Communication methods and apparatuses, and storage medium

Abstract

The embodiments of the present disclosure provide communication methods and apparatuses, and a storage medium. A communication method is applied to a first node, and the method comprises: sending first signaling to a second node, wherein the first signaling comprises identifiers of first information processing units; receiving second signaling sent by the second node, wherein the second signaling is used for determining a target first information processing unit; and, on the basis of the second signaling, determining the target first information processing unit from amongst the first information processing units.

Description

Communication method, device, and storage medium

[0001] This disclosure claims priority to Chinese patent application No. 202311870166.4, filed on December 29, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of communication technologies, and in particular to a communication method and device, and a storage medium. Background Art

[0003] The application of technologies such as artificial intelligence and deep learning on wireless air interfaces has received widespread attention and recognition in the industry. However, due to the limited generalization of AI information processing units (e.g., models) and limited computing resources, these units trained on the terminal side typically only operate in specific configurations, scenarios, sites, or environments, and are heavily dependent on the terminal's software / hardware environment and mobility characteristics.

[0004] Summary of the Invention

[0005] In one aspect, a communication method is provided, applied to a first node. The communication method includes:

[0006] Sending a first signaling to the second node, where the first signaling includes an identifier of the first information processing unit;

[0007] receiving a second signaling sent by the second node, where the second signaling is used to determine a target first information processing unit;

[0008] Based on the second signaling, a target first information processing unit is determined from the first information processing units.

[0009] On the other hand, a communication method is provided, which is applied to a second node. The communication method includes:

[0010] receiving a first signaling sent by the first node, where the first signaling includes an identifier of the first information processing unit;

[0011] A second signaling is sent to the first node, where the second signaling is used to determine a target first information processing unit.

[0012] In another aspect, a communication device is provided, applied to a first node. The communication device includes:

[0013] a sending unit, configured to send a first signaling to the second node, where the first signaling includes an identifier of the first information processing unit;

[0014] a receiving unit, configured to receive a second signaling sent by the second node, where the second signaling is used to determine a target first information processing unit;

[0015] A processing unit is used to determine the target first information processing unit from the first information processing units based on the second signaling.

[0016] In another aspect, a communication device is provided, which is applied to a second node. The communication device includes:

[0017] a receiving unit, configured to receive a first signaling sent by the first node, where the first signaling includes an identifier of the first information processing unit;

[0018] The sending unit is used to send a second signaling to the first node, where the second signaling is used to determine a target first information processing unit.

[0019] In yet another aspect, a communication device is provided, comprising: a processor, a memory, and computer program instructions stored in the memory and executable on the processor; when the processor executes the computer program instructions, the communication method described in any one of the above aspects is implemented.

[0020] In yet another aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes the communication method described in any one of the above aspects.

[0021] In yet another aspect, a computer program product comprising computer instructions is provided. When the computer instructions are executed on a computer, the computer is caused to execute the communication method according to any one of the above aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the technical solution of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the technical solution of the present disclosure and do not constitute a limitation to the technical solution of the present disclosure.

[0023] FIG1 is a schematic diagram of the architecture of a communication system according to some embodiments of the present disclosure.

[0024] FIG2 is a schematic diagram of a bilateral model according to some embodiments of the present disclosure.

[0025] FIG3 is a flow chart of a communication method according to some embodiments of the present disclosure.

[0026] FIG4 is a schematic diagram of a method for sorting identifications of a model according to some embodiments of the present disclosure.

[0027] FIG5 is a schematic diagram of another method for sorting identifications of a model according to some embodiments of the present disclosure.

[0028] FIG6 is a schematic diagram of a sorting method of identification of another model according to some embodiments of the present disclosure.

[0029] FIG7 is a schematic diagram of a sorting method of identification of another model according to some embodiments of the present disclosure.

[0030] FIG8 is a schematic diagram of a sorting method for identification of another model according to some embodiments of the present disclosure.

[0031] FIG9 is a schematic diagram of a sorting method for identification of another model according to some embodiments of the present disclosure.

[0032] FIG10 is a schematic diagram of a model training process according to some embodiments of the present disclosure.

[0033] FIG11 is a flow chart of another communication method according to some embodiments of the present disclosure.

[0034] FIG12 is a schematic diagram showing the composition of a communication device according to some embodiments of the present disclosure.

[0035] FIG13 is a schematic diagram showing the composition of another communication device according to some embodiments of the present disclosure.

[0036] FIG14 is a schematic structural diagram of a communication device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0037] To enable those skilled in the art to better understand the technical solutions of the embodiments of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0038] Unless the context requires otherwise, throughout the specification and claims, the term "comprise" and its other forms, such as the third person singular form "comprises" and the present participle form "comprising", are to be interpreted as meaning "open", "including", that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples" are intended to indicate that the particular features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the particular features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner.

[0039] The terms "first," "second," and the like are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature qualified by the terms "first," "second," and the like may explicitly or implicitly include one or more of such features. Throughout this disclosure, unless otherwise specified, "plurality" means two or more.

[0040] In the embodiments of the present disclosure, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present disclosure should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in a concrete manner.

[0041] Additionally, the use of “based on” is meant to be open and inclusive, as a process, step, calculation, or other action “based on” one or more stated conditions or values ​​may, in practice, be based on additional conditions or values ​​beyond those stated.

[0042] The application of technologies such as artificial intelligence (AI) and deep learning in wireless air interfaces has garnered widespread attention and recognition across the industry. The industry is currently conducting feasibility research and developing standards support for AI technologies in wireless air interfaces, including AI / deep learning-based channel state information feedback, beam management, and positioning. Take AI-based beam management as an example. In the traditional beam scanning process, the base station configures multiple reference signal resources for the terminal for beam measurement. These reference signal resources are carried on different downlink transmit beams. The terminal measures these reference signal resources and reports the beam measurement results to the base station. Since beams are typically selected from a predetermined simulated beam codebook, exhaustively scanning all beams in the codebook is the optimal beam training solution. However, this can result in excessive training overhead, measurement power consumption, and processing latency. In AI-based beam management, the base station only needs to transmit reference signal resources in a portion of the beam space or at a portion of time. AI algorithms are then used to predict the full beam space information and optimal beam at all times, effectively reducing beam training overhead and terminal measurement power consumption.

[0043] However, due to the generalization and limited computing resources of artificial intelligence information processing units (e.g., models), taking the information processing unit as an example, the model trained on the terminal side can usually only work in a specific configuration, scenario, site or environment, and is heavily dependent on the software / hardware environment and mobility characteristics of the terminal side. This results in many cases, the second node is unable to accurately instruct and operate the model on the terminal side, which in turn results in the model on the terminal side not being accurately matched with the model of the second node, resulting in a degradation of the model's performance. How to improve the matching accuracy between the information processing unit on the terminal side and the information processing unit on the base station side is an urgent problem to be solved.

[0044] Based on this, the embodiments of the present disclosure provide a communication method, device and storage medium, in which the target first information processing unit of the first node is determined based on the second signaling sent by the second node. In this way, the matching accuracy between the information processing unit of the first node and the information processing unit of the second node is improved, and the performance degradation of the information processing unit can be avoided.

[0045] The technical solutions provided by the embodiments of the present disclosure can be applied to various mobile communication networks, for example, new radio (NR) mobile communication networks using fifth-generation mobile communication technology (5G), future mobile communication networks, or multiple communication convergence systems, etc., but the embodiments of the present disclosure are not limited to this.

[0046] The network architecture of the mobile communication network (including but not limited to the third generation 3G, the fourth generation 4G, the fifth generation 5G and future mobile communication networks, such as the sixth generation 6G) in the embodiments of the present disclosure may include network side devices (for example, including but not limited to base stations) and receiving side devices (for example, including but not limited to terminals). And it should be understood that, in this example, in the downlink, the first communication node (also referred to as the first communication node device, the first node) can be the second node device, and the second communication node (also referred to as the second communication node device, the second node) can be the terminal side device. Of course, in the uplink, the first communication node can also be the terminal side device, and the second communication node can also be the second node device. In the device-to-device communication between the two communication nodes, the first communication node and the second communication node can both be base stations or terminals. The first communication node and the second communication node can be referred to as the first node and the second node, respectively.

[0047] In a wireless communication scenario, a first communication node and a second communication node communicate via a wireless channel. For example, the first communication node is a terminal and the second communication node is a base station, and the base station and the terminal communicate via a wireless channel. In another example, the first communication node is a terminal and the second communication node is a wireless router, and the wireless router and the terminal communicate via a wireless channel. In another example, the first communication node is a first base station and the second communication node is a second base station, and the first and second base stations communicate via a wireless channel. In another example, the first communication node is a first terminal and the second communication node is a second terminal, and the first and second terminals communicate via a wireless channel. In another example, the first communication node is a repeater and the second communication node is a base station, and the base station and the repeater communicate via a wireless channel. In another example, the first communication node is a terminal and the second communication node is a repeater, and the repeater and the terminal communicate via a wireless channel. In another example, the first communication node is a first repeater and the second communication node is a second repeater, and the first and second repeaters communicate via a wireless channel. In another example, the first communication node is a base station, the second communication node is a satellite, and the satellite and the base station communicate via a wireless channel. In another example, the first communication node is a satellite, the second communication node is a base station, and the base station and the satellite communicate via a wireless channel. In another example, the first communication node is a terminal, the second communication node is a satellite, and the satellite and the terminal communicate via a wireless channel. In another example, the first communication node is a satellite, the second communication node is a terminal, and the terminal and the satellite communicate via a wireless channel. In another example, the first communication node is a ground device, the second communication node is an aircraft, and the aircraft and the ground device communicate via a wireless channel. In another example, the first communication node is a first aircraft, the second communication node is a second aircraft, and the first and second aircraft communicate via a wireless channel.

[0048] In this disclosure, the terms "first" communication node, "second" communication node, "first" mode, "second" mode, "first" method, "second" method, "first" matrix, "second" matrix, "first part," and "second part" are used only for descriptive purposes and do not represent a sequence or precedence, nor do they represent superiority or inferiority. In other words, the terms "first" and "second" in the embodiments of this disclosure are used only for descriptive purposes and do not represent a sequence or precedence, nor do they represent superiority or inferiority.

[0049] For example, taking the network-side device as a base station and the receiving-side device as a terminal as an example, FIG1 is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure. As shown in FIG1 , the communication system 10 includes multiple base stations (e.g., base station 21 and base station 22) and multiple terminals (e.g., terminal 31, terminal 32, terminal 33, and terminal 34). Multiple base stations and multiple terminals can be communicatively connected.

[0050] In the present disclosure, the base station can be a base station or an evolved base station (eNB or eNodeB) in long term evolution (LTE), long term evolution advanced (LTEA), a base station device in a 5G network, or a base station in a future communication system (such as 6G), etc. The base station can include various macro base stations, micro base stations, home base stations, wireless remote devices, reconfigurable intelligent surfaces (RISs), routers, wireless fidelity (WIFI) devices, or various network side devices such as primary cells and collaborative cells (secondary cells).

[0051] In the present disclosure, a terminal is a device with wireless transceiver capabilities that can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons, and satellites, etc.). The terminal can be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in smart grids, a wireless terminal in transportation safety, a wireless terminal in smart cities, a wireless terminal in smart homes, and the like. The embodiments of the present disclosure do not limit the application scenarios. A terminal may also sometimes be referred to as a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication device, UE agent or UE apparatus, etc. The embodiments of the present disclosure are not limited thereto.

[0052] In some embodiments, high-layer signaling includes but is not limited to radio resource control (RRC), and media access control-control element (MAC CE), or other high-layer signaling above the physical layer. Physical layer signaling includes but is not limited to downlink control information and uplink control information. As an example, between a base station and a terminal, physical layer signaling can be transmitted on a physical downlink control channel (PDCCH), physical layer signaling can be transmitted on a physical uplink control channel (PUCCH), data can be transmitted on a physical downlink shared channel (PDSCH), and data can be transmitted on a physical uplink shared channel (PUSCH).

[0053] In some embodiments, the indicator of a parameter may also be referred to as an index or an identifier (ID), and the indication, identifier and index are equivalent concepts. For example, the resource identifier of a wireless system may also be referred to as a resource indication or a resource index. The resource identifier of a wireless system includes, but is not limited to, one of the following: reference signal resources, reference signal resource groups, reference signal resource configurations, channel state information (CSI) reports, CSI report sets, identifiers corresponding to terminals, base stations, panels, neural networks, sub-neural networks, neural network layers, etc. The base station may indicate the identifier of one or a group of resources to the terminal through various high-layer signaling or physical layer signaling. The terminal may feedback the identifier of one or a group of resources to the base station through various high-layer signaling and / or physical layer signaling.

[0054] In some embodiments, a time slot may be a time slot or a mini slot. A time slot or a mini slot includes at least one symbol. A symbol refers to a time unit in a subframe, frame, or time slot. For example, a symbol may be an orthogonal frequency division multiplexing (OFDM) symbol, a single-carrier frequency division multiple access (SC-FDMA) symbol, an orthogonal frequency division multiple access (OFDMA) symbol, etc.

[0055] In some embodiments, in order to calculate channel state information or perform channel estimation, mobility management, positioning, etc., a base station or user needs to send a reference signal (RS). Reference signals include, but are not limited to, a channel-state information reference signal (CSI-RS). CSI-RS includes zero-power CSI-RS (ZP CSI-RS) and non-zero-power CSI-RS (NZP CSI-RS), a channel-state information-interference measurement signal (CSI-IM), a sounding reference signal (SRS), a synchronization signal block (SSB), a physical broadcast channel (PBCH), and a synchronization signal block / physical broadcast channel (SSB / PBCH). NZP CSI-RS can be used to measure channels or interference, and CSI-RS can also be used for tracking, called a tracking reference signal (TRS). CSI-IM is generally used to measure interference, and SRS is used to measure uplink channels. In addition, the resource elements (REs) used to transmit reference signals include a set of resource elements (REs), such as CSI-RS resources, SRS resources, CSI-IM resources, and SSB resources. Time-frequency resources also include resource element groups (REGs), physical resource blocks (PRBs), physical resource block groups (RBGs), widebands, and subbands. In this article, SSBs include synchronization signal blocks and / or physical broadcast channels.

[0056] In some embodiments, in order to save signaling overhead, etc., multiple reference signal resources may be divided into multiple sets (such as CSI-RS resource set, CSI-IM resource set, SRS resource set), and the reference signal resource set includes at least one reference signal resource, and multiple reference signal resource sets can all come from the same reference signal resource setting (such as CSI-RS resource setting, SRS resource setting, where CSI-RS resource setting may be merged with CSI-IM resource setting, both referred to as CSI-RS resource setting) to configure parameter information.

[0057] In some embodiments, beams include transmit beams, receive beams, receive beams, transmit beam pairs, and transmit beams and receive beam pairs. A beam index can be replaced with a resource index (e.g., a reference signal resource index) because a beam can be bundled with some time-frequency code resources for transmission. A beam can also be a transmission (transmit / receive) mode; the transmission mode may include spatial division multiplexing, frequency / time domain diversity, beamforming, etc. In some embodiments, a beam pair includes a combination of a transmit beam and a receive beam.

[0058] In some embodiments, a beam is equivalent to a beam state, a quasi-co-location (QCL) state, a transmission configuration indicator (TCI) state, a spatial relation, spatial relation information, a reference signal (RS), a reference signal resource, a spatial filter, and a precoding. In some embodiments, a transmit beam is equivalent to a QCL state, a TCI state, a spatial relation, a spatial relation state, an uplink / downlink reference signal (such as CSI-RS, SSB, DMRS, SRS, PRACH), a transmit spatial filter, and a transmit precoding. In some embodiments, a receive beam is equivalent to a QCL state, a TCI state, a spatial relation, a spatial relation state, a spatial receive parameter, a spatial filter, a receive spatial filter, and a receive precoding. A spatial filter is also called a spatial domain filter, which can be either a second node or a UE side. In some embodiments, the base station can perform quasi co-location (QCL) configuration for two reference signals and inform the user terminal to describe the channel characteristic assumption. The parameters involved in the quasi-co-location include at least: Doppler spread, Doppler shift, delay spread, average delay, average gain and spatial parameter (Spatial Rx parameter, or Spatial parameter); wherein, the spatial parameter may include spatial reception parameter, angle information, spatial correlation of the receiving beam, average delay, correlation of time-frequency channel response (including phase information). The angle information may include at least one of the following: angle of arrival (AOA), angle of departure (AOD), ZOD (zenith angle of departure), ZOA (zenith angle of arrival). The spatial filtering may be at least one of the following: DFT vector, precoding vector, DFT matrix, precoding matrix, or a vector composed of a plurality of DFT linear combinations, a vector composed of a plurality of precoding vector linear combinations. In some embodiments, the concepts of vector and vector are interchangeable.

[0059] In some examples, in order to better transmit data or signals, the base station or terminal needs to obtain measurement parameters. The measurement parameters may include channel state information or other parameters used to characterize the channel, wherein the channel state information may include at least one of the following: channel state information-reference signal resource indicator (CSI-RS resource indicator, CRI), synchronization signal block resource indicator (synchronization signals block resource indicator, SSBRI), layer 1 reference signal received power (L1 reference signal received power, L1-RSRP or RSRP), differential RSRP (Differential RSRP); layer 1 reference signal signal to interference noise ratio (L1 signal to interference noise ratio, L1-SINR or SINR), differential L1-SINR (Differential L1-SINR); reference signal received quality (Reference Signal Received Quality, RSRQ), channel quality indicator (CQI), precoding matrix indicator (PMI), layer indicator (LI), rank indicator (RI), and related precoding information. Precoding information includes the first type of precoding information, such as codebook-based precoding information. Here, the precoding matrix indicator is a type of codebook-based precoding information. Precoding information also includes non-codebook-based implementations. For example, the second type of precoding information, such as precoding information obtained using advanced technologies such as artificial intelligence, is used.

[0060] In some embodiments, beam parameter information may also be referred to as beam quality information, or channel measurement results, or beam measurement results, or measurement results, or measurement parameters. In some embodiments, beam parameter information is a subset of channel state information, meaning that beam parameter information is channel state information, which in turn is a measurement parameter. In some embodiments, measurement parameters, channel state information, and beam parameter information are all measurement results, processing results, or generation results.

[0061] In some embodiments, in order to transmit channel state information at the physical layer, the terminal and the base station define a CSI report (CSI report or CSI report config), where the CSI report defines at least one of the following parameters: time-frequency resources used for CSI feedback, report quality included in the CSI, time domain category report ConfigType for CSI feedback, channel measurement resources, interference measurement resources, measurement bandwidth size, etc. The CSI report can be transmitted on uplink transmission resources, where the uplink transmission resources include PUSCH and PUCCH, and the CSI report also includes time domain characteristics, including periodic CSI report (P-CSI), aperiodic CSI report (AP-CSI), and semi-persistent CSI report (SP-CSI).

[0062] In some embodiments, the base station configures the terminal with NC CSI reports (CSI reports) that need to be fed back to the base station through high-layer signaling and / or physical layer signaling. Each CSI report has an identifier (identity, ID), called CSI reportID. The terminal can select MC CSI reports from the NC CSI reports based on its own computing power or processing power and the requirements of the base station. And based on the uplink feedback resources, at least one CSI report from the MC CSI reports is fed back, where NC and MC are positive integers and MC<=NC. In one example, MC CSI reports need to be fed back, but the feedback resources of at least two of the MC reports are conflicting. The conflict of feedback resources of the two reports means that at least one symbol in the transmission resources (such as PUCCH or PUSCH) corresponding to the two reports is the same and / or at least one subcarrier is the same. In some embodiments, feeding back CSI can also be called transmitting CSI or sending CSI, such as carrying channel state information on uplink transmission resources for feedback or transmission. The uplink transmission resources and the corresponding CSI are both indicated by a channel state information report. In some embodiments, feeding back or transmitting a CSI report refers to feeding back channel state information of the CSI report configuration. In some embodiments, feeding back or transmitting a CSI report refers to transmitting the content of the CSI report configuration that needs to be transmitted via a transmission resource.

[0063] In some embodiments, artificial intelligence (AI) includes self-learning devices, components, software, and modules such as machine learning (ML), deep learning, reinforcement learning, transfer learning, deep reinforcement learning, and meta-learning. In some embodiments, artificial intelligence is implemented through an artificial intelligence network (or neural network), which includes multiple layers, each layer including at least one node. In one example, the neural network includes an input layer, an output layer, and at least one hidden layer. Each layer of the neural network includes, but is not limited to, at least one of a fully connected layer, a dense layer, a convolutional layer, a transposed convolutional layer, a direct connection layer, an activation function, a normalization layer, and a pooling layer. In some embodiments, each layer of the neural network may include a sub-neural network, such as a residual network block (or Resnet block), a dense network block (Densenet Block), a recurrent neural network (RNN), a transformer network, and the like. The artificial intelligence network can be implemented through a model, which may include a neural network model, wherein the neural network model includes a neural network model structure and / or neural network model parameters, wherein the neural network model structure can be referred to as a model structure, and the neural network model parameters can be referred to as network parameters or model parameters. A model structure defines the network architecture, including the number of neural network layers, the size of each layer, the activation function, the connection status, the convolution kernel and the size of the convolution step, the convolution type (such as 1D convolution, 2D convolution, 3D convolution, hollow convolution, transposed convolution, separable convolution, grouped convolution, extended convolution, etc.), and the network parameters are the weights and / or biases of each layer of the neural network model and their values. A model structure can correspond to multiple sets of different neural network model parameter values ​​to adapt to different scenarios. The neural network model parameters are obtained through online training or offline training. For example, by inputting at least one sample and label, the neural network model is trained to obtain the neural network model parameters.

[0064] In some embodiments, a model is a general term used to describe a processing method, function, feature, or feature group that a terminal can perform. In some embodiments, a model is equivalent to a function (function / functionality), a functional module, a functional entity, a processing method, an information processing method, an implementation, a feature, a feature group, an information processing unit, an information processing method, etc. In some embodiments, each model corresponds to a model indicator or a functionality indicator or a model identity (Model ID) or a functionality identity. In some embodiments, a model identity may also have one of the following other equivalent names or concepts: model index, first identifier, functionality identifier, model indicator, etc.

[0065] In some embodiments, a model refers to a data flow from the original input of a sample to the output target through multiple linear or nonlinear components. The model includes a neural network model, a non-artificial intelligence module for processing information or its corresponding model, and a functional component or function that maps input information to output information (the mapping here includes linear mapping and nonlinear mapping).

[0066] In some examples, a model includes a model structure and model parameters. For example, if the model is a neural network model, the neural network model includes a neural network model structure and neural network model parameters, which are used to describe the structure of the neural network and the parameter values ​​of the neural network, respectively. A neural network model structure can correspond to multiple neural network model parameters, that is, the neural network model structure can be the same, but the corresponding neural network model parameter values ​​can be different.

[0067] In some examples, models include one-sided models and two-sided models. For example, a one-sided model is a model deployed / inferenced on the terminal side or a second node, while a two-sided model is a model deployed on the terminal side and a second node, respectively. The two models require certain coordination for inference calculations (for example, the structure of an autoencoder (AE)). For example, a two-sided model can be shown in Figure 2.

[0068] In some embodiments, the slash symbol ' / ' represents 'and'. In some embodiments, the slash symbol ' / ' represents 'or'. In some embodiments, the slash symbol ' / ' represents 'and / or'.

[0069] The communication method provided in the embodiment of the present disclosure is applicable to a communication system including at least one first node and at least one second node. The communication method provided in the embodiment of the present disclosure is described below with the first node as a terminal and the second node as a base station.

[0070] Next, as shown in FIG3 , an embodiment of the present disclosure provides a communication method, which is applied to a first node. The first node may be the terminal 31 shown in FIG1 . The method may include the following S101 - S103 .

[0071] S101. Send a first signaling to a second node.

[0072] In a frequency division duplexing (FDD) communication system, because the uplink channel and the downlink channel are located at different frequencies, the reciprocity between the two channels is weak, and the second node (i.e., the base station) cannot obtain the downlink channel conditions by measuring the uplink channel conditions obtained by the uplink reference signal. Therefore, the first node (i.e., the terminal) needs to measure the downlink reference signal sent by the second node to estimate the downlink channel and feedback the downlink channel state information (CSI) to the second node so that the second node can obtain the downlink channel state information. Typically, considering the limited uplink transmission resources, the first node will quantize and compress the complete CSI using methods such as codebooks, and feedback the CSI to the second node with less feedback overhead. However, in this case, some CSI information will be lost, resulting in a decrease in the accuracy of the fed-back CSI. Therefore, how to provide more accurate CSI feedback without significantly increasing the uplink feedback overhead is an urgent problem to be solved. Based on this, in the artificial intelligence-based CSI compression feedback method, the first node quantizes and compresses the channel measurement results into AI-based CSI through artificial intelligence / machine learning / deep learning models and feeds it back to the second node. The second node further restores the original channel measurement results as much as possible through artificial intelligence / machine learning / deep learning models for use by the second node. The information processing unit (for example, model) of the first node needs to match the information processing unit of the second node to achieve high-precision CSI recovery. At the same time, this method can also further reduce the overhead of CSI feedback of the first node.

[0073] Taking the information processing unit as an example, the model input, model output, required reference signal resource configuration, CSI reporting configuration, model applicable scenarios, etc. corresponding to different models may be different. Therefore, before activating the model of the first node, the first node needs to indicate the model-related information to the second node to achieve a consistent understanding of the model by the second node and the first node and to pave the way for subsequent model matching. This model-related information may include some static information (required reference signal resource configuration, CSI reporting configuration, etc.) or dynamic information (scenario, site, data set information corresponding to model training, etc.), as well as model pairing indication information (for example: model ID / pairing ID / data set ID / training period / stage ID, etc.), wherein the static information and the model pairing indication information may include but are not limited to being reported to the second node through the capability report of the first node. It should be noted that the information processing unit in the embodiment of the present disclosure may also have one of the following other equivalent names or concepts, for example, information processing mode, information processing method, model, etc.

[0074] In some embodiments, to improve the matching accuracy between the information processing unit on the terminal side and the information processing unit on the base station side, that is, to improve the matching accuracy between the information processing unit of the first node and the information processing unit of the second node, when the first node determines the information processing unit to be used by the first node, the first node sends a first signaling to the second node, where the first signaling includes an identifier of the first information processing unit. Correspondingly, the second node receives the first signaling sent by the first node.

[0075] In some embodiments, the first information processing unit can be understood as an information processing unit supported by the first node. It should be understood that the first signaling sent by the first node to the second node includes an identifier of the first information processing unit supported by the first node, so that the second node can determine the first information processing unit supported by the first node based on the identifier of the first information processing unit included in the first signaling, and then indicate to the first node the information processing unit that the first node should use based on the first information processing unit supported by the first node, thereby improving the matching accuracy of the information processing unit of the first node and the information processing unit of the second node.

[0076] In some embodiments, the identifier of the first information processing unit is used to uniquely indicate a first information processing unit. For example, the identifier of the first information processing unit may be the name of the first information processing unit. The identifier of the first information processing unit included in the first signaling may also be replaced by indication information of the first information processing unit.

[0077] In some embodiments, the identifier of the first information processing unit is a single-layer structure, and the identifier of the first information processing unit is indicated, allocated or configured by the second node. For example, taking the first information processing unit as UE_Model#1 as an example, assuming that UE_Model#1 is trained based on the data set Dataset#1, the identifier of the first information processing unit can be represented by UE_ID#1, indicating that UE_Model#1 is trained under Dataset#1. For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple first information processing units UE_Model#1 and UE_Model#2 as an example, wherein the first information processing units UE_Model#1 and UE_Model#2 are both trained in the same training period / stage Session#1, the identifier of UE_Model#1 can be represented as UE_ID#1, indicating that it is UE_Model#1 trained under Session#1.

[0078] In some embodiments, the sorting method of the identifiers of the first information processing unit is related to the sorting method of the identifiers of the data set corresponding to the first information processing unit. Taking the information processing unit as an example, illustratively, as shown in Figure 4, Figure 4 is a schematic diagram of the sorting method of the identifiers of a model provided by an embodiment of the present disclosure. It should be noted that the sorting method of the identifiers of the first information processing unit is not limited to the sorting method shown in Figure 4. In some embodiments, the sorting method of the identifiers of the first information processing unit is related to the generation order of the first information processing unit. illustratively, as shown in Figure 5, Figure 5 is a schematic diagram of the sorting method of the identifiers of another model provided by an embodiment of the present disclosure. As shown in Figure 5, when a new model is generated (developed), the model's identity document (ID) / indication information is added by 1 to the last number of the existing ID. Continuing to refer to Figure 5, ID#1 to ID#6 have been sorted according to the model development order. When a new model #2 is developed based on data set #3, the identifier of model #2 is set to ID#7 according to the development order.

[0079] In some embodiments, the sorting method of the identifiers of the first information processing unit is related to the sorting method of the identifiers of the training phase corresponding to the first information processing unit. Taking the information processing unit as an example, illustratively, as shown in FIG6 , FIG6 is a schematic diagram of the sorting method of the identifiers of another model provided by the embodiment of the present disclosure. It should be noted that the sorting method of the identifiers of the first information processing unit is not limited to the sorting method shown in FIG6 , and the sorting method of the identifiers of the first information processing unit can also be sorted according to the generation order of the first information processing unit. When a new first information processing unit is generated, the identifier of the new first information processing unit can be 1 added to the identifier of the existing last first information processing unit. illustratively, as shown in FIG7 , FIG7 is a schematic diagram of the sorting method of the identifiers of another model provided by the embodiment of the present disclosure. ID#1 to ID#6 have been sorted according to the generation order of the model. When a new model #2 is generated based on Session#3, the identifier of the new model is set to ID#7.

[0080] In some embodiments, when an already developed information processing unit (i.e., model) is updated (for example, the information processing unit parameters or the information processing unit structure are updated, etc.), the identification / indication information ID of the information processing unit may include but is not limited to a new identification / indication information, that is, a new identification / indication information may be assigned according to the generation order of the information processing unit, or the current identification / indication information may be kept unchanged, etc.

[0081] In some embodiments, when multiple first information processing units are trained and developed based on a subset of a data set, the multiple first information processing units can belong to the same Dataset_ID or to different Dataset_IDs. Furthermore, when multiple first information processing units belong to different Dataset_IDs, the first node needs to inform the second node which subset of the data set each first information processing unit is trained on, so as to maintain a consistent understanding of the conditions for information processing unit development on both sides (i.e., the first node side and the second node side), while helping the second node select an adapted second node side information processing unit.

[0082] In some embodiments, the identifier of the first information processing unit is a multi-layer structure. Taking the first information processing unit as an example, as shown in FIG8 , FIG8 is a schematic diagram of the sorting method of the identifiers of another model provided in an embodiment of the present disclosure. Referring to FIG8 , the identifier of model #1 can be represented as ID#1-1, indicating that model #1 is trained by data set #1. Alternatively, as shown in FIG9 , FIG9 is a schematic diagram of the sorting method of the identifiers of another model provided in an embodiment of the present disclosure. Referring to FIG9 , the identifier of model #1 can be represented as ID#1-1, indicating that model #1 is trained in Session #1.

[0083] In some embodiments, the identifier of the first information processing unit may be determined based on identifier set information corresponding to the first information processing unit and identifier information of the first information processing unit. The identifier set information includes at least one of the following: identifier information of a data set corresponding to the first information processing unit, identifier information of a training phase corresponding to the first information processing unit, and description information of the first information processing unit.

[0084] For example, take the example where the identification of the first information processing unit is determined based on the identification information of the data set corresponding to the first information processing unit and the identification information of the first information processing unit. For example, the identification of the first information processing unit is composed of the identification information of the data set corresponding to the first information processing unit + the identification information of the first information processing unit, and the identification of UE_Model#1 can be UE_ID#1-1, which represents UE_Model#1 trained by the first information processing unit under Dataset#1. It should be noted that in order for the second node and the first node to have a common understanding of the identification of the information processing unit and to better manage the first information processing unit on the first node side, the identification of the first information processing unit may include but is not limited to being allocated by the second node.

[0085] In some embodiments, when a dataset contains only one first information processing unit, the first node may only return the dataset's identifier, Dataset_ID, without returning the unit's identification information. A second node may also simply indicate the Dataset_ID when indicating the first information processing unit. For example, when Dataset #3 contains only one first information processing unit, either the first or second node may only need to return Dataset_ID #3. When a first node supports all first information processing units in a dataset, it may also only return the Dataset_ID, without returning the unit's identification information. For example, when a first node supports all three first information processing units in Dataset #1, it may only need to return Dataset_ID #1. However, since Dataset #1 contains three first information processing units, the second node still needs to specify the specific first information processing unit when indicating which first information processing unit to use. In conjunction with Figure 8 above, assuming that the second node indicates the use of the second model in Dataset #1 for the first node, the second node may indicate ID #1-2 to instruct the first node to use the second model in Dataset #1, i.e., Model #2.

[0086] For example, the identification of the first information processing unit can be determined based on the identification information of the training phase corresponding to the first information processing unit and the identification information of the first information processing unit. For example, the identification of the first information processing unit is composed of the identification information of the training phase + the identification information of the first information processing unit. That is, the identification of UE_Model#1 can be UE_ID#1-1, indicating UE_Model#1 trained in Session#1.

[0087] In some embodiments, when there is only one first information processing unit in a certain training stage, the first node can only feedback Session_ID without feedback of the identification information of the first information processing unit; the second node can also only indicate Dataset_ID when indicating the first information processing unit. For example, when there is only one first information processing unit in Session#3, the first node or the second node can only feedback Session_ID#3. When the first node supports all first information processing units in a certain training stage, the first node can also only feedback Session_ID without feedback of the identification information of the first information processing unit. For example, when the first node supports all three first information processing units in Session#1, the first node only needs to feedback Session_ID#1. However, since there are three first information processing units under Session#1, the second node still needs to indicate the specific first information processing unit when indicating which first information processing unit is for the first node to use. Combined with the above Figure 9, assuming that the second node indicates the use of the second model under Session#1 for the first node to use, the second node can indicate ID#1-2 to instruct the first node to use the second model in Session#1, that is, model #2.

[0088] It should be noted that: the second node can indicate the first information processing unit that the first node should use based on certain relevant information (the relevant information may include but is not limited to information such as scenario / configuration / implementation method / auxiliary information provided by the first node (for example: UE speed, motion trajectory, etc.)), which may include but is not limited to the first information processing unit with the best performance. Taking the information processing unit as an example, for example: Model A is a model trained based on an indoor scene dataset, and Model B is a model trained based on a mixed indoor and outdoor scene dataset. Of course, Model A performs better than Model B in indoor environments, but Model B has a certain degree of generalization in outdoor scenes and can work in outdoor scenes, while Model A may not work in outdoor environments. Therefore, when the motion trajectory of the first node is about to go outdoors from indoors, the second node can select Model B as the model that the first node should use based on some trajectory information of the first node, so that the performance will not suddenly drop.

[0089] In some embodiments, the first signaling may include, but is not limited to, a capability report of the first node.

[0090] In some embodiments, the first signaling may include, but is not limited to, at least one of the following: UCI signaling, MAC CE signaling, and high-layer signaling.

[0091] In some embodiments, the first node sends the first signaling to the second node, and the first node may dynamically send the first signaling to the second node.

[0092] S102: Receive second signaling sent by the second node.

[0093] The second signaling may include but is not limited to at least one of the following: RRC signaling, MAC CE signaling, and DCI signaling.

[0094] In some embodiments, after receiving the first signaling sent by the first node, the second node sends a second signaling to the first node in response to the first signaling. Accordingly, the first node receives the second signaling sent by the second node. The second signaling is used to determine the target first information processing unit, which can be understood as the information processing unit that the first node should use.

[0095] In some embodiments, the content included in the second signaling is related to the content included in the first signaling. The content included in the first signaling and the second signaling can refer to the relevant description in the following S103 and will not be repeated here.

[0096] S103: Determine a target first information processing unit from the first information processing units based on the second signaling.

[0097] In some embodiments, the first information processing unit includes one or more, that is, the number of information processing units supported by the first node is one or more. When the number of information processing units supported by the first node is one, that is, when the first signaling includes an identifier of a first information processing unit, after receiving the first signaling, the second node determines the second information processing unit that matches the first information processing unit based on the identifier of the first information processing unit included in the first signaling, and then sends a second signaling to the first node. The second signaling includes the identifier of the target first information processing unit, and the identifier of the target first information processing unit is also the identifier of the first information processing unit supported by the first node, so as to instruct the first node to use a first information processing unit supported by the first node to perform subsequent reasoning and calculation work.

[0098] In some embodiments, the second information processing unit matches the first information processing unit, and can be obtained by joint training of the first information processing unit and the second information processing unit. The first information processing unit and the second information processing unit are jointly trained. The first information processing unit and the second information processing unit can be obtained by the second node transmitting the first information processing unit to the first node after the second node completes the joint training of the first information processing unit and the second information processing unit on the second node side. Alternatively, in the same training phase, the first node completes the training of the first information processing unit on the first node side, and the second node completes the training of the second information processing unit on the second node side. Alternatively, the second node completes the training of the second information processing unit on the second node side, and then sends the data set generated during the training of the second information processing unit to the first node, and the first node trains the first information processing unit based on the data set generated during the training of the second information processing unit sent by the second node to obtain the trained first information processing unit. Alternatively, the first node sends the data set generated during the training of the first information processing unit on the first node side to the second node, and the second node trains the second information processing unit based on the data set generated during the training of the first information processing unit sent by the first node. It should be noted that the training period can be an offline stage or an online stage, and the method of determining the training order can be determined by offline negotiation or configured by the second node, etc., and the embodiments of the present disclosure do not limit this.

[0099] Taking the information processing unit as the model, the identifier of the information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports the model UE_Model#1, and reports the indication information UE_ID#1 of the model to the second node through the capability report. The second node receives the indication information UE_ID#1 of the model and selects / confirms the matching second node side model NW_Model#1. The reason why the two are matched may be that UE_Model#1 and NW_Model#1 are paired models jointly trained offline. Therefore, after the second node confirms that it can match, it instructs the first node to use the model UE_Model#1 for subsequent inference calculations.

[0100] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports model UE_Model#1, which is trained based on the data set Dataset#1 sent by the second node. Therefore, the first node reports the indication information Dataset_ID#1 of the model to the second node through a capability report. The second node receives the indication information Dataset_ID#1 of the model and selects / confirms the matching second node side model NW_Model#1. The reason why the two match is that the data set Dataset#1 is generated during the training process of the second node side model NW_Model#1. Therefore, after the second node confirms that it can match, it instructs the first node to use the model UE_Model#1 for subsequent inference calculations.

[0101] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports model UE_Model#1, which is trained based on the training period / stage Session#1. Therefore, the first node reports the indication information Session_ID#1 of the model to the second node through the capability report. The second node receives the indication information Session_ID#1 of the model and selects / confirms the matching second node model NW_Model#1. The reason why the two are matched is that UE_Model#1 and NW_Model#1 are paired models jointly trained during the offline training period / stage Session#1. Therefore, after the second node confirms that it can match, it instructs the first node to use the model UE_Model#1 for subsequent inference calculations.

[0102] In some embodiments, the second node uniformly trains the first information processing unit and the second information processing unit on the second node side. The second node may train the first information processing unit corresponding to each of the multiple first nodes for multiple first nodes, and train the second information processing unit corresponding to the second node, and then send the first information processing unit corresponding to each first node to each first node, that is, the second node performs one-to-many training of the information processing unit; or the second node may train the first information processing unit corresponding to a first node for the first node, and train the second information processing unit corresponding to the second node, and then send the trained first information processing unit to the first node, that is, the second node performs one-to-one training of the information processing unit.

[0103] In some embodiments, when the number of information processing units supported by the first node includes multiple, that is, when the first signaling includes the identifiers of multiple first information processing units, the following uses several examples to illustrate how to determine the target first information processing unit from the first information processing units based on the second signaling.

[0104] Example 1: The first signaling further includes first information and second information, and the second signaling includes an identifier of the target first information processing unit.

[0105] The second information is obtained by the first node after processing the first information based on the first information processing unit, the target first information processing unit is determined by the second node from the first information processing unit based on the performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0106] In some embodiments, the first information can be understood as the original channel state information. The first information may also be called by other names, for example, initial channel state information, target channel state information, note channel state information, etc. The first information may include information processed by a possible information preprocessing method. The second information can be understood as the channel state information compressed by the first information processing unit. The third information can be understood as the channel state information decompressed (restored) based on the second information processing unit.

[0107] For example, when the first signaling also includes the first information and the second information, after receiving the first signaling, the second node can determine the multiple first information processing units supported by the second node based on the identifier of the first information processing unit included in the first signaling, and then determine the second information processing unit that matches each first information processing unit based on the multiple first information processing units. The second node then inputs the second information into the multiple second information processing units to decompress the second information to obtain multiple third information. The second node then determines the target first information processing unit from the first information processing unit based on the performance evaluation index between each third information and the first information corresponding to each third information. After the second node determines the target first information processing unit from the first information processing unit, the second node can send a second signaling to the first node, where the second signaling includes the identifier of the target first information processing unit.

[0108] Based on this, the first node determines the target first information processing unit from the first information processing unit based on the second signaling, which can be implemented as the first node determining the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit included in the second signaling, that is, taking the first information processing unit corresponding to the identifier of the target first information processing unit in the first information processing unit as the target first information processing unit.

[0109] It should be noted that a third information is obtained by the second node after processing the second information based on a second information processing unit, and a performance evaluation indicator is obtained based on a third information and a first information, that is, a third information corresponds to a second information processing unit and a performance evaluation indicator, and a second information processing unit is matched with a first information processing unit. Based on this, the target first information processing unit can be the first information processing unit that matches the second information processing unit corresponding to the optimal performance evaluation indicator among the performance evaluation indicators between each third information and the first information corresponding to each third information.

[0110] In some embodiments, the performance evaluation indicators include a first type of evaluation indicators, a second type of evaluation indicators, and a third type of evaluation indicators; wherein the first type of evaluation indicators include evaluation indicators based on distance error and evaluation indicators based on similarity; the evaluation indicators based on distance error include at least one of the following: Euclidean distance (ED), mean squared error (MSE), and normalized mean squared error (NMSE); the evaluation indicators based on similarity include at least one of the following: cosine similarity (CS), generalized cosine similarity (GCS), and cross entropy (CE);

[0111] The second category of evaluation indicators includes throughput-based evaluation indicators and channel quality-based evaluation indicators. Throughput-based evaluation indicators include at least one of the following: system throughput (Throughput), user throughput (UPT), average user throughput, 5% user throughput, and spectral efficiency (SE). Channel quality-based evaluation indicators include at least one of the following: bit error rate (BER), block error rate (BLER), hypothetical bit error rate (hypothetical BER), hypothetical block error rate (hypothetical BLER), signal-to-noise ratio (SNR), signal-to-interference-plus-noise ratio (SINR), modulation and coding scheme (MCS), and transmission level.

[0112] The third type of evaluation indicators includes evaluation indicators based on data distribution error, and the evaluation indicators based on data distribution error include at least one of the following: power spectrum, energy spectrum, amplitude spectrum, and phase spectrum.

[0113] It should be noted that the performance evaluation indicators may also include but are not limited to the test performance of the information processing unit after training, that is, after the information processing unit is trained, it must pass the information processing unit test before it can be used. Specifically, the performance evaluation indicators may be average performance indicators, pass rate, etc.

[0114] Taking the first information processing unit as a model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, and the first node reports the indication information UE_ID#1, UE_ID#2 of these models and the first information and the second information to the second node through the capability report. After receiving the capability report of the first node, the second node selects / confirms the matching multiple second node side models NW_Model#1, NW_Model#2 (for example, NW_Model#1 and UE_Model#1 are jointly trained). NW_Model#2 and UE_Model#2 are jointly trained, so a second node side model can be matched to a first node side model), and the second information is input into the corresponding second node side model to recover the third information. The second node calculates the performance evaluation index of the third information and the first information fed back by the first node to compare which model has better model performance index under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the second node instructs the first node to use the model with the best performance index to perform subsequent reasoning calculations, that is, to indicate that the first information processing unit corresponding to the optimal performance evaluation index is the target first information processing unit. Alternatively, after receiving the capability report of the first node, the second node selects / confirms a matching second node side model NW_Model#1 (for example, NW_Model#1 is jointly trained with UE_Model#1 and UE_Model#2, so one second node side model can match multiple first node side models), and inputs the second information into the corresponding second node side model to recover the third information. The second node calculates the performance evaluation indicators of the third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the second node instructs the first node to use the model with the best performance indicator to perform subsequent reasoning calculations, that is, send a second signaling to the first node, and the second signaling includes the identifier of the target first information processing unit.

[0115] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, wherein model UE_Model#1 is trained based on data set Dataset#1, and model UE_Model#2 is trained based on data set Dataset#2. The training process can be shown in FIG10 , where data set #1 in FIG10 can correspond to Dataset#1, and data set #2 can correspond to Dataset#2. It should be noted that the data set may include but is not limited to a data set sent by the second node to the first node / a data set collected by the second node instructing the first node (for example, a certain spatial area / time period / scenario / configuration / function / feature / feature group / implementation method, etc.), and different data sets may be completely different / have partial overlap / subset relationships, and the data set sending method may be that the second node broadcasts to the entire cell / users in a specific area or may be transmitted separately to one or more first nodes. Therefore, after the first node reports the capability report of the first node (including Dataset_ID#1, Dataset_ID#2, the first information and the second information) to the second node, the second node can select / confirm the matching second node side models NW_Model#1 and NW_Model#2, and then the second node can input the second information into NW_Model#1 and NW_Model#2 to recover two third information. The second node calculates the performance evaluation indicators of the two third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the second node instructs the first node to use the model with the best performance indicator to perform subsequent reasoning calculations, that is, send a second signaling to the first node, and the second signaling includes the identifier of the target first information processing unit.

[0116] It should be noted that the second node can perform a performance comparison based on the information partially reported by the first node. For example, the second node can use the third information recovered by different second information processing units after processing the second information to determine the difference between the current channel information and the channel information at the previous moment, as well as the range of the difference, to indirectly determine the performance difference and pave the way for the first information processing unit's instructions and selections. This approach is applicable to all embodiments of the present disclosure and will not be elaborated on below.

[0117] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, where both models UE_Model#1 and UE_Model#2 are trained based on the same dataset Dataset#1. As an example, when the identifier of the first information processing unit is a single-layer structure, that is, when the identifier / indication information of the model is a single-layer structure, the identification information of UE_Model#1 can be UE_ID#1, indicating that it is UE_Model#1 trained under Dataset#1. After the first node reports the first node's capability report (including UE_ID#1, UE_ID#2, the first information, and the second information) to the second node, the second node determines to select / confirm a matching second-node-side model NW_Model#1 (for example, UE_Model#1 and UE_Model#2 are both trained based on the dataset Dataset#1 sent by the second node, where Dataset#1 may be generated after the training of NW_Model#1, so one second-node-side model can match multiple first-node-side models), and inputs the second information into the corresponding second-node-side model to recover third information (for example, third channel state information). The second node calculates performance evaluation indicators of the third information and the first information to compare which model has the better model performance indicator under the indication information, that is, the model with the highest matching degree or the most suitable for the current scenario / configuration / function / feature / feature group / implementation method. The second node then instructs the first node to use the model with the best performance indicator for subsequent inference calculation work, that is, sends second signaling to the first node, where the second signaling includes an identifier of the target first information processing unit.

[0118] As another example, in the case where the identification of the first information processing unit is a multi-layer structure, that is, in the case where the identification / indication information of the model is a multi-layer structure, for example, taking the identification of the first information processing unit as an example, which is determined based on the identification information of the data set corresponding to the first information processing unit and the identification information of the first information processing unit, assuming that the models supported by the first node are UE_Model#1 and UE_Model#2, the identification information of UE_Model#1 can be UE_ID#1-1, indicating UE_Model#1 trained under Dataset#1, and the identification information of UE_Model#2 can be UE_ID#1-2, indicating UE_Model#2 trained under Dataset#1. After the first node reports the first node's capability report (including UE_ID#1-1, UE_ID#1-2, the first information, and the second information) to the second node, the second node selects / confirms a matching second node-side model NW_Model#1 (for example, UE_Model#1 and UE_Model#2 are both trained based on the dataset Dataset#1 sent by the base station, where Dataset#1 may be generated after the training of NW_Model#1, so one second node-side model can match multiple first node-side models). The second node then inputs the two second information corresponding to the two first node-side models into the corresponding second node-side models to recover two third information (for example, third channel state information). The second node calculates performance evaluation indicators of the two third information and the first information to compare which model has the best model performance indicator under the indication information, i.e., the model with the highest matching degree or the most suitable for the current scenario / configuration / function / feature / feature group / implementation method. The second node then instructs the first node to use the model with the best performance indicator for subsequent inference calculations, i.e., sends a second signaling to the first node, where the second signaling includes an identifier of the target first information processing unit.

[0119] Still taking the first information processing unit as the model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, where model UE_Model#1 is obtained based on training period / stage Session#1, and model UE_Model#2 is obtained based on training period / stage Session#2. After the first node reports the capability report of the first node (including UE_Model#1, UE_Model#2, the first information and the second information) to the second node, the second node selects / confirms the matching second node side models NW_Model#1 and NW_Model#2, and then inputs the second information into NW_Model#1 and NW_Model#2 to recover two third information. Then, the second node calculates the performance evaluation indicators between the two third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing matching degree is the highest or the most suitable for the current scenario / configuration / function / feature / feature group / implementation method. Then, the second node instructs the first node to use the model with the best performance indicator to perform subsequent reasoning and calculation work, that is, send a second signaling to the first node, and the second signaling includes the identifier of the target first information processing unit.

[0120] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, where models UE_Model#1 and UE_Model#2 are trained in the same training period / stage Session#1. As an example, when the identifier of the first information processing unit is a single-layer structure, that is, when the identifier / indication information of the model is a single-layer structure, the identification information of UE_Model#1 can be UE_ID#1, indicating UE_Model#1 trained in Session#1. After the first node reports the first node's capability report (including UE_ID#1, UE_ID#2, first information, and second information) to the second node, the second node selects / confirms a matching second node-side model NW_Model#1 (for example, UE_Model#1, UE_Model#2, and NW_Model#1 are all trained under Session#1, so one second node-side model can match multiple first node-side models). The second node then inputs the two second information corresponding to the two first node-side models into the corresponding second node-side models to recover two third information (for example, third channel state information). The second node calculates performance evaluation indicators of the two third information and the first information to compare which model has the better model performance indicator under the indication information, that is, the model with the highest matching degree or the most suitable for the current scenario / configuration / function / feature / feature group / implementation method. The second node then instructs the first node to use the model with the best performance indicator for subsequent inference calculations, that is, sends a second signaling to the first node, where the second signaling includes an identifier of the target first information processing unit.

[0121] As another example, when the identification of the first information processing unit is a multi-layer structure, that is, when the identification / indication information of the model is a multi-layer structure, for example, taking the identification of the first information processing unit as an example, the identification information of the training stage corresponding to the first information processing unit and the identification information of the first information processing unit is determined, the identification information of UE_Model#1 can be UE_ID#1-1, which means UE_Model#1 trained by the model under Session#1. After the first node reports the first node's capability report (including UE_ID#1-1, UE_ID#1-2, first information, and second information) to the second node, the second node selects / confirms a matching second node-side model NW_Model#1 (for example, UE_Model#1, UE_Model#2, and NW_Model#1 are all trained based on Session#1, so one second node-side model can match multiple first node-side models). The second node then inputs the two second information corresponding to the two first node-side models into the second node-side model to recover two third information (for example, third channel state information). The second node calculates performance evaluation indicators of the two third information and the first information to compare which model has the better model performance indicator under the indication information, that is, the model with the highest matching degree or the most suitable for the current scenario / configuration / function / feature / feature group / implementation method. The second node then instructs the first node to use the model with the best performance indicator for subsequent inference calculation work, that is, sends a second signaling to the first node, the second signaling including the identifier of the target first information processing unit.

[0122] In some embodiments, after the second node determines the target first information processing unit, the second node may select a target second information processing unit that matches the target first information processing unit to perform subsequent reasoning and calculation work.

[0123] Example 2: The first signaling also includes second information, and the second signaling includes third information.

[0124] The third information is obtained after the second node processes the second information based on the second information processing unit.

[0125] The example shown in Example 1 above is that the first node reports both the first information and the second information to the second node, and the second node determines the target first information processing unit based on the performance evaluation index between the third information and the first information. In some embodiments, the first node may also only report the identifier and the second information of the first information processing unit supported by itself to the second node. After receiving the first signaling, the second node determines the first information processing unit supported by the first node based on the identifier of the first information processing unit included in the first signaling, and then determines the second information processing unit that matches the first information processing unit, and then processes the second information based on the second information processing unit to obtain the third information, and then sends the second signaling including the third information to the first node, so that the first node can determine the target first information processing unit based on the performance evaluation index between the third information in the second signaling and the first information.

[0126] In some embodiments, the information or signaling involved in the embodiments of the present disclosure, such as the first information, the second information, the first signaling, and the second signaling, can all be information or signaling quantized by a quantization method, and the quantization method can be scalar quantization, vector quantization, codebook quantization, etc.

[0127] Based on this, when the first signaling further includes the second information and the second signaling includes the third information, determining the target first information processing unit from the first information processing unit based on the second signaling may include the following A1-A2.

[0128] A1. Determine a performance evaluation index between the first information and the third information.

[0129] For the description of the performance evaluation indicators, please refer to the corresponding description in Example 1 above and will not be repeated here.

[0130] A2. Determine the target first information processing unit from the first information processing units based on a performance evaluation index between the first information and the third information.

[0131] In some embodiments, the first node may determine a first information processing unit that matches a second information processing unit corresponding to an optimal performance evaluation indicator as a target first information processing unit.

[0132] In some embodiments, when the first signaling also includes second information and the second signaling includes third information, after the first node determines the target first information processing unit from the first information processing unit based on the second signaling, the first node may also send the identifier of the target first information processing unit to the second node, so that the second node can perform subsequent reasoning calculations based on the identifier of the target first information processing unit using the target second information processing unit that matches the target first information processing unit.

[0133] In some embodiments, the transmission of the third information may include but is not limited to scalar quantization, vector quantization, or codebook quantization (for example, Type I codebook, Type II codebook, various enhanced Type I / II codebooks, etc.). The data / information / parameters / models / signaling and other methods involved in the transmission process in the embodiments of the present disclosure are all applicable to the above-mentioned quantization methods. For example, the transmission of the first signaling and the transmission of the second signaling are both applicable to the above-mentioned quantization methods, which will not be elaborated on.

[0134] The following describes, with reference to several examples, how to determine the target first information processing unit from the first information processing unit based on the second signaling when the first signaling also includes the second information and the second signaling includes the third information.

[0135] Taking the first information processing unit as the model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1, UE_Model#2, and reports the indication information UE_ID#1, UE_ID#2 and the second information of these models to the second node through capability report / dynamic report (for example, CSI report). After the second node receives the capability report of the first node, the second node selects one or more adapted second node side models (i.e., second information processing units) based on UE_ID#1 and UE_ID#2, and then inputs the second information into one or more second node side models for processing to obtain one or more third information, and then sends a second signaling to the first node, and the second signaling includes one or more third information. After the first node receives the second signaling, the first node calculates the performance evaluation index of each third information and the first information to compare which model has a better model performance index under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best model performance index (that is, the optimal performance evaluation index) to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0136] It should be noted that when the second node transmits multiple adapted third information, it may include but is not limited to binding relevant information indicated by the model identification with the third information and indicating it to the first node, in order to help the first node understand the adapted second information for performance evaluation (for example, the third information output by NW_Model#1 is the third information output by the second node-side model that matches UE_ID#1). Moreover, the number of third information is the same as the number of models supported by the first node. When the second node transmits only one adapted third information, it may not indicate relevant information indicated by the model identification to the first node. For example, the first node only reports the identification / indication information of one model.

[0137] For example, after the second node receives the capability report sent by the first node, the second node determines the matching second node side models NW_Model#1 and NW_Model#2 based on UE_ID#1 and UE_ID#2 included in the capability report (for example, NW_Model#1 and UE_Model#1 are jointly trained, and NW_Model#2 and UE_Model#2 are jointly trained, so one second node side model can be matched to one first node side model), and sends the two second information included in the capability report to the matching NW_Model#1, NW_Model#2 obtains two corresponding third information, and transmits the two third information to the first node, that is, sends the second signaling to the first node, and the second signaling includes two third information. After the first node receives the second signaling, the first node calculates the performance evaluation index of each third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance index to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0138] For another example, after the second node receives the capability report sent by the first node, the second node determines the matching second node side model NW_Model#1 based on UE_ID#1 and UE_ID#2 included in the capability report (for example, NW_Model#1 is jointly trained with UE_Model#1 and UE_Model#2, so one second node side model can match multiple first node side models). The second node inputs the second information corresponding to UE_ID#1 and the second information corresponding to UE_ID#2 included in the capability report into NW_Model#1 respectively, obtains two third information, and transmits the two third information to the first node, that is, sends the second signaling to the first node, and the second signaling includes two third information. After the first node receives the second signaling, the first node calculates the performance evaluation index of each third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance index to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0139] For another example, the first node supports multiple models UE_Model#1 and UE_Model#2, which may include but are not limited to those trained based on the same data set Dataset#1. After the second node receives the capability report sent by the first node, the second node determines the matching second node side model NW_Model#1 based on UE_ID#1 and UE_ID#2 included in the capability report (for example, NW_Model#1, UE_Model#1 and UE_Model#2 are trained based on the same data set Dataset#1, so one second node side model can match multiple first node side models). The second node inputs the second information corresponding to UE_ID#1 and the second information corresponding to UE_ID#2 included in the capability report into NW_Model#1 respectively, obtains two third information, and transmits the two third information to the first node, that is, sends second signaling to the first node, and the second signaling includes two third information. After the first node receives the second signaling, the first node calculates the performance evaluation index of each third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance index to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0140] For another example, the multiple models UE_Model#1 and UE_Model#2 supported by the first node may include but are not limited to those trained based on the same time period / phase Session#1. After the second node receives the capability report sent by the first node, the second node determines the matching second node side model NW_Model#1 based on UE_ID#1 and UE_ID#2 included in the capability report (for example, NW_Model#1, UE_Model#1 and UE_Model#2 are trained based on the same time period / phase Session#1, so one second node side model can match multiple first node side models). The second node inputs the second information corresponding to UE_ID#1 and the second information corresponding to UE_ID#2 included in the capability report into NW_Model#1 respectively, obtains two third information, and transmits the two third information to the first node, that is, sends a second signaling to the first node, and the second signaling includes two third information. After the first node receives the second signaling, the first node calculates the performance evaluation index of each third information and the first information to compare which model has better model performance indicators under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance index to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0141] Example 3: The second signaling includes a third information processing unit.

[0142] The third information processing unit is an information processing unit that is determined by the second node based on the identifier of the first information processing unit and matches the first information processing unit.

[0143] The above example 2 is an example in which the second signaling sent by the second node includes the third information, so that the first node can determine the target first information processing unit based on the performance evaluation index between the third information and the first information. In some embodiments, the first signaling may also only include the identifier of the first information processing unit. After the second node receives the first signaling, it can determine the third information processing unit that matches the first information processing unit based on the identifier of the first information processing unit, and then send a second signaling to the first node. The second signaling includes the third information processing unit, so that the first node processes the second information based on the third information processing unit to obtain the fourth information, and then determines the target first information processing unit based on the performance evaluation index between the first information and the fourth information. The third information processing unit may be the same as the above-mentioned second information processing unit, or it may be different from the above-mentioned second information processing unit, and this is not limited in the embodiment of the present disclosure. In the case where the third information processing unit is the same as the above-mentioned second information processing unit, the fourth information may be the same as the above-mentioned third information. It should be understood that the computing power resources of the first node are limited. When the computing power resources required by the second information processing unit are higher, the third information processing unit included in the second signaling may be a simplified second information processing unit. When the computing power resources required by the second information processing unit are lower, the third information processing unit included in the second signaling may be the second information processing unit.

[0144] Based on this, when the first signaling also includes the second information and the second signaling includes the third information, determining the target first information processing unit from the first information processing unit based on the second signaling may include the following B1-B3.

[0145] B1. Process the second information based on the third information processing unit to obtain fourth information.

[0146] In some embodiments, when the second signaling includes a third information processing unit, after receiving the second signaling, the first node can input the second information corresponding to each first information processing unit in multiple first information processing units into the third information processing unit to obtain multiple fourth information.

[0147] B2. Determine a performance evaluation index between the first information and the fourth information.

[0148] B3. Determine a target first information processing unit from the first information processing units based on a performance evaluation index between the first information and the fourth information.

[0149] For the description of B2-B3, please refer to the above description of A1-A2, which will not be repeated here.

[0150] In some embodiments, when the second signaling includes a third information processing unit, after the first node determines the target first information processing unit from the first information processing unit based on the second signaling, the first node may also send the identifier of the target first information processing unit to the second node, so that the second node can use the target second information processing unit that matches the target first information processing unit to perform subsequent reasoning calculations based on the identifier of the target first information processing unit.

[0151] For example, after the first node determines the performance evaluation index between the first information and the fourth information, the first node may also send the performance evaluation index between the first information and the fourth information to the second node, and the second node determines the target first information processing unit from the first information processing unit based on the performance evaluation index between the first information and the fourth information, and then sends the identifier of the target first information processing unit to the first node, and the first node determines the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit. That is, in the case where the second signaling includes the third information processing unit, after S102, the first node may send a third signaling to the second node, the third signaling including the performance evaluation index between the first information and the fourth information, and then the first node receives the fourth signaling sent by the second node, the fourth signaling including the identifier of the target first information processing unit, and then the first node determines the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit.

[0152] For another example, after the first node determines the performance evaluation index between the first information and the fourth information, the first node may also determine a candidate information processing unit from the first information processing unit based on the performance evaluation index between the first information and the fourth information, and then send information processing unit suggestion (recommendation) information to the second node, the information processing unit suggestion information including the identifier of the candidate first information processing unit, and the second node determines the target first information processing unit from the candidate first information processing unit based on the identifier of the candidate first information processing unit included in the information processing unit suggestion information, and then the second node sends the identifier of the target first information processing unit to the first node, and the first node determines the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit. That is, in the case where the second signaling includes the third information processing unit, after S102, the first node may send five signalings to the second node, the fifth signaling including the information processing unit suggestion (recommendation) information, and then the first node receives the sixth signaling sent by the second node, the sixth signaling including the identifier of the target first information processing unit, and then the first node determines the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit.

[0153] It should be noted that the example in which, after determining the performance evaluation indicator, the first node determines the candidate first information processing unit based on the performance evaluation indicator, and then recommends information to the second node information processing unit is also applicable to other embodiments of the present disclosure in which the performance evaluation indicator is determined by the first node, and will not be repeated below.

[0154] The following describes, with reference to several examples, how to determine a target first information processing unit from among the first information processing units based on the second signaling when the second signaling includes a third information processing unit.

[0155] Taking the first information processing unit as the model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, and reports the indication information UE_ID#1 and UE_ID#2 of these models to the second node through capability report / dynamic report (for example, CSI report). After the second node receives the capability report of the first node, the second node selects one or more adapted second node side models (that is, the third information processing unit) based on UE_ID#1UE_ID#2, and then sends a second signaling to the first node, where the second signaling includes one or more adapted second node side models.

[0156] For example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, where the models UE_Model#1 and UE_Model#2 may include but are not limited to those trained based on the same data set Dataset#1. The first node reports UE_ID#1 and UE_ID#2 to the second node through a capability report. After the second node receives the capability report sent by the first node, the second node determines the matching second node side models NW_Model#1 and NW_Model#2 based on UE_ID#1 and UE_ID#2 included in the capability report, and then the second node sends a second signaling to the first node, and the second signaling includes NW_Model#1 and NW_Model#2. After receiving the second signaling, the first node inputs the multiple second information into NW_Model#1 and NW_Model#2 respectively, obtains the fourth information corresponding to NW_Model#1 and the fourth information corresponding to NW_Model#2, and then compares which model has better model performance indicators under the indication information based on the performance evaluation indicators between the two fourth information and the first information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance indicator to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0157] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2, where the models UE_Model#1 and UE_Model#2 may include but are not limited to those obtained based on the same training period / stage Session#1 training. The first node reports UE_ID#1 and UE_ID#2 to the second node through a capability report. After the second node receives the capability report sent by the first node, the second node determines the matching second node side models NW_Model#1 and NW_Model#2 based on UE_ID#1 and UE_ID#2 included in the capability report, and then the second node sends a second signaling to the first node, and the second signaling includes NW_Model#1 and NW_Model#2. After receiving the second signaling, the first node inputs the multiple second information into NW_Model#1 and NW_Model#2 respectively, obtains the fourth information corresponding to NW_Model#1 and the fourth information corresponding to NW_Model#2, and then compares which model has better model performance indicators under the indication information based on the performance evaluation indicators between the two fourth information and the first information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the first node uses the model UE_Model#1 with the best performance indicator to perform subsequent reasoning and calculation work. At the same time, the first node needs to report UE_ID#1 to the second node, and the second node selects NW_Model#1 corresponding to UE_ID#1 for subsequent reasoning and calculation work.

[0158] Example 4: The first signaling also includes performance indicator information, and the second signaling includes an identifier of the target first information processing unit.

[0159] The performance indicator information includes a performance evaluation indicator between the first information and the fifth information. The fifth information is obtained by the first node after processing the second information based on the fourth information processing unit. The identifier of the target first information processing unit is determined by the second node from the first information processing unit based on the performance indicator information.

[0160] In Example 3 above, the second node sends a third information processing unit that matches the first information processing unit to the first node. The first node processes the second information based on the third information processing unit to obtain fourth information, and then determines the target first information processing unit from the first information processing units based on the performance evaluation index between the fourth information and the first information. In some embodiments, the first node pre-configures or pre-stores a fourth information processing unit that matches the first information processing unit. After processing the first information based on multiple first information processing units to obtain multiple second information, the first node can process the multiple second information based on multiple fourth information processing units to obtain multiple fifth information, and then determine the performance evaluation index between the multiple fifth information and the first information. The first node then sends a first signaling to the second node. The first signaling includes the identifier of the first information processing unit and performance index information, so that the second node can determine the target first information processing unit from the first information processing unit based on the performance index information. After receiving the first signaling, the second node determines the target first information processing unit from the first information processing unit based on the performance index information, and then sends a second signaling to the first node. The second signaling includes the identifier of the target first information processing unit.

[0161] It should be noted that when the second node has the same understanding of the order of the first information processing units of the first node as the first node, the first node only needs to feedback the performance evaluation indicators in the order of the first information processing units, without having to feedback the identifier of the first information processing unit corresponding to each performance evaluation indicator. In this way, the feedback overhead of the first node can be reduced.

[0162] Based on this, when the first signaling also includes performance indicator information and the second signaling includes the identifier of the target first information processing unit, the target first information processing unit is determined from the first information processing unit based on the second signaling. The first node may determine the target first information processing unit from the first information processing unit based on the identifier of the target first information processing unit included in the second signaling.

[0163] In some embodiments, when the first signaling also includes performance indicator information and the second signaling includes the identifier of the target first information processing unit, after the first node determines the target first information processing unit from the first information processing unit based on the second signaling, the first node may also send the identifier of the target first information processing unit to the second node, so that the second node can use the target second information processing unit that matches the target first information processing unit to perform subsequent inference calculations based on the identifier of the target first information processing unit.

[0164] The following uses several examples to illustrate how to determine the target first information processing unit from the first information processing units based on the second signaling when the first signaling also includes performance indicator information and the second signaling includes the identifier of the target first information processing unit.

[0165] Taking the first information processing unit as a model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1 and UE_Model#2 (wherein UE_Model#1 and UE_Model#2 may include but are not limited to being based on the same data set, in the same training phase, or based on the same second node side model training), the first node calculates the corresponding performance information #1 and performance information #2 through the fourth information processing unit ( Performance information #1 is better than performance information #2), and the performance indicator information (including performance information #1 and performance information #2) and / or the first information and the model indication information UE_ID#1, UE_ID#2 are reported to the second node through the capability report / dynamic report (for example, CSI report, etc.). After receiving the capability report / dynamic report, the second node determines the UE_Model#1 with better performance based on the performance indicator information, and indicates the UE_Model#1 with better performance to the first node for subsequent reasoning calculation, that is, sending a second signaling to the first node, the second signaling including the identifier of the target first information processing unit.

[0166] Example 5: The first signaling also includes performance indicator information, and the second signaling includes an identifier of the candidate first information processing unit.

[0167] The candidate first information processing unit is determined by the second node from the first information processing units based on the performance indicator information.

[0168] In the above-mentioned Example 4, the second node directly determines the target first information processing unit from the first information processing unit based on the performance indicator information. In some embodiments, the second node can also determine the candidate first information processing unit from the first information processing unit based on the performance indicator information, and then send a second signaling to the first node. The second signaling includes the identifier of the candidate first information processing unit, and the first node determines the target first information processing unit from the candidate first information processing units.

[0169] For example, assuming that the number of first information processing units supported by the first node is M, the second node can determine N candidate first information processing units from the M first information processing units based on performance indicator information, and then send a second signaling to the first node. The second signaling includes the identifiers of the N candidate first information processing units, and the first node determines the target first information processing unit from the N candidate first information processing units. <N<M。

[0170] Based on this, when the first signaling also includes performance indicator information and the second signaling includes the identifier of the candidate first information processing unit, the target first information processing unit is determined from the first information processing unit based on the second signaling. The first node may determine the target first information processing unit from the first information processing unit based on the attribute information of the first node and the identifier of the candidate first information processing unit.

[0171] The attribute information of the first node includes at least one of the following: capability information of the first node and resource usage of the first node. The capability information of the first node includes at least one of the following: software capability and hardware capability. The resource usage of the first node includes at least one of the following: CSI processing unit usage (which can be understood as central processing unit (CPU) usage) and power consumption.

[0172] In some embodiments, when the first signaling also includes performance indicator information and the second signaling includes the identifier of the candidate first information processing unit, after the first node determines the target first information processing unit from the first information processing units based on the second signaling, the first node may also send the identifier of the target first information processing unit to the second node, so that the second node can use the target second information processing unit that matches the target first information processing unit to perform subsequent inference calculations based on the identifier of the target first information processing unit.

[0173] The following describes, with reference to some examples, how to determine a target first information processing unit from among the first information processing units based on the second signaling when the first signaling also includes performance indicator information and the second signaling includes an identifier of a candidate first information processing unit.

[0174] Taking the first information processing unit as a model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1, UE_Model#2 and UE_Model#3, and then the first node reports the indication information UE_ID#1, UE_ID#2, UE_ID#3 of the multiple models, and the performance indicator information to the second node through the capability report. The second node determines which model has better model performance indicators under the indication information through the relevant performance indicators in the performance indicator information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / Function / feature / feature group / implementation method, and then the second node determines that the performance of UE_ID#2 and UE_ID#3 can both meet certain performance evaluation indicators, that is, the models corresponding to UE_ID#2 and UE_ID#3 are candidate models, and then the second node indicates to the first node that the performance of UE_ID#2 and UE_ID#3 can both meet certain evaluation indicators. The first node further selects the model UE_Model#2 corresponding to UE_ID#2 as the target model based on its own attribute information, and reports the indication information UE_ID#2 of the model corresponding to UE_Model#2 to the second node, and the second node further selects NW_Model#2 that matches UE_ID#2 for subsequent inference calculations.

[0175] Example 6: The first signaling further includes first information and second information, and the second signaling includes an identifier of the candidate first information processing unit.

[0176] The candidate first information processing unit is determined by the second node from the first information processing unit based on the performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0177] In Example 1 above, the second node directly determines the target first information processing unit from the first information processing units based on the performance evaluation index between the third information and the first information, and then indicates the target first information processing unit to the first node. In some embodiments, the second node may also determine candidate first information processing units from the first information processing units based on the performance evaluation index between the third information and the first information, and then indicate the candidate first information processing units to the first node, and the first node determines the target first information processing unit from the first information processing units based on the candidate first information processing units.

[0178] Based on this, the first signaling also includes first information and second information, and when the second signaling includes the identifier of the candidate first information processing unit, the target first information processing unit is determined from the first information processing unit based on the second signaling. The first node may determine the target first information processing unit from the first information processing unit based on the attribute information of the first node and the identifier of the candidate first information processing unit.

[0179] For the description of the attribute information of the first node, please refer to the relevant description in the above example 5. For the description of how the second node determines the candidate first information processing unit from the first information processing unit based on the performance evaluation index between the third information and the first information, please refer to the description of how the second node determines the target first information processing unit from the first information processing unit based on the performance evaluation index between the third information and the first information in the above example 1. It will not be repeated here.

[0180] The following describes, with reference to some examples, how to determine a target first information processing unit from among the first information processing units based on the second signaling when the first signaling also includes performance indicator information and the second signaling includes an identifier of a candidate first information processing unit.

[0181] Taking the first information processing unit as a model, the identifier of the first information processing unit as the indication information of the model, and the first signaling as the capability report of the first node as an example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1, UE_Model#2 and UE_Model#3, and then the first node reports the indication information UE_ID#1, UE_ID#2, UE_ID#3, the first information and the second information of the multiple models to the second node through the capability report. After receiving the capability report, the second node selects / confirms the matching multiple second node side models NW_Model#1, NW_Model#2, NW_Model#3 (for example, NW_Model#1 and UE_Model#1 are jointly trained, NW_Model#2 and UE_Model#2 are jointly trained, and NW_Model#3 and UE_Model#3 are jointly trained, so a second node side model can be matched to a first node side model ), and input each second information into the corresponding second node side model to recover multiple third information. The base station calculates the performance evaluation index between each third information and the first information to compare which model has better model performance index under the indication information, that is, the model pairing has the highest matching degree or is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the second node determines that the performance of UE_ID#2 and UE_ID#3 can both meet certain performance evaluation indicators, that is, the models corresponding to UE_ID#2 and UE_ID#3 are candidate models, and then the second node indicates the first node UE_ID#2, UE_ID#3 The performance can meet certain evaluation indicators, the first node further selects the model UE_Model#2 corresponding to UE_ID#2 as the target model according to its own attribute information, and reports the indication information UE_ID#2 of the model corresponding to UE_Model#2 to the second node, and the second node further selects NW_Model#2 matching UE_ID#2 for subsequent reasoning calculations.

[0182] For another example, for a certain scenario / configuration / function / feature / feature group / implementation method, the first node supports multiple models UE_Model#1, UE_Model#2 and UE_Model#3, and then the first node reports the indication information UE_ID#1, UE_ID#2, UE_ID#3, the first information and the second information of the multiple models to the second node through a capability report. After receiving the capability report, the second node selects / confirms the matching second node side model NW_Model#1 (for example, NW_Model#1 and UE_Model#1, UE_Model#2, UE_Model#3 are jointly trained together, so one second node side model can match multiple first node side models), and inputs each second information into the second node side model to recover multiple third information. The base station calculates the relationship between each third information and the first information. The performance evaluation indicators are used to compare which model has better model performance indicators under the indication information, that is, the model pairing matching degree is the highest or the model is most suitable for the current scenario / configuration / function / feature / feature group / implementation method, and then the second node determines that the performance of UE_ID#2 and UE_ID#3 can both meet certain performance evaluation indicators, that is, the models corresponding to UE_ID#2 and UE_ID#3 are candidate models, and then the second node indicates to the first node UE_ID#2, UE_ID#3 that the performance can both meet certain evaluation indicators. The first node further selects the model UE_Model#2 corresponding to UE_ID#2 as the target model according to its own attribute information, and reports the indication information UE_ID#2 of the model corresponding to UE_Model#2 to the second node, and the second node further selects NW_Model#2 matching UE_ID#2 for subsequent reasoning and calculation.

[0183] Based on the embodiment shown in Figure 3, the target first information processing unit of the first node is determined based on the second signaling sent by the second node. In this way, the matching accuracy between the information processing unit of the first node and the information processing unit of the second node is improved, and the performance degradation of the information processing unit can be avoided.

[0184] In some embodiments, the method may further include the following C1-C2.

[0185] C1. Receive first indication information sent by the second node.

[0186] In some embodiments, the second node sends the first indication information to the first node periodically / non-periodically / semi-continuously or based on event triggering. Accordingly, the first node receives the first indication information sent by the second node. Based on the event triggering, the second node switches the information processing unit, and the first indication information is used to indicate the fifth information processing unit. The fifth information processing unit can be understood as the information processing unit that the second node is about to switch or is currently using. The fifth information processing unit can be the same as the above-mentioned second information processing unit or different from the above-mentioned second information processing unit. The embodiments of the present disclosure are not limited to this.

[0187] In some embodiments, the first indication information includes at least one of the following: identification information of the fifth information processing unit, identification information of the data set corresponding to the fifth information processing unit, identification information of the training stage corresponding to the fifth information processing unit, description information of the fifth information processing unit, etc.

[0188] C2. Based on the first indication information, determine a sixth information processing unit that matches the fifth information processing unit.

[0189] After receiving the first indication information, the first node can determine, based on the first indication information, a sixth information processing unit that matches the fifth information processing unit, and then use the sixth information processing unit to perform subsequent reasoning and computing. It should be understood that the sixth information processing unit is determined by the first indication information sent by the second node. Therefore, the first node uses the sixth information processing unit to perform subsequent reasoning and computing, thereby improving the matching accuracy between the first node's information processing unit and the second node's information processing unit and avoiding performance degradation of the information processing units.

[0190] In some embodiments, after determining the sixth information processing unit, the first node may send the identifier of the sixth information processing unit to the second node, so that the second node is informed that the first node will use the sixth information processing unit for subsequent reasoning and computation. This allows the first and second nodes to have a consistent understanding of the sixth information processing unit.

[0191] In some embodiments, the first node sends the identifier of the sixth information processing unit or the identifier of the target first information processing unit to the second node, which may be information processing unit identification information sent by the first node to the second node, where the information processing unit identification information includes the identifier of the sixth information processing unit or the identifier of the target first information processing unit. The information processing unit identification information may include, but is not limited to, information processing unit identification information determined through an information processing unit identification / authentication process, and the information processing unit identification information may be global / universal identification information or local / small-scale management identification information.

[0192] It should be noted that, when the number of sixth information processing units determined by the first node is 1, the first node may report the identifier of the sixth information processing unit to the second node, or may not report the identifier of the sixth information processing unit to the second node, or may report indication information indicating whether pairing is supported to the second node. For example, a 1-bit indication information is sent to the second node. When the value of the indication information is a first value, it indicates that the first node supports pairing with the fifth information processing unit, that is, it can determine the sixth information processing unit that matches the fifth information processing unit. When the value of the indication information is a second value, it indicates that the first node does not support pairing with the fifth information processing unit. The first value and the second value are different, for example, the first value is a non-zero integer (e.g., 1) and the second value is 0, or the first value is 0 and the second value is a non-zero integer; for example, the first value is true (TRUE) and the second value is false (FALSE), or the first value is false (FALSE) and the second value is true (TRUE). The present embodiment is not limited to this.

[0193] If the first node determines that there is no sixth information processing unit paired with the fifth information processing unit, the first node may send indication information to the second node indicating that pairing is not supported. For example, the first node may send 1-bit indication information to the second node. If the value of the indication information is a second value, it indicates that the first node does not support pairing with the fifth information processing unit. After receiving the indication information, the second node will not activate the fifth information processing unit or respond.

[0194] In some embodiments, the above-mentioned indication information for indicating whether pairing is supported and the above-mentioned indication information for indicating that pairing is not supported can both be reported to the second node in the first signaling, that is, the first signaling can include the above-mentioned indication information for indicating whether pairing is supported and the above-mentioned indication information for indicating that pairing is not supported.

[0195] For example, the first indication information may be the identifier of the fifth information processing unit. The second node sends the first indication information, which may be the second node broadcasting / indicating the identifier of the fifth information processing unit to all / part of the first nodes in the cell / a certain area. After the first node receives the identifier of the fifth information processing unit, it selects / confirms the matching sixth information processing unit, and further reports the identifier of the sixth information processing unit to the second node to inform the second node that the first node will use the sixth information processing unit for subsequent reasoning and calculation work.

[0196] For another example, the first indication information is the identification information of the data set corresponding to the fifth information processing unit. The second node sends the first indication information, which may be that the second node broadcasts / indicates the identification information of the data set corresponding to the fifth information processing unit to all / part of the first nodes in the cell / a certain area. After the first node receives the identification information of the data set corresponding to the fifth information processing unit, it selects / confirms the sixth information processing unit that matches the fifth information processing unit, and further reports the identification of the sixth information processing unit to the second node to inform the second node that it will use the sixth information processing unit for subsequent reasoning and calculation work.

[0197] In some embodiments, when the first information processing unit of the first node is trained by the second node and needs to be transmitted to the first node for use, the second node transmits and configures the first information processing unit to the first node and assigns the corresponding information processing unit identification information, such as the ID information of the information processing unit, etc.; the first node side receives the identification information, selects / confirms the matching first information processing unit, and naturally matches the second information processing unit on the second node side, and then the first node reports the identification information of the adapted first information processing unit to the second node to inform the second node that it will perform subsequent inference calculations based on the first information processing unit.

[0198] In some embodiments, when the second node transmits only one first information processing unit to the first node for use by the first node, the first node may not report identification information of the corresponding information processing unit.

[0199] In some embodiments, when the second node trains multiple first information processing units and transmits multiple first information processing units to the first node for use by the first node, the first node needs to report the identification information of one or more information processing units that meet the capabilities / conditions of the first node. The subsequent model pairing and indication process refers to the embodiment shown in Figure 3. For example, the second node transmits two models UE_Model#1 and UE_Model#2 to the first node, and the corresponding identification information of these two models is UE_ID#1 and UE_ID#2 respectively. The first node selects / confirms UE_Model#1 that meets its current capabilities / conditions. The first node reports the identification information UE_ID#1 corresponding to UE_Model#1 to the second node to complete the pairing and identification process between the two parties. For another example, the second node transmits three models UE_Model#1, UE_Model#2, and UE_Model#3 to the first node. The corresponding identification information of these three models are UE_ID#1, UE_ID#2, and UE_ID#3, respectively. The first node selects / confirms that the models that meet its current capabilities / conditions are UE_Model#1 and UE_Model#2. The first node reports the identification information UE_ID#1 and UE_ID#2 corresponding to UE_Model#1 and UE_Model#2 to the second node, and the second node decides the model that the first node should use.

[0200] In some embodiments, in order to better match the information processing unit of the first node with the information processing unit of the second node, the second node may send auxiliary information to the first node to help the first node select a more suitable information processing unit. Based on this, the method may further include the following D1.

[0201] D1. Receive second indication information sent by the second node.

[0202] The second indication information is used by the first node to select an information processing unit.

[0203] In some embodiments, the second indication information includes at least one of the following: structural information of an information processing unit that the first node should use; structural information of an information processing unit used by the second node.

[0204] In this way, the first node can determine, based on the second indication information, an information processing unit that can better match the second information processing unit of the second node.

[0205] For example, if the information processing unit used by the second node is a Transformer network structure, then the second node indicates to the first node that the information processing unit should be used by the Transformer structure, so that the information processing unit used by the first node can be better adapted to the information processing unit used by the second node. In some embodiments, when the second indication information includes the structural information of the information processing unit to be used by the first node and / or the structural information of the information processing unit used by the second node, the structural information can be indicated by a K-bit bitmap (for example, there are four information processing unit structures, where 0001 represents the Transformer structure, 0010 represents the CNN structure, 0100 represents the RNN structure, and 1000 represents the DNN structure); further, in order to reduce the bit overhead of the second indication information, M bits can also be used for indication (for example, there are four information processing unit structures, where 00 represents the Transformer structure, 01 represents the CNN structure, 10 represents the RNN structure, and 11 represents the DNN structure).

[0206] In some embodiments, the second indication information further includes at least one of the following: information processing unit complexity of the information processing unit; computational complexity of the information processing unit; reasoning time range of the information processing unit; storage overhead range of the information processing unit.

[0207] For example, the second node instructs the first node to perform reasoning using an information processing method with less than 20M floating point operations per second (FLOPs); for another example, the second node instructs the first node to perform reasoning using an information processing unit with an inference delay of less than T slots / subframes / symbols.

[0208] As an example, the second indication information sent by the second node to the first node only assists the first node in selecting an information processing unit and does not force the first node to select an information processing unit based on the second indication information. As another example, the second indication information sent by the second node to the first node forces the first node to select an information processing unit based on the second indication information. For example, the second node forces the first node to use an information processing unit with a Transformer structure.

[0209] It should be understood that since the information processing unit does not have good generalization, it is impossible to implement one information processing unit for all scenarios / configurations, which will lead to performance degradation. Based on this, the method may also include E1.

[0210] E1. Receive third indication information sent by the second node.

[0211] In some embodiments, when the second node detects that the performance of the information processing unit has declined over a period of time, or detects that the performance of the information processing unit is less than or equal to a preset performance threshold over a period of time, the second node sends third indication information to the first node. Accordingly, the first node receives the third indication information sent by the second node, and the third indication information is used for at least one of the following: information processing unit group activation, information processing unit group deactivation, information processing unit group switching, information processing unit group update, information processing unit activation, information processing unit deactivation, information processing unit switching, information processing unit update, and fallback to the default information processing mode.

[0212] Taking the information processing unit as an example, when the second node detects that the model performance has declined over a period of time, the second node performs at least one of the following operations on the entire model group / function group / configuration group of the first node (wherein, there can be one or more models in the model group / function group / configuration group, the number of models in different model groups / function groups / configuration groups can be the same or different, and a model can belong to one or more different model groups / function groups / configuration groups): group activation / group deactivation / group switching, etc. (that is, the operation is performed on all models in the entire group. For example: group deactivation means that every model in the group is deactivated). For example, a first node supports two related functional groups, UE_Functionality#1 and UE_Functionality#2. The model currently used by the first node belongs to UE_Functionality#1. When it detects that the performance of the current model has deteriorated to a poor level, the second node can instruct the first node to deactivate / switch UE_Functionality#1 to UE_Functionality#2 through high-layer or physical layer signaling (e.g., RRC / MAC CE / DCI) (i.e., third indication information), and select a model under UE_Functionality#2 for subsequent reasoning. It should be noted that the management decision of the second node is at the granularity of the model group / functional group / configuration group, and the specific model used by the first node is transparent to the second node.

[0213] For another example, when the second node detects that the model performance has degraded over a period of time, the second node performs at least one of the following operations on the models in the model group / function group / configuration group of the first node (wherein, there may be one or more models in the model group / function group / configuration group, the number of models in different model groups / function groups / configuration groups may be the same or different, and a model may belong to one or more different model groups / function groups / configuration groups): model activation / model deactivation / model switching, etc. For example, the first node has one supported related functional group UE_Functionality#1, and there are two models UE_Model#1 and UE_Model#2 in the functional group. The first node currently uses UE_Model#1. When the second node detects that the performance of the current model has degraded to a poor level, the second node instructs the first node through high-layer or physical layer signaling (e.g., RRC / MAC CE / DCI) to deactivate / switch UE_Model#1 to UE_Model#2 for subsequent reasoning. It should be noted that the management decision of the second node is at the granularity of the model, and the specific model used by the first node is not transparent to the second node (ie, the second node can make management decisions on the model).

[0214] For another example, when the second node detects that the performance of a model has degraded over a period of time, the second node performs at least one of the following operations on the models in the model group / functional group / configuration group of the first node (wherein a model group / functional group / configuration group may contain one or more models, the number of models in different model groups / functional groups / configuration groups may be the same or different, and a model may belong to one or more different model groups / functional groups / configuration groups): model activation / model deactivation / model switching, etc. For example, the first node supports two related functional groups UE_Functionality#1 and UE_Functionality#2, the functional group UE_Functionality#1 contains two models UE_Model#1 and UE_Model#2, and the functional group UE_Functionality#2 contains two models UE_Model#3 and UE_Model#4. The first node is currently using UE_Model#1 within UE_Functionality#1. When the second node detects that the performance of the current model has deteriorated to a poor level, the second node instructs the first node via higher-layer or physical-layer signaling (e.g., RRC / MAC CE / DCI) to deactivate UE_Model#1 or switch to UE_Model#3 within UE_Functionality#2 for subsequent reasoning. It should be noted that the second node's management decisions are made at the model granularity, and the specific model used by the first node is not transparent to the second node (i.e., the second node can make management decisions about the model).

[0215] For example, if a model is highly generalizable and can support multiple scenarios, configurations, or functions, it may belong to multiple different model groups, function groups, or configuration groups. If the model's performance under the current function / configuration is poor, the first node may not switch models when the second node activates or switches the model group, function group, or configuration group of the first node. For example, the first node supports two related function groups, UE_Functionality#1 and UE_Functionality#2, and model UE_Model#1 belongs to both function groups UE_Functionality#1 and UE_Functionality#2. The first node model is currently working under function / configuration UE_Functionality#1. When the second node detects that the performance of the current model has deteriorated to a poor level, the second node instructs the first node to deactivate / switch the model group / function group / configuration group UE_Functionality#1 to UE_Functionality#2 through high-level or physical layer signaling (for example: RRC / MAC CE / DCI). At this time, the terminal does not need to switch the model for subsequent reasoning, which can further reduce the delay of the management process (for example: activation / deactivation / switching operation delay).

[0216] In some embodiments, the method may further include the following F1.

[0217] F1. Receive fourth indication information sent by the second node.

[0218] In some embodiments, when the second node detects that the performance of the information processing unit has degraded over a period of time, or detects that the performance of the information processing unit is less than or equal to a preset performance threshold over a period of time, the second node sends fourth indication information to the first node. Accordingly, the first node receives the fourth indication information sent by the second node, where the fourth indication information is used for at least one of the following: activation of some information processing units, deactivation of some information processing units, or switching of some information processing units.

[0219] F2. In response to the fourth indication information, send decision information to the second node.

[0220] The decision information is used to represent the decision executed by the first node within a preset time period.

[0221] Taking the information processing unit as an example, when the second node detects that the model's performance has degraded over a period of time, the second node can instruct the first node to perform at least one of the following operations on a portion of the models: activation / deactivation / switching of the portion. The first node then reports the decision information within a preset time period to the second node, allowing the second node to have a certain understanding of the first node's decision and make subsequent decisions. It should be noted that the authorized portion of the model can be opaque to the second node (i.e., the second node can make management decisions on the model). For example, the first node has four related models, UE_Model#1 to UE_Model#4 (where the models can belong to the same or different model groups / function groups / configuration groups). The second node instructs the first node, through high-layer or physical layer signaling (e.g., RRC / MAC CE / DCI), to perform model activation / deactivation / switching only on UE_Model#1 and UE_Model#3. Since the first node makes the management operation decisions, this significantly reduces the latency and signaling overhead of the model management process. When the second node / first node detects that the model performance has degraded, the first node deactivates the current model accordingly and activates / switches to the authorized model for the next reasoning process. The first node needs to report decision information to the second node periodically or non-periodically within a preset time period (for example, switching 4 times within 10ms, identification information of the switching model, etc.). The second node makes the next management decision based on the reported decision information, such as: deactivating the model / model group, switching to another model / model group, updating the current model / model group, or falling back to the default method, etc.

[0222] In some embodiments, the method may further include the following G1.

[0223] G1. Receive fifth indication information sent by the second node.

[0224] The fifth indication information is used to indicate a switching duration threshold when the first node switches the information processing unit.

[0225] In this way, when the first node switches the information processing unit, it can switch the information processing unit within the switching time threshold indicated by the second node based on the fifth indication information, so that the information processing unit on the first node side can match the information processing unit on the second node side, thereby improving the matching accuracy between the information processing unit on the first node side and the information processing unit on the second node side, that is, improving the matching accuracy between the information processing unit on the terminal side and the information processing unit on the base station side, and preventing the performance of the information processing unit from degrading.

[0226] For example, the fifth indication information can be used to indicate multiple candidate switching duration thresholds. After receiving the fifth indication information, the first node can determine the target switching duration threshold from the candidate switching duration thresholds based on the fifth indication information, and then send the target switching duration threshold to the second node. In this way, when the first node switches the information processing unit, it can switch the information processing unit within the target switching duration threshold.

[0227] For another example, the fifth indication information may be used to indicate a maximum switching duration threshold, so that when the first node switches the information processing unit, the information processing unit may be switched within the maximum switching duration threshold.

[0228] It should be noted that, when the information processing unit is updated, a new identification information of the information processing unit may be allocated or the previous identification information may be used.

[0229] In some embodiments, the first node may also receive an authorization time from the second node. This authorization time specifies the duration during which the first node is permitted to operate in the autonomous model. During this configured duration, the first node is authorized to operate the information processing unit without having to request or obtain permission from the second node. The authorization time may be expressed in frames, subframes, slots, subslots, or symbols.

[0230] In some embodiments, within a configured time period, the first node may operate independently of the information processing unit without sending any feedback information to the second node.

[0231] In some embodiments, within a configured time length, the first node needs to send feedback information to the second node after performing an autonomous information processing unit operation. This feedback information may include one of the following: the number of information processing unit operations (such as the number of information processing unit switches, the number of information processing unit activations / deactivations, the number of information processing unit updates), the information processing unit identifier (such as the model identifier before / after the information processing unit switch, the identifier of the activated information processing unit, the identifier of the deactivated information processing unit).

[0232] In some embodiments, the method may further include the following H1.

[0233] H1. Receive sixth indication information sent by the second node.

[0234] In some embodiments, the second node may send sixth indication information to the first node, and accordingly, the first node receives the sixth indication information sent by the second node. The sixth indication information includes a threshold value or a threshold condition, and the sixth indication information is used to indicate that the target first information processing unit is determined based on the threshold value or the threshold condition.

[0235] That is to say, the second node can recommend / indicate a threshold value / threshold condition to the first node, so that the first node can select the corresponding target first information processing unit based on whether the performance evaluation index meets the threshold value. For example: when the second node recommends / instructs the first node to select the target first information processing unit, it must meet the information processing unit reasoning performance index SGCS (Squared Generalization Cosine Similarity)>0.9 before it can be used. It should be noted that the threshold value / threshold condition is also applicable to the above-mentioned embodiment of the first node calculating other performance evaluation indicators, which will not be repeated here.

[0236] In some embodiments, the method may further include the following I1.

[0237] I1. Send information processing unit status information to the second node.

[0238] The information processing unit status information includes at least one of the following:

[0239] the identification of the seventh information processing unit;

[0240] Instruction information used to indicate whether transmission of the eighth information processing unit is supported;

[0241] an identifier of the eighth information processing unit;

[0242] The time information is used to represent at least one of the following: the time required to switch to the eighth information processing unit, the time required to activate the eighth information processing unit, and the time required to deactivate the seventh information processing unit.

[0243] In some embodiments, the seventh information processing unit can be understood as the old information processing unit, and the eighth information processing unit can be understood as the new information processing unit. The identifier of the seventh information processing unit can be understood as the identifier of the old information processing unit that needs to be deactivated or switched, the indication information for indicating whether the transmission of the eighth information processing unit is supported can be understood as the indication information for indicating whether the eighth information processing unit exists, and the identifier of the eighth information processing unit can be understood as the identifier of the new information processing unit that is switched or activated or the identifier of the new information processing unit after the old information processing unit is updated. The time information can be understood as the time period for indicating how long it will take to switch to the new information processing unit or activate the new information processing unit or deactivate the old information processing unit. The time information can be a frame / subframe / time slot / sub-time slot / symbol, for example, the first node recommends in the report that the second node switch to the new information processing unit after a specific time slot.

[0244] Taking the information processing unit as an example, it should be understood that the reference signal resources, CSI reporting and other configurations corresponding to different first-node side models may be different, and how to perform resource / reporting configuration is completely controlled by the second node. Therefore, under normal circumstances, the second node should decide on the activation / deactivation / switching / selection of the first node side model and other model operations. However, in some cases, the first node may have a better prediction or understanding of the future working state of the model. For example, the model performance is closely related to the running load, computing resources and running trajectory, moving speed and surrounding environment perceived by the first node. If the first node can predict the future working conditions of the model based on the perception of the moving trajectory, surrounding environment or its own software / hardware environment, this information (i.e., the above-mentioned information processing unit status information) can be actively reported to the second node, thereby assisting the second node in pre-switching or pre-deactivation of the model.

[0245] In some embodiments, after I1, the method may further include the following I2.

[0246] I2. When the response information of the second node is monitored within a specific time window, the information processing unit is switched or deactivated after a preset time period.

[0247] For example, after the first node sends information processing unit status information to the second node, the first node needs to monitor a specific CORESET (control resource set) or a specific search space that carries the response information of the second node within a specific time window. When the response information of the second node is detected, the first node can actively perform information processing unit operations such as switching or deactivating the information processing unit after a preset time (specific time). Otherwise, the first node should not actively perform information processing unit operations such as switching or deactivating the information processing unit.

[0248] In some embodiments, as shown in FIG11 , an embodiment of the present disclosure further provides a communication method, which is applied to a second node. The second node may be the base station 21 shown in FIG2 above. The method may include the following S201 - S202 .

[0249] S201: Receive first signaling sent by a first node.

[0250] The first signaling includes an identifier of the first information processing unit.

[0251] S202: Send a second signaling to the first node.

[0252] The second signaling is used to determine the target first information processing unit.

[0253] For the description of the first signaling and the second signaling, reference may be made to the corresponding description in the embodiment shown in FIG3 , which will not be repeated here.

[0254] In some embodiments, the method further includes: receiving an identifier of a target first information processing unit or a performance evaluation indicator between the first information and the fourth information, sent by the first node. For a description of why the first node sends the identifier of the target first information processing unit or the performance evaluation indicator between the first information and the fourth information, reference can be made to the corresponding description in the embodiment shown in FIG. 3 above, and is not further elaborated here.

[0255] In some embodiments, the method further includes: sending first indication information to the first node, the first indication information being used to indicate the fifth information processing unit. For the description of the first indication information, reference may be made to the corresponding description in the above embodiment, which will not be repeated here.

[0256] In some embodiments, the method further includes: sending second indication information to the first node, the second indication information being used by the first node to select an information processing unit. For the description of the second indication information, reference may be made to the corresponding description in the above embodiment and will not be repeated here.

[0257] In some embodiments, the method further includes: sending third indication information to the first node. For a description of why the second node sends the third indication information to the first node, reference can be made to the corresponding description in the above embodiment, which will not be repeated here.

[0258] For example, sending the third indication information to the first node may be when the second node detects that the performance of the information processing unit has declined over a period of time, or detects that the performance of the information processing unit is less than or equal to a preset performance threshold over a period of time, and then sending the third indication information to the first node.

[0259] In some embodiments, the method further includes: sending fourth indication information to the first node. For a description of why the second node sends the fourth indication information to the first node, reference can be made to the corresponding description in the above embodiment, which will not be repeated here.

[0260] For example, sending the fourth indication information to the first node may be when the second node detects that the performance of the information processing unit has declined over a period of time, or detects that the performance of the information processing unit is less than or equal to a preset performance threshold over a period of time, and thus sending the fourth indication information to the first node.

[0261] In some embodiments, after sending the fourth indication information to the first node, the method may further include the following operation: receiving decision information sent by the first node. For the description of the decision information, reference may be made to the corresponding description in the above embodiment and will not be repeated here.

[0262] For example, after receiving the decision information, the second node can make the next management decision based on the decision information, such as: deactivating the information processing unit / information processing unit group, switching to another information processing unit / information processing unit group, updating the current information processing unit / information processing unit group, or falling back to the default method, etc.

[0263] In some embodiments, the method further includes: sending fifth indication information to the first node. For the description of the fifth indication information, reference may be made to the corresponding description in the above embodiments, which will not be repeated here.

[0264] In some embodiments, the method further includes: sending sixth indication information to the first node. For the description of the sixth indication information, reference may be made to the corresponding description in the above embodiments, which will not be repeated here.

[0265] In some embodiments, the second node may further send an authorization time to the first node. For the description of the authorization time, reference may be made to the corresponding description in the above embodiment, which will not be repeated here.

[0266] In some embodiments, the second node may also receive feedback information sent by the first node, and the feedback information may include one of the following: the number of information processing unit operations (such as the number of information processing unit switches, the number of information processing unit activations / deactivations, the number of information processing unit updates), the information processing unit identifier (such as the identifier before the information processing unit is switched / after the information processing unit is switched, the identifier of the activated information processing unit, the identifier of the deactivated information processing unit).

[0267] In some embodiments, the method further includes: receiving information processing unit status information sent by the first node. For the description of the information processing unit status information, reference can be made to the relevant description in the above embodiments, which will not be repeated here.

[0268] In the embodiments of the present disclosure, a variety of pre-operation mechanisms for information processing units are proposed, including activation, deactivation, selection, update, switching, etc. of information processing units. In this way, on the one hand, before performing an information processing unit operation, the second node can indicate multiple candidate information processing units in advance and start a feasibility test of the information processing units, and determine the final information processing unit operation based on the content reported by the first node (i.e., the first signaling). On the other hand, the first node can report the recommended information processing unit operation and the corresponding time information to the second node based on its own environmental perception to assist the second node in deciding the final information processing unit operation. In addition, the embodiments of the present disclosure propose a pre-authorization mechanism for information processing unit operation, that is, the second node provides the identification, authorization time, authorization content and other information of the authorized information processing unit to the first node, allowing the first node to perform autonomous information processing unit operation and information feedback. Through the communication method provided by the embodiments of the present disclosure, it is possible to achieve accurate indication of the information processing unit operation on the first node side by the second node, and reduce signaling overhead and processing delay, thereby improving the matching accuracy between the information processing unit on the first node side and the information processing unit on the second node side, and preventing the performance of the information processing unit from degrading.

[0269] The above mainly introduces the solution provided by the present disclosure from the perspective of the interaction between each node. It is understandable that each node, such as the first node and the second node, includes a hardware structure and / or software module corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0270] FIG12 is a schematic diagram showing the components of a communication device according to an embodiment of the present disclosure. As shown in FIG12 , the communication device 30 includes a sending unit 301 , a receiving unit 302 , and a processing unit 303 .

[0271] The communication device 30 may be the first node or a chip in the first node. When the communication device 30 is used to implement the function of the first node in the above embodiment, each unit is used to implement the following functions.

[0272] A sending unit 301 is configured to send a first signaling to a second node, where the first signaling includes an identifier of a first information processing unit;

[0273] A receiving unit 302 is configured to receive a second signaling sent by a second node, where the second signaling is used to determine a target first information processing unit;

[0274] The processing unit 303 is configured to determine a target first information processing unit from the first information processing units based on the second signaling.

[0275] In some embodiments, the first signaling also includes first information and second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of the target first information processing unit, and the target first information processing unit is determined by the second node from the first information processing unit based on the performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0276] In some embodiments, performance evaluation indicators include a first type of evaluation indicators, a second type of evaluation indicators, and a third type of evaluation indicators; the first type of evaluation indicators include evaluation indicators based on distance error and evaluation indicators based on similarity; the evaluation indicators based on distance error include at least one of the following: Euclidean distance, mean square error, normalized mean square error; the evaluation indicators based on similarity include at least one of the following: cosine similarity, generalized cosine similarity, cross entropy; the second type of evaluation indicators include evaluation indicators based on throughput and evaluation indicators based on channel quality; the evaluation indicators based on throughput include at least one of the following: system throughput, user throughput, average user throughput, 5% user throughput, spectrum efficiency; the evaluation indicators based on channel quality include at least one of the following: bit error rate, block error rate, assumed bit error rate, assumed block error rate, signal-to-noise ratio, signal-to-interference-plus-noise ratio, modulation and coding scheme MCS transmission level; the third type of evaluation indicators include evaluation indicators based on data distribution error, and the evaluation indicators based on data distribution error include at least one of the following: power spectrum, energy spectrum, amplitude spectrum, phase spectrum.

[0277] In some embodiments, the second information processing unit is an information processing unit that matches the first information processing unit.

[0278] In some embodiments, the processing unit 303 is configured to determine the target first information processing unit from the first information processing units based on an identifier of the target first information processing unit included in the second signaling.

[0279] In some embodiments, the first signaling also includes second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes third information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0280] In some embodiments, the processing unit 303 is configured to determine a performance evaluation index between the first information and the third information; and determine a target first information processing unit from the first information processing units based on the performance evaluation index between the first information and the third information.

[0281] In some embodiments, the processing unit 303 is configured to determine the first information processing unit that matches the second information processing unit corresponding to the optimal performance evaluation indicator as the target first information processing unit.

[0282] In some embodiments, the sending unit 301 is further configured to send an identifier of the target first information processing unit to the second node.

[0283] In some embodiments, the second signaling includes a third information processing unit, where the third information processing unit is an information processing unit that is determined by the second node based on an identifier of the first information processing unit and matches the first information processing unit.

[0284] In some embodiments, the processing unit 303 is used to process the first information based on the third information processing unit to obtain fourth information; determine the performance evaluation index between the first information and the fourth information; and determine the target first information processing unit from the first information processing unit based on the performance evaluation index between the first information and the fourth information.

[0285] In some embodiments, the sending unit 301 is further configured to send an identifier of the target first information processing unit or a performance evaluation index between the first information and the fourth information to the second node.

[0286] In some embodiments, the first signaling also includes performance indicator information, the performance indicator information includes a performance evaluation indicator between the first information and the fifth information, the fifth information is obtained by the first node after processing the second information based on the fourth information processing unit, and the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of the target first information processing unit, and the target first information processing unit is determined by the second node from the first information processing unit based on the performance indicator information.

[0287] In some embodiments, the processing unit 303 is configured to determine the target first information processing unit from the first information processing units based on an identifier of the target first information processing unit included in the second signaling.

[0288] In some embodiments, the first signaling also includes performance indicator information, which is a performance evaluation indicator between the first information and the fifth information, the fifth information is obtained by the first node after processing the second information based on the fourth information processing unit, and the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing unit based on the performance indicator information.

[0289] In some embodiments, the processing unit 303 is configured to determine a target first information processing unit from the first information processing units based on the attribute information of the first node and the identifiers of the candidate first information processing units.

[0290] In some embodiments, the sending unit 301 is further configured to send an identifier of the target first information processing unit to the second node.

[0291] In some embodiments, the first signaling also includes first information and second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing unit based on a performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0292] In some embodiments, the processing unit 303 is configured to determine a target first information processing unit from the first information processing units based on the attribute information of the first node and the identifiers of the candidate first information processing units.

[0293] In some embodiments, the sending unit 301 is further configured to send an identifier of the target first information processing unit to the second node.

[0294] In some embodiments, the identifier of the first information processing unit is a single-layer structure, and the identifier of the first information processing unit is indicated, allocated, or configured by the second node.

[0295] In some embodiments, the order in which the identifiers of the first information processing units are sorted is related to the order in which the first information processing units are generated.

[0296] In some embodiments, the identification of the first information processing unit is a multi-layer structure, and the identification of the first information processing unit is determined based on identification information of the data set corresponding to the first information processing unit and identification information of the first information processing unit.

[0297] In some embodiments, the receiving unit 302 is further configured to receive first indication information sent by the second node, where the first indication information is used to instruct the fifth information processing unit;

[0298] The processing unit 303 is further configured to determine, based on the first indication information, a sixth information processing unit that matches the fifth information processing unit.

[0299] In some embodiments, the sending unit 301 is further configured to send an identifier of the sixth information processing unit to the second node.

[0300] In some embodiments, the receiving unit 302 is further configured to receive second indication information sent by the second node, where the second indication information is used by the first node to select an information processing unit.

[0301] In some embodiments, the second indication information includes at least one of the following: structural information of an information processing unit that the first node should use; structural information of an information processing unit used by the second node.

[0302] In some embodiments, the second indication information further includes at least one of the following: information processing unit complexity of the information processing unit; computational complexity of the information processing unit; reasoning time range of the information processing unit; storage overhead range of the information processing unit.

[0303] In some embodiments, the receiving unit 302 is also used to receive third indication information sent by the second node, and the third indication information is used for at least one of the following: information processing unit group activation, information processing unit group deactivation, information processing unit group switching, information processing unit activation, information processing unit deactivation, information processing unit switching, information processing unit update, fallback to the default information processing mode, and information processing unit group update.

[0304] In some embodiments, the receiving unit 302 is further configured to receive fourth indication information sent by the second node, where the fourth indication information is used for at least one of the following: activation of part of the information processing unit, deactivation of part of the information processing unit, and switching of part of the information processing unit;

[0305] The sending unit 301 is further configured to send decision information to the second node in response to the fourth indication information, where the decision information is used to represent the decision executed by the first node within a preset time period.

[0306] In some embodiments, the receiving unit 302 is further configured to receive fifth indication information sent by the second node, where the fifth indication information is configured to indicate a switching duration threshold when the first node switches the information processing unit.

[0307] In some embodiments, the receiving unit 302 is further used to receive sixth indication information sent by the second node, the sixth indication information includes a threshold value or a threshold condition, and the sixth indication information is used to indicate the determination of the target first information processing unit based on the threshold value or the threshold condition.

[0308] In some embodiments, the sending unit 301 is also used to send information processing unit status information to the second node, and the information processing unit status information includes at least one of the following: an identifier of the seventh information processing unit; indication information for indicating whether the transmission of the eighth information processing unit is supported; an identifier of the eighth information processing unit; and time information, the time information is used to represent at least one of the following: the time required to switch to the eighth information processing unit, the time required to activate the eighth information processing unit, and the time required to deactivate the seventh information processing unit.

[0309] In some embodiments, the processing unit 303 is further configured to, when a response message from the second node is monitored within a specific time window, execute a switching or deactivation operation of the information processing unit after a preset time period.

[0310] FIG13 is a schematic diagram showing the composition of another communication device provided by an embodiment of the present disclosure. As shown in FIG13 , the communication device 40 includes a receiving unit 401 and a sending unit 402 .

[0311] The communication device 40 may be the second node or a chip in the second node. When the communication device 40 is used to implement the function of the second node in the above embodiment, each unit is used to implement the following functions.

[0312] A receiving unit 401 is configured to receive a first signaling sent by a first node, where the first signaling includes an identifier of a first information processing unit;

[0313] The sending unit 402 is configured to send a second signaling to the first node, where the second signaling is used to determine a target first information processing unit.

[0314] In some embodiments, the first signaling also includes first information and second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of the target first information processing unit, and the target first information processing unit is determined by the second node from the first information processing unit based on the performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0315] In some embodiments, performance evaluation indicators include a first type of evaluation indicators, a second type of evaluation indicators, and a third type of evaluation indicators; the first type of evaluation indicators include evaluation indicators based on distance error and evaluation indicators based on similarity; the evaluation indicators based on distance error include at least one of the following: Euclidean distance, mean square error, normalized mean square error; the evaluation indicators based on similarity include at least one of the following: cosine similarity, generalized cosine similarity, cross entropy; the second type of evaluation indicators include evaluation indicators based on throughput and evaluation indicators based on channel quality; the evaluation indicators based on throughput include at least one of the following: system throughput, user throughput, average user throughput, 5% user throughput, spectrum efficiency; the evaluation indicators based on channel quality include at least one of the following: bit error rate, block error rate, assumed bit error rate, assumed block error rate, signal-to-noise ratio, signal-to-interference-plus-noise ratio, modulation and coding scheme MCS transmission level; the third type of evaluation indicators include evaluation indicators based on data distribution error, and the evaluation indicators based on data distribution error include at least one of the following: power spectrum, energy spectrum, amplitude spectrum, phase spectrum.

[0316] In some embodiments, the second information processing unit is an information processing unit that matches the first information processing unit.

[0317] In some embodiments, the target first information processing unit is determined from the first information processing units based on an identifier of the target first information processing unit included in the second signaling.

[0318] In some embodiments, the first signaling also includes second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes third information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0319] In some embodiments, the target first information processing unit is determined from the first information processing units based on a performance evaluation index between the first information and the third information.

[0320] In some embodiments, the target first information processing unit is a first information processing unit that matches a second information processing unit corresponding to the optimal performance evaluation indicator.

[0321] In some embodiments, the receiving unit 401 is further configured to receive an identifier of a target first information processing unit sent by the first node.

[0322] In some embodiments, the second signaling includes a third information processing unit, where the third information processing unit is an information processing unit that is determined by the second node based on an identifier of the first information processing unit and matches the first information processing unit.

[0323] In some embodiments, the target first information processing unit is determined from the first information processing unit based on a performance evaluation index between the first information and fourth information, and the fourth information is obtained based on processing the first information by the third information processing unit.

[0324] In some embodiments, the receiving unit 401 is further configured to receive an identifier of a target first information processing unit sent by the first node or a performance evaluation indicator between the first information and the fourth information.

[0325] In some embodiments, the first signaling also includes performance indicator information, the performance indicator information includes a performance evaluation indicator between the first information and the fifth information, the fifth information is obtained by the first node after processing the second information based on the fourth information processing unit, and the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of the target first information processing unit, and the target first information processing unit is determined by the second node from the first information processing unit based on the performance indicator information.

[0326] In some embodiments, the target first information processing unit is determined in the first information processing unit based on an identifier of the target first information processing unit included in the second signaling.

[0327] In some embodiments, the first signaling also includes performance indicator information, the performance indicator information includes a performance evaluation indicator between the first information and the fifth information, the fifth information is obtained by the first node after processing the second information based on the fourth information processing unit, and the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing unit based on the performance indicator information.

[0328] In some embodiments, the target first information processing unit is determined from the first information processing units based on the attribute information of the first node and the identifiers of the candidate first information processing units.

[0329] In some embodiments, the receiving unit 401 is further configured to receive an identifier of a target first information processing unit sent by the first node.

[0330] In some embodiments, the first signaling also includes first information and second information, wherein the second information is obtained by the first node after processing the first information based on the first information processing unit; the second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing unit based on a performance evaluation index between the third information and the first information, and the third information is obtained by the second node after processing the second information based on the second information processing unit.

[0331] In some embodiments, the target first information processing unit is determined from the first information processing units based on the attribute information of the first node and the identifiers of the candidate first information processing units.

[0332] In some embodiments, the receiving unit 401 is further configured to receive an identifier of a target first information processing unit sent by the first node.

[0333] In some embodiments, the identifier of the first information processing unit is a single-layer structure, and the identifier of the first information processing unit is indicated, allocated, or configured by the second node.

[0334] In some embodiments, the order in which the identifiers of the first information processing units are sorted is related to the order in which the first information processing units are generated.

[0335] In some embodiments, the identification of the first information processing unit is a multi-layer structure, and the identification of the first information processing unit is determined based on identification information of the data set corresponding to the first information processing unit and identification information of the first information processing unit.

[0336] In some embodiments, the sending unit 402 is further configured to send first indication information to the first node, where the first indication information is used to indicate the fifth information processing unit.

[0337] In some embodiments, the sending unit 402 is further configured to send second indication information to the first node, where the second indication information is used by the first node to select an information processing unit.

[0338] In some embodiments, the second indication information includes at least one of the following: structural information of an information processing unit that the first node should use; structural information of an information processing unit used by the second node.

[0339] In some embodiments, the second indication information further includes at least one of the following: information processing unit complexity of the information processing unit; computational complexity of the information processing unit; reasoning time range of the information processing unit; storage overhead range of the information processing unit.

[0340] In some embodiments, the sending unit 402 is also used to send a third indication message to the first node, and the third indication message is used for at least one of the following: information processing unit group activation, information processing unit group deactivation, information processing unit group switching, information processing unit activation, information processing unit deactivation, information processing unit switching, information processing unit update, fallback to the default information processing mode, and information processing unit group update.

[0341] In some embodiments, the sending unit 402 is further configured to send fourth indication information to the first node, where the fourth indication information is used for at least one of the following: activation of some information processing units, deactivation of some information processing units, and switching of some information processing units;

[0342] The receiving unit 401 is further configured to receive decision information sent by the first node, where the decision information is used to represent the decision executed by the first node within a preset time period.

[0343] In some embodiments, the sending unit 402 is further configured to send fifth indication information to the first node, where the fifth indication information is configured to indicate a switching duration threshold when the first node switches the information processing unit.

[0344] In some embodiments, the receiving unit 401 is also used to receive information processing unit status information sent by the first node, and the information processing unit status information includes at least one of the following: an identifier of the seventh information processing unit; indication information for indicating whether the transmission of the eighth information processing unit is supported; an identifier of the eighth information processing unit; and time information, the time information is used to characterize at least one of the following: the time required to switch to the eighth information processing unit, the time required to activate the eighth information processing unit, and the time required to deactivate the seventh information processing unit.

[0345] If the various units in Figures 12 and 13 are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present disclosure. The storage medium for storing computer software products includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0346] In the case of implementing the functions of the above-mentioned integrated modules in hardware, an embodiment of the present disclosure provides a schematic structural diagram of a communication device, which may be the above-mentioned communication device 30 or communication device 40. As shown in Figure 14, the communication device 50 includes: a memory 501, a processor 502, a communication interface 503, and a bus 504.

[0347] The memory 501 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store dynamic information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0348] The processor 502 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein. The processor 502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. The processor 502 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein. The processor 502 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0349] The communication interface 503 is used to connect to other devices via a communication network, such as Ethernet, wireless access network, or wireless local area network (WLAN).

[0350] In some embodiments, the memory 501 may exist independently of the processor 502 and may be connected to the processor 502 via a bus 504 for storing instructions or program codes. When the processor 502 calls and executes the instructions or program codes stored in the memory 501, the communication method provided in the embodiments of the present disclosure can be implemented.

[0351] In some embodiments, the memory 501 may also be integrated with the processor 502 .

[0352] Bus 504 can be an Extended Industry Standard Architecture (EISA) bus, for example. Bus 504 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG14 shows bus 504 using only a single thick solid line. This does not imply that there is only one bus or only one type of bus.

[0353] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above models is used as an example. In actual applications, the above functions can be allocated to different models as needed, that is, the internal structure of the base station or terminal can be divided into different models to complete all or part of the functions described above.

[0354] The present disclosure also provides a computer-readable storage medium. All or part of the processes in the above-mentioned method embodiments can be completed by computer instructions to the relevant hardware, and the program can be stored in the above-mentioned computer-readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments. The computer-readable storage medium can be the internal storage unit of the first node or the second node of any of the above-mentioned embodiments, such as the hard disk or memory of the computer device. The above-mentioned computer-readable storage medium can also be an external storage device of the above-mentioned first node or the second node, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the above-mentioned first node or the second node. Further, the above-mentioned computer-readable storage medium can also include both the internal storage unit of the above-mentioned first node or the second node and an external storage device. The above-mentioned computer-readable storage medium is used to store the above-mentioned computer program and other programs and data required by the above-mentioned first node or the second node. The above-mentioned computer-readable storage medium can also be used to temporarily store data that has been output or is to be output. The above-mentioned computer-readable storage medium also includes a non-transitory computer-readable storage medium.

[0355] An embodiment of the present disclosure further provides a computer program product, which includes a computer program. When the computer program product is run on a computer, the computer is enabled to execute any one of the communication methods provided in the above embodiments.

[0356] Although the present disclosure is described herein in conjunction with various embodiments, in the process of implementing the disclosure for which protection is sought, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple components. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0357] Although the present disclosure has been described with reference to specific features and embodiments thereof, it will be apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely illustrative of the present disclosure as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is intended to encompass such modifications and variations if they fall within the scope of the claims of the present disclosure and their equivalents.

[0358] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or replacements within the technical scope disclosed in the present disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A communication method, applied to a first node, wherein, The method includes: Sending a first signaling to a second node, where the first signaling includes an identifier of a first information processing unit; Receiving a second signaling sent by the second node, where the second signaling is used to determine a target first information processing unit; Determining the target first information processing unit from the first information processing units based on the second signaling.

2. The method according to claim 1, wherein The first signaling further includes first information and second information, where the second information is obtained by the first node after processing the first information based on the first information processing unit; The second signaling includes an identifier of the target first information processing unit, where the target first information processing unit is determined by the second node from the first information processing units based on a performance evaluation index between third information and the first information, and the third information is obtained by the second node after processing the second information based on a second information processing unit.

3. The method according to claim 2, wherein, The performance evaluation index includes a first type of evaluation index, a second type of evaluation index, and a third type of evaluation index; The first type of evaluation index includes an evaluation index based on distance error and an evaluation index based on similarity; the evaluation index based on distance error includes at least one of the following: Euclidean distance, mean square error, normalized mean square error; the evaluation index based on similarity includes at least one of the following: cosine similarity, generalized cosine similarity, cross entropy; The second type of evaluation index includes an evaluation index based on throughput and an evaluation index based on channel quality; the evaluation index based on throughput includes at least one of the following: system throughput, user throughput, average user throughput, 5% user throughput, spectral efficiency; the evaluation index based on channel quality includes at least one of the following: bit error rate, block error rate, assumed bit error rate, assumed block error rate, signal-to-noise ratio, signal-to-interference-plus-noise ratio, modulation and coding scheme (MCS) transmission level; The third type of evaluation index includes an evaluation index based on data distribution error, and the evaluation index based on data distribution error includes at least one of the following: power spectrum, energy spectrum, amplitude spectrum, phase spectrum.

4. The method according to claim 2, wherein, The second information processing unit is an information processing unit that matches the first information processing unit.

5. The method according to claim 2, wherein The determining the target first information processing unit from the first information processing units based on the second signaling includes: Determining the target first information processing unit from the first information processing units based on the identifier of the target first information processing unit included in the second signaling.

6. The method according to claim 1, wherein The first signaling further includes second information, where the second information is obtained by the first node after processing first information based on the first information processing unit; The second signaling includes third information, where the third information is obtained by the second node after processing the second information based on the second information processing unit.

7. The method according to claim 6, wherein, The determining the target first information processing unit from the first information processing units based on the second signaling includes: Determining a performance evaluation index between the first information and the third information; Determine the target first information processing unit from the first information processing units based on the performance evaluation metric between the first information and the third information.

8. The method according to claim 7, wherein The determining the target first information processing unit from the first information processing units based on the performance evaluation metric between the first information and the third information includes: Determine the first information processing unit that matches the second information processing unit corresponding to the optimal performance evaluation metric as the target first information processing unit.

9. The method according to claim 7, further comprising: Send the identifier of the target first information processing unit to the second node.

10. The method according to claim 1, wherein, The second signaling includes a third information processing unit, and the third information processing unit is an information processing unit that matches the first information processing unit determined by the second node based on the identifier of the first information processing unit.

11. The method according to claim 10, wherein, The determining the target first information processing unit from the first information processing units based on the second signaling includes: Process the second information based on the third information processing unit to obtain fourth information, where the second information is obtained by the first node processing the first information based on the first information processing unit; Determine the performance evaluation metric between the first information and the fourth information; Determine the target first information processing unit from the first information processing units based on the performance evaluation metric between the first information and the fourth information.

12. The method according to claim 11, further comprising: Send the identifier of the target first information processing unit or the performance evaluation metric between the first information and the fourth information to the second node.

13. The method according to claim 1, wherein The first signaling further includes performance metric information, and the performance metric information includes the performance evaluation metric between the first information and the fifth information, where the fifth information is obtained by the first node processing the second information based on the fourth information processing unit, and the second information is obtained by the first node processing the first information based on the first information processing unit; The second signaling includes the identifier of the target first information processing unit, and the target first information processing unit is determined by the second node from the first information processing units based on the performance metric information.

14. The method according to claim 13, wherein, The determining the target first information processing unit from the first information processing units based on the second signaling includes: Determine the target first information processing unit from the first information processing units based on the identifier of the target first information processing unit included in the second signaling.

15. The method according to claim 1, wherein The first signaling further includes performance metric information, and the performance metric information includes the performance evaluation metric between the first information and the fifth information, where the fifth information is obtained by the first node processing the second information based on the fourth information processing unit, and the second information is obtained by the first node processing the first information based on the first information processing unit; The second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing units based on the performance metric information.

16. The method according to claim 15, wherein Determining the target first information processing unit from the first information processing units based on the second signaling includes: Determining the target first information processing unit from the first information processing units based on the attribute information of the first node and the identifier of the candidate first information processing unit.

17. The method according to claim 16, further comprising: Sending the identifier of the target first information processing unit to the second node.

18. The method according to claim 1, wherein, The first signaling further includes first information and second information, where the second information is obtained by the first node processing the first information based on the first information processing unit; The second signaling includes an identifier of a candidate first information processing unit, and the candidate first information processing unit is determined by the second node from the first information processing units based on a performance evaluation metric between third information and the first information, and the third information is obtained by the second node processing the second information based on a second information processing unit.

19. The method according to claim 18, wherein Determining the target first information processing unit from the first information processing units based on the second signaling includes: Determining the target first information processing unit from the first information processing units based on the attribute information of the first node and the identifier of the candidate first information processing unit.

20. The method according to claim 19, further comprising: Sending the identifier of the target first information processing unit to the second node.

21. The method according to claim 1, wherein The identifier of the first information processing unit is of a single-layer structure, and the identifier of the first information processing unit is indicated, assigned, or configured by the second node.

22. The method according to claim 1, wherein The sorting method of the identifier of the first information processing unit is related to the generation order of the first information processing unit.

23. The method according to claim 1, wherein, The identifier of the first information processing unit is of a multi-layer structure, and the identifier of the first information processing unit is determined based on the corresponding identifier set information of the first information processing unit and the identifier information of the first information processing unit.

24. The method according to claim 1, further comprising: Receiving first indication information sent by a second node, where the first indication information is used to indicate a fifth information processing unit; Determining a sixth information processing unit that matches the fifth information processing unit based on the first indication information.

25. The method according to claim 24, further comprising: Sending the identifier of the sixth information processing unit to the second node.

26. The method according to claim 1, further comprising: Receiving second indication information sent by a second node, where the second indication information is used for the first node to select an information processing unit.

27. The method according to claim 26, wherein, The second indication information includes at least one of the following: Structure information of the information processing unit that the first node should use; Structure information of the information processing unit used by the second node.

28. The method according to claim 27, wherein, The second indication information further includes at least one of the following: The information processing unit complexity of the information processing unit. Computational complexity of the information processing unit; Inference time range of the information processing unit; Storage overhead range of the information processing unit.

29. The method according to claim 1, further comprising: Receiving third indication information sent by a second node, where the third indication information is used for at least one of the following: Activating an information processing unit group, deactivating an information processing unit group, switching an information processing unit group, activating an information processing unit, deactivating an information processing unit, switching an information processing unit, updating an information processing unit, reverting to a default information processing mode, updating an information processing unit group.

30. The method according to claim 1, further comprising: Receiving fourth indication information sent by a second node, where the fourth indication information is used for at least one of the following: Activating some information processing units, deactivating some information processing units, switching some information processing units; In response to the fourth indication information, sending decision information to the second node, where the decision information is used to represent the decisions made by the first node within a preset time period.

31. The method according to claim 1, further comprising: Receiving fifth indication information sent by a second node, where the fifth indication information is used to indicate a switching duration threshold when the first node performs an information processing unit switch.

32. The method according to claim 1, further comprising: Receiving sixth indication information sent by a second node, where the sixth indication information includes a threshold value or a threshold condition, and the sixth indication information is used to indicate determining a target first information processing unit based on the threshold value or the threshold condition.

33. The method according to claim 1, further comprising: Sending information processing unit status information to the second node, where the information processing unit status information includes at least one of the following: Identifier of a seventh information processing unit; Indication information used to indicate whether transmission of an eighth information processing unit is supported; Identifier of the eighth information processing unit; Time information, where the time information is used to represent at least one of the following: Time required to switch to the eighth information processing unit, time required to activate the eighth information processing unit, time required to deactivate the seventh information processing unit.

34. The method according to claim 33, further comprising: In the case of hearing response information of the second node within a specific time window, performing an information processing unit switch or deactivation operation after a preset time period.

35. A communication method, applied to a second node, wherein, The method includes: Receiving a first signaling sent by a first node, where the first signaling includes an identifier of a first information processing unit; Sending a second signaling to the first node, where the second signaling is used to determine a target first information processing unit.

36. The method according to claim 35, wherein, The first signaling further includes second information, where the second information is obtained by the first node after processing first information based on the first information processing unit; The second signaling includes third information, where the third information is obtained by the second node after processing the second information based on a second information processing unit.

37. The method according to claim 35, wherein, The second signaling includes a third information processing unit, and the third information processing unit is an information processing unit determined by the second node based on the identifier of the first information processing unit and matching the first information processing unit.

38. A communication device, comprising a memory, a processor, and computer program instructions stored on the memory and executable on the processor, wherein, When the processor executes the computer program instructions, it implements the method according to any one of claims 1 to 34 or according to claims 35 to 37.

39. A computer-readable storage medium, wherein, The computer-readable storage medium includes computer program instructions; wherein, when the computer program instructions run on a computer, the computer is caused to execute the method according to any one of claims 1 to 34 or according to claims 35 to 37.

Images