Transmission method and apparatus, and terminal and network-side device

Abstract

The present application belongs to the technical field of communications. Disclosed are a transmission method and apparatus, and a terminal and a network-side device. The transmission method in the embodiments of the present application comprises: a terminal receiving first information sent by a network-side device; the terminal determining a target artificial intelligence (AI) unit on the basis of the first information, wherein the target AI unit is associated with a target modulation mode of the network-side device for sending downlink data; and the terminal receiving the downlink data on the basis of the target AI unit.

Description

Transmission method, apparatus, terminal and network side device

[0001] Cross-reference to Related Applications

[0002] This application claims priority to Chinese Patent Application No. 202410724764.9, filed on June 5, 2024 in China, the contents of which are incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and specifically relates to a transmission method, apparatus, terminal and network side device. BACKGROUND

[0004] In related technologies, when performing downlink transmission, a network side device usually modulates to-be-sent information by using a Quadrature Amplitude Modulation (QAM) or Phase Shift Keying (PSK) modulation scheme, and a terminal receives downlink data by using a fixed receiving mode, which may have poor adaptability to the modulation scheme of the network side device, which will result in poor transmission performance. SUMMARY

[0005] Embodiments of the present application provide a transmission method, apparatus, terminal and network side device, which can solve the problem of poor transmission performance.

[0006] In a first aspect, a transmission method is provided, which is executed by a terminal, and the method comprises:

[0007] The terminal receives first information sent by a network side device;

[0008] The terminal determines a target Artificial Intelligence (AI) unit based on the first information, and the target AI unit is associated with a target modulation mode used by the network side device to send downlink data;

[0009] The terminal receives the downlink data based on the target AI unit.

[0010] In a second aspect, a transmission method is provided, which is executed by a network side device, and the method comprises:

[0011] The network side device sends first information to a terminal, and the first information is used to determine a target AI unit, and the target AI unit is associated with a target modulation mode used to send downlink data;

[0012] The network side device sends downlink data based on the target modulation mode.

[0013] In a third aspect, a transmission apparatus is provided, which comprises:

[0014] receiving a first information sent by a network side device;

[0015] determining a target AI unit based on the first information, the target AI unit being associated with a target modulation mode used by the network side device to send downlink data;

[0016] The receiving module is further configured to receive the downlink data based on the target AI unit.

[0017] In a fourth aspect, a transmission apparatus is provided, comprising:

[0018] sending a first information to a terminal, the first information being used to determine a target AI unit, the target AI unit being associated with a target modulation mode used to send downlink data;

[0019] The sending module is further configured to send downlink data based on the target modulation mode.

[0020] In a fifth aspect, a transmission apparatus is provided, the apparatus being configured to perform the steps of the method of the first aspect, or to implement the steps of the method of the second aspect.

[0021] In a sixth aspect, a terminal is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of the first aspect.

[0022] In a seventh aspect, a terminal is provided, comprising a processor and a communication interface, wherein:

[0023] The communication interface is configured to receive a first information sent by a network side device;

[0024] The processor is configured to determine a target AI unit based on the first information, the target AI unit being associated with a target modulation mode used by the network side device to send downlink data;

[0025] The communication interface is further configured to receive the downlink data based on the target AI unit.

[0026] In an eighth aspect, a network side device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method of the second aspect.

[0027] In a ninth aspect, a network side device is provided, comprising a processor and a communication interface, wherein:

[0028] The communication interface is configured to send first information to the terminal, where the first information is used to determine a target AI unit associated with a target modulation mode used by the network side device to send downlink data.

[0029] The communication interface is further configured to send the downlink data based on the target modulation mode.

[0030] In a tenth aspect, a readable storage medium is provided, where the readable storage medium stores a program or instructions, and the program or instructions are executed by a processor to implement steps of the method in the first aspect or implement steps of the method in the second aspect.

[0031] In an eleventh aspect, a wireless communication system is provided, where the wireless communication system includes a terminal and a network side device, the terminal is configured to implement steps of the method in the first aspect, and the network side device is configured to implement steps of the method in the second aspect.

[0032] In a twelfth aspect, a chip is provided, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method in the first aspect or implement the method in the second aspect.

[0033] In a thirteenth aspect, a computer program / program product is provided, where the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the method in the first aspect or implement the method in the second aspect.

[0034] In the embodiments of the present application, a terminal receives first information sent by a network side device, determines a target artificial intelligence (AI) unit based on the first information, where the target AI unit is associated with a target modulation mode used by the network side device to send downlink data, and receives the downlink data based on the target AI unit. In this way, the terminal determines an AI unit used to receive the downlink data through the first information sent by the network side device, so as to adapt the AI unit used by the terminal to receive the downlink data to the modulation mode used by the network side device to send the downlink data, receive the downlink data through the AI unit associated with the target modulation mode, improve data throughput, reduce block error rate, and further improve transmission performance. BRIEF DESCRIPTION OF DRAWINGS

[0035] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0036] FIG. 2 is a schematic diagram of a neural network in the related art;

[0037] FIG. 3 is a schematic diagram of a neuron in the related art;

[0038] FIG. 4 is a flow chart of a transmission method according to an embodiment of the present application;

[0039] FIG. 5 is a flow chart of downlink data processing according to an embodiment of the present application;

[0040] FIG. 6 is a flow chart of a transmission method according to another embodiment of the present application;

[0041] FIG. 7 is a flow chart of a transmission method according to another embodiment of the present application;

[0042] FIG. 8 is a flow chart of a transmission method according to another embodiment of the present application;

[0043] FIG. 9 is a structural diagram of a transmission apparatus according to an embodiment of the present application;

[0044] FIG. 10 is a structural diagram of a transmission apparatus according to another embodiment of the present application;

[0045] FIG. 11 is a structural diagram of a communication device according to an embodiment of the present application;

[0046] FIG. 12 is a structural diagram of a terminal according to an embodiment of the present application;

[0047] FIG. 13 is a structural diagram of a network-side device according to an embodiment of the present application;

[0048] FIG. 14 is a structural diagram of a network-side device according to another embodiment of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be described clearly below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those of ordinary skill in the art belong to the scope of the present application.

[0050] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0051] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0052] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0053] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0054] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0055] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make a specific limitation hereon. It can be understood that the above function modules can be network elements in a hardware device, can be software function modules running on a special hardware, or can be virtualized function modules instantiated on a platform (for example, a cloud platform).

[0056] For the convenience of understanding, some contents related to the embodiments of the present application are explained as follows:

[0057] 1, Artificial Intelligence (AI)

[0058] Artificial intelligence (AI) has been widely applied in various fields. It is an important task for future wireless communication networks to integrate artificial intelligence into wireless communication networks and significantly improve technical indicators such as throughput, latency, and user capacity. There are various implementation ways for AI modules, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The embodiments of the present application take neural networks as an example for illustration, but the specific type of AI module is not limited.

[0059] A schematic diagram of a neural network is shown in FIG. 2:

[0060] The neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG. 3. The inputs are a1, a2, … aK, the weight (multiplicative coefficient) is w, the bias (additive coefficient) is b, and the activation function is σ(.). Common activation functions include Sigmoid, tanh, linear rectification function, or rectified linear unit (ReLU), etc.

[0061] The parameters of the neural network are optimized by a gradient optimization algorithm. The gradient optimization algorithm is a class of algorithms for minimizing or maximizing an objective function (or described as a loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) is constructed. After the model is obtained, the predicted output f(x) can be obtained according to the input x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated, which is the loss function. Find the appropriate W, b to minimize the value of the above loss function, and the smaller the loss value, the closer the model is to the true situation.

[0062] The common optimization algorithm at present is basically based on error back propagation (BP) algorithm. The basic idea of BP algorithm is that the learning process is composed of two processes of forward propagation of signals and backward propagation of errors. In the forward propagation, the input sample is transmitted from the input layer to the output layer through the processing of each hidden layer. If the actual output of the output layer does not match the expected output, the backward propagation of errors is entered. The error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and allocate the error to all units of each layer, so as to obtain the error signal of each unit of each layer, which is used as the basis for correcting the weight of each unit. The weight adjustment process of each layer of the signal forward propagation and the error backward propagation is repeated. The process of continuously adjusting the weight is the learning and training process of the network. This process is carried out until the error of the network output is reduced to an acceptable level, or until the preset learning times are reached.

[0063] Generally, according to different types of solutions, the selected AI algorithm and the adopted AI model also have differences. In the related art, the main method for improving the performance of the 5th Generation Mobile Communication Technology (5G) network by means of AI is to enhance or replace the existing algorithm or processing module by means of the neural network-based algorithm and AI model. In a specific scenario, the neural network-based algorithm and AI model can achieve better performance than the deterministic algorithm. Commonly used neural networks include deep neural networks, convolutional neural networks and recurrent neural networks. With the existing AI tools, the construction, training and verification of the neural network can be realized.

[0064] In the related art, AI can obtain better performance than traditional methods in complex communication tasks such as wireless environment modeling, signal detection, channel estimation, beamforming, positioning, mobility management, wireless resource allocation, traffic prediction, and network state tracking and intelligent scheduling. In the related art, the 3rd Generation Partnership Project (3GPP) has carried out wireless AI standardization research on multiple projects such as AI / ML for OAM (Operation Administration and Maintenance), AI / ML for NG-RAN (Next Generation Radio Access Network), Enablers for Network Automation for 5G-Phase 3, 5G Systems Support for AI / ML-based Services, and AI / ML for Air Interface. The specific research directions are as follows:

[0065] AI / ML for OAM mainly studies management data analytics service (MDAS).

[0066] Enablers for Network Automation for 5G-Phase 3 and 5G Systems Support for AI / ML-based Services are projects that introduce AI into the core network. In the R18 stage, the main research is AI model sharing, supporting federated learning, enhancement of NWDAF, 5G system assisting AI / ML model to realize intelligent transmission and provide transmission guarantee.

[0067] AI / ML for NG-RAN studied three use cases and basic function frameworks such as network energy saving, load balancing and mobility optimization in the R17 stage. In the R18 stage, the main research is how to carry out data collection and signaling enhancement.

[0068] AI / ML for Air Interface is a project for air interface enhancement established in R18, which focuses on the general architecture of air interface AI such as cooperation level and life cycle management, and three use cases such as channel state information (CSI) enhancement, beam enhancement and positioning enhancement based on AI.

[0069] With the popularization of AI technology and resources, more high-value use cases will emerge, continuously improving the performance of mobile communication systems.

[0070] The transmission method, device and related equipment provided by the embodiments of the present application will be described in detail in combination with some embodiments and their application scenarios.

[0071] Referring to FIG. 4, FIG. 4 is a flowchart of a transmission method provided by an embodiment of the present application, as shown in FIG. 4, the transmission method includes the following steps:

[0072] Step 101, the terminal receives first information sent by the network side device.

[0073] The first information can be used to indicate one or more first AI units. The terminal can report the first AI unit to the network side device. The first information can indicate one or more first AI units in the first AI unit reported by the terminal. Alternatively, the network side device can directly indicate one or more first AI units to the terminal through the first information. Alternatively, the first information can be confirmation information used to indicate whether to agree with the request of third information sent by the terminal, and the third information is used to indicate the first AI unit used by the terminal to receive downlink data.

[0074] In addition, the terminal reporting the first AI unit to the network side device can include: the terminal sending second information to the network side device, the second information being used to indicate capability information of the terminal for downlink data reception, and the capability information including the first AI unit supported by the terminal; or the terminal sending third information to the network side device, the third information being used to indicate the first AI unit used by the terminal to receive downlink data; and the like.

[0075] Step 102, the terminal determines a target artificial intelligence (AI) unit based on the first information, and the target AI unit is associated with a target modulation mode used by the network side device to send downlink data.

[0076] The first information can be used to indicate one or more first AI units, and the first information indicates one or more first AI units in the first AI units reported by the terminal. In the case where the first information indicates one first AI unit, the terminal can take the first AI unit indicated by the first information as the target AI unit; in the case where the first information indicates multiple first AI units, the terminal can select a target AI unit from the first AI units indicated by the first information. The terminal can select a target AI unit from the first AI units indicated by the first information according to the applicable conditions of the first AI units; or, the terminal can randomly select an AI unit from the first AI units indicated by the first information as the target AI unit.

[0077] In an implementation, the terminal can select a target AI unit from the first AI units indicated by the first information according to the applicable conditions of the first AI units, and take the first AI unit satisfying the applicable conditions among the first AI units indicated by the first information as the target AI unit. Taking the applicable conditions of the first AI units as an example, the terminal information includes the remaining power, and the target AI unit can be selected according to the remaining power of the terminal. When the terminal has more remaining power, a first AI unit with high computational complexity can be taken as the target AI unit; when the terminal has less remaining power, a first AI unit with low computational complexity can be taken as the target AI unit, so as to avoid rapid consumption of power.

[0078] The target AI unit is associated with the target modulation mode, which can also be described as the target AI unit corresponding to the target modulation mode, or the target AI unit matching the target modulation mode, or the target AI unit adapting to the target modulation mode; the target AI unit and the target modulation mode satisfy a binding relationship.

[0079] The target AI unit is associated with the target modulation mode, which can mean that the target AI unit and the target modulation mode have a binding relationship or an association relationship, for example, the network side device stores a binding relationship or an association relationship between the target AI unit and the target modulation mode; or, when training the target AI unit, the modulation mode used for modulating the training sample is the target modulation mode.

[0080] It should be noted that the network side device can store the association relationship or the binding relationship between the first AI unit and the modulation mode, and one first AI unit is used in a binding manner with one or more specific modulation modes, or one modulation mode is used in a binding manner with one or more specific first AI units.

[0081] The modulation mode can also be described as a modulation scheme or a modulation strategy. For example, the target modulation mode can also be described as a target modulation scheme or a target modulation strategy. The network side device can modulate the to-be-sent information, such as the codeword information, by using the target modulation mode.

[0082] The target AI unit can be one or more of the first AI units reported by the terminal.

[0083] In addition, the function of the first AI unit can be to convert the symbol sequence received by the terminal into a bit sequence. The input of the first AI unit at least contains the received modulated data signal, or the input of the first AI unit can also contain the received demodulation reference signal (DMRS) signal, the DMRS original signal sent by the terminal, or the estimation of the channel. The terminal can directly use the received modulated data signal, the received DMRS signal, the DMRS original signal sent by the terminal, or the estimation of the channel (all of which are complex signals) as the input of the first AI unit, that is, use the complex signal as the input of the first AI unit; or, the real part and the imaginary part of the received modulated data signal, the received DMRS signal, the DMRS original signal sent by the terminal, or the estimation of the channel are taken out and arranged into a specific dimension (such as a vector, a matrix, or a tensor) as the input of the first AI unit. The output of the first AI unit is a bit sequence corresponding to the received modulated data signal.

[0084] In addition, the network side device can select a target modulation mode for sending downlink data based on the first AI unit reported by the terminal. The target modulation mode is associated with at least one of the first AI units reported by the terminal. Further, the network side device can also select a target modulation mode according to the to-be-sent downlink data. The network side device can select an applicable target modulation mode according to the data characteristics of the downlink data. For example, for downlink data with different complexities, the selected target modulation mode can be different. The network side device can comprehensively consider the first AI unit reported by the terminal and the to-be-sent downlink data to select a target modulation mode, so that the downlink data modulated by the target modulation mode can be demodulated by the terminal and can achieve a better transmission effect.

[0085] It should be noted that the network side device can select a target modulation mode from a plurality of modulation modes for data transmission, and the selected modulation mode needs to match the first AI unit supported by the terminal. Each of the plurality of modulation modes can be used to map a bit sequence into a symbol sequence. Each of the plurality of modulation modes (such as the target modulation mode) can be a rule of modulating M bits into N symbols. Wherein, the modulation order of the modulation mode can be described by a fraction M / N or an integer group [M, N]. When N = 1, it degenerates into the modulation order used in the related art. The specific mapping rule of the modulation mode can be implemented by a function, a table or a third AI unit. The specific mapping rule can be predefined by a protocol, or can be sent to the terminal side by the network side when the mapping rule is actually called, and the standard format of the mapping rule at this time is predefined by the protocol.

[0086] Examples of the specific mapping rule of the modulation mode (such as the target modulation mode) described by the function are as follows:

[0087] The function is Y = f(X), X is the bit sequence before modulation, the length is M, and Y is the symbol sequence (generally a complex sequence) after modulation, the length is N. Or the acquisition process of the real part and the imaginary part of Y is described by Re(Y) = f1(X) and Im(Y) = f2(X) respectively.

[0088] Examples of the specific mapping rule of the modulation mode (such as the target modulation mode) described by the table are as follows:

[0089] Taking the modulation of [M = 5, N = 2] as an example, the specific mapping rule of the modulation mode described by the table can be as follows:

[0090] Wherein, y i,j is a real number or a complex number.

[0091] Examples of the specific mapping rule of the modulation mode (such as the target modulation mode) described by the third AI unit are as follows:

[0092] The input of the third AI unit is the bit sequence before modulation or the sequence obtained after preprocessing thereof, and the output of the third AI unit can be directly used as the symbol sequence after modulation or used as the symbol sequence after modulation after processing (such as matching and mapping of the real part and the imaginary part).

[0093] Step 103, the terminal receives the downlink data based on the target AI unit.

[0094] The terminal can use the target AI unit to demodulate the received downlink data; or the terminal can use the target AI unit to jointly process the received downlink data for equalization and demodulation; or the terminal can use the target AI unit to jointly process the received downlink data for channel estimation, equalization and demodulation; and the like.

[0095] In an embodiment, the target AI unit is used for demodulation processing, the terminal performs OFDM demodulation processing, channel estimation processing and equalization processing on the received downlink data to obtain information after equalization processing; and the terminal uses the target AI unit to perform demodulation processing on the information after equalization processing to obtain demodulated information.

[0096] In an embodiment, the target AI unit is used for joint processing of equalization and demodulation, the terminal performs OFDM demodulation processing and channel estimation processing on the received downlink data to obtain information after channel estimation processing; and the terminal uses the target AI unit to process the information after channel estimation processing to obtain demodulated information.

[0097] In an embodiment, the target AI unit is used for joint processing of channel estimation, equalization and demodulation, the terminal performs OFDM demodulation processing on the received downlink data to obtain information after OFDM demodulation processing; and the terminal uses the target AI unit to process the information after OFDM demodulation processing to obtain demodulated information.

[0098] In addition, the network side device can send downlink data based on the target modulation mode. The network side device can modulate the to-be-sent information using the target modulation mode, and send the downlink data based on the modulated information. For example, the network side device can perform resource mapping processing on the modulated information to obtain information after resource mapping processing; perform OFDM modulation processing on the information after resource mapping processing to obtain downlink data; and send the downlink data. Alternatively, the network side device can perform resource mapping processing on the modulated information to obtain information after resource mapping processing; perform DMRS insertion processing on the information after resource mapping processing to obtain information after DMRS insertion processing; perform OFDM modulation processing on the information after DMRS insertion processing to obtain downlink data; and send the downlink data.

[0099] In an embodiment, in the case that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the network side device can send a target request to a target device, the target request being used to request information related to a second modulation mode matching the first AI unit reported by the terminal.

[0100] The second modulation mode includes the target modulation mode.

[0101] In addition, the related information of the second modulation mode can include an identifier, a version, a specific mapping rule (e.g., a function, a table, or a third AI unit) of the second modulation mode, and an applicable condition of the second modulation mode.

[0102] In addition, the target device can be a core network device, a network management center device, a regional center device, or the like.

[0103] The AI unit in the embodiments of the present application can also be referred to as an AI model, an AI structure, or the like. Alternatively, the AI unit can refer to a processing unit that can implement a specific algorithm, a formula, a processing flow, a capability, or the like related to AI. Alternatively, the AI unit can be a processing method, an algorithm, a function, a module, or a unit for a specific data set. Alternatively, the AI unit can be a processing method, an algorithm, a function, a module, or a unit running on an AI-related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), or an application specific integrated circuit (ASIC). The embodiments of the present application do not make a specific limitation in this regard. Optionally, the specific data set includes an input or an output of the AI unit.

[0104] Optionally, the identifier of the AI unit can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, a functionality identifier (functionality ID), a physical identifier, a logical identifier, a global identifier, a local identifier, or an identifier of a specific data set associated with the AI unit. Alternatively, the identifier of the AI unit can be an identifier of a specific scene, an environment, a channel feature, or a device related to AI. Alternatively, the identifier of the AI unit can be an identifier of a function, a feature, a capability, or a module related to AI. The embodiments of the present application do not make a specific limitation in this regard.

[0105] It should be noted that Quadrature Amplitude Modulation (QAM) and Phase Shift Keying (PSK) modulation are the most commonly used modulation schemes in existing communication systems. However, theoretically, when the modulation order is greater than 4, these two are not the optimal modulation methods. Moreover, the actual signal detection performance is closely related to the specific receiver. In this regard, the embodiments of the present application perform end-to-end design through AI, jointly optimize the modulation scheme of the sending end and the receiver algorithm of the receiving end, and thus obtain better transmission performance. In the embodiments of the present application, the transceiver first agrees on the consistency of the transmission scheme, and then performs actual data transmission, which can enable the matching use of the modulation scheme and the receiver scheme optimized by the end-to-end design. The embodiments of the present application consider the downlink of the network side device deploying a new modulation scheme and the terminal deploying a new AI receiving scheme, and propose an end-to-end downlink transmission method, which can realize the reporting of the terminal about the AI receiver capability and the supported modulation scheme; the process of determining the modulation scheme and the AI receiver scheme suitable for sending data by the terminal and the network side device; and the processing scheme when the modulation of the network side device and the AI receiver of the terminal side do not match.

[0106] The embodiments of the present application are schemes for AI end-to-end transmission, and through the embodiments of the present application, the process of how to instruct the terminal to select an AI receiver scheme that matches the modulation scheme of the network side device is realized. The embodiments of the present application mainly realize that the network side device and the terminal agree on a modulation scheme (for example, AI training of multiple modulation schemes, including M-to-1 constellation shaping and M-to-N mapping rules) and a receiving scheme (such as AI receiver) in downlink transmission, and perform efficient data transmission. The constellation and receiver obtained through AI training can achieve higher throughput and lower block error rate (BLER) compared to traditional QAM modulation or PSK modulation, and can be optimized for different scenarios to obtain overfitting gain and further improve transmission performance.

[0107] In the embodiments of the present application, a terminal receives first information sent by a network side device; the terminal determines a target artificial intelligence (AI) unit based on the first information, the target AI unit being associated with a target modulation method used by the network side device to send downlink data; and the terminal receives the downlink data based on the target AI unit. In this way, receiving downlink data through an AI unit associated with a target modulation method can improve data throughput and reduce block error rate, thereby improving transmission performance; and the terminal determines an AI unit used to receive downlink data through first information sent by the network side device, thereby enabling the adaptation of the AI unit used by the terminal to receive downlink data to the modulation method used by the network side device to send downlink data, and further improving transmission performance.

[0108] Optionally, the target modulation mode is used to map a bit sequence into a symbol sequence.

[0109] The modulation mode in the related art is a rule of mapping M bits into 1 symbol, and the target modulation mode in the embodiment of the application is a rule of mapping a bit sequence into a symbol sequence, such as M bits modulating N symbols, M is a positive integer, and N is a positive integer. The target modulation mode can be described by a fraction M / N or an integer group [M, N], which can make the application of modulation more extensive.

[0110] In this embodiment, the target modulation mode is used to map a bit sequence into a symbol sequence, and the flexibility of modulation by using the modulation mode of mapping a bit sequence into a symbol sequence is higher than that of only supporting mapping a bit sequence into one symbol in the related art.

[0111] Optionally, before the terminal receives the first information sent by the network side device, the method further comprises:

[0112] The terminal sends second information to the network side device, and the second information is used to indicate capability information of the terminal for downlink data reception.

[0113] The capability information can represent a receiving scheme or a modulation scheme (or described as a modulation mode) supported by the terminal, such as which modulation schemes are used by the network side device. The capability information can include: an identifier of a first AI unit supported by the terminal; or, a suitable condition of the first AI unit supported by the terminal; or, a modulation mode used by the network side device; and the like, which are not limited in the embodiment.

[0114] In addition, the terminal sends second information to the network side device, and the second information is used to indicate capability information of the terminal for downlink data reception; the terminal receives first information sent by the network side device, and the first information can be used to indicate one or more first AI units represented by the capability information; and the terminal selects a target AI unit from the one or more first AI units indicated by the first information.

[0115] In this embodiment, the terminal sends second information to the network side device, and the second information is used to indicate capability information of the terminal for downlink data reception, so that the network side device can know the capability of the terminal for downlink data reception, and then the network side device can select a modulation mode matching the capability of the terminal to send downlink data according to the capability of the terminal.

[0116] Optionally, the capability information includes at least one of the following:

[0117] The first AI unit supported by the terminal;

[0118] The applicable condition of the first AI unit supported by the terminal;

[0119] The first AI unit is used to convert the symbol sequence received by the terminal into a bit sequence.

[0120] The capability information can include at least one first AI unit supported by the terminal. For example, the capability information can include all the first AI units supported by the terminal. The first AI units supported by the terminal in the capability information can be represented in the form of a set, or in the form of a list, or in other forms, which are not limited in the embodiment.

[0121] The second information can include scene information, configuration information, channel quality condition, terminal information or other information that can be used to describe the applicable condition of the first AI unit, which is not limited in the embodiment.

[0122] In an embodiment, the capability information includes at least one of the following:

[0123] The set of the first AI units supported by the terminal;

[0124] The applicable condition of the first AI unit supported by the terminal.

[0125] In this embodiment, the capability information can include the identity of the first AI unit supported by the terminal, so that the network side device can know the first AI unit supported by the terminal, and then the network side device can select a modulation mode matched with the first AI unit supported by the terminal to send downlink data according to the first AI unit supported by the terminal.

[0126] In this embodiment, the capability information can include the applicable condition of the first AI unit supported by the terminal, so that the network side device can know the applicable condition of the first AI unit supported by the terminal, and then the network side device can determine the first AI unit applicable to the terminal according to the applicable condition of the first AI unit supported by the terminal, and select a modulation mode matched with the first AI unit applicable to the terminal to send downlink data.

[0127] Optionally, in the case where the second information is used to indicate the applicable condition, the second information includes at least one of the following:

[0128] Scene information; configuration information; channel quality condition; terminal information.

[0129] The scene information can include channel scene or a scene where the terminal is located (such as a line of sight (LOS) or a non-line of sight (NLOS) channel, an indoor or outdoor scene, an urban or suburban or plain or mountainous scene), and position or area information (such as a cell identifier (ID), a sector ID, a city or region ID, and a zone ID).

[0130] The configuration information can include information such as port configuration of a receiving end or a sending end, frequency domain configuration (such as bandwidth, bandwidth part (BWP) size and frequency domain position, sub-band number and frequency domain position, resource block (RB) number and frequency domain position, and the like), time domain configuration (such as symbol number or slot number, and the like), and the like.

[0131] The channel quality condition can include a condition described by an index such as a channel quality indicator (CQI), a signal-to-noise and interference ratio (SINR), a signal-to-noise ratio (SNR), or a reference signal received power (RSRP).

[0132] The terminal information can be terminal self-information, and the terminal information can include a moving speed, an available power or a remaining power, an available storage space, or an available computing unit.

[0133] Optionally, the first information includes an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit includes the target AI unit.

[0134] The at least one first AI unit is associated with the target modulation mode, and it can be understood that each first AI unit in the at least one first AI unit is associated with the target modulation mode.

[0135] In this embodiment, the first information includes an identifier of at least one first AI unit supported by the terminal. In this way, the network-side device feeds back, to the terminal, the identifier of at least one first AI unit associated with the target modulation mode, so that the terminal can select a target AI unit from the at least one first AI unit supported by the terminal for receiving the downlink data, thereby achieving adaptation of the AI unit of the terminal for receiving the downlink data to the modulation mode of the network-side device for sending the downlink data, and improving transmission performance.

[0136] Optionally, before the terminal receives the first information sent by the network-side device, the method further includes:

[0137] The terminal sends, to the network-side device, third information, where the third information is used to indicate a first AI unit requested by the terminal to be used for receiving the downlink data, and the first AI unit is used to convert the symbol sequence received by the terminal into a bit sequence.

[0138] The third information can include an identifier of one or more first AI units, and the first AI unit indicated by the third information can be the first AI unit requested by the terminal to be used for receiving the downlink data.

[0139] In addition, the network-side device can determine the target modulation mode based on the third information. The network-side device can randomly select the target modulation mode from the modulation modes associated with the first AI unit indicated by the third information, or the network-side device can select the target modulation mode from the modulation modes associated with the first AI unit indicated by the third information by referring to other information. For example, the network-side device can also select the target modulation mode according to the downlink data to be sent. The embodiments of the present application do not limit the specific implementation of the network-side device for selecting the target modulation mode.

[0140] It should be noted that in some scenarios where the terminal is limited, such as scenarios where the power, storage or computing power is limited, the terminal cannot or does not want to perform the scheme indicated by the network-side device. In this case, the terminal can request or suggest a scheme that the terminal wants. The terminal sends, to the network-side device, third information, where the third information is used to indicate a first AI unit requested by the terminal to be used for receiving the downlink data, thereby realizing a mode of initiating selection of a target AI unit from the terminal side.

[0141] In the embodiment, the terminal sends third information to the network side device, the third information is used to indicate a first AI unit requested by the terminal to receive downlink data, and the first information is used to respond to the request of the third information. In this way, the network side device can select a target modulation mode according to the first AI unit requested by the terminal to receive downlink data, and feed back the first information to the terminal, so that the terminal can select a target AI unit according to the first information to receive downlink data, thereby realizing the adaptation of the AI unit of the terminal to receive downlink data and the modulation mode of the network side device to send downlink data, and improving the transmission performance.

[0142] Optionally, the first information includes at least one of the following:

[0143] The confirmation information is used to indicate whether to agree with the request of the third information.

[0144] The third information indicates an identity of at least one first AI unit in the first AI units, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit includes the target AI unit.

[0145] The confirmation information can be used to indicate that the request of the third information is agreed, or the confirmation information can be used to indicate that the request of the third information is not agreed. For example, the confirmation information is 1, indicating that the request of the terminal is agreed; or the confirmation information is 0, indicating that the request of the terminal is not agreed.

[0146] In an embodiment, the first information can include confirmation information, and the terminal determines the target AI unit based on the first information. For example, when the confirmation information is used to indicate that the request of the third information is agreed, the terminal can select the target AI unit from the first AI units indicated by the third information. The terminal can select the target AI unit from the first AI units indicated by the third information according to the applicable conditions of the first AI units; or the terminal can randomly select an AI unit from the first AI units indicated by the third information as the target AI unit. When the confirmation information is used to indicate that the request of the third information is not agreed, the terminal can not select the target AI unit; or when the confirmation information is used to indicate that the request of the third information is not agreed, the terminal can receive second AI unit information sent by the network side device, the second AI unit is associated with the modulation mode supported by the network side device, and the terminal can take the second AI unit sent by the network side device as the target AI unit.

[0147] In an implementation, the first information can include an identity of at least one of the first AI units indicated by the third information. In a case where the first information includes an identity of one first AI unit, the terminal can take the first AI unit indicated by the first information as the target AI unit; in a case where the first information includes identities of multiple first AI units, the terminal can select the target AI unit from the first AI units indicated by the first information.

[0148] In this implementation, the first information can include confirmation information, and the terminal can determine whether the network-side device agrees with the request of the third information according to the confirmation information. When the network-side device agrees with the request of the third information, the terminal can select the target AI unit from the first AI units requested by the terminal for reception of the downlink data; or, the first information can include an identity of at least one of the first AI units indicated by the third information, so that the terminal can select the target AI unit according to the identity of the first AI unit fed back by the network-side device for reception of the downlink data, thereby achieving adaptation of the AI unit used by the terminal for reception of the downlink data to the modulation mode used by the network-side device for transmission of the downlink data, and improving transmission performance.

[0149] Optionally, the first information is used to indicate whether the modulation mode supported by the network-side device matches the first AI unit reported by the terminal;

[0150] In a case where the first information indicates that the modulation mode supported by the network-side device matches the first AI unit reported by the terminal, the first information further includes an identity of at least one of the first AI units reported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit includes the target AI unit; or

[0151] In a case where the first information indicates that the modulation mode supported by the network-side device does not match the first AI unit reported by the terminal, the first information further includes related information of a second AI unit, the second AI unit is associated with the modulation mode supported by the network-side device; or, in a case where the first information indicates that the modulation mode supported by the network-side device does not match the first AI unit reported by the terminal, the first information further includes an identity of a first AI unit that does not match the modulation mode supported by the network-side device.

[0152] The related information of the second AI unit can include an identifier or a version of the second AI unit, a description or an execution file of the second AI unit, and a second AI unit applicable condition, and the like. The description or the execution file of the second AI unit includes information such as a structure, a parameter, or an applicable AI framework of the second AI unit, and the terminal can directly run the description or the execution file of the second AI unit to use the second AI unit for inference, or the terminal can need to compile or recompile the description or the execution file of the second AI unit to use the second AI unit for inference, and the embodiment is not limited to the specific implementation of using the second AI unit.

[0153] In addition, the first AI unit reported by the terminal can be the first AI unit reported through the second information or the third information. For example, the terminal sends second information to the network side device, the second information is used to indicate the capability information of the terminal for downlink data reception, and the capability information includes the first AI unit supported by the terminal; or the terminal sends third information to the network side device, the third information is used to indicate the first AI unit requested by the terminal to be used for receiving downlink data; and the like.

[0154] In addition, the modulation mode supported by the network side device matches the first AI unit reported by the terminal, which means that the network side device can find the modulation mode associated with the first AI unit reported by the terminal in the modulation modes supported by the network side device. The modulation mode supported by the network side device does not match the first AI unit reported by the terminal, which means that the network side device cannot find the modulation mode associated with the first AI unit reported by the terminal in the modulation modes supported by the network side device.

[0155] For example, the network side device can store an association relationship table (or a binding relationship table) of the modulation mode and the first AI unit, and the modulation modes in the association relationship table are all the modulation modes supported by the network side device. The network side device can find whether there is a modulation mode matching the first AI unit reported by the terminal from the association relationship table.

[0156] In addition, the modulation mode supported by the network side device matches the first AI unit reported by the terminal, which means that the identifier of the modulation mode matches (or is associated with) the identifier of the first AI unit; or the identifier and the version number of the modulation mode match the identifier of the first AI unit; or the identifier of the modulation mode matches the identifier and the version number of the first AI unit; or the identifier and the version number of the modulation mode match the identifier and the version number of the first AI unit; and the like. Taking the network side device storing the association relationship table of the modulation mode and the first AI unit as an example, the modulation mode in the association relationship table can be represented by the identifier, or represented by the identifier and the version number; and the first AI unit can be represented by the identifier, or represented by the identifier and the version number.

[0157] In the embodiment, in a case where the first information indicates that the modulation mode supported by the network side device matches the first AI unit reported by the terminal, the first information further comprises an identifier of at least one of the first AI units reported by the terminal, so that the network side device can select a modulation mode matching the first AI unit reported by the terminal for sending the downlink data according to the first AI unit reported by the terminal, and feed back the identifier of at least one of the first AI units associated with the selected target modulation mode to the terminal, and the terminal can select a target AI unit for receiving the downlink data according to the identifier of the first AI unit fed back by the network side device, so as to realize the adaptation of the AI unit used by the terminal for receiving the downlink data and the modulation mode used by the network side device for sending the downlink data, and improve the transmission performance.

[0158] In the embodiment, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises the related information of the second AI unit, so that the terminal can obtain the related information of the second AI unit associated with the modulation mode supported by the network side device, and select a target AI unit for receiving the downlink data through the second AI unit, so as to realize the adaptation of the AI unit used by the terminal for receiving the downlink data and the modulation mode used by the network side device for sending the downlink data, and improve the transmission performance.

[0159] In the embodiment, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises an identifier of the first AI unit that does not match the modulation mode supported by the network side device, so that the terminal can obtain the first AI unit that does not match the modulation mode supported by the network side device, and then eliminate the first AI unit that does not match the modulation mode supported by the network side device when selecting a target AI unit.

[0160] Optionally, the target AI unit is used for any one of the following:

[0161] Demodulation processing;

[0162] Joint processing of equalization and demodulation;

[0163] Joint processing of channel estimation, equalization and demodulation.

[0164] In a case where the target AI unit is used for demodulation processing, the input of the target AI unit is associated with a complex signal after equalization of a received data signal (such as downlink data), and the output of the target AI unit is a bit sequence corresponding to the data signal.

[0165] In the case that the target AI unit is used for joint processing of channel estimation, equalization and demodulation (i.e., channel estimation + equalization + demodulation), the input of the target AI unit is associated with the received data signal (downlink data), the received DMRS signal and the DMRS original signal sent by the network side device, and the output of the target AI unit is the bit sequence corresponding to the data signal.

[0166] In the case that the target AI unit is used for joint processing of channel estimation, equalization and demodulation (i.e., channel estimation + equalization + demodulation), the input of the target AI unit is associated with the received data signal (downlink data), the received DMRS signal and the DMRS original signal sent by the network side device, and the output of the target AI unit is the bit sequence corresponding to the data signal.

[0167] In addition, the joint processing of channel estimation, equalization and demodulation can include joint processing of channel estimation, equalization and demodulation in pilotless transmission.

[0168] In the case that the target AI unit is used for joint processing of channel estimation, equalization and demodulation in pilotless transmission (i.e., channel estimation in pilotless transmission + equalization + demodulation), the input of the target AI unit is associated with the received data signal, and the output of the target AI unit is the bit sequence corresponding to the data signal. In this mode, the network side device only sends the data signal and does not send the DMRS.

[0169] In addition, the input of the target AI unit associated with the received data signal (or the estimated value of the channel, or the received DMRS signal, or the DMRS original signal sent by the network side device, or the complex signal after equalization of the received data signal) can mean that the received data signal (or the estimated value of the channel, or the received DMRS signal, or the DMRS original signal sent by the network side device, or the complex signal after equalization of the received data signal) is directly used as the input of the target AI unit; or, the signal after processing the received data signal (or the estimated value of the channel, or the received DMRS signal, or the DMRS original signal sent by the network side device, or the complex signal after equalization of the received data signal) can be used as the input of the target AI unit, for example, the real part and the imaginary part of the received data signal are taken out and arranged into a specific dimension (such as a vector, a matrix or a tensor) as the input of the target AI unit.

[0170] It should be noted that the generalization ability of the target AI unit is different when it implements different functions. The generalization performance of the AI unit for implementing demodulation processing, the AI unit for implementing joint processing of equalization and demodulation, and the AI unit for implementing joint processing of channel estimation, equalization, and demodulation gradually deteriorates in turn. Therefore, even if the network side device transmits data using the same modulation scheme, different terminals can use different target AI units to complete data reception and obtain bit sequences. For example, a terminal with a high activity scene change can use a target AI unit for implementing demodulation processing, and a terminal with a low activity scene change can use a target AI unit for implementing joint processing of channel estimation, equalization, and demodulation in the case of pilot-free transmission. Even if the network side device uses the same modulation scheme, different terminals can be configured and use different target AI units.

[0171] The embodiments of the present application consider the downlink of the network side deploying a new modulation scheme and the terminal side deploying a new receiving scheme, and clearly define the related terminal capability reporting, the determination process of the modulation scheme and the receiver scheme, and the alignment scheme when the transmitting end and the receiving end do not match. In an implementation manner, a downlink data processing flow block diagram corresponding to the transmission method in the embodiments of the present application is shown in FIG. 5, mainly involving modulation of the network side device and demodulation, equalization, and channel estimation functions of the terminal side, and the main purpose is to use a more flexible and efficient modulation scheme (the specific mapping rule can be described in multiple ways, such as a function, a table, and a third AI unit) and a receiver scheme (an AI-based receiver, i.e., receiving based on a first AI unit) matched therewith to complete data reception.

[0172] The transmission method is further described through several examples as follows:

[0173] In the following examples, the modulation scheme can also be described as a modulation method or a modulation strategy, that is, the modulation scheme can be replaced by the modulation method or the modulation strategy.

[0174] Example One:

[0175] In this example, the transmission method includes the following processes:

[0176] Step (1), the terminal reports second information (i.e., the terminal sends second information to the network side device), the second information describes the receiving scheme or modulation scheme supported by the terminal (such as which modulation schemes are used by the network side, and which modulation schemes can be received by the terminal), and the second information includes at least one of the following:

[0177] A. A first set of AI units supported by the terminal, each of which is configured to convert a received symbol sequence into a bit sequence. The input of the first AI unit includes at least a received modulated data signal, and can also include a received DMRS signal, a DMRS original signal sent by the terminal, or an estimated value of a channel. The terminal can directly use the received modulated data signal, the received DMRS signal, the DMRS original signal sent by the terminal, or the estimated value of the channel (all of which are complex signals) as the input of the first AI unit, that is, use the complex signals as the input of the first AI unit; or, extract the real and imaginary parts of the received modulated data signal, the received DMRS signal, the DMRS original signal sent by the terminal, or the estimated value of the channel, respectively, and arrange them into a specific dimension (such as a vector, a matrix, or a tensor) as the input of the first AI unit. The output of the first AI unit is a bit sequence corresponding to the received modulated data signal.

[0178] B. Applicable conditions of each of the first AI units in the first set of AI units, that is, which first AI unit is used under which condition. The applicable conditions include at least one of the following:

[0179] Scenario information, including at least one of a channel scenario or a scenario in which the terminal is located (such as an LOS or NLOS channel, an indoor or outdoor scenario, an urban or suburban or plain or mountainous scenario), and a location or area (such as a cell ID, a sector ID, a city or region ID, an area ID, etc.);

[0180] Configuration information, including at least one of a receiving end or a sending end port configuration, a frequency domain configuration (such as a bandwidth, a BWP size and a frequency domain position, a sub-band number and a frequency domain position, a number of RBs and a frequency domain position, etc.), and a time domain configuration (such as a symbol number, a slot number, etc.);

[0181] Channel quality conditions, such as conditions described by CQI, SINR, SNR, RSRP, etc.

[0182] Terminal self information, such as a moving speed, an available power or a remaining power, an available storage space, or an available computing unit, etc.

[0183] The network side device has multiple modulation schemes for data transmission, but the selected modulation scheme needs to match the first AI unit supported by the terminal. The modulation scheme is the rule of modulating M bits into N symbols. Among them, the modulation order can be described by the fraction M / N or the integer group [M, N]. When N = 1, it degenerates into the modulation order used in the existing standard. The specific mapping rule of the modulation scheme can be realized by a function, a table or a third AI unit. The specific mapping rule can be predefined by the protocol, or it can be sent to the terminal side by the network side when actually calling the mapping rule, and the standard format of the mapping rule at this time is predefined by the protocol.

[0184] Examples of the specific mapping rule of the modulation scheme described by the function are as follows:

[0185] The function is Y = f(X), X is the bit sequence before modulation, the length is M, and Y is the symbol sequence after modulation (usually a complex sequence), the length is N. Or the real part and the imaginary part of Y are described by Re(Y) = f1(X) and Im(Y) = f2(X) respectively.

[0186] Examples of the specific mapping rule of the modulation scheme described by the table are as follows:

[0187] Taking the modulation of [M = 5, N = 2] as an example, the specific mapping rule of the modulation scheme described by the table can be as follows:

[0188] Where y i,j is a real number or a complex number.

[0189] Examples of the specific mapping rule of the modulation scheme described by the third AI unit are as follows:

[0190] The input of the third AI unit is the bit sequence before modulation or the sequence obtained after preprocessing it, and the output of the third AI unit can be directly used as the symbol sequence after modulation or used as the symbol sequence after modulation after processing (such as matching and mapping of real part and imaginary part).

[0191] Step (2), the terminal determines the target AI unit for data reception.

[0192] In an implementation, the network side device determines to use the target modulation scheme for data transmission according to the second information, and sends the first information to the terminal, the content of the first information includes the identification of one or more first AI units. The one or more first AI units are associated or bound with the target modulation scheme;

[0193] The network side device uses the target modulation scheme to send data, and the terminal determines to use the target AI unit to complete data reception according to the first information.

[0194] In another implementation, the terminal sends third information to the network side device, where the third information describes which first AI unit the terminal requests to use for data reception. Therefore, the content of the third information includes the identification of one or more first AI units.

[0195] The network side device sends first information to the terminal side, where the first information is a reply to the third information. The first information includes at least one of the following:

[0196] 1) confirmation information, such as a confirmation information of 1 indicating agreement with the terminal's request, or a confirmation information of 0 indicating disagreement.

[0197] 2) the identification of a specified first AI unit, where the specified first AI unit is one of the multiple first AI units included in the third information, i.e., indicating the terminal to receive data using the specified first AI unit.

[0198] The terminal determines a target AI unit to complete data reception according to the first information. The target AI unit is the first AI unit specified in the first information.

[0199] It should be noted that the network side device can maintain an association or binding relationship between the first AI unit and the modulation scheme, where a first AI unit is bound to use a specific modulation scheme, or a modulation scheme is bound to use a specific first AI unit.

[0200] One modulation scheme can be associated with multiple first AI units, and different first AI units can implement different functions as follows:

[0201] Function 1: demodulation. The input of the first AI unit is associated with the complex signal after equalization of the received data signal, and the output of the first AI unit is the bit sequence corresponding to the data signal.

[0202] Function 2: joint processing of equalization and demodulation (i.e., equalization + demodulation). The input of the first AI unit is associated with the received data signal and the estimate of the channel, and the output of the first AI unit is the bit sequence corresponding to the data signal.

[0203] Function 3: joint processing of channel estimation, equalization, and demodulation (i.e., channel estimation + equalization + demodulation). The input of the first AI unit is associated with the received data signal, the received DMRS signal, and the DMRS original signal sent by the network side device, and the output of the first AI unit is the bit sequence corresponding to the data signal.

[0204] Function four: joint processing of channel estimation, equalization and demodulation when there is no pilot transmission (i.e., channel estimation + equalization + demodulation when there is no pilot transmission). In this mode, the network side device only transmits data signals and does not transmit DMRS. Therefore, the input of the first AI unit is associated with the received data signal, and the output of the first AI unit is a bit sequence corresponding to the data signal.

[0205] The generalization ability of the first AI unit is different when it implements different functions, and the generalization performance gradually deteriorates from function one to function four. Therefore, even if the network side device transmits data using the same modulation scheme, different terminals can use different first AI units to complete data reception and obtain bit sequences. For example, a terminal with a high activity scene change can use a first AI unit corresponding to function one, and a terminal with a low activity scene change can use a first AI unit corresponding to function four. Even if the network side device uses the same modulation scheme, different terminals can be configured and use different first AI units.

[0206] One AI unit can also be associated with multiple modulation schemes:

[0207] For example, a terminal can use the same first AI unit to receive data transmitted by a network side device using different modulation schemes.

[0208] When the modulation scheme supported by the network side device and the first AI unit supported (or reported) by the terminal side do not match, no alignment processing can be performed, and only the modulation scheme and receiving scheme that can be matched by both ends are selected. The mismatch here can refer to any of the following:

[0209] The identification of the modulation scheme and the identification of the first AI unit do not satisfy the binding relationship;

[0210] The {identification, version number} of the modulation scheme and the {identification, version number} of the first AI unit do not satisfy the binding relationship;

[0211] The identification of the modulation scheme and the {identification, version number} of the first AI unit do not satisfy the binding relationship;

[0212] The {identification, version number} of the modulation scheme and the identification of the first AI unit do not satisfy the binding relationship.

[0213] The network side device can send an error cause information to the terminal to inform the terminal that a mismatch has occurred. The error cause can include a set of first AI units, indicating that the network side device cannot support the AI units in the set.

[0214] When the modulation scheme supported by the network side device and the first AI unit supported (or reported) by the terminal side do not match, the following process can be used for alignment processing:

[0215] 1) Network side device does not have the modulation scheme required by the terminal, which can do one of the following processing: network side device sends a request to the core network, network management center or regional center, etc. Apply for the corresponding new modulation scheme, modulation scheme applicable conditions, modulation scheme specific mapping rules (such as functions, tables or third AI units).

[0216] 2) The terminal side does not have the first AI unit corresponding to the modulation scheme supported by the network side device, which can do the following processing: the network side device sends the fourth information to the terminal side, which includes the corresponding new first AI unit (including identification, version and first AI unit description or execution file), the applicable conditions of the first AI unit.

[0217] For example, after receiving the first information or the third information, the network side device finds that the network side device does not have any modulation scheme that can be associated with the first AI unit reported by the terminal. At this time, the alignment processing is carried out through the above process.

[0218] Example two:

[0219] In this example, the network side device initiates the selection of the first AI unit.

[0220] In this example, as shown in FIG. 6, the transmission method includes the following processes:

[0221] Step (1), the terminal reports the second information. Same as step (1) in example one.

[0222] Step (2), the network side device determines the modulation scheme and the first AI unit.

[0223] The network side device determines to use the target modulation scheme for data transmission according to the second information, and determines one or more first AI units, which are associated or bound with the target modulation scheme.

[0224] Step (3), the network side device sends the first information to the terminal.

[0225] The content of the first information includes the identification of one or more first AI units determined in step (2).

[0226] The terminal determines the target AI unit according to the first information.

[0227] Step (4), the network side device sends the first data to the terminal.

[0228] The network side device sends the first data using the determined target modulation scheme, and the terminal completes the reception of the first data according to the determined target AI unit.

[0229] Example three:

[0230] In this example, the terminal side initiates the selection of the first AI unit.

[0231] In this example, as shown in FIG. 7, the transmission method includes the following processes:

[0232] Step (1), the terminal reports the second information. Same as step (1) in example one.

[0233] Step (2), the terminal sends the third information to the network side device.

[0234] The third information describes which first AI unit the terminal requests to use for data reception. Therefore, the content of the third information includes the identification of one or more first AI units.

[0235] Step (3), the network side device determines the modulation scheme and the first AI unit according to the third information.

[0236] Step (4), the network side device sends the first information to the terminal.

[0237] The first information is a reply to the third information. The first information includes at least one of the following:

[0238] 1) confirmation information, such as confirmation information 1 indicating agreement with the terminal's request; or confirmation information 0 indicating disagreement.

[0239] 2) the identification of a specified first AI unit, which is one of the identifications of the multiple first AI units contained in the third information, that is, indicating the terminal to receive data using the specified first AI unit.

[0240] The terminal determines the target AI unit according to the first information. The target AI unit is the first AI unit specified by the first information.

[0241] Step (5), the network side device sends the first data to the terminal.

[0242] The network side device sends the first data using the target modulation scheme, and the terminal completes the reception of the first data according to the target AI unit.

[0243] The embodiments of the present application consider the downlink of the network side device deploying a new modulation scheme and the terminal deploying a new AI receiving scheme, and propose an end-to-end downlink transmission method. Through the modulation scheme (such as constellation) and AI receiver obtained by end-to-end AI training, on the one hand, higher throughput and lower BLER can be achieved compared to traditional QAM modulation or PSK modulation, and on the other hand, different scenarios can be optimized to obtain overfitting gain and further improve transmission performance.

[0244] Referring to FIG. 8, FIG. 8 is a flowchart of a transmission method provided by an embodiment of the present application. As shown in FIG. 8, the transmission method comprises the following steps.

[0245] Step 201, a network-side device sends first information to a terminal, the first information being used to determine a target AI unit, the target AI unit being associated with a target modulation mode used to send downlink data.

[0246] Step 202, the network-side device sends downlink data based on the target modulation mode.

[0247] Optionally, the target modulation mode is used to map a bit sequence into a symbol sequence.

[0248] Optionally, before the network-side device sends the first information to the terminal, the method further comprises:

[0249] The network-side device receives second information sent by the terminal, the second information being used to indicate capability information of the terminal for downlink data reception.

[0250] Optionally, the capability information comprises at least one of the following:

[0251] A first AI unit supported by the terminal;

[0252] An applicable condition of a first AI unit supported by the terminal;

[0253] The first AI unit is used to convert a symbol sequence received by the terminal into a bit sequence.

[0254] Optionally, in the case where the second information is used to indicate the applicable condition, the second information comprises at least one of the following:

[0255] Scene information; configuration information; channel quality condition; terminal information.

[0256] Optionally, the first information comprises an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

[0257] Optionally, before the network-side device sends the first information to the terminal, the method further comprises:

[0258] The network-side device receives third information sent by the terminal, the third information being used to indicate a first AI unit requested by the terminal to adopt to receive downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence.

[0259] The network-side device determines the target modulation mode based on the third information.

[0260] Optionally, the first information includes at least one of the following:

[0261] confirmation information, the confirmation information being used to indicate whether to agree with the request of the third information;

[0262] an identity of at least one first AI unit in the first AI units indicated by the third information, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit including the target AI unit.

[0263] Optionally, the first information is used to indicate whether the modulation modes supported by the network-side device match the first AI units reported by the terminal.

[0264] In a case where the first information indicates that the modulation modes supported by the network-side device match the first AI units reported by the terminal, the first information further includes an identity of at least one first AI unit in the first AI units reported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit including the target AI unit; or

[0265] In a case where the first information indicates that the modulation modes supported by the network-side device do not match the first AI units reported by the terminal, the first information further includes related information of a second AI unit, the second AI unit being associated with the modulation modes supported by the network-side device; or, in a case where the first information indicates that the modulation modes supported by the network-side device do not match the first AI units reported by the terminal, the first information further includes an identity of a first AI unit that does not match the modulation modes supported by the network-side device.

[0266] Optionally, before the network-side device sends the first information to the terminal, the method further includes:

[0267] In a case where the modulation modes supported by the network-side device do not match the first AI units reported by the terminal, the network-side device sends a target request to a target device, the target request being used to request related information of a second modulation mode that matches the first AI units reported by the terminal;

[0268] The second modulation mode includes the target modulation mode.

[0269] Optionally, the target AI unit is used for any one of the following:

[0270] demodulation processing;

[0271] Joint processing of equalization and demodulation;

[0272] Joint processing of channel estimation, equalization and demodulation.

[0273] It should be noted that the embodiment is as an implementation of a network side device corresponding to the embodiment shown in FIG. 4, and the specific implementation can refer to the related description of the embodiment shown in FIG. 4. To avoid repeated description, the embodiment will not be described again.

[0274] The transmission method provided in the embodiment of the application can be executed by the transmission device. In the embodiment of the application, the transmission device is taken as an example to illustrate the transmission device provided in the embodiment of the application.

[0275] The transmission device provided in the embodiment of the application can be a communication device or a component in the communication device, for example, a chip. The communication device can be a terminal, a network side device or a server, etc. For example, the terminal can include but is not limited to the types of the terminal 11 listed above, and the network side device can include but is not limited to the types of the network side device 12 listed above, which are not limited in the embodiment of the application.

[0276] The transmission device includes a receiving module, a sending module and a processing module. The receiving module, the sending module and the processing module can be implemented by software or hardware. When implemented by hardware, the processing module can be implemented by a processor, for example, a general processor, a special processor, etc., such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA) or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, etc. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, etc.

[0277] Specifically, referring to FIG. 9, when the transmission device is a terminal or a component in the terminal, the transmission device 300 includes:

[0278] The receiving module 301 is configured to receive first information sent by a network-side device.

[0279] The processing module 302 is configured to determine a target artificial intelligence (AI) unit based on the first information, the target AI unit being associated with a target modulation mode used by the network-side device to send downlink data.

[0280] The receiving module 301 is further configured to receive the downlink data based on the target AI unit.

[0281] Optionally, the target modulation mode is used to map a bit sequence into a symbol sequence.

[0282] Optionally, the apparatus further includes:

[0283] The sending module is configured to send second information to the network-side device, the second information being used to indicate capability information of the terminal for downlink data reception.

[0284] Optionally, the capability information includes at least one of:

[0285] a first AI unit supported by the terminal;

[0286] an applicable condition of the first AI unit supported by the terminal;

[0287] the first AI unit is used to convert a symbol sequence received by the terminal into a bit sequence.

[0288] Optionally, in a case where the second information is used to indicate the applicable condition, the second information includes at least one of:

[0289] scene information; configuration information; channel quality condition; terminal information.

[0290] Optionally, the first information includes an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit including the target AI unit.

[0291] Optionally, the apparatus further includes:

[0292] The sending module is configured to send third information to the network-side device, the third information being used to indicate a first AI unit requested by the terminal to be used to receive downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence.

[0293] Optionally, the first information includes at least one of:

[0294] confirmation information, the confirmation information being used to indicate whether to agree with the request of the third information.

[0295] the third information indicates an identity of at least one first AI unit in the first AI units, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit includes the target AI unit.

[0296] Optionally, the first information is used to indicate whether the modulation mode supported by the network side device matches the first AI unit reported by the terminal.

[0297] In a case where the first information indicates that the modulation mode supported by the network side device matches the first AI unit reported by the terminal, the first information further includes an identity of at least one first AI unit in the first AI unit reported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit includes the target AI unit.

[0298] In a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further includes related information of a second AI unit, the second AI unit is associated with the modulation mode supported by the network side device; or, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further includes an identity of a first AI unit that does not match the modulation mode supported by the network side device.

[0299] Optionally, the target AI unit is used for any one of the following:

[0300] demodulation processing;

[0301] joint processing of equalization and demodulation;

[0302] joint processing of channel estimation, equalization and demodulation.

[0303] Embodiments of the present application can improve transmission effect.

[0304] Referring to FIG. 10, when the transmission device is a network side device or a component in the network side device, the transmission device 400 includes:

[0305] a sending module 401 configured to send first information to a terminal, the first information being used to determine a target AI unit, the target AI unit being associated with a target modulation mode used to send downlink data;

[0306] The sending module 401 is further configured to send downlink data based on the target modulation mode.

[0307] Optionally, the target modulation mode is used to map a bit sequence into a symbol sequence.

[0308] Optionally, the apparatus further comprises:

[0309] a receiving module, configured to receive second information sent by the terminal, the second information being used to indicate capability information of the terminal for downlink data reception.

[0310] Optionally, the capability information comprises at least one of:

[0311] a first AI unit supported by the terminal;

[0312] a condition for application of the first AI unit supported by the terminal;

[0313] the first AI unit is used to convert a symbol sequence received by the terminal into a bit sequence.

[0314] Optionally, in the case where the second information is used to indicate the condition for application, the second information comprises at least one of:

[0315] scene information; configuration information; channel quality condition; terminal information.

[0316] Optionally, the first information comprises an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

[0317] Optionally, the apparatus further comprises:

[0318] a receiving module, configured to receive third information sent by the terminal, the third information being used to indicate a first AI unit requested by the terminal to be used for downlink data reception, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence;

[0319] a processing module, configured to determine the target modulation mode based on the third information.

[0320] Optionally, the first information comprises at least one of:

[0321] confirmation information, the confirmation information being used to indicate whether to agree with the request of the third information;

[0322] an identifier of at least one first AI unit indicated by the third information, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

[0323] Optionally, the first information is used to indicate whether a modulation mode supported by the network side device matches the first AI unit reported by the terminal.

[0324] In a case where the first information indicates that the modulation mode supported by the network side device matches the first AI unit reported by the terminal, the first information further comprises an identifier of at least one first AI unit in the first AI unit reported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit comprises the target AI unit; or

[0325] In a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises related information of a second AI unit, the second AI unit is associated with the modulation mode supported by the network side device; or, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises an identifier of a first AI unit that does not match the modulation mode supported by the network side device.

[0326] Optionally, the sending module 401 is further configured to:

[0327] In a case where the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, sending a target request to a target device, the target request being used to request related information of a second modulation mode that matches the first AI unit reported by the terminal;

[0328] The second modulation mode comprises the target modulation mode.

[0329] Optionally, the target AI unit is configured to perform any one of the following:

[0330] Demodulation processing;

[0331] Joint processing of equalization and demodulation;

[0332] Joint processing of channel estimation, equalization and demodulation.

[0333] Embodiments of the present application can improve transmission effect.

[0334] The transmission device provided by the embodiments of the present application can implement each process implemented by the method embodiments of FIG. 4 and FIG. 8, and achieve the same technical effects. To avoid repetition, details are not described here.

[0335] As shown in FIG. 11, the embodiment of the present application further provides a communication device 500, comprising a processor 501 and a memory 502, wherein the memory 502 stores programs or instructions executable by the processor 501. For example, when the communication device 500 is a terminal, the programs or instructions are executed by the processor 501 to implement each step of the above-mentioned transmission method embodiment and achieve the same technical effects. When the communication device 500 is a network side device, the programs or instructions are executed by the processor 501 to implement each step of the above-mentioned transmission method embodiment and achieve the same technical effects. To avoid repetition, details are not described herein.

[0336] The embodiment of the present application further provides a terminal, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement steps in the method embodiment shown in FIG. 4. The terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation manner of the above-mentioned method embodiment can be applied to the terminal embodiment and achieve the same technical effects. The terminal can be the transmission apparatus shown in FIG. 9. Specifically, FIG. 12 is a schematic diagram of a hardware structure of a terminal for implementing the embodiment of the present application.

[0337] The terminal 600 includes, but is not limited to, at least part of the following components: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, and a processor 610, etc.

[0338] Those skilled in the art can understand that the terminal 600 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 610 through a power management system, so as to realize functions such as power management, discharge management and power consumption management through the power management system. The terminal structure shown in FIG. 12 does not constitute a limitation on the terminal, and the terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which are not described herein.

[0339] It should be understood that in the embodiments of the present application, the input unit 604 can include a graphics processor 6041 and a microphone 6042, and the graphics processor 6041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 606 can include a display panel 6061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 607 includes at least one of a touch panel 6071 and other input devices 6072. The touch panel 6071 is also called a touch screen. The touch panel 6071 can include two parts of a touch detection device and a touch controller. The other input devices 6072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, and the like, which will not be described here.

[0340] In the embodiments of the present application, after the radio frequency unit 601 receives the downlink data from the network side device, it can be transmitted to the processor 610 for processing. In addition, the radio frequency unit 601 can send uplink data to the network side device. Generally, the radio frequency unit 601 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0341] The memory 609 can be used to store software programs or instructions and various data. The memory 609 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 609 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 609 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0342] The processor 610 can include one or more processing units; optionally, the processor 610 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 610.

[0343] The radio frequency unit 601 is configured to receive first information sent by a network side device.

[0344] The processor 610 is configured to determine a target artificial intelligence (AI) unit based on the first information, wherein the target AI unit is associated with a target modulation mode used by the network side device to send downlink data.

[0345] The radio frequency unit 601 is further configured to receive the downlink data based on the target AI unit.

[0346] Optionally, the target modulation mode is used to map a bit sequence into a symbol sequence.

[0347] Optionally, the radio frequency unit 601 is further configured to send second information to the network side device, the second information being used to indicate capability information of the terminal for downlink data reception.

[0348] Optionally, the capability information comprises at least one of:

[0349] a first AI unit supported by the terminal;

[0350] a condition for application of the first AI unit supported by the terminal;

[0351] the first AI unit is used to convert a symbol sequence received by the terminal into a bit sequence.

[0352] Optionally, in a case where the second information is used to indicate the condition for application, the second information comprises at least one of:

[0353] scene information; configuration information; channel quality condition; terminal information.

[0354] Optionally, the first information comprises an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

[0355] Optionally, the radio frequency unit 601 is further configured to send third information to the network side device, the third information being used to indicate a first AI unit requested by the terminal to be used for receiving downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence.

[0356] Optionally, the first information comprises at least one of:

[0357] confirmation information, the confirmation information being used to indicate whether to agree with the request of the third information;

[0358] an identifier of at least one first AI unit in the first AI unit indicated by the third information, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

[0359] Optionally, the first information is used to indicate whether a modulation mode supported by the network side device matches the first AI unit reported by the terminal;

[0360] In a case where the first information indicates that the modulation mode supported by the network side device matches the first AI unit reported by the terminal, the first information further comprises an identifier of at least one first AI unit in the first AI unit reported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit comprises the target AI unit; or

[0361] In a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises related information of a second AI unit, the second AI unit is associated with the modulation mode supported by the network side device; or, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises an identifier of a first AI unit that does not match the modulation mode supported by the network side device.

[0362] Optionally, the target AI unit is configured to perform any one of the following:

[0363] Demodulation processing;

[0364] Joint processing of equalization and demodulation;

[0365] Joint processing of channel estimation, equalization and demodulation.

[0366] The embodiments of the present application can improve the transmission effect.

[0367] It can be understood that the implementation process of each implementation mode mentioned in the embodiments can refer to the related description of the method embodiment of FIG. 4, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0368] The embodiments of the present application further provide a network side device comprising a processor and a communication interface, the communication interface and the processor are coupled, and the processor is configured to run programs or instructions to implement the steps of the method embodiments as shown in FIG. 8. The network side device embodiments correspond to the above-mentioned network side device method embodiments, and each implementation process and implementation mode of the above-mentioned method embodiments can be applied to the network side device embodiments, and can achieve the same technical effects.

[0369] Specifically, the embodiment of the present application further provides a network side device, which can be the transmission apparatus shown in FIG. 10. As shown in FIG. 13, the network side device 700 includes an antenna 701, a radio frequency device 702, a baseband device 703, a processor 704 and a memory 705. The antenna 701 is connected with the radio frequency device 702. In the uplink direction, the radio frequency device 702 receives information through the antenna 701, and sends the received information to the baseband device 703 for processing. In the downlink direction, the baseband device 703 processes information to be sent, and sends the processed information to the radio frequency device 702, and the radio frequency device 702 processes the received information and sends the processed information out through the antenna 701.

[0370] The method performed by the network side device in the above embodiment can be implemented in the baseband device 703, which includes a baseband processor.

[0371] The baseband device 703 can include at least one baseband board, for example, a plurality of chips are arranged on the baseband board, as shown in FIG. 13, one of the chips is a baseband processor, which is connected with the memory 705 through a bus interface to call the program in the memory 705 and perform the network device operation shown in the above method embodiment.

[0372] The network side device can further include a network interface 706, which is a common public radio interface (CPRI) for example.

[0373] Specifically, the network side device 700 of the embodiment of the present application further includes instructions or programs stored in the memory 705 and executable on the processor 704, the processor 704 calls the instructions or programs in the memory 705 to perform the method performed by each module shown in FIG. 10 and achieve the same technical effects, and thus the description is omitted here.

[0374] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG. 14, the network side device 800 includes a processor 801, a network interface 802 and a memory 803. The network side device can be the transmission apparatus shown in FIG. 10. The network interface 802 is a common public radio interface (CPRI) for example.

[0375] Specifically, the network side device 800 of the embodiment of the present application further includes instructions or programs stored in the memory 803 and executable on the processor 801, the processor 801 calls the instructions or programs in the memory 803 to perform the method performed by each module shown in FIG. 10 and achieve the same technical effects, and thus the description is omitted here.

[0376] The embodiment of the present application further provides a readable storage medium, and the readable storage medium stores programs or instructions, which are executed by a processor to realize the processes of the transmission method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0377] The processor is the processor in the terminal or the network side device in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0378] The embodiment of the present application further provides a chip, which includes a processor and a communication interface. The communication interface is coupled with the processor. The processor is used to run programs or instructions to realize the processes of the transmission method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0379] It should be understood that the chip mentioned in the embodiment of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[0380] The embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to realize the processes of the transmission method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0381] The embodiment of the present application further provides a wireless communication system, which includes a terminal and a network side device. The terminal can be used to execute the steps of the transmission method applied to the terminal. The network side device can be used to execute the steps of the transmission method applied to the network side device.

[0382] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a", "comprising", or the like does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. Furthermore, it is to be understood that the methods and apparatuses of the present application can be carried out by specific hardware, by software, or by a combination of hardware and software. It is therefore, contemplated to this patent to cover any and all modifications, variations, or equivalents that fall within the scope of the present application. Accordingly, where a concept can have been illustrated in only one of the exemplary embodiments, various aspects of the concept can be modified and / or combined to produce a variety of other embodiments that are not specifically illustrated. Thus, for purposes of describing particular embodiments, reference has been made to orientations. However, it is to be understood that the teachings of this patent are not limited in their application to any one of the mentioned orientations, but are applicable to any assembly having the features currently described or hereinafter ascertained.

[0383] From the above description of the embodiments, it is apparent that the method of the above embodiments can be realized by means of a computer software product and a general hardware platform as necessary, of course, also by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), and includes a plurality of instructions for making a terminal or a network side device execute the method described in each embodiment of the present application.

[0384] The embodiments of the present application are described above in conjunction with the drawings, but the present application is not limited to the above specific embodiments, and the above specific embodiments are merely illustrative rather than restrictive, and a person of ordinary skill in the art can make many forms of embodiments under the inspiration of the present application without departing from the scope of the present application and the protection scope of the claims, and these embodiments all belong to the protection scope of the present application.

Claims

1. A transmission method, comprising: receiving, by a terminal, first information sent by a network-side device; determining, by the terminal, a target artificial intelligence (AI) unit based on the first information, the target AI unit being associated with a target modulation mode used by the network-side device to send downlink data; receiving, by the terminal, the downlink data based on the target AI unit.

2. The method of claim 1, wherein, The target modulation mode is used to map a bit sequence into a symbol sequence.

3. The method according to claim 1 or 2, characterized in that, Before the receiving, by the terminal, the first information sent by the network-side device, the method further comprises: sending, by the terminal, second information to the network-side device, the second information being used to indicate capability information of the terminal for receiving the downlink data.

4. The method of claim 3, wherein, The capability information comprises at least one of: a first AI unit supported by the terminal; an applicable condition of a first AI unit supported by the terminal; The first AI unit is used to convert a symbol sequence received by the terminal into a bit sequence.

5. The method of claim 4, wherein, In a case where the second information is used to indicate the applicable condition, the second information comprises at least one of: scene information; configuration information; channel quality condition; terminal information.

6. The method of any one of claims 1-5, wherein, The first information comprises an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

7. The method of any one of claims 1-5, wherein, Before the receiving, by the terminal, the first information sent by the network-side device, the method further comprises: sending, by the terminal, third information to the network-side device, the third information being used to indicate a first AI unit requested by the terminal to be used to receive the downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence.

8. The method of claim 7, wherein, The first information comprises at least one of: confirmation information used to indicate whether to agree with the request of the third information; an identifier of at least one first AI unit in the first AI unit indicated by the third information, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit.

9. The method of any one of claims 1-8, wherein, The first information is used to indicate whether a modulation mode supported by the network-side device matches a first AI unit reported by the terminal; In a case where the first information indicates that the modulation mode supported by the network-side device matches the first AI unit reported by the terminal, the first information further comprises an identifier of at least one first AI unit in the first AI unit reported by the terminal, the at least one first AI unit being associated with the target modulation mode, and the at least one first AI unit comprising the target AI unit; or In a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises relevant information of a second AI unit, the second AI unit being associated with the modulation mode supported by the network side device; or, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises an identifier of the first AI unit that does not match the modulation mode supported by the network side device.

10. The method of any one of claims 1-9, wherein, The target AI unit is used for any one of the following: demodulation processing; joint processing of equalization and demodulation; joint processing of channel estimation, equalization and demodulation.

11. A transmission method, comprising: a network side device sending first information to a terminal, the first information being used for determining a target AI unit, the target AI unit being associated with a target modulation mode used for sending downlink data; the network side device sending downlink data based on the target modulation mode.

12. The method of claim 11, wherein, The target modulation mode is used for mapping a bit sequence into a symbol sequence.

13. The method of claim 11 or 12, wherein, Before the network side device sends the first information to the terminal, the method further comprises: the network side device receiving second information sent by the terminal, the second information being used for indicating capability information of the terminal for downlink data reception.

14. The method of claim 13, wherein, The capability information comprises at least one of the following: a first AI unit supported by the terminal; an applicable condition of the first AI unit supported by the terminal; The first AI unit is used for converting a symbol sequence received by the terminal into a bit sequence.

15. The method of claim 14, wherein, In a case where the second information is used for indicating the applicable condition, the second information comprises at least one of the following: scene information; configuration information; channel quality condition; terminal information.

16. The method of any one of claims 11-15, wherein, The first information comprises an identifier of at least one first AI unit supported by the terminal, the at least one first AI unit being associated with the target modulation mode, the at least one first AI unit comprising the target AI unit.

17. The method of any one of claims 11-15, wherein, Before the network side device sends the first information to the terminal, the method further comprises: the network side device receiving third information sent by the terminal, the third information being used for indicating a first AI unit requested by the terminal to be used for receiving downlink data, the first AI unit being used for converting a symbol sequence received by the terminal into a bit sequence; the network side device determining the target modulation mode based on the third information.

18. The method of claim 17, wherein, The first information comprises at least one of the following: confirmation information, the confirmation information being used for indicating whether to agree with the request of the third information; an identifier of at least one first AI unit in the first AI unit indicated by the third information, the at least one first AI unit being associated with the target modulation mode, the at least one first AI unit comprising the target AI unit.

19. The method of any one of claims 11-18, wherein, The first information is used for indicating whether the modulation mode supported by the network side device matches the first AI unit reported by the terminal; in a case where the first information indicates that the modulation mode supported by the network side device matches the first AI unit reported by the terminal, the first information further comprises an identifier of at least one first AI unit in the first AI unit reported by the terminal, the at least one first AI unit is associated with the target modulation mode, and the at least one first AI unit comprises the target AI unit; or in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises related information of a second AI unit, the second AI unit is associated with the modulation mode supported by the network side device; or, in a case where the first information indicates that the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the first information further comprises an identifier of a first AI unit that does not match the modulation mode supported by the network side device.

20. The method of any one of claims 11-18, wherein, Before the network side device sends the first information to the terminal, the method further comprises: in a case where the modulation mode supported by the network side device does not match the first AI unit reported by the terminal, the network side device sends a target request to a target device, the target request is used to request related information of a second modulation mode that matches the first AI unit reported by the terminal; wherein the second modulation mode comprises the target modulation mode.

21. The method of any one of claims 11-20, wherein, The target AI unit is used for any one of: demodulation processing; joint processing of equalization and demodulation; joint processing of channel estimation, equalization and demodulation.

22. A transmission apparatus comprising: a receiving module configured to receive first information sent by a network side device; a processing module configured to determine a target AI unit based on the first information, the target AI unit being associated with a target modulation mode used by the network side device to send downlink data; the receiving module is further configured to receive the downlink data based on the target AI unit.

23. The apparatus of claim 22, further comprising: a sending module configured to send second information to the network side device, the second information being used to indicate capability information of a terminal for downlink data reception.

24. The apparatus of claim 22 or 23, further comprising: a sending module configured to send third information to the network side device, the third information being used to indicate a first AI unit requested by the terminal to adopt for receiving downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence.

25. A transmission apparatus comprising: a sending module configured to send first information to a terminal, the first information being used to determine a target AI unit, the target AI unit being associated with a target modulation mode used to send downlink data; the sending module is further configured to send downlink data based on the target modulation mode.

26. The apparatus of claim 25, further comprising: a receiving module configured to receive second information sent by the terminal, the second information being used to indicate capability information of the terminal for downlink data reception.

27. The apparatus of claim 25 or 26, further comprising: receive a third information sent by the terminal, the third information being used to indicate a first AI unit used by the terminal to receive downlink data, the first AI unit being used to convert a symbol sequence received by the terminal into a bit sequence; determine the target modulation mode based on the third information.

28. A terminal comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the transmission method according to any one of claims 1-10.

29. A network side device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the transmission method according to any one of claims 11-21.

30. A readable storage medium, the readable storage medium storing programs or instructions, the programs or instructions being executed by a processor to implement the steps of the transmission method according to any one of claims 1-10, or to implement the steps of the transmission method according to any one of claims 11-21.

Images