Communication method, apparatus, readable storage medium, chip and program product

Abstract

The present application relates to the technical field of communications. Disclosed in the embodiments of the present application are a communication method, an apparatus, a readable storage medium, a chip and a program product, which can improve the revenue of models transmitted between terminals and network devices. The method comprises: acquiring first information, the first information comprising at least one of the following: a first adaptation parameter, or a second adaptation parameter, wherein the first adaptation parameter is an adaptation parameter of a preset model at a terminal, the second adaptation parameter is an adaptation parameter of the preset model at a network device, the adaptation parameters are parameters related to first performance of the preset model, and the first performance is used for representing the total revenue value of using the preset model; and when the first performance of the preset model satisfies a first preset condition, triggering transmission of the preset model, the first performance of the preset model being determined on the basis of the first information. The embodiments of the present application are applied to model transmission.

Description

Communication method and device, readable storage medium, chip and program product

[0001] The present application claims priority from the Chinese patent application No. 202411089148.7 filed on August 8, 2024, and entitled "Communication method and device, readable storage medium, chip and program product", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a communication method, device, readable storage medium, chip and program product. BACKGROUND

[0003] In a wireless communication network, as the diversification of service requirements and the enhancement of network functions, service implementation, network planning, configuration and resource scheduling also become increasingly complex. For example, service implementation, network planning, configuration and resource scheduling may involve modulation, coding, transmitters, receivers, multiple antenna technology, or positioning technology in a wireless communication system. Among them, the network device can implement schemes such as modulation and demodulation of signals, information encoding and decoding, channel state information (CSI) feedback, beam management (BM) or mobility management by performing related operations.

[0004] Currently, in the process of implementing the above schemes through a wireless communication network, the network device needs to manage the operations involved in the above schemes to configure corresponding resources. However, in the process of management, the model (or function, feature) needs to be activated or transmitted, and there is a problem of low model benefit when the current activation or transmission is performed, resulting in high resources required for model management. SUMMARY

[0005] To solve the above technical problems, the embodiments of the present application provide a communication method, device, readable storage medium, chip and program product, which can improve the benefit of the model transmitted between the terminal and the network device, and reduce the resources required for model management.

[0006] In a first aspect, a communication method is provided. The method can be performed by a first node, or by a component of the first node, such as a processor, a chip, or a chip system of the first node, or by a logic module or software that can implement all or part of the function of the first node. The method is described below by way of example with reference to the first node. The communication method comprises: obtaining first information; the first information comprises at least one of: a first adaptation parameter or a second adaptation parameter, wherein the first adaptation parameter is an adaptation parameter of a preset model and a terminal, and the second adaptation parameter is an adaptation parameter of the preset model and a network device; the adaptation parameter is a parameter related to a first performance of the preset model; the first performance is used to represent a total revenue value of the preset model; and in a case where the first performance of the preset model meets a first preset condition, triggering transmission or triggering activation of the preset model, wherein the first performance of the preset model is determined based on the first information.

[0007] Based on the communication method provided in the present application, the first node determines the total revenue value of the preset model according to the adaptation parameter of the preset model and the terminal and / or the adaptation parameter of the preset model and the network device, and triggers transmission or activation of the preset model in a case where the total revenue value of the preset model meets a preset condition. In this way, the model with a higher revenue value can be transmitted or activated between the terminal and the network device, thereby improving the revenue of the model transmitted or activated between the terminal and the network device, and reducing the resources required for model management.

[0008] In a possible implementation, the first adaptation parameter is used to represent at least one of: a first time length related to the preset model and the terminal; a second performance of the preset model, the second performance being used to represent a unit revenue of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance being used to represent a total revenue value of the preset model related to the terminal.

[0009] Based on this, the first adaptation parameter can represent at least one of a first time length, a unit revenue, a transmission delay, or a total revenue of the preset model related to the terminal; based on these parameters, the first node can determine the revenue value of the preset model related to the adaptation parameter of the terminal.

[0010] In a possible implementation, the first adaptation parameter comprises at least one of: a transmission delay of the preset model between the terminal and the network device; a start time related to the preset model and the terminal; an end time related to the preset model and the terminal; a duration related to the preset model and the terminal; a second performance of the preset model, the second performance being used to represent a unit revenue of the preset model determined by the terminal; or a third performance of the preset model determined by the terminal; the third performance being used to represent a total revenue value of the preset model related to the terminal.

[0011] Based on this, since the first adaptation parameters are all terminal-related parameters, the first node can determine the yield value of the preset model related to the adaptation parameters of the terminal based on the first adaptation parameters, so that the total yield of the determined model can conform to the adaptation parameters of the terminal.

[0012] In a possible implementation, the second adaptation parameter is used to represent at least one of the following: a second duration of the preset model related to the network device; a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit yield of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total yield value of the preset model related to the network device.

[0013] Based on this, the first adaptation parameter can represent at least one of the following: a second duration related to the yield value of the preset model at the network device, a unit yield, a transmission delay, or a total yield of the preset model at the network device; based on these parameters, the first node can determine the yield value of the preset model related to the adaptation parameters of the network device.

[0014] In a possible implementation, the second adaptation parameter includes at least one of the following: a transmission delay of the preset model between the terminal and the network device; a start time of the preset model related to the network device; an end time of the preset model related to the network device; a duration of the preset model related to the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit yield of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total yield value of the preset model related to the network device.

[0015] Based on this, since the second adaptation parameters are all network device-related parameters, the first node can determine the yield value of the preset model related to the adaptation parameters of the network device based on the second adaptation parameters, so that the total yield of the determined model can conform to the adaptation parameters of the network device.

[0016] In a possible implementation, the first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; and the second adaptation parameters are used to represent a second time length related to the network device of the preset model. The first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model; the sixth performance is a second performance and / or a third performance in the first adaptation parameters and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model.

[0017] Based on this, the first node can determine the total benefit of the preset model based on the unit benefit of the preset model and the applicable time length of the preset model. The first node can determine the applicable time length of the preset model according to the first time length related to the terminal of the preset model and the second time length related to the network device of the preset model.

[0018] In a possible implementation, the first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; and the second adaptation parameters are used to represent a second time length related to the network device of the preset model. The first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model, and a time delay of the terminal and the network device in transmitting the preset model; the sixth performance is a second performance and / or a third performance in the first adaptation parameters and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model. The time delay of the terminal and the network device in transmitting the preset model is a time delay in the first adaptation parameters or a time delay in the second adaptation parameters.

[0019] Based on this, the first node can determine the total revenue of the preset model based on the unit revenue of the preset model and the applicable duration of the preset model. Wherein, the first node can determine the applicable duration of the preset model according to the first duration related to the terminal of the preset model, the second duration related to the network device of the preset model, and the transmission delay of the preset model between the terminal and the network device.

[0020] In a possible implementation, the transmission delay of the preset model between the terminal and the network device is determined based on the model size of the transmitted preset model and the transmission performance between the terminal and the network device.

[0021] Based on this, the first node can determine the transmission delay of the transmitted preset model based on the model size of the preset model and the transmission performance of the network.

[0022] In a possible implementation, the preset model corresponds to at least two quantization manners; the model size and the model performance of the preset model are different in different quantization manners; wherein, the adaptation parameters include adaptation parameters corresponding to different quantization manners in at least two quantization manners; in the case that the first performance of the preset model meets the first preset condition, triggering the transmission or triggering the activation of the preset model includes: in the case that the first performance of the preset model corresponding to the first quantization manner meets the first preset condition, triggering the transmission or triggering the activation of the preset model corresponding to the first quantization manner, wherein, the first quantization manner is a quantization manner meeting the second preset condition in the at least two quantization manners.

[0023] Based on this, in the case that the preset model corresponds to at least two quantization manners, the first node can select a first quantization manner from the at least two quantization manners, which can make the preset model meet the second preset condition, and quantize the preset model based on the first quantization manner and then transmit, so that the network device sends the preset model to the terminal, which meets the demand in model size and model performance.

[0024] In a possible implementation, the second preset condition includes at least one of the following: the first performance determined based on the sixth performance of the preset model and the model size is maximum; in the case that the model size of the preset model is less than or equal to a first threshold, the sixth performance of the preset model is maximum; in the case that the sixth performance of the preset model is greater than or equal to a second threshold, the model size of the preset model is minimum; the first performance of the preset model is greater than or equal to a preset threshold; wherein, the sixth performance is the second performance and / or the third performance in the first adaptation parameter, and / or the fourth performance and / or the fifth performance in the second adaptation parameter; the second performance is used to represent the unit revenue of the preset model determined by the terminal; the third performance is used to represent the total revenue value of the preset model related to the terminal; the fourth performance is used to represent the unit revenue of the preset model determined by the network device; the fifth performance is used to represent the total revenue value of the preset model related to the network device.

[0025] Based on this, when the second preset condition is that the first performance determined based on the sixth performance of the preset model and the model size is maximum, the first node can select a quantization manner that maximizes the benefit value of the preset model to quantize the preset model.

[0026] In a case where the second preset condition is that the model size of the preset model is less than or equal to a first threshold value, and the sixth performance of the preset model is maximum, the first node can select a quantization manner with maximum benefit from among quantization manners that meet the requirement of transmission resources (such as transmission delay) required for transmission.

[0027] In a case where the second preset condition is that the sixth performance of the preset model is greater than or equal to a second threshold value, and the model size of the preset model is minimum, the first node can select a quantization manner with minimum transmission resources (or transmission delay) required for transmission from among quantization manners that meet the requirement of model benefit.

[0028] In a case where the second preset condition is that the first performance of the preset model is greater than or equal to a preset threshold value, the first node can select a quantization manner that meets the requirement of total benefit of the preset model to quantize the preset model.

[0029] In a possible implementation, in a case where the first node is a terminal, obtaining the first information includes: determining a first adaptation parameter related to the preset model from adaptation parameters stored by the terminal; and / or, receiving first indication information from a network device; the first indication information is used to indicate a second adaptation parameter.

[0030] Based on this, in a case where the first node is a terminal, the terminal can determine the first adaptation parameter from adaptation parameters stored by the terminal, and / or the terminal can determine the second adaptation parameter based on an indication of a network device.

[0031] In a possible implementation, in a case where the first node is a terminal, triggering transmission of the preset model includes: sending second indication information to a network device, the second indication information being used to instruct the network device to send the preset model to the terminal.

[0032] Based on this, the terminal can trigger the network device to transmit the preset model to the terminal by sending indication information to the network device.

[0033] In a possible implementation, in a case where the first node is a terminal, the triggering activation of the preset model includes: sending fourth indication information to the network device, the fourth indication information being used to request or instruct the network device to activate the preset model.

[0034] Based on this, the terminal can trigger activation of the preset model by sending indication information to the network device.

[0035] In a possible implementation, in the case where the first node is a network device, the obtaining the first information comprises: determining, from the stored adaptation parameters of the network device, a second adaptation parameter related to the preset model; and / or, receiving third indication information from the terminal; the third indication information is used to indicate the first adaptation parameter.

[0036] Based on this, in the case where the first node is a network device, the network device can determine the second adaptation parameter from the stored adaptation parameters of the network device, and / or the network device can determine the first adaptation parameter based on the indication of the terminal.

[0037] In a possible implementation, in the case where the first node is a network device, the triggering the transmission of the preset model comprises: sending the preset model to the terminal, or requesting the preset model to be sent to the terminal.

[0038] Based on this, the manner in which the network device triggers the transmission of the preset model is to directly send the preset model to the terminal, or to request whether the preset model can be sent to the terminal.

[0039] In a possible implementation, in the case where the first node is a network device, the triggering the activation of the preset model comprises: instructing the terminal to activate the preset model, or requesting the terminal to activate the preset model.

[0040] Based on this, the manner in which the network device triggers the transmission of the preset model is to directly send the preset model to the terminal, or to request whether the preset model can be sent to the terminal.

[0041] In a possible implementation, the first performance of the preset model comprises the performance of one or more evaluation indexes in a plurality of evaluation indexes of the preset model.

[0042] Based on this, the first node can determine the first performance of the preset model based on the performance of one or more evaluation indexes in a plurality of evaluation indexes of the preset model.

[0043] In a possible implementation, the one or more evaluation indexes are evaluation indexes selected from the plurality of evaluation indexes based on the network parameters of the network device.

[0044] Based on this, the first node can select the evaluation indexes conforming to the network parameters of the network device from the plurality of evaluation indexes.

[0045] In a possible implementation, the performance of each evaluation index in the one or more evaluation indexes comprises the performance of each evaluation index in at least two quantization manners.

[0046] Based on this, the first node can further determine the performance of various evaluation indexes in each quantization manner based on different quantization manners.

[0047] It should be understood that the model involved in the embodiments of the present application can be described as a function (such as an artificial intelligence (AI) function or a machine learning (ML) function), a feature or an algorithm, and the model includes an AI model or an ML model, etc. For the sake of simplicity of description, the model / function / feature is referred to as a model in the present application, that is, the model in the present application can be replaced by a model / function / feature.

[0048] It should be noted that the model transmission (or transmitting a model) and the like described in the embodiments of the present application can be replaced by model activation. In other words, the process of model transmission can also be understood as the process of model activation, which is not limited in the present application.

[0049] In a second aspect, a communication apparatus is provided for implementing the methods described above. The communication apparatus can be the first node in the first aspect, or a device including the first node, or a device included in the first node, such as a chip. The communication apparatus includes modules, units, or means corresponding to the methods described above, which can be implemented by hardware, software, or by executing corresponding software with hardware. The hardware or software includes one or more modules or units corresponding to the functions described above.

[0050] In some possible designs, the communication apparatus can include a processing module and a transceiver module. The transceiver module, which can also be referred to as a transceiver unit, is configured to implement the functions of transmitting and / or receiving in any of the aspects and any possible implementation manners thereof. The transceiver module can be composed of a transceiver circuit, a transceiver, a transceiver, or a communication interface. The processing module can be configured to implement the processing functions in any of the aspects and any possible implementation manners thereof.

[0051] In some possible designs, the transceiver module includes a transmitting module and a receiving module, which are configured to implement the functions of transmitting and receiving in any of the aspects and any possible implementation manners thereof.

[0052] In a third aspect, a communication apparatus is provided, which includes at least one processor and a memory. The processor is configured to execute computer programs or instructions stored in the memory, so that the communication apparatus performs the method of any of the aspects described above. The memory can be coupled with the processor, or can be independent of the processor. The communication apparatus can be the first node in the first aspect, or a device including the first node, or a device included in the first node, such as a chip. In some possible designs, the communication apparatus includes a memory, which is configured to store necessary program instructions and data.

[0053] In a possible implementation, the processor includes a logic circuit, and an input interface and / or an output interface. The output interface is configured to perform the sending action in the corresponding method, and the input interface is configured to perform the receiving action in the corresponding method.

[0054] In a possible implementation, the communication apparatus further includes a communication interface and a communication bus, and the processor, the memory and the communication interface are connected through the communication bus. The communication interface is configured to perform the transceiving action in the corresponding method. The communication interface can also be referred to as a transceiver. Optionally, the communication interface includes a transmitter and a receiver, in which case, the transmitter is configured to perform the sending action in the corresponding method, and the receiver is configured to perform the receiving action in the corresponding method.

[0055] In some possible designs, the communication apparatus can be a chip or a chip system. When the communication apparatus is a chip system, it can be composed of a chip or include a chip and other discrete devices. When the communication apparatus is a chip, the sending action / function described above can be understood as output, and the receiving action / function described above can be understood as input.

[0056] In a fourth aspect, a chip is provided, which includes a processor configured to implement the functions involved in any of the aspects or any of the implementation manners thereof.

[0057] In some possible designs, the chip includes a memory configured to store necessary program instructions and data.

[0058] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions, and when the computer program or instructions are executed on a communication apparatus, the communication apparatus is enabled to perform the method in any of the aspects or any of the implementation manners thereof.

[0059] In a sixth aspect, a computer program product is provided, which includes instructions, and when the computer program product is executed on a communication apparatus, the communication apparatus is enabled to perform the method in any of the aspects or any of the implementation manners thereof.

[0060] The technical effects brought by any of the implementation manners of the second to sixth aspects can refer to the technical effects brought by the corresponding implementation manners of the first aspect, which will not be described here.

[0061] It should be noted that the various possible implementation manners of any one of the aspects described above can be combined as long as the solutions are not contradictory. BRIEF DESCRIPTION OF DRAWINGS

[0062] FIG. 1 is a flow diagram of model activation / configuration model between a terminal and a network device provided in the present application;

[0063] FIG. 2 is a flow diagram illustrating a process of activating / configuring a model between a terminal and a network device in a scenario where the network device is a CU-DU split node according to an embodiment of the present disclosure;

[0064] FIG. 3 is a schematic diagram of a system architecture of a communication system according to an embodiment of the present disclosure;

[0065] FIG. 4 is a schematic diagram of a system architecture of a communication system according to an embodiment of the present disclosure;

[0066] FIG. 5 is a schematic diagram of a structure of an O-RAN system according to an embodiment of the present disclosure;

[0067] FIG. 6 is a schematic diagram of a system architecture of a communication system according to an embodiment of the present disclosure;

[0068] FIG. 7 is a schematic diagram of a structure of a communication apparatus according to an embodiment of the present disclosure;

[0069] FIG. 8 is a flow diagram illustrating a communication method according to an embodiment of the present disclosure;

[0070] FIG. 9 is a schematic diagram of a unit reward, a transmission delay, a first time length, and a second time length of a preset model according to an embodiment of the present disclosure;

[0071] FIG. 10 is a flow diagram illustrating a communication method according to an embodiment of the present disclosure;

[0072] FIG. 11 is a flow diagram illustrating a communication method according to an embodiment of the present disclosure;

[0073] FIG. 12 is a schematic diagram of model sizes and model performances of two quantization manners of a preset model and a delay corresponding to each of the two quantization manners according to an embodiment of the present disclosure;

[0074] FIG. 13 is a schematic diagram of a structure of a communication apparatus according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0075] To facilitate understanding of the technical solutions of the embodiments of the present disclosure, a brief introduction to the related art of the present disclosure is given as follows.

[0076] 1. Artificial intelligence / machine learning model

[0077] In a wireless communication network, as the diversification of service demands and the enhancement of network functions, service implementation, network planning, configuration, and resource scheduling also become increasingly complex. For example, service implementation, network planning, configuration, and resource scheduling can involve modulation, coding, transmitters, receivers, multi-antenna technology, or positioning technology in a wireless communication system. Among them, the network device can implement, for example, signal modulation and demodulation, information encoding and decoding, CSI feedback, BM, or mobility management, etc. by performing relevant operations.

[0078] Exemplarily, the communication device can execute the technical solutions in the above-mentioned various service scenarios through a traditional algorithm, or can apply artificial intelligence (AI) / machine learning (ML) technology to the technical solutions in the above-mentioned service scenarios. The AI / ML technology refers to model training through related data, so as to use the trained model to achieve a specific purpose. The purpose that can be achieved by the model is related to the data used during training.

[0079] For example, in the service scenario of AI / ML-based CSI feedback, the service scenario of AI / ML-based CSI feedback includes AI / ML-based CSI compression and AI / ML-based CSI prediction. The AI / ML-based CSI compression refers to that the terminal compresses the downlink CSI (measured by the terminal) through the AI / ML technology. Then, the terminal can send the compressed CSI to the network device through the air interface. The network device restores (decompresses) the CSI based on AI / ML. Compared with the traditional compression algorithm, the AI / ML-based compression algorithm has higher compression rate and better CSI restoration capability. Therefore, the terminal can feed back more CSI through smaller air interface overhead, so that the network device can more accurately perform downlink precoding. The AI / ML-based CSI prediction refers to that the network device predicts the downlink CSI at a future time based on the downlink CSI at a current / historical time through the AI / ML technology, and then performs precoding according to the predicted CSI. The CSI predicted by this scheme is more matched to the channel state when the downlink data is scheduled, so it can overcome the problem of channel aging and achieve more accurate downlink precoding. The training data of the model involved in the service scenario of AI / ML-based CSI feedback includes CSI.

[0080] Taking a business scenario of BM based on AI / ML as an example, the network device and the terminal device can predict the sending beam and / or the receiving beam through AI / ML technology, for example, infer a small amount of beam scanning results through AI / ML to obtain an optimal beam. Compared with the traditional scheme in which a large number of beams need to be scanned to obtain an optimal beam, the beam prediction based on AI / ML can reduce the processing overhead of beam scanning. For example, the terminal can scan a small amount of beams, and then predict an optimal beam from a large number of candidate beams through an AI / ML model, so it is not necessary to scan all candidate beams, thereby reducing the overhead. The small amount of beams scanned by the terminal can be sparse beams or wide beams, and the candidate beams can be dense beams or narrow beams. The terminal can input the beam information scanned at the current / historical moment into the model to predict the optimal beam at the future moment, so it is not necessary to perform beam scanning again at the future moment, thereby improving the beam scanning efficiency. The training data of the model involved in the business scenario of BM based on AI / ML includes beam information, for example, the beam information can be beam ID and / or beam corresponding reference signal receiving power (RSRP) and other beam related information.

[0081] Taking a business scenario of positioning based on AI / ML as an example, the communication device inputs channel information into an AL / ML model to infer an intermediate parameter required for positioning, or directly obtains a position coordinate value. Compared with the traditional positioning algorithm, the intermediate parameter or the position coordinate value obtained based on AL / ML is more accurate. The training data of the model involved in the business scenario of positioning based on AL / ML includes channel information and / or position information, and the channel information includes power information, phase information, time delay information, distance information, speed information, channel scattering information, and line of sight (LOS) / non line of sight (NLOS) information and other channel related information.

[0082] 2. Model transmission

[0083] In the related art, if the model used by the first node is stored in the second node, the first node needs to obtain the model from the second node when using the model. The first node is a terminal or a network device; the second node is a device opposite to the first node. For example, when the first node is a terminal, the second node is a network device; when the first node is a network device, the second node is a terminal.

[0084] Exemplarily, taking an example of a first node being a terminal and a second node being a network device, a model used by the terminal is stored in the network device. When the terminal needs to use the model, the terminal triggers transmission of the model, such as the terminal sending a model obtaining request to the network device, so that the network device directly transmits the model to the terminal. Alternatively, when the terminal needs to use the model, the network device triggers transmission of the model, such as the network device actively sending the model to the terminal. Optionally, the model can also be stored in a third-party server, and the network device transmits the model to the terminal after obtaining the model from the third-party server.

[0085] The current manner of triggering transmission of the model includes active triggering and passive triggering. The process of active triggering includes: the first node predicts the current scenario of the terminal, determines that the scenario of the terminal will switch to scenario 1 at a T time point after the current time, and determines that the terminal needs to use model A corresponding to scenario 1, and then the first node triggers transmission of model A to the terminal before the T time point. The process of passive triggering includes: the first node determines the current scenario of the terminal, and if it is determined that the terminal is currently in scenario 1, triggers transmission of model A to the terminal.

[0086] In the case where the first node is the terminal, the process of triggering transmission of model A to the terminal includes: the terminal sends a model A transmission request to the network device to request the network device to send model A to the terminal. In the case where the first node is the network device, the process of triggering transmission of model A to the terminal includes: the network device directly sends model A to the terminal, or the network device requests the terminal to send model A. Optionally, in the case where the model is stored in a third-party server, the network device requests the third-party server to obtain model A before sending model A to the terminal.

[0087] Taking an example of the terminal requesting the network device to transmit the model, the process of activating / configuring the model between the terminal and the network device can be implemented through the steps shown in FIG. 1.

[0088] Step 101: The terminal sends model indication information to the network device. Correspondingly, the network device receives the model indication information from the terminal.

[0089] The model indication information is used to indicate a model that can be supported or used or applicable to the terminal. The model indication information can be supported model indication information, and can also be availability indication information of the model or applicability indication information of the model.

[0090] Exemplarily, the supported model indication information can be supported model indication information.

[0091] Step 102, the network device performs model selection based on the model indication information.

[0092] For example, the network device can select a model that is supported, available or applicable to the terminal from the model meta information.

[0093] Step 103, the network device sends model configuration information to the terminal. Correspondingly, the terminal receives the model configuration information from the network device.

[0094] The model configuration information includes configuration parameters of the selected AI / ML model.

[0095] As an example, the model configuration information can be RRC configuration information or RRC reconfiguration information. Then, the terminal and the network device can perform model transmission / delivery operation.

[0096] Step 104, the terminal sends model transmission / delivery waiting indication information to the network device. Correspondingly, the network device receives the model transmission / delivery waiting indication information from the terminal.

[0097] As an example, the model transmission / delivery waiting indication information can be RRC configuration complete information or RRC reconfiguration complete information. Step 104 is an optional step, i.e., step 104 can not be performed, and the terminal can not send model transmission / delivery waiting indication information.

[0098] Step 105, the terminal and the network device perform model transmission / delivery operation.

[0099] As an example, if the model configured by the terminal is not available, the required model can be obtained through the model transmission / delivery operation.

[0100] Step 106, the terminal sends model transmission / delivery completion indication information to the network device. Correspondingly, the network device receives the model transmission / delivery completion indication information from the terminal.

[0101] As an example, the model transmission / delivery completion indication information can be RRC configuration complete information or RRC reconfiguration complete information. Step 106 is an optional step, i.e., step 106 can not be performed, and the terminal can not send model transmission / delivery completion indication information.

[0102] Further, as shown in FIG. 2, in the case of a node in which a network device is a central unit (CU) and a distributed unit (DU) is separated, the network device includes a CU-control plane (CP), a CU-machine learning plane (MLP), and a DU. Taking an example of a terminal requesting a transmission model from the network device, the process of model activation / configuration of a model between the terminal and the network device can be implemented through the steps as shown in FIG. 2.

[0103] Step 201, the terminal sends terminal capability information to the CU-CP. Correspondingly, the CU-CP receives the terminal capability information from the terminal.

[0104] As an example, the terminal capability information is UE capability information.

[0105] Step 202, the CU-CP determines whether to use an ML function.

[0106] As an example, the ML function can also be referred to as ML functionality.

[0107] Step 203, in the case where the CU-CP determines to use the ML function, the CU-CP sends a terminal context setup request message to the CU-MLP. Correspondingly, the CU-MLP receives the terminal context setup request message from the CU-CP.

[0108] As an example, the terminal context setup request message is a UE context setup request.

[0109] Step 204, the CU-MLP sends a model setup request message to the DU. Correspondingly, the DU receives the model setup request message from the CU-MLP.

[0110] As an example, the model setup request message is a ML model setup request.

[0111] Step 205, the DU sends a model setup response message to the CU-MLP. Correspondingly, the CU-MLP receives the model setup response message from the DU.

[0112] As an example, the model setup response message is a UE context setup response.

[0113] Step 206, the CU-MLP sends a terminal context setup response message to the CU-CP. Correspondingly, the CU-CP receives the terminal context setup response message from the CU-MLP.

[0114] As an example, the terminal context setup response message is: UE context setup response.

[0115] Step 207, the CU-CP sends an RRC reconfiguration request message to the terminal. Correspondingly, the terminal receives the RRC reconfiguration request message from the CU-CP.

[0116] Optionally, the RRC reconfiguration request includes an ML configuration message.

[0117] As an example, the RRC reconfiguration request message is: RRC reconfiguration request.

[0118] The ML configuration message is: ML configuration information.

[0119] Step 208, the terminal sends an RRC reconfiguration complete message to the CU-CP. Correspondingly, the CU-CP receives the reconfiguration complete message from the terminal.

[0120] As an example, the RRC reconfiguration complete message is: RRC reconfiguration complete.

[0121] Step 209, the terminal downloads the ML model.

[0122] Step 210, the terminal sends an ML model ready for use message to the CU-CP. Correspondingly, the CU-CP receives the ML model ready for use message from the terminal.

[0123] As an example, the ML model ready for use message is: ML model ready for use.

[0124] Step 211, the CU-CP sends an ML model ready for use message to the CU-MLP. Correspondingly, the CU-MLP receives the ML model ready for use message from the CU-CP.

[0125] Step 212, the CU-CP sends an ML model activation message to the terminal. Correspondingly, the terminal receives the ML model activation message from the CU-CP.

[0126] As an example, the ML model activation message is: Activate ML model.

[0127] The above describes the model transmission process related to the embodiments of the application.

[0128] 3. Model activation

[0129] Model activation refers to that one or more models have been activated and executed. For example, the model starts to perform inference according to the model input to obtain the model output within an expected time. Model activation can also be referred to as model starting to run, or model starting to perform inference, or model starting to execute, or configuring the model.

[0130] In the related art, if the model used by the first node needs to determine whether to activate the model or exchange information about whether the model has been activated with the second node. For example, when the first node is a terminal, the second node is a network device; when the first node is a network device, the first node is a terminal.

[0131] For example, when the first node is a terminal and the second node is a network device. When the terminal needs to activate the model, the terminal triggers to activate the model, for example, the terminal sends a model activation request to the network device to make the network device confirm to activate the model. Alternatively, when the terminal needs to activate the model, the terminal activates the model and reports the information that the model has been activated to the network device.

[0132] For example, when the first node is a network device and the second node is a terminal. When the network device needs to activate the model, the network device triggers to activate the model, for example, the network device sends a model activation request to the terminal to make the terminal confirm to activate the model. Alternatively, when the network device needs to activate the model, the network device instructs the terminal to activate the model.

[0133] It should be noted that the steps related to model transmission in the embodiments of the application can also be replaced by model activation, which is not limited in the application.

[0134] 4. Model benefit

[0135] Model benefit refers to the benefit brought by the model in the process of using the model by the terminal (which can also be a network device, and the application mainly takes the terminal as an example for description).

[0136] In the related art, the total revenue of a model is related to the model performance (also referred to as the unit revenue of the model) and the applicable duration of the model. For example, the total revenue of the model = the unit revenue of the model x the applicable duration of the model. The applicable duration of the model is related to the generalization of the model. The generalization of the model refers to the degree of adaptation of the model to the conditions of the terminal (internal conditions of the terminal, such as power, computing power, storage space, etc., and / or external conditions of the terminal, such as channel conditions in which the terminal is located) and / or the conditions of the network device (performance expectation of the network device for the model, configuration of the network device, such as RRC configuration, or internal implementation of the network device, such as antenna deployment).

[0137] The degree of adaptation of the model to the terminal is generally related to the use scenarios of the terminal. The use scenarios of the terminal may, for example, include the moving speed of the terminal or the power of the terminal, etc. As an example, assuming that model A is adapted to a first scenario and a second scenario of the terminal, the terminal can take the duration predicted for the terminal to stay in the first scenario and the second scenario as the duration related to the terminal for model A.

[0138] The degree of adaptation of the model to the network device is related to the network configuration of the network device. As an example, assuming that model A is adapted to a first network configuration and a second network configuration of the network device, the network device can take the duration predicted for the network device to stay in the first network configuration and the second network configuration as the duration related to the terminal for model A.

[0139] If the generalization of the model is strong, for example, it can adapt to most scenarios of the terminal and / or adapt to most configurations of the network device, the expected applicable duration of the model is relatively long, and the total revenue brought by using the model is also relatively large. However, the generalization of the current model is generally weak, and it can only be applicable to part of the scenarios of the terminal and / or adapt to part of the configurations of the network device. Accordingly, the expected applicable duration of the model is relatively short, and the total revenue brought by using the model is also limited.

[0140] The total revenue of the model in the embodiments of the present application can be understood as the improvement of the communication performance brought by using the model. The unit revenue of the model can be understood as the model performance of the model (for example, the inference accuracy of the model, the prediction accuracy of the model, the accuracy of the monitoring performance of the model), or the improvement of the communication performance (for example, system throughput, BER, etc.) brought by using the model in unit time.

[0141] The unit revenue of the model can also be understood as the model performance, or the revenue brought by the model in unit time, which is not limited in the present application.

[0142] 5、Model quantization

[0143] Model quantization is a technique to reduce model size and computational resource consumption, commonly used to accelerate inference process and reduce power consumption. Quantization achieves this goal by converting weights and / or activations in the model from higher precision representation to lower precision representation. Here are several common quantization precisions:

[0144] FP32 (single precision floating point number); FP32 is the most common data type, using 32 bits (1 bit sign bit, 8 bit exponent bit, 23 bit fraction bit) to store a floating point number; this format provides relatively high precision.

[0145] FP16 (half precision floating point number); FP16 uses 16 bits to represent a floating point number (1 bit sign bit, 5 bit exponent bit, 10 bit fraction bit). Compared to FP32, it reduces storage and bandwidth requirements, but maintains sufficient precision to adapt to many application scenarios.

[0146] INT8 (8-bit integer);

[0147] INT8 uses 8-bit integers to represent weights and activations. This format further reduces the demand for storage space, and can perform efficient integer operations on hardware. INT8 quantization usually requires a calibration step to determine the appropriate quantization range to avoid information loss.

[0148] The process of model quantization generally includes the following steps: preprocessing: preparing training data and calibration dataset. Training: if using Quantization-Aware Training (QAT), the quantization effect will be simulated during the training process. Calibration: for Post-Training Quantization (PTQ), calibration dataset is needed to adjust the quantization parameters. Quantization: quantize the weights and / or activations of the model to lower precision. Verification: ensure the accuracy of the quantized model close to the original model.

[0149] After quantizing the model based on different quantization methods, the model size of the obtained model is different, and the model performance is also different. Generally speaking, the smaller the model size of the quantized model, the lower the model performance, the larger the model size, the higher the model performance. In the embodiments of the present application, the model size affects the transmission delay of the model, and the model performance affects the unit revenue of the model. Therefore, the total revenue of using the preset model under different quantization methods is usually different.

[0150] It should be understood that the model involved in the embodiments of the present application can be described as a function (such as an artificial intelligence (AI) function or a machine learning (ML) function), a feature or an algorithm, and the model includes an AI model or an ML model, etc. For the sake of simplicity of description, the model / function / feature is referred to as a model in the present application, that is, the model in the present application can be replaced by a model / function / feature.

[0151] It should be noted that the model transmission (or transmitting a model) and the like involved in the embodiments of the present application can be replaced by model activation. In other words, the process of model transmission can be replaced by the process of model activation, which is not limited in the present application.

[0152] The above describes the technology involved in the present application in detail.

[0153] As described in the background, when the model is transmitted between the terminal and the network device, since the benefit of the transmitted model is unknown, it can cause the problem of high resource required for model management.

[0154] To solve the above technical problem, the present application provides a communication method. Before triggering transmission or triggering activation of a preset model, the first node can determine a total benefit value of the preset model based on an adaptation parameter of the preset model and the terminal and / or an adaptation parameter of the preset model and the network device. The first node triggers transmission or triggers activation of the preset model when the total benefit value of the preset model meets a preset condition. In this way, the terminal and the network device can transmit or activate the preset model with a high benefit value, thereby improving the benefit of the model transmitted between the terminal and the network device, and further reducing the resource required for model management, such as the resource for transmitting the model or the monitoring resource configured for monitoring the model after the model is activated.

[0155] In addition, the benefit of the model will be different based on the adaptability of the model to the terminal and / or the network device. In view of this, when determining the total benefit value of the preset model, the first node determines the total benefit value of the preset model based on the adaptation parameter of the preset model and the terminal and / or the adaptation parameter of the preset model and the network device. Thus, the total benefit value of the preset model determined by the first node can adapt to different situations.

[0156] As an example, the adaptability of the model is only related to the scenario of the terminal and is irrelevant to the configuration of the network device. Then, the first node only obtains a first adaptation parameter of the preset model and the terminal. The first node determines the total benefit value of the preset model according to the first adaptation parameter, so that the total benefit value of the preset model determined by the first node is related to the scenario of the terminal.

[0157] As yet another example, the adaptability of the model is only related to the scenario of the network device and is not related to the configuration of the terminal, and the first node only acquires the second adaptation parameter of the preset model and the network device. The first node determines the total revenue value of the preset model according to the second adaptation parameter, so that the total revenue value of the preset model determined by the first node is related to the scenario of the network device.

[0158] As yet another example, the adaptability of the model is related to both the scenario of the network device and the configuration of the terminal, and the first node acquires the second adaptation parameter of the preset model and the network device and the first adaptation parameter of the preset model and the terminal, respectively. The first node determines the total revenue value of the preset model according to the first adaptation parameter and the second adaptation parameter, so that the total revenue value of the preset model determined by the first node is related to the scenario of the terminal and the network device.

[0159] Based on the above scheme, the problem that the model revenue determined by the first node cannot match the demand of the terminal and / or the network device and thus the model revenue is low can be avoided.

[0160] The following will give a specific description of the scheme provided by the embodiments of the present application. Before introducing the embodiments of the present application, the following points are explained.

[0161] In the description of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural.

[0162] In the description of the present application, A sending a message to B can be understood as A sending a message to B through one or more network elements.

[0163] In the description of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one" or the like means any combination of the items, including any combination of single item or multiple items. For example, at least one of a, b and (or) c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0164] In addition, in order to facilitate clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. also do not mean necessarily different.

[0165] In the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, an instance, or an illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or superior to other embodiments or design solutions. In fact, the use of the words "exemplary" or "for example" is intended to present related concepts in a specific manner, facilitating understanding.

[0166] It can be understood that the "embodiments" mentioned throughout the specification mean that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, the various embodiments throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It can be understood that in various embodiments of the present application, the size of the serial number of each process does not mean the execution order, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0167] It can be understood that in the present application, "when" and "if" both refer to making corresponding processing under certain objective circumstances, not limited to time, and do not require judgment actions when implementing, nor mean that there are other limitations.

[0168] It can be understood that some optional features in the embodiments of the present application can be implemented independently in some scenarios, without relying on other features, such as the scheme currently based on, to solve the corresponding technical problems and achieve the corresponding effects. In some scenarios, the features can be combined with other features according to the needs. Correspondingly, the devices given in the embodiments of the present application can also realize these features or functions, which will not be described here.

[0169] In the present application, the same or similar parts among various embodiments can be mutually referred to, unless otherwise specified. In the present application, the terms and / or descriptions among different embodiments, and among various implementation manners / implementation methods / realization methods in each embodiment, are consistent and can be mutually referred to, unless otherwise specified and in conflict with logic. The technical features in different embodiments, and among various implementation manners / implementation methods / realization methods in each embodiment, can be combined to form new embodiments, implementation manners, implementation methods, or realization methods according to their inherent logical relationship. The implementation manners of the present application described below do not constitute a limitation on the protection scope of the present application.

[0170] The technical solutions of the embodiments of the present application can be applied to various communication systems. The communication system can be a third generation partnership project (3GPP) communication system, for example, a long term evolution (LTE) system, a fourth generation (4G) system, a new radio (NR) system, a fifth generation (5G) system, a system of mixed networking of LTE and 5G, a communication and sensing integrated system, a non-terrestrial network (NTN), a device-to-device (D2D) communication system, a vehicle to everything (V2X) communication system, a machine-type communication (MTC) system, an internet of things (IoT) system, or other future communication systems. The communication system can also be a non-3GPP communication system, which is not limited.

[0171] It should be noted that the above-mentioned communication system to which the present application is applied is only an example, and the communication system to which the present application is applied is not limited thereto. The communication system provided by the present application does not cause any limitation on the solutions of the present application. Here, it is uniformly stated that the following will not be described in detail.

[0172] FIG. 3 shows a possible, non-limiting system diagram. As shown in FIG. 3, the communication system includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in FIG. 3, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in FIG. 3, collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in FIG. 3), etc., can also be included in the RAN 100. The terminal 120 is connected to the RAN node 110 in a wireless manner. The RAN node 110 is connected to the core network 200 in a wireless or wired manner. The core network node in the core network 200 and the RAN node 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the radio access network.

[0173] In a possible implementation, the core network node can refer to a device in the core network 200 that provides service support for the terminal 120. In the embodiments of the present application, the core network node in the core network 200 includes a sensing function (SF) network element, which is mainly used to implement sensing functions, such as sensing control functions and / or sensing calculation functions. Further, the SF network element can also support sensing billing functions when the terminal 120 and / or the RAN node 110 perform sensing. For example, the sensing control function can include determining sensing devices, sensing nodes, etc. The sensing device can be understood as a device that transmits and / or receives sensing signals, and further performs corresponding signal processing on the received echo signals to obtain sensing measurement data. For example, the sensing device can be the RAN node 110 or the terminal 120, etc. The sensing node can refer to a network node participating in the sensing service process in the wireless network. The sensing calculation function can include performing corresponding signal processing on the echo signals received by the sensing device to obtain sensing measurement data, and further processing the sensing measurement data and application information to obtain sensing results, etc.

[0174] For example, the SF network element can also be referred to as a communication device, for example, the SF network element can be understood as a communication device with core network sensing functions. In addition, the SF network element can also be referred to as a sensing server, etc., without limitation.

[0175] In a possible scenario, the functions of the SF network element can be implemented by a network data analytics function (NWDAF) network element, or the SF network element and the NWDAF network element can be combined.

[0176] Optionally, in addition to the SF network element, the core network nodes in the core network 200 can also include at least one of the following: an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element, a policy control function (PCF) network element, a unified data management (UDM) network element, an application function (AF) network element, a network exposure function (NEF) network element, a network slice selection function (NSSF) network element, or a location management function (LMF) network element, etc. Of course, the core network 200 can also include other core network nodes, which are not limited.

[0177] The AMF network element is a network element deployed in the core network 200, which provides mobility management and connection management for the network, such as user location update, user registration network, user handover, etc. The AMF network element can be used as an intermediate route of the LMF, the SMF and the RAN 100. The SMF network element is mainly responsible for session management in the mobile network, such as session establishment, modification, release, etc. The UPF network element is a functional network element of the user plane, which is mainly responsible for connecting external networks and processing user packets, such as forwarding, charging, etc. The PCF network element is mainly responsible for providing policies to the AMF and the SMF, such as quality of service (QoS) policies, slice selection policies, etc. The UDM network element is used to store user data, such as subscription information, authentication / authorization information, etc. The AF network element is responsible for providing services to the 3GPP network. The NEF network element is mainly used to open the capabilities of various network functions and is responsible for converting internal and external information. The LMF network element is a device or component deployed in the core network 200, which provides positioning functions for the terminal 120, for example, the LMF network element can initiate a positioning process and perform positioning on a specific terminal.

[0178] It should be noted that the network element in the present application can also be referred to as an entity or a functional entity, for example, the SF network element can also be referred to as an SF entity or an SF functional entity. In addition, the above-mentioned AMF network element, SMF network element, UPF network element, PCF network element, UDM network element, AF network element, NEF network element, and LMF network element can also have other names in future communication systems, which are not limited in the present application.

[0179] In a possible implementation, the RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., a 4G, 5G mobile communication system, or a future-oriented evolution system. The RAN 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), an NTN network (e.g., an NTN supporting a transparent mode and / or a regenerative mode, or an NTN supporting a fixed earth mode and / or a moving earth mode), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system in which two or more of the above systems are fused.

[0180] The RAN node 110, which can also be referred to as an access network device, a RAN entity, or an access node, etc., forms part of the communication system to help terminals to access wirelessly. The RAN nodes 110 in the RAN 100 can be of the same type or of different types. In some scenarios, the roles of the RAN node 110 and the terminal 120 are relative, e.g., the network element 120i in Figure 3 can be a helicopter or a drone, which can be configured as a mobile base station. For those terminals 120j accessing the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. Both the RAN node 110 and the terminal 120 are sometimes referred to as communication apparatuses, e.g., the network elements 110a and 110b in Figure 3 can be understood as communication apparatuses with base station functions, and the network elements 120a-120j can be understood as communication apparatuses with terminal functions.

[0181] For the RAN node 110, in one possible scenario, the RAN node 110 can be a base station, an evolved Node B (eNodeB, also referred to as eNB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a future communications base station in a future mobile communications system, or an access node in a WiFi system, etc. The RAN node 110 can be a macro base station (e.g., 110a in Figure 3), a micro base station or indoor station (e.g., 110b in Figure 3), a relay node or donor node, or a wireless controller in a CRAN scenario. For example, a satellite base station, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a home base station (e.g., home eNodeB, or home NodeB, HNB), a relay station, a balloon station, a drone station, a wireless backhaul node, or a grant node (G-node) in a Starlink, etc. It can be understood that the network device can be a device arranged on the ground, or a non-ground device (such as a satellite, a drone, a high-altitude communication device, etc.). In addition, in a communication system using different wireless access technologies, the name of the network device with base station function may be different, which is not limited in the present application. Optionally, the RAN node 110 can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the vehicle to everything (V2X) technology can be a road side unit (RSU). The RAN node 110 is also referred to as a next generation-RAN (NG-RAN) node.

[0182] In another possible scenario, multiple RAN nodes 110 cooperate to assist a terminal to access the wireless access, and different RAN nodes 110 respectively implement part of the functions of a base station. For example, the RAN node 110 can be a CU, a DU, a CU-CP, a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0183] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, the CU-CP, the CU-UP, the DU and the RU are taken as examples for description in this application. Any one of the CU (or the CU-CP, the CU-UP), the DU and the RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0184] For the terminal 120, in a possible scenario, the terminal 120 can be a device for implementing a wireless communication function, for example, a terminal or a chip or circuit used in a terminal, or an entity associated with the terminal, etc. Among them, the terminal 120 can be a user equipment (UE), an access terminal, a terminal unit, a terminal station, a mobile station (MS), a mobile station, a remote station, a remote terminal, a mobile device, a wireless communication device, a terminal agent or a terminal device, a subscriber unit, a smart phone, a wireless data card, a tablet computer, a wireless modem, a laptop computer, a machine type communication (MTC) terminal, a tag, etc. in a 5G network or a future evolved public land mobile network (PLMN). The access terminal can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handset with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device or a wearable device, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, or a terminal node (T node) in starlink, etc. In a possible implementation, the terminal 120 can be mobile or fixed. It can be understood that the terminal and the mobile user can be completely independent. All information related to the user can be stored in a subscriber identity module (SIM) card, which can be used on a terminal device.The terminal can send and / or receive signals through the air interface to complete interaction with the network side device.

[0185] The chip or circuit in the terminal includes components inside the terminal, such as at least one of a chip, a central processing unit (CPU), a network process unit (NPU), and a terminal radio frequency module.

[0186] The entity associated with the terminal includes a server on the terminal side, a computing / processing node, a computing / processing entity, a computing / processing unit, a server, such as an over the top (OTT) server, etc. OTT refers to a third party other than a network operator providing various services to users based on the operator's network, such as OTT voice communication services, OTT multimedia services, and OTT data processing services, etc. The terminal interacts with relevant information (such as data) through communication with the associated network entity. For example, the associated network entity and the terminal belong to the same manufacturer. Due to model training, model selection, etc., it can not be executed on the terminal, but on the OTT server on the terminal side, so the "terminal" in this embodiment also includes the OTT server on the terminal side.

[0187] It should be understood that the terminal in this embodiment can also be referred to as "terminal side" (UE side) or "terminal part" (UE part).

[0188] For example, as shown in FIG. 4, an exemplary implementation of the system shown in FIG. 3. The communication system can include an AI / ML node, a first terminal, and a first device. The first device can provide services for the terminal.

[0189] Optionally, the first device can be a server, which can be a single server, or can also be a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. The server can provide services for the chip, so it can also be called a chip server. Alternatively, the first device can be a first network element in the core network. The first device can train a model or deliver a model or deliver a model inference result for the terminal it serves.

[0190] Optionally, the communication system shown in FIG. 4 can include a network device. The network device can be any device deployed in an access network that can communicate wirelessly with a terminal (e.g., the first terminal, the second terminal), can also be a chip or chip system that can be disposed in the above-mentioned device, can also be a logical node or a logical module or a software-implemented function, and is mainly responsible for functions such as wireless physical control, resource scheduling, radio resource management, quality of service management, data compression and encryption, wireless access control, and mobility management. Specifically, the network device can be a device supporting wired access or a device supporting wireless access.

[0191] In some embodiments, when the model data is stored in the network device, the model can be directly transmitted to the first terminal by the network device. When the model data is stored in the first device, the model can be transmitted to the first terminal by the first device through UP interface data transmission, or the model can be transmitted to the network device by the server and then forwarded to the first terminal by the network device.

[0192] The AI / ML node in FIG. 4 is used to support the use of AI / ML technology in an AI / ML scenario.

[0193] Optionally, the AI / ML node can be deployed in one or more of the following positions in the communication system shown in FIG. 4: the network device, the first terminal, the second terminal, the first device, etc., or the AI / ML node can also be deployed separately, for example, in a position other than the above-mentioned devices.

[0194] For example, the AI / ML node can be deployed in a host or a cloud server of an OTT system. When the device deploying the AI / ML node communicates with the network device, the device can also act as a terminal in the communication system. When the device deploying the AI / ML node communicates with the terminal, the device can also act as a network device in the communication system.

[0195] It can be understood that the number of AI / ML nodes is not limited in the present application. For example, when there are multiple AI / ML nodes, the multiple AI / ML nodes can be divided based on functions, such as different AI / ML nodes being responsible for different functions.

[0196] It can also be understood that the AI / ML node can be a separate device, can also be integrated into the same device to implement different functions, or can be a network element in a hardware device, can also be a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform), and the specific form of the AI / ML node is not limited in the present application.

[0197] The AI / ML node can be an AI / ML network element or an AI / ML module.

[0198] It can be understood that the above Figure 4 is only a schematic diagram, and does not constitute a limitation on the applicable scenarios of the technical solutions provided in the present application. It should be understood by those skilled in the art that, in the specific implementation process, the communication system shown in Figure 4 can also include fewer devices than those shown in Figure 4, or the communication system shown in Figure 4 can also include other devices, and the number of devices in the communication system shown in Figure 4 can also be determined according to specific needs, and is not limited.

[0199] Optionally, each device in Figure 4, such as the first device, the first terminal, the network device, and the second terminal, can also be referred to as a communication apparatus, which can be a general-purpose device or a special-purpose device, and the embodiments of the present application do not make specific limitations.

[0200] Optionally, the related functions of each device in Figure 4 of the present application can be implemented by one device, or can be implemented by multiple devices together, or can be implemented by one or more functional modules in a device, and the embodiments of the present application do not make specific limitations. It can be understood that the above functions can be network elements in a hardware device, or software functions running on a special-purpose hardware, or a combination of hardware and software, or virtualized functions instantiated on a platform (for example, a cloud platform).

[0201] In a possible implementation, the network device (such as an access node or a core network node) in the embodiments of the present application and the terminal 120 can also be referred to as a communication apparatus, which can be a general-purpose device or a special-purpose device, and the network device can include an access node (RAN node), an operation administration and maintenance (OAM) device, or a core network node. For the OAM device, it can include a device in an element management system (EMS), or a device in a network management system (NMS). It should be understood that the network device in the present embodiment can also be referred to as "network side" or "network part". The embodiments of the present application do not make specific limitations.

[0202] In a possible implementation, the related functions of the terminal 120 or the network device in the embodiments of the present application can be implemented by one device, or can be implemented by multiple devices together, or can be implemented by one or more function modules in a device, and the embodiments of the present application do not make a specific limitation. It can be understood that the above functions can be network elements in a hardware device, can be software functions running on a dedicated hardware, or can be a combination of hardware and software, or can be a virtualized function instantiated on a platform (for example, a cloud platform).

[0203] It should be noted that the RAN node can be a device or a component in the device in the above NG-RAN, for example, can be an ng-eNB node, a gNB node, or a transmission point (TP) in the ng-eNB node and the gNB node, a transmission and reception point (TRP), or a central unit (CU) integrated on the NG-RAN. The RAN node can also be a network element with transmission function, for example, a transmission measurement function network element (TMF). In some embodiments, the RAN node can also be an access node in the O-RAN system. The RAN is usually composed of a series of modules, for example, antenna, RRU, and BBU modules, and the traditional RAN architecture defines the overall receiving and output of the RAN node, and does not limit the transmission and contact between the internal modules. The O-RAN architecture defines the architecture contact and standardized interface between the modules in the RAN, so that the RAN can be decoupled into multiple standardized modules, so that the combination and replacement of the modules can be realized.

[0204] An exemplary structure of an O-RAN system is shown in FIG. 5. A service management and orchestration framework (SMO) is used as a network management device in the O-RAN system to manage the devices in the O-RAN system. A non-real time RAN intelligent controller (Non-RT RIC) is located in the SMO module to implement non-real time intelligent management of the RAN functions, such as to implement an AI / ML workflow including model training and model updating, and to guide the applications / functions in the Near-RT RIC based on a policy. A near-real time RAN intelligent controller (Near-RT RIC) is used to implement near-real time intelligent management of the RAN. Through data collection and related operations on the E2 interface, near-real time control and optimization of the modules and resources of the O-RAN system are implemented.

[0205] An O-RAN central unit (O-CU) includes an O-RAN central unit control plane (O-CU-CP) and an O-RAN central unit user plane (O-CU-UP). The O-CU is used to implement a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer and other control functions. The O-CU-CP is used to implement the functions of the RRC layer and the control plane functions of the PDCP layer. The O-CU-UP is used to implement the functions of the SDAP layer and the user plane functions of the PDCP layer.

[0206] An O-RAN distributed unit (O-DU) is configured to implement a radio link control (RLC) layer, a media access control (MAC) layer, and a higher physical layer (Higher PHY). The Higher PHY functions include one or more of forward error correction (FEC) encoding / decoding, scrambling / descrambling, or modulation / demodulation.

[0207] An O-RAN radio unit (O-RU) is configured to implement lower physical layer (Lower PHY) functions and radio frequency functions. The Lower PHY functions include one or more of fast Fourier transform (FFT) transform / inverse fast Fourier transformation (iFFT) transform, digital beamforming, or extraction and filtering of a physical random access channel (PRACH). That is, the O-RU has functions similar to those of a radio frequency device such as a TRP or a RRH and Lower PHY processing functions. In addition, the O-RU, the O-CU, and the O-DU can be collectively referred to as an O-eNB / gNB and configured to implement the above functions.

[0208] An O-RAN cloud (O-Cloud) is a cloud computing platform and includes physical infrastructure nodes configured to host O-RAN functions such as RICs and O-DUs. The O-Cloud supports software components (e.g., operating systems, virtual machine monitors, container runtimes), management, and orchestration functions.

[0209] In a possible scenario, a sensing unit (SU) is further included in the O-RAN system. The SU is mainly configured to implement sensing-related functions, such as transmitting a sensing signal and / or receiving an echo signal of the sensing signal, performing corresponding signal processing on the received echo signal to obtain sensing measurement data, and performing sensing-related processing.

[0210] As a possible implementation, the RAN node can include at least one of a CU, a DU, an SU, and an RU. A communication interface exists between the CU and the SU. A communication interface can or can not exist between the SU and the DU. In the case where no communication interface exists between the SU and the DU, the SU and the DU can communicate through the CU.

[0211] In the O-RAN architecture, the module receiving the difference reporting between the twin channel and the measurement channel can be a CU, a RT RIC, a Non-RT RIC, etc., and the DU is responsible for receiving signals, signal processing, multipath measurement, and channel difference calculation.

[0212] For example, the O-RAN system includes communication interfaces between newly added internal components and other communication interfaces. For example, the A1 interface is an interface between the Non-RT RIC and the Near-RT RIC, which is used for intelligent and dynamic control of O-RAN internal wireless resources. The Non-RT RIC can provide policies, rich information, and ML model updates to the Near-RT RIC through the A1 interface, and the Near-RT RIC can provide policy feedback to the Non-RT RIC through the A1 interface.

[0213] The E2 interface is an open interface between two endpoints, which is used to connect the Near-RT RIC and the RAN node, including the CU, DU in 5G, the O-RAN compatible eNB in 4G, the O-CU (O-CU-CP and / or O-CU-UP) and / or O-DU in O-RAN, etc. The Near-RT RIC can obtain RAN node data collection and feedback through the E2 node, and the RAN node can obtain control feedback from the Near-RT RIC through the E2 node.

[0214] The O1 interface is an interface between the management entity in the SMO and the O-RAN module, which is used for operation management. Through this interface, network management (such as fault management, configuration management, billing management, performance management, security management, also known as FCAPS management), software management, and file management are realized. The O2 interface is an interface between the SMO and the infrastructure management framework supporting the O-RAN virtual network function.

[0215] The open front-haul (FH) CUS-Plane interface includes the control plane C-Plane, the user plane U-Plane, and the synchronization plane S-Plane interface. The control plane is used for real-time control between the O-DU and the O-RU, such as transmitting the weight for beamforming from the O-DU to the O-RU, or power control from the O-DU to the O-RU, etc. The user plane is used for transmitting communication data between the access network device and the terminal between the DU and the RU. The synchronization plane is used for the O-DU to provide clock synchronization to the O-RU. The Open FH M-Plane interface is a management plane interface, which is used for connection between the O-RU and the O-DU and the SMO, and can realize management, monitoring, and configuration functions, etc.

[0216] In addition, the NG interface is an interface between a RAN node (e.g., a base station, a CU, a CU-CP, a CU-UP) and a core network, NG-u is a user plane NG interface, and NG-c is a control plane NG interface. The Xn interface is an interface between NR RAN nodes, Xn-u is a user plane Xn interface, and Xn-c is a control plane Xn interface. The X2 interface is an interface between LTE RAN nodes, X2-u is a user plane X2 interface, and X2-c is a control plane X2 interface. In the NR system, the X2 interface is mainly used in an E-UTRA-NR dual connectivity scenario (EN-DC), in which a master base station is an LTE RAN node, and the master base station is connected to an LTE core network through the X2 interface. The E1 interface is an interface between the CU-CP and the CU-UP, the F1-C interface is an interface between the CU-CP and the DU, and the F1-U interface is an interface between the CU-UP and the DU.

[0217] In some embodiments, the communication apparatus in the embodiments of the present application can implement an AI / ML workflow (also referred to as model operation), which includes data collection, model training, model delivery, model updating, model inference, model monitoring, and model management.

[0218] The communication method provided by the embodiments of the present application can be applied to the scenario of communication between a terminal and a network device. For example, as shown in FIG. 6, an architecture schematic diagram of a communication system 60 provided by the embodiments of the present application is shown, the communication system 60 includes a terminal 601 and a network device 602. The network device 602 is configured to send a preset model required by the terminal 601 to the terminal 601. After receiving the preset model sent by the network device 602, the terminal 601 performs corresponding processing based on the preset model to improve the communication performance. Alternatively, the network device 602 is configured to activate the preset model in the terminal 601. The terminal 601 activates the preset model based on the activation indication of the network device 602.

[0219] In a possible implementation manner, before triggering the transmission model or the activation model, the terminal 601 or the network device 602 can determine the benefit of using the preset model by the terminal according to the adaptation parameter of the preset model and the terminal and / or the adaptation parameter of the preset model and the network device, and trigger the transmission or the activation of the preset model when the benefit of the preset model meets a preset condition.

[0220] As an example, when the preset model is a model only related to terminal adaptation parameters, the terminal 601 acquires the adaptation parameters related to the preset model stored by the terminal 601, and then calculates and determines the model revenue of the preset model according to the terminal adaptation parameters. When the revenue generated by the preset model meets the preset condition, the terminal 601 sends a request message to the network device 602 to request the network device 602 to send the preset model to the terminal 601 or activate the preset model.

[0221] As another example, when the preset model is a model only related to terminal adaptation parameters, the network device 602 acquires the adaptation parameters related to the preset model from the terminal 601, and then calculates and determines the model revenue of the preset model according to the terminal adaptation parameters. When the revenue generated by the preset model meets the preset condition, the network device 602 sends the preset model to the terminal 601 or activates the preset model.

[0222] As another example, when the preset model is a model only related to network device adaptation parameters, the terminal 601 acquires the adaptation parameters related to the preset model from the network device 602, and then calculates and determines the model revenue of the preset model according to the network device adaptation parameters. When the revenue generated by the preset model meets the preset condition, the terminal 601 sends a request message to the network device 602 to request the network device 602 to send the preset model to the terminal 601 or activate the preset model.

[0223] As another example, when the preset model is a model only related to network device adaptation parameters, the network device 602 acquires the adaptation parameters related to the preset model stored by the network device 602, and then calculates and determines the model revenue of the preset model according to the network device adaptation parameters. When the revenue generated by the preset model meets the preset condition, the network device 602 sends the preset model to the terminal 601 or activates the preset model.

[0224] As another example, when the preset model is a model related to both network device adaptation parameters and terminal adaptation parameters, the terminal 601 acquires the adaptation parameters related to the preset model from the network device 602 and acquires the adaptation parameters related to the preset model stored by the terminal 601, and then the terminal 601 further calculates and determines the model revenue of the preset model according to the network device adaptation parameters and the terminal adaptation parameters. When the revenue generated by the preset model meets the preset condition, the terminal 601 sends a request message to the network device 602 to request the network device 602 to send the preset model to the terminal 601 or activate the preset model.

[0225] As a further example, when the preset model is a model related to both the network device adaptation parameter and the terminal adaptation parameter, the network device 602 acquires the adaptation parameter related to the preset model from the terminal 601 and the adaptation parameter related to the preset model stored by the network device 602, and further calculates the model benefit of the preset model according to the network device adaptation parameter and the terminal adaptation parameter. When the benefit generated by the preset model meets the preset condition, the network device 602 sends the preset model or activates the preset model to the terminal 601.

[0226] In a possible implementation, FIG. 7 is a constituent diagram of a communication apparatus 700 provided by an embodiment of the present application. The network device and the terminal shown in FIG. 3 can adopt the constituent structure shown in FIG. 7, or include the components shown in FIG. 7. Alternatively, the components (for example, chips) in the network device and the terminal shown in FIG. 3 can adopt the constituent structure shown in FIG. 7, or include the components shown in FIG. 7. It can be understood that the communication apparatus 700 includes necessary means such as modules, units, elements, circuits, or interfaces, which are configured together to execute the present solution.

[0227] As shown in FIG. 7, the communication apparatus 700 includes one or more processors 71 configured to implement processes, determine processes, and so on, performed by each device in the embodiments below. The processor 71 can be a general processor or a special purpose processor. For example, it can be a baseband processor or a central processing unit. The baseband processor can be configured to process communication protocols and communication data. The central processing unit can be configured to control the communication apparatus (for example, a RAN node, a terminal, or a chip), execute software programs, and process data of the software programs.

[0228] Optionally, in a design, the processor 71 can include a program 73 (which can also be referred to as code or instructions at times) that can be run on the processor 71, so that the communication apparatus 700 executes the methods described in the embodiments below.

[0229] Optionally, the communication apparatus 700 can include one or more memories 72 having a program 74 (which can also be referred to as code or instructions at times) stored thereon. The program 74 can be run on the processor 71, so that the communication apparatus 700 executes the methods described in the embodiments below.

[0230] Optionally, the processor 71 and / or the memory 72 can include an AI module 77 and an AI module 78, which are used to implement AI-related functions. The AI modules can be implemented in software, hardware, or a combination of software and hardware. For example, the AI modules can include a radio access network intelligence controller (RIC) module. For example, the AI modules can be near-real-time RIC or non-real-time RIC.

[0231] Optionally, the processor 71 and / or the memory 72 can also store data. The processor and the memory can be separately arranged or integrated together.

[0232] Optionally, the communication device 700 can also include a transceiver 75, which is used to implement the transceiving processes performed by various devices in the embodiments described below. The processor 71 can also be referred to as a processing unit, which controls the communication device (e.g., a RAN node or a terminal). The transceiver 75 can also be referred to as a transceiving unit, a transceiver, a transceiving circuit, or a transceiver, and the communication device 700 can also include an antenna 76.

[0233] It should be noted that the constituent structures shown in FIG. 7 do not constitute a limitation on the communication device, and the communication device can include more or fewer components than those shown in FIG. 7, or combine certain components, or different component arrangements.

[0234] In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0235] In addition, the actions, terms, and the like involved in the embodiments of the present application can be mutually referred to and are not limited. The message name or parameter name in the message exchanged between various devices in the embodiments of the present application is only an example, and other names can also be used in specific implementations, which are not limited.

[0236] The communication method provided by the embodiments of the present application will be described below in conjunction with FIGS. 1 to 7.

[0237] It should be noted that the message name between various network elements, the name of each parameter, or the name of each information in the embodiments of the present application described below is only an example, and in other embodiments, other names can also be used, and the communication method provided by the present application does not make specific limitations.

[0238] It can be understood that, in the embodiments of the present application, each network element can perform part or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, each step can be performed in a different order as presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are performed.

[0239] It can be understood that, in the embodiments of the present application, each network element can perform part or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, each step can be performed in a different order as presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are performed.

[0240] FIG. 8 is a flowchart of a communication method according to an embodiment of the present application. In the embodiments of the present application, the first node determines the total revenue value of the preset model according to the adaptation parameter of the preset model and the terminal and the adaptation parameter of the preset model and the network device, and triggers transmission or triggers activation of the preset model in the case that the total revenue value of the preset model meets the preset condition. In the following, the functions and executed actions of each device in the communication system provided by the embodiments of the present application are introduced. As shown in FIG. 8, the communication method includes the following steps:

[0241] Step 801, the first node obtains first information.

[0242] The first information includes at least one of the following: the first adaptation parameter or the second adaptation parameter, wherein the first adaptation parameter is the adaptation parameter of the preset model and the terminal, and the second adaptation parameter is the adaptation parameter of the preset model and the network device; the adaptation parameter is a parameter related to the first performance of the preset model; the first performance is used to represent the total revenue value of using the preset model. In the embodiments of the present application, the first node can be a terminal or a network device, and the present application does not limit this.

[0243] In some implementations, the process in which the first node obtains the first information includes: the first node obtaining an adaptation parameter of the preset model on a side of the first node; or, the first node obtaining an adaptation parameter of the preset model on a side of a second node; or, the first node obtaining an adaptation parameter of the preset model on the side of the first node and an adaptation parameter of the preset model on the side of the second node. The second node is a device opposite to the first node. For example, when the first node is a terminal, the second node is a network device; when the first node is a network device, the first node is a terminal.

[0244] At step 802, the first node triggers transmission or triggers activation of the preset model when the first performance of the preset model meets the first preset condition.

[0245] The first performance of the preset model is determined based on the first information.

[0246] In some implementations, after the first node obtains the first information, the first node determines a total revenue value of the preset model according to at least one of the first adaptation parameter and the second adaptation parameter in the first information. The first node determines whether the total revenue value of the preset model meets the first preset condition. When the first performance of the preset model meets the first preset condition, the first node triggers transmission or triggers activation of the preset model.

[0247] In the embodiments of the present application, the manner in which the first node calculates the first performance can be a predefined calculation manner or a calculation manner determined by negotiation between the terminal and the network device, which is not limited in the present application. Similarly, the first preset condition described above can be a predefined preset condition or a preset condition determined by negotiation between the terminal and the network device, which is not limited in the present application.

[0248] It should be noted that when the first node is a terminal, the process in which the first node triggers transmission of the preset model can be that the terminal sends preset model request information to the network device to request the network device to send the preset model to the terminal. When the first node is a network device, the process in which the first node triggers transmission of the preset model can be that the network device directly sends the preset model to the terminal or the network device requests the terminal whether the preset model can be sent to the terminal.

[0249] In addition, the process in which the first node triggers activation of the preset model is that, when the first node is a terminal, the terminal sends an activation request message to the network device to request the network device to activate the preset model. When the first node is a network device, the network device directly instructs the terminal to activate the preset model or the network device requests the terminal whether the preset model can be instructed to activate the preset model. The present application is not limited in this regard.

[0250] It should be noted that the preset model in the present application can be a preset model used by the terminal or a preset model used by the network device, and the present application mainly takes the preset model used by the terminal as an example for description, and the present application does not limit this.

[0251] Based on the communication method provided in the present application, the first node determines the total yield value of the preset model according to the adaptation parameter of the preset model and the terminal and / or the adaptation parameter of the preset model and the network device, and triggers transmission or triggers activation of the preset model in the case that the total yield value of the preset model meets the preset condition. In this way, the model with a higher transmission yield value between the terminal and the network device can be transmitted, thereby improving the yield of the model transmitted between the terminal and the network device.

[0252] In the following, the first adaptation parameter and the second adaptation parameter in the embodiments of the present application are described in detail.

[0253] I. The first adaptation parameter

[0254] The first adaptation parameter is used to represent at least one of the following: a first duration related to the preset model and the terminal; a second performance of the preset model; the second performance is used to represent a unit yield of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total yield value related to the preset model and the terminal. Based on this, since the first adaptation parameter is all related to the terminal, the first node can determine the yield value of the preset model related to the adaptation parameter on the terminal side based on the first adaptation parameter, and then make the total yield of the determined model meet the adaptation parameter on the terminal side.

[0255] The first duration related to the preset model and the terminal can be represented by at least one of the following: a start time related to the preset model and the terminal, an end time related to the preset model and the terminal, and a duration related to the preset model and the terminal. In other words, the first adaptation parameter includes at least one of the following: a transmission delay of the preset model between the terminal and the network device; a start time related to the preset model and the terminal; an end time related to the preset model and the terminal; a duration related to the preset model and the terminal; a second performance of the preset model; the second performance is used to represent a unit yield of the preset model determined by the terminal; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total yield value related to the preset model and the terminal.

[0256] It should be noted that the first adaptation parameter includes the above parameters, and can also be understood as the first adaptation parameter representing the above parameters, or the first adaptation parameter indicating the above parameters, which are collectively described here and will not be described again below.

[0257] In the following, each specific parameter represented by the first adaptation parameter is described in detail.

[0258] 1、first duration related to the terminal

[0259] The first duration related to the terminal is a parameter required for calculating the total income of the preset model in the terminal. In some embodiments, the total income of the preset model = unit income of the preset model x applicable duration of the preset model. The applicable duration of the preset model can be determined based on the first duration. For example, the first node determines the first duration as the applicable duration of the preset model; or the first node determines the intersection of the first duration and the second duration as the applicable duration of the preset model; or the first node determines the intersection of the first duration and the second duration minus the transmission delay of the preset model as the applicable duration of the preset model. The second duration is a duration related to the network device.

[0260] It should be noted that the first duration can be determined based on the applicable duration of the preset model in the relevant scenario of the terminal. For example, the preset model is applicable to scenario A and scenario B of the terminal, and the terminal predicts the duration of the terminal in scenario A and scenario B based on the current state of the terminal. The first node takes the duration of the terminal in scenario A and scenario B as the first duration.

[0261] As an example, the preset model is applicable to the communication transmission scenario of the terminal in a specific area, the terminal predicts the time when the terminal leaves the specific area based on the moving speed and moving track of the terminal, and further determines the duration of the terminal in the specific area. The first node takes the duration of the terminal in the specific area as the first duration.

[0262] As another example, the preset model is applicable to the scenario of the terminal in a non-energy-saving mode, the terminal predicts the time when the terminal enters the energy-saving mode based on the current power of the terminal and the power consumption of the terminal, and further determines the duration of the terminal in the non-energy-saving mode scenario. The first node takes the duration of the terminal in the non-energy-saving mode scenario as the first duration.

[0263] 2、second performance of the preset model

[0264] The second performance of the preset model can be the unit income of the preset model configured for the terminal in advance, or the unit income of the preset model determined by the terminal according to the income of the preset model used by the terminal before the current time.

[0265] In some embodiments, the performance of the preset model comprises performances of a plurality of evaluation indexes. The evaluation index can also be referred to as a performance index. For example, the evaluation index can be a model inference accuracy, a model prediction accuracy, or a model monitoring accuracy. For example, for a function of CSI compression-recovery, the evaluation index can be an accuracy of CSI compression-recovery; for a function of CSI prediction, the evaluation index can be an accuracy of CSI prediction; for a function of beam prediction, the evaluation index can be an accuracy of beam prediction; for a function of positioning inference, the evaluation index can be an accuracy of positioning inference. In addition, the evaluation index can also be modulation / demodulation, encoding / decoding, channel equalization, channel estimation, pilot generation, resource mapping, resource demapping, interference suppression, interference prediction, or a receiver / transmitter, and the like, which will not be listed one by one.

[0266] It should be noted that the performance of each evaluation index can also include a plurality of performances, for example, the accuracy of prediction as one performance, and the stability of prediction as another performance. In addition, the performance of the evaluation index can also include performances of other dimensions, which will not be described herein.

[0267] In some embodiments, the one or more evaluation indexes are evaluation indexes selected from the plurality of evaluation indexes based on network parameters of the network device and / or parameters of the terminal. In other words, the first node can select one or more evaluation indexes from the plurality of evaluation indexes based on the performance expectation of the network device on the preset model. Alternatively, the first node can select one or more evaluation indexes from the plurality of evaluation indexes based on the performance expectation of the terminal on the preset model. Alternatively, the first node can select one or more evaluation indexes from the plurality of evaluation indexes based on the performance expectation of the terminal and the network device on the preset model. The present application does not limit this.

[0268] As an example, the network parameter can be a parameter based on the performance requirement of the network on the model, or a parameter based on the performance requirement of the system. For example, the performance requirement of the system is that the accuracy of the system throughput is improved by 10% compared with the case without CSI prediction. Correspondingly, the evaluation index of the preset model is that the CSI prediction accuracy is greater than 0.9.

[0269] 3. Transmission delay of the preset model between the terminal and the network device

[0270] The transmission delay of the preset model between the terminal and the network device (hereinafter referred to as the transmission delay of the preset model) is determined based on the model size of the transmitted preset model and the transmission performance between the terminal and the network device. The larger the preset model, the greater the transmission delay of the preset model; the better the transmission performance between the terminal and the network device, the smaller the transmission delay of the preset model. For example, the transmission delay of the preset model = the model size of the preset model ÷ the transmission rate between the terminal and the network device.

[0271] In some scenarios, the transmission delay of the preset model can affect the applicable duration of the preset model. For example, the first node requests the preset model when the use scenario of the terminal is related to the preset model, and the applicable duration of the preset model is the duration between the time when the terminal receives the preset model and activates the preset model and the time when the use scenario of the terminal is switched to another scenario, where the preset model is not related to the other scenario (for example, the model cannot meet the expected evaluation index in the other scenario). At this time, the first node needs to subtract the transmission delay of the preset model between the terminal and the network device from the relevant duration of the preset model to the terminal and / or the network device to obtain the applicable duration of the preset model.

[0272] In yet other scenarios, the transmission delay of the preset model does not affect the applicable duration of the preset model. For example, in the scenario where the first node triggers transmission or activation of the preset model in advance, if the time when the first node triggers in advance is greater than the transmission delay of the preset model between the terminal and the network device, the preset model has been transmitted to the terminal before the terminal uses the preset model, and at this time, the transmission delay of the preset model does not affect the applicable duration of the preset model. The applicable duration of the first node is the relevant duration of the preset model to the terminal and / or the network device.

[0273] 4. Third performance of the preset model determined by the terminal

[0274] The third performance of the preset model determined by the terminal is used to represent the total benefit value related to the terminal. In the case where the first node only needs to determine the total benefit value related to the preset model and the terminal, the first node can directly determine whether to trigger transmission or activation of the preset model based on the third performance of the preset model determined by the terminal. In the case where the first node also needs to determine the total benefit value related to the preset model and the network device, the first node can determine the first duration related to the terminal based on the third performance of the preset model determined by the terminal and the unit benefit of the preset model. After that, the first node determines the total benefit value of the preset model based on the first duration related to the terminal, the second duration related to the network device, and the unit benefit of the preset model.

[0275] The above describes each parameter in the first adaptation parameter in detail.

[0276] II. Second adaptation parameter

[0277] In a possible implementation, the second adaptation parameter is used to represent at least one of: a second time length related to the preset model and the network device; a transmission time delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total benefit value related to the preset model and the network device. Based on this, since the second adaptation parameter is related to the network device, the first node can determine the benefit value of the preset model related to the adaptation parameter of the network device based on the second adaptation parameter, so that the total benefit of the determined model can meet the adaptation parameter of the network device.

[0278] The first time length related to the preset model and the network device is represented by at least one of: a start time related to the preset model and the network device; an end time related to the preset model and the network device; or a duration related to the preset model and the network device. The second adaptation parameter includes at least one of: a transmission time delay of the preset model between the terminal and the network device; a start time related to the preset model and the network device; an end time related to the preset model and the network device; a duration related to the preset model and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total benefit value related to the preset model and the network device.

[0279] It should be noted that the second adaptation parameter includes the above-mentioned parameters, and can also be understood as the second adaptation parameter being used to represent the above-mentioned parameters, or the second adaptation parameter being used to indicate the above-mentioned parameters. Here, the above-mentioned parameters are collectively described, and the following will not be described again.

[0280] The following will be described in detail the specific parameters represented by the second adaptation parameter.

[0281] 5. The first time length related to the preset model and the network device

[0282] The first time length related to the preset model and the network device is a parameter required for calculating the total benefit of the preset model in the network device.

[0283] In some embodiments, the total benefit of the preset model = the unit benefit of the preset model x the applicable time length of the preset model. The applicable time length of the preset model can be determined based on the second time length related to the preset model and the network device. For example, the first node determines the second time length as the applicable time length of the preset model; or the first node determines the intersection of the first time length and the second time length as the applicable time length of the preset model; or the first node determines the intersection of the first time length and the second time length minus the transmission time delay of the preset model as the applicable time length of the preset model.

[0284] It should be noted that the second duration can be determined based on a preset model applicable to a duration of the relevant configuration of the network device. For example, the preset model is applicable to the configuration C and the configuration D of the network device, and the network device predicts the duration of the network device in the configuration C and the configuration D based on the current state of the network device. The first node takes the duration of the network device in the configuration C and the configuration D as the second duration.

[0285] 6. The fourth performance of the preset model

[0286] The fourth performance of the preset model can be a unit profit of the preset model configured in advance for the network device, or can be a unit profit of the preset model determined by the network device according to the profit of the preset model used by one or more terminals before the current time.

[0287] The performance of the preset model can be understood with reference to the performance of the preset model described in the first adaptation parameter, which will not be repeated here.

[0288] It should be noted that the fourth performance of the preset model determined by the network device and the second performance of the preset model determined by the terminal can be the same or different. For example, the second performance and the fourth performance are both preset performances; or the second performance and the fourth performance are both unit profits of the preset model determined according to the profit of the preset model used by the terminal before the current time; or the second performance is a preset performance and the fourth performance is a unit profit of the preset model determined according to the profit of the preset model used by one or more terminals before the current time; or the second performance is a unit profit of the preset model determined according to the profit of the preset model used by the terminal before the current time and the fourth performance is a unit profit of the preset model determined according to the profit of the preset model used by one or more terminals before the current time; or the second performance is a unit profit of the preset model determined according to the profit of the preset model used by the terminal before the current time; and the fourth performance is a preset performance. The present application does not limit this.

[0289] 7. Transmission delay of the preset model between the terminal and the network device

[0290] The transmission delay of the preset model between the terminal and the network device can be understood with reference to the transmission delay of the preset model between the terminal and the network device described in the first adaptation parameter, which will not be limited herein.

[0291] It should be noted that in the embodiments of the present application, the transmission delay of the preset model between the terminal and the network device can be determined by the terminal or the network device, which will not be limited herein. Whether the terminal determines the delay or the network device determines the delay, the first node can obtain the delay from the communication device that determines the delay.

[0292] 8. The fifth performance of the preset model determined by the network device

[0293] The fifth performance of the preset model determined by the network device is used to represent the total revenue value of the preset model related to the network device. In a case where the first node only needs to determine the total revenue value of the preset model related to the network device, the first node can directly determine whether to trigger transmission or to trigger activation of the preset model based on the fifth performance of the preset model determined by the network device. In a case where the first node also needs to determine the total revenue value of the preset model related to the terminal, the first node can determine the second time length of the preset model related to the network device according to the third performance of the preset model determined by the terminal and the unit revenue of the preset model. After that, the first node determines the total revenue value of the preset model based on the first time length of the preset model related to the terminal, the second time length of the preset model related to the network device, and the unit revenue of the preset model.

[0294] The above describes each parameter in the second adaptation parameter in detail.

[0295] In some embodiments, the first node needs to determine the first performance of the preset model in advance before triggering transmission or triggering activation of the preset model. The following describes an example in which the first information includes the first adaptation parameter and / or the second adaptation parameter, the first adaptation parameter is used to represent the first time length of the preset model related to the terminal, and the second adaptation parameter is used to represent the second time length of the preset model related to the network device.

[0296] First, the first node determines the unit revenue of the preset model, which can be the unit revenue of the preset model determined by the terminal or the unit revenue of the preset model determined by the network device.

[0297] After that, the first node determines the applicable time length of the preset model. The applicable time length of the preset model includes at least one of the following: the first time length, the second time length, the intersection between the first time length and the second time length, or the time length obtained by subtracting the time delay of the preset model from the intersection between the first time length and the second time length. Whether the transmission time delay of the preset model needs to be considered when calculating the applicable time length of the preset model can be understood in combination with the above description of the transmission time delay of the preset model in the first adaptation parameter, and the present application will not be repeated here.

[0298] After the first node determines the applicable time length of the preset model, the first node determines the product of the unit revenue of the preset model and the applicable time length of the preset model as the total revenue of the preset model, that is, the first performance of the preset model.

[0299] In other words, the above determination of the first performance of the preset model by the first node can also be understood as:

[0300] The first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; the second adaptation parameters are used to represent a second time length related to the network device of the preset model; the first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; wherein the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model; the sixth performance is a second performance and / or a third performance in the first adaptation parameters and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model.

[0301] Alternatively, the first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; the second adaptation parameters are used to represent a second time length related to the network device of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; the first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; wherein the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model and a time delay of the preset model transmitted by the terminal and the network device; the sixth performance is a second performance and / or a third performance in the first adaptation parameters and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model; the time delay of the preset model transmitted by the terminal and the network device is a time delay in the first adaptation parameters or a time delay in the second adaptation parameters.

[0302] In the embodiments of the present application, the first node can be a network device (denoted as scenario 1), or the first node can also be a terminal (denoted as scenario 2). The process of the terminal obtaining the first information and triggering transmission or triggering activation of the preset model is different from the process of the network device obtaining the first information and triggering transmission or triggering activation of the preset model, which will be described in detail below.

[0303] Scenario 1: the first node is a network device.

[0304] In a case that the first node is a network device, the network device acquires the first information, including: the network device determining, from the adaptation parameters stored by the network device, a second adaptation parameter related to the preset model; and / or, the network device receiving third indication information from the terminal; the third indication information being used for indicating the first adaptation parameter.

[0305] In other words, in the scenario 1, the process in which the network device acquires the first information includes the following manner 1, manner 2 and manner 3, which are described in detail as follows.

[0306] The manner 1 is that the network device determines, from the adaptation parameters stored by the network device, a second adaptation parameter related to the preset model, and determines the second adaptation parameter as the first information.

[0307] The manner 1 is applicable to a scenario in which the applicable time length of the preset model is related to the adaptation parameter of the network device. In this scenario, the network device only determines the second adaptation parameter from the self adaptation parameter, and determines the total revenue of the preset model according to the second adaptation parameter.

[0308] In the manner 1, the second adaptation parameter determined by the network device is used to represent a second time length related to the preset model and the network device. For example, the preset model is in the duration of the configuration C and the configuration D adapted by the network device. The network device determines the total revenue of the preset model based on the product of the second time length and the unit revenue of the preset model.

[0309] In addition, the second adaptation parameter can also be used to represent at least one of the following: a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model, the fourth performance being used to represent the unit revenue of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device, the fifth performance being used to represent the total revenue value of the preset model and the network device; which are not limited in the present application.

[0310] The manner 2 is that the network device receives third indication information from the terminal, and determines the first adaptation parameter indicated by the third indication information as the first information.

[0311] The third indication information is used for indicating the first adaptation parameter.

[0312] The manner 2 is applicable to a scenario in which the applicable time length of the preset model is related to the adaptation parameter of the terminal. In this scenario, the network device only acquires the first adaptation parameter from the terminal, and determines the total revenue of the preset model according to the first adaptation parameter.

[0313] In the manner 2, the first adaptation parameter determined by the network device is used to represent a first time length related to the preset model and the terminal. For example, the preset model is in the duration of the scene A and the scene B adapted by the terminal. The network device determines the total revenue of the preset model based on the product of the first time length and the unit revenue of the preset model.

[0314] In addition, the first adaptation parameter can also be used to represent at least one of the following: a second performance of the preset model; the second performance is used to represent a unit profit of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total profit value of the preset model related to the terminal. Based on this, the first node can determine the total profit of the model based on the related parameters in the first adaptation parameter, so that the total profit of the determined model meets the adaptation parameter of the terminal; the present application does not limit this.

[0315] In mode 3, the network device determines the second adaptation parameter related to the preset model from the adaptation parameter stored by the network device, and determines the first adaptation parameter according to the third indication information from the terminal; and determines the second adaptation parameter and the first adaptation parameter as the first information.

[0316] Mode 3 is applicable to a scenario in which the applicable duration of the preset model is related to the adaptation parameter of the network device and the adaptation parameter of the terminal. In this scenario, the network device respectively obtains the second adaptation parameter from the network device and the first adaptation parameter from the terminal. After that, the network device determines the total profit of the preset model according to the first adaptation parameter and the second adaptation parameter.

[0317] In mode 3, the first adaptation parameter determined by the network device includes the first duration, and the second adaptation parameter includes the second duration. For example, the first duration is the duration of scenario A and scenario B in which the preset model is adapted by the terminal, and the second duration is the duration of configuration C and configuration D in which the preset model is adapted by the network device. The network device determines the intersection of the first duration and the second duration, and determines the total profit of the preset model based on the product of the duration of the intersection and the unit profit of the preset model; or the network device determines the difference value between the intersection of the first duration and the second duration and the transmission delay of the preset model, and determines the total profit of the preset model based on the product of the duration of the difference value and the unit profit of the preset model.

[0318] As an example, as shown in FIG. 9, a schematic diagram of the unit profit, the transmission delay, the first duration, and the second duration of the preset model provided by the present application is provided. Among them, t1 is the start time of the first duration, t2 is the end time of the first duration, t1' is the start time of the second duration, and t2' is the end time of the second duration.

[0319] It should be pointed out that the unit profit of the preset model in the above mode 1-mode 3 can be determined by the network device, or can be determined by the terminal device and then sent to the network device, and the present application does not limit this.

[0320] As shown in FIG. 10, in the manner 3 of the scenario 1, the network device obtaining the first information and triggering the transmission or the process of triggering the activation of the preset model can be implemented through the following steps 1001 to 1005.

[0321] In step 1001, the terminal sends third indication information to the network device. Correspondingly, the network device receives the third indication information from the terminal.

[0322] In some embodiments, the terminal identifies an application scenario and determines a preset model corresponding to the application scenario. Then, the terminal determines a unit revenue of the preset model, a start time of the preset model, and a first time length of the preset model. The terminal determines a first adaptation parameter based on the above information and generates the third indication information. Optionally, the first adaptation parameter further includes an end time of the preset model. The first time length of the preset model is a time length between a time when the transmission is completed and the preset model is activated and a time when the use of the preset model ends.

[0323] It should be noted that the unit revenue of the preset model determined by the terminal can include the unit revenue of the preset model under different quantization manners and the model size under different quantization manners.

[0324] In a possible implementation, the third indication information includes at least one of the following information: an identifier of the preset model, a start time related to the terminal of the preset model, an end time related to the terminal of the preset model, a model size of the preset model, or a unit revenue of the preset model.

[0325] In step 1002, the network device determines a second adaptation parameter related to the preset model from the adaptation parameters stored in the network device.

[0326] In some embodiments, the network device determines configuration information of the network device and determines a configuration used by the preset model. The network device determines a second time length related to the network device of the preset model based on a start time and an end time of the configuration of the network device applicable to the preset model. The network device determines a model size of the preset model and a network transmission performance (such as a channel condition of the time of transmitting the preset model). The network device determines a transmission delay of the preset model according to the model size of the preset model and the network transmission performance. The network device determines the second adaptation parameter based on at least one of the following: the start time, the end time, or the second time length, or the transmission delay of the configuration of the preset model.

[0327] In step 1003, the network device determines a first performance of the preset model based on the second adaptation parameter and the first adaptation parameter.

[0328] In some embodiments, the network device determines the applicable time length of the preset model based on the first time length in the first adaptation parameter, the second time length in the second adaptation parameter, and the transmission time delay of the preset model. The network device determines the first performance of the preset model based on the product of the unit benefit of the preset model in the first adaptation parameter and the time length of the preset model.

[0329] Optionally, in the scenario where the network device transmits the preset model, the process of transmitting the preset model by the network device can be implemented through the following step 1004:

[0330] Step 1004, the network device transmits the preset model to the terminal or requests to transmit the preset model to the terminal in the case where the first performance meets the first preset condition.

[0331] In the case where the network device determines that the first performance meets the first preset condition, the network device can directly transmit the preset model to the terminal without the terminal requesting the preset model.

[0332] In some embodiments, the request of the network device to transmit the preset model to the terminal means that the network device requests the terminal device whether the preset model can be transmitted to the terminal. In other words, before the network device transmits the preset model to the terminal, the network device can first request the terminal whether the preset model can be transmitted, and in the case where the terminal determines that the preset model can be transmitted, the network device transmits the preset model to the terminal.

[0333] Optionally, in the scenario where the network device activates the preset model, step 1004 can be replaced by the following step 1005 accordingly:

[0334] Step 1005, the network device instructs the terminal to activate the preset model or requests the terminal to activate the preset model.

[0335] In this step 1005, the network device does not transmit the preset model to the terminal, but instructs or requests the terminal to activate the preset model, so that the terminal uses the activated model.

[0336] In some embodiments, the request of the network device to the terminal to activate the preset model means that the network device requests the terminal device whether the preset model can be instructed to activate the preset model. In other words, before the network device instructs the terminal to activate the preset model, the network device can first request the terminal whether the preset model can be instructed to activate, and in the case where the terminal determines that the preset model can be instructed to activate, the network device instructs the terminal to activate the preset model.

[0337] It should be noted that FIG. 10 only illustrates the process of the network device obtaining the first information and triggering the transmission or triggering the activation of the preset model in the manner 3 of the scenario 1. The process of the network device obtaining the first information and triggering the transmission or triggering the activation of the preset model in the manners 1 and 2 can be understood with reference to FIG. 10, and only needs to adaptively adjust the process of obtaining the first information based on the required adaptation parameter, which will not be described herein again.

[0338] It can be understood that the sequence of the steps 1001 and 1002 is not limited in the present application, and in the specific implementation, the step 1001 can be performed first and then the step 1002, or the step 1002 can be performed first and then the step 1001, or the steps 1001 and 1002 can be performed simultaneously, which is not limited in the present application. In addition, in some manners, the step 1002 can not be performed, that is, the second adaptation parameter is not obtained, and correspondingly, the network device can not include the second adaptation parameter in the step 1003, that is, the network device only obtains the first adaptation parameter and determines the first performance of the preset model based on the first adaptation parameter. The present application will not be described again.

[0339] In the scenario 2, the first node is a terminal.

[0340] In the case that the first node is a terminal, the terminal obtains the first information, including: the terminal determines the first adaptation parameter related to the preset model from the adaptation parameter stored in the terminal; and / or, the terminal receives the first indication information from the network device; the first indication information is used to indicate the second adaptation parameter.

[0341] In other words, in the scenario 2, the process of the terminal obtaining the first information includes the following manners 4, 5 and 6, respectively.

[0342] The manner 4 is that the terminal determines the first adaptation parameter related to the preset model from the adaptation parameter stored in the terminal.

[0343] The manner 4 is applicable to the scenario that the applicable time length of the preset model is related to the adaptation parameter of the terminal. In this scenario, the terminal only determines the first adaptation parameter from the self-adaptation parameter, and determines the total income of the preset model according to the first adaptation parameter.

[0344] In the manner 4, the first adaptation parameter determined by the terminal is used to represent the first time length related to the terminal of the preset model. For example, the duration time of the preset model in the scene A and the scene B adapted by the terminal. The terminal determines the total income of the preset model based on the product of the first time length and the unit income of the preset model.

[0345] In addition, the first adaptation parameter can be used to represent at least one of: a second performance of the preset model; the second performance is used to represent a unit profit of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or, a third performance of the preset model determined by the terminal; the third performance is used to represent a total profit value of the preset model related to the terminal. Based on this, the first node can determine the total profit of the model based on the related parameters in the first adaptation parameter, so that the determined total profit of the model meets the adaptation parameter of the terminal; the present application does not limit this.

[0346] Option 5, the terminal receives first indication information from the network device; and determines the second adaptation parameter indicated by the first indication information as the first information.

[0347] The first indication information is used to indicate the second adaptation parameter.

[0348] Option 5 is applicable to a scenario in which the applicable duration of the preset model is related to the adaptation parameter of the network device. In this scenario, the terminal only obtains the first adaptation parameter from the network device, and determines the total profit of the preset model based on the first adaptation parameter.

[0349] In option 5, the first adaptation parameter determined by the terminal is used to represent a second duration of the preset model related to the network device. For example, the preset model is in the duration of the configuration C and the configuration D adapted by the network device. The terminal determines the total profit of the preset model based on the product of the second duration and the unit profit of the preset model.

[0350] In addition, the second adaptation parameter can be used to represent at least one of: a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit profit of the preset model determined by the network device; or, a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total profit value of the preset model related to the network device; the present application does not limit this.

[0351] Option 6, the terminal determines the first adaptation parameter related to the preset model from the adaptation parameter stored in the terminal, and determines the second adaptation parameter according to the first indication information from the network device; the terminal determines the first adaptation parameter and the second adaptation parameter as the first information.

[0352] Option 6 is applicable to a scenario in which the applicable duration of the preset model is related to the adaptation parameter of the network device and the adaptation parameter of the terminal. In this scenario, the terminal obtains the second adaptation parameter from the network device, and obtains the first adaptation parameter from the terminal. After that, the terminal determines the total profit of the preset model according to the first adaptation parameter and the second adaptation parameter.

[0353] In the manner 6, the first adaptation parameter determined by the terminal includes a first time length, and the second adaptation parameter includes a second time length. For example, the first time length is the time length of the preset model in the scene A and the scene B adapted by the terminal, and the second time length is the time length of the configuration C and the configuration D adapted by the network device. The terminal determines the intersection of the first time length and the second time length, and determines the total income of the preset model based on the product of the time length of the intersection and the unit income of the preset model; or the terminal determines the difference value between the intersection of the first time length and the second time length and the transmission delay of the preset model, and determines the total income of the preset model based on the product of the time length of the difference value and the unit income of the preset model.

[0354] It should be noted that the unit income of the preset model in the above manners can be determined by the terminal, or can be determined by the network device and then sent to the terminal, which is not limited in the present application.

[0355] As shown in FIG. 11, in the manner 6 of the scene 2, the terminal obtaining the first information and triggering the transmission or the process of triggering the activation of the preset model can be implemented through the following steps 1101 to 1107.

[0356] In step 1101, the network device sends first indication information to the terminal. Correspondingly, the terminal receives the first indication information from the network device.

[0357] In some embodiments, the network device identifies the application scenario of the terminal, and determines the preset model corresponding to the application scenario. After that, the network device determines the configuration information of the network device, and determines the configuration applicable to the preset model. The network device determines the second time length based on the start time and the end time of the configuration applicable to the preset model of the network device. The network device determines the model size of the preset model and the network transmission performance (such as the channel condition of the time of transmitting the preset model), and determines the transmission delay of the preset model according to the model size of the preset model and the network transmission performance. The network device determines the second adaptation parameter based on at least one of the start time, the end time, the second time length, or the transmission delay of the above configuration of the preset model.

[0358] In a possible implementation manner, the first indication information includes at least one of the following information: the identifier of the preset model, the start time, the end time, or the second time length of the preset model related to the network device.

[0359] In step 1102, the terminal determines the first adaptation parameter related to the preset model from the adaptation parameters stored in the terminal.

[0360] After that, the terminal determines a unit reward of the preset model, a start time of the preset model, and a first duration of the preset model. The terminal determines the first adaptation parameter based on the above information. Optionally, the first adaptation parameter further includes an end time of the preset model. The first duration of the preset model is a duration between a duration of completing transmission and activating the preset model and an end time of ending using the preset model.

[0361] It should be noted that the unit reward of the preset model determined by the terminal can include unit rewards of the preset model in different quantization manners and model sizes in different quantization manners.

[0362] In step 1103, the terminal determines the first performance of the preset model based on the second adaptation parameter and the first adaptation parameter.

[0363] In some embodiments, the terminal determines an applicable duration of the preset model based on the first duration in the first adaptation parameter, the second duration in the second adaptation parameter, and a transmission delay of the preset model. The terminal determines the first performance of the preset model based on a product of the unit reward of the preset model in the first adaptation parameter and the duration of the preset model.

[0364] In step 1104, the terminal sends second indication information to the network device in a case where the first performance meets a first preset condition.

[0365] In a case where the network device determines that the first performance meets the first preset condition, the terminal sends the second indication information to the network device to request the network device to send the preset model to the terminal.

[0366] In step 1105, the network device sends the preset model to the terminal. Correspondingly, the terminal receives the preset model from the network device.

[0367] Optionally, in a scenario where the network device activates the preset model, step 1104 and step 1105 can be replaced by the following step 1106 and step 1107:

[0368] In step 1106, the terminal sends fourth indication information to the network device. Correspondingly, the network device receives the fourth indication information from the terminal.

[0369] The fourth indication information is used to request or instruct the network device to activate the preset model.

[0370] In some embodiments, in a case where the fourth indication information is used to instruct the network device to activate the preset model, the terminal can send the fourth indication information to the network device to instruct the network device that the preset model has been activated by the terminal after activating the preset model.

[0371] In step 1107, the network device instructs the terminal to activate the preset model. Correspondingly, the terminal activates the preset model.

[0372] In this step 1107, the network device does not send the preset model to the terminal, but instructs or requests the terminal to activate the preset model, so that the terminal uses the activated model.

[0373] It should be noted that FIG. 11 only illustrates the process of the terminal obtaining the first information and triggering the transmission or triggering the activation of the preset model in the manner 6 of the scenario 2. The process of the terminal obtaining the first information and triggering the transmission or triggering the activation of the preset model in the manners 4 and 5 can be understood with reference to FIG. 11, and only needs to adaptively adjust the process of obtaining the first information based on the required adaptation parameters, which will not be described herein again.

[0374] It can be understood that the present application does not limit the sequence of the above-mentioned step 1101 and step 1102. In specific implementation, the step 1101 can be executed first and then the step 1102 can be executed, or the step 1102 can be executed first and then the step 1101 can be executed, or the step 1101 and the step 1102 can be executed simultaneously, which will not be limited by the present application. In addition, in some manners, the step 1102 can not be executed, that is, the first adaptation parameter is not obtained, and correspondingly, the network device can not include the first adaptation parameter in the step 1103, that is, the network device only obtains the second adaptation parameter and determines the first performance of the preset model based on the second adaptation parameter. The present application will not be described again.

[0375] The above, in combination with different scenarios, the process of determining the first information and triggering the transmission or triggering the activation of the preset model for the network device and the terminal is described in detail.

[0376] In some implementation manners, the preset model corresponds to at least two quantization manners; the model size and the model performance of the preset model are different under different quantization manners; wherein, the adaptation parameters include adaptation parameters corresponding to different quantization manners under at least two quantization manners; in the case that the first performance of the preset model meets the first preset condition, triggering the transmission or triggering the activation of the preset model, comprising: in the case that the first performance of the preset model corresponding to the first quantization manner meets the first preset condition, triggering the transmission or triggering the activation of the preset model corresponding to the first quantization manner, wherein, the first quantization manner is a quantization manner meeting the second preset condition in the at least two quantization manners. In this way, in the case that the preset model corresponds to at least two quantization manners, the first node can select a quantization manner from the multiple quantization manners, which can make the preset model meet the second preset condition, and quantize the preset model, thereby further improving the benefit of the transmitted preset model.

[0377] In some embodiments, as shown in FIG. 12, a schematic diagram of model size and model performance of two quantization manners of determining a preset model by a terminal and a network device provided in embodiments of the present application, and time delay corresponding to the two quantization manners respectively.

[0378] In a possible implementation, the second preset condition comprises at least one of the following: the first performance determined based on the sixth performance of the preset model and the model size is maximum; the sixth performance of the preset model is maximum in a case where the model size of the preset model is less than or equal to a first threshold; the model size of the preset model is minimum in a case where the sixth performance of the preset model is greater than or equal to a second threshold; the first performance of the preset model is greater than or equal to a preset threshold; wherein the sixth performance is a second performance and / or a third performance in the first adaptation parameter, and / or a fourth performance and / or a fifth performance in the second adaptation parameter; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value of the preset model related to the terminal; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value of the preset model related to the network device.

[0379] In this way, when the second preset condition is that the first performance determined based on the sixth performance of the preset model and the model size is maximum, the first node can select a quantization manner that maximizes the benefit value of the preset model to quantize the preset model.

[0380] When the second preset condition is that the sixth performance of the preset model is maximum in a case where the model size of the preset model is less than or equal to the first threshold, the first node can select a quantization manner that has the maximum benefit from the quantization manners whose transmission resources (or transmission time delays) required for transmission meet the demand to quantize the preset model.

[0381] When the second preset condition is that the model size of the preset model is minimum in a case where the sixth performance of the preset model is greater than or equal to the second threshold, the first node can select a quantization manner that has the minimum transmission resources (or transmission time delays) required for transmission from the quantization manners whose model benefits meet the demand to quantize the preset model.

[0382] When the second preset condition is that the first performance of the preset model is greater than or equal to the preset threshold, the first node can select a quantization manner whose total benefit of the preset model meets the demand to quantize the preset model.

[0383] In some embodiments, when the first node quantizes the preset model, the performance of each index of the preset model is different under different quantization manners. Accordingly, when the first node determines the total benefit of the preset model, the total benefit of the preset model is determined based on the performance of each index of the preset model after quantization. In other words, the performance of each evaluation index in one or more evaluation indexes comprises the performance of each evaluation index under at least two quantization manners.

[0384] Based on this, the first node can further determine the performance of an evaluation index under each quantization manner based on different quantization manners.

[0385] The above mainly introduces the scheme provided by the embodiments of the present application from the perspective of interaction between network elements. Correspondingly, the embodiments of the present application further provide a communication apparatus for implementing the above various methods. The communication apparatus can be the first node in the above method embodiments, or a device containing the above first node, or a component applicable to the first node; the communication apparatus can be the network equipment in the above method embodiments, or a device containing the above network equipment, or a component applicable to the network equipment; or the communication apparatus can be the terminal in the above method embodiments, or a device containing the above terminal, or a component applicable to the terminal. It can be understood that, in order to implement the above functions, the communication apparatus contains the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed in the present application, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0386] The embodiments of the present application can divide the functions of the communication apparatus according to the method embodiments described above, for example, each function module can be divided according to each function, or two or more functions can be integrated in one processing module. The integrated module can be realized in the form of hardware or software function module. It should be understood that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. There can be another division method when actually implemented.

[0387] For example, FIG. 13 is a schematic diagram of a communication apparatus 1300 provided by the embodiments of the present application, which includes a transceiver module 1310. Optionally, a processing module 1320 is included. The transceiver module 1310, which can also be called a transceiver unit, is used to implement the transceiving function, for example, can be a transceiving circuit, a transceiver, a transceiver or a communication interface.

[0388] In a possible implementation, the first adaptation parameter is used to represent at least one of the following: a first time length related to the preset model and the terminal; a second performance of the preset model; the second performance is used to represent a unit profit of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total profit value related to the preset model and the terminal.

[0389] In a possible implementation, the first adaptation parameter is used to represent at least one of the following: a first time length related to the preset model and the terminal; a second performance of the preset model; the second performance is used to represent a unit profit of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total profit value related to the preset model and the terminal.

[0390] In a possible implementation, the first adaptation parameter is used to represent at least one of the following: a first time length related to the preset model and the terminal; a second performance of the preset model; the second performance is used to represent a unit profit of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total profit value related to the preset model and the terminal.

[0391] In a possible implementation, the second adaptation parameter is used to represent at least one of the following: a second time length related to the preset model and the network device; a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit profit of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total profit value related to the preset model and the network device.

[0392] In a possible implementation, the second adaptation parameter is used to represent at least one of the following: a second time length related to the preset model and the network device; a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit profit of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total profit value related to the preset model and the network device.

[0393] In a possible implementation, the first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; the second adaptation parameters are used to represent a second time length related to the network device of the preset model; the first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; wherein the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model; the sixth performance is a second performance and / or a third performance in the first adaptation parameters, and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model.

[0394] In a possible implementation, the first information comprises first adaptation parameters and / or second adaptation parameters; the first adaptation parameters are used to represent a first time length related to the terminal of the preset model; the second adaptation parameters are used to represent a second time length related to the network device of the preset model; the first performance of the preset model is determined based on the first information, comprising: the first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; wherein the applicable time length of the preset model is determined based on the first time length related to the terminal of the preset model and / or the second time length related to the network device of the preset model, and a transmission delay of the preset model between the terminal and the network device; the sixth performance is a second performance and / or a third performance in the first adaptation parameters, and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; the fifth performance is used to represent a total benefit value related to the network device of the preset model; and the transmission delay of the preset model between the terminal and the network device is a transmission delay in the first adaptation parameters or a transmission delay in the second adaptation parameters.

[0395] In a possible implementation, the transmission delay of the preset model between the terminal and the network device is determined based on a model size of the transmitted preset model and a transmission performance between the terminal and the network device.

[0396] In a possible implementation, the preset model corresponds to at least two quantization manners; the preset model has different model sizes and different model performances in different quantization manners; the adaptation parameters include adaptation parameters corresponding to different quantization manners in the at least two quantization manners; in a case where the first performance of the preset model meets the first preset condition, triggering transmission or triggering activation of the preset model includes: in a case where the first performance of the preset model corresponding to the first quantization manner meets the first preset condition, triggering transmission or triggering activation of the preset model corresponding to the first quantization manner, where the first quantization manner is a quantization manner that meets the second preset condition in the at least two quantization manners.

[0397] In a possible implementation, the second preset condition includes at least one of the following: the first performance determined based on the sixth performance of the preset model and the model size is maximum; in a case where the model size of the preset model is less than or equal to a first threshold, the sixth performance of the preset model is maximum; in a case where the sixth performance of the preset model is greater than or equal to a second threshold, the model size of the preset model is minimum; the first performance of the preset model is greater than or equal to a preset threshold; where the sixth performance is a second performance and / or a third performance in the first adaptation parameters, and / or a fourth performance and / or a fifth performance in the second adaptation parameters; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal of the preset model; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device of the preset model.

[0398] In a possible implementation, in a case where the first node is the terminal, the processing module 1320 is specifically configured to determine the first adaptation parameter related to the preset model from the adaptation parameter stored by the terminal; and / or, the transceiver module 1310 is specifically configured to receive first indication information from the network device; the first indication information is used to indicate the second adaptation parameter.

[0399] In a possible implementation, in a case where the first node is the terminal, the transceiver module 1310 is specifically configured to send second indication information to the network device, the second indication information being used to indicate that the network device sends the preset model to the terminal.

[0400] In a possible implementation, in a case where the first node is the terminal, the transceiver module 1310 is specifically configured to send fourth indication information to the network device, the fourth indication information being used to request or indicate that the network device activates the preset model.

[0401] In a possible implementation, in the case where the first node is a network device, the processing module 1320 is specifically configured to determine the second adaptation parameter related to the preset model from the adaptation parameters stored by the network device; and / or, the transceiver module 1310 is specifically configured to receive third indication information from the terminal, the third indication information being used to indicate the first adaptation parameter.

[0402] In a possible implementation, in the case where the first node is a network device, the transceiver module 1310 is specifically configured to send the preset model to the terminal, or request the terminal to send the preset model.

[0403] In a possible implementation, in the case where the first node is a network device, the transceiver module 1310 is specifically configured to instruct the terminal to activate the preset model, or request the terminal to activate the preset model.

[0404] In a possible implementation, the first performance of the preset model includes the performance of one or more evaluation indexes in a plurality of evaluation indexes of the preset model.

[0405] In a possible implementation, the one or more evaluation indexes are evaluation indexes selected from the plurality of evaluation indexes based on network parameters of the network device.

[0406] In a possible implementation, the performance of each evaluation index in the one or more evaluation indexes includes the performance of each evaluation index in at least two quantization manners.

[0407] Based on this, the first node can further determine the performance of an evaluation index in each quantization manner based on different quantization manners.

[0408] The above method embodiments involve all related contents of each step, which can be referred to the function description of the corresponding function module, and will not be repeated here. Optionally, the communication apparatus 1300 can further include a storage module 1330, which can be used to store instructions or and / or data, and the processing module 1320 can read the instructions or and / or data in the storage module 1330.

[0409] In the embodiments of the present application, the communication apparatus 1300 is presented in the form of dividing various function modules in an integrated manner. The "module" here can refer to a specific application specific integrated circuit (ASIC), a circuit, a processor and a memory executing one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions. In a simple embodiment, those skilled in the art can think that the communication apparatus can adopt the form of the communication apparatus 700 shown in FIG. 7.

[0410] Specifically, the functions / implementation procedures of the transceiver module 1310 and the processing module 1320 in FIG. 13 can be implemented by invoking the computer-executed instructions stored in the memory 72 by the processor 71 in the communication apparatus 700 shown in FIG. 7. Alternatively, the functions / implementation procedures of the processing module 1320 in FIG. 13 can be implemented by invoking the computer-executed instructions stored in the memory 72 by the processor 71 in the communication apparatus 700 shown in FIG. 7, and the functions / implementation procedures of the transceiver module 1310 in FIG. 13 can be implemented by the transceiver 75 in the communication apparatus 700 shown in FIG. 7.

[0411] Since the communication apparatus provided by the embodiments of the present application can perform the above communication method, the technical effects that can be obtained thereby can refer to the above method embodiments, which will not be repeated here.

[0412] It should be understood that one or more of the above modules or units can be implemented in software, hardware, or a combination of both. When any of the above modules or units is implemented in software, the software exists in the form of computer program instructions, and is stored in a memory. The processor can be used to execute the program instructions and implement the above method flow. The processor can be built in a SoC (System on Chip) or an ASIC, or be a separate semiconductor chip. The processor further includes a core for executing software instructions to perform operations or processing, and can further include necessary hardware accelerators, such as a field programmable gate array (FPGA), a programmable logic device (PLD), or a logic circuit for implementing special logic operations.

[0413] When any of the above modules or units is implemented in hardware, the hardware can be any one or any combination of a central processing unit (CPU), a microprocessor, a digital signal processing (DSP) chip, a microcontroller unit (MCU), an artificial intelligence processor, an ASIC, a SoC, a FPGA, a PLD, a dedicated digital circuit, a hardware accelerator, or a non-integrated discrete device, which can run necessary software or be independent of software to perform the above method flow.

[0414] Optionally, the embodiments of the present application further provide a communication apparatus (for example, the communication apparatus can be a chip or a chip system), which comprises a processor, and the processor is configured to implement the method in any of the method embodiments. In a possible design, the communication apparatus further comprises a memory. The memory is configured to store necessary program instructions and data, and the processor can invoke the program instructions stored in the memory to instruct the communication apparatus to perform the method in any of the method embodiments. Of course, the memory can also not be in the communication apparatus. When the communication apparatus is a chip system, the communication apparatus can be composed of a chip, or can comprise a chip and other discrete devices, and the embodiments of the present application do not make a specific limitation in this regard.

[0415] Optionally, the embodiments of the present application further provide a computer readable storage medium, which stores a computer program or instructions, and when the computer program or instructions are executed on a communication apparatus, the communication apparatus can perform the method in any of the method embodiments or any of the implementation manners thereof.

[0416] Optionally, the embodiments of the present application further provide a communication system, which comprises the network device in the method embodiments and the terminal in the method embodiments.

[0417] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or data storage device such as one or more servers, data centers, etc. integrated with one or more media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD) or semiconductor media (for example, solid state disk (SSD)) and the like.

[0418] Although the application has been described in connection with the embodiments thereof with reference to the various drawings, it will be understood that other variations and modifications of the details, and specific examples can be resorted to by those skilled in the art without departing from the scope of the application. It will be noted that the term "comprising" does not, by itself, exclude other components or steps, and the singular return to plural is not excluded unless otherwise indicated. A single processor or other unit can fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0419] Although the application has been described in connection with specific embodiments thereof, it will be understood that it is capable of modifications and that the particular embodiments set forth are meant to be illustrative only and not as limiting the scope of the application. Accordingly, the specification and drawings are to be regarded simply as illustrative and the scope of the application is to be determined solely by the claims that follow. Obviously, many modifications and variations of this application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the claims, the application can be practiced otherwise than as specifically described.

Claims

1. A communication method characterized by comprising: The method is applied to a first node, and the method comprises: obtaining first information; the first information comprises at least one of a first adaptation parameter or a second adaptation parameter, wherein the first adaptation parameter is an adaptation parameter of a preset model and a terminal, and the second adaptation parameter is an adaptation parameter of the preset model and a network device; the adaptation parameter is a parameter related to a first performance of the preset model; the first performance is used to represent a total revenue value of the preset model; in a case where the first performance of the preset model meets a first preset condition, triggering transmission or triggering activation of the preset model, wherein the first performance of the preset model is determined based on the first information.

2. The method of claim 1, wherein, The first adaptation parameter is used to represent at least one of: a first time length related to the terminal of the preset model; a second performance of the preset model; the second performance is used to represent a unit revenue of the preset model determined by the terminal; a transmission delay of the preset model between the terminal and the network device; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total revenue value of the preset model related to the terminal.

3. The method according to claim 1 or 2, characterized in that, The first adaptation parameter comprises at least one of: a transmission delay of the preset model between the terminal and the network device; a start time related to the terminal of the preset model; an end time related to the terminal of the preset model; a duration related to the terminal of the preset model; a second performance of the preset model; the second performance is used to represent a unit revenue of the preset model determined by the terminal; or a third performance of the preset model determined by the terminal; the third performance is used to represent a total revenue value of the preset model related to the terminal.

4. The method according to any one of claims 1 to 3, characterized in that, The second adaptation parameter is used to represent at least one of: a second time length related to the network device of the preset model; a transmission delay of the preset model between the terminal and the network device; a fourth performance of the preset model; the fourth performance is used to represent a unit revenue of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total revenue value of the preset model related to the network device.

5. The method according to any one of claims 1 to 4, characterized in that, The second adaptation parameter comprises at least one of: a transmission delay of the preset model between the terminal and the network device; a start time related to the network device of the preset model; an end time related to the network device of the preset model; a duration related to the network device of the preset model; a fourth performance of the preset model; the fourth performance is used to represent a unit revenue of the preset model determined by the network device; or a fifth performance of the preset model determined by the network device; the fifth performance is used to represent a total revenue value of the preset model related to the network device.

6. The method according to any one of claims 1 to 5, characterized in that, The first information comprises the first adaptation parameter and / or the second adaptation parameter; the first adaptation parameter is used to represent a first time length related to the terminal of the preset model; The second adaptation parameter is used to represent a second time length related to the network device. The first performance of the preset model is determined based on the first information, including: The first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; the applicable time length of the preset model is determined based on a first time length related to the terminal, a second time length related to the network device and a transmission / activation time delay between the terminal and the network device; the sixth performance is a second performance and / or a third performance in the first adaptation parameter and / or a fourth performance and / or a fifth performance in the second adaptation parameter; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device.

7. The method according to any one of claims 1 to 5, characterized in that, The first information includes a first adaptation parameter and / or a second adaptation parameter; the first adaptation parameter is used to represent a first time length related to the terminal. The second adaptation parameter is used to represent a second time length related to the network device. The first performance of the preset model is determined based on the first information, including: The first performance of the preset model is determined based on a sixth performance of the preset model and an applicable time length of the preset model; the applicable time length of the preset model is determined based on a first time length related to the terminal, a second time length related to the network device and a transmission / activation time delay between the terminal and the network device; the sixth performance is a second performance and / or a third performance in the first adaptation parameter and / or a fourth performance and / or a fifth performance in the second adaptation parameter; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value related to the terminal; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value related to the network device; and the transmission / activation time delay between the terminal and the network device is a time delay in the first adaptation parameter or a time delay in the second adaptation parameter.

8. The method according to any one of claims 4-7, characterized in that, The transmission / activation time delay of the preset model between the terminal and the network device is determined based on a model size of the transmitted preset model and a transmission / activation performance between the terminal and the network device.

9. The method according to any one of claims 1 to 8, characterized in that, The preset model corresponds to at least two quantization manners; the model size and the model performance of the preset model are different under different quantization manners; the adaptation parameter includes adaptation parameters corresponding to different quantization manners under the at least two quantization manners; in a case where the first performance of the preset model meets a first preset condition, the preset model is triggered to be transmitted or activated, including: In a case where a first performance of the preset model corresponding to the first quantization manner meets a first preset condition, the preset model corresponding to the first quantization manner is triggered to be transmitted or activated, wherein the first quantization manner is a quantization manner that meets a second preset condition among the at least two quantization manners.

10. The method of claim 9, wherein, The second preset condition comprises at least one of the following: The first performance determined based on the sixth performance of the preset model and the model size is maximum. In a case where the model size of the preset model is less than or equal to a first threshold, the sixth performance of the preset model is maximum. In a case where the sixth performance of the preset model is greater than or equal to a second threshold, the model size of the preset model is minimum. The first performance of the preset model is greater than or equal to a preset threshold. The sixth performance is a second performance and / or a third performance in the first adaptation parameter, and / or a fourth performance and / or a fifth performance in the second adaptation parameter; the second performance is used to represent a unit benefit of the preset model determined by the terminal; the third performance is used to represent a total benefit value of the preset model related to the terminal; the fourth performance is used to represent a unit benefit of the preset model determined by the network device; and the fifth performance is used to represent a total benefit value of the preset model related to the network device.

11. The method according to any one of claims 1 to 10, characterized in that, In a case where the first node is a terminal, the first information is obtained by: determining, from adaptation parameters stored by the terminal, first adaptation parameters related to the preset model; and / or receiving first indication information from a network device; the first indication information is used to indicate the second adaptation parameters.

12. The method of claim 11, wherein, The preset model is triggered to be transmitted by: sending, to the network device, second indication information used to request or indicate that the network device transmits the preset model to the terminal.

13. The method of claim 11, wherein, The preset model is triggered to be activated by: sending, to the network device, fourth indication information used to request or indicate that the network device activates the preset model.

14. The method according to any one of claims 1 to 13, characterized in that, In a case where the first node is a network device, the first information is obtained by: determining, from adaptation parameters stored by the network device, second adaptation parameters related to the preset model; and / or receiving third indication information from a terminal; the third indication information is used to indicate the first adaptation parameters.

15. The method of claim 14, wherein, The preset model is triggered to be transmitted by: sending, to the terminal, the preset model, or requesting the terminal to send the preset model.

16. The method of claim 14, wherein, The preset model is triggered to be activated by: indicating the terminal to activate the preset model, or requesting the terminal to activate the preset model.

17. The method according to any one of claims 1 to 16, characterized in that, The first performance of the preset model comprises performances of one or more evaluation indexes in a plurality of evaluation indexes of the preset model.

18. The method of claim 17, wherein, The one or more evaluation indexes are evaluation indexes selected from the plurality of evaluation indexes based on network parameters of the network device and / or parameters of the terminal.

19. The method of claim 18, wherein, The performance of each evaluation index in the one or more evaluation indexes comprises performances of the each evaluation index in at least two quantization manners.

20. A communications device, characterized by ​ A functional unit configured to perform the method according to any one of claims 1-19; wherein the actions performed by the functional unit are implemented by hardware or by hardware executing corresponding software.

21. A communications device, characterized by comprising: a processor; the processor is connected with a memory, the memory is used to store computer execution instructions, the processor executes the computer execution instructions stored in the memory, so that the communication device implements the method according to any one of claims 1-19.

22. A computer-readable storage medium, characterized in that, instructions that, when executed on a computer, cause the computer to perform the method according to any one of claims 1-19.

23. A chip, characterized by the chip comprises a processor; the processor is connected with a memory, the memory is used to store computer execution instructions, the processor executes the computer execution instructions stored in the memory, so that the communication device implements the method according to any one of claims 1-19.

24. A computer program product comprising instructions, characterized in that, when it is executed on a communication device, it makes the communication device implement the method according to any one of claims 1-19.

Images