Model-based feedback method, apparatus, and device, medium, and program product

Abstract

The present application relates to the field of wireless communications, and discloses a model-based feedback method, apparatus, and device, a medium, and a program product. The method comprises: sending feedback information, the feedback information being obtained on the basis of A-bit feedback response information and an agreed model, and A being a positive integer. Because the model has relatively high scalability and flexibility, and real-time response to feedback of multi-bit response information is facilitated, thereby improving feedback efficiency, while also ensuring the accuracy and granularity of the feedback information.

Description

Model-based feedback methods, devices, equipment, media, and program products Technical Field

[0001] This application relates to the field of wireless communication, and in particular to a model-based feedback method, apparatus, device, medium, and program product. Background Technology

[0002] Communication equipment requires feedback of Hybrid Automatic Repeat reQuest (HARQ) and Acknowledgement (ACK) information. Due to reliability requirements, there are limitations on the number of bits and physical resources available for feedback information in air interface transmission.

[0003] However, such limitations on the number of bits or physical resources for feedback information inevitably reduce the precision of the feedback information and may even lead to inaccuracy.

[0004] Summary of the Invention

[0005] This application provides a model-based feedback method, apparatus, device, medium, and program product, the technical solution of which includes at least:

[0006] According to one aspect of the embodiments of this application, a model-based feedback method is provided, the method comprising:

[0007] Send feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0008] According to another aspect of the embodiments of this application, a model-based feedback method is provided, the method comprising:

[0009] The system receives feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0010] According to one aspect of the embodiments of this application, a model-based feedback device is provided, the device comprising:

[0011] The sending module is used to send feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0012] According to another aspect of the embodiments of this application, a model-based feedback device is provided, the device comprising:

[0013] The receiving module is used to receive feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0014] According to one aspect of the embodiments of this application, a model-based feedback device is provided. The communication device includes: a processor; a transceiver connected to the processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to load and execute the executable instructions to implement the model-based feedback method as described in the foregoing aspects.

[0015] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores at least one program that is loaded and executed by a processor to implement the model-based feedback method as described in the foregoing aspects.

[0016] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium, a processor retrieving the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to implement the model-based feedback method as described in the above aspects.

[0017] According to one aspect of the embodiments of this application, a chip is provided, the chip including programmable logic circuitry and / or at least a program, the chip being configured to implement the model-based feedback method as described in the foregoing aspects based on the programmable logic circuitry and / or the at least a program.

[0018] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0019] Thanks to the model's high scalability, flexibility, and processing efficiency, using the model to implement feedback helps to improve feedback efficiency while ensuring the efficiency, accuracy, and precision of the feedback information. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 shows a schematic diagram of a wireless communication system provided in an exemplary embodiment of this application;

[0022] Figure 2 shows a flowchart of a model-based feedback method provided in an exemplary embodiment of this application;

[0023] Figure 3 shows a flowchart of a model-based feedback method provided in an exemplary embodiment of this application;

[0024] Figure 4 shows a flowchart of a model-based feedback method provided in an exemplary embodiment of this application;

[0025] Figure 5 shows a flowchart of a model-based feedback method provided in an exemplary embodiment of this application;

[0026] Figure 6 illustrates a schematic diagram of a model-based feedback method provided in an exemplary embodiment of this application;

[0027] Figure 7 shows a structural block diagram of a model-based feedback device provided in an exemplary embodiment of this application;

[0028] Figure 8 shows a structural block diagram of a model-based feedback device provided in an exemplary embodiment of this application;

[0029] Figure 9 shows a schematic diagram of the structure of a model-based feedback device provided in an exemplary embodiment of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings. Exemplary embodiments will be described in detail here, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0031] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0032] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein can be interpreted as "when," "when," or "in response to determination." In this specification, when expressing the meaning of Boolean Values, it is expressed that "0" represents "first meaning" and "1" represents "second meaning." Without loss of generality, those skilled in the art will understand that the meanings they represent can be interchanged, that is, "1" represents "first meaning" and "0" represents "second meaning."

[0033] In New Radio (NR) systems, a Cyclic Redundancy Check (CRC) record is added to each Transport Block (TB). This CRC is generated based on the entire TB and can therefore be considered a TB-level CRC. The receiver uses the TB-level CRC to determine if the TB has been correctly decoded. A large TB (including the TB-level CRC) can be divided into multiple Code Blocks (CBs). Each CB has its own CRC record added, generated based on the CB and thus considered a CB-level CRC. Each CB is encoded and decoded independently. The receiver uses the CB-level CRC to determine if the CB has been correctly decoded.

[0034] Accordingly, the NR system supports two types of feedback methods: Hybrid Automatic Repeat reQuest (HARQ) and Acknowledgement (ACK).

[0035] I. HARQ-ACK information is generated based on TB (TB-based HARQ-ACK), meaning one TB corresponds to one bit of HARQ-ACK information. If any CB in a TB fails to decode, the feedback information for that TB is a negative acknowledgement (NACK). If all CBs in a TB are successfully decoded, but the TB-level CRC checksum included in that TB fails or fails, the feedback information for that TB is NACK. In other words, if any CRC checksum in either the CB-level CRC or the TB-level CRC corresponding to a TB fails or fails, the feedback information for that TB is NACK.

[0036] II. HARQ-ACK information is generated based on coded block groups (CB Groups, CBGs) (CBG-based HARQ-ACK). This involves dividing a TB (Block Module) into N CBGs (where N is an integer greater than or equal to 1), with each CBG containing at least one CB and each CBG corresponding to 1 bit of HARQ-ACK information. If the decoding of any CB in a CBG fails, the feedback information for that CBG is NACK. If all CBGs in a TB are successfully decoded, but the TB-level CRC checksum of that TB fails or fails, the feedback information for all CBGs in that TB is NACK.

[0037] The purpose of introducing CBG-based HARQ-ACK is to improve data retransmission efficiency. For example, when some CBGs in a large TB fail to decode, only the CBGs that failed to decode need to be retransmitted, instead of retransmitting the entire TB. From this perspective, the smaller the granularity of the CBGs, the better; ideally, each CB should correspond to 1 bit of feedback information. Smaller feedback granularity results in increased feedback overhead. The reliability requirements for feedback information are much higher than those for data reliability; therefore, the capacity of uplink control signaling is usually small. Considering both downlink retransmission efficiency and uplink control signaling overhead, in NR systems, a TB can be divided into a maximum of 8 CBGs for single-codeword transmission and a maximum of 4 CBGs for dual-codeword transmission. In other words, a downlink channel can correspond to a maximum of 8 bits of HARQ-ACK information.

[0038] The NR system supports multiple HARQ-ACK codebook generation methods. Regardless of the type of HARQ-ACK codebook, the goal is to multiplex the HARQ-ACK information corresponding to multiple downlink channels before transmission, thereby improving system efficiency. Downlink channels include, for example, the Physical Downlink Shared Channel (PDSCH) and the Physical Downlink Control Channel (PDCCH).

[0039] Multiple downlink channels' HARQ-ACK information is multiplexed to generate a single HARQ-ACK codebook. A larger number of bits in the multiplexed information is more beneficial for improving transmission efficiency. However, the number of bits in the multiplexed information is also limited by reliability requirements. The reliability requirements of the feedback information will constrain the amount of data transmitted over the air interface or the physical resources occupied by the transmission.

[0040] For example, 100 bits of HARQ-ACK information theoretically corresponds to 2100 different feedback messages. If the air interface transmission limits the number of information bits to 10 bits, then a maximum of 210 feedback messages can be expressed. Similarly, if the air interface transmission limits the physical resources used to one Physical Resource Block (PRB), it is also impossible to transmit 2100 feedback messages using only one PRB. Such limitations on the number of bits or physical resources in the feedback message inevitably reduce the precision of the feedback information and may even lead to inaccuracies.

[0041] To this end, this application provides a model-based feedback method that helps to provide more refined feedback information when air interface transmission is limited.

[0042] The models involved in this application can be mathematical models based on mathematical modeling or artificial intelligence (AI) models, but are not limited to these two types of models.

[0043] AI (Artificial Intelligence) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0044] AI technology is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning (ML) / deep learning.

[0045] An AI model can be trained and obtained through the processes of data set construction, training, validation, and testing.

[0046] AI models are an important component of AI technology, used for tasks such as processing, analysis, and prediction. Common AI models include various types, such as neural networks, decision trees, support vector machines, random forests, and mean-based algorithms.

[0047] A neural network is a computational model consisting of multiple interconnected neurons (nodes). A simple neural network's basic structure includes an input layer, hidden layers, and an output layer. The input layer receives data, the hidden layers process the data, and the final result is generated in the output layer. By using different connections, weights, and activation functions between neurons, different outputs can be produced, thus fitting a mapping relationship from input to output.

[0048] When neural network models are used for wireless communication between terminal devices and network devices, training can be divided into offline training and online training. Offline training allows the network device or terminal device to obtain a static training result by training offline using a dataset. Online training, on the other hand, refers to the process where, as the network device or terminal device uses the neural network model, it continues to collect more data through further measurements and / or reporting from the terminal device. This allows for real-time online training to optimize the neural network model's parameters, achieving better inference and prediction results. After obtaining the neural network model, the corresponding model output can be obtained by inputting the currently acquired information into the model.

[0049] When neural network models are used in wireless communication, they can be divided into single-ended models and dual-ended models. Single-ended models can be used by deploying only on one side of the terminal device or network device, and the model training can also be performed on only one side. Dual-ended models need to be deployed on both the terminal device and the network device, and the models on both sides need to be trained together. That is to say, the models deployed on both sides are corresponding or paired and cannot be used or updated separately.

[0050] To achieve different wireless communication functions, different AI models can be introduced, with corresponding inputs and outputs defined.

[0051] Figure 1 illustrates a schematic diagram of a wireless communication system 100 provided in an exemplary embodiment of this application. The wireless communication system 100 includes terminal devices with terminal devices, or terminal devices with network devices, or stations (STAs) with stations; this application does not limit the specific examples. Figure 1 uses an example where the wireless communication system 100 includes network device 110 and terminal device 120.

[0052] The network device 110 in this application supports wireless communication functions, including but not limited to: Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), Radio Network Controller (RNC), Base Station (BS), Base Station Controller (BSC), Base Transceiver Station (BTS), Home Evolved Node B (or Home Node B, HNB), Baseband Unit (BBU), Distributed Unit (DU), Wireless Relay Node, Wireless Backhaul Node, Transmission Point (TP), Transmission and Reception Point (TRP), Antenna Panel, Router, etc.

[0053] The terminal device 120 in this application, also referred to as user equipment (UE), includes, but is not limited to: mobile phones, tablets, e-book readers, laptops, desktop computers, televisions, virtual reality (VR) devices, augmented reality (AR) devices, mixed reality (MR) devices, extended reality (XR) devices, remote terminals, set-top boxes, vehicle communication equipment, handheld devices, wearable devices, wireless devices in industrial control, wireless devices in self-driving, wireless devices in remote medical care, wireless devices in smart grids, wireless devices in transportation safety, wireless devices in smart cities, wireless devices in smart homes (such as smart cameras, smart remote controls, smart water and electricity meters, etc.), wireless communication chips, application-specific integrated circuits (ASICs), systems-on-chips (SoCs), and Internet of Things (IoT) devices. Things (IoT) nodes, Internet of Vehicles (IoV) nodes, sensors, etc., can also be computing devices with wireless communication capabilities or other processing devices connected to a wireless modem.

[0054] In some embodiments, both network device 110 and terminal device 120 support the 3rd Generation Partnership Project (3GPP) protocol, but are not limited to the 3GPP protocol.

[0055] In some embodiments, the frequency bands supported by the wireless communication system 100 include, but are not limited to: centimeter wave bands (such as bands in the range of 450MHz-6GHz, also called Sub-6GHz bands), millimeter wave (mmWave) bands (such as 45GHz, 60GHz, etc., which belong to the range of 30-300GHz), and low-frequency bands. Among them, low-frequency bands include Sub-7GHz bands (such as 2.4GHz, 5GHz, 6GHz, etc., which belong to the range of 1-7.25GHz).

[0056] This application mainly involves two communication scenarios: one is the uplink transmission scenario, which refers to the scenario where the terminal device sends signals / data to the network device; the other is the downlink transmission scenario, which refers to the scenario where the network device sends signals / data to the terminal device.

[0057] The technical solutions described in some embodiments of this application can be applied to various communication systems, such as: NR systems, evolution systems of NR systems, 5th-Generation (5G) systems, Beyond 5th-Generation (B5G) systems, 6G systems, evolution systems following 6G, Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, cellular IoT systems, Wireless Local Area Networks (WLAN) systems, Wireless Fidelity (Wi-Fi) systems, Global System for Mobile Communication (GSM) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA) systems, and General Packet Radio (GPRS). Services (GPRS), terrestrial networks (TN), and non-terrestrial networks (NTN) systems.

[0058] Figure 2 illustrates a flowchart of a model-based feedback method provided in an exemplary embodiment of this application. The method is executed by a first device and includes at least some of the following steps:

[0059] Step 220: Send feedback information. The feedback information is obtained based on A-bit feedback response information and the agreed model, where A is a positive integer.

[0060] A convention model refers to a pre-agreed processing model. Optionally, the processing model is agreed upon by the communication protocol, or by the sender and receiver of feedback information through negotiation, or by the network device through configuration, or by the terminal device through reporting. Optionally, the processing model may be dedicated solely to feedback information processing, or it may not be solely dedicated to feedback information processing, but may also support other functions such as Channel State Information (CSI) feedback, location, channel coding, channel decoding, modulation, demodulation, and channel estimation.

[0061] In some embodiments, the convention model is a two-end model. Optionally, convention models are deployed on both the sending and receiving sides of the feedback information. These convention models support both the functions required by the sender of the feedback information (such as encoding, modulation, mapping, or one or more processing methods) and the functions required by the receiver of the feedback information (such as decoding, demodulation, detection, or one or more processing methods). Optionally, the convention model is jointly deployed on both the sending and receiving sides of the feedback information. The sender deploys a sending-end model of the convention model (also known as an encoding-end model or modulation-end model, etc.), and the receiver deploys a receiving-end model of the convention model (also known as a decoding-end model or demodulation-end model, etc.). The sending-end model and the receiving-end model are corresponding or paired.

[0062] In some embodiments, the agreed model is an offline trained model, for example, it is obtained by the network device and the terminal device through offline training with a dataset, or it is obtained by the network device through offline training with a dataset and sent to the terminal device, or it is obtained by the terminal device through offline training with a dataset and sent to the network device.

[0063] In some embodiments, the convention model is an online trained model, for example, the parameters of the convention model are further optimized by network devices and / or terminal devices using the information collected during the use of the convention model.

[0064] Optionally, the processing model can be a mathematical model or an AI model. AI models include one or more of the following types: neural networks, decision trees, support vector machines, random forests, mean-based algorithms, etc. Optionally, AI models can also be called AI rules, AI functions, or other names.

[0065] In some embodiments, the number of bits in the feedback information is less than A, or the feedback information obtained after processing by a pre-defined model can be sent without further pre-defined processing by the transmitting end. Pre-defined processing may include channel coding and / or modulation.

[0066] Step 220 can be performed by a network device or a terminal device. That is, the sender of the feedback information (i.e., the first device) can be a network device or a terminal device.

[0067] In summary, the embodiments of this application provide a method for implementing feedback using a model. Because the model has high scalability, flexibility, and high processing efficiency, it helps to respond to multi-bit response information in real time, improves feedback efficiency, and ensures the efficiency, accuracy, and precision of the feedback information.

[0068] In some embodiments, based on the embodiment shown in FIG2, step 220 can be further implemented as step 340, as shown in FIG3. Optionally, in addition to step 340, the model-based feedback method also includes the following optional step: step 320.

[0069] Figure 3 illustrates a flowchart of a model-based feedback method provided in an exemplary embodiment of this application. The method is executed by a first device and includes at least some of the following steps:

[0070] Step 320: Determine the convention model.

[0071] (1) The agreed model is determined based on the first information.

[0072] In some embodiments, the convention model is determined based on first information, which is used to indicate or activate the convention model.

[0073] In some embodiments, the first information carries one or more of the following model information: the model identifier of the conventional model, the model functionality of the conventional model, the input information features of the conventional model, the output information features of the conventional model, the model performance of the conventional model, the dataset of the conventional model, the dataset identifier of the conventional model, the usage scenario information of the conventional model, and the usage condition information of the conventional model.

[0074] In some embodiments, the first device receives first information and determines a convention model based on the first information.

[0075] In some embodiments, the first device determines the agreed-upon model based on the first information. Optionally, the first device further sends the first information to enable the second device to determine the agreed-upon model based on the first information.

[0076] In some embodiments, the first information is carried in Radio Resource Control (RRC) signaling, or in Media Access Control (MAC) control element (CE), or in Uplink Control Information (UCI), or in Downlink Control Information (DCI), or in capability information reported by the UE.

[0077] In some embodiments, the validity of the first information satisfies one or more of the following: the effective time of the first information is agreed upon by the communication protocol; the effective time of the first information is indicated by the network device; the effective time of the first information is indicated by the terminal device; the effective time of the first information is indicated by the first information; the end position of the effective time of the first information is the receiving time of the next first information; the first information is valid for a single feedback.

[0078] In some embodiments, the transmission of the first information and the transmission of the feedback information are associated with any one or more of the following: the first information and the feedback information are transmitted through the same channel; the first information and the feedback information are transmitted within the same time unit; the first information and the feedback information are transmitted within the same frequency domain unit; there is a first offset between the transmission time of the first information and the transmission time of the feedback information; the triggering signaling for the feedback information includes the first information, and the triggering signaling is used to trigger the transmission of the feedback information; the requesting signaling for the feedback information includes the first information, and the requesting signaling is used to request the triggering signaling for the transmission of the feedback information. Optionally, the first offset is agreed upon by the communication protocol, indicated by the network device, or indicated by the terminal device.

[0079] In this application, time units include, for example, one or more of the following: frame, subframe, slot, mini-slot, sub-slot, symbol, symbol group, and units based on other time-domain units. Frequency-domain units include, for example, one or more of the following: bandwidth, carrier, physical resource block (PRB), bandwidth part (BWP), subband, subchannel, subcarrier, and units based on other frequency-domain units. Of course, time units and frequency-domain units are not limited to the units listed above; units defined in future communication protocols also apply to this application.

[0080] The transmission time of the first information refers to the time of its transmission, or the start time of the first information in the time domain, or the end time of the first information in the time domain. The transmission time of the third information refers to the time of its transmission, or the start time of the third information in the time domain, or the end time of the third information in the time domain. There is a first offset between the transmission time of the first information and the transmission time of the feedback information, which may be any of the following: there is a first offset between the transmission time of the first information and the transmission time of the third information; there is a first offset between the start time of the first information and the start time of the third information in the time domain; there is a first offset between the end time of the first information and the end time of the third information in the time domain; there is a first offset between the start time of the first information and the end time of the third information in the time domain; there is a first offset between the end time of the first information and the start time of the third information in the time domain.

[0081] In some embodiments, the location where the first information is sent has a periodic characteristic. For example, the first information is sent periodically. Or, the first information is sent on periodic physical resources, but it is not necessary to send it every period.

[0082] (2) The agreed model is determined based on the second information.

[0083] In some embodiments, the agreed-upon model is determined based on the second information. Optionally, the second information is agreed upon by the communication protocol, or by the sending and receiving parties of the feedback information through negotiation, or by the network device through configuration, or by the terminal device through reporting.

[0084] In some embodiments, the second information includes one or more of the following: data parameters corresponding to the feedback information; transmission parameters of the feedback information; performance monitoring results of the feedback information; and model switching request information. The model switching request information is used to request a switch to a pre-defined model and can be sent by a network device or a terminal device.

[0085] The data parameters corresponding to the feedback information refer to the parameters of the data to which the feedback information is directed. For example, if feedback information F is used to report the reception status of data D, then data D is the data corresponding to feedback information F, and the parameters of data D are the data parameters corresponding to feedback information F. Optionally, the data parameters corresponding to the feedback information may include one or more of the following: data volume, number of coded blocks, data transmission scheduling method, coding rate, modulation and coding method, and resource mapping method.

[0086] Optionally, the transmission parameters for feedback information may include one or more of the following: channel type, channel format, number of bits, HARQ-ACK codebook type, number of transmission resources, whether to use repeated transmission, and whether to use multiplexed transmission.

[0087] Optionally, the performance monitoring results of the feedback information may be associated with one or more of the following: retransmission information includes data that has been correctly decoded, and data that failed to be decoded and was not retransmitted. Optionally, the performance monitoring results of the feedback information may be the results of a single monitoring session or a statistical result of multiple monitoring sessions.

[0088] Here are some specific examples of determining the convention model based on the second information:

[0089] 1. Taking the first quantity as an example, the first quantity can be one or more of the following: data volume, number of coded blocks, number of bits of feedback information, and number of transmission resources for feedback information. In some cases, the first quantity can also be the result of mathematical operations on the above quantities (e.g., sum, difference, product, quotient, remainder, modulo result, average, etc.).

[0090] For example, if the first quantity is less than the first value (or threshold), Model 1 is used; if the first quantity is greater than or equal to the second value (or threshold), Model 2 is used.

[0091] For example, if the first quantity falls within a first numerical range, Model 1 is used; if the first quantity falls within a second numerical range, Model 2 is used.

[0092] For example, if the first quantity is less than the first value, the first model is used; if the first quantity is greater than or equal to the second value, the second model is used.

[0093] For example, if the first quantity falls within a first numerical range, the first model is used; if the first quantity falls within a second numerical range, the second model is used.

[0094] The first and second sets of models can be divided based on one or more aspects such as model function, input information features, output information features, model performance, model usage scenario information, model usage condition information, model structure, and model parameters. For example, the first set of models may all be model structure 1, and the second set of models may all be model structure 2. Alternatively, the first set of models may all be model function 1, and the second set of models may all be model function 2. Or, the first set of models may all be applicable to scenario 1, and the second set of models may all be applicable to scenario 2, and so on. It is impossible to list all possibilities here, but it should be understood that this application supports determining a specific conventional model based on the second information, and also supports determining a class of conventional models or a set of conventional models based on the second information. The first device and the second device can achieve relatively accurate and refined feedback by using any one of these conventional models or sets of conventional models.

[0095] 2. Taking data transmission scheduling methods as an example. Data transmission scheduling methods include the following: semi-static scheduling, semi-persistent scheduling, dynamic scheduling, scheduling using different signaling formats (DCI format), initial transmission, and retransmission.

[0096] For example, when data transmission uses the first scheduling method, Model 1 is used; when data transmission uses the second scheduling method, Model 2 is used. The first and second scheduling methods differ. For instance, the first scheduling method may be semi-static or semi-persistent scheduling, while the second scheduling method is dynamic scheduling. Another example is that the first scheduling method uses the first signaling format (e.g., the first DCI format), and the second scheduling method uses the second signaling format (e.g., the second DCI format). Yet another example is that the first scheduling method is for initial transmission, and the second scheduling method is for retransmission.

[0097] For example, when data transmission is in the first scheduling mode, the first set of models is used; when data transmission is in the second scheduling mode, the second set of models is used.

[0098] ·3. Taking coding rate / modulation coding method as an example.

[0099] For example, if the coding rate is less than a first value (or threshold), Model 1 is used; if the coding rate is greater than or equal to a second value (or threshold), Model 2 is used.

[0100] For example, when the coding rate is less than a first value, the first model is used; when the coding rate is greater than or equal to a second value, the second model is used.

[0101] For example, if the modulation and coding level is in the first level range, Model 1 is used; if the modulation and coding level is in the second level range, Model 2 is used.

[0102] For example, when the modulation and coding level falls within the first level range, the first model is used; when the modulation and coding level falls within the second level range, the second model is used.

[0103] 4. Taking resource mapping methods as an example. Resource mapping methods include the following: time domain mapping, frequency domain mapping, spatial domain mapping, interleaving mapping, and non-interleaving mapping.

[0104] For example, when data transmission uses the first resource mapping method, Model 1 is used; when data transmission uses the second resource mapping method, Model 2 is used. The first and second resource mapping methods are different. For instance, the first resource mapping method may be a first time-domain mapping rule, and the second resource mapping method may be a second time-domain mapping rule. Alternatively, the first resource mapping method may be a first frequency-domain mapping rule, and the second resource mapping method may be a second frequency-domain mapping rule. Another example is that the first resource mapping method may be a first spatial-domain mapping rule, and the second resource mapping method may be a second spatial-domain mapping rule. Yet another example is that the first resource mapping method is interleaved mapping, and the second resource mapping method is non-interleaved mapping.

[0105] For example, when data transmission is in the first resource mapping mode, the first set of models is used; when data transmission is in the second resource mapping mode, the second set of models is used.

[0106] 5. Taking channel type as an example. Channel types include the following: uplink channel, downlink channel, shared channel, control channel, and broadcast channel.

[0107] For example, when the channel type of the feedback information is the first channel type, Model 1 is used; when the channel type of the feedback information is the second channel type, Model 2 is used. The first channel type and the second channel type are different. For example, the first channel type is an uplink channel, and the second channel type is a downlink channel. Or, for example, the first channel type is a shared channel, and the second channel type is a control channel or a broadcast channel.

[0108] For example, when the channel type of the feedback information is the first channel type, the first set of models is used; when the channel type of the feedback information is the second channel type, the second set of models is used.

[0109] 6. Take channel format as an example.

[0110] For example, when the channel format of the feedback information is the first channel format, Model 1 is used; when the channel format of the feedback information is the second channel format, Model 2 is used. The first channel format and the second channel format are different. For instance, taking the channel as the Physical Uplink Control Channel (PUCCH) as an example, the first channel format is the first PUCCH format, and the second channel format is the second PUCCH format. As another example, taking the channel as the Physical Uplink Shared Channel (PUSCH) as an example, the first channel format is the first PUSCH format, and the second channel format is the second PUSCH format.

[0111] For example, when the channel format of the feedback information is the first channel format, the first set of models is used; when the channel format of the feedback information is the second channel format, the second set of models is used.

[0112] 7. Take the HARQ-ACK codebook type as an example.

[0113] For example, when the feedback information uses the first type of HARQ-ACK codebook, Model 1 is used; when the feedback information uses the second type of HARQ-ACK codebook, Model 2 is used. The first type of HARQ-ACK codebook and the second type of HARQ-ACK codebook are different. For example, the first type of HARQ-ACK codebook is a Type-1 HARQ-ACK codebook, and the second type of HARQ-ACK codebook is a Type-2 HARQ-ACK codebook. Or, for example, the first type of HARQ-ACK codebook is a Type-1 HARQ-ACK codebook, and the second type of HARQ-ACK codebook is a Type-3 HARQ-ACK codebook. Or, for example, the first type of HARQ-ACK codebook is a Type-3 HARQ-ACK codebook, and the second type of HARQ-ACK codebook is a Type-2 HARQ-ACK codebook. Or, for example, the first type of HARQ-ACK codebook is the HARQ-ACK codebook used for the initial transmission, and the second type of HARQ-ACK codebook is the HARQ-ACK codebook used for retransmissions. Of course, future communication protocols may also stipulate new types of HARQ-ACK codebooks, and these new types of HARQ-ACK codebooks are also applicable to this application.

[0114] For example, when the feedback information uses the first type of HARQ-ACK codebook, the first model is used; when the feedback information uses the second type of HARQ-ACK codebook, the second model is used.

[0115] 8. Take whether or not to use repeated transmission as an example.

[0116] For example, when the feedback information is transmitted repeatedly, Model 1 is used; when the feedback information is not transmitted repeatedly, Model 2 is used.

[0117] For example, when the feedback information is transmitted repeatedly, the first model is used; when the feedback information is not transmitted repeatedly, the second model is used.

[0118] 9. Take whether or not multiplexing transmission is used as an example.

[0119] For example, when the feedback information is transmitted using multiplexing, Model 1 is used; when the feedback information is not transmitted using multiplexing, Model 2 is used.

[0120] For example, when the feedback information is transmitted using multiplexing, the first model is used; when the feedback information is not transmitted using multiplexing, the second model is used.

[0121] 10. Take the performance monitoring results of feedback information as an example.

[0122] For example, if the feedback information performance test result indicates that the amount of data that has been correctly decoded in the retransmission information is greater than the third value (or threshold), Model 1 is used; if the feedback information performance test result indicates that the amount of data that has been correctly decoded in the retransmission information is less than or equal to the fourth value (or threshold), Model 2 is used.

[0123] For example, when the feedback information performance test result indicates that the amount of decoding failure data that was not retransmitted is greater than the third value (or threshold), Model 1 is used; when the feedback information performance test result indicates that the amount of decoding failure data that was not retransmitted is less than or equal to the fourth value (or threshold), Model 2 is used.

[0124] For example, if the feedback information performance test result indicates that the proportion of correctly decoded data included in the retransmission information is greater than the third value (or threshold), Model 1 is used; if the feedback information performance test result indicates that the proportion of correctly decoded data included in the retransmission information is less than or equal to the fourth value (or threshold), Model 2 is used.

[0125] For example, when the feedback information performance test result indicates that the proportion of decoded data that was not retransmitted is greater than the third value (or threshold), Model 1 is used; when the feedback information performance test result indicates that the proportion of decoded data that was not retransmitted is less than or equal to the fourth value (or threshold), Model 2 is used.

[0126] For example, if the feedback information performance test result indicates that the amount of data that has been correctly decoded in the retransmitted information is greater than the third value (or threshold), the first model is used; if the feedback information performance test result indicates that the amount of data that has been correctly decoded in the retransmitted information is less than or equal to the fourth value (or threshold), the second model is used.

[0127] For example, when the feedback information performance test result indicates that the amount of decoding failure data that was not retransmitted is greater than the third value (or threshold), the first model is used; when the feedback information performance test result indicates that the amount of decoding failure data that was not retransmitted is less than or equal to the fourth value (or threshold), the second model is used.

[0128] For example, if the feedback information performance test result indicates that the proportion of correctly decoded data included in the retransmitted information is greater than the third value (or threshold), the first model is used; if the feedback information performance test result indicates that the proportion of correctly decoded data included in the retransmitted information is less than or equal to the fourth value (or threshold), the second model is used.

[0129] For example, when the feedback information performance test result indicates that the proportion of decoded data that was not retransmitted is greater than the third value (or threshold), the first model is used; when the feedback information performance test result indicates that the proportion of decoded data that was not retransmitted is less than or equal to the fourth value (or threshold), the second model is used.

[0130] The terms 1 through 10 above can be used individually or in combination. In other words, the agreed-upon model can be confirmed based on second information from one dimension or a combination of second information from multiple dimensions.

[0131] In some embodiments, after the first device determines the agreed-upon model based on the second information, it also sends the first information to the second device to indicate or activate the agreed-upon model; or, the first device and the second device each determine the agreed-upon model based on the second information. Of course, it is also possible that after the second device determines the agreed-upon model based on the second information, the second device sends the first information to the first device to indicate or activate the agreed-upon model.

[0132] (3) The convention model is one of multiple models.

[0133] In some embodiments, the designated model is one of a plurality of models indicated or activated by the first information.

[0134] In some embodiments, the agreed model is one of a plurality of models determined based on the second information.

[0135] In some embodiments, multiple models differ in one or more of the following aspects: model identifier, model function, input information features, output information features, model performance, model dataset, model dataset identifier, model usage scenario information, model usage condition information, model structure, and model parameters.

[0136] The differences in model functionality, model performance, model usage scenario information, and model usage condition information may be influenced by one or more of the following factors: service characteristics (such as data volume, reliability, latency, etc.), uplink channel transmission characteristics (such as antenna configuration, spatial channel characteristics, interference level, mobile speed, channel fading characteristics, etc.), downlink channel transmission characteristics, serving cell characteristics (such as cell coverage, network equipment capabilities, network equipment version, single carrier operating mode, carrier aggregation operating mode, etc.), and terminal equipment capabilities.

[0137] The model structure can be any of several candidate model structures, such as: Transformer structure, Residual Neural Network (ResNet), Recurrent Neural Network (RNN), Convolutional Neural Networks (CNN), Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Deep Neural Network (DNN). Optionally, the model structure may also include the number of layers in the neural network, the quantization method, etc.

[0138] Model parameters include the parameters used by the model. A neural network model typically includes at least an input layer, hidden layers, and an output layer.

[0139] Different models correspond to different input information and / or different output information in their datasets.

[0140] Optionally, multiple models are agreed upon by the communication protocol or are predefined. Among them, "predefined" can be achieved by pre-storing corresponding codes, tables or other means that can be used to indicate relevant information in the communication device (e.g., terminal device, network device), and this application does not limit the specific implementation method.

[0141] Optionally, multiple models may be indicated or configured by network devices; or multiple models may be reported by terminal devices; or, some of the multiple models may be indicated or configured by network devices, while other models may be reported by terminal devices.

[0142] Optionally, some or all of the multiple models may be configured / instructed / reported via third information. This third information is sent by the network device or the terminal device. It is important to note that the sender of the third information may not be the same as the sender of the first information. For example, the network device may send both the first and third information; or, the network device may send the first information and the terminal device may send the third information; or, the network device may send the third information and the terminal device may send the first information; or, the terminal device may send both the first and third information.

[0143] In some embodiments, the third information is carried in RRC signaling, or in MAC CE, or in UCI, or in DCI, or in the capability information reported by the UE.

[0144] In some embodiments, if the first information is sent by the first device, the first information and the feedback information can be sent simultaneously or multiplexed during transmission. Simultaneous transmission can be understood as transmission through a single channel, transmission within the same time unit, or transmission within a limited time range (e.g., transmitting the first information at time t0, transmitting the feedback information at time t0+offset, where the offset value is pre-configured).

[0145] In some embodiments, if the first information is sent by the second device, the triggering signaling sent by the second device includes the first information. The triggering signaling is used to trigger the peer to send feedback information.

[0146] In some embodiments, if the first information is sent by the first device, the request signaling sent by the first device includes the first information. The request signaling is used to request the peer to send trigger signaling.

[0147] In some embodiments, the receiving end of the first information needs to correctly receive the first information before it can receive the feedback information sent this time. Therefore, the first device and the second device can also confirm the receipt of the first information.

[0148] For example, when the first device sends the first information, the first device also receives response information in response to the first information.

[0149] For example, when the first device receives the first information, the first device also sends response information in response to the first information.

[0150] Response information is used to confirm whether the first message was successfully received. For example, response information may include confirmation messages, feedback responses, or other information exchanged between the first and second devices. Through the exchange of response information, it is ensured that the first and second devices have a consistent understanding of the agreed-upon model used, thereby guaranteeing the accuracy of the feedback information. The exchange of response information is particularly important when the third message / first message remains in effect for an extended period.

[0151] Step 340: Send feedback information. The feedback information is obtained based on A-bit feedback response information and the agreed model, where A is a positive integer.

[0152] The A-bit feedback response information is generated by the sender of the feedback information and serves as the input to the agreed-upon model. The sender of the feedback information (i.e., the first device) can use the agreed-upon model to obtain / predict / infer the feedback information.

[0153] In some embodiments, the number of bits in the feedback information is less than A, or the feedback information obtained after processing by a pre-defined model can be sent without further pre-defined processing by the transmitting end. Pre-defined processing may include channel coding and / or modulation.

[0154] In some embodiments, A-bit feedback response information is used as input information to a predefined model. After processing by the predefined model, B-bit feedback information is obtained, where B is less than A. The B-bit feedback information is then processed by encoding and / or modulation and mapped onto a first physical resource for transmission.

[0155] In some embodiments, the A-bit feedback response information is used as input information of the agreed model. After being processed by the agreed model, feedback information is obtained. The feedback information does not need to be processed by channel coding and / or modulation, and can be directly mapped to the first physical resource for transmission.

[0156] In summary, this application provides a method for implementing feedback using a model. Because the model possesses high scalability, flexibility, and processing efficiency, it helps to handle multi-bit response information feedback in real time, improving feedback efficiency while ensuring the efficiency, accuracy, and precision of the feedback information. Furthermore, it provides a reliable method for determining the agreed-upon model, helping to ensure that both parties receiving the feedback information have a consistent understanding of the agreed-upon model used, thereby guaranteeing the accuracy of the feedback information.

[0157] Figure 4 illustrates a flowchart of a model-based feedback method provided in an exemplary embodiment of this application. The method is executed by a second device and includes at least some of the following steps:

[0158] Step 420: Receive feedback information. The feedback information is obtained based on A-bit feedback response information and the agreed model, where A is a positive integer.

[0159] A convention model refers to a pre-defined processing model. Optionally, the processing model is agreed upon by the communication protocol, or by the sender and receiver of feedback information through negotiation, or by the network device through configuration, or by the terminal device through reporting. Optionally, the processing model may be dedicated solely to feedback information processing, or it may not be solely dedicated to feedback information processing, but may also support other functions such as CSI feedback, location, channel coding, channel decoding, modulation, demodulation, and channel estimation.

[0160] In some embodiments, the convention model is a two-end model. Optionally, convention models are deployed on both the sending and receiving sides of the feedback information. These convention models support both the functions required by the sender of the feedback information (such as encoding, modulation, mapping, or one or more processing methods) and the functions required by the receiver of the feedback information (such as decoding, demodulation, detection, or one or more processing methods). Optionally, the convention model is jointly deployed on both the sending and receiving sides of the feedback information. The sender deploys a sending-end model of the convention model (also known as an encoding-end model or modulation-end model, etc.), and the receiver deploys a receiving-end model of the convention model (also known as a decoding-end model or demodulation-end model, etc.). The sending-end model and the receiving-end model are corresponding or paired.

[0161] In some embodiments, the agreed model is an offline trained model, for example, it is obtained by the network device and the terminal device through offline training with a dataset, or it is obtained by the network device through offline training with a dataset and sent to the terminal device, or it is obtained by the terminal device through offline training with a dataset and sent to the network device.

[0162] In some embodiments, the convention model is an online trained model, for example, the parameters of the convention model are further optimized by network devices and / or terminal devices using the information collected during the use of the convention model.

[0163] Optionally, the processing model can be a mathematical model or an AI model. AI models include one or more of the following types: neural networks, decision trees, support vector machines, random forests, mean-based algorithms, etc. Optionally, AI models can also be called AI rules, AI functions, or other names.

[0164] In some embodiments, the number of bits in the feedback information is less than A, or the feedback information obtained after processing by a pre-defined model can be sent without further pre-defined processing by the transmitting end. Pre-defined processing may include channel coding and / or modulation.

[0165] Step 320 can be performed by a network device or a terminal device. That is, the recipient of the feedback information (i.e., the second device) can be a network device or a terminal device.

[0166] In summary, the embodiments of this application provide a method for implementing feedback using a model. Because the model has high scalability, flexibility, and high processing efficiency, it helps to respond to multi-bit response information in real time, improves feedback efficiency, and ensures the efficiency, accuracy, and precision of the feedback information.

[0167] In some embodiments, based on the embodiment shown in FIG4, step 420 can be further implemented as step 540, as shown in FIG5. Optionally, in addition to step 540, the model-based feedback method also includes the following optional steps: step 520 and step 560.

[0168] Figure 5 illustrates a flowchart of a model-based feedback method provided in an exemplary embodiment of this application. The method is executed by a second device and includes at least some of the following steps:

[0169] Step 520: Determine the convention model.

[0170] In some embodiments, the convention model is determined based on first information, which is used to indicate or activate the convention model.

[0171] In some embodiments, the second device receives the first information and determines the agreed model based on the third information.

[0172] In some embodiments, the second device determines the agreed-upon model based on the first information. Optionally, the second device further sends the first information to enable the first device to determine the agreed-upon model based on the first information.

[0173] In some embodiments, the agreed-upon model is determined based on the second information. Optionally, the second information is agreed upon by the communication protocol, or by the sending and receiving parties of the feedback information through negotiation, or by the network device through configuration, or by the terminal device through reporting.

[0174] In some embodiments, after the second device determines the agreed-upon model based on the second information, it also sends the first information to the first device to indicate or activate the agreed-upon model; or, the first device and the second device each determine the agreed-upon model based on the second information. Of course, it is also possible that after the first device determines the agreed-upon model based on the second information, the first device sends the first information to the second device to indicate or activate the agreed-upon model.

[0175] In some embodiments, the designated model is one of a plurality of models indicated or activated by the first information.

[0176] In some embodiments, the agreed model is one of a plurality of models determined based on the second information.

[0177] In some embodiments, when the second device sends the first information, the second device also receives response information in response to the first information.

[0178] In some embodiments, when the second device receives the first information, the second device also sends response information in response to the first information.

[0179] Please refer to step 320 for other related content, which will not be repeated here.

[0180] Step 540: Receive feedback information. The feedback information is obtained based on A-bit feedback response information and the agreed model, where A is a positive integer.

[0181] The A-bit feedback response information is generated by the sender of the feedback information and serves as the input to the agreed-upon model. The sender of the feedback information (i.e., the first device) can use the agreed-upon model to obtain / predict / infer the feedback information.

[0182] In some embodiments, the number of bits in the feedback information is less than A, or the feedback information obtained after processing by a pre-defined model can be sent without further pre-defined processing by the transmitting end. Pre-defined processing may include channel coding and / or modulation.

[0183] In some embodiments, A-bit feedback response information is used as input information to a predefined model. After processing by the predefined model, B-bit feedback information is obtained, where B is less than A. The B-bit feedback information is then processed by encoding and / or modulation and mapped onto a first physical resource for transmission.

[0184] In some embodiments, the A-bit feedback response information is used as input information of the agreed model. After being processed by the agreed model, feedback information is obtained. The feedback information does not need to be processed by channel coding and / or modulation, and can be directly mapped to the first physical resource for transmission.

[0185] For other details, please refer to step 420; they will not be repeated here.

[0186] Step 560: Obtain A-bit feedback response information based on the feedback information and the agreed model.

[0187] The recipient of the feedback information can use the feedback information as input to a predefined model to obtain / predict / infer A bits of feedback response information.

[0188] In summary, the embodiments of this application provide a method for implementing feedback using a model. Because the model possesses high scalability and flexibility, it facilitates real-time and efficient handling of multi-bit response information feedback, and helps the receiver obtain more accurate and refined feedback information through the model. Furthermore, it provides a reliable method for determining the agreed-upon model, helping to ensure that both parties receiving the feedback information have a consistent understanding of the agreed-upon model used, thereby guaranteeing the accuracy of the feedback information.

[0189] Furthermore, based on the embodiments shown in Figures 2, 3, 4, and 5, this application makes more detailed designs for the A-bit feedback response information.

[0190] At the sending end of the feedback information, A bits of feedback response information can be used as input to the agreed-upon model. At the receiving end of the feedback information, A bits of feedback response information can be used as output to the agreed-upon model.

[0191] The first feedback response information in the A-bit feedback response information includes one or more of the following: feedback response information corresponding to one or a group of resources, where the resources include at least one time unit and / or at least one frequency unit; feedback response information corresponding to one or a group of channels; feedback response information corresponding to one or a group of HARQ processes; feedback response information corresponding to one or a group of TBs; and feedback response information corresponding to one or a group of CBs. Wherein, the first feedback response information is any one bit of feedback response information in the A-bit feedback response information.

[0192] In some embodiments, the first feedback response information is generated based on one or more of the following: the decoding result of information received in one or a set of resources; the decoding result of a channel received in one or a set of resources; the decoding result of one or a set of channels received; the decoding result of one or a set of HARQ processes received; the decoding result of one or a set of TBs received; and the decoding result of one or a set of CBs received.

[0193] In other words, the first feedback response information may be a feedback response at the resource or resource group level, a feedback response at the channel or channel group level, a feedback response at the HARQ process or HARQ process group level, a feedback response at the TB or TB group (TBG) level, or a feedback response at the CB or CBG level.

[0194] In some embodiments, the first feedback response information can be one of three possibilities:

[0195] (1) In the first case, the first feedback response information is the first agreed information. Optionally, the first agreed information represents a positive response, such as ACK.

[0196] The first category includes one or more of the following: information received in one or a set of resources is correctly decoded; channels received in one or a set of resources are correctly decoded; one or a set of channels received are correctly decoded; one or a set of HARQ processes received are correctly decoded; one or a set of TBs received are correctly decoded; and one or a set of CBs received are correctly decoded.

[0197] (2) In the second case, the first feedback response information is the second agreed-upon information. Optionally, the second agreed-upon information represents a negative response, such as NACK.

[0198] The second category includes one or more of the following: information received in one or a set of resources was not correctly decoded; a channel received in one or a set of resources was not correctly decoded; one or a set of channels received was not correctly decoded; one or a set of HARQ processes received was not correctly decoded; one or a set of TB processes received was not correctly decoded; and one or a set of CB processes received was not correctly decoded. "Not correctly decoded" can be understood as a decoding error or a decoding failure.

[0199] (3) In the third case, the first feedback response information is the third agreed information. Optionally, the third agreed information represents a negative response, such as NACK; or, the third agreed information represents discontinuous transmission (DTX). The third agreed information may be the same as or different from the second agreed information.

[0200] The third category includes one or more of the following: no information was received in one or a group of resources, no channel was received in one or a group of resources, no channel was received, no HARQ process was received, no TB was received, and no CB was received.

[0201] In some embodiments, the A-bit feedback response information is obtained by concatenating the feedback response information of the corresponding resource or channel or TB or TBG or CB or CBG or HARQ process in a first order. The first order includes one or more of the following orders: time-domain ascending order, time-domain descending order, frequency-domain ascending order, frequency-domain descending order, spatial-domain ascending order, spatial-domain descending order, numbering ascending order, and numbering descending order.

[0202] In some embodiments, the A-bit feedback response information is obtained based on the C-bit information. Optionally, the C-bit information is the feedback response information corresponding to C resources, C channels, C TBs, C TBGs, C CBs, C CBGs, or C HARQ processes. Optionally, the C-bit information is the decoding result information corresponding to C resources, C channels, C TBs, C TBGs, C CBs, C CBGs, or C HARQ processes. C is an integer greater than A.

[0203] In some embodiments, each bit of the feedback response information in the A-bit feedback response information corresponds one-to-one with A packets, which are obtained by dividing C resources, C channels, C HARQ processes, C transport blocks, or C coding blocks. C is an integer greater than A.

[0204] For example, each bit of the feedback response information in the A-bit feedback response information corresponds one-to-one with the resources in group A, which are obtained by uniformly or non-uniformly dividing the resources in group C.

[0205] For example, each bit of the feedback response information in the A-bit feedback response information corresponds to a group of channels A, which is obtained by uniformly or non-uniformly dividing C channels.

[0206] For example, each bit of the feedback response information in the A-bit feedback response information corresponds to a group A of TBs, which are obtained by uniformly or non-uniformly dividing C TBs.

[0207] For example, each bit of the feedback response information in the A-bit feedback response information corresponds one-to-one with group A CB, and group A CB is obtained by uniformly or non-uniformly dividing C CBs.

[0208] For example, each bit of the feedback response information in the A-bit feedback response information corresponds to a group A of HARQ processes, which are obtained by uniformly or non-uniformly dividing the C HARQ processes.

[0209] In some embodiments, the value of A is determined based on the configuration of the network device, or based on the agreement of the communication protocol, or based on the information reported by the terminal device.

[0210] In some embodiments, the first device determines at least one corresponding resource, channel, or HARQ process based on the value of A. Alternatively, the first device determines corresponding A bit feedback information based on at least one resource, channel, or HARQ process. Or, the first device determines the corresponding value of A based on at least one resource, channel, or HARQ process.

[0211] In some embodiments, the receiving parties of the feedback information agree on one or more of the following: the value of A, the A-bit feedback response information, the generation / compression / merging method of the A-bit feedback response information, the codebook type of the A-bit feedback response information, and the resource / channel / HARQ process corresponding to the A-bit feedback response information. This agreement can be achieved through communication protocol agreements, instructions from network devices, or reporting from terminal devices.

[0212] In some embodiments, one or more of the following information is indicated by the network device, reported by the terminal device, or agreed upon by the communication protocol: one or a group of resources; one or a group of channels; one or a group of HARQ processes; the generation method of A-bit feedback response information; the codebook type of A-bit feedback response information; the compression method of A-bit feedback response information; the merging method of A-bit feedback response information; the number of bits of feedback response information corresponding to one or a group of resources; the number of bits of feedback response information corresponding to one or a group of channels; the number of bits of feedback response information corresponding to one or a group of HARQ processes; the association relationship between A-bit feedback response information and at least one or a group of resources; the association relationship between A-bit feedback response information and at least one or a group of channels; and the association relationship between A-bit feedback response information and at least one or a group of HARQ processes.

[0213] Figure 6 illustrates a schematic diagram of a model-based feedback method provided in an exemplary embodiment of this application, which is executed by a first device and a second device. Taking the example that the agreed-upon model includes an encoding end model (or a transmitting end model, or other names) and a decoding end model (or a receiving end model, or other names), the encoding end model is deployed on the first device side, and the decoding end model is deployed on the second device side.

[0214] The first device acquires the A-bit feedback response information. Details regarding the A-bit feedback response information can be found above. Here, three specific examples are used to further illustrate the acquisition of the A-bit feedback response information.

[0215] (1) A bit feedback response information is the feedback response information corresponding to M resources, where M is an integer greater than or equal to 1.

[0216] The M resources may include at least one time unit and / or at least one frequency unit. Each of the M resources corresponds to at least 1 bit of information.

[0217] In some embodiments, the first device first determines at least some information about M resources, such as based on network configuration, UE reporting, or protocol agreement, and then determines the value of A based on the at least some information about the M resources and a first rule. The first rule is agreed upon by the communication protocol, network configuration, or UE reporting. Optionally, the first rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0218] In some embodiments, the first device first determines the value of A, for example, based on network configuration, UE reporting, or protocol agreement, and then determines M resources based on the value of A and the second rule. The second rule is agreed upon by the communication protocol, network configuration, or UE reporting. Optionally, the second rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0219] In some embodiments, the first device first determines the value of A and at least some information of M resources, and then determines the M resources based on the value of A, the at least some information of the M resources, and a third rule. The third rule is agreed upon by the communication protocol, configured by the network, or reported by the UE. Optionally, the third rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0220] In some embodiments, at least some information of the M resources includes one or more of the following: time-domain information, frequency-domain information, and spatial-domain information. The spatial-domain information can be represented by antenna port, layer, codeword, rank information, etc. The time-domain information may include the quantity and / or location information of the time-domain resources, such as: a time window, or a time-domain start position and duration, or a time-domain start position and end position, or a time-domain end position and duration. The frequency-domain information may include the quantity and / or location information of the frequency-domain resources, such as: a frequency-domain window, or a frequency-domain start position and the number of frequency-domain elements, or a frequency-domain start position and the number of frequency-domain elements, or a frequency-domain end position and the number of frequency-domain elements.

[0221] If the first device receives a channel or data within the first resource out of M resources, it generates feedback response information corresponding to the first resource based on the decoding result of the received channel or data. The feedback response information corresponding to the first resource can be for the decoding result of TB (e.g., TB-level HARQ-ACK); or for the decoding result of CB (e.g., CB-level HARQ-ACK); or for the decoding result of CBG (e.g., CBG-level HARQ-ACK). If the decoding result is "correctly decoded," the feedback response information is ACK; if the decoding result is "incorrectly decoded" or "decoding failed," the feedback response information is NACK.

[0222] If the first device does not receive a channel or data in the second resource among the M resources, the feedback response information corresponding to the second resource is set to reserved information, such as NACK or DTX.

[0223] The feedback response information corresponding to M resources is concatenated in a first order to obtain A bits of feedback response information. The first order includes ascending or descending order of one or more dimensions such as time domain, frequency domain, and spatial domain, and the order of different dimensions can be adjusted according to the actual situation. For example, in the case of two dimensions, it can be time domain first (ascending or descending) then frequency domain (ascending or descending), time domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then time domain (ascending or descending), spatial domain first (ascending or descending) then time domain (ascending or descending), spatial domain first (ascending or descending) then frequency domain (ascending or descending), and so on. Of course, three dimensions can also be used; not all possibilities are listed here.

[0224] If the value of A is a preset value, and the total number of feedback response information corresponding to M resources is less than A, then placeholder information (Padding Bit) is added after the feedback response information corresponding to M resources so that the total number of bits of the feedback response information is equal to A.

[0225] If A is a preset value, and the total number of feedback response messages corresponding to M resources is greater than A, then the feedback response messages corresponding to the M resources are compressed or merged so that the total number of bits in the feedback response messages is equal to A. Merging methods include one or more of the following: merging multiple CB-level HARQ-ACKs to obtain CBG-level HARQ-ACKs, merging multiple CB-level HARQ-ACKs to obtain TB-level HARQ-ACKs, merging multiple CBG-level HARQ-ACKs to obtain TB-level HARQ-ACKs, and merging multiple TB-level HARQ-ACKs to obtain 1 bit of feedback response information.

[0226] In some embodiments, the sender and receiver of the feedback information have the same understanding of the M resources, for example, the M resources are determined according to network configuration or protocol agreement or UE reporting.

[0227] In some embodiments, the sending and receiving ends of the feedback information have the same understanding of how the feedback response information for each resource is generated, for example, the generation method is determined based on network configuration, protocol agreement, or UE reporting. The generation method may include, for example, the HARQ-ACK level (TB-level / CB-level / CBG-level, etc.), the first order, placeholder information, etc.

[0228] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the compression / merging method of the feedback response information corresponding to each resource, for example, the compression / merging method is determined according to network configuration or protocol agreement or UE reporting.

[0229] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the number of bits of the feedback response information corresponding to each resource, for example, the number of bits of the feedback response information corresponding to each resource is determined according to network configuration or protocol agreement or UE reporting.

[0230] In some embodiments, the sending and receiving ends of the feedback information have a consistent understanding of the correspondence / association management between the A-bit feedback response information and the M resources. That is, both the sending and receiving ends clearly understand that the A-bit feedback response information corresponds to the feedback response information for the M resources.

[0231] (2) The A-bit feedback response information is the feedback response information corresponding to P channels, where P is an integer greater than or equal to 1.

[0232] The P channels may include one or more of the following: channels carrying data, channels carrying control information, shared channels, and control channels. The P channels may also be channels received by the first device. Each of the P channels corresponds to at least 1 bit of information.

[0233] In some embodiments, the first device first determines P channels, for example, based on network configuration, UE reporting, or protocol agreement, and then determines the value of A based on the P channels and the fourth rule. The fourth rule is agreed upon by the communication protocol, network configuration, or UE reporting. Optionally, the fourth rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0234] In some embodiments, the first device first determines the value of A, for example, based on network configuration, UE reporting, or protocol agreement, and then determines P channels based on the value of A and the fifth rule. The fifth rule is agreed upon by the communication protocol, network configuration, or UE reporting. Optionally, the fifth rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0235] The first device generates feedback response information corresponding to a channel based on the decoding result of that channel. The feedback response information for a channel can be for the decoding result of TB (TB-level), such as TB-level HARQ-ACK; or for the decoding result of CB (CB-level), such as CB-level HARQ-ACK; or for the decoding result of CBG (CBG-level), such as CBG-level HARQ-ACK. If the decoding result is "correctly decoded," the feedback response information is ACK; if the decoding result is "incorrectly decoded" or "decoding failed," the feedback response information is NACK.

[0236] The feedback response information corresponding to P channels is concatenated in the first order to obtain A bits of feedback response information. The first order includes ascending or descending order of one or more dimensions such as time domain, frequency domain, spatial domain, and channel number (or index), and the order of different dimensions can be adjusted according to the actual situation. For example, in the case of two dimensions, it can be time domain first (ascending or descending) then frequency domain (ascending or descending), time domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then time domain (ascending or descending), spatial domain first (ascending or descending) then time domain (ascending or descending), and spatial domain first (ascending or descending) then frequency domain (ascending or descending). The order of channel numbering can be categorized as follows: first channel number (ascending or descending) then time domain (ascending or descending); first channel number (ascending or descending) then frequency domain (ascending or descending); first channel number (ascending or descending) then spatial domain (ascending or descending); first time domain (ascending or descending) then channel number (ascending or descending); first frequency domain (ascending or descending) then channel number (ascending or descending); first spatial domain (ascending or descending) then channel number (ascending or descending), and so on. Of course, three or four dimensions can also be used; not all possibilities are listed here.

[0237] If the value of A is a preset value, and the total number of feedback response information corresponding to P channels is less than A, then placeholder information (Padding Bit) is added after the feedback response information corresponding to P channels so that the total number of bits of the feedback response information is equal to A.

[0238] If A is a preset value, and the total number of feedback response messages corresponding to P channels is greater than A, then the feedback response messages corresponding to P channels are compressed or merged so that the total number of bits of the feedback response messages is equal to A. Merging methods include one or more of the following: merging multiple CB-level HARQ-ACKs to obtain CBG-level HARQ-ACK, merging multiple CB-level HARQ-ACKs to obtain TB-level HARQ-ACK, merging multiple CBG-level HARQ-ACKs to obtain TB-level HARQ-ACK, and merging multiple TB-level HARQ-ACKs to obtain 1 bit of feedback response information.

[0239] In some embodiments, the sender and receiver of the feedback information have the same understanding of the P channels, for example, the P channels are determined according to network configuration or protocol agreement or UE reporting.

[0240] In some embodiments, the sending and receiving ends of the feedback information have the same understanding of how the feedback response information is generated for each channel, for example, the generation method is determined based on network configuration, protocol agreement, or UE reporting. The generation method may include, for example, the HARQ-ACK level (TB-level / CB-level / CBG-level, etc.), the first order, placeholder information, etc.

[0241] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the compression / merging method of the feedback response information corresponding to each channel, for example, the compression / merging method is determined according to network configuration or protocol agreement or UE reporting.

[0242] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the number of bits of the feedback response information corresponding to each channel, for example, the number of bits of the feedback response information corresponding to each channel is determined according to network configuration or protocol agreement or UE reporting.

[0243] In some embodiments, the sending and receiving ends of the feedback information have a consistent understanding of the correspondence / association management between the A-bit feedback response information and the P channels. That is, both the sending and receiving ends clearly understand that the A-bit feedback response information corresponds to the feedback response information for the P channels.

[0244] (3) The A-bit feedback response information is the feedback response information corresponding to Q HARQ processes, where Q is an integer greater than or equal to 1.

[0245] One of the Q HARQ processes corresponds to at least 1 bit of information.

[0246] In some embodiments, the first device first determines Q HARQ processes, for example, based on network configuration, UE reporting, or protocol agreement, and then determines the value of A based on the Q HARQ processes and the sixth rule. The sixth rule is determined by the communication protocol, network configuration, or UE reporting. Optionally, the sixth rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0247] In some embodiments, the first device first determines the value of A, for example, based on network configuration, UE reporting, or protocol agreement, and then determines Q HARQ processes based on the value of A and the seventh rule. The seventh rule is agreed upon by the communication protocol, network configuration, or UE reporting. Optionally, the seventh rule is defined in the form of a textual description, a mathematical formula, or a mapping relationship.

[0248] If the first device receives the first HARQ process, it generates a feedback response message corresponding to the first HARQ process based on the decoding result of the first HARQ process. The feedback response message corresponding to the first HARQ process can be for the decoding result of TB, such as TB-level HARQ-ACK; or for the decoding result of CB, such as CB-level HARQ-ACK; or for the decoding result of CBG, such as CBG-level HARQ-ACK. If the decoding result is "correctly decoded," the feedback response message is ACK; if the decoding result is "incorrectly decoded" or "decoding failed," the feedback response message is NACK.

[0249] If the first device does not receive the second HARQ process, the feedback response information corresponding to the second HARQ process is set to reserved information, such as NACK or DTX.

[0250] The feedback response information corresponding to Q HARQ processes is concatenated in the first order to obtain A bits of feedback response information. The first order includes ascending or descending order of one or more dimensions such as time domain, frequency domain, spatial domain, and HARQ process number, and the order of different dimensions can be adjusted according to the actual situation. For example, in the case of two dimensions, it can be time domain first (ascending or descending) then frequency domain (ascending or descending), time domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then spatial domain (ascending or descending), frequency domain first (ascending or descending) then time domain (ascending or descending), spatial domain first (ascending or descending) then time domain (ascending or descending), spatial domain first (ascending or descending) then frequency domain (ascending or descending), and HARQ process first. The order of operations can be: first the HARQ process number (ascending or descending) then the time domain (ascending or descending); first the HARQ process number (ascending or descending) then the frequency domain (ascending or descending); first the HARQ process number (ascending or descending) then the spatial domain (ascending or descending); first the time domain (ascending or descending) then the HARQ process number (ascending or descending); first the frequency domain (ascending or descending) then the HARQ process number (ascending or descending); first the spatial domain (ascending or descending) then the HARQ process number (ascending or descending), and so on. Of course, three or four dimensions can also be used; not all possibilities are listed here.

[0251] If the value of A is a preset value, and the total number of feedback response messages corresponding to Q HARQ processes is less than A, then placeholder information (Padding Bit) is added after the feedback response messages corresponding to Q HARQ processes, so that the total number of bits of the feedback response messages is equal to A.

[0252] If A is a preset value, and the total number of feedback response messages corresponding to the Q HARQ processes is greater than A, then the feedback response messages corresponding to the Q HARQ processes are compressed or merged so that the total number of bits in the feedback response messages is equal to A. Merging methods include one or more of the following: merging multiple CB-level HARQ-ACKs to obtain CBG-level HARQ-ACKs, merging multiple CB-level HARQ-ACKs to obtain TB-level HARQ-ACKs, merging multiple CBG-level HARQ-ACKs to obtain TB-level HARQ-ACKs, and merging multiple TB-level HARQ-ACKs to obtain 1 bit of feedback response information.

[0253] In some embodiments, the sender and receiver of the feedback information have the same understanding of the Q HARQ processes, for example, the Q HARQ processes are determined according to network configuration or protocol agreement or UE reporting.

[0254] In some embodiments, the sending and receiving ends of the feedback information have the same understanding of how the feedback response information for each HARQ process is generated, for example, the generation method is determined based on network configuration, protocol agreement, or UE reporting. The generation method may include, for example, the HARQ-ACK level (TB-level / CB-level / CBG-level, etc.), the first order, placeholder information, etc.

[0255] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the compression / merging method of the feedback response information corresponding to each HARQ process, for example, the compression / merging method is determined according to network configuration or protocol agreement or UE reporting.

[0256] In some embodiments, the sending end and receiving end of the feedback information have the same understanding of the number of bits of the feedback response information corresponding to each HARQ process, for example, the number of bits of the feedback response information corresponding to each HARQ process is determined according to network configuration or protocol agreement or UE reporting.

[0257] In some embodiments, the sending and receiving ends of the feedback information have a consistent understanding of the correspondence / association management between the A-bit feedback response information and the Q HARQ processes. That is, both the sending and receiving ends clearly understand that the A-bit feedback response information corresponds to the feedback response information of the Q HARQ processes.

[0258] After obtaining A-bit feedback response information, the first device inputs the A-bit feedback response information into the encoding end model of the agreed model, and the encoding end model outputs feedback information. Optionally, the encoding end model outputs B-bit feedback information, where B is less than A. The B-bit feedback information is then processed by encoding and / or modulation and mapped onto the first physical resource for transmission. Optionally, the feedback information output by the encoding end model does not require channel coding and / or modulation processing and can be directly mapped onto the first physical resource for transmission.

[0259] After receiving the feedback information, the second device inputs it into the decoding model of the agreed-upon model. The decoding model then outputs A-bit feedback response information. In other words, the second device can use the decoding model to reconstruct the A-bit feedback response information from the received feedback information.

[0260] Figure 7 shows a structural block diagram of a model-based feedback device provided in an exemplary embodiment of this application. This device can be implemented as the first device described above, or as part of the first device described above. The first device can be the network device 110 or the terminal device 120 shown in Figure 1. The device includes a transmitting module 710. Optionally, the device also includes a processing module 730 and / or a receiving module 750.

[0261] The sending module 710 is used to send feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0262] In some embodiments, the sending module 710 is further configured to send one or more of the following information: first information, third information, request signaling for feedback information, model switching request information, and response information for the first information.

[0263] In some embodiments, the processing module 730 is configured to perform one or more of the following steps: determining a convention model based on first information, determining a convention model based on second information, determining the value of A, determining M resources, determining P channels, determining Q HARQ processes, determining A bits of feedback information, determining at least some information of the M resources, determining the generation method of the feedback response information, determining the compression method of the feedback response information, determining the merging method of the feedback response information, and determining the number of bits of the feedback response information.

[0264] In some embodiments, the processing module 730 is further configured to: train the convention model, update the convention model, and switch the convention model.

[0265] In some embodiments, the receiving module 750 is configured to perform one or more of the following steps: receiving first information, receiving third information, receiving trigger signaling for feedback information, receiving model switching request information, receiving response information for the first information, receiving data, receiving a channel, receiving configuration information. The configuration information may be used to configure one or more of the following: second information, the value of A, M resources, P channels, Q HARQ processes, at least some information of the M resources, the method for generating feedback response information, the method for compressing feedback response information, the method for merging feedback response information, and the number of bits in the feedback response information.

[0266] The steps performed by the sending module 710, the processing module 730, and the receiving module 750 are the same as those performed by the first device in the embodiments shown above. The relevant content described in the previous embodiments also applies to the device shown in Figure 7, and will not be repeated here.

[0267] In summary, the apparatus provided in this application supports feedback using a model. Because the model has high scalability, flexibility, and high processing efficiency, it helps to respond to multi-bit response information in real time, improving feedback efficiency while ensuring the efficiency, accuracy, and precision of the feedback information.

[0268] Figure 8 shows a structural block diagram of a model-based feedback device provided in an exemplary embodiment of this application. This device can be implemented as the second device described above, or as part of the second device described above. The second device can be the network device 110 or the terminal device 120 shown in Figure 1. The device includes a receiving module 810. Optionally, the device also includes a processing module 830 and / or a transmitting module 850.

[0269] The receiving module 810 is used to receive feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

[0270] In some embodiments, the receiving module 810 is further configured to receive one or more of the following information: first information, third information, request signaling for feedback information, model switching request information, and response information for the first information.

[0271] In some embodiments, the processing module 830 is used to obtain the A-bit feedback response information based on the feedback information and the agreed model.

[0272] In some embodiments, the processing module 830 is further configured to perform one or more of the following steps: determining a convention model based on first information, determining a convention model based on second information, determining the value of A, determining M resources, determining P channels, determining Q HARQ processes, determining A bits of feedback information, determining at least some information of the M resources, determining the generation method of the feedback response information, determining the compression method of the feedback response information, determining the merging method of the feedback response information, and determining the number of bits of the feedback response information.

[0273] In some embodiments, the processing module 830 is further configured to: train the convention model, update the convention model, and switch the convention model.

[0274] In some embodiments, the sending module 850 is configured to perform one or more of the following steps: sending first information, sending third information, sending a trigger signaling message for sending feedback information, sending a model switching request message, sending a response message for sending the first information, sending data, sending a channel, sending configuration information. The configuration information may be used to configure one or more of the following: second information, the value of A, M resources, P channels, Q HARQ processes, at least some information of the M resources, the method for generating the feedback response information, the method for compressing the feedback response information, the method for merging the feedback response information, and the number of bits in the feedback response information.

[0275] The steps performed by the receiving module 810, processing module 830, and sending module 850 are the same as those performed by the second device in the embodiments shown above. The relevant content described in the previous embodiments also applies to the device shown in Figure 8, and will not be repeated here.

[0276] In summary, the apparatus provided in this application supports feedback using a model. Because the model has high scalability, flexibility, and high processing efficiency, it helps to respond to multi-bit response information in real time, improving feedback efficiency while ensuring the efficiency, accuracy, and precision of the feedback information.

[0277] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the communication device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept.

[0278] Figure 9 shows a schematic diagram of a model-based feedback device provided in an exemplary embodiment of this application, including at least one of the following: a receiver 901, a transmitter 902, a processor 903, a memory 904, and a bus (not shown in the figure). Optionally, the feedback device 900 is used to perform some or all of the steps performed by the first device described above. Optionally, the feedback device 900 is used to perform some or all of the steps performed by the second device described above.

[0279] In this design, receiver 901 is used to implement the receiving function, and transmitter 902 is used to implement the transmitting function. Optionally, receiver 901 and transmitter 902 can be implemented as a communication component, which can be a communication chip, and can be referred to as a transceiver. Optionally, receiver 901 and transmitter 902 can be implemented as a wireless communication component and / or a wired communication component. Optionally, the wireless communication component includes a wireless communication chip and / or a radio frequency antenna. Optionally, the wired communication component includes a wired communication chip and / or a wired interface.

[0280] In some embodiments, receiver 901 can be used to implement the functions and steps of receiving module 750, and transmitter 902 can be used to implement the functions and steps of sending module 710.

[0281] In some embodiments, receiver 901 can be used to implement the functions and steps of receiving module 810, and transmitter 902 can be used to implement the functions and steps of sending module 850.

[0282] The processor 903 includes one or more processing cores. The processor 903 executes various functional applications and information processing by running software programs and modules. In some embodiments, the processor 903 can be used to implement the functions and steps of the processing module 730 or processing module 830 described above.

[0283] The memory 904 can be used to store a computer program executed by the processor 903, which executes the computer program to implement the various steps in the above method embodiments.

[0284] Furthermore, the memory 904 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, including but not limited to: magnetic disks or optical disks, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), read-only memory (ROM), magnetic storage, flash memory, and programmable read-only memory (PROM).

[0285] In some embodiments, the memory 904 may be connected to the processor 903, the receiver 901, and the transmitter 902.

[0286] In some embodiments, the receiver 901 independently receives signals / data, or the processor 903 controls the receiver 901 to receive signals / data, or the processor 903 requests the receiver 901 to receive signals / data, or the processor 903 cooperates with the receiver 901 to receive signals / data.

[0287] In some embodiments, the transmitter 902 independently transmits signals / data, or the processor 903 controls the transmitter 902 to transmit signals / data, or the processor 903 requests the transmitter 902 to transmit signals / data, or the processor 903 cooperates with the transmitter 902 to transmit signals / data.

[0288] For details not described in this embodiment, please refer to the embodiments above, which will not be repeated here.

[0289] In one exemplary embodiment of this application, a chip is also provided, the chip including programmable logic circuits and / or program instructions, which, when the chip is run on a communication device, is used to implement the model-based feedback method provided in the above-described method embodiments.

[0290] In some embodiments, the chip includes a transmitting module 710. Optionally, the chip further includes a processing module 730 and / or a receiving module 750. Related details can be found above and will not be repeated here. Optionally, each module can be implemented as a circuit structure.

[0291] In some embodiments, the chip includes a receiving module 810. Optionally, the chip further includes a processing module 830 and / or a transmitting module 850. Related details can be found above and will not be repeated here. Optionally, each module can be implemented as a circuit structure.

[0292] In one exemplary embodiment of this application, a computer-readable storage medium is also provided, which stores at least one program that is loaded and executed by a processor to implement the model-based feedback method provided in the above-described method embodiments.

[0293] In one exemplary embodiment of this application, a computer program product is also provided, the computer program product including computer instructions, the computer instructions being stored in a computer-readable storage medium, a processor retrieving the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to implement the model-based feedback method provided in the above-described method embodiments.

[0294] In one exemplary embodiment of this application, a computer program is also provided, the computer program including computer instructions stored in a computer-readable storage medium, a processor obtaining the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to implement the model-based feedback method provided in the above-described method embodiments.

[0295] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0296] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A model-based feedback method, characterized in that, The method includes: Send feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

2. The method according to claim 1, characterized in that, The agreed-upon model is indicated or activated by first information, which is sent by a network device or a terminal device.

3. The method according to claim 2, characterized in that, The first information carries one or more of the following model information: the model identifier of the agreed model, the model function of the agreed model, the input information features of the agreed model, the output information features of the agreed model, the model performance of the agreed model, the dataset of the agreed model, the dataset identifier of the agreed model, the usage scenario information of the agreed model, and the usage condition information of the agreed model.

4. The method according to claim 2 or 3, characterized in that, The validity of the first information satisfies one or more of the following: the effective time of the first information is agreed upon by the communication protocol; the effective time of the first information is indicated by the network device; the effective time of the first information is indicated by the terminal device; the effective time of the first information is indicated by the first information; the end position of the effective time of the first information is the receiving time of the next first information; the first information is valid for a single feedback.

5. The method according to any one of claims 2 to 4, characterized in that, The transmission of the first information and the transmission of the feedback information are associated with any one or more of the following: the first information and the feedback information are transmitted through the same channel; the first information and the feedback information are transmitted within the same time unit; the first information and the feedback information are transmitted within the same frequency domain unit; there is a first offset between the transmission time of the first information and the transmission time of the feedback information; the triggering signaling of the feedback information includes the first information, and the triggering signaling is used to trigger the transmission of the feedback information; the requesting signaling of the feedback information includes the first information, and the requesting signaling is used to request the triggering signaling of the feedback information to be sent.

6. The method according to any one of claims 2 to 5, characterized in that, The method further includes: Upon receiving the first information, send a response message in response to the first information; or... When the first information is sent, a response information is received in response to the first information.

7. The method according to any one of claims 2 to 6, characterized in that, The agreed-upon model is one of multiple models that is indicated or activated by the first information.

8. The method according to claim 1, characterized in that, The agreed-upon model is one of multiple models determined based on the second information.

9. The method according to claim 8, characterized in that, The second information includes one or more of the following: data parameters corresponding to the feedback information; transmission parameters of the feedback information; performance monitoring results of the feedback information; and model switching request information, used to request switching of the agreed model.

10. The method according to claim 9, characterized in that, The data parameters corresponding to the feedback information include one or more of the following: data volume, number of coding blocks, data transmission scheduling method, coding rate, modulation coding method, and resource mapping method. The transmission parameters of the feedback information include one or more of the following: channel type, channel format, number of bits, HARQ-ACK codebook type, number of transmission resources, whether to use repeated transmission, and whether to use multiplexed transmission. The performance monitoring results of the feedback information are associated with one or more of the following: retransmission information includes data that has been correctly decoded and data that failed to be decoded and was not retransmitted.

11. The method according to any one of claims 7 to 10, characterized in that, The multiple models are indicated by a network device; or the multiple models are reported by a terminal device; or, a portion of the multiple models are indicated by the network device and another portion are reported by the terminal device.

12. The method according to any one of claims 1 to 11, characterized in that, The first feedback response information in the A-bit feedback response information includes one or more of the following: feedback response information corresponding to one or a group of resources, wherein the resources include at least one time-domain unit and / or at least one frequency-domain unit; feedback response information corresponding to one or a group of channels; feedback response information corresponding to one or a group of HARQ processes; feedback response information corresponding to one or a group of transport blocks; and feedback response information corresponding to one or a group of coding blocks.

13. The method according to claim 12, characterized in that, In the first case, the first feedback response information is a first agreed-upon information; or, in the second case, the first feedback response information is a second agreed-upon information; or, in the third case, the first feedback response information is a third agreed-upon information. The first type of situation includes one or more of the following: the information received in the one or a group of resources is correctly decoded, the channel received in the one or a group of resources is correctly decoded, the one or a group of channels received is correctly decoded, the one or a group of HARQ processes received is correctly decoded, the one or a group of transport blocks received is correctly decoded, and the one or a group of coded blocks received is correctly decoded. The second category includes one or more of the following: information received in one or more of the resources was not correctly decoded; a channel received in one or more of the resources was not correctly decoded; the received one or more channels were not correctly decoded; and the received information was not correctly decoded. The following are examples of incorrect decoding: one or more HARQ processes are not correctly decoded, one or more transport blocks are not correctly decoded, and one or more coded blocks are not correctly decoded. The third category includes one or more of the following: no information was received in one or a group of resources, no channel was received in one or a group of resources, no channel was received, no HARQ process was received, no transport block was received, and no coding block was received.

14. The method according to any one of claims 1 to 13, characterized in that, The A-bit feedback response information is obtained by concatenating the corresponding resources, channels, transport blocks, coding blocks, coding block groups, or HARQ processes in a first order; wherein, the first order includes one or more of the following orders: time-domain ascending order, time-domain descending order, frequency-domain ascending order, frequency-domain descending order, spatial-domain ascending order, spatial-domain descending order, number ascending order, and number descending order.

15. The method according to any one of claims 1 to 14, characterized in that, The A-bit feedback response information is obtained based on the C-bit information; or, each bit of the A-bit feedback response information corresponds to one of A groups, and the A groups are obtained by dividing C resources, C channels, C HARQ processes, C transport blocks, or C coding blocks; where C is an integer greater than A.

16. The method according to any one of claims 1 to 15, characterized in that, The value of A is determined based on the network device configuration, or according to the communication protocol, or according to the information reported by the terminal device.

17. The method according to any one of claims 1 to 16, characterized in that, The method further includes: The value of A determines at least one corresponding resource, channel, or HARQ process; or, The corresponding A-bit feedback information is determined based on at least one resource, channel, or HARQ process; or... The value of A is determined based on at least one resource, channel, or HARQ process.

18. The method according to any one of claims 1 to 17, characterized in that, The following one or more pieces of information are indicated by the network device, reported by the terminal device, or agreed upon by the communication protocol: one or a group of resources; one or a group of channels; one or a group of HARQ processes; the generation method of the A-bit feedback response information; the codebook type of the A-bit feedback response information; and the compression method of the A-bit feedback response information. The merging method of the A-bit feedback response information; the number of bits of the feedback response information corresponding to one or a group of resources; the number of bits of the feedback response information corresponding to one or a group of channels; the number of bits of the feedback response information corresponding to one or a group of HARQ processes; the association relationship between the A-bit feedback response information and the at least one or a group of resources; the association relationship between the A-bit feedback response information and the at least one or a group of channels; the association relationship between the A-bit feedback response information and the at least one or a group of HARQ processes.

19. A model-based feedback method, characterized in that, The method includes: The system receives feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

20. The method according to claim 19, characterized in that, The method further includes: Based on the feedback information and the agreed model, the A-bit feedback response information is obtained.

21. The method according to claim 19 or 20, characterized in that, The agreed-upon model is indicated or activated by first information, which is sent by a network device or a terminal device.

22. The method according to claim 21, characterized in that, The first information carries one or more of the following model information: the model identifier of the agreed model, the model function of the agreed model, the input information features of the agreed model, the output information features of the agreed model, the model performance of the agreed model, the dataset of the agreed model, the dataset identifier of the agreed model, the usage scenario information of the agreed model, and the usage condition information of the agreed model.

23. The method according to claim 21 or 22, characterized in that, The validity of the first information satisfies one or more of the following: the effective time of the first information is agreed upon by the communication protocol; the effective time of the first information is indicated by the network device; the effective time of the first information is indicated by the terminal device; the effective time of the first information is indicated by the first information; the end position of the effective time of the first information is the receiving time of the next first information; the first information is valid for a single feedback.

24. The method according to any one of claims 21 to 23, characterized in that, The transmission of the first information and the transmission of the feedback information are associated with any one or more of the following: the first information and the feedback information are transmitted through the same channel; the first information and the feedback information are transmitted within the same time unit; the first information and the feedback information are transmitted within the same frequency domain unit; there is a first offset between the transmission time of the first information and the transmission time of the feedback information; the triggering signaling of the feedback information includes the first information, and the triggering signaling is used to trigger the transmission of the feedback information; the requesting signaling of the feedback information includes the first information, and the requesting signaling is used to request the triggering signaling of the feedback information to be sent.

25. The method according to any one of claims 21 to 24, characterized in that, The method further includes: Upon receiving the first information, send a response message in response to the first information; or... When the first information is sent, a response information is received in response to the first information.

26. The method according to any one of claims 21 to 25, characterized in that, The agreed-upon model is one of multiple models that is indicated or activated by the first information.

27. The method according to claim 19 or 20, characterized in that, The agreed-upon model is one of multiple models determined based on the second information.

28. The method according to claim 27, characterized in that, The second information includes one or more of the following: data parameters corresponding to the feedback information; transmission parameters of the feedback information; performance monitoring results of the feedback information; and model switching request information, used to request switching of the agreed model.

29. The method according to claim 28, characterized in that, The data parameters corresponding to the feedback information include one or more of the following: data volume, number of coding blocks, data transmission scheduling method, coding rate, modulation coding method, and resource mapping method. The transmission parameters of the feedback information include one or more of the following: channel type, channel format, number of bits, HARQ-ACK codebook type, number of transmission resources, whether to use repeated transmission, and whether to use multiplexed transmission. The performance monitoring results of the feedback information are associated with one or more of the following: retransmission information includes data that has been correctly decoded and data that failed to be decoded and was not retransmitted.

30. The method according to any one of claims 26 to 29, characterized in that, The multiple models are indicated by a network device; or the multiple models are reported by a terminal device; or, a portion of the multiple models are indicated by the network device and another portion are reported by the terminal device.

31. The method according to any one of claims 19 to 30, characterized in that, The first feedback response information in the A-bit feedback response information includes one or more of the following: feedback response information corresponding to one or a group of resources, wherein the resources include at least one time-domain unit and / or at least one frequency-domain unit; feedback response information corresponding to one or a group of channels; feedback response information corresponding to one or a group of HARQ processes; feedback response information corresponding to one or a group of transport blocks; and feedback response information corresponding to one or a group of coding blocks.

32. The method according to claim 31, characterized in that, In the first case, the first feedback response information is a first agreed-upon information; or, in the second case, the first feedback response information is a second agreed-upon information; or, in the third case, the first feedback response information is a third agreed-upon information. The first type of situation includes one or more of the following: the information received in the one or a group of resources is correctly decoded, the channel received in the one or a group of resources is correctly decoded, the one or a group of channels received is correctly decoded, the one or a group of HARQ processes received is correctly decoded, the one or a group of transport blocks received is correctly decoded, and the one or a group of coded blocks received is correctly decoded. The second category includes one or more of the following: information received in one or a group of resources is not correctly decoded, a channel received in one or a group of resources is not correctly decoded, the received one or a group of channels is not correctly decoded, the received one or a group of HARQ processes is not correctly decoded, the received one or a group of transport blocks is not correctly decoded, and the received one or a group of coded blocks is not correctly decoded. The third category includes one or more of the following: no information was received in one or a group of resources, no channel was received in one or a group of resources, no channel was received, no HARQ process was received, no transport block was received, and no coding block was received.

33. The method according to any one of claims 19 to 32, characterized in that, The A-bit feedback response information is obtained by concatenating the corresponding resources, channels, transport blocks, coding blocks, coding block groups, or HARQ processes in a first order; wherein, the first order includes one or more of the following orders: time-domain ascending order, time-domain descending order, frequency-domain ascending order, frequency-domain descending order, spatial-domain ascending order, spatial-domain descending order, number ascending order, and number descending order.

34. The method according to any one of claims 19 to 33, characterized in that, The A-bit feedback response information is obtained based on the C-bit information; or, each bit of the A-bit feedback response information corresponds to one of A groups, which are obtained by dividing C resources, C channels, C HARQ processes, C transport blocks, or C coding blocks; where C is an integer greater than A.

35. The method according to any one of claims 19 to 34, characterized in that, The value of A is determined based on the network device configuration, or according to the communication protocol, or according to the information reported by the terminal device.

36. The method according to any one of claims 19 to 35, characterized in that, The method further includes: determining at least one corresponding resource, channel, or HARQ process based on the value of A; or determining corresponding A bit feedback information based on at least one resource, channel, or HARQ process; or determining the corresponding value of A based on at least one resource, channel, or HARQ process.

37. The method according to any one of claims 19 to 36, characterized in that, The following one or more pieces of information are indicated by the network device, reported by the terminal device, or agreed upon by the communication protocol: one or a group of resources; one or a group of channels; one or a group of HARQ processes; the generation method of the A-bit feedback response information; the codebook type of the A-bit feedback response information; and the compression method of the A-bit feedback response information. The merging method of the A-bit feedback response information; the number of bits of the feedback response information corresponding to one or a group of resources; the number of bits of the feedback response information corresponding to one or a group of channels; the number of bits of the feedback response information corresponding to one or a group of HARQ processes; the association relationship between the A-bit feedback response information and the at least one or a group of resources; the association relationship between the A-bit feedback response information and the at least one or a group of channels; the association relationship between the A-bit feedback response information and the at least one or a group of HARQ processes.

38. A model-based feedback device, characterized in that, The device includes: The sending module is used to send feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

39. The apparatus according to claim 38, characterized in that, The agreed-upon model is indicated or activated by first information, which is sent by a network device or a terminal device.

40. The apparatus according to claim 39, characterized in that, The first information carries one or more of the following model information: the model identifier of the agreed model, the model function of the agreed model, the input information features of the agreed model, the output information features of the agreed model, the model performance of the agreed model, the dataset of the agreed model, the dataset identifier of the agreed model, the usage scenario information of the agreed model, and the usage condition information of the agreed model.

41. The apparatus according to claim 39 or 40, characterized in that, The validity of the first information satisfies one or more of the following: the effective time of the first information is agreed upon by the communication protocol; the effective time of the first information is indicated by the network device; the effective time of the first information is indicated by the terminal device; the effective time of the first information is indicated by the first information; the end position of the effective time of the first information is the receiving time of the next first information; the first information is valid for a single feedback.

42. The apparatus according to any one of claims 39 to 41, characterized in that, The transmission of the first information and the transmission of the feedback information are associated with any one or more of the following: the first information and the feedback information are transmitted through the same channel; the first information and the feedback information are transmitted within the same time unit; the first information and the feedback information are transmitted within the same frequency domain unit; there is a first offset between the transmission time of the first information and the transmission time of the feedback information; the triggering signaling of the feedback information includes the first information, and the triggering signaling is used to trigger the transmission of the feedback information; the requesting signaling of the feedback information includes the first information, and the requesting signaling is used to request the triggering signaling of the feedback information to be sent.

43. The apparatus according to any one of claims 39 to 42, characterized in that, The sending module is further configured to send response information in response to the first information; or, The device further includes a receiving module for receiving response information in response to the first information.

44. The apparatus according to any one of claims 39 to 43, characterized in that, The agreed-upon model is one of multiple models that is indicated or activated by the first information.

45. The apparatus according to claim 38, characterized in that, The agreed-upon model is one of multiple models determined based on the second information.

46. ​​The apparatus according to claim 45, characterized in that, The second information includes one or more of the following: data parameters corresponding to the feedback information; transmission parameters of the feedback information; performance monitoring results of the feedback information; and model switching request information, used to request switching of the agreed model.

47. The apparatus according to claim 46, characterized in that, The data parameters corresponding to the feedback information include one or more of the following: data volume, number of coding blocks, data transmission scheduling method, coding rate, modulation coding method, and resource mapping method. The transmission parameters of the feedback information include one or more of the following: channel type, channel format, number of bits, HARQ-ACK codebook type, number of transmission resources, whether to use repeated transmission, and whether to use multiplexed transmission. The performance monitoring results of the feedback information are associated with one or more of the following: retransmission information includes data that has been correctly decoded and data that failed to be decoded and was not retransmitted.

48. The apparatus according to any one of claims 44 to 47, characterized in that, The multiple models are indicated by a network device; or the multiple models are reported by a terminal device; or, a portion of the multiple models are indicated by the network device and another portion are reported by the terminal device.

49. The apparatus according to any one of claims 38 to 48, characterized in that, The first feedback response information in the A-bit feedback response information includes one or more of the following: feedback response information corresponding to one or a group of resources, wherein the resources include at least one time-domain unit and / or at least one frequency-domain unit; feedback response information corresponding to one or a group of channels; feedback response information corresponding to one or a group of HARQ processes; feedback response information corresponding to one or a group of transport blocks; and feedback response information corresponding to one or a group of coding blocks.

50. The apparatus according to claim 49, characterized in that, In the first case, the first feedback response information is a first agreed-upon information; or, in the second case, the first feedback response information is a second agreed-upon information; or, in the third case, the first feedback response information is a third agreed-upon information. The first type of situation includes one or more of the following: the information received in the one or a group of resources is correctly decoded, the channel received in the one or a group of resources is correctly decoded, the one or a group of channels received is correctly decoded, the one or a group of HARQ processes received is correctly decoded, the one or a group of transport blocks received is correctly decoded, and the one or a group of coded blocks received is correctly decoded. The second category includes one or more of the following: information received in one or more of the resources was not correctly decoded, and in the... The received channel in one or a group of resources was not correctly decoded, the received one or a group of channels was not correctly decoded, the received one or a group of HARQ processes was not correctly decoded, the received one or a group of transport blocks was not correctly decoded, and the received one or a group of coded blocks was not correctly decoded. The third category includes one or more of the following: no information was received in one or a group of resources, no channel was received in one or a group of resources, no channel was received, no HARQ process was received, no transport block was received, and no coding block was received.

51. The apparatus according to any one of claims 38 to 50, characterized in that, The A-bit feedback response information is obtained by concatenating the corresponding resources, channels, transport blocks, coding blocks, coding block groups, or HARQ processes in a first order; wherein, the first order includes one or more of the following orders: time-domain ascending order, time-domain descending order, frequency-domain ascending order, frequency-domain descending order, spatial-domain ascending order, spatial-domain descending order, number ascending order, and number descending order.

52. The apparatus according to any one of claims 38 to 51, characterized in that, The A-bit feedback response information is obtained based on the C-bit information; or, each bit of the A-bit feedback response information corresponds to one of A groups, which are obtained by dividing C resources, C channels, C HARQ processes, C transport blocks, or C coding blocks; where C is an integer greater than A.

53. The apparatus according to any one of claims 38 to 52, characterized in that, The value of A is determined based on the network device configuration, or according to the communication protocol, or according to the information reported by the terminal device.

54. The apparatus according to any one of claims 38 to 53, characterized in that, The device further includes a processing module, configured to: determine at least one corresponding resource, channel, or HARQ process based on the value of A; or, determine corresponding A bit feedback information based on at least one resource, channel, or HARQ process; or, determine the corresponding value of A based on at least one resource, channel, or HARQ process.

55. The apparatus according to any one of claims 38 to 54, characterized in that, The following one or more pieces of information are indicated by the network device, reported by the terminal device, or agreed upon by the communication protocol: one or a group of resources; one or a group of channels; one or a group of HARQ processes; the generation method of the A-bit feedback response information; the codebook type of the A-bit feedback response information; and the compression method of the A-bit feedback response information. The merging method of the A-bit feedback response information; the number of bits of the feedback response information corresponding to one or a group of resources; the number of bits of the feedback response information corresponding to one or a group of channels; the number of bits of the feedback response information corresponding to one or a group of HARQ processes; the association relationship between the A-bit feedback response information and the at least one or a group of resources; the association relationship between the A-bit feedback response information and the at least one or a group of channels; the association relationship between the A-bit feedback response information and the at least one or a group of HARQ processes.

56. A model-based feedback device, characterized in that, The device includes: The receiving module is used to receive feedback information, which is obtained based on A-bit feedback response information and a conventional model, where A is a positive integer.

57. The apparatus according to claim 56, characterized in that, The device further includes a processing module for obtaining the A-bit feedback response information based on the feedback information and the agreed model.

58. The apparatus according to claim 56 or 57, characterized in that, The agreed-upon model is indicated or activated by first information, which is sent by a network device or a terminal device.

59. The apparatus according to claim 58, characterized in that, The first information carries one or more of the following model information: the model identifier of the agreed model, the model function of the agreed model, the input information features of the agreed model, the output information features of the agreed model, the model performance of the agreed model, the dataset of the agreed model, the dataset identifier of the agreed model, the usage scenario information of the agreed model, and the usage condition information of the agreed model.

60. The apparatus according to claim 58 or 59, characterized in that, The validity of the first information satisfies one or more of the following: the effective time of the first information is agreed upon by the communication protocol; the effective time of the first information is indicated by the network device; the effective time of the first information is indicated by the terminal device; the effective time of the first information is indicated by the first information; the end position of the effective time of the first information is the receiving time of the next first information; the first information is valid for a single feedback.

61. The apparatus according to any one of claims 58 to 60, characterized in that, The transmission of the first information and the transmission of the feedback information are associated with any one or more of the following: the first information and the feedback information are transmitted through the same channel; the first information and the feedback information are transmitted within the same time unit; the first information and the feedback information are transmitted within the same frequency domain unit; there is a first offset between the transmission time of the first information and the transmission time of the feedback information; the triggering signaling of the feedback information includes the first information, and the triggering signaling is used to trigger the transmission of the feedback information; the requesting signaling of the feedback information includes the first information, and the requesting signaling is used to request the triggering signaling of the feedback information to be sent.

62. The apparatus according to any one of claims 58 to 61, characterized in that, The receiving module is further configured to receive response information in response to the first information; or, The device further includes a sending module for sending response information in response to the first information.

63. The apparatus according to any one of claims 58 to 62, characterized in that, The agreed-upon model is one of multiple models that is indicated or activated by the first information.

64. The apparatus according to claim 56 or 57, characterized in that, The agreed-upon model is one of multiple models determined based on the second information.

65. The apparatus according to claim 64, characterized in that, The second information includes one or more of the following: data parameters corresponding to the feedback information; transmission parameters of the feedback information; performance monitoring results of the feedback information; and model switching request information, used to request switching of the agreed model.

66. The apparatus according to claim 65, characterized in that, The data parameters corresponding to the feedback information include one or more of the following: data volume, number of coding blocks, data transmission scheduling method, coding rate, modulation coding method, and resource mapping method. The transmission parameters of the feedback information include one or more of the following: channel type, channel format, number of bits, HARQ-ACK codebook type, number of transmission resources, whether to use repeated transmission, and whether to use multiplexed transmission. The performance monitoring results of the feedback information are associated with one or more of the following: retransmission information includes data that has been correctly decoded and data that failed to be decoded and was not retransmitted.

67. The apparatus according to any one of claims 63 to 66, characterized in that, The multiple models are indicated by a network device; or the multiple models are reported by a terminal device; or, a portion of the multiple models are indicated by the network device and another portion are reported by the terminal device.

68. The apparatus according to any one of claims 56 to 67, characterized in that, The first feedback response information in the A-bit feedback response information includes one or more of the following: feedback response information corresponding to one or a group of resources, wherein the resources include at least one time-domain unit and / or at least one frequency-domain unit; feedback response information corresponding to one or a group of channels; feedback response information corresponding to one or a group of HARQ processes; feedback response information corresponding to one or a group of transport blocks; and feedback response information corresponding to one or a group of coding blocks.

69. The apparatus according to claim 68, characterized in that, In the first case, the first feedback response information is a first agreed-upon information; or, in the second case, the first feedback response information is a second agreed-upon information; or, in the third case, the first feedback response information is a third agreed-upon information. The first type of situation includes one or more of the following: the information received in the one or a group of resources is correctly decoded, the channel received in the one or a group of resources is correctly decoded, the one or a group of channels received is correctly decoded, the one or a group of HARQ processes received is correctly decoded, the one or a group of transport blocks received is correctly decoded, and the one or a group of coded blocks received is correctly decoded. The second category includes one or more of the following: information received in one or a group of resources is not correctly decoded, a channel received in one or a group of resources is not correctly decoded, the received one or a group of channels is not correctly decoded, the received one or a group of HARQ processes is not correctly decoded, the received one or a group of transport blocks is not correctly decoded, and the received one or a group of coded blocks is not correctly decoded. The third category includes one or more of the following: no information was received in one or a group of resources, no channel was received in one or a group of resources, no channel was received, no HARQ process was received, no transport block was received, and no coding block was received.

70. The apparatus according to any one of claims 56 to 69, characterized in that, The A-bit feedback response information is obtained by concatenating the corresponding resources, channels, transport blocks, coding blocks, coding block groups, or HARQ processes in a first order; wherein, the first order includes one or more of the following orders: time-domain ascending order, time-domain descending order, frequency-domain ascending order, frequency-domain descending order, spatial-domain ascending order, spatial-domain descending order, number ascending order, and number descending order.

71. The apparatus according to any one of claims 56 to 70, characterized in that, The A-bit feedback response information is obtained based on the C-bit information; or, each bit of the A-bit feedback response information corresponds to one of A groups, which are obtained by dividing C resources, C channels, C HARQ processes, C transport blocks, or C coding blocks; where C is an integer greater than A.

72. The apparatus according to any one of claims 56 to 71, characterized in that, The value of A is determined based on the network device configuration, or according to the communication protocol, or according to the information reported by the terminal device.

73. The apparatus according to any one of claims 56 to 72, characterized in that, The device further includes a processing module, configured to: determine at least one corresponding resource, channel, or HARQ process based on the value of A; or, determine corresponding A bit feedback information based on at least one resource, channel, or HARQ process; or, determine the corresponding value of A based on at least one resource, channel, or HARQ process.

74. The apparatus according to any one of claims 56 to 73, characterized in that, The following one or more pieces of information are indicated by the network device, reported by the terminal device, or agreed upon by the communication protocol: one or a group of resources; one or a group of channels; one or a group of HARQ processes; the generation method of the A-bit feedback response information; the codebook type of the A-bit feedback response information; and the compression method of the A-bit feedback response information. The merging method of the A-bit feedback response information; the number of bits of the feedback response information corresponding to one or a group of resources; the number of bits of the feedback response information corresponding to one or a group of channels; the number of bits of the feedback response information corresponding to one or a group of HARQ processes; the association relationship between the A-bit feedback response information and the at least one or a group of resources; the association relationship between the A-bit feedback response information and the at least one or a group of channels; the association relationship between the A-bit feedback response information and the at least one or a group of HARQ processes.

75. A model-based feedback device, characterized in that, The communication device includes: a processor; a transceiver connected to the processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to load and execute the executable instructions to implement the model-based feedback method as described in any one of claims 1 to 18, or the model-based feedback method as described in any one of claims 19 to 37.

76. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one program, which is loaded and executed by a processor to implement the model-based feedback method as described in any one of claims 1 to 18, or the model-based feedback method as described in any one of claims 19 to 37.

77. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor retrieving the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to implement the model-based feedback method as described in any one of claims 1 to 18, or the model-based feedback method as described in any one of claims 19 to 37.

78. A computer program, characterized in that, The computer program includes computer instructions stored in a computer-readable storage medium, the processor retrieves the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to implement the model-based feedback method as described in any one of claims 1 to 18, or the model-based feedback method as described in any one of claims 19 to 37.

79. A chip, characterized in that, The chip includes a programmable logic circuit and / or at least a program, the chip being used to implement the model-based feedback method as described in any one of claims 1 to 18, or the model-based feedback method as described in any one of claims 19 to 37, based on the programmable logic circuit and / or the at least a program.

Images