Model training method, model deployment method, and communication method and apparatus

Abstract

Provided in the present application are a model training method, a model deployment method, and a communication method and apparatus. In an embodiment, the model training method comprises: acquiring a sample, wherein the sample comprises impact information of a radio channel, the radio channel being a path between a first communication apparatus and a second communication apparatus, and the impact information comprising a physical environment of a radio communication network formed by the first communication apparatus, and the position of the second communication apparatus in the radio communication network, and the sample corresponds to a modulation coding scheme (MCS) index value of an MCS; and by using the sample as an input and an MCS index ranking corresponding to the sample as an output, training an MCS index ranking model to obtain a trained MCS index ranking model, wherein the MCS index ranking model is used for outputting the MCS index ranking. Thus, by considering a physical environment of a radio communication network and the position of a communication apparatus in the radio communication network, an MCS ranking model can output an MCS index ranking more accurately; and an MCS index value is determined on the basis of the MCS index ranking.

Description

Model training method, model deployment method, communication method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on February 20, 2024, with application number 202410191078.X and application name “Model training method, model deployment method, communication method and device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a model training method, a model deployment method, a communication method and a device. Background Art

[0003] Currently, in some communication technologies, an MCS configuration scheme is provided for channel data transmission through one or more modulation coding scheme (MCS) tables. Network devices and terminal devices can select the MCS table through parameters configured by radio resource control (RRC) signaling. The MCS table includes multiple numbers, each number is called an MCS index value, and each MCS index value corresponds to a coding modulation scheme. After configuring the MCS table, the network device can determine the MCS index value based on the wireless channel information through a link adaptation algorithm, and send the determined MCS index value to the terminal device through downlink control information (DCI). Currently, an alternative solution for determining the MCS index value is urgently needed. Summary of the Invention

[0004] The embodiments of the present application provide a model training method, a model deployment method, a communication method and a device. The MCS sorting model can output the MCS index sorting more accurately by considering the physical environment of the wireless communication network and the location of the communication device in the wireless communication network. Subsequently, the MCS index value of the adapted wireless channel is determined based on the MCS index sorting.

[0005] In a first aspect, an embodiment of the present application provides a model training method, comprising:

[0006] Acquire samples, where the samples include impact information of a wireless channel, where the wireless channel is a path between a first communication device, such as a base station, and a second communication device, such as a mobile phone. The impact information includes description information of the physical environment of the wireless communication network formed by the first communication device and description information of the position of the second communication device in the wireless communication network. The description information of the physical environment includes description information of the position of the first communication device. The samples correspond to the MCS index value of the modulation and coding scheme. With the samples as input and the MCS index value corresponding to the samples as output, an MCS index sorting model is trained to obtain a trained MCS index sorting model.

[0007] In this solution, the MCS ranking model can output the MCS index ranking more accurately by considering the physical environment of the wireless communication network and the location of the communication device in the wireless communication network. Subsequently, the MCS index value of the adapted wireless channel is determined based on the MCS index ranking.

[0008] In one possible implementation, the trained MCS index ranking model is used to store the correspondence between each of multiple location points in the wireless communication network and a wireless channel, and the correspondence between the wireless channel and the MCS index ranking. The location point indicates the location of the second communication device in the wireless communication network. It should be understood that the location point can be a physical location point or a logical or virtual location point, such as a set of areas.

[0009] In this solution, the MCS sorting model learns the correspondence between each of multiple location points in the wireless communication network and the wireless channel, and the correspondence between the wireless channel and the MCS index sorting by considering the physical environment of the wireless communication network and the location of the second communication device in the wireless communication network, thereby improving the reference value of the MCS index sorting output by the MCS sorting model.

[0010] In a possible implementation, the sample corresponds to one or more MCS index values, and the multiple MCS index values ​​are arranged in sequence.

[0011] In a possible implementation, the sample further includes auxiliary information corresponding to the second communication apparatus, where the auxiliary information indicates information affecting the MCS index sorting in addition to the influencing information.

[0012] In one possible implementation, the auxiliary information corresponding to the second communication device includes one or more of the following:

[0013] Communication parameters of the wireless communication network and / or communication parameters of the second communication device; the communication parameters of the second communication device include an identifier of an MCS table, and the MCS table is used to record a mapping relationship between multiple MCS index values ​​and coding modulation schemes.

[0014] In one possible implementation, the MCS index sorting model includes a first module and a second module. The first module is used to output description information of the wireless channel between the first communication device and the second communication device based on samples; the second module is used to output the MCS index sorting based on the output of the first module.

[0015] In one possible implementation, the MCS index sorting model includes a first module and a second module, wherein the first module is used to output description information of the wireless channel between the first communication device and the second communication device based on the impact information of the wireless channel; and the second module is used to output the MCS index sorting based on the output of the first module and the auxiliary information corresponding to the second communication device.

[0016] In a second aspect, an embodiment of the present application provides a model deployment method, including:

[0017] Obtain descriptive information of the available hardware resources of the second communication device; based on the descriptive information, determine a model deployment plan, the model deployment plan indicating the content of the MCS index sorting model deployed on the first communication device and the second communication device, the MCS index sorting model being trained by the method provided by the first aspect; deploy at least part of the MCS index sorting model according to the model deployment plan.

[0018] In this solution, the MCS index sorting model is deployed according to the storage capacity and computing power of the second communication device, which can not only fully utilize the storage capacity and computing power of the second communication device, but also avoid bringing excessive storage and computing overhead to the second communication device, thereby ensuring the normal use of subsequent MCS index sorting models.

[0019] In a possible implementation, the model deployment solution is to deploy the first module on a first communication device and the second module on a second communication device.

[0020] In some possible implementations, the model deployment scheme includes a first bit value and a second bit value, the first bit value is used to indicate that the first module is deployed on the first communication device or the second communication device, and the second bit value is used to indicate that the second module is deployed on the first communication device or the second communication device.

[0021] In a possible implementation, deploying the MCS index sorting model according to the model deployment solution includes sending content of the MCS index sorting model deployed on the second communication device to the second communication device, so that the second communication device deploys the content.

[0022] In one possible implementation, the MCS index sorting model is deployed according to the model deployment scheme, including: sending the model deployment scheme to the second communication device, and sending the identifier of the second communication device and the model deployment scheme to other communication devices that communicate with the second communication device, so that the second communication device obtains the content of the MCS index sorting model deployed in the second communication device from the other communication devices.

[0023] In one possible implementation, deploying the MCS index sorting model according to the model deployment plan includes: sending the model deployment plan to the second communication device so that the second communication device obtains the content of the MCS index sorting model deployed in the second communication device from other communication devices communicating with it.

[0024] In a possible implementation manner, the model deployment method is applied to a first communication device.

[0025] In a third aspect, an embodiment of the present application provides a communication method, applied to a first communication device, the method comprising:

[0026] Receive location information sent by a second communication device, where the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; run an MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained using the method provided by the first aspect; determine a target MCS index value based on the MCS index sorting; and send the target MCS index value to the second communication device.

[0027] In this solution, the second communication device does not need to feed back wireless channel information, thereby solving the signaling overhead of the second communication device and improving communication efficiency.

[0028] In one possible implementation, running an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device includes:

[0029] An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0030] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0031] In one possible implementation, the method further includes:

[0032] Receive the changed location information sent by the second communication device; run the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or run the MCS index sorting model based on the changed location information, auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0033] In this solution, when the location of the second communication device changes, the physical environment of the wireless communication network can be reused, thereby reducing the overhead of information transmission.

[0034] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0035] In one possible implementation, the method further includes: updating the target index value based on feedback information and MCS index sorting of the second communication device; the feedback information indicates a situation where communication is performed according to a coding modulation scheme indicated by the target MCS index value.

[0036] In a fourth aspect, an embodiment of the present application provides a communication method, applied to a first communication device, the method comprising:

[0037] Receive wireless channel information and location information sent by a second communication device, the wireless channel information indicating the status of the wireless channel between the second communication device and the first communication device; the location information indicating the location of the second communication device in the wireless communication network formed by the first communication device; determine the standard MCS index value based on the wireless channel information; run the deployed MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to determine the MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by the method provided by the first aspect; determine the target sequence number based on the MCS index sorting and the standard MCS index value; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting; send the target sequence number to the second communication device, so that the second communication device runs the deployed MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and determines the target MCS index value based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

[0038] In this solution, the sequence number is sent instead of the MCS index value, thereby reducing the communication overhead and improving the communication efficiency.

[0039] According to a feasible implementation, when the sequence number of the standard MCS index value in the MCS index sorting is less than or equal to the MCS index value threshold, the target MCS index value is the standard index value.

[0040] According to a feasible implementation method, when the sequence number of the standard MCS index value in the MCS index sorting is greater than the MCS index value threshold, the target MCS index value is less than or equal to the MCS index value threshold in the MCS index sorting and has the smallest difference with the standard MCS index value.

[0041] According to a feasible implementation method, the method also includes: updating the target index value based on the feedback information, standard index value, target index value and MCS index sorting of the second communication device; the feedback information indicates the situation of communicating according to the coding modulation scheme indicated by the target MCS index value.

[0042] In one possible implementation, running an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device includes:

[0043] An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0044] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0045] In one possible implementation, the method further includes:

[0046] Receive the changed location information sent by the second communication device; run the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or run the MCS index sorting model based on the changed location information, auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0047] In a fifth aspect, an embodiment of the present application provides a communication method, applied to a first communication device, the method comprising:

[0048] Receive location information sent by the second communication device, where the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; run the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain the description information of the wireless channel output by the first module; send the description information of the wireless channel to the second communication device, so that the second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting.

[0049] In this solution, the second communication device does not need to feed back wireless channel information, thereby solving the signaling overhead of the second communication device and improving communication efficiency.

[0050] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0051] In one possible implementation, the method further includes:

[0052] Receive the changed location information sent by the second communication device; and run the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0053] In a sixth aspect, an embodiment of the present application provides a communication method, applied to a first communication device, the method comprising:

[0054] Receive description information of a wireless channel sent by a second communication device, where the description information of the wireless channel is description information of the physical environment of the wireless communication network formed by the second communication device based on the location information and the first communication device, run the first module in the MCS index sorting model, and the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; based on the description information of the wireless channel, run the second module in the MCS index sorting model, obtain the MCS index sorting output by the second module, and determine the target MCS index value based on the MCS index sorting; and send the target MCS index value to the second communication device.

[0055] In this solution, the second communication device partially feeds back wireless channel information through the MCS index sorting model, thereby reducing signaling overhead and improving communication efficiency.

[0056] In one possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; and based on description information of the wireless channel, run a second module in the MCS index sorting model, including:

[0057] Based on the description information of the wireless channel and the identifier of the MCS table corresponding to the configured second communication device, the second module in the MCS index sorting model is executed.

[0058] In one possible implementation, running the second module in the MCS index sorting model based on the description information of the wireless channel includes:

[0059] Based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device, the second module in the MCS index sorting model is executed.

[0060] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0061] In one possible implementation, the method further includes:

[0062] Receive description information of the changed wireless channel sent by the second communication device; and run the second module in the MCS index sorting model based on the description information of the changed wireless channel.

[0063] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0064] In a seventh aspect, an embodiment of the present application provides a communication method, applied to a second communication device, the method comprising:

[0065] Wireless channel information and location information are sent to the first communication device, where the wireless channel information indicates the status of the wireless channel between the second communication device and the first communication device; the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; so that the first communication device determines the target MCS index value based on the wireless channel information; based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, an MCS index sorting model is run to determine the MCS index sorting output by the MCS index sorting model; based on the MCS index sorting and the standard MCS index value, a target sequence number is determined; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting; the MCS index sorting model is trained by the method of the first aspect; the target sequence number sent by the first communication device is received; and the target MCS index value is determined based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

[0066] In this solution, the sequence number is sent instead of the MCS index value, thereby reducing the communication overhead and improving the communication efficiency.

[0067] In one possible implementation, running an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device includes:

[0068] An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0069] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0070] In one possible implementation, the method further includes:

[0071] Send the changed location information to the first communication device so that the first communication device runs an MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or run the MCS index sorting model based on the changed location information, the description information of the physical environment of the wireless communication network formed by the first communication device and the auxiliary information corresponding to the second communication device.

[0072] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0073] In an eighth aspect, an embodiment of the present application provides a communication method, applied to a second communication device, the method comprising:

[0074] The method includes sending location information to the first communication device, wherein the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; enabling the first communication device to run the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and obtain the description information of the wireless channel output by the first module; receiving the description information of the wireless channel sent by the first communication device; running the second module in the MCS index sorting model based on the description information of the wireless channel, and obtain the MCS index sorting output by the second module, and determining the target MCS index value based on the MCS index sorting.

[0075] In this solution, the second communication device does not need to feed back wireless channel information, thereby solving the signaling overhead of the second communication device and improving communication efficiency.

[0076] In a possible implementation, running the second module in the MCS index sorting model based on the description information of the wireless channel includes: running the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

[0077] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0078] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0079] In one possible implementation, the method further includes:

[0080] The changed location information is sent to the first communication device, so that the first communication device runs the first module in the MCS index sorting model based on the changed location information and description information of the physical environment of the wireless communication network formed by the first communication device.

[0081] In a ninth aspect, an embodiment of the present application provides a communication method, applied to a second communication device, the method comprising:

[0082] Based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, the first module in the MCS index sorting model is run to obtain the description information of the wireless channel output by the first module, and the location information indicates the position of the second communication device in the wireless communication network formed by the first communication device; the description information of the wireless channel is sent to the first communication device, so that the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting; and receives the target MCS index value sent by the first communication device.

[0083] In this solution, the second communication device partially feeds back wireless channel information through the MCS index sorting model, thereby reducing signaling overhead and improving communication efficiency.

[0084] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0085] In one possible implementation, the method further includes:

[0086] Auxiliary information corresponding to the second communication device is sent to the first communication device, so that the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

[0087] In a tenth aspect, an embodiment of the present application provides a communication method, the method comprising:

[0088] The second communication device sends location information to the first communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device;

[0089] The first communication device runs an MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained using the method of the first aspect;

[0090] The first communication device determines a target MCS index value based on the MCS index sorting;

[0091] The first communication device sends a target MCS index value to the second communication device.

[0092] In this solution, the second communication device does not need to feed back wireless channel information, thereby solving the signaling overhead of the second communication device and improving communication efficiency.

[0093] In one possible implementation, the first communication device runs an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device, including:

[0094] An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0095] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0096] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0097] In one possible implementation, the method further includes: the first communication device updates the target index value based on feedback information and MCS index sorting of the second communication device; the feedback information indicates a situation where communication is performed according to a coding modulation scheme indicated by the second MCS index value.

[0098] In one possible implementation, the method further includes:

[0099] The second communication device sends the changed location information to the first communication device;

[0100] The first communication device runs the MCS index sorting model based on the changed position information and the description information of the physical environment of the wireless communication network formed by the first communication device; or runs the MCS index sorting model based on the changed position information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0101] In an eleventh aspect, an embodiment of the present application provides a communication method, the method comprising:

[0102] The second communication device sends wireless channel information and location information to the first communication device, where the wireless channel information indicates the status of the wireless channel between the second communication device and the first communication device; and the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device.

[0103] The first communication device determines a standard MCS index value based on the wireless channel information

[0104] The first communication device runs an MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by the method provided by the first aspect;

[0105] The first communication device determines a target sequence number based on the MCS index sorting and the standard MCS index value; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting;

[0106] The first communication device sends a target sequence number to the second communication device;

[0107] The second communication device runs a deployed MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device;

[0108] The second communication device determines a target MCS index value based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

[0109] In this solution, the sequence number is sent instead of the MCS index value, thereby reducing the communication overhead and improving the communication efficiency.

[0110] According to a feasible implementation, when the sequence number of the standard MCS index value in the MCS index sorting is less than or equal to the MCS index value threshold, the target MCS index value is the standard index value.

[0111] According to a feasible implementation method, when the sequence number of the standard MCS index value in the MCS index sorting is greater than the MCS index value threshold, the target MCS index value is less than or equal to the MCS index value threshold in the MCS index sorting and has the smallest difference with the standard MCS index value.

[0112] According to a feasible implementation method, the method also includes: the first communication device updates the target index value based on the feedback information, standard index value, target index value and MCS index sorting of the second communication device; the feedback information indicates the situation of communicating according to the coding modulation scheme indicated by the target MCS index value.

[0113] According to a feasible implementation, running an MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device includes:

[0114] An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0115] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0116] In one possible implementation, the method further includes:

[0117] The second communication device sends the changed location information to the first communication device;

[0118] The first communication device runs the MCS index sorting model based on the changed position information and the description information of the physical environment of the wireless communication network formed by the first communication device; or runs the MCS index sorting model based on the changed position information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0119] In a twelfth aspect, an embodiment of the present application provides a communication method, the method comprising:

[0120] The second communication device sends location information to the first communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device;

[0121] The first communication device runs the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and obtains the description information of the wireless channel output by the first module;

[0122] The first communication device sends description information of the wireless channel to the second communication device;

[0123] The second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting.

[0124] In this solution, the second communication device does not need to feed back wireless channel information, thereby solving the signaling overhead of the second communication device and improving communication efficiency.

[0125] In one possible implementation, the second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, including: the second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

[0126] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0127] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0128] In one possible implementation, the method further includes:

[0129] The second communication device sends the changed location information to the first communication device;

[0130] The first communication device runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0131] In a thirteenth aspect, an embodiment of the present application provides a communication method, the method comprising:

[0132] The second communication device runs the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain the description information of the wireless channel output by the first module, where the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device;

[0133] The second communication device sends description information of the wireless channel to the first communication device;

[0134] The first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, and obtains the MCS index sorting output by the second module;

[0135] The first communication device determines a target MCS index value based on the MCS index sorting;

[0136] The first communication device sends a target MCS index value to the second communication device.

[0137] In this solution, the second communication device partially feeds back wireless channel information through the MCS index sorting model, thereby reducing signaling overhead and improving communication efficiency.

[0138] In one possible implementation, the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, including: the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

[0139] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0140] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0141] In one possible implementation, the method further includes:

[0142] The second communication device sends description information of the changed wireless channel to the first communication device;

[0143] The first communication device runs the second module in the MCS index sorting model based on the description information of the changed wireless channel; or runs the second module in the MCS index sorting model based on the description information of the changed wireless channel and the auxiliary information corresponding to the second communication device.

[0144] In a fourteenth aspect, an embodiment of the present application provides a wireless communication system, which may include a first communication device and a second communication device, wherein the system is configured to execute the method provided in any one of the tenth to thirteenth aspects.

[0145] In the fifteenth aspect, an embodiment of the present application provides a model training device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method provided in the first aspect.

[0146] In the sixteenth aspect, an embodiment of the present application provides a model deployment device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method provided in the second aspect.

[0147] In the seventeenth aspect, an embodiment of the present application provides a first communication device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method provided in any one of the third to sixth aspects.

[0148] In the eighteenth aspect, an embodiment of the present application provides a second communication device, comprising: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, when the program stored in the memory is executed, the processor is used to execute the method provided in any one of aspects from the seventh to the ninth aspect.

[0149] In the nineteenth aspect, an embodiment of the present application provides a computer storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes any one of the methods provided in the first to thirteenth aspects.

[0150] In the twentieth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any one of the methods provided in the first to thirteenth aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0151] FIG1 is a schematic diagram of an artificial intelligence main body framework provided by an embodiment of the present application;

[0152] FIG2 is a schematic diagram of the architecture of a wireless communication system provided in an embodiment of the present application;

[0153] FIG3 is a schematic diagram of an MCS map provided in an embodiment of the present application;

[0154] FIG4 is a schematic diagram of a header of an MCS table provided in an embodiment of the present application;

[0155] FIG5 is a schematic diagram of a process flow of a processing stage provided in an embodiment of the present application;

[0156] FIG6 is a flow chart of a model training method according to an embodiment of the present application;

[0157] FIG7 is a flow chart of a model deployment method according to an embodiment of the present application;

[0158] FIG8 a is a flow chart of step 703 in FIG7 ;

[0159] FIG8 b is a second flow chart of step 703 in FIG7 ;

[0160] FIG9 is a flow chart of a communication method according to an embodiment of the present application;

[0161] FIG10 is a second flow chart of a communication method according to an embodiment of the present application;

[0162] FIG11 is a third flow chart of a communication method according to an embodiment of the present application;

[0163] FIG12 is a fourth flow chart of a communication method provided on the basis of FIG9 ;

[0164] FIG13 is a flow chart of a communication method provided on the basis of FIG10 ;

[0165] FIG14 is a structural diagram of a model training device provided in an embodiment of the present application;

[0166] FIG15 is a structural diagram of an exemplary model deployment device provided in an embodiment of the present application;

[0167] FIG16 is a structural diagram of a communication method according to an embodiment of the present application;

[0168] FIG17 is a second structural diagram of the communication method provided in an embodiment of the present application;

[0169] FIG18 is a third structural diagram of the communication method provided in an embodiment of the present application;

[0170] FIG19 is a fourth structural diagram of a communication method provided in an embodiment of the present application;

[0171] FIG20 is a fifth structural diagram of a communication method provided in an embodiment of the present application;

[0172] FIG21 is a schematic structural diagram of a first communication device provided in an embodiment of the present application;

[0173] Figure 22 is a structural diagram of the second communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0174] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0175] In the description of the embodiments of the present application, words such as "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of the present application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0176] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "plurality" means two or more. For example, "multiple systems" refers to two or more systems, and "multiple terminals" refers to two or more terminals.

[0177] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly identifying the technical features being referred to. Thus, features specified as "first" or "second" may explicitly or implicitly include one or more of such features. The terms "include," "comprising," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0178] The following is an explanation of some of the terms used in this embodiment. It should be noted that these explanations are for the purpose of facilitating understanding by those skilled in the art and are not intended to limit the scope of protection claimed in this application.

[0179] Long Term Evolution (LTE): is the long-term evolution of the UMTS (Universal Mobile Telecommunications System) technical standards developed by the 3GPP (The 3rd Generation Partnership Project) organization.

[0180] Physical Downlink Shared Channel (PDSCH): used to transmit downlink service data and system messages.

[0181] Physical Uplink Shared Channel (PUSCH): used to transmit uplink service data and can also be used to carry uplink control information (UCI).

[0182] Modulation and Coding Scheme (MCS): This selects the physical modulation scheme and coding rate using the MCS index. MCS forms a table of modulation schemes and coding rates, with the desired modulation schemes and coding rates as columns and the MCS indexes as rows. Therefore, each MCS index corresponds to a modulation scheme and coding rate under a set of parameters.

[0183] Radio Map: A radio map displays parameter values ​​at various points in a wireless network. Common radio maps include channel gain maps, received signal strength maps, and power spectrum density maps. Radio maps are widely used in wireless communications and networking, including network planning, interference control, power control, resource allocation, handover management, multi-hop routing, dynamic spectrum access, and cognitive radio network tasks. This application focuses on modulation and coding scheme (MCS) maps, a specific form of radio map.

[0184] Artificial intelligence (AI) is a branch of computer science that seeks to understand the essence of intelligence and create new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. It can imbue machines with human intelligence, for example, by enabling them to use computer hardware and software to simulate certain intelligent human behaviors. Artificial intelligence (AI) can be achieved through machine learning. In machine learning, a machine uses training data to learn (or train) a model. This model represents the mapping from input to output. The learned model can be used for inference (or prediction), meaning that the model can be used to predict the output corresponding to a given input. This output can also be called an inference result (or prediction result). Given its proven performance in various fields, AI is also considered a key technology for building various radio maps.

[0185] Base Station: A base station is a unit of coverage within a carrier's network. It serves as the interface for mobile devices to access the internet and is also a type of radio station. It is a radio transceiver station that transmits information between mobile phone terminals and the mobile communication exchange center within a specific radio coverage area. Examples include the 5G base station (next generation Node B, pronounced "g-node-B," or gNB for short), the 4G base station (eNodeB), and the 3G base station (NodeB).

[0186] User Equipment (UE): can refer to terminal devices such as mobile phones, tablet computers, and laptops.

[0187] Channel State Information (CSI) is a channel property of a communication link. It describes the signal attenuation factor along each transmission path, namely, the value of each element in the channel gain matrix H. This information includes information such as signal scattering, environmental fading (multipath fading or shadowing fading), and distance power decay. CSI enables the communication system to adapt to current channel conditions, ensuring high-reliability and high-speed communication in multi-antenna systems.

[0188] Block Error Rate (BLER): The percentage of erroneous blocks among all transmitted blocks. A block is a series of consecutive bits associated with a wireless channel.

[0189] Wireless channel: It is a figurative metaphor for the path between the sender and the receiver in wireless communication. For radio waves, there is no tangible connection between the sender and the receiver, and there may be more than one propagation path. In order to vividly describe the work between the sender and the receiver, we can imagine that there is an invisible road connecting the two. This connecting path is called a channel. The wireless channel is also the wireless "frequency band (Channel)".

[0190] Orthogonal Frequency Division Multiplexing (OFDM): A type of multi-carrier modulation (MCM), OFDM enables parallel transmission of high-speed serial data through frequency division multiplexing. It offers robustness against multipath fading and supports multi-user access.

[0191] Figure 1 shows a schematic diagram of an artificial intelligence main framework, which describes the overall workflow of the artificial intelligence system and is applicable to general artificial intelligence field needs.

[0192] The following explains the above artificial intelligence theme framework from the two dimensions of "intelligent information chain" (horizontal axis) and "IT value chain" (vertical axis).

[0193] The "intelligent information chain" reflects the entire process from data acquisition to processing. For example, it can be a general process of intelligent information perception, intelligent information representation and formation, intelligent reasoning, intelligent decision-making, and intelligent execution and output. In this process, data undergoes a condensed process of "data-information-knowledge-wisdom."

[0194] The "IT value chain" reflects the value that artificial intelligence brings to the information technology industry, from the underlying infrastructure of artificial intelligence, information (providing and processing technology implementation) to the system's industrial ecological process.

[0195] (1) Infrastructure:

[0196] Infrastructure provides computing power for AI systems, enabling communication with the outside world and supporting this through a foundational platform. External communication occurs through sensors; computing power is provided by intelligent chips (CPUs, NPUs, GPUs, ASICs, FPGAs, and other hardware accelerators). The foundational platform includes a distributed computing framework and network-related platform guarantees and support, including cloud storage and computing, and interconnected networks. For example, sensors communicate with the outside world to acquire data, which is then fed into the intelligent chips within the distributed computing system provided by the foundational platform for computation.

[0197] (2) Data

[0198] Data above the infrastructure layer represents data sources for AI. This data includes graphics, images, voice, and text, as well as IoT data from traditional devices. This includes business data from existing systems and sensor data such as force, displacement, liquid level, temperature, and humidity.

[0199] (3) Data processing

[0200] Data processing generally includes data training, machine learning, deep learning, search, reasoning, decision-making, etc.

[0201] Among them, machine learning and deep learning can symbolize and formalize data for intelligent information modeling, extraction, preprocessing, and training.

[0202] Reasoning refers to the process of simulating human intelligent reasoning in computers or intelligent systems, using formalized information to perform machine thinking and solve problems based on reasoning control strategies. Typical functions are search and matching.

[0203] Decision-making refers to the process of making decisions after intelligent information is reasoned, and usually provides functions such as classification, sorting, and prediction.

[0204] (4) General ability

[0205] After the data has undergone the data processing mentioned above, some general capabilities can be further formed based on the results of the data processing, such as algorithms or a general system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

[0206] (5) Smart products and industry applications

[0207] Smart products and industry applications refer to the products and applications of artificial intelligence systems in various fields. They are the encapsulation of the overall artificial intelligence solution, which productizes intelligent information decision-making and realizes practical application. Its application areas mainly include: smart manufacturing, smart transportation, smart home, smart medical care, smart security, autonomous driving, safe cities, smart terminals, etc.

[0208] Next, the application scenarios of the embodiments of the present application are introduced.

[0209] Under the above artificial intelligence framework, the data in Figure 1 can be voice, text and other data. Correspondingly, data processing can be done using Iranian language processing, which can realize various functions such as translation, text analysis, speech recognition, question and answer, and voice control.

[0210] Next, the wireless communication system to which the model training method, model deployment method, and communication method provided in the embodiments of the present application may be applied is introduced. Figure 2 shows an example architecture diagram of a wireless communication system provided in the embodiments of the present application. The model training method, model deployment method, and communication method provided in the embodiments of the present application can be applied to the system architecture diagram shown in Figure 2.

[0211] The wireless communication system may use any known network communication protocol to implement wireless communication. The network communication protocol can be a global system of mobile communication (GSM), code division multiple access (CDMA) IS-95, code division multiple access (CDMA) 2000, time division-synchronous code division multiple access (TDSCDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), time division duplexing-long term evolution (TDD LTE), frequency division duplexing-long term evolution (FDD LTE), long term evolution-advanced (LTE-advanced), personal handy-phone system (PHS), wireless fidelity (WiFi) specified in the 802.11 series of protocols, a combination of one or more of a 5G mobile communication system, a 6G mobile communication system, or a new radio (NR) communication system.

[0212] 2 , the wireless communication information includes one or more first communication devices 110 and one or more second communication devices 120. A wireless channel exists between the first communication device 110 and the second communication device 120.

[0213] The first communication device 110 may be a device on the network side. For example, the first communication device 110 may be a network device, or a chip, processor, or other computing module in the network device.

[0214] Among them, the network device can be a device with wireless transceiver functions such as a base station. Exemplarily, the network device can be an evolutionary base station (evolutional Node B, NodeB or eNB) in LTE, a base station (next generation node B, gNodeB or gNB) or a transmission reception point (TRP) in NR, a base station of subsequent evolution of 3GPP, an access node in a WiFi system, a wireless relay node, a wireless backhaul node, etc. When the network device is a base station, the base station can be used as a macro base station, a micro base station, a pico base station, a small station, a relay station, or a balloon station, etc. In systems using different wireless access technologies, the name of the device with base station function may be different. For example, in an LTE system, it is called an evolved Node B (evolved NodeB, eNB or eNodeB), and in a third generation (3G) system, it is called a Node B, etc. It can be understood that all or part of the functions of the network device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (such as a cloud platform).

[0215] The second communication device 120 may be a device on the user side. For example, the second communication device 120 may be a user device, or a chip, a processor, or other computing module in a terminal device.

[0216] User equipment may include various handheld devices with wireless communication capabilities, vehicle-mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem. The type of terminal device is not limited here either. Exemplarily, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a wireless terminal in the Internet of Things (IoT), a wearable device, a subscriber unit, a cellular phone, a wireless data card, a personal digital assistant (PDA), a wireless modem, a handset, a laptop computer, a machine type communication (MTC) terminal, or a combination of one or more thereof.

[0217] It should be noted that the user-side device is equipped with a baseband processing device, which may include one or more processors and memory. Processors include microprocessors (e.g., X86, ARM), microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), GPUs, programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform various functions. In other words, the processor used in the baseband can be used to implement any one or more of the processes described below.

[0218] The processing device can be implemented using a bus architecture, typically represented by a bus. The bus can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the processing system. The bus communicatively couples various circuits together, including one or more processors (typically represented by a processor), memory, and computer-readable media (typically represented by a computer-readable medium). The bus can also link various other circuits, such as timing sources, peripherals, voltage regulators, and power management circuits, which are well known in the art and, therefore, will not be described further. The bus interface provides an interface between the bus and the transceiver, and between the bus and the interface.

[0219] The transceiver provides a communication interface or means for communicating with various other devices via a wireless transmission medium. The transceiver can be coupled to an antenna array, and the transceiver and antenna array can be used together to communicate with the corresponding network type. At least one interface (e.g., a network interface and / or a user interface) provides a communication interface or means for communicating via an internal bus or via an external transmission medium.

[0220] The processor is responsible for managing the bus and general processing, including executing software stored on a computer-readable medium. When the software is executed by the processor, the software causes the processing system to perform the various functions described below for any particular device.

[0221] The functions that can be implemented by the processor, memory and computer-readable medium can be: encoding, decoding, rate matching, de-rate matching, scrambling, de-scrambling, modulation, demodulation, layer mapping, FFT, IFFT, IDFT, precoding, RE mapping, channel equalization, de-RE mapping, digital BF, adding CP, removing CP, AI reasoning, etc.

[0222] In a bidirectional communication scenario between the first communication device 110 and the second communication device 120, the first communication device 110 and the second communication device 120 can communicate via a downlink channel and an uplink channel, wherein the downlink channel and the uplink channel can each include one or more unidirectional channels.

[0223] The downlink channel may include one or more of a physical downlink shared channel (PDSCH) and a physical downlink control channel (PDCCH). The uplink channel may include one or more of a physical uplink control channel (PUCCH), a physical random access channel (PRACH), and a physical uplink shared channel (PUSCH). Of course, in some other examples, the downlink channel and the uplink channel may also include other channels, which is not limited in the embodiments of the present application.

[0224] The embodiments of the present application relate to MCS. MCS defines the number of valid bits that an RE (Resource Element, resource unit 1) can carry. MCS defines two parts, modulation scheme (Modulation) and code rate (Code Rate); wherein the code rate is the ratio between useful bits and total transmitted bits (useful + redundant bits), which is used to measure the redundancy added by the physical layer. Redundant bits are used for forward error correction (FEC). From another perspective, the code rate can be considered as the ratio between the number of information bits at the top of the physical layer and the number of bits mapped to the PDSCH at the bottom of the physical layer. The lower the coding rate, the more redundancy is added. For example, 5G NR (5G New Radio, a global 5G standard based on a new air interface design of OFDM) supports optional modulation schemes including QPSK, 16QAM, 64QAM and 256QAM. Using QPSK, each RE can transmit 2 bits of information, using 16QAM can transmit 4 bits, using 64QAM can transmit 6 bits, and using 256QAM can transmit 8 bits. At present, there are 32 MCS numbers from 0 to 31. Each number can be considered as an MCS index value, which is used to describe a coding modulation scheme. 29-31 are reserved, and different coding modulation schemes are distinguished by MCS index values. Generally speaking, the higher the MCS index value, the higher the number of effective bits that can be carried. Specifically, MCS defines two parts, modulation scheme (Modulation) and code rate (Code Rate). The choice of MCS index value depends on the quality of the wireless channel. The better the quality, the higher the MCS index value. Currently, in communication technology, one or more MCS tables can be used to provide MCS configuration schemes for channel data transmission. Each MCS table can store multiple MCS index values ​​and parameters corresponding to each MCS index value (such as modulation scheme and code rate, etc.). For example, 3GPP specification 38.214 gives PDSCH 2 Three tables are provided (64QAM table, 256QAM table, and low spectrum efficiency 64QAM table). The specific conditions for selecting each table are as follows:

[0225] 64QAM table: When the gNB or UE does not support 256QAM or the channel is poor, the 256QAM table decoding is unsuccessful and the gNB needs to use QPSK modulation, the 64QAM table can be used.

[0226] 256QAM table: The channel status is good and the device supports 256QAM.

[0227] Low Spectral Efficiency (Low SE) 64QAM table: Suitable for applications requiring reliable data transmission, such as URLLC applications. This table's MCS improves channel reliability by reducing the coding rate and increasing channel coding redundancy, resulting in lower spectral efficiency.

[0228] As shown in Figure 4, there are four columns in the MCS table. The first column is the MCS index value, 29-31 are reserved. The second column is the modulation order, which represents the modulation method used. m =2, means use 2 2 =4, i.e. QPSK; Q m =4, means use 2 4 = 16, which means 16QAM. The third column represents the target bit rate, which is the desired bit rate after selecting this modulation scheme and the corresponding redundancy. The fourth column represents the spectral efficiency, which represents the frequency efficiency when this MCS is selected. In the MCS table, the target bit rate is proportional to the spectral efficiency; the higher the spectral efficiency, the higher the target bit rate.

[0229] In related technologies, 3GPP TS 38.214 provides an MCS configuration scheme for data transmission on the Physical Downlink Shared Channel (PDSCH) and the Physical Uplink Shared Channel (PUSCH). First, 3GPP TS 38.214 provides multiple MCS tables for data transmission on both PDSCH and PUSCH. The MCS table can be selected through parameters configured by Radio Resource Control (RRC) signaling. Next, the network device determines the MCS index value based on the wireless channel information and the link adaptation algorithm, and provides the MCS index value to the user through Downlink Control Information (DCI). Finally, the user can determine the modulation order and coding rate based on the MCS table configured by RRC and by using the MCS index lookup table.

[0230] Currently, there are few solutions for determining index values, and there is an urgent need to determine an alternative solution for MCS index values.

[0231] In order to solve the above technical problems, an MCS map is provided in an embodiment of the present application; the MCS map refers to the mapping relationship between one or more location points in a wireless communication system and the MCS index sorting.

[0232] Among them, the location point in the MCS map can be a location point in the physical sense, or a logical or virtual location point, such as an area set. In an embodiment of the present application, a location point may include one or more second communication devices 120. For example, as shown in the example of Figure 3, it may include location point 1, location point 2 and location point 3, wherein location point 1 refers to device 1 on the user side, location point 2 refers to device 2 on the user side, and location point 3 refers to device 3 on the user side. In some other examples, a location point may also include multiple user-side devices, and the MCS index order of the multiple user-side devices at the location point may be the same. Location point 1, location point 2 and location point 3 can communicate wirelessly with the device on the network side.

[0233] In the example shown in FIG3 , position point 1, position point 2, and position point 3 each correspond to their own MCS index sorting. It should be noted that the MCS index sorting is used to describe the sorting of multiple MCS index values ​​in the MCS table. Specifically, the MCS index sorting is used to indicate each MCS index value and serial number in the MCS table; wherein, the serial number of any MCS index value in the MCS index sorting is used to describe the position of the MCS index value in the sorting method, and different serial numbers correspond to different priorities, such as the smaller the serial number, the greater the priority. In other words, the MCS index sorting reflects the respective priorities of different MCS indexes. For example, as shown in FIG3 , the MCS information of position point 1 is [15, 16, 20, …, 0], wherein 16 represents the MCS index value, the serial number of 16 is 2, which represents the priority, and 15, 20, …0 are similar and will not be repeated; position point 2 and position point 3 are similar and will not be repeated.

[0234] In some network communication protocols, such as 3GPP TS 38.214 and other standard protocols, multiple MCS tables are provided for PDSCH and PUSCH data transmission. Since there may be multiple correspondences between the MCS map and the MCS table, there may also be multiple map identification methods for the MCS map.

[0235] Specifically, there may be the following correspondences between the MCS map and the MCS table:

[0236] 1) If an MCS map is applicable to all MCS tables, the MCS map can be identified by the name of the MCS map.

[0237] 2) Each MCS table corresponds to only one MCS map, and the MCS map can be identified by the corresponding MCS table.

[0238] 3) Each MCS table corresponds to multiple MCS maps.

[0239] It should be noted that there are multiple ways to sort the MCS index values ​​in the MCS table. The MCS tables corresponding to the MCS index sorting of different locations can be the same or different. For example, as shown in Figure 3, the MCS tables corresponding to location 1 and location 2 are different, while the MCS tables corresponding to location 2 and location 3 are the same.

[0240] In the embodiment of the present application, the specific form of the MCS map can be various. No limitation is made here. For example, the storage form of the MCS map includes but is not limited to graphs, lists, machine learning models, etc. The MCS map can be constructed in a centralized or distributed manner on a network-side device, a user-side device, or a third-party device (such as an operator's or manufacturer's computing cloud or server, etc.). In the actual process, the MCS map is used to determine the sequence number of the MCS index value, and the sequence number is used instead of the MCS index value to reduce the transmission overhead; or, when the MCS map can accurately reflect the mapping relationship between the location point and the MCS index sorting, the MCS index value at the first position in the MCS index sorting output by the MCS map is directly used.

[0241] In the embodiments of the present application, the MCS map is implemented using a machine learning model, which, for ease of description and distinction, may be referred to as an MCS index ranking model. Specifically, as shown in FIG5 , the method of the embodiments of the present application may include one or more of the following processing stages: data collection and preprocessing, training the MCS index ranking model, deploying the MCS index ranking model, information configuration, using the MCS index ranking model, and adaptively adjusting the MCS index ranking.

[0242] Below, each processing stage is introduced respectively.

[0243] 1. Data collection and preprocessing.

[0244] In some embodiments, training an MCS index ranking model requires collecting data, preprocessing the collected data to construct samples, and labeling the samples. The sample and the label labeled with the sample can be referred to as a sample pair. A sample is used to describe the content that affects the wireless channel between a single first communication device 110 and a single second communication device 120. The label of the sample is used to describe the MCS index value corresponding to the single first communication device 110 and the single second communication device 120. The MCS index value is used to indicate the MCS index value of the optimal modulation and coding scheme for wireless channel communication between the second communication device and the first communication device. The optimal modulation and coding scheme can be understood as the most suitable modulation and coding scheme for wireless channel communication between the second communication device and the first communication device. In some possible cases, the sample includes an MCS table identifier, and the label labeled with the sample indicates the MCS index value of the optimal modulation and coding scheme corresponding to the MCS table indicated by the sample. In other possible cases, the sample does not include an MCS table identifier, and the label of the sample indicates the MCS table identifier and the MCS index value of the optimal modulation and coding scheme used for wireless channel communication between the second communication device and the first communication device. It should be noted that the content of the tag can be designed based on actual needs. This is not specifically limited in the embodiments of the present application. Considering that the relationship between the MCS table and the location of the second communication device 120 in the wireless communication network formed by the first communication device 110 is relatively complex, if the MCS index ranking model learns this relationship, it may affect the accuracy of the MCS index ranking model. To ensure the accuracy of the MCS index ranking model, the sample can include the tag of the MCS table. In this way, the MCS index ranking model does not need to consider the mapping relationship between the location of the second communication device 120 in the wireless communication network formed by the first communication device 110 and the MCS table, and directly learns the relationship between the location of the second communication device 120 in the wireless communication network formed by the first communication device 110 and the MCS index value of the optimal modulation and coding scheme (specified by the MCS table). In some possible cases, the content of the tag can be several MCS index values. If there are multiple MCS index values, the multiple MCS index values ​​are arranged in order. The content of the tag also includes the order between the multiple MCS index values. In this way, the MCS index ranking model can more accurately learn the relationship between the location point and the MCS index ranking. Among them, the multiple MCS index values ​​in the label are used to indicate the MCS index values ​​of the optimal multiple modulation and coding schemes for wireless channel communication between the second communication device and the first communication device. Exemplarily, the number of multiple MCS index values ​​can be flexibly set based on actual conditions, such as 2, 3, or 5.

[0245] For example, the collected data may include information related to the wireless communication network. This information may include one or more of the following:

[0246] 1) Information about the impact of wireless channels between the first communication device 110 and the second communication device 120, where the first communication device 110 forms a wireless communication network. Specifically, the impact information may include one or more of the following information:

[0247] A: Description information of the location of the second communication device 120 in the wireless communication network formed by the first communication device 110. Specifically, the description information of the location may include one or more of the following information:

[0248] A1. Location information of the second communication device 120 in the wireless communication network; illustratively, it can be described based on the coordinates, longitude and latitude of the second communication device 120 in the coordinate system corresponding to the wireless communication network.

[0249] A2. Relative position information between the first communication device 110 and the second communication device 120.

[0250] Exemplarily, the relative position information may include direction information and / or distance information between the first communication device 110 and the second communication device 120. The direction information may be described by the angle information between the first communication device 110 and the second communication device 120 and possible deformations (such as the sine and cosine values ​​of the angle); the distance information may be described by the distance information between the first communication device 110 and the second communication device 120 and possible deformations (such as the logarithmic value of the distance).

[0251] B: Configuration information of the antennas of the second communication device 120 and the first communication device 110. Exemplarily, the configuration information may include one or more of the following information:

[0252] B1: number of antennas;

[0253] B2: frequency range of the antenna;

[0254] B3: Antenna polarization (the direction of the electric field intensity formed when the antenna radiates), for example, vertical linear polarization, horizontal linear polarization, or slant polarization.

[0255] The above description of the antenna configuration information is merely an example and does not constitute a specific limitation. The antenna configuration information may be set in accordance with actual conditions.

[0256] C. Description of the physical environment of the wireless communication network.

[0257] Exemplarily, the description information of the physical environment of the wireless communication network can be described based on, for example, an environmental map (e.g., a satellite map, a topological map, etc.), an environmental elevation map, etc. The description information of the physical environment can be used to describe the objects that affect wireless communication within the area managed by the first communication device 110 and the area managed by it. The objects can be buildings, trees, etc. For each object, the location and size (length, width, height) need to be described, and further, the material can also be described. For the first communication device 110, the location of the first communication device 110 needs to be described. Exemplarily, the description information of the physical environment can include description information of the location of the first communication device 110 in the wireless communication network. The description information of the location can be described based on the coordinates, longitude and latitude, and other information of the first communication device 110 in the coordinate system corresponding to the wireless communication network.

[0258] 2) Auxiliary information corresponding to the second communication device 120, which indicates other information that affects the MCS index sorting. The auxiliary information may include one or more of the following information:

[0259] Communication parameters of the wireless communication network in which the second communication device 120 resides and / or communication parameters of the second communication device 120; wherein the communication parameters of the wireless communication network may include communication power, carrier frequency, and OFDM parameters such as symbol period length and guard interval, which are generally pre-configured by the first communication device 110; the communication parameters of the second communication device 120 may include an MCS table identifier (used to indicate a specific MCS table, such as a table ID) and transmit power. The communication parameters of the wireless communication network and the communication parameters of the second communication device 120 may be set based on actual circumstances and are not specifically limited in this embodiment of the present application.

[0260] It should be noted that the auxiliary information 120 of different second communication devices may be partially the same or completely different; for example, if multiple second communication devices 120 communicate wirelessly with the same first communication device 110, the multiple second communication devices 120 are located in the same wireless communication network, and the parameter values ​​of the communication parameters of the wireless communication network are generally the same, but the parameter values ​​of the communication parameters of each second communication device 120 are generally different.

[0261] It should be noted that the specific division of impact information and auxiliary information is merely illustrative and does not constitute a specific limitation. The specific division can be determined based on actual needs. For example, the relative position information between the first communication device 110 and the second communication device 120 can be used as auxiliary information, the identifier of the MCS table can be used as impact information, and the configuration information of the antenna of the first communication device 110 can be used as descriptive information of the physical environment of the wireless communication network.

[0262] The above data can be collected based on historical data related to the wireless communication network. When collecting the above data, in order to ensure that the data can more comprehensively reflect the status of the wireless communication network, the second communication devices 120 involved in the data should cover the entire wireless communication network as much as possible. Specifically, it is necessary to consider all second communication devices 120 that communicate with the first communication device 110. Furthermore, during the data collection phase, the second communication device 120 may include or exclude the second communication device in the subsequent examples, and the first communication device 110 may include or exclude the first communication device in the subsequent examples.

[0263] Furthermore, the collected data can be processed by removing abnormal data (e.g., data with missing features), encoding, and normalization to obtain processed samples. These samples are then labeled to generate sample pairs, which serve as the data foundation for training the MCS index ranking model. Sample labels can be descriptions of actual data collection or labels of similar samples (describing similar wireless channels). In some possible scenarios, after obtaining sample pairs, they can be stored in a database for easy maintenance, updating, and use.

[0264] 2. Train the MCS index sorting model.

[0265] After obtaining multiple groups of sample pairs, the MCS index ranking model can be trained using the multiple groups of sample pairs.

[0266] In addition, for the development of MCS index sorting models, developers can install an AI development framework on a user-side device, such as the second communication device 120, and then develop the AI ​​model locally. They can also use the AI ​​development framework on an online platform (for example, an online open source framework platform, a public cloud AI basic development platform, etc.) to develop the AI ​​model. AI development frameworks in the industry are usually open source. Typical AI development frameworks for developing deep learning models, also known as deep learning frameworks, include PaddlePaddle, Tensorflow, Caffe, Theano, MXNet, Torch, and PyTorch.

[0267] Next, we will introduce the model training systems that may be used for the model training method provided in the embodiments of this application. There are mainly four situations:

[0268] Case 1: The MCS index ranking model is trained by a user-side device.

[0269] Case 2: The MCS index ranking model is trained by a device on the network side.

[0270] Case 3: The MCS index ranking model is trained by the user-side device and the network-side device.

[0271] Case 4: Training the MCS index ranking model through third-party equipment.

[0272] For situation 4, the third-party device can be several devices. For example, the third-party device can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. In addition, the third-party device can also be a cloud server or a cloud server cluster. The cloud server or cloud server cluster is used to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN) and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server cluster is deployed in several cloud data centers, etc., but is not limited to the above forms.

[0273] In one possible scenario, a third-party device can act as a cloud (a software platform that uses application virtualization technology, integrating multiple functions such as software search, download, use, management, and backup); during specific use, the third-party device deploys a cloud management platform and a data center, and the user-side device and the cloud interact through the cloud management platform; in addition, the data center can deploy nodes, where the nodes in the data center can be virtual machine instances, container instances, physical servers, etc.; in the data center, the number of nodes is generally massive.

[0274] In an embodiment of the present application, on the one hand, a node can be used for model training; in one possible case, when the scale of the model is large, the model can be distributedly deployed on multiple nodes for parallel training based on the idea of ​​model parallelism. In another possible case, the model can be trained on one node. In an embodiment of the present application, the model can be an MCS index sorting model. On the other hand, a node can be used to store an MCS index sorting model (generally a trained model). In one possible scenario, the deployed MCS index sorting model is used to be stored in a database for easy subsequent deployment and use.

[0275] It should be noted that the four situations shown above are only examples and do not constitute specific limitations. The specific situations can be determined based on actual conditions.

[0276] FIG6 is a flow chart of a model training method provided in an embodiment of the present application. This embodiment can be applied to the first communication device 110, the second communication device 120, or a third-party device. As shown in FIG6, the model training method provided in an embodiment of the present application includes at least the following steps:

[0277] Step 601: Obtain a sample, where the sample includes impact information of a wireless channel. The wireless channel is the path between the first communication device 110 and the second communication device 120. The impact information includes description information of the physical environment of the wireless communication network formed by the first communication device 110 and description information of the position of the second communication device 120 in the wireless communication network. The sample corresponds to the MCS index value of the modulation and coding scheme.

[0278] In some possible cases, the sample pairs can be obtained from a database storing the sample pairs. For details about the samples and the impact information, please refer to the description of data collection and preprocessing, which will not be repeated here.

[0279] In some possible implementations, the sample may further include auxiliary information corresponding to the second communication device 120 .

[0280] Step 602: Take the sample as input and the MCS index value corresponding to the sample as output, train the MCS index sorting model, and obtain a trained MCS index sorting model. The MCS index sorting model is used to output the MCS index sorting, and the MCS index sorting indicates the priority of the MCS index value in the MCS table.

[0281] In this embodiment of the present application, an MCS index ranking model is used to store a correspondence between each of multiple location points in a wireless communication network and a wireless channel, and a correspondence between a wireless channel and an MCS index ranking. A location point indicates the location of the second communication device 120 in the wireless communication network. Specifically, the MCS index ranking model can be used to determine description information of the wireless channel at the location point, and based on the description information of the wireless channel, determine the MCS index ranking corresponding to the wireless channel.

[0282] In some possible implementations, the MCS index ranking model includes a wireless channel description module (first module) and a ranking prediction module (second module). The wireless channel description module (first module) can be a machine learning model, which can be a convolutional neural network (CNN), a recurrent neural network (RNN), a graph neural network (GNN), or a combination of one or more subsequently developed machine learning models. The ranking prediction module (second module) is similar and will not be further described.

[0283] Next, the specific processing procedures of the wireless channel description module (first module) and the ranking prediction module (second module) are described, mainly including the following two examples.

[0284] In one example, the wireless channel description module (first module) is configured to output descriptive information of the wireless channel between the first communication device 110 and the second communication device 120 based on samples; and the ranking prediction module (second module) outputs an MCS index ranking based on the output of the wireless channel description module (first module). The wireless channel description information is used to describe the wireless channel and may include one or more of the following: channel type, channel strength, channel capacity, channel bandwidth, latency, and CSI. The above wireless channel description information is provided for illustrative purposes only and does not constitute a specific limitation. The specific information can be determined based on actual needs.

[0285] In one example, the wireless channel description module (first module) is used to output description information of the wireless channel between the first communication device 110 and the second communication device 120 based on the impact information of the wireless channel; the sorting prediction module (second module) outputs the MCS index sorting based on the output of the wireless channel description module (first module) and the auxiliary information affecting the MCS index sorting (auxiliary information corresponding to the second communication device 120).

[0286] In some possible scenarios, the sample includes an MCS table identifier; accordingly, the MCS index ranking model can learn the relationship between the wireless channel and the MCS index ranking in the (specified) MCS table. Since the location of the second communication device 120 can reflect a location point in the wireless communication network, the MCS index ranking model can learn the relationship between the location point in the wireless communication network, the wireless channel, and the MCS index ranking in the (specified) MCS table. Accordingly, the MCS index ranking model can only output the MCS index ranking. When the MCS index ranking model includes a wireless channel description module (first module) and a ranking prediction module (second module), optionally, the wireless channel description module (first module) is configured to output description information of the wireless channel between the first communication device 110 and the second communication device 120 based on information affecting the wireless channel; and the ranking prediction module (second module) outputs the MCS index ranking based on the output of the wireless channel description module (first module), or based on the output of the wireless channel description module (first module) and auxiliary information affecting the MCS index ranking (auxiliary information corresponding to the second communication device 120).

[0287] In some possible scenarios, the sample does not include the identifier of the MCS table; the MCS index ranking model can learn the relationship between different wireless channels and MCS tables, as well as the relationship between different wireless channels and the MCS index ranking in the MCS table based on the impact information of the wireless channel; since the location of the second communication device 120 can reflect the location point in the wireless communication network, the MCS index ranking model can learn the relationship between the location point in the wireless communication network, the MCS table, and the MCS index ranking of the MCS table; accordingly, the MCS index ranking model can output the identifier of the MCS table and the MCS index ranking. When the MCS index ranking model includes a wireless channel description module (first module) and a ranking prediction module (second module), optionally, the wireless channel description module (first module) is used to output description information of the wireless channel between the first communication device 110 and the second communication device 120, and the identifier of the MCS table based on the impact information of the wireless channel; the ranking prediction module (second module) outputs the MCS index ranking based on the output of the wireless channel description module (first module), or based on the output of the wireless channel description module (first module) and auxiliary information that affects the MCS index ranking. Optionally, the wireless channel description module (first module) is used for the impact information of the wireless channel, and outputs the description information of the wireless channel between the first communication device 110 and the second communication device 120; the sorting prediction module (second module) is based on the output of the wireless channel description module (first module), or based on the output of the wireless channel description module (first module) and auxiliary information affecting the MCS index sorting, outputs the MCS index sorting and the identifier of the MCS table.

[0288] In an embodiment of the present application, the purpose of training the MCS index sorting model is to make the MCS index value with the highest probability output by the MCS index sorting model be the MCS index value indicated by the label. In a specific training process, the MCS index sorting model can predict the MCS index sorting corresponding to the sample, and obtain a prediction result based on the predicted MCS index value of the MCS index sorting. For example, the MCS index value with the highest probability value in the MCS index sorting is used as the prediction result, and the error between the predicted result and the true result is evaluated, thereby training the MCS index sorting model. Specifically, for each sample, the sample is input into the MCS index sorting model to obtain the predicted MCS index sorting, and the error between the predicted MCS index sorting and the sample label is calculated; then, based on the errors of multiple samples, the MCS index sorting model is trained. In some possible implementations, the label may indicate the MCS index value through a vector, where the number of elements in the vector is the number of MCS index values, such as 32, and each element corresponds to an MCS index value. The element value of each element is used to indicate whether the MCS index value corresponding to the element exists, such as 1 if it exists and 0 if it does not exist. For example, assuming that the MCS index value indicated by the label is 1 and the MCS index value is 3, the MCS index values ​​corresponding to the 32 elements in the vector are 0, 1, 2, ..., 31, then the label is [0, 0, 0, 1, 0, ..., 0]; assuming that Suppose there are two MCS index values ​​indicated by the label, and the MCS index values ​​are 5 and 7, then the labels are [0, 0, 0, 0, 0, 1, 0, 1, 0, …, 0]; in this implementation method, in the specific model training process, the MCS index sorting model can predict the MCS index sorting corresponding to the sample (generally expressed as a vector, which is used to describe 32 MCS index values ​​arranged in order) and evaluate the error between the MCS index sorting and the label. For example, the difference between the two vectors of label and MCS index sorting can be used to train the MCS index sorting model.

[0289] It should be noted that the MCS index sorting model corresponds to the MCS table, and the MCS index sorting model stores the relationship between the MCS index sorting of the corresponding MCS table and the wireless channel, and the relationship between the wireless channel and the location point in the wireless communication network; the MCS table corresponding to the MCS index sorting model depends on the identifier of the MCS table input into the model during the training process, or the identifier of the MCS table in the sample label; among them, the MCS index sorting model can correspond to one or more MCS tables.

[0290] 3. Deploy the MCS index sorting model.

[0291] After obtaining the trained MCS index ranking model, the MCS index ranking model can be deployed. The MCS index ranking model can be deployed to the first communication device 110 and the second communication device 120 in the wireless communication system.

[0292] FIG7 is a flow chart of a model deployment method provided in an embodiment of the present application. This embodiment can be applied to the first communication device 110, the second communication device 120, or a third-party device. Here, the first communication device 110 is used as an example for description. As shown in FIG7, the model deployment method provided in an embodiment of the present application includes at least the following steps:

[0293] Step 701 : The first communication device 110 obtains description information of available hardware resources of the second communication device 120 .

[0294] Considering the limited computing power of the second communication device 120 and the need to ensure a limited user experience, whether the MCS index sorting model is deployed on the second communication device 120 needs to consider the computing power and storage capacity of the second communication device 120. Therefore, it is necessary to report the computing power and storage capacity of the second communication device 120. In specific implementations, the second communication device 120 needs to actively request the first communication device 110 to deploy the model and actively report the description of its available hardware resources.

[0295] Hardware resources may include processors and memory. Available hardware resources can be understood as the additional resource usage that the second communication device 120 can accept. For example, if the second communication device 120 has high performance requirements and requires a large amount of storage space, the available hardware resources are relatively small. If the second communication device 120 has low performance requirements and does not require a large amount of storage space, the available hardware resources are relatively large. The description of available hardware resources is used to indicate the size of the available hardware resources, such as the number of CPU cores, the amount of memory, and the size of the hard disk.

[0296] Step 702 : The first communication device 110 determines a model deployment solution based on the description information of the available hardware resources of the second communication device 120 . The model deployment solution indicates the content of the MCS index sorting model deployed in the second communication device 120 and / or the first communication device 110 .

[0297] In some possible scenarios, the first communication device 110 determines, based on the description information of the available hardware resources of the second communication device 120, whether the available hardware resources of the second communication device 120 are capable of deploying an MCS index ranking model. If so, the model deployment solution is determined to be deploying the MCS index ranking model on the second communication device 120. If the available hardware resources of the second communication device 120 are not capable of deploying a complete MCS index ranking model, the first communication device 110 determines whether the second communication device 120 is capable of deploying a portion of the MCS index ranking model. If so, the MCS index ranking model is deployed on both the second communication device 120 and the first communication device 110. It should be noted that the deployed portion of the MCS index ranking model can implement certain functions and has specific inputs and outputs, such as a wireless channel description module (first module) or a ranking prediction module (second module). Exemplarily, the model deployment solution is to deploy the wireless channel description module (first module) or the ranking prediction module (second module) on the second communication device 120. If the second communication device 120 cannot deploy part of the MCS index sorting model, considering that the first communication device 110 has more hardware resources, the model deployment solution is determined to be deploying the MCS index sorting model in the first communication device 110 .

[0298] Considering that the wireless channel description module (first module) typically requires more storage resources and computing power, while the ranking prediction module (second module) requires less storage resources and computing power, it is preferred to deploy the wireless channel description module (first module) on the first communication device 110 and the ranking prediction module (second module) on the second communication device 120. In some possible scenarios, based on the description information of the available hardware resources of the second communication device 120, the first communication device 110 determines whether the available hardware resources of the second communication device 120 are sufficient to deploy the ranking prediction module (second module) in the MCS index ranking model. If so, the model deployment solution is determined to be deploying the ranking prediction module (second module) in the MCS index ranking model on the second communication device 120 and deploying the wireless channel description module (first module) on the first communication device 110. If the available hardware resources of the second communication device 120 are not sufficient to deploy the ranking prediction module (second module), the model deployment solution is determined to be deploying the MCS index ranking model on the first communication device 110.

[0299] In some possible implementations, the model partial scheme is represented by an index. The index can be a vector, each element of which indicates a module in the MCS index sorting model. The value of the element is used to indicate whether it is deployed on the user side, such as the second communication device 120. For example, 1 indicates that the corresponding module is deployed on the user side, such as the second communication device 120, and 0 indicates that the corresponding module is deployed on the network side, such as the first communication device 110. The length of the index is equal to the number of modules in the MCS index sorting model. For example, the MCS index sorting model is divided into a wireless channel description module (first module) and a sorting prediction module (second module). The vector length is 2, the first element corresponds to the wireless channel description module (first module), and the second element corresponds to the sorting prediction module (second module). Then [0, 1] indicates that the wireless channel description module (first module) is deployed on the network side, and the sorting prediction module (second module) is deployed on the user side.

[0300] The model deployment scheme exemplified above is merely an example and does not constitute a specific limitation. In some possible implementations, when the second communication device 120 can deploy the MCS index sorting model, the model deployment scheme may also indicate that the MCS index sorting model may be deployed simultaneously on the first communication device 110 and the second communication device 120.

[0301] In actual applications, the MCS index sorting model is used to process the MCS table used in the training process. The second communication device 120 is a movable device. Once its position changes, the wireless channel will also change. Correspondingly, the MCS table may need to be reconfigured. Therefore, the deployed MCS index sorting model needs to cover as many MCS tables or all MCS tables commonly used by the second communication device 120 as possible. For example, there can be one or more MCS index sorting models. The embodiment of the present application does not make specific restrictions on this. The MCS index sorting model can be flexibly deployed in combination with actual conditions. In specific implementation, before step 702, the first communication device 110 can obtain the identifier of the MCS table that the second communication device 120 needs to use, and determine the MCS index sorting model that needs to be deployed based on the identifier of the MCS table that the second communication device 120 needs to use and the identifier of the MCS table corresponding to the MCS index sorting model.

[0302] Step 703: The first communication device 110 deploys the MCS index sorting model according to the model deployment solution.

[0303] It should be noted that after the MCS index sorting model is obtained, the MCS index sorting model can be deployed to the first communication device 110 and / or the second communication device 120 in the wireless communication system.

[0304] If the model deployment solution indicates that the MCS index sorting model is deployed on the first communication device 110, the deployment of the MCS index sorting model on the first communication device 110 may include but is not limited to the following three situations:

[0305] 1) If the MCS index sorting model is constructed in the first communication device 110 , the MCS index sorting model deployment of the first communication device 110 can be directly implemented after the construction is completed.

[0306] 2) If the MCS index sorting model is constructed on a third-party device (such as a cloud service provider's cloud server, an operator's server, or a manufacturer's server, etc.), such as the electronic device 620, the first communication device 110 needs to send a request to the third-party device to download the MCS index sorting model.

[0307] 3) If the MCS index sorting model is constructed by the second communication device 120 , then after the MCS index sorting model is constructed, the second communication device 120 sends the MCS index sorting model to the first communication device 110 .

[0308] If the model deployment solution indicates that at least some modules in the MCS index sorting model are deployed on the second communication device 120, the deployment of the MCS index sorting model on the second communication device 120 may include but is not limited to the following two situations:

[0309] 1) If a second communication device 120 participates in the construction of the MCS index sorting model, the MCS index sorting model of the second communication device 120 can be directly deployed after the construction is completed.

[0310] 2) If a second communication device 120 does not participate in the MCS index sorting model construction, there are several ways to complete the MCS map deployment:

[0311] Method A: requesting the first communication device 110 to send at least part of the modules in the MCS index sorting model that needs to be deployed.

[0312] Method B: Request the first communication device 110 to schedule other second communication devices 120 or third-party devices adjacent to the second communication device 120 to share at least part of the modules in the MCS index sorting model, where the other second communication device 120 is a second communication device 120 that has participated in the construction of the MCS index sorting model or has completed the deployment of the MCS index sorting model, and the third-party device is a third-party device that constructs the MCS index sorting model, or deploys the MCS index sorting model.

[0313] Method C: Requesting other adjacent second communication devices 120 or third-party devices to share at least some modules in the MCS index sorting model. The other second communication devices are second communication devices 120 that have constructed or deployed the MCS index sorting model.

[0314] Next, in conjunction with steps 701 to 703 , the specific application of the above-mentioned method A, method B, and method C will be described in detail.

[0315] For method A described above, in one possible scenario, in step 703, the first communication device 110 sends the content of the MCS index sorting model that needs to be deployed on the second communication device 120 to the second communication device 120; the second communication device 120 deploys the received content of the MCS index sorting model.

[0316] For the above-described method B, in one possible scenario, FIG8a shows a flow chart of step 703 in the embodiment shown in FIG7. As shown in FIG8a, based on the embodiment shown in FIG7, in the embodiment of the present application, step 703 may specifically include the following steps:

[0317] Step 7031a: The first communication device 110 sends the model deployment solution to the second communication device 120.

[0318] Step 7032a: The first communication device 110 sends the identifier of the second communication device and the model deployment solution to other communication devices communicating with the second communication device 120.

[0319] The other communication device may be another second communication device 120, or may be another third-party device other than the first communication device 110 and the second communication device 120, so that at least part of the MCS index sorting model can be shared. In the scenario where the other communication device is another second communication device 120, when the second communication device 120 requests the first communication device 110 to deploy the model, in order to improve the efficiency of the model deployment, the first communication device 110 sends the identifier of the second communication device and the model deployment plan to the other second communication device 120 communicating with the second communication device 120 when the distance between the second communication device 120 and the other second communication device 120 is close, for example, the distance is less than or equal to a preset threshold. The identifier of the second communication device is used to indicate a unique identifier of the second communication device 120.

[0320] Step 7033a: The second communication device 120 sends a sharing request to other communication devices.

[0321] Step 7034a: The other communication device sends the content of the deployed MCS index sorting model to the second communication device 120.

[0322] Step 7035a: The second communication device 120 deploys the content of the received MCS index sorting model.

[0323] For the above-described method C, FIG8b shows a flow chart of step 703 in the embodiment shown in FIG7. As shown in FIG8b, based on the embodiment shown in FIG7, in the embodiment of the present application, step 703 may specifically include the following steps:

[0324] Step 7031b: The first communication device 110 sends the model deployment solution to the second communication device 120.

[0325] Step 7032b: The second communication device 120 sends a sharing request and a model deployment solution to other communication devices communicating with the second communication device 120.

[0326] Step 7033b: The other communication devices send the content of the MCS index sorting model deployed by themselves to the second communication device 120 according to the received model deployment solution.

[0327] Step 7034b: The second communication device 120 deploys the content of the received MCS index sorting model.

[0328] In a specific implementation, the second communication device 120 sends a model deployment plan to a neighboring second communication device 120 or a third-party device such as the electronic device 620, and requests the content of the MCS index model indicated by the deployment model deployment plan, thereby realizing model sharing.

[0329] 4. Configure the MCS index sorting model.

[0330] Before using the MCS index sorting model, the first communication device 110 and the second communication device 120 may further configure related parameters and information.

[0331] Exemplarily, the configuration information related to the MCS index sorting model may include one or more of the following information: auxiliary information corresponding to the second communication device 120, descriptive information of the physical environment of the wireless communication network formed by the first communication device 110, the MCS table corresponding to the second communication device 120, the model identifier of the MCS index sorting model and the MCS index value threshold.

[0332] The specific content of the auxiliary information corresponding to the second communication device 120 can refer to the relevant description of the above-mentioned data collection and preprocessing part, and will not be repeated here. In some possible situations, the first communication device 110 and the second communication device 120 configure the auxiliary information corresponding to the second communication device 120 in the following manner: the second communication device 120 reports the communication parameters of the second communication device 120 to the first communication device 110; the first communication device 110 sends the communication parameters of the wireless communication network formed by the first communication device 110 to the second communication device 120; or, a third-party device sends auxiliary information to the first communication device 110 and the second communication device 120. The method of configuring auxiliary information is only an example and does not constitute a specific limitation. It can be flexibly configured in combination with the content of the auxiliary information.

[0333] The specific content of the description information of the physical environment of the wireless communication network formed by the first communication device 110 can refer to the relevant description of the data collection and preprocessing section above, and will not be repeated here. In some possible situations, the way in which the second communication device 120 configures the description information of the physical environment of the wireless communication network formed by the first communication device 110 can be: the first communication device 110 sends the description information of the physical environment of the wireless communication network formed by the first communication device 110 to the second communication device 120, or a third-party device sends the description information of the physical environment of the wireless communication network formed by the first communication device 110 to the second communication device 120; the way in which the first communication device 110 configures the description information of the physical environment of the wireless communication network can be: the third-party device sends the description information of the physical environment of the wireless communication network to the first communication device 110. The way to configure the description information of the physical environment of the wireless communication network formed by the first communication device 110 is only an example and does not constitute a specific limitation. It can be flexibly configured in combination with the content of the auxiliary information.

[0334] It should be noted that the auxiliary information corresponding to the second communication device 120 and the description information of the physical environment of the wireless communication network formed by the first communication device 110 are generally not changed after being configured.

[0335] In some possible scenarios, the MCS index sorting model corresponds to the identifier of the MCS table. In scenarios where the input of the MCS index sorting model includes the identifier of the MCS table, it is necessary to configure the MCS table corresponding to the second communication device 120. Specifically, the first communication device 110 and the second communication device 120 need to uniformly configure the MCS table corresponding to the second communication device 120. A specific method is to select the MCS table based on parameters configured by radio resource control (RRC) signaling, etc. The RRC signaling can be sent by the first communication device 110 to the second communication device 120, or by the second communication device 120 to the first communication device 110. It should be noted that the configuration of the MCS table corresponding to the second communication device 120 will be updated as the wireless channel changes.

[0336] Furthermore, after configuring the MCS table, considering that the input of the MCS index sorting model includes the identifier of the MCS table, the identifier of the MCS index sorting model corresponding to the MCS table can be configured (used to distinguish different MCS index sorting models), so that the MCS index sorting model corresponding to the MCS table can be used to predict the MCS index sorting; in some possible ways, a new field can be defined in the RRC signaling to record the identifier of the MCS index sorting model, so as to unify the MCS index sorting models used by the first communication device 110 and the second communication device 120; in actual application, the MCS table and the identifier of the MCS index sorting model corresponding to the MCS table can be selected according to parameters configured by RRC signaling or other means.

[0337] The MCS index value threshold may indicate the maximum value of the MCS index. For example, the MCS index value threshold may be the number of bits of the signal. For example, if the MCS index value threshold is 3 bits, the maximum value of the MCS index is 7. Before using the MCS index sorting model, during the MCS index sorting model configuration phase, in order to perform blind detection of DCI downlink control information, the first communication device 110 and the second communication device 120 need to reach an agreement on the MCS index value threshold.

[0338] The manner in which the first communication device 110 and the second communication device 120 agree on the MCS index value threshold may include but is not limited to the following two:

[0339] (1) The first communication device 110 determines an MCS index value threshold, and sends the determined MCS index value threshold to each second communication device 120 .

[0340] After receiving the MCS index sorting model configuration request sent by the second communication device 120, the first communication device 110 determines an MCS index value threshold based on information about the model performance, such as the accuracy of the MCS index sorting model, and sends the MCS index value threshold to the second communication device 120. In addition, in some examples, the first communication device 110 may periodically adjust the MCS index value threshold based on factors such as the accuracy of the MCS index sorting model.

[0341] In this example, the MCS index value thresholds corresponding to the respective second communication devices 120 in the wireless communication system may be the same.

[0342] (2) The second communication device 120 determines the MCS index value threshold.

[0343] The second communication device 120 may send an MCS index sorting model configuration request and an MCS index sorting accuracy requirement to the first communication device 110. After receiving the MCS index sorting model configuration request sent by the second communication device 120, the first communication device 110 may determine an MCS index value threshold and the MCS index sorting accuracy requirement of the second communication device 120 based on information about the model performance, such as the accuracy of the MCS index sorting model, determine an MCS index value threshold specific to the second communication device 120, and send the MCS index value threshold specific to the second communication device 120 to the second communication device 120.

[0344] In addition, the second communication device 120 can also determine the MCS index value threshold and the accuracy requirement of the MCS index sorting by the second communication device 120 based on the information of the model performance such as the accuracy of the MCS index sorting by the MCS index sorting model. After determining the corresponding MCS index value threshold, the MCS index value threshold of the second communication device 120 is sent to the first communication device 110.

[0345] In this example, when there are multiple second communication devices 120 in the wireless communication system, each second communication device 120 can customize its own MCS index value threshold, that is, the MCS index value threshold corresponding to each second communication device 120 in the wireless communication system can be different.

[0346] Generally speaking, in the MCS index ranking, the MCS index value with the highest ranking is the MCS index value that can bring high performance between the second communication device 120 and the first communication device 110. Therefore, the specific value of the MCS index value threshold can be relatively small, thereby saving corresponding signaling overhead.

[0347] 5. Use MCS index sorting model.

[0348] After the first communication device 110 and / or the second communication device 120 deploys the MCS index sorting model, the MCS index between the first communication device 110 and the second communication device 120 may be determined according to the MCS index sorting model.

[0349] In some possible scenarios, the MCS index sorting model is deployed on the first communication device 110. FIG9 is a flow chart of the communication method provided by an embodiment of the present application. As shown in FIG9, the communication method provided by an embodiment of the present application includes at least the following steps:

[0350] Step 901: The second communication device 120 reports its own location information to the first communication device 110.

[0351] As mentioned above, the location information can be described by information such as the coordinates, longitude and latitude of the second communication device 120 in the coordinate system corresponding to the wireless communication network.

[0352] Step 902: The first communication device 110 runs an MCS index sorting model based on the received location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110 to obtain an MCS index sorting output by the MCS index sorting model.

[0353] It should be noted that the entire MCS index sorting model is deployed on the first communication device 110. In the embodiment of the present application, the MCS index sorting model is used to store the correspondence between each location point, the wireless channel, and the MCS index sorting in a plurality of location points in the wireless communication network; the location point indicates the location of the second communication device in the wireless communication network. In a specific application, at least the location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110 are input into the MCS index sorting model. The MCS index sorting model can determine the wireless channel between the second communication device 120 and the first communication device 110 based on the location information of the second communication device 120, and output the MCS index sorting corresponding to the wireless channel between the second communication device 120 and the first communication device 110. More specifically, the MCS index sorting model can determine the description information of the wireless channel based on the location information of the second communication device 120, and determine the MCS index sorting based on the description information of the wireless channel.

[0354] It should be noted that the MCS index sorting indicates the sorting of multiple MCS index values ​​in a certain MCS table, and may specifically include multiple MCS index values ​​and their respective sequence numbers. The sequence number is used to indicate the order of the MCS index value among the multiple MCS index values. The sequence number is used to indicate the priority, and the higher the priority, the smaller the sequence number. Exemplarily, the MCS index sorting can be expressed as a vector, where the vector is a plurality of index values ​​sorted as required; for example, as shown in FIG3 , the MCS index sorting can be [15, 16, 20, …, 0], where 16 represents the MCS index value and the sequence number of 16 is 2, which is used to indicate the priority.

[0355] It is worth noting that during the execution of the MCS index ranking model, in addition to inputting location information and the description of the physical environment of the wireless communication network formed by the first communication device 110 into the model, other information may also be input, such as the auxiliary information described in the aforementioned data collection and preprocessing. The specific content of the auxiliary information can be found in the description above. In scenarios where the input to the MCS index ranking model includes auxiliary information, the second communication device 120 may also report the auxiliary information corresponding to the second communication device 120 in step 901. Accordingly, in step 902, the first communication device 110 executes the MCS index ranking model based on the received location information, the description of the physical environment of the wireless communication network formed by the first communication device 110, and the auxiliary information corresponding to the second communication device 120, to obtain the MCS index ranking output by the MCS index ranking model. Furthermore, the description of the physical environment of the wireless communication network formed by the first communication device 110 and the auxiliary information corresponding to the second communication device 120 may be reused. When the location of the second communication device 120 changes, the second communication device 120 may also report the changed location information, which indicates the location of the second communication device 120 after moving within the wireless communication network. Correspondingly, when the input of the MCS index sorting model does not include auxiliary information, the first communication device 110 runs the MCS index sorting model based on the changed position information and the description information of the physical environment of the wireless communication network formed by the first communication device 110, and obtains the MCS index sorting output by the MCS index sorting model; when the input of the MCS index sorting model includes auxiliary information, the first communication device 110 runs the MCS index sorting model based on the changed position information, the description information of the physical environment of the wireless communication network formed by the first communication device 110 and the auxiliary information corresponding to the second communication device 120, and obtains the MCS index sorting output by the MCS index sorting model.

[0356] It should be noted that in a scenario where the input of the MCS index sorting model includes an MCS table identifier, the first communication device 110 and the second communication device 120 need to unify the configuration of the MCS table. Specifically, the MCS table can be selected through parameters configured through RRC signaling or other means. Subsequently, the first communication device 110 inputs at least the received location information, the description of the physical environment of the wireless communication network formed by the first communication device 110, and the identifier of the MCS table into the MCS index sorting model to obtain the MCS index sorting output by the MCS index sorting model.

[0357] Step 903: The first communication device 110 determines a target MCS index value based on the MCS index sorting.

[0358] The target MCS index value is any one from 0 to 31.

[0359] In some possible implementations, the first communication device 110 does not store an MCS index value threshold corresponding to the second communication device 120. The target MCS index value is the MCS index value with the highest priority in the MCS index ranking. Optionally, considering that the MCS index ranking model has high accuracy, the MCS index ranking output by the MCS index ranking model has a high reference value, and considering that the MCS index ranking is arranged in descending order of priority, the target MCS index value may be the first MCS index value in the MCS index ranking.

[0360] The above method for determining the MCS index value is merely an example and does not constitute a specific limitation. In other possible implementations, considering that the MCS index sorting model may still be erroneous, the top n (greater than or equal to 2) MCS index values ​​in the MCS index sorting can be used as the target index value, facilitating subsequent selection of the target index value for final use by the second communication device 120 from among the multiple target index values. For example, the MCS index sorting can be [15, 16, 20, ..., 0], where the top three digits are: 15, 16, 20. The value n can be determined based on actual needs and is not specifically limited in this embodiment of the present application.

[0361] In some possible implementations, the first communication device 110 stores an MCS index value threshold corresponding to the second communication device 120, and the target MCS index value may be the MCS index value with the highest priority among the at least one candidate MCS index value. The at least one candidate MCS index value is each MCS index value in the MCS index sorting that is less than or equal to the MCS index value threshold.

[0362] The sequence number of the candidate MCS index value is the sequence number of the candidate MCS index value in the MCS index sorting, and the sequence number of the candidate MCS index value may indicate the order of the candidate MCS index value in at least one candidate MCS index value.

[0363] Correspondingly, the target MCS index value may be the MCS index value with the highest priority among at least one candidate MCS index value, which can be understood as: the target MCS index value is the candidate MCS index value with the smallest sequence number.

[0364] The above-mentioned method of determining the MCS index value is merely an example and does not constitute a specific limitation. In other possible implementation methods, considering that the MCS index sorting model may still be erroneous, the top n candidate MCS index values ​​in at least one candidate MCS index value can be used as the target index value, so as to facilitate the subsequent second communication device 120 to select the target index value to be finally used from multiple target index values.

[0365] Step 904 : The first communication device 110 sends a target MCS index value to the second communication device 120 .

[0366] During specific implementation, the target MCS index value is sent to the second communication device 120 via DCI.

[0367] If there are multiple target MCS index values, the second communication device 120 compares the performance of the coding and modulation scheme indicated by each target MCS index value, and uses the coding and modulation scheme indicated by the target MCS index value with the best performance as the scheme actually used; in specific implementation, the second communication device 120 communicates with the first communication device 110 according to the coding and modulation scheme indicated by the target MCS index value for each target MCS index value, and obtains the performance of the coding and modulation scheme indicated by the target MCS index value.

[0368] In this solution, the MCS index value is directly determined by the MCS index ranking output by the MCS index ranking model, without the need for the second communication device 120 to upload wireless channel information, which can reduce the signaling overhead of the second communication device 120.

[0369] In some possible scenarios, the MCS index sorting model is fully deployed on the first communication device 110 and the second communication device 120. FIG10 is a flow chart of the communication method provided by an embodiment of the present application. As shown in FIG10, the communication method provided by an embodiment of the present application includes at least the following steps:

[0370] Step 1001: The second communication device 120 reports wireless channel information and its own location information to the first communication device 110.

[0371] It should be noted that the second communication device 120 determines the wireless channel information when testing the wireless channel communication with the first communication device 110. The wireless channel information is used to indicate the wireless channel tested by the second communication device 120.

[0372] As mentioned above, the location information can be described by information such as the coordinates, longitude and latitude of the second communication device 120 in the coordinate system corresponding to the wireless communication network.

[0373] Step 1002: The first communication device 110 determines a standard MCS index value according to wireless channel information.

[0374] In some possible scenarios, the first communication device 120 uses a link adaptation algorithm to allocate an MCS table and determine a standard MCS index value based on wireless channel information. Specifically, a BLER threshold equal to 10% is generally defined. The first communication device 120 uses the link adaptation algorithm to allocate an MCS table so that the BLER does not exceed the threshold under different radio conditions.

[0375] It should be noted that the standard MCS index value is only named for the convenience of distinction. In some possible scenarios, it can also be called a reference MCS index value, or a first MCS index value. The embodiments of the present application do not make specific limitations on this.

[0376] Step 1003: The first communication device 110 runs an MCS index sorting model based on the received location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110 to obtain an MCS index sorting output by the MCS index sorting model.

[0377] For details, please refer to the description of step 903 and will not be repeated here.

[0378] Step 1004: The first communication device 110 determines a target sequence number based on the standard MCS index value and the MCS index sorting, where the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting.

[0379] In scenarios where the MCS index value threshold is not considered, the target sequence number is used to indicate the sequence number of the standard MCS index value in the MCS index sorting. For example, assuming the MCS index sorting can be [15, 16, 20, ..., 0], the standard MCS index value is 16, and the sequence number of the standard MCS index value is 2.

[0380] In the scenario where the MCS index value threshold is considered, in step 1004, the first communication device 110 determines the target sequence number based on the standard MCS index value, the MCS index order, and the MCS index value threshold. Specifically, the target sequence number can be determined in the following two implementations.

[0381] For the first implementation, if the standard MCS index value is less than or equal to the MCS index value threshold, the target sequence number is the sequence number of the standard MCS index value in the MCS index sorting.

[0382] For the second implementation method, if the standard MCS index value is greater than the MCS index value threshold, the target sequence number is the sequence number of the MCS index value in the MCS index sorting whose sequence number is less than or equal to the MCS index value threshold and is close to the standard MCS index value (which can be called a pseudo-standard MCS index value).

[0383] Exemplarily, the pseudo-standard MCS index value may be the MCS index value with the smallest absolute difference from the standard MCS index value among the MCS index values ​​whose sequence numbers are less than or equal to the MCS index value threshold in the MCS index sorting. For example, the sequence number of the standard MCS index value is 10. If the MCS index value threshold is 8, 10 exceeds 8. Therefore, the MCS index value closest to the standard MCS index value is selected from the first 8 MCS index values ​​in the MCS index sorting. Assuming that the sequence number of the MCS index value closest to the standard MCS index value is 5, 5 is used as the target sequence number.

[0384] It is worth noting that if there are multiple pseudo standard MCS index values, considering that the higher the ranking of the MCS index value, the higher the priority, the minimum value among the sequence numbers of the multiple pseudo standard MCS index values ​​can be selected as the target sequence number.

[0385] Step 1005 : The first communication device 110 sends a target sequence number to the second communication device 120 .

[0386] During specific implementation, the target sequence number is sent to the second communication device 120 via DCI.

[0387] Step 1006: The second communication device 120 runs the MCS index sorting model based on its own location information and the description information of the physical environment of the wireless communication network formed with the first communication device 110 to obtain the MCS index sorting output by the MCS index sorting model.

[0388] For details, please refer to the description of step 903 and will not be repeated here.

[0389] Step 1007: The second communication device 120 determines a target MCS index value based on the target sequence number and the MCS index sorting.

[0390] It should be noted that the target MCS index value is only named for the convenience of distinction. In some possible scenarios, it can also be called the second MCS index value, or the MCS index value to be used. The embodiments of the present application do not make specific limitations on this.

[0391] In some possible scenarios, the target MCS index value is the MCS index value corresponding to the target sequence number in the MCS index sorting. For example, assuming the MCS index sorting can be [15, 16, 20, ..., 0] and the sequence number is 2, the target MCS index value is 16. In this scenario, in step 1004, the process of determining the target sequence number does not consider the MCS index value threshold, or the process of determining the target sequence number considers the MCS index value threshold, and the standard MCS index value is less than or equal to the MCS index value threshold.

[0392] In other possible scenarios, such as when the MCS index value threshold is not considered in step 1004 and the standard MCS index value is greater than the MCS index value threshold, the target MCS index value may be determined based on the target sequence number, the MCS index ranking, and the MCS index value threshold in step 1007. Specifically, the target MCS index value is an MCS index value whose sequence number in the MCS index ranking is less than or equal to the MCS index value threshold and is close to the standard MCS index value (a pseudo-standard MCS index value).

[0393] Exemplarily, the pseudo-standard MCS index value may be the MCS index value with the smallest absolute difference from the standard MCS index value among the MCS index values ​​whose sequence numbers are less than or equal to the MCS index value threshold in the MCS index sorting. For example, the sequence number of the standard MCS index value is 10. If the MCS index value threshold is 8, 10 exceeds 8. Therefore, the MCS index value closest to the standard MCS index value is selected from the first 8 MCS index values ​​in the MCS index sorting. Assuming that the sequence number of the MCS index value closest to the standard MCS index value is 5, 5 is used as the target sequence number.

[0394] It is worth noting that if there are multiple pseudo-standard MCS index values, considering that the higher the ranking of the MCS index value, the higher the priority, the minimum value among the multiple pseudo-standard MCS index values ​​can be selected as the target MCS index value.

[0395] In this solution, the MCS index value is replaced by the sequence number, which can reduce the DCI signaling overhead.

[0396] In some possible scenarios, the wireless channel description module (first module) of the MCS index sorting model is deployed on the first communication device 110, and the sorting prediction module (second module) is deployed on the second communication device 120. Figure 11 is a flow chart of the communication method provided in an embodiment of the present application. This embodiment can be applied to a wireless communication system. As shown in Figure 11, the communication method provided in an embodiment of the present application includes at least the following steps:

[0397] Step 1101: The second communication device 120 reports its own location information to the first communication device 110.

[0398] As mentioned above, the location information can be described by information such as the coordinates, longitude and latitude of the second communication device 120 in the coordinate system corresponding to the wireless communication network.

[0399] Step 1102: The first communication device 110 runs a portion of the deployed MCS index sorting model based on the received location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110 to obtain description information of the wireless channel.

[0400] For example, in the embodiment of the present application, the wireless channel description module (first module) in the MCS index sorting module is deployed in the first communication device 110. As described above, the wireless channel description module (first module) is configured to output description information of the wireless channel between the first communication device 110 and the second communication device 120 based on the impact information of the wireless channel. For details, see the description of the wireless channel description module (first module) above.

[0401] It should be noted that the description information of the physical environment of the wireless communication network formed by the first communication device 110 can be reused. When the position of the second communication device 120 changes, the second communication device 120 can also report the changed location information. The changed location information is used to indicate the position of the second communication device 120 after moving in the wireless communication network. Correspondingly, the first communication device 110 runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110 to obtain the description information of the changed wireless channel.

[0402] Step 1103 : The first communication device 110 sends description information of the wireless channel to the second communication device 120 .

[0403] Step 1104: The second communication device 120 runs another part of the deployed MCS index sorting model based on the received description information of the wireless channel to obtain the MCS index sorting.

[0404] For example, in an embodiment of the present application, the ranking prediction module (second module) in the MCS index ranking module is deployed in the second communication device 120. The second communication device 120 can input the description information of the wireless channel into the ranking prediction module (second module) to obtain the second MCS index ranking output by the ranking prediction module (second module). Here, the ranking prediction module (second module) is used to determine the correspondence between the wireless channels and the MCS index ranking in the wireless communication network and output the MCS index ranking. In a specific application, the ranking prediction module (second module) can determine and output the MCS index ranking that matches the wireless channel based on the description information of the wireless channel.

[0405] It is worth noting that in addition to inputting the description information of the wireless channel into the sorting prediction module (second module), other information may also need to be input, such as the auxiliary information corresponding to the second communication device 120 in the aforementioned data collection and preprocessing. The specific content of the auxiliary information corresponding to the second communication device 120 can be found in the description above. It is worth noting that when the auxiliary information corresponding to the second communication device 120 includes the identifier of the MCS table, at this time, the first communication device 110 and the second communication device 120 need to uniformly configure the MCS table corresponding to the second communication device 120, and the corresponding auxiliary information corresponding to the second communication device 120 includes the identifier of the configured MCS table corresponding to the second communication device 120. It should be noted that the auxiliary information corresponding to the second communication device 120 can be reused. When the position of the second communication device 120 changes, the second communication device 120 can also obtain the description information of the changed wireless channel based on the first module in the MCS index sorting model. The description information of the changed wireless channel is used to indicate the wireless channel between the second communication device 120 and the first communication device 110 after the position change. Correspondingly, when the input of the MCS index sorting model does not include auxiliary information, the second communication device 120 runs the first module in the MCS index sorting model based on the description information of the changed wireless channel to obtain the description information of the wireless channel; when the input of the MCS index sorting model includes auxiliary information, the second communication device 120 runs the second module in the MCS index sorting model based on the description information of the changed wireless channel and the auxiliary information corresponding to the second communication device 120 to obtain the description information of the wireless channel.

[0406] Step 1105: The second communication device 120 determines a target MCS index value based on the MCS index sorting.

[0407] Please refer to the description of step 903 for details, which will not be repeated here.

[0408] The above embodiments of the communication method are merely examples and do not constitute specific limitations. Specifically, the communication method can be designed in conjunction with the deployment of the MCS index sorting model on the first communication device 110 and the second communication device 120. In some possible scenarios, the wireless channel description module (first module) is deployed on the second communication device 120, and the sorting prediction module (second module) is deployed on the first communication device 110. The communication method provided in the embodiments of the present application includes at least the following:

[0409] Based on its own location information and the description information of the physical environment of the wireless communication network formed by the first communication device 110, the second communication device 120 runs the wireless channel description module (first module) of the deployed MCS index sorting model, and obtains the description information of the wireless channel output by the wireless channel description module (first module) (for details, see the description of step 1102 above, which will not be repeated here); the second communication device 120 sends the description information of the wireless channel to the first communication device 110; based on the description information of the wireless channel, the first communication device 110 runs the sorting prediction module (second module) in the MCS index sorting model, obtains the MCS index sorting output by the sorting prediction module (second module), and determines the target MCS index value based on the MCS index sorting (for details, see the description of step 1104 above, which will not be repeated here); and sends the target MCS index value to the second communication device 120.

[0410] In some possible scenarios, the MCS index ranking model is deployed on the first communication device 110, and the ranking prediction module (second module) is deployed on the second communication device 120. The communication method provided in the embodiment of the present application includes at least the following contents:

[0411] Step 1: The second communication device 120 reports its own location information to the first communication device 110.

[0412] Step 2: The first communication device 110 executes the MCS index sorting model based on the received location information and the description of the physical environment of the wireless communication network formed by the first communication device 110, and obtains a first MCS index sorting output by the MCS index sorting model. For details, refer to the description of step 902 above and will not be repeated here.

[0413] Step 3: The first communication device 110 sends the first MCS index ranking to the second communication device 120.

[0414] Step 4: The second communication device 120 runs the module in the deployed MCS index sorting model based on the wireless channel information to obtain the second MCS index sorting output by the module in the deployed MCS index sorting model. For a detailed description of the wireless channel information, see step 1001.

[0415] Step 5: The second communication device 120 determines a target MCS index value based on the first MCS index sorting and the second MCS index sorting.

[0416] The target MCS index value is any one of 0 to 31. For details, please refer to the description of step 903 above, with the following differences:

[0417] In the scenario where the first communication device 110 does not store the MCS index value threshold corresponding to the second communication device 120, the target MCS index value is the n (greater than or equal to 2)-bit MCS index value that is at the first or top position in the first MCS index sorting and the second MCS index sorting.

[0418] In the scenario where the first communication device 110 stores the MCS index value threshold corresponding to the second communication device 120, the differences are as follows:

[0419] First, the MCS index sorting is a first MCS index sorting and a second MCS index sorting.

[0420] Second, there are multiple candidate MCS index values, where the multiple candidate MCS index values ​​are at least one first candidate MCS index value and a second candidate MCS index value, and the at least one first candidate MCS index value is each MCS index value less than or equal to the MCS index value threshold value among the MCS index values ​​indicated by the first MCS index sorting. The at least one second candidate MCS index value is each MCS index value less than or equal to the MCS index value threshold value among the MCS index values ​​indicated by the second MCS index sorting.

[0421] Third, the sequence number of the candidate MCS index value is the sequence number of the candidate MCS index value in the first MCS index sorting or the second MCS index sorting. There may be multiple candidate MCS index values ​​with the same sequence number.

[0422] Fourth, the target MCS index value may be n candidate MCS index values ​​with the smallest sequence number or the highest ranking among at least one candidate MCS index value.

[0423] It is worth noting that if there are multiple target MCS index values, the first communication device 110 compares the performance of the coding and modulation scheme indicated by each MCS index value, and uses the coding and modulation scheme indicated by the target MCS index value with the best performance as the scheme actually used.

[0424] In this solution, the target MCS index value is comprehensively determined by the first MCS index sorting and the second MCS index sorting, thereby improving the accuracy of the determined MCS index value.

[0425] In the above embodiment, in step 3, to improve communication efficiency, the first communication device 110 sends several MCS index values ​​with the highest priority in the first MCS index sorting (for ease of description and distinction, they may be referred to as first MCS index values) to the second communication device 120. For example, the MCS index value that is ranked first in the first MCS index sorting, or the MCS index values ​​in the first MCS index sorting that are less than or equal to the MCS index value threshold. Subsequently, in step 5, if the first index value with the highest priority in the first MCS index sorting and the MCS index value with the highest priority in the second MCS index sorting (for ease of description and distinction, they may be referred to as second MCS index values) are the same, the first index value with the highest priority in the first MCS index sorting is used as the target index value. In other possible scenarios, if the first index value with the highest priority in the first MCS index sorting and the second MCS index value with the highest priority in the second MCS index sorting are different, the first index value with the highest priority in the first MCS index sorting and the second MCS index value with the highest priority in the second MCS index sorting can be fused, or the maximum value of the first index value with the highest priority in the first MCS index sorting and the second MCS index value with the highest priority in the second MCS index sorting can be selected.

[0426] 6. Adaptively adjust the target MCS index value.

[0427] In the embodiment of the present application, during the use of the MCS index sorting model, the accuracy of the MCS index sorting can be determined based on the feedback from the second communication device 120, and the MCS index sorting can be adaptively adjusted.

[0428] As shown in FIG12 , based on the embodiment described in FIG9 , the communication method provided in the embodiment of the present application includes at least the following steps:

[0429] Step 905: The second communication apparatus 120 sends feedback information to the first communication apparatus 110, where the feedback information indicates a situation where communication is performed according to the coding and modulation scheme indicated by the target MCS index value.

[0430] In some examples, the feedback information may be an ACK, indicating that the target MCS index is available but not optimal, that is, it can be determined based on the resource information of the second communication device 120 that the second communication device 120 can be configured with an MCS with better performance. In other examples, the feedback information may also be a NACK, indicating that the target MCS index is not available, that is, it can be determined based on the resource information of the second communication device 120 that the second communication device 120 cannot successfully configure the modulation order and coding rate corresponding to the target MCS index.

[0431] Step 906 : The first communication device 110 updates the target MCS index value based on the feedback information from the second communication device 120 .

[0432] In an embodiment of the present application, the updated target MCS index may be greater than or less than the target MCS index.

[0433] It should be noted that in the embodiment of the present application, there is no need to consider whether the MCS index sorting model is credible. The MCS index sorting model is directly considered to be credible. The first communication device 110 can directly update the MCS index based on the feedback information of the second communication device 120 and the MCS index sorting output by the MCS index sorting model.

[0434] Exemplarily, when the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), it means that the MCS index indicated by the target MCS index value can carry less information, then the updated target MCS index value is greater than the target MCS index value.

[0435] Exemplarily, when the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), it means that the MCS index indicated by the target MCS index value can carry more information, and the updated MCS index value is smaller than the target MCS index value.

[0436] The first communication device 110 uses the MCS index sorting model to output the MCS index sorting. There are two ways in which the updated target MCS index can be greater than (less than) the target MCS index:

[0437] Mode 1: The first communication device 110 determines candidate MCS index values ​​that are greater than (smaller than) the target MCS index value from the MCS index ranking, and selects the candidate MCS index value with the smallest sequence number as the updated MCS index value.

[0438] Method 2: The first communication device 110 deletes the MCS index values ​​in the MCS index sorting that are less than or equal to the MCS index value threshold and greater than (less than) the target MCS index value, and obtains an updated MCS index sorting, where the MCS index values ​​in the updated MCS index sorting are less than or equal to the MCS index value threshold and greater than (less than) the target MCS index value; then, the MCS index value ranked first in the updated MCS index sorting is selected as the updated MCS index value.

[0439] Step 907 : The first communication device 110 sends the updated target MCS index value to the second communication device 120 .

[0440] In addition, based on the embodiment shown in FIG11 , the communication method provided in the embodiment of the present application may further include: updating the target MCS index value based on the feedback information of the second communication device 120. For details, see the description of step 1006 and will not be repeated here.

[0441] As shown in FIG13 , based on the embodiment described in FIG10 , if the target MCS index value is the MCS index value corresponding to the target sequence number in the MCS index sorting, the communication method provided in the embodiment of the present application includes at least the following steps:

[0442] Step 1008: The second communication apparatus 120 sends feedback information to the first communication apparatus 110, where the feedback information indicates a situation where communication is performed according to the coding and modulation scheme indicated by the target MCS index value.

[0443] Please refer to the description of step 1005 for details, which will not be repeated here.

[0444] Step 1009: The first communication device 110 determines an updated target sequence number based on the feedback information of the second communication device 120, the target MCS index value, and the standard MCS index value. The updated target sequence number indicates the sequence number of the updated target MCS index in the MCS index sorting.

[0445] It should be noted that the solution provided in the embodiment of the present application requires continuous execution of steps 1001 to 1007. Therefore, for each iteration, there are standard MCS index values ​​and target MCS index values. If the standard MCS index value and the target MCS index value are different, it means that the accuracy of the MCS index sorting model is relatively low. If the standard MCS index value and the target MCS index value are different for a long time, the MCS index sorting model is unreliable. In order to evaluate the reliability of the MCS index sorting model, the number of consecutive times the target MCS index value is different from the standard MCS index value can be recorded.

[0446] The first communication device 110 may determine the updated target sequence number in the following two ways:

[0447] Implementation Method A: When the MCS index ranking model is credible, that is, when the MCS index ranking model is highly accurate, for example, the number of consecutive times that the target MCS index value differs from the standard MCS index value is greater than or equal to 0 and less than or equal to a preset threshold, the first communication device 110 updates the target MCS index value based on the MCS index ranking output by the MCS index ranking model based on the feedback information from the second communication device 120, and determines the sequence number of the updated MCS index value in the MCS index ranking as the updated target sequence number. For the method of updating the target MCS index value based on the MCS index ranking output by the MCS index ranking model, see the relevant description in step 906.

[0448] In implementation A, the MCS index value is updated mainly through the following four methods.

[0449] (1) The number of consecutive times that the target MCS index value is different from the standard MCS index value is 0, indicating that the credibility of the MCS index sorting model is high, and the target MCS index value can be updated through the MCS index sorting; the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), which means that the MCS index indicated by the target MCS index value can carry less information, and the updated MCS index value is greater than the target MCS index value.

[0450] (2) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than 0 and less than or equal to the preset threshold value indicates that the MCS index sorting model has a certain degree of credibility and the target MCS index value can be updated through MCS index sorting; the target MCS index value is greater than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), which means that the MCS index indicated by the target MCS index value can carry less information, and the updated MCS index value is greater than the target MCS index value.

[0451] (3) The number of consecutive times that the target MCS index value is different from the standard MCS index value is 0, indicating that the credibility of the MCS index sorting model is high, and the target MCS index value can be updated through the MCS index sorting; the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the MCS index indicated by the target MCS index value can carry more information, and the updated MCS index value is smaller than the target MCS index value.

[0452] (4) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than 0 and less than or equal to the preset threshold value, indicating that the MCS index sorting model has a certain degree of credibility, and the target MCS index value can be updated through MCS index sorting; the target MCS index value is greater than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the MCS index indicated by the target MCS index value can carry less information. In this case, it means that the MCS index indicated by the target MCS index value can carry more information, and the updated MCS index value is less than the target MCS index value.

[0453] Implementation B: When the MCS index ranking model is unreliable, that is, when the MCS index ranking model has low accuracy, for example, if the number of consecutive times the target MCS index value differs from the standard MCS index value exceeds a preset threshold, the first communications device 110 determines an updated target MCS index based on the feedback information from the second communications device 120, the standard MCS index value, and the target MCS index value. Here, the updated target MCS index value is the standard MCS index value. Furthermore, the number of consecutive times the target MCS index value differs from the standard MCS index value is set to 0.

[0454] Exemplarily, when the target MCS index value is greater than the standard MCS index value, the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the target MCS index value is unavailable, and the updated MCS index value is the standard MCS index value.

[0455] Exemplarily, when the target MCS index value is less than the standard MCS index value, the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK). At this time, in order to ensure better results, the updated MCS index value is the standard MCS index value.

[0456] In addition, for implementation method B, on the one hand, considering that the MCS index sorting model is no longer trustworthy and that data can be continuously collected to update the MCS index sorting model, it can be replaced based on the already updated MCS index sorting model, reducing model update time and improving processing efficiency. Subsequently, the updated MCS index sorting model will need to be used. On the other hand, if the MCS index sorting model cannot be updated quickly, the MCS index value threshold can be updated, such as by increasing the MCS index value threshold. Subsequently, the updated MCS index value threshold will need to be used.

[0457] In summary, if the updated MCS index value is less than the target MCS index value, it may include but is not limited to the following three situations:

[0458] Case (1) The number of consecutive times that the target MCS index value is different from the standard MCS index value is 0, indicating that the credibility of the MCS index sorting model is high, and the target MCS index value can be updated through MCS index sorting; the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), which means that the MCS index indicated by the target MCS index value can carry less information, and the updated MCS index value is greater than the target MCS index value.

[0459] Case (2) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than 0 and less than or equal to the preset threshold value, indicating that the MCS index sorting model has a certain degree of credibility, and the target MCS index value can be updated through MCS index sorting; the target MCS index value is greater than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), which means that the MCS index indicated by the target MCS index value can carry less information, and the updated MCS index value is greater than the target MCS index value.

[0460] Case (3) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than the preset threshold, indicating that the MCS index sorting model is unreliable and the target MCS index value cannot be updated through MCS index sorting; the target MCS index value is less than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the target MCS index value is unavailable, and the updated MCS index value is the standard MCS index value.

[0461] If the updated MCS index value is less than the target MCS index value, the following three situations may occur:

[0462] Case (4) The number of consecutive times that the target MCS index value is different from the standard MCS index value is 0, indicating that the credibility of the MCS index sorting model is high, and the target MCS index value can be updated through MCS index sorting; the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the MCS index indicated by the target MCS index value can carry more information, and the updated MCS index value is smaller than the target MCS index value.

[0463] Case (5) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than 0 and less than or equal to the preset threshold value, indicating that the MCS index sorting model has a certain degree of credibility, and the target MCS index value can be updated through MCS index sorting; the target MCS index value is greater than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK), which means that the MCS index indicated by the target MCS index value can carry less information. In this case, it means that the MCS index indicated by the target MCS index value can carry more information, and the updated MCS index value is less than the target MCS index value.

[0464] Case (6) The number of consecutive times that the target MCS index value is different from the standard MCS index value is greater than the preset threshold, indicating that the MCS index sorting model is unreliable and the target MCS index value cannot be updated through MCS index sorting; the target MCS index value is greater than the standard MCS index value, and the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK). At this time, in order to ensure better results, the updated MCS index value is the standard MCS index value.

[0465] It should be noted that the above situation 6 is only an example and does not constitute a specific limitation. Specifically, the scheme for updating the MCS index value can be flexibly set in combination with actual needs to ensure that the coding modulation scheme is available or optimal. Exemplarily, based on the above situations (1) to (6), when the target MCS index value is greater than the standard MCS index value, the feedback information indicates that the MCS index indicated by the target MCS index value is available but not optimal (ACK), or when the target MCS index value is less than the standard MCS index value, the feedback information indicates that the MCS index indicated by the target MCS index value is unavailable (NACK). At this time, the MCS index sorting model and / or the MCS index value threshold can be updated.

[0466] Step 1010: The first communication device 110 sends the updated sequence number to the second communication device 120.

[0467] Step 1011: The second communication device 120 determines an updated target MCS index value based on the updated target sequence number and MCS index sorting.

[0468] Based on the same concept as the embodiment of the method of the present application, the embodiment of the present application also provides a model training device. The model training device includes several modules, each module is used to execute each step in the model training method provided in the embodiment of the present application, and the division of the modules is not limited here. Those skilled in the art can clearly understand that in actual applications, the various steps in the model training method, model deployment method, and communication method provided in the embodiment of the present application can be assigned to different modules as needed, that is, the internal structure of the device is divided into different modules to complete all or part of the functions described above. The modules in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more modules can be integrated into a unit, and the above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the modules are only for the convenience of distinguishing each other and are not used to limit the scope of protection of this application. The specific working process of the modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0469] For example, the model training device is used to execute the model training method provided in the embodiment of the present application. FIG14 is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. As shown in FIG14, the model training device provided in the embodiment of the present application includes:

[0470] Acquisition module 1401 is configured to acquire a sample, the sample including impact information of a wireless channel, where the wireless channel is a path between a first communication device and a second communication device, the impact information including description information of a physical environment of a wireless communication network formed by the first communication device and description information of a location of the second communication device in the wireless communication network; and an MCS index value of a modulation and coding scheme corresponding to the sample.

[0471] The training module 1402 is used to take samples as input and the MCS index values ​​corresponding to the samples as output, train the MCS index sorting model, and obtain a trained MCS index sorting model. The MCS index sorting model is used to output the MCS index sorting, and the MCS index sorting indicates the priority of the MCS index values ​​in the MCS table.

[0472] In a possible implementation manner, the description information of the physical environment includes description information of the location of the first communication device.

[0473] In one possible implementation, the MCS index ranking model is used to store a correspondence between each of multiple location points in the wireless communication network and a wireless channel, and a correspondence between the wireless channel and the MCS index ranking. The location point indicates the location of the second communication device in the wireless communication network. It should be understood that the location point can be a physical location point or a logical or virtual location point, such as a set of areas.

[0474] In a possible implementation, the sample further includes auxiliary information corresponding to the second communication apparatus, where the auxiliary information indicates information affecting the MCS index sorting in addition to the influencing information.

[0475] In one possible implementation, the auxiliary information includes one or more of the following:

[0476] Communication parameters of the wireless communication network and / or communication parameters of the second communication device; the communication parameters of the second communication device include an identifier of an MCS table, and the MCS table is used to record a mapping relationship between multiple MCS index values ​​and coding modulation schemes.

[0477] In one possible implementation, the MCS index ranking model includes a first module and a second module. The first module is configured to output description information of the wireless channel between the first communication device and the second communication device based on samples; the second module is configured to output an MCS index ranking based on the output of the first module. Exemplarily, the first module is the wireless channel description module described above, and the second module is the ranking prediction module described above.

[0478] In one possible implementation, the MCS index sorting model includes a first module and a second module, wherein the first module is used to output description information of the wireless channel between the first communication device and the second communication device based on the impact information of the wireless channel; and the second module is used to output the MCS index sorting based on the output of the first module and the auxiliary information corresponding to the second communication device.

[0479] It should be noted that, in some possible cases, the model training device is deployed on the first communication device 110, the second communication device 120 and / or a third-party device.

[0480] Based on the same concept as the embodiment of the method of the present application, the embodiment of the present application also provides a model deployment device. The model training device includes several modules, each of which is used to execute each step of the model deployment method provided in the embodiment of the present application. The division of modules is not limited here.

[0481] For example, the model deployment device is used to execute the model deployment method provided in the embodiment of the present application. FIG15 is a schematic diagram of the structure of the model deployment device provided in the embodiment of the present application. As shown in FIG15, the model deployment device provided in the embodiment of the present application includes:

[0482] An acquisition module 1501 is configured to acquire description information of available hardware resources of a second communication device;

[0483] An analyzing module 1502 is configured to determine a model deployment solution based on the description information, where the model deployment solution indicates content of the MCS index sorting model deployed on the first communication device and the second communication device;

[0484] The deployment module 1503 is used to deploy at least part of the MCS index sorting model according to the model deployment plan.

[0485] In a possible implementation, the model deployment solution is to deploy the first module on a first communication device and the second module on a second communication device.

[0486] In some possible implementations, the model deployment scheme includes a first bit value and a second bit value, the first bit value is used to indicate that the first module is deployed on the first communication device or the second communication device, and the second bit value is used to indicate that the second module is deployed on the first communication device or the second communication device.

[0487] In a possible implementation, the analysis module 1502 is configured to send the content of the MCS index sorting model deployed on the second communication device to the second communication device, so that the second communication device deploys the content.

[0488] In one possible implementation, the analysis module 1502 is used to send a model deployment plan to the second communication device, and send an identifier of the second communication device and a model deployment plan to other communication devices that communicate with the second communication device, so that the second communication device obtains the content of the MCS index sorting model deployed in the second communication device from the other communication devices.

[0489] In a possible implementation, the analysis module 1502 is configured to send a model deployment solution to the second communication device, so that the second communication device obtains the content of the MCS index sorting model deployed in the second communication device from other communication devices communicating with it.

[0490] It should be noted that, in some possible cases, the model deployment device is deployed in the first communication device 110 and / or a third-party device.

[0491] Based on the same concept as the embodiment of the method of the present application, the embodiment of the present application also provides a communication device. The communication device includes several modules, each module is used to perform each step in the communication method provided in the embodiment of the present application, and there is no limitation on the division of the modules. Here, the communication device is used to perform the communication method performed by the first communication device provided in the embodiment of the present application.

[0492] For example, FIG16 is a structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG16 , the communication device provided in an embodiment of the present application includes:

[0493] Receiving module 1601, configured to receive location information sent by a second communication device, where the location information indicates a location of the second communication device in a wireless communication network formed by the first communication device;

[0494] A ranking determination module 1602 is configured to run an MCS index ranking model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index ranking output by the MCS index ranking model;

[0495] An index value determining module 1603 is configured to determine a target MCS index value based on the MCS index sorting;

[0496] The sending module 1604 is configured to send the target MCS index value to the second communication device.

[0497] In one possible implementation, the ranking determination module 1602 is configured to run an MCS index ranking model based on location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0498] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0499] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0500] In a possible implementation, the receiving module 1601 is configured to receive the changed location information sent by the second communication device;

[0501] The sorting determination module 1602 is used to run the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or to run the MCS index sorting model based on the changed location information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0502] In one possible implementation, the device further includes: an updating module configured to update the target index value based on feedback information and MCS index sorting from the second communication device; the feedback information indicates a situation where communication is performed according to a coding modulation scheme indicated by the second MCS index value.

[0503] For example, FIG17 is a second structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG17 , the communication device provided in an embodiment of the present application includes:

[0504] Receiving module 1701, configured to receive wireless channel information and location information sent by a second communication device, where the wireless channel information indicates a condition of a wireless channel between the second communication device and the first communication device; and the location information indicates a location of the second communication device in a wireless communication network formed by the first communication device.

[0505] An index value determining module 1702 is configured to determine a standard MCS index value based on wireless channel information;

[0506] A ranking determination module 1703 is configured to run a deployed MCS index ranking model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to determine an MCS index ranking output by the MCS index ranking model;

[0507] A sequence number determination module 1704 is configured to determine a target sequence number based on the MCS index sorting and the standard MCS index value; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting;

[0508] The sending module 1705 is used to send the target sequence number to the second communication device, so that the second communication device runs the deployed MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and determines the target MCS index value based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

[0509] According to a feasible implementation, when the sequence number of the standard MCS index value in the MCS index sorting is less than or equal to the MCS index value threshold, the target MCS index value is the standard index value.

[0510] According to a feasible implementation method, when the sequence number of the standard MCS index value in the MCS index sorting is greater than the MCS index value threshold, the target MCS index value is less than or equal to the MCS index value threshold in the MCS index sorting and has the smallest difference with the standard MCS index value.

[0511] According to a feasible implementation method, the device also includes: an update module, which is used to update the target index value based on the feedback information, standard index value, target index value and MCS index sorting of the second communication device; the feedback information indicates the situation of communicating according to the coding modulation scheme indicated by the target MCS index value.

[0512] According to a feasible implementation, the ranking determination module 1703 is configured to run an MCS index ranking model based on location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0513] According to a feasible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0514] According to a feasible implementation, the receiving module 1701 is configured to receive the changed location information sent by the second communication device;

[0515] The sorting determination module 1703 is used to run the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or to run the MCS index sorting model based on the changed location information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0516] For example, FIG18 is a second structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG18 , the communication device provided in an embodiment of the present application includes:

[0517] A receiving module 1801 is configured to receive location information sent by a second communication device, where the location information indicates a location of the second communication device in a wireless communication network formed by the first communication device;

[0518] a description information determining module 1802 configured to execute the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, to obtain description information of the wireless channel output by the first module;

[0519] The sending module 1803 is used to send description information of the wireless channel to the second communication device, so that the second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting.

[0520] In one possible implementation, the receiving module 1801 is used to receive the changed location information sent by the second communication device; the description information determination module 1802 is used to run the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

[0521] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0522] Based on the same concept as the method embodiment of the present application, the embodiment of the present application also provides a communication device. The communication device includes several modules, each of which is used to perform each step of the communication method provided in the embodiment of the present application. The division of modules is not limited here. Here, the communication device is used to perform the communication method performed by the second communication device provided in the embodiment of the present application.

[0523] For example, FIG19 is a second structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG19 , the communication device provided in an embodiment of the present application includes:

[0524] A sending module 1901 is configured to send wireless channel information and location information to a first communication device, where the wireless channel information indicates a condition of a wireless channel between a second communication device and the first communication device; the location information indicates a location of the second communication device in a wireless communication network formed by the first communication device; so that the first communication device determines a target MCS index value based on the wireless channel information; runs an MCS index sorting model based on the location information and description information of a physical environment of the wireless communication network formed by the first communication device to determine an MCS index sorting output by the MCS index sorting model; determines a target sequence number based on the MCS index sorting and a standard MCS index value; the target sequence number being less than or equal to a sequence number of the standard MCS index value in the MCS index sorting;

[0525] Receiving module 1902, configured to receive a target sequence number sent by a first communication device;

[0526] The ranking determination module 1903 is configured to run the MCS index ranking model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to determine the MCS index ranking output by the MCS index ranking model.

[0527] The index value determination module 1904 is configured to determine a target MCS index value based on the target sequence number and the MCS index ranking output by the MCS index ranking model.

[0528] According to a feasible implementation, the ranking determination module 1903 is configured to run an MCS index ranking model based on location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

[0529] According to a feasible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0530] A sending module 1901 is configured to send the changed location information to the first communication device, so that the first communication device runs an MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or runs the MCS index sorting model based on the changed location information, the description information of the physical environment of the wireless communication network formed by the first communication device, and the auxiliary information corresponding to the second communication device;

[0531] The sorting determination module 1903 is used to run the MCS index sorting model based on the changed position information and the description information of the physical environment of the wireless communication network formed by the first communication device; or to run the MCS index sorting model based on the changed position information, the description information of the physical environment of the wireless communication network formed by the first communication device and the auxiliary information corresponding to the second communication device.

[0532] For example, FIG20 is a second structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG20 , the communication device provided in an embodiment of the present application includes:

[0533] A sending module 2001 is configured to send location information to a first communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; so that the first communication device runs a first module in an MCS index sorting model based on the location information and description information of a physical environment of the wireless communication network formed by the first communication device, to obtain description information of a wireless channel output by the first module;

[0534] The receiving module 2002 is configured to receive description information of a wireless channel sent by a first communication device;

[0535] The ranking determination module 2003 is configured to run the second module in the MCS index ranking model based on the description information of the wireless channel to obtain the MCS index ranking output by the second module;

[0536] The index value determination module 2004 is configured to determine a target MCS index value based on the MCS index sorting.

[0537] In a possible implementation, the ranking determination module 2003 is configured to run the second module in the MCS index ranking model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

[0538] In a possible implementation, the first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

[0539] In a possible implementation, the target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

[0540] In one possible implementation, the sending module 2001 is configured to send the changed location information to the first communication device, so that the first communication device runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and the first module outputs the description information of the changed wireless channel;

[0541] The ranking determination module 2003 is configured to run the second module in the MCS index ranking model based on the description information of the changed wireless channel.

[0542] Based on the same concept as the method embodiment of the present application, the embodiment of the present application also provides a first communication device 110.

[0543] FIG21 is a schematic structural diagram of a first communication device 110 provided in an embodiment of the present application.

[0544] As shown in FIG. 21 , the first communication device 110 includes a processor 111 , a memory 112 , and a network interface 113 .

[0545] The processor 111 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0546] In an embodiment of the present application, the processor 111 may include a communication and processing circuit. The communication and processing circuit may include one or more hardware components that provide a physical structure that performs various processes related to wireless communication (e.g., signal reception and / or signal transmission). The communication and processing circuit may include two or more transmit / receive chains. The functions implemented by the communication and processing circuit may also be processed on a computer-readable medium.

[0547] The processor 111 may include an information processing circuit configured to process wireless channel impact information, process auxiliary information, execute an MCS index ranking model (including a wireless channel description module (first module) and a ranking prediction module (second module)), determine an MCS index value based on the MCS index ranking, and support subsequent coding and modulation of the MCS index value. The functions of the information processing circuit may also be processed on a computer-readable medium.

[0548] Processor 111 also includes a coding and modulation circuit configured to encode and modulate the output of the MCS index ranking model to obtain a transmit signal. For example, the circuit determines an MCS index value based on the MCS index ranking output of the MCS index ranking model, and performs coding and modulation on the MCS index value. The coding and modulation circuit may include coding and modulation functionality. The functionality of the coding and modulation circuit may also be stored on a computer-readable medium.

[0549] Among them, the non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0550] For example, a computer program may be stored in the memory 112, and when the processor 111 executes the computer program, the steps in the above-mentioned model training method, model deployment method, and communication method embodiments are implemented, such as steps 601 and 602 described in Figure 6, steps 701 to 703 shown in Figure 7, and the steps performed by the first communication device 110 in Figures 9, 10, and 11. Alternatively, when the processor 111 executes the computer program, the functions of the modules in the above-mentioned device embodiments are implemented. For example, the computer program may be divided into one or more modules / units, and the one or more modules / units may be a series of computer program instruction segments that can perform specific functions. The one or more modules / units are stored in the memory 112 and executed by the processor 111 to complete this application. For example, a computer program may be divided into an acquisition module 1401 and a training module 1402; or, an acquisition module 1501, an analysis module 1502, and a deployment module 1503; or, a receiving module 1601, a sorting determination module 1602, and an index value determination module 1603; or, a receiving module 1701, an index value determination module 1702, a sorting determination module 1703, a sequence number determination module 1704, and a sending module 1705; or, a receiving module 1801, a description information determination module 1802, and a sending module 1803; wherein, the specific functions of each module are described above.

[0551] The network interface 113 is used to send and receive data, for example, to send data processed by the processor 111 to other electronic devices such as the second communication device 120 or a third-party device, or to receive data sent by other electronic devices.

[0552] Of course, for the sake of simplicity, FIG21 only shows some of the components of the first communication device 110 that are related to the present application, and omits components such as a bus, an input / output interface, an antenna, and the like.

[0553] Based on the same concept as the method embodiment of the present application, the embodiment of the present application also provides a second communication device 120.

[0554] FIG22 is a schematic structural diagram of a second communication device 120 provided in an embodiment of the present application.

[0555] As shown in FIG. 22 , the second communication device 120 includes a processor 121 , a memory 122 , and a network interface 123 .

[0556] The details of the processor 121 refer to the description of the processor 111 and will not be repeated here.

[0557] Among them, for the detailed contents of the memory 122, please refer to the description of the memory 112 and will not be repeated here. The difference is that a computer program can be stored on the memory 122, and when the processor 121 executes the computer program, it implements the steps in the above-mentioned model training method, model deployment method, and communication method embodiments, such as steps 601 and 602 described in Figure 6, steps 701 to 703 shown in Figure 7, and the steps performed by the second communication device 120 in Figures 9, 10, and 11. Alternatively, when the processor 121 executes the computer program, it implements the functions of each module in the above-mentioned device embodiment. Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units can be a series of computer program instruction segments that can perform specific functions. The one or more modules / units are stored in the memory 122 and executed by the processor 121 to complete this application. For example, the computer program can be divided into an acquisition module 1401 and a training module 1402; or, an acquisition module 1501, an analysis module 1502, and a deployment module 1503; or, a sending module 1901, a receiving module 1902, a sorting determination module 1903, and an index value determination module 1904; or, a sending module 2001, a receiving module 2002, a sorting determination module 2003, and an index value determination module 2004; wherein, the specific functions of each module can be found in the description above.

[0558] Based on the same concept as the method embodiment of the present application, the embodiment of the present application also provides an electronic device, which includes a processor, a memory, and a network interface.

[0559] For details of the processor, please refer to the description of processor 111 and will not be repeated here.

[0560] Among them, for the detailed contents of the memory, please refer to the description of the memory 112 and will not be repeated here. The difference is that a computer program can be stored on the memory, and when the processor executes the computer program, the steps in the above-mentioned model training method and model deployment method embodiments are implemented, such as steps 601 and 602 described in Figure 6, and steps 701 to 703 shown in Figure 7. Alternatively, when the processor executes the computer program, the functions of each module in the above-mentioned device embodiment are implemented. Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units can be a series of computer program instruction segments that can perform specific functions. The one or more modules / units are stored in the memory and executed by the processor to complete this application. For example, the computer program can be divided into an acquisition module 1401 and a training module 1402; or, an acquisition module 1501, an analysis module 1502, and a deployment module 1503; wherein, the specific functions of each module can be described above.

[0561] The network interface is used to send and receive data, for example, to send data processed by the processor 111 to other electronic devices such as the first communication device 110 and the second communication device 120, or to receive data sent by other electronic devices.

[0562] The embodiment of the present application may also provide a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to execute the steps of the model training method, model deployment method, and communication method of the various embodiments of the present application described in the "Method" section above. The computer program product can be written in any combination of one or more programming languages ​​to write computer program code for performing the operations of the embodiments of the present application, and the programming language includes an object-oriented programming language such as Java, C++, etc., and also includes a conventional procedural programming language such as "C" language or a similar programming language. The computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0563] In addition, an embodiment of the present application may also provide a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps in the display control method according to various embodiments of the present disclosure described in the "Method" section above. The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0564] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0565] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0566] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of the present disclosure. In addition, the specific details disclosed above are merely illustrative and for ease of understanding, and are not restrictive. The above details do not limit the present disclosure to necessarily being implemented using the above specific details.

[0567] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0568] It should also be noted that in the apparatus, device, and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0569] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

[0570] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

Claims

1. A model training method, characterized in that: include: Obtaining a sample, the sample including impact information of a wireless channel, the wireless channel being a path between a first communication device and a second communication device, the impact information including description information of a physical environment of a wireless communication network formed by the first communication device and description information of a location of the second communication device in the wireless communication network; and an MCS index value of a modulation and coding scheme corresponding to the sample; Taking the sample as input and the MCS index value corresponding to the sample as output, an MCS index sorting model is trained to obtain a trained MCS index sorting model. The MCS index sorting model is used to output an MCS index sorting, and the MCS index sorting indicates the priority of the MCS index value in the MCS table.

2. The method according to claim 1, characterized in that The trained MCS index sorting model is used to store a correspondence between each of a plurality of position points in the wireless communication network and a wireless channel, and a correspondence between the wireless channel and the MCS index sorting; the position point indicates a position of the second communication device in the wireless communication network; and / or, The sample further includes auxiliary information corresponding to the second communication device, where the auxiliary information indicates information affecting the MCS index sorting other than the influencing information.

3. The method according to claim 2, characterized in that The auxiliary information includes one or more of the following: The communication parameters of the wireless communication network and / or the communication parameters of the second communication device; the communication parameters of the second communication device include an identifier of an MCS table, and the MCS table is used to record a mapping relationship between multiple MCS index values ​​and coding modulation schemes.

4. The method according to any one of claims 1 to 3, characterized in that: The MCS index sorting model includes a first module and a second module. The first module is used to output description information of the wireless channel between the first communication device and the second communication device based on the sample; the second module outputs the MCS index sorting based on the output of the first module.

5. The method according to claims 1 to 3, characterized in that The MCS index sorting model includes a first module and a second module, wherein the first module is used to output description information of the wireless channel between the first communication device and the second communication device based on the impact information of the wireless channel; and the second module is used to output the MCS index sorting based on the output of the first module and the auxiliary information corresponding to the second communication device.

6. A model deployment method, characterized in that: The method comprises: Obtaining description information of available hardware resources of the second communication device; Determining a model deployment scheme based on the description information, the model deployment scheme indicating content of an MCS index sorting model deployed in the first communication device and the second communication device, the MCS index sorting model being trained by the method according to any one of claims 1 to 5; Deploy at least a portion of the MCS index sorting model according to the model deployment scheme.

7. The method according to claim 6, characterized in that The model deployment solution is to deploy the first module on a first communication device and the second module on a second communication device.

8. The method according to claim 6 or 7, characterized in that The deploying the MCS index sorting model according to the model deployment scheme includes: The content of the MCS index sorting model deployed on the second communication device is sent to the second communication device, so that the second communication device deploys the content.

9. The method according to claim 6 or 7, characterized in that The deploying the MCS index sorting model according to the model deployment scheme includes: Sending the model deployment scheme to the second communication device, and sending the identifier of the second communication device and the model deployment scheme to other communication devices communicating with the second communication device, so that the second communication device obtains the content of the MCS index sorting model deployed on the second communication device from the other communication device; or The model deployment solution is sent to the second communication device, so that the second communication device obtains the content of the MCS index sorting model deployed in the second communication device from other communication devices communicating with it.

10. A communication method, characterized in that: Applied to a first communication device, the method includes: receiving location information sent by a second communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; Based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, the MCS index sorting model is run to obtain the MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by the method according to any one of claims 1 to 5; Determining a target MCS index value based on the MCS index sorting; The target MCS index value is sent to the second communication device.

11. The method according to claim 10, characterized in that The description information of the physical environment of the wireless communication network formed based on the location information and the first communication device includes: The MCS index sorting model is run based on the location information, the auxiliary information corresponding to the second communication device, and the description information of the physical environment of the wireless communication network formed by the first communication device.

12. The method according to any one of claim 11, characterized in that: configuring, by the first communication device and the second communication device, an MCS table corresponding to the second communication device; The auxiliary information corresponding to the second communication device includes an identifier of a configured MCS table corresponding to the second communication device.

13. The method according to any one of claims 10 to 12, characterized in that: The method further comprises: receiving the changed location information sent by the second communication device; The MCS index sorting model is run based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or the MCS index sorting model is run based on the changed location information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

14. The method according to any one of claims 11 to 13, characterized in that: The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

15. The method according to any one of claims 11 to 14, characterized in that: The method further comprises: Based on the feedback information of the second communication device and the MCS index sorting, the target index value is updated; the feedback information indicates a situation where communication is performed according to the coding and modulation scheme indicated by the target MCS index value.

16. A communication method, characterized in that: Applied to a first communication device, the method includes: receiving wireless channel information and location information sent by a second communication device, wherein the wireless channel information indicates a condition of a wireless channel between the second communication device and the first communication device; and the location information indicates a location of the second communication device in a wireless communication network formed by the first communication device; Determining a standard MCS index value based on the wireless channel information; Based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, running the deployed MCS index sorting model to determine the MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by the method according to any one of claims 1 to 5; Determining a target sequence number based on the MCS index sorting and the standard MCS index value; wherein the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting; The target sequence number is sent to the second communication device so that the second communication device runs the deployed MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and determines the target MCS index value based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

17. The method according to claim 16, characterized in that The sequence number of the standard MCS index value in the MCS index sorting is less than or equal to the MCS index value threshold, and the target MCS index value is the standard index value; or, The sequence number of the standard MCS index value in the MCS index sorting is greater than the MCS index value threshold, and the target MCS index value is less than or equal to the MCS index value threshold in the MCS index sorting and has the smallest difference from the standard MCS index value.

18. The method according to claim 16 or 17, characterized in that The method further comprises: Based on the feedback information of the second communication device, the standard index value, the target index value and the MCS index sorting, the target index value is updated; the feedback information indicates the situation of communicating according to the coding modulation scheme indicated by the target MCS index value.

19. The method according to any one of claims 16 to 18, characterized in that: The description information of the physical environment of the wireless communication network formed based on the location information and the first communication device includes: The MCS index sorting model is run based on the location information, the auxiliary information corresponding to the second communication device, and the description information of the physical environment of the wireless communication network formed by the first communication device.

20. The method according to claim 19, characterized in that The first communication device and the second communication device configure an MCS table corresponding to the second communication device; The auxiliary information corresponding to the second communication device includes an identifier of a configured MCS table corresponding to the second communication device.

21. The method according to any one of claims 16 to 20, characterized in that The method further comprises: receiving the changed location information sent by the second communication device; The MCS index sorting model is run based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device; or the MCS index sorting model is run based on the changed location information, the auxiliary information corresponding to the second communication device and the description information of the physical environment of the wireless communication network formed by the first communication device.

22. A communication method, characterized in that: Applied to a first communication device, the method includes: receiving location information sent by a second communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; Based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, running the first module in the MCS index sorting model to obtain the description information of the wireless channel output by the first module; Send the description information of the wireless channel to the second communication device, so that the second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting.

23. The method according to claim 22, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

24. The method according to claim 22 or 23, characterized in that The method further comprises: receiving the changed location information sent by the second communication device; Based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device, a first module in the MCS index sorting model is executed.

25. A communication method, characterized in that: Applied to a first communication device, the method includes: receiving description information of a wireless channel sent by a second communication device, the description information of the wireless channel being description information of the second communication device based on location information and a physical environment of a wireless communication network formed by the first communication device, running a first module in an MCS index sorting model, wherein the first module outputs a result, the location information indicating a location of the second communication device in the wireless communication network formed by the first communication device; Running a second module in the MCS index sorting model based on the description information of the wireless channel to obtain an MCS index sorting output by the second module; Determine a target MCS index value based on the MCS index sorting; The target MCS index value is sent to the second communication device.

26. The method according to claim 25, characterized in that The running of the second module in the MCS index sorting model based on the description information of the wireless channel includes: Based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device, the second module in the MCS index sorting model is executed.

27. The method according to claim 26, characterized in that The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

28. The method according to any one of claims 25 to 27, characterized in that The method further comprises: receiving description information of the changed wireless channel sent by the second communication device; Based on the description information of the changed wireless channel, the second module in the MCS index sorting model is run.

29. The method according to any one of claims 25 to 28, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

30. A communication method, characterized in that: Applied to a second communication device, the method includes: Sending wireless channel information and location information to a first communication device, wherein the wireless channel information indicates a condition of a wireless channel between the second communication device and the first communication device; the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; so that the second communication device determines a target MCS index value based on the wireless channel information; running the MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to determine an MCS index sorting output by the MCS index sorting model; determining a target sequence number based on the MCS index sorting and the standard MCS index value; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting; the MCS index sorting model is trained by the method of any one of claims 1 to 5; receiving a target sequence number sent by the first communication device; running the deployed MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device; A target MCS index value is determined based on the target sequence number and the MCS index sorting output by the MCS index sorting model.

31. The method according to claim 30, wherein The first communication device and the second communication device configure an MCS table corresponding to the second communication device; The running and deploying of the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device includes: The MCS index sorting model is run based on the location information, the description information of the physical environment of the wireless communication network formed by the first communication device, and the identifier of the configured MCS table corresponding to the second communication device.

32. A communication method, characterized in that: Applied to a second communication device, the method includes: sending location information to the first communication device, the location information indicating the location of the second communication device in the wireless communication network formed by the first communication device; causing the first communication device to run a first module in the MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device, to obtain description information of the wireless channel output by the first module; receiving description information of the wireless channel sent by the first communication device; Running a second module in the MCS index sorting model based on the description information of the wireless channel to obtain an MCS index sorting output by the second module; A target MCS index value is determined based on the MCS index ranking.

33. The method according to claim 32, characterized in that The running of the second module in the MCS index sorting model based on the description information of the wireless channel includes: Based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device, the second module in the MCS index sorting model is executed.

34. The method according to claim 33, wherein The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

35. The method according to claim 33 or 34, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

36. The method according to any one of claims 32 to 35, characterized in that The method further comprises: The changed location information is sent to the first communication device, so that the first communication device runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

37. [Corrected 23.12.2024 in accordance with Rule 26] A communication method, characterized in that Applied to a second communication device, the method includes: Running a first module in an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device to obtain description information of a wireless channel output by the first module, wherein the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; Sending the description information of the wireless channel to the first communication device, so that the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines a target MCS index value based on the MCS index sorting; Receive the target MCS index value sent by the first communication device.

38. The method according to claim 37, wherein The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

39. The method according to claim 37 or 38, characterized in that The method further comprises: Auxiliary information corresponding to the second communication device is sent to the first communication device, so that the first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

40. A communication method, characterized in that: The method comprises: The second communication device sends location information to the first communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; The first communication device runs an MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by any one of the methods described in claims 1 to 5; The first communication device determines a target MCS index value based on the MCS index sorting; The first communication device sends the target MCS index value to the second communication device.

41. The method according to claim 40, wherein The first communication device runs an MCS index sorting model based on the location information and description information of a physical environment of a wireless communication network formed by the first communication device, including: An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

42. The method according to claim 41, wherein The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

43. The method according to any one of claims 40 to 42, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

44. The method according to any one of claims 40 to 43, characterized in that The method further comprises: The first communication device updates a target MCS index value based on feedback information from the second communication device and the MCS index sorting; the feedback information indicates a situation where communication is performed according to a coding and modulation scheme indicated by the target MCS index value.

45. The method according to any one of claims 40 to 43, characterized in that The method further comprises: The second communication device sends the changed location information to the first communication device; The first communication device runs the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

46. ​​A communication method, characterized in that: The method comprises: The second communication device sends wireless channel information and location information to the first communication device, wherein the wireless channel information indicates a condition of a wireless channel between the second communication device and the first communication device; and the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device. The first communication device determines a standard MCS index value based on the wireless channel information; The first communication device runs an MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; the MCS index sorting model is trained by any one of the methods described in claims 1 to 5; The first communication device determines a target sequence number based on the MCS index sorting and the standard MCS index value; the target sequence number is less than or equal to the sequence number of the standard MCS index value in the MCS index sorting; The first communication device sends the target sequence number to the second communication device; The second communication device runs the deployed MCS index sorting model based on the location information and description information of the physical environment of the wireless communication network formed by the first communication device to obtain an MCS index sorting output by the MCS index sorting model; The second communication device determines a target MCS index value based on the target sequence number and the MCS index sorting.

47. The method according to claim 46, wherein The sequence number of the standard MCS index value in the MCS index sorting is less than or equal to the MCS index value threshold, and the target MCS index value is the standard MCS index value.

48. The method according to claim 46, wherein The sequence number of the standard MCS index value in the MCS index sorting is greater than the MCS index value threshold, and the target MCS index value is less than or equal to the MCS index value threshold in the second MCS index sorting and has the smallest difference from the standard MCS index value.

49. The method according to any one of claims 46 to 48, characterized in that The method further comprises: The first communication device updates the target MCS index value based on the feedback information of the second communication device, the standard MCS index value, the target MCS index value and the MCS index sorting; the feedback information indicates the situation of communicating according to the coding modulation scheme indicated by the target MCS index value.

50. The method according to any one of claims 46 to 49, characterized in that The running of an MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device includes: An MCS index sorting model is run based on the location information, description information of a physical environment of a wireless communication network formed by the first communication device, and auxiliary information corresponding to the second communication device.

51. The method according to claim 50, wherein The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

52. The method according to any one of claims 46 to 51, characterized in that The method further comprises: The second communication device sends the changed location information to the first communication device; The first communication device runs the MCS index sorting model based on the changed location information and description information of the physical environment of the wireless communication network formed by the first communication device.

53. A communication method, characterized in that: The method comprises: The second communication device sends location information to the first communication device, where the location information indicates a location of the second communication device in the wireless communication network formed by the first communication device; The first communication device runs the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device, and obtains the description information of the wireless channel output by the first module; The first communication device sends description information of the wireless channel to the second communication device; The second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, obtains the MCS index sorting output by the second module, and determines the target MCS index value based on the MCS index sorting.

54. The method according to claim 53, wherein The second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, including: The second communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

55. The method according to claim 54, characterized in that The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

56. The method according to any one of claims 53 to 55, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

57. The method according to any one of claims 53 to 56, characterized in that The method further comprises: The second communication device sends the changed location information to the first communication device; The first communication device runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

58. A communication method, characterized in that: The method comprises: The second communication device runs the first module in the MCS index sorting model based on the location information and the description information of the physical environment of the wireless communication network formed by the first communication device to obtain the description information of the wireless channel output by the first module, wherein the location information indicates the location of the second communication device in the wireless communication network formed by the first communication device; The second communication device sends the description information of the wireless channel to the first communication device; The first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel to obtain the MCS index sorting output by the second module; The first communication device determines a target MCS index value based on the MCS index sorting; The first communication device sends a target MCS index value to the second communication device.

59. The method according to claim 58, characterized in that The first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel, including: The first communication device runs the second module in the MCS index sorting model based on the description information of the wireless channel and the auxiliary information corresponding to the second communication device.

60. The method according to claim 59, wherein The first communication device and the second communication device configure an MCS table corresponding to the second communication device; the auxiliary information corresponding to the second communication device includes an identifier of the configured MCS table corresponding to the second communication device.

61. The method according to any one of claims 58 to 60, characterized in that The target MCS index value is the MCS index value that is ranked first in the MCS index sorting.

62. The method according to any one of claims 58 to 61, characterized in that The method further comprises: The second communication device sends the changed location information to the first communication device; The first communication device runs the first module in the MCS index sorting model based on the changed location information and the description information of the physical environment of the wireless communication network formed by the first communication device.

63. A model training device, characterized in that include: at least one memory for storing a program; At least one processor is configured to execute the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to execute the method according to any one of claims 1 to 5.

64. A model deployment device, characterized in that include: at least one memory for storing a program; At least one processor is configured to execute the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to execute the method according to any one of claims 6 to 9.

65. A first communication device, characterized in that: include: at least one memory for storing a program; At least one processor is used to execute the program stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 6 to 29.

66. A second communication device, characterized in that include: at least one memory for storing a program; At least one processor is used to execute the program stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 30 to 39.

67. A computing device cluster, characterized in that: comprising at least one computing device, each computing device including a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in a memory of the at least one computing device, so that the computing device cluster executes the method according to claims 1 to 9.

68. A computer storage medium, characterized in that The computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the method according to any one of claims 1 to 62.

69. A computer program product comprising instructions, characterized in that When the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 62.

Images