134] For the description of the situation in which the second node receives the first channel state information report sent by the first node or receives the second channel state information report and the third channel state information report sent by the first node, reference can be made to the corresponding description in the embodiments Figure 3 shown above, and details are not described herein again.

[0135] In some embodiments, the time domain position of the second type of channel state information feedback information is before the time domain position of the first type of channel state information feedback information.

[0136] In some embodiments, during the warm-up stage of the first information processing method of the first node, the second node receives the first channel state information feedback information sent by the first node. Among them, the duration of the warm-up stage of the first information processing method is predefined or indicated by the network side. The duration of the warm-up stage includes at least one feedback period or feedback times of the channel state information.

[0137] In some embodiments, the first information processing method of the second node can be sent by the first node to the second node after the first node completes training. As an example, the second node receives the first information sent by the first node. The first information includes the first information processing method, or a data set for training the first information processing method. Among them, the first information also includes the duration information of the warm-up stage of the first information processing method, such as the minimum duration requirement information.

[0138] In some embodiments, different data transmission layers support independently enabling a first information processing method and / or resetting first state information of the first information processing method. For example, the first information processing method is enabled and / or the first state information of the first information processing method is reset according to the data transmission layer level.

[0139] In some embodiments, when the first information processing method is enabled and / or the first state information of the first information processing method is reset according to the data transmission layer level (different data transmission layers support independently enabling or resetting the first state information of the first information processing method), the channel state information output by the first information processing method of the second node or the channel state information output by the second information processing method of the second node includes the channel state information corresponding to one data transmission layer.

[0140] In some embodiments, when the first information processing method is enabled or the first state information of the first information processing method is reset according to the terminal level (different data transmission layers cannot independently enable or reset the first state information of the first information processing method), the channel state information output by the first information processing method of the second node or the channel state information output by the second information processing method of the second node includes the channel state information corresponding to the overall of all data transmission layers.

[0141] In some embodiments, after the second node receives the first channel state information feedback information, it can reconstruct the first channel state information based on the first channel state information feedback information to obtain the reconstructed first channel state information. The reconstructed first channel state information includes the reconstructed first type of channel state information and the reconstructed second type of channel state information. For example, the first type of channel state information feedback information is used as the input of the first information processing method of the second node for reconstruction to obtain the reconstructed first type of channel state information. The second type of channel state feedback information is used as the input of the second information processing method of the second node for reconstruction to obtain the reconstructed second type of channel state information.

[0142] As an example, the second node uses the first type of channel state information feedback information and the first state information of the first information processing method of the second node as the input of the first information processing method of the second node for reconstruction to obtain the reconstructed first type of channel state information, and the updated first state information of the first information processing method of the second node.

[0143] In some embodiments, the second type of channel state information is reconstructed based on the second type of channel state information feedback information to obtain the reconstructed second type of channel state information; the reconstructed second type of channel state information is used for beamforming. As an example, in the warm-up phase of the first information processing mode of the first node, for the actual downlink service scheduling of the first node, the second node uses the reconstructed second type of channel state information for beamforming of the actual downlink service scheduling of the first node.

[0144] In some embodiments, after the second node reconstructs the first type of channel state information feedback information based on the first information processing mode and the second information processing mode to obtain the reconstructed first type of channel state information and the reconstructed second type of channel state information, the second node may, based on the similarity between the reconstructed first type of channel state information and the reconstructed second type of channel state information, then determine, according to the similarity metric value, the management decision for the warm-up phase of the first information processing mode of the first node, and the management decision is used to indicate to extend the duration of the warm-up phase or stop the warm-up phase. For example, if the similarity metric value exceeds the threshold, the management decision is to stop (end in advance) the warm-up phase, otherwise the duration of the warm-up phase remains unchanged or is extended. After determining the management decision, the second node may send the second information to the first node, and the second information is used to indicate the management decision for the warm-up phase of the first information processing mode, and the management decision is used to indicate to extend the warm-up phase or stop the warm-up phase. Among them, the second information is carried in the layer 1 / layer 2 (L1 / L2) control instruction.

[0145] In some embodiments, after receiving the first type of channel state information feedback information, that is, after step S201, the second node receives the second type of channel state information feedback information sent by the first node. Among them, the second type of channel state information feedback information is used to indicate the channel state information, and the second type of channel state information is obtained after the first node processes the channel state information based on the first information processing mode.

[0146] After the second node receives the second type of channel state information feedback information, it reconstructs the channel state information based on the second type of channel state information feedback information to obtain the reconstructed channel state information and the first state information (i.e., the historical state information) of the updated first information processing mode of the second node. The reconstructed channel state information is used for beamforming of the downlink service of the first node.

[0147] As an example, the second node inputs the second type of channel state information feedback information and the first state information of the first information processing mode of the second node into the first information processing mode of the second node for reconstruction to obtain the reconstructed channel state information and the updated first state information of the first information processing mode.

[0148] In the above embodiments, during the warm-up stage of the first information processing method, the CSI compression feedback performance is ensured by enabling the first information processing method and the second information processing method simultaneously. However, the same method is not applicable to the case where the channel state information feedback information is not correctly received by the second node. In some embodiments, when the channel state information feedback information is not correctly received by the second node due to some reasons, it may also cause the STF model (the first node STF encoder model and / or the second node STF decoder model) to not have sufficient historical state information, thereby reducing the CSI compression feedback performance. Based on this, as Figure 7 shown, an embodiment of the present disclosure provides a communication method, which can be applied to a first node, and the method may include the following steps:

[0149] S301. Receive third information from a second node.

[0150] In some embodiments, during the process of the first node processing the channel state information based on the initialization information processing method, the first node receives third information from the second node. Among them, the third information is used to indicate the target information processing method, and the target information processing method includes the first information processing method and / or the second information processing method. For example, the target information processing method includes the first information processing method. For another example, the target information processing method includes the second information processing method. For yet another example, the target information processing method includes the first information processing method and the second information processing method. The initialization information processing method is the first information processing method or the second information processing method, and the initialization information processing method is predefined or indicated by the network side. For the descriptions of the first information processing method and the second information processing method, reference may be made to the corresponding descriptions in the above Figure 3 shown embodiments, which will not be elaborated here.

[0151] In some embodiments, the third information includes or indicates at least one of the following:

[0152] Indication information for indicating the switching of the information processing method;

[0153] The number of consecutive channel state information feedback information that the second node did not correctly receive;

[0154] The number of consecutive channel state information feedback information that the second node correctly received;

[0155] The number of channel state information feedback information that the second node did not correctly receive within the first time window;

[0156] The number of channel state information feedback information that the second node correctly received within the second time window;

[0157] The first threshold value is used to determine that the target information processing mode is the second information processing mode when the first information processing mode is applied and the number of consecutive channel state information feedback messages not correctly received by the second node is greater than the first threshold value; or,

[0158] The first threshold value is used to determine that the target information processing mode is the second information processing mode when the first information processing mode is applied and the number of channel state information feedback messages not correctly received by the second node within the first time window is greater than the first threshold value;

[0159] The second threshold value is used to determine that the target information processing mode is the first information processing mode when the second information processing mode is applied and the number of consecutive channel state information feedback messages correctly received by the second node is greater than the second threshold value;

[0160] Or, the second threshold value is used to determine that the target information processing mode is the first information processing mode when the second information processing mode is applied and the number of channel state feedback messages correctly received by the second node within the second time window is greater than the second threshold value.

[0161] In some embodiments, the first threshold value is equal to the second threshold value.

[0162] S302. Process the channel state information by using the target information processing mode based on the third information.

[0163] Taking the third information including indication information for indicating the switching of the information processing mode as an example, assuming that the information processing mode currently applied by the first node is the first information processing mode, then after receiving the third information, the first node determines that the second information processing mode is the target information processing mode, and further processes the channel state information by using the second information processing mode.

[0164] In some embodiments, the indication information may include an identifier of the target information processing mode, and the first node may determine the target information processing mode based on the identifier of the target information processing mode in the indication information, and further process the channel state information by using the target information processing mode.

[0165] Taking the third information including the number of consecutive channel state information feedback messages not correctly received by the second node as an example, when the first node determines that the number of consecutive channel state information feedback messages not correctly received by the second node is greater than the first threshold value, it determines that the target information processing mode is the second information processing mode. The first threshold value is predefined or indicated by the third information, that is, the first threshold value is predefined or indicated by the network side. Similarly, the second threshold value is also predefined or indicated by the network side.

[0166] In some embodiments, the first node processes the channel state information by using a target information processing method to obtain channel state information feedback, and then sends the channel state information feedback to the second node.

[0167] In some embodiments, the third information further includes a third threshold value, which is used to reset the first state information of the first information processing method when the first information processing method is applied and the number of consecutive channel state information feedbacks that the second node fails to correctly receive is greater than the third threshold value and less than or equal to the first threshold value;

[0168] Alternatively, the third threshold value is used to reset the first state information of the first information processing method, that is, to reset the historical state information of the first information processing method, when the first information processing method is applied and the number of channel state feedbacks correctly received by the second node within the second time window is greater than the third threshold value and less than or equal to the first threshold value. The third threshold value is less than the first threshold value.

[0169] In some embodiments, when the first information processing method is applied, for each feedback of the channel state information feedback, the first node uses the channel state information and the first state information of the first information processing method of the first node as the input of the first information processing method to obtain the channel state information feedback and the updated first state information of the first information processing method, and then sends the channel state information feedback to the second node. After receiving the above channel state information feedback, the second node uses the channel state information feedback and the first state information of the first information processing method of the second node as the input of the first information processing method to obtain the reconstructed channel state information and the updated first state information of the first information processing method of the second node.

[0170] In some embodiments, when the second information processing method is applied, for each feedback of the channel state information feedback, the first node uses the channel state information as the input of the second information processing method of the first node to obtain the channel state information feedback and sends the channel state information feedback to the second node. After receiving the channel state information feedback, the second node uses the channel state information feedback as the input of the second information processing method of the second node to obtain the reconstructed channel state information.

[0171] Based on Figure 7 the embodiments shown, the first node switches the information processing method based on the third information sent by the second node, which can avoid or mitigate the performance loss caused by simply applying the first information processing method (corresponding to the STF model) when the channel state information feedback is not correctly received by the base station, thereby ensuring the performance of CSI compression feedback.

[0172] It should be noted that, in the embodiments of the present disclosure, the reasons for the CSI feedback information not being correctly received by the base station include but are not limited to: due to the existing RANK adaptation, the CSI feedback information corresponding to some data transmission layers is not fed back by the terminal (for example, when it is assumed that the RANK value switches repeatedly between RANK2 and RANK3, the CSI feedback information of layer 3 will not be fed back by the terminal in the case of RANK2), due to limited uplink resources, the CSI feedback information corresponding to some or all data transmission layers is discarded by the terminal, and the base station fails to decode the CSI feedback information.

[0173] In some embodiments, as Figure 8 shown, the embodiments of the present disclosure provide a communication method, which is applied to a second node, and the method may include the following steps:

[0174] S401. Send third information to the first node.

[0175] Wherein, the third information is used to indicate a target information processing manner, and the target information processing manner includes a first information processing manner and / or a second information processing manner.

[0176] In some embodiments, when a preset rule is satisfied, the second node sends the third information to the first node. Wherein, the preset rule includes at least one of the following:

[0177] The first preset rule: when applying the first information processing manner, and the number of consecutive channel state information feedback information not correctly received by the second node is greater than a first threshold value. Or, when applying the second information processing manner, and the number of consecutive channel state information feedback information correctly received by the second node is greater than a second threshold value.

[0178] The second preset rule: when applying the first information processing manner, and within a first time window, the number of channel state information feedback information not correctly received by the second node is greater than a first threshold value; or, when applying the second information processing manner, and within a second time window, the number of channel state feedback information correctly received by the second node is greater than a second threshold value.

[0179] In some embodiments, the third information includes or indicates at least one of the following:

[0180] Indication information for indicating a switch of the information processing manner;

[0181] The number of consecutive channel state information feedback information not correctly received by the second node;

[0182] The number of consecutive channel state information feedback information correctly received by the second node;

[0183] The number of channel state information feedback messages not correctly received by the second node within the first time window;

[0184] The number of channel state information feedback messages correctly received by the second node within the second time window;

[0185] The first threshold value, which is used to determine that the target information processing method is the second information processing method when applying the first information processing method and the number of consecutive channel state information feedback messages not correctly received by the second node is greater than the first threshold value; or,

[0186] The first threshold value is used to determine that the target information processing method is the second information processing method when applying the first information processing method and the number of channel state information feedback messages not correctly received by the second node within the first time window is greater than the first threshold value.

[0187] The second threshold value, which is used to determine that the target information processing method is the first information processing method when applying the second information processing method and the number of consecutive channel state information feedback messages correctly received by the second node is greater than the second threshold value;

[0188] Or, the second threshold value is used to determine that the target information processing method is the first information processing method when applying the second information processing method and the number of channel state feedback messages correctly received by the second node within the second time window is greater than the second threshold value.

[0189] In some embodiments, in some embodiments, the third information further includes a third threshold value, which is used to reset the first state information of the first information processing method when applying the first information processing method and the number of consecutive channel state information feedback messages not correctly received by the second node is greater than the third threshold value and less than or equal to the first threshold value; or, the third threshold value is used to reset the first state information of the first information processing method, that is, reset the historical state information of the first information processing method, when applying the first information processing method and the number of channel state feedback messages correctly received by the second node within the second time window is greater than the third threshold value and less than or equal to the first threshold value. The third threshold value is less than the first threshold value.

[0190] The above embodiments are described by taking the second node instructing the first node to switch the information processing method as an example. In some embodiments, under the condition of meeting the preset rules, the second node can also switch the information processing method.

[0191] As an example, if the first information processing method is currently being applied, the second node determines whether the number of consecutive CSI feedback messages that have not been correctly received exceeds a first threshold value. If it exceeds the first threshold value, the second information processing method is applied. If the second information processing method is currently enabled, the second node determines whether the number of consecutive CSI feedback messages that have been correctly received exceeds a second threshold value. If it exceeds the second threshold value, the first information processing method is enabled instead.

[0192] Among them, the first threshold value is equal to or not equal to the second threshold value.

[0193] Exemplarily, as Figure 9 shown, it is a schematic diagram of model switching provided by an embodiment of the present disclosure. Refer to Figure 9 in (1). Assume that the base station is currently applying the STF model and the first threshold value is 3. Taking the moment t1 as an example, the base station determines that the number of consecutive CSI feedback messages that have not been correctly received is 3, which does not exceed the first threshold value, and continues to apply the STF model. Taking the moment t2 as an example, the base station determines that the number of consecutive CSI feedback messages that have not been correctly received is 4, which exceeds the first threshold value. Starting from the moment t2, the SF model is enabled. Refer to Figure 9 in (2). Assume that the base station is currently applying the SF model and the second threshold value is 1. Taking the moment t1 as an example, the base station determines that the number of consecutive CSI feedback messages that have been correctly received is 1, which does not exceed the second threshold value, and continues to apply the SF model. Taking the moment t2 as an example, the base station determines that the number of consecutive CSI feedback messages that have been correctly received is 2, which exceeds the second threshold value. Starting from the moment t2, the STF model is enabled.

[0194] Among them, enabling the SF model includes enabling the terminal SF encoder model and the base station SF decoder model, and enabling the STF model includes enabling the terminal STF encoder model and the base station STF decoder model. Enabling the terminal SF encoder or enabling the terminal STF encoder model is achieved by one of the following methods:

[0195] 1) It is achieved through the indication of the base station; 2) The base station indicates the received information of the terminal CSI feedback message. The terminal obtains the number of consecutive CSI feedback messages that the base station has not correctly received from the received information of the CSI feedback message from the base station, and determines whether to enable the terminal SF encoder model after comparing it with the first threshold value; or obtains the number of consecutive CSI feedback messages that the base station has correctly received, and determines whether to enable the terminal STF encoder model after comparing it with the second threshold value.

[0196] As another example, if the STF model is currently being applied, the base station determines whether the number of CSI feedback messages not correctly received within the first time window exceeds a first threshold. If it exceeds the first threshold, the SF model is enabled. If the SF model is currently being applied, the base station determines whether the number of CSI feedback messages correctly received within the second time window exceeds a second threshold. If it exceeds the second threshold, the STF model is enabled. Here, the first threshold is equal to or not equal to the second threshold.

[0197] Exemplarily, as Figure 10 shown, FIG. provides another schematic diagram of model switching according to an embodiment of the present disclosure. Refer to Figure 10 in (1). Assume that the base station is currently applying the STF model and the first threshold is set to 2. Taking the time t1 as an example, the base station determines that the number of CSI feedback messages not correctly received within time window 1 is 2, which does not exceed the first threshold, and continues to apply the STF model. Continuing with the time t2 as an example, the base station determines that the number of CSI feedback messages not correctly received within time window 2 is 3, which exceeds the first threshold. Starting from time t2, the SF model is enabled. Refer to Figure 10 in (2). Assume that the base station is currently applying the SF model and the second threshold is set to 1. Taking the time t1 as an example, the base station determines that the number of CSI feedback messages correctly received within time window 1 is 1, which does not exceed the second threshold, and continues to apply the SF model. Taking the time t2 as an example, the base station determines that the number of CSI feedback messages correctly received within time window 2 is 2, which exceeds the second threshold. Starting from time t2, the STF model is enabled.

[0198] Here, enabling the SF model includes enabling the terminal SF encoder model and the base station SF decoder model, and enabling the STF model includes enabling the terminal STF encoder model and the base station STF decoder model. Enabling the terminal SF encoder model or enabling the terminal STF encoder model is achieved by one of the following methods:

[0199] 1) Achieved through base station indication; 2) The base station indicates the reception information of the terminal CSI feedback message. The terminal obtains, from the reception information of the CSI feedback message from the base station, the number of CSI feedback messages not correctly received by the base station within the first time window, and determines whether to enable the terminal SF encoder model after comparing it with the first threshold; or, obtains the number of CSI feedback messages correctly received by the base station within the first time window, and determines whether to enable the terminal STF encoder model after comparing it with the second threshold.

[0200] As another example, if the STF model is currently being applied, the base station determines whether the number of consecutive CSI feedback messages that are not correctly received exceeds a third threshold value or a first threshold value. If it exceeds the third threshold value and is less than or equal to the first threshold value, the historical state information of the STF model is reset. If it exceeds the first threshold value, the SF model is enabled. If the SF model is currently being applied, the base station determines whether the number of consecutive CSI feedback messages that are correctly received exceeds a second threshold value. If it exceeds the second threshold value, the STF model is enabled. Herein, the third threshold value is less than the first threshold value.

[0201] Exemplarily, as Figure 11 shown, another model switching schematic diagram provided by an embodiment of the present disclosure is shown. Refer to Figure 11 (1) therein. Assume that the base station is currently applying the STF model, the third threshold value is 1, and the first threshold value is 3. Taking the moment t1 as an example, the base station determines that the number of consecutive CSI feedback messages that are not correctly received is 2, which is greater than the third threshold value and less than the first threshold value, and resets the historical state information of the STF model. Taking the moment t2 as an example, the base station determines that the number of consecutive CSI feedback messages that are not correctly received is 3, which exceeds the third threshold value and is equal to the first threshold value, and resets the historical state information of the STF model. Continuing with the moment t3 as an example, the base station determines that the number of consecutive CSI feedback messages that are not correctly received is 4, which exceeds the first threshold value. Starting from the moment t3, the SF model is enabled. Refer to Figure 11 (2) therein. Assume that the base station is currently applying the SF model and the second threshold value is 1. Taking the moment t1 as an example, the base station determines that the number of consecutive CSI feedback messages that are correctly received is 1, which does not exceed the second threshold value, and continues to apply the SF model. Taking the moment t2 as an example, the base station determines that the number of consecutive CSI feedback messages that are correctly received is 2, which exceeds the second threshold value. Starting from the moment t2, the STF model is enabled.

[0202] Among them, enabling the SF model includes enabling the terminal SF encoder model and the base station SF decoder model, enabling the STF model includes enabling the terminal STF encoder model and the base station STF decoder model, and resetting the historical state information of the STF model includes resetting the historical state information of the terminal STF encoder model and the historical state information of the base station STF decoder model. Enabling the terminal SF encoder model, or enabling the terminal STF encoder model, or resetting the historical state information of the terminal STF encoder model is achieved by one of the following methods: 1) achieved through base station indication; 2) the base station indicates the received information of the terminal CSI feedback information, and the terminal obtains the number of consecutive CSI feedback information that the base station has not correctly received from the received information of the CSI feedback information from the base station. After comparing with the third threshold and the first threshold, it is determined whether to reset the historical state information of the terminal STF encoder model or whether to enable the terminal SF encoder model; alternatively, obtain the number of consecutive CSI feedback information correctly received by the base station, and determine whether to enable the terminal STF encoder model after comparing with the second threshold. Among them, the first threshold, the second threshold, and the third threshold are agreed values or configured through the base station.

[0203] As another example, if the STF model is currently being applied, the base station determines whether the number of CSI feedback information not correctly received within the first time window range exceeds the third threshold or the first threshold. If it exceeds the third threshold and is less than the first threshold, the historical state information of the STF model is reset. If it exceeds the first threshold, the SF model is enabled; if the SF model is currently being applied, the base station determines whether the number of consecutive CSI feedback information correctly received within the second time window range exceeds the second threshold. If it exceeds the second threshold, the STF model is enabled.

[0204] Among them, the third threshold is less than the first threshold.

[0205] Exemplarily, as Figure 12 shown, another model switching schematic diagram provided by the embodiment of the present disclosure is shown. Refer to Figure 12 in (1). Assume that the base station is currently applying the STF model, and the third threshold is 2 and the first threshold is 3. Taking the t1 moment as an example, the base station determines that the number of consecutive CSI feedback information not correctly received within the time window 1 is 2, which is equal to the third threshold. The STF model continues to be applied and the historical state information of the STF model does not need to be reset. Taking the t2 moment as an example, the base station determines that the number of consecutive CSI feedback information not correctly received within the time window 2 is 3, which is greater than the third threshold and equal to the second threshold. The historical state information of the STF model is reset. Taking the t3 moment as an example, the base station determines that the number of consecutive CSI feedback information not correctly received within the time window 3 is 4, which exceeds the first threshold. Starting from the t3 moment, the SF model is enabled. Refer to Figure 12In (2) above, assume that the base station is currently applying the SF model and the second threshold value is set to 1. Taking time t1 as an example, the base station determines that the number of consecutive CSI feedback messages correctly received within time window 1 is 1, which does not exceed the second threshold value. The SF model continues to be applied. Taking time t2 as an example, the base station determines that the number of consecutive CSI feedback messages correctly received within time window 2 is 2, which exceeds the second threshold value. Starting from time t2, the STF model is enabled.

[0206] Among them, enabling the SF model includes enabling the terminal SF encoder model and the base station SF decoder model. Enabling the STF model includes enabling the terminal STF encoder model and the base station STF decoder model. Resetting the historical state information of the STF model includes resetting the historical state information of the terminal STF encoder model and the historical state information of the base station STF decoder model. Enabling the terminal SF encoder model, or enabling the terminal STF encoder model, or resetting the historical state information of the terminal STF encoder model is achieved by one of the following methods: 1) Achieved through base station indication; 2) The base station indicates the received information of the terminal CSI feedback message. The terminal obtains the number of CSI feedback messages not correctly received by the base station within the first time window from the received information of the CSI feedback message from the base station, and determines whether to reset the historical state information of the terminal STF encoder model or whether to enable the terminal SF encoder model after comparing with the third threshold value and the first threshold value; alternatively, obtains the number of CSI feedback messages correctly received by the base station within the second time window, and determines whether to enable the terminal STF encoder model after comparing with the second threshold value. The first threshold value, the second threshold value, and the third threshold value are agreed values or configured by the base station.

[0207] Based on Figure 8 the embodiments shown above, in the case where the CSI feedback message is not correctly received by the base station due to some reasons, the switching between the first information processing method (corresponding to the STF model) and the second information processing method (corresponding to the SF model) is performed according to predefined rules, reducing or avoiding the performance loss caused by simply applying the first information processing method, thereby ensuring the performance of CSI compressed feedback.

[0208] As can be seen from the above description, when CSI feedback information is not correctly received by the base station due to some reasons, it may lead to insufficient historical state information in the terminal STF encoder model and / or the base station STF decoder model. One of the reasons for the incorrect reception of CSI feedback information by the base station is that in the existing RANK adaptation technology, the terminal defaults to feedback CSI feedback information to the base station according to the time-varying number of data transmission layers (or called data stream numbers) equal to the RANK value, which may result in the CSI feedback information of some data transmission layers (or data streams) not being fed back by the terminal. To avoid the situation where the terminal STF encoder model and / or the base station STF decoder model do not have sufficient historical state information due to the reason that the CSI information of some data transmission layers is not fed back by the terminal caused by RANK adaptation, as Figure 13 shown, an embodiment of the present disclosure further provides a communication method, which is applied to a first node, and the method may include the following steps:

[0209] S501. In a RANK adaptation scenario, send channel state information feedback information based on a specified number of data transmission layers.

[0210] In some embodiments, the RANK value fed back by the first node to the second node is less than or equal to the specified number of data transmission layers. That is to say, the first node may also send RANK feedback information to the second node, where the RANK feedback information includes a RANK value, and the RANK value is less than or equal to the specified number of data transmission layers.

[0211] In some embodiments, the specified number of data transmission layers includes at least one of the following:

[0212] The maximum RANK value supported by the first node; for example, assuming that the first node has 4 receiving antennas, the maximum RANK value supported by the first node is 4. In this case, the first node always feeds back 4 CSI feedback information corresponding to 4 data transmission layers to the second node. However, the actual RANK value fed back by the first node to the second node is one of 1, 2, 3, and 4.

[0213] The maximum RANK value among the currently measured and historically fed back RANK values of the first node; for example, assuming that the historically fed back RANK values of the first node include 2 and 3, and the currently planned RANK value to be fed back is 4. In this case, the first node feeds back 4 CSI feedback information corresponding to 4 data transmission layers to the second node at the current moment; or, assuming that the historically fed back RANK values of the first node include 3 and 4, and the currently planned RANK value to be fed back is 2. In this case, the first node still feeds back 4 CSI feedback information corresponding to 4 data transmission layers to the second node at the current moment.

[0214] Configuration value; that is, the specified number of data transmission layers is configured for the second node. For example, the second node configures the first node to feedback CSI feedback information to the second node according to 3 data transmission layers. In this case, the first node always feedbacks 3 CSI feedback information corresponding to 3 data transmission layers to the second node, but the actual RANK value feedback to the second node is one of 1, 2, and 3.

[0215] In the embodiments of the present disclosure, the RANK information or RANK value refers to the optimal number of data transmission layers for spatial multiplexing, and the RANK feedback information is the feedback information including the RANK information or RANK value.

[0216] Based on Figure 13 In the shown embodiment, by sending the channel state information feedback information according to the specified number of data transmission layers, the problem of missing historical state information of the first information processing method (corresponding to the STF model) caused by the fact that the CSI information corresponding to the specified data transmission layer is not feedback by the first node due to RANK adaptation is avoided, thereby avoiding or reducing the performance loss of the first information processing method (corresponding to the STF model) and ensuring the performance of CSI compressed feedback.

[0217] In some embodiments, as Figure 14 shown, the embodiments of the present disclosure provide a communication method, which is applied to the second node, and the method may include the following steps:

[0218] S601. In the RANK adaptation scenario, receive the channel state information feedback information.

[0219] Wherein, the channel state information feedback information is sent based on the specified number of data transmission layers.

[0220] In some embodiments, step S601 may be alternatively described as receiving the channel state information feedback information according to the specified number of data transmission layers in the RANK adaptation scenario.

[0221] In some embodiments, the second node receives the RANK feedback information sent by the first node, wherein the RANK feedback information includes the RANK value, and the RANK value is less than or equal to the specified number of data transmission layers.

[0222] In some embodiments, the specified number of data transmission layers includes at least one of the following:

[0223] The maximum RANK value supported by the first node;

[0224] The maximum RANK value among the RANK values currently measured and historically feedback by the first node;

[0225] Configuration value.

[0226] For the description of the specified number of data transmission layers, reference may be made to the corresponding description in the embodiment shown above Figure 12 and will not be elaborated here.

[0227] In some embodiments, the first node executes or closes the communication method provided in the embodiments of the present disclosure according to the indication information of the second node.

[0228] The communication method provided in the embodiments of the present disclosure can be used at the data transmission layer level or the terminal level. If it is used at the data transmission layer level, the input of the terminal STF or SF encoder model and the output of the base station STF or SF decoder model are the channel state information corresponding to one data transmission layer. As an option, the communication method provided in the embodiments of the present disclosure can be switched at the data transmission layer level, so that the communication method provided in the embodiments of the present disclosure can be used for some data transmission layers, and the remaining transmission layers are not used. If it is used at the terminal level, the input of the terminal STF or SF encoder model and the output of the base station STF or SF decoder model are the channel state information corresponding to all data transmission layers as a whole. At this time, the communication method provided in the embodiments of the present disclosure can only be switched at the terminal level, that is, it is not possible to use the communication method provided in the embodiments of the present disclosure for some data transmission layers.

[0229] The above mainly introduces the solution provided by the present disclosure from the perspective of the interaction between each node. It can be understood that each node, such as the first node or the second node, includes the corresponding hardware structure and / or software module for implementing the above functions. Those skilled in the art should easily realize that, combined with the algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0230] The embodiments of the present disclosure can divide the first node or the second node into function modules according to the above method embodiments. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one function module. The above integrated module can be implemented in the form of hardware or software. It should be noted that the division of modules in the embodiments of the present disclosure is illustrative, only a logical function division, and there may be other division methods in actual implementation. The following will be described by taking the example of dividing each function module corresponding to each function.

[0231] Figure 15A schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure. As Figure 15 shown, the communication device 70 includes a processing unit 701 and a sending unit 702. In some embodiments, the communication device 70 further includes a receiving unit 703.

[0232] The communication device 70 may be the above-mentioned first node or a chip in the first node. When the communication device 70 is used to implement the functions of the first node in the above embodiments, each unit is specifically used to implement the following functions.

[0233] The processing unit 701 is configured to process channel state information based on a first information processing method and a second information processing method to obtain first channel state information feedback information;

[0234] The sending unit 702 is configured to send the first channel state information feedback information.

[0235] In some embodiments, the processing unit 701 is specifically configured to enable the second information processing method during the warm-up stage of the first information processing method; process the channel state information based on the first information processing method and the second information processing method to obtain first channel state information feedback information, where the warm-up stage of the first information processing method is the initial stage after enabling the first information processing method or the initial stage after resetting the first state information of the first information processing method.

[0236] In some embodiments, the sending unit 702 is specifically configured to send a first channel state information report, and the first channel state information report includes first-type channel state information feedback information and second-type channel state information feedback information.

[0237] In some embodiments, the sending unit 702 is specifically configured to send a second channel state information report and a third channel state information report, where the second channel state information report includes first-type channel state information feedback information, and the third channel state information report includes second-type channel state information feedback information.

[0238] In some embodiments, the sending unit 702 is further configured to send first information, the first information includes the first information processing method, or a data set for training the first information processing method; the first information further includes the minimum duration requirement information of the warm-up stage of the first information processing method.

[0239] In some embodiments, the processing unit 701 is further configured to process the channel state information based on the first information processing method to obtain second channel state information feedback information;

[0240] The sending unit 702 is further configured to send the second channel state information feedback information.

[0241] In some embodiments, the processing unit 701 is specifically configured to process the channel state information based on the first information processing method after the warm-up phase of the first information processing method, so as to obtain the second channel state information feedback information.

[0242] In some embodiments, the receiving unit 703 is configured to receive second information, where the second information is used to indicate the management decision of the warm-up phase of the first information processing method, and the management decision is used to indicate to extend the warm-up phase or stop the warm-up phase;

[0243] The processing unit 701 is further configured to execute the management decision in response to the second information.

[0244] Figure 16 It is a schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 16 shown, the communication device 80 includes a receiving unit 801. In some embodiments, the communication device 80 may further include a processing unit 802.

[0245] The communication device 80 may be the above-mentioned second node or a chip in the second node. When the communication device 80 is used to implement the functions of the second node in the above embodiments, each unit is specifically configured to implement the following functions.

[0246] The receiving unit 801 is configured to receive the first channel state information feedback information, where the first channel state information feedback information is used to indicate the channel state information, and the first channel state information feedback information is obtained by processing the channel state information based on the first information processing method and the second information processing method.

[0247] In some embodiments, the processing unit 802 is configured to reconstruct the second type of channel state information based on the second type of channel state information feedback information to obtain the reconstructed second type of channel state information; the reconstructed second type of channel state information is used for beamforming.

[0248] Figure 17 It is a schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 17 shown, the communication device 90 includes a receiving unit 901 and a processing unit 902.

[0249] The communication device 90 may be the above-mentioned first node or a chip in the first node. When the communication device 90 is used to implement the functions of the first node in the above embodiments, each unit is specifically configured to implement the following functions.

[0250] The receiving unit 901 is configured to receive third information from the second node; the third information is used to indicate the target information processing method, and the target information processing method includes the first information processing method and / or the second information processing method;

[0251] A processing unit 902, configured to process the channel state information by using a target information processing manner based on third information.

[0252] Figure 18 This is a schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 18 shown, the communication device 100 includes a sending unit 1001.

[0253] The communication device 100 may be the above-mentioned second node or a chip in the second node. When the communication device 100 is used to implement the functions of the second node in the above embodiment, each unit is specifically used to implement the following functions.

[0254] The sending unit 1001 is configured to send third information to the first node, where the third information is used to indicate a target information processing manner, and the target information processing manner includes a first information processing manner and / or a second information processing manner.

[0255] Figure 19 This is a schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 19 shown, the communication device 110 includes a sending unit 1101.

[0256] The communication device 110 may be the above-mentioned first node or a chip in the first node. When the communication device 110 is used to implement the functions of the first node in the above embodiment, each unit is specifically used to implement the following functions.

[0257] The sending unit 1101 is configured to send channel state information feedback information based on a specified data transmission layer number in a rank RANK adaptation scenario.

[0258] In some embodiments, the sending unit 1101 is further configured to send RANK feedback information, where the RANK feedback information includes a RANK value, and the RANK value is less than or equal to the specified data transmission layer number.

[0259] Figure 20 This is a schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 20 shown, the communication device 120 includes a receiving unit 1201.

[0260] The communication device 120 may be the above-mentioned second node or a chip in the second node. When the communication device 120 is used to implement the functions of the second node in the above embodiment, each unit is specifically used to implement the following functions.

[0261] The receiving unit 1201 is configured to receive channel state information feedback information in a RANK adaptation scenario, where the channel state information feedback information is sent based on a specified data transmission layer number.

[0262] It should be noted that Figures 15 to 20 the units in Figures 15 to 20 can also be referred to as modules. For example, the sending unit can be called the sending module. Additionally, in the

[0263] Figures 15 to 20 embodiment shown, the names of the respective units may not be the names shown in the figure. For example, the sending unit can also be called the communication unit, and the receiving unit can also be called the communication unit. When the respective units in

[0264] are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present disclosure. The storage media for storing the computer software product include: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

[0264] When the above communication devices 70 to 120 implement the functions of the above integrated modules in the form of hardware, the embodiments of the present disclosure provide a structural schematic diagram of a communication device. As Figure 21 shown, the communication device 130 includes: a processor 1302, a communication interface 1303, and a bus 1304. Optionally, the communication device 130 may further include a memory 1301.

[0265] The processor 1302 can be used to implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosed content of the embodiments of the present disclosure. The processor 1302 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosed content of the embodiments of the present disclosure. The processor 1302 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0266] A communication interface 1303 is used to connect to other devices via a communication network. The communication network can be an Ethernet, a radio access network, a wireless local area network (WLAN), etc.

[0267] The memory 1301 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0268] As a possible implementation, the memory 1301 can exist independently of the processor 1302. The memory 1301 can be connected to the processor 1302 via a bus 1304 for storing instructions or program code. When the processor 1302 calls and executes the instructions or program code stored in the memory 1301, the communication method provided by the embodiments of the present disclosure can be implemented.

[0269] In another possible implementation, the memory 1301 can also be integrated with the processor 1302.

[0270] The bus 1304 can be an extended industry standard architecture (EISA) bus, etc. The bus 1304 can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 21 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0271] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the first node or the second node can be divided into different functional modules to complete all or part of the functions described above.

[0272] Embodiments of the present disclosure also provide a computer-readable storage medium. All or part of the processes in the above method embodiments can be completed by computer instructions instructing relevant hardware. The program can be stored in the above computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The above computer-readable storage medium can also be an external storage device of the above first node or second node, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the above first node or second node. Further, the above computer-readable storage medium can also include both the internal storage unit of the above first node or second node and the external storage device. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above first node or second node. The above computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0273] Embodiments of the present disclosure also provide a computer program product. The computer product includes a computer program. When the computer program product runs on a computer, it causes the computer to execute any one of the communication methods provided in the above embodiments.

[0274] Although the present disclosure has been described in conjunction with various embodiments, however, in the process of implementing the claimed present disclosure, those skilled in the art can understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure content, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality of cases. A single processor or other unit can implement several functions recited in the claims. Certain measures are recited in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0275] Although the present disclosure has been described in conjunction with specific features and their embodiments, it is obvious that various modifications and combinations can be made without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are only exemplary descriptions of the present disclosure defined by the appended claims, and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present disclosure. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalent technologies, the present disclosure is also intended to include these changes and modifications.

[0276] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present disclosure should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that: Applied to the first node, the method comprises: Processing the channel state information based on the first information processing mode and the second information processing mode to obtain first channel state information feedback information; Send the first channel state information feedback information.

2. The method according to claim 1, characterized in that The processing of the channel state information based on the first information processing mode and the second information processing mode to obtain first channel state information feedback information includes: In the warm-up phase of the first information processing mode, enabling the second information processing mode; The channel state information is processed based on the first information processing mode and the second information processing mode to obtain the first channel state information feedback information, wherein the warm-up stage of the first information processing mode is an initial stage after enabling the first information processing mode or an initial stage after resetting the first state information of the first information processing mode.

3. The method according to claim 1, characterized in that The first channel state information feedback information includes first-category channel state information feedback information and second-category channel state information feedback information, wherein the first-category channel state information feedback information is obtained by processing the channel state information based on the first information processing method, and the second-category channel state information feedback information is obtained by processing the channel state information based on the second information processing method.

4. The method according to claim 3, characterized in that The sending the first channel state information feedback information includes: A first channel state information report is sent, where the first channel state information report includes the first type of channel state information feedback information and the second type of channel state information feedback information.

5. The method according to claim 3, characterized in that: The sending the first channel state information feedback information includes: A second channel state information report and a third channel state information report are sent, wherein the second channel state information report includes the first type of channel state information feedback information, and the third channel state information report includes the second type of channel state information feedback information.

6. The method according to claim 3, characterized in that The time domain position of the second type of channel state information feedback information is located before the time domain position of the first type of channel state information feedback information.

7. The method according to claim 2, characterized in that The duration of the warm-up phase of the first information processing method is predefined or indicated by the network side.

8. The method according to claim 7, characterized in that The duration of the warm-up phase includes at least one feedback cycle or feedback times of the channel state information.

9. The method according to claim 2, characterized in that: The duration of the warm-up phase of the first information processing method is used for performance monitoring of the first information processing method.

10. The method according to claim 1, characterized in that Different data transmission layers support independently enabling the first information processing mode and / or resetting the first status information of the first information processing mode.

11. The method according to claim 1, characterized in that: When the information processing method is used at the data transmission layer level, the channel state information of the first information processing method input to the first node or the channel state information of the second information processing method input to the first node includes channel state information corresponding to a data transmission layer.

12. The method according to claim 1, characterized in that When the information processing method is used at the terminal level, the channel state information of the first information processing method input to the first node or the channel state information of the second information processing method input to the first node includes the channel state information corresponding to all data transmission layers.

13. The method according to claim 2, characterized in that The method further comprises: Sending first information, wherein the first information includes the first information processing method, or a data set used to train the first information processing method; the first information also includes minimum required duration information of a warm-up phase of the first information processing method.

14. The method according to claim 2, characterized in that The method further comprises: Processing the channel state information based on the first information processing mode to obtain second channel state information feedback information; Send the second channel state information feedback information.

15. The method according to claim 14, characterized in that The processing of the channel state information based on the first information processing mode to obtain second channel state information feedback information includes: After a warm-up phase of the first information processing mode, the channel state information is processed based on the first information processing mode to obtain the second channel state information feedback information.

16. The method according to claim 2, characterized in that The method further comprises: receiving second information, where the second information is used to indicate a management decision of a preheating phase of the first information processing method, where the management decision is used to indicate extending the preheating phase or stopping the preheating phase; The management decision is executed in response to the second information.

17. The method according to claim 1, characterized in that The processing flow of the first information processing method includes the processing flow of the second information processing method.

18. The method according to claim 1, characterized in that The first information processing method is a space-time-frequency encoder model or a space-time-frequency domain channel state information compression method, and the second information processing method is a space-frequency encoder model or a space-frequency domain channel state information compression method.

19. The method according to claim 18, characterized in that The structure of the space-time-frequency encoder model includes the structure of the space-frequency encoder model and the structure of the long short-term memory (LSTM).

20. A communication method, characterized in that: Applied to the second node, the method comprises: First channel state information feedback information is received, wherein the first channel state information feedback information is used to indicate channel state information, and the first channel state information feedback information is obtained by processing the channel state information based on a first information processing method and a second information processing method.

21. The method according to claim 20, characterized in that The first channel state information feedback information includes first-category channel state information feedback information and second-category channel state information feedback information, wherein the first-category channel state information feedback information is obtained by processing the channel state information based on the first information processing method, and the second-category channel state information feedback information is obtained by processing the channel state information based on the second information processing method.

22. The method according to claim 21, characterized in that The method further comprises: The second type of channel state information is reconstructed based on the second type of channel state information feedback information to obtain reconstructed second type of channel state information; the reconstructed second type of channel state information is used for beamforming.

23. A communication method, characterized in that: Applied to the first node, the method comprises: receiving third information from the second node; the third information is used to indicate a target information processing mode, and the target information processing mode includes a first information processing mode and / or a second information processing mode; Based on the third information, the channel state information is processed using the target information processing method.

24. The method according to claim 23, characterized in that The third information includes or indicates at least one of the following: Instruction information used to indicate the switching of information processing mode; the number of consecutive channel state information feedback information not correctly received by the second node; the number of consecutive channel state information feedback information correctly received by the second node; within the first time window, the amount of channel state information feedback information incorrectly received by the second node; the amount of channel state information feedback information correctly received by the second node within the second time window; a first threshold value, where the first threshold value is used to determine that the target information processing mode is the second information processing mode when the first information processing mode is applied and the number of continuous channel state information feedback information that is not correctly received by the second node is greater than the first threshold value; or, The first threshold value is used to determine that the target information processing mode is the second information processing mode when the first information processing mode is applied and the amount of channel state information feedback information that is not correctly received by the second node within the first time window is greater than the first threshold value; a second threshold value, where the second threshold value is used to determine that the target information processing mode is the first information processing mode when the second information processing mode is applied and the number of continuous channel state information feedback information correctly received by the second node is greater than the second threshold value; Alternatively, the second threshold value is used to determine that the target information processing mode is the first information processing mode when the second information processing mode is applied and, within the second time window, the number of channel state feedback information correctly received by the second node is greater than the second threshold value.

25. The method according to claim 24, characterized in that The third information further includes a third threshold value, and the third threshold value is used to reset the first state information of the first information processing mode when the first information processing mode is applied and the number of continuous channel state information feedback information that is not correctly received by the second node is greater than the third threshold value and less than or equal to the first threshold value; or, The third threshold value is used to reset the first state information of the first information processing mode when the first information processing mode is applied and within the second time window, the number of channel state feedback information correctly received by the second node is greater than the third threshold value and less than or equal to the first threshold value.

26. A communication method, characterized in that: Applied to the second node, the method comprises: Sending third information to the first node, where the third information is used to indicate a target information processing mode, where the target information processing mode includes the first information processing mode and / or the second information processing mode.

27. A communication method, characterized in that: Applied to the first node, the method comprises: In the rank adaptation scenario, channel state information feedback information is sent based on the specified number of data transmission layers.

28. The method according to claim 27, characterized in that The method further comprises: Send RANK feedback information, where the RANK feedback information includes a RANK value, and the RANK value is less than or equal to the specified number of data transmission layers.

29. The method according to claim 27, characterized in that The specified number of data transmission layers includes at least one of the following: The maximum RANK value supported by the first node; The maximum RANK value among the RANK values ​​currently measured and historically fed back by the first node; Configuration value.

30. A communication method, characterized in that: Applied to the second node, the method comprises: In a RANK adaptive scenario, channel state information feedback information is received, wherein the channel state information feedback information is sent based on a specified number of data transmission layers.

31. A communication device, characterized in that: include: Memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 30 is performed.

32. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 30.

33. A computer program product, characterized in that The computer program product comprises computer instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 30.

Images