WO2023124694A1

WO2023124694A1 - Channel access mode determination method and apparatus

Info

Publication number: WO2023124694A1
Application number: PCT/CN2022/134771
Authority: WO
Inventors: 刘鹏; 郭子阳; 郭宇宸; 杨讯
Original assignee: 华为技术有限公司
Priority date: 2021-12-30
Filing date: 2022-11-28
Publication date: 2023-07-06
Also published as: CN116419416A

Abstract

The present application provides a channel access mode determination method and apparatus. In the method, a first apparatus receives a performance evaluation value of a first channel access mode, and determines, according to the performance evaluation value, a channel access mode of a station (STA) from the first channel access mode and a second channel access mode, wherein the first channel access mode refers to determining, by means of a neural network, that the STA gets access to a channel, the second channel access mode refers to determining, by means of carrier-sense multiple access with collision avoidance, that the STA gets access to the channel, and the performance evaluation value comprises at least one of the accuracy and a loss value of the neural network. The first apparatus determines, according to the performance evaluation value of the first channel access mode, whether the channel access mode of the STA is the first channel access mode or the second channel access mode, so as to help the STA determine to get access to the channel in a proper channel access mode, thereby further helping to increase system throughput and reduce communication time delay.

Description

Method and device for determining channel access mode

This application claims the priority of a Chinese patent application filed with the State Intellectual Property Office of China on December 30, 2021, with the application number 202111660704.8 and the application name "Method and Device for Determining Channel Access Mode", the entire contents of which are hereby incorporated by reference In this application.

technical field

The present application relates to the field of communication technologies, and in particular to a method and device for determining a channel access mode.

Background technique

In wireless networks such as short-distance transmission network systems and wireless fidelity (Wi-Fi) systems, channels are shared, that is, multiple terminal devices in the wireless network use the same shared channel for communication. Then, if two or more terminal devices send messages at the same time, a communication conflict will occur, and the message transmission of the terminal device will fail, resulting in a low throughput of the channel and a large communication delay of the terminal device. .

At present, terminal devices can use carrier-sense multiple access with collision avoidance (CSMA/CA) mechanism or neural network to decide whether to access the channel to avoid shared channel conflicts. However, the CSMA/CA mechanism avoids conflicts through randomization, which has defects such as large time delay and poor fairness. The neural network that decides whether to access the channel is obtained through a large amount of environmental data training. If the real environmental information is quite different from the training data, the channel access results output by the neural network will deviate from the real results, and there will always be conflicts or no packets will be sent. The phenomenon.

Therefore, how a terminal device decides to access a channel by using an appropriate channel access method is still a problem that needs to be solved urgently.

Contents of the invention

Embodiments of the present application provide a method and device for determining a channel access mode, which is beneficial to improving system throughput and reducing communication delay.

In a first aspect, the embodiment of the present application provides a method for determining a channel access mode. In this method, the first device receives the performance evaluation value of the first channel access mode, and determines the channel access mode of the station STA from the first channel access mode and the second channel access mode according to the performance evaluation value. Among them, the first channel access method refers to using the neural network to decide the STA access channel, and the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel. The performance evaluation value includes the accuracy and accuracy of the neural network. At least one of the loss values.

It can be seen that the first device determines whether the channel access mode of the STA is the first channel access mode or the second channel access mode according to the performance evaluation value of the first channel access mode, which is beneficial for the STA to adopt an appropriate channel access mode to decide to connect. Incoming channel, which is beneficial to improve system throughput and reduce communication delay.

In an optional implementation manner, the first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value, including: When a preset value is reached, determine that the channel access method of the STA is the first channel access method; when the accuracy is less than or equal to the first preset value, the first device determines that the channel access method of the STA is the second channel access method Way.

When the accuracy received by the first device is greater than the first preset value, it indicates that the accuracy of the first channel access method exceeds expectations, so that the first device determines the first channel access method as the channel access method of the STA; the first When the accuracy received by the device is less than or equal to the first preset value, it indicates that the accuracy of the first channel access method does not exceed expectations, and the STA is not suitable for using the first channel access method to decide to access the channel, so the first device uses the first channel access method to decide to access the channel. The two-channel access mode determines the channel access mode of the STA. It can be seen that this method is beneficial for the STA to adopt an appropriate channel access method to decide to access the channel.

In another optional implementation manner, the first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value, including: When it is greater than the second preset value, determine that the channel access method of the STA is the first channel access method; the second preset value is greater than zero; or, when the first value is less than or equal to the second preset value, the first device, It is determined that the channel access mode of the STA is the second channel access mode. The second preset value is greater than zero.

Wherein, the first value is a value obtained by subtracting the accuracy of the first channel access mode used by the STA from the accuracy. If the second preset value is greater than zero, then the accuracy received by the first device is greater than the accuracy of the first channel access method used by the STA. When the first value is greater than the second preset value, it indicates that the accuracy received by the first device is greater than the accuracy of the first channel access method used by the STA and exceeds the expected value, so that the first device determines the channel access method of the STA It is the first channel access method. When the first preset value is less than or equal to the second preset value, it indicates that the receiving accuracy of the first device is greater than the accuracy of the first channel access method used by the STA, and the degree of accuracy does not exceed the expected value, that is, the STA is not suitable for using the first channel access method. A channel access mode decides to access the channel, so that the first device determines that the channel access mode of the STA is the second channel access mode.

In another optional implementation manner, the foregoing first value is a value obtained by subtracting the loss value received by the first device from the loss value of the first channel access mode used by the STA. The first value is greater than zero, indicating that the loss value received by the first device is smaller than the loss value of the first channel access mode used by the STA. When the first preset value is greater than the second preset value, it indicates that the loss value received by the first device is smaller than the loss value of the first channel access mode used by the STA and exceeds expectations, so that the first device determines the channel access mode of the STA is the first channel access method; when the first preset value is less than or equal to the second preset value, it indicates that the loss value received by the first device is less than the loss value of the first channel access method used by the STA and does not exceed expectations, That is, the STA is not suitable for adopting the first channel access mode to decide to access the channel, so the first device determines that the channel access mode of the STA is the second channel access mode.

It can be seen that the above two methods are beneficial for the STA to adopt an appropriate channel access method to decide the STA access channel.

In an optional implementation manner, if the first device determines that the channel access mode of the STA is the first channel access mode according to the accuracy, the first device may also send The second device sends first indication information, where the first indication information is used to indicate that the STA needs to update the channel access parameter. The third preset value is greater than the first preset value, and the channel access parameters may be the structure of the neural network, the weights and offsets of the neural network, and the like.

In another optional implementation manner, if the first device determines that the channel access mode of the STA is the first channel access mode according to the above-mentioned first value, the first device may also select the channel access mode of the STA when the first value is greater than the first channel access mode. When the preset value is four, the first indication information is sent to the second device, where the first indication information is used to indicate that the STA needs to update the channel access parameter. The fourth preset value is greater than the second preset value.

It can be seen that, when the received performance evaluation value is sufficiently larger than the performance evaluation value of the first channel access method used by the STA, the first device may determine that the STA needs to update the channel used by the first channel access method to decide to access the channel. Neural network, so that STA uses the updated neural network to decide STA access channel, which can further improve system throughput and reduce communication delay.

In an optional implementation manner, when the determined channel access mode is different from the current channel access mode of the STA, the first device may also send the determined channel access mode to the second device, so that the second device The channel access mode determined by the first device is acquired.

In an optional implementation manner, when the first device is a STA, the first device may also receive second indication information from the second device, and the second indication information is used to indicate that the second device agrees to access the channel of the STA The mode is switched to the determined channel access mode. Therefore, the first device switches the current channel access mode of the STA to the determined channel access mode.

In another optional implementation manner, when the first device is an access point AP, the first device may also update the channel access mode status table stored by the first device according to the determined channel access mode. The channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

It can be seen that when the first device agrees with the second device to update the current channel access mode of the STA to a certain channel access mode, the first device can also update the channel access mode status table to maintain the same channel access mode as the STA. way of data transmission.

In an optional implementation manner, when the first device is a STA, and the first device determines that the STA needs to update the channel access parameter, it may also receive the channel access parameter from the second device. Therefore, the first device updates the neural network according to the channel access parameter to obtain the updated neural network, and then the first device uses the updated neural network to decide the STA access channel.

In another optional implementation manner, when the first device is an AP and the first device determines that the STA needs to update the channel access parameter, the first device may also send the channel access parameter to other STAs associated with the first device. parameters, so that other STAs can also update the neural network according to the channel access parameters, and use the updated neural network to decide the STA access channel.

In a second aspect, the present application also provides a method for determining a channel access mode. The method for determining the channel access mode in this aspect corresponds to the method for determining the channel access mode in the first aspect, and the method for determining the channel access mode in this aspect is explained from the side of the second device. In this method, the second device trains the neural network to obtain the performance evaluation value of the first channel access mode. The second device sends the performance evaluation value of the first channel access mode. Wherein, the first channel access mode refers to using a neural network to decide a station STA to access a channel. The performance evaluation value includes at least one of accuracy and loss value of the neural network.

It can be seen that in the embodiment of the present application, the second device obtains the performance evaluation value of the first channel access mode by training the neural network that decides the STA access channel, and sends the performance evaluation value to the second device. Therefore, it is beneficial for the second device to determine the channel access method of the STA from the first access method and the second channel access method according to the performance evaluation value. The second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel. It is beneficial for the STA to adopt an appropriate channel access method to decide the STA access channel. In turn, it is beneficial to improve system throughput and reduce communication delay.

In an optional implementation manner, the second device may further receive a channel access mode from the first device, and the channel access mode is determined by the first device according to a performance evaluation value of the first channel access mode.

In an optional implementation manner, the second device is an access point AP. Then, the second device determines, according to the received channel access mode, that the STA needs to update the current channel access. Therefore, the second device may also update the stored channel access mode state table according to the channel access mode, and send the second indication information to the first device. The second indication information is used to instruct the second device to agree with the first device to switch the channel access mode of the STA to a certain channel access mode. The channel access mode status table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

In another optional implementation manner, the second device is a STA, and after receiving the channel access mode from the first device, the second device switches the current channel access mode of the second device to the channel access mode , so that the second device adopts the switched channel access mode to decide the channel to be accessed by the STA.

In another optional implementation manner, when the second device is an access point AP, the second device may also receive first indication information from the first device, and the first indication information is used to indicate that the STA needs to update the channel access parameter . Thus, the second device sends the channel access parameter to the first device, so that the first device updates the neural network according to the channel access parameter. Wherein, the channel access parameters include neural network structure parameters and neural network parameters of the neural network.

In yet another optional implementation manner, when the second device is a STA, the second device may further receive first indication information from the first device, where the first indication information is used to indicate that the STA needs to update the channel access parameter. Therefore, the second device updates the neural network according to the channel access parameters corresponding to the neural network, and obtains the updated neural network. Furthermore, the second device adopts the updated neural network to decide to access the channel.

In a third aspect, the embodiment of the present application further provides a method for determining a channel access mode. In the method, the first device trains the neural network to obtain the performance evaluation value of the first channel access mode. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. Among them, the first channel access method refers to the use of neural network decision-making station STA to access the channel, the performance evaluation value includes at least one of the accuracy and loss value of the neural network, and the second channel access method refers to the use of carrier sense The collision avoidance mechanism decides the channel to be accessed by the STA.

It can be seen that in the embodiment of the present application, the first device obtains the performance evaluation value of the first channel access method by training the neural network that decides the STA access channel, and uses the performance evaluation value from the first channel access method and the second channel access method. The channel access mode determines the channel access mode of the STA. Therefore, it is beneficial for the STA to adopt an appropriate channel access method to decide to access the channel, thereby improving the system throughput and reducing the communication delay.

When the accuracy of the neural network trained by the first device is greater than the first preset value, it indicates that the accuracy of the neural network exceeds expectations, so that the first device determines the first channel access method as the channel access method of the STA; the first device When the accuracy of training the neural network is less than or equal to the first preset value, it indicates that the accuracy of the neural network has not exceeded expectations, and the STA is not suitable for using the first channel access method to decide to access the channel, so the first device uses the second channel The access mode determines the channel access mode of the STA. It can be seen that this method is beneficial for the STA to adopt an appropriate channel access method to decide to access the channel.

In another optional implementation manner, the first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value, including: When it is greater than the second preset value, determine that the channel access method of the STA is the first channel access method; the second preset value is greater than zero; or, when the first value is less than or equal to the third preset value, the first device, It is determined that the channel access mode of the STA is the second channel access mode. The first value is the value of accuracy minus the accuracy of the first channel access method used by the STA; or, the first value is the value of the loss value of the first channel access method used by the STA minus the loss value.

Wherein, the first value is a value obtained by subtracting the accuracy of the first channel access mode used by the STA from the accuracy. If the second preset value is greater than zero, then the accuracy of the neural network trained by the first device is greater than the accuracy of the first channel access method used by the STA. When the first value is greater than the second preset value, it indicates that the accuracy of the neural network trained by the first device is greater than the accuracy of the first channel access method used by the STA and exceeds the expected value, so that the first device determines the channel of the STA The access mode is the first channel access mode. When the first preset value is less than or equal to the second preset value, it indicates that the degree of accuracy of the neural network trained by the first device is greater than the accuracy of the first channel access method used by the STA does not exceed the expected value, that is, the STA does not It is suitable to use the first channel access mode to decide to access the channel, so that the first device determines that the channel access mode of the STA is the second channel access mode.

In another optional implementation manner, the foregoing first value is a value obtained by subtracting the loss value received by the first device from the loss value of the first channel access mode used by the STA. The first value is greater than zero, indicating that the loss value received by the first device is smaller than the loss value of the first channel access mode used by the STA. When the first preset value is greater than the second preset value, it indicates that the loss value of the neural network trained by the first device is smaller than the loss value of the first channel access method used by the STA and exceeds expectations, so that the first device determines the channel of the STA The access method is the first channel access method; when the first preset value is less than or equal to the second preset value, it indicates that the loss value of the neural network trained by the first device is smaller than the first channel access method used by the STA. The loss value does not exceed the expectation, that is, the STA is not suitable for adopting the first channel access mode to decide to access the channel, so the first device determines that the channel access mode of the STA is the second channel access mode.

In an optional implementation manner, if the first device determines that the channel access method of the STA is the first channel access method according to the accuracy, the first device may also send a request to the second channel access method when the accuracy is greater than the third preset value. The second device sends first indication information, where the first indication information is used to indicate that the STA needs to update the channel access parameter, and the second preset value is greater than the first preset value. The channel access parameters may be the structure of the neural network, the weights and biases of the neural network, and the like.

In another optional implementation manner, if the first device determines that the channel access mode of the STA is the first channel access mode according to the above-mentioned first value, the first device may also set the first value greater than the fourth preset value , sending first indication information to the second device, where the first indication information is used to indicate that the STA needs to update the channel access parameter, and the fourth preset value is greater than the second preset value.

It can be seen that, when the received performance evaluation value is sufficiently larger than the performance evaluation value of the first channel access method used by the STA, the first device may determine that the STA needs to update the channel used by the first channel access method to decide to access the channel. Neural network, so that STAs use the updated neural network to decide STA access channels, which can further improve system throughput and reduce communication delay.

In an optional implementation manner, the first device may also send the determined channel access method to the second device when the determined channel access method is different from the current channel access method of the STA, so that the second device The channel access mode determined by the first device is acquired.

In an optional implementation manner, when the first device is an access point AP, and the determined channel access mode is different from the current channel access mode of the STA, the first device may also update the channel access mode status table , to perform data transmission in the same channel access mode as the STA. The channel access mode status table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

In another optional implementation manner, when the first device is a STA, and the determined channel access method is different from the current channel access method of the STA, the first device may also access the channel of the first device The mode is switched to the determined channel access mode, so that the first device adopts the determined channel access mode to decide to access the channel by the STA.

In an optional implementation manner, when the first device is an access point AP, and the first device determines that the STA needs to update the channel access parameter, the first device may also send the channel access parameter to the second device, so that The second means updates the neural network according to the channel access parameters. The channel access parameters include neural network structure parameters and neural network parameters of the neural network.

In an optional implementation manner, when the first device is a STA and the first device determines that the STA needs to update the channel access parameters, the first device can also update the neural network according to the channel access parameters corresponding to the neural network to obtain the updated The updated neural network, so that the first device uses the updated neural network to decide the STA access channel.

In a fourth aspect, the present application also provides a method for determining a channel access mode. The method for determining the channel access mode in this aspect corresponds to the method for determining the channel access mode in the third aspect, and the method for determining the channel access mode in this aspect is explained from the side of the second device. In this method, the second device receives the channel access method from the first device; the second device switches the current channel access method to the received channel access method, and the channel access method is the first device according to the first channel access method. The performance evaluation value of the access mode is determined from the first channel access mode and the second channel access mode. The first channel access method refers to using the neural network to decide the access channel of the station STA, and the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel; the performance evaluation value includes the accuracy and loss of the neural network at least one of the values.

It can be seen that the channel access mode received by the second device is determined by the first device from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. Therefore, the second device switches the current channel access mode to the received channel access mode, so that the STA can use an appropriate channel access mode to decide to access the channel.

In an optional implementation manner, the second device may also receive channel access parameters, and update the neural network according to the channel access parameters to obtain an updated neural network. Therefore, the second device adopts the updated neural network to decide the STA access channel.

In a fifth aspect, the present application also provides a method for determining a channel access mode. The method for determining the channel access mode in this aspect corresponds to the method for determining the channel access mode in the third aspect, and the method for determining the channel access mode in this aspect is explained from the side of the second device. In the method, the second device receives the channel access mode from the first device, and updates the channel access mode state table according to the channel access mode. Wherein, the channel access mode is determined by the first device from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. The first channel access method refers to using the neural network to decide the access channel of the station STA, and the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel. The performance evaluation value includes at least one of accuracy and loss value of the neural network. The channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

It can be seen that the channel access mode received by the second device is determined by the first device according to the performance evaluation value of the first channel access mode, so the second device updates the channel access mode status table according to the received channel access mode to The second device adopts the same channel access method as that of the first device to decide to access the channel.

In an optional implementation manner, the second device may further receive first indication information from the first device, where the first indication information is used to indicate that the STA needs to update the channel access parameter. Therefore, the second device can send channel access parameters to other STAs associated with the second device, so that other STAs associated with it can also update the neural network according to the channel access parameters, and then use the updated neural network to decide STA access channel. The channel access parameters include neural network structure parameters and neural network parameters of the neural network.

In a sixth aspect, the present application further provides a communication device. The communication device has part or all of the functions of the first device described in the above first aspect, or part or all of the functions of the second device described in the above second aspect, or has the function of realizing the above third aspect. Part or all of the functions of the first device either implement part or all of the functions of the second device described in the fourth aspect above, or realize part or all of the functions of the second device described in the fifth aspect above. For example, the function of the device may have the functions of some or all embodiments of the first device described in the first aspect of the present application, and may also have the function of independently implementing any embodiment of the present application. The functions described above may be implemented by hardware, or may be implemented by executing corresponding software on the hardware. The hardware or software includes one or more units or modules corresponding to the above functions.

In a possible design, the structure of the device may include a processing unit and a communication unit, and the processing unit is configured to support the communication device to perform corresponding functions in the foregoing method. The communication unit is used to support communication between the communication device and other communication devices. The communication device may further include a storage unit, which is used to be coupled with the processing unit and the communication unit, and stores necessary program instructions and data of the communication device.

In one embodiment, the communication device includes: a processing unit and a communication unit, and the processing unit is used to control the communication unit to perform data/signaling transceiving;

A communication unit, configured to receive a performance evaluation value of a first channel access method; the first channel access method refers to using a neural network decision-making station STA to access a channel, and the performance evaluation value includes the accuracy of the neural network and at least one of loss value;

A processing unit, configured to determine the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value; the second channel access method refers to using The carrier sense collision avoidance mechanism decides the channel to be accessed by the STA.

In addition, in this aspect, for other optional implementation manners of the communication device, reference may be made to the relevant content of the above-mentioned first aspect, which will not be described in detail here.

In another implementation manner, the communication device includes: a processing unit and a communication unit, and the processing unit is used to control the communication unit to perform data/signaling transceiving;

The processing unit is used to train the neural network and obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network to decide the station STA to access the channel; the performance evaluation value includes the At least one of the accuracy and loss values of the neural network;

The communication unit is configured to send the performance evaluation value of the first channel access mode.

In addition, in this aspect, for other optional implementation manners of the communication device, reference may be made to the relevant content of the above-mentioned second aspect, which will not be described in detail here.

In yet another implementation manner, the communication device includes: a processing unit and a communication unit, and the processing unit is used to control the communication unit to perform data/signaling transceiving;

The processing unit is used to train the neural network and obtain the performance evaluation value of the first channel access mode; the first channel access mode refers to using the neural network decision-making station STA to access the channel, and the performance evaluation value includes at least one of an accuracy and a loss value of the neural network;

The processing unit is further configured to determine the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode; The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide the channel access of the STA.

In addition, in this aspect, for other optional implementation manners of the communication device, reference may be made to the relevant content of the above-mentioned third aspect, which will not be described in detail here.

The communication unit is configured to receive a channel access mode from the first device;

The processing unit is configured to switch the current channel access mode to the channel access mode;

The channel access method is determined by the first device from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method;

The first channel access method refers to using the neural network to decide the access channel of the station STA; the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel; the performance evaluation value At least one of the accuracy and loss value of the neural network is included.

In addition, in this aspect, for other optional implementation manners of the communication device, reference may be made to the relevant content of the fourth aspect above, which will not be described in detail here.

The processing unit is configured to update the channel access mode status table according to the channel access mode;

The first channel access method refers to using the neural network to decide the STA access channel; the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel;

The performance evaluation value includes at least one of the accuracy and loss value of the neural network; the channel access mode state table includes the identity of each STA in the plurality of STAs associated with the first device, each STA Whether to support the first channel access mode and the current channel access mode of each STA.

In addition, in this aspect, for other optional implementation manners of the communication device, reference may be made to the relevant content of the fifth aspect above, which will not be described in detail here.

As an example, the communication unit may be a transceiver or a communication interface, the storage unit may be a memory, and the processing unit may be a processor.

In one embodiment, the communication device includes: a processor and a transceiver, and the processor is used to control the transceiver to perform data/signaling transceiving;

The transceiver is used to receive the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network decision-making station STA to access the channel, and the performance evaluation value includes the accuracy of the neural network and at least one of loss value;

a processor, configured to determine the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value; the second channel access method refers to using The carrier sense collision avoidance mechanism decides the channel to be accessed by the STA.

In another implementation manner, the communication device includes: a processor and a transceiver, and the processor is used to control the transceiver to perform data/signaling transceiving;

The processor is used to train the neural network and obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network to decide the station STA to access the channel; the performance evaluation value includes the At least one of the accuracy and loss values of the neural network;

A transceiver, configured to send the performance evaluation value of the first channel access manner.

In yet another implementation manner, the communication device includes: a processor and a transceiver, and the processor is used to control the transceiver to perform data/signaling transceiving;

A processor, configured to train a neural network, and obtain a performance evaluation value of a first channel access method; the first channel access method refers to using the neural network decision-making station STA to access a channel, and the performance evaluation value includes the At least one of the accuracy and loss value of the neural network;

The processor is further configured to determine the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode; the second channel access mode The two-channel access mode refers to using a carrier sense collision avoidance mechanism to decide the STA access channel.

The transceiver is used to receive the channel access mode from the first device;

A processor, configured to switch the current channel access mode to the channel access mode; the channel access mode is the performance evaluation value of the first device according to the first channel access mode, from the first channel access mode The access method and the second channel access method are determined; the first channel access method refers to using the neural network decision-making station STA to access the channel; the second channel access method refers to the use of carrier sense conflict avoidance A mechanism decides the access channel of the STA; the performance evaluation value includes at least one of the accuracy and the loss value of the neural network.

In another embodiment, the communication device includes: a processor and a transceiver, the processor is used to control the transceiver to perform data/signaling transmission and reception; the transceiver is used to receive the channel access method from the first device; processing A device, configured to update the channel access mode status table according to the channel access mode;

In another implementation manner, the communication device is a chip or a chip system. The processing unit may also be embodied as a processing circuit or a logic circuit; the transceiver unit may be an input/output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip or chip system.

During implementation, the processor may be used to perform, for example but not limited to, baseband related processing, and the transceiver may be used to perform, for example but not limited to, radio frequency transceiving. The above-mentioned devices may be respectively arranged on independent chips, or at least partly or all of them may be arranged on the same chip. For example, processors can be further divided into analog baseband processors and digital baseband processors. Wherein, the analog baseband processor can be integrated with the transceiver on the same chip, and the digital baseband processor can be set on an independent chip. With the continuous development of integrated circuit technology, more and more devices can be integrated on the same chip. For example, a digital baseband processor can be integrated with various application processors (such as but not limited to graphics processors, multimedia processors, etc.) on the same chip. Such a chip can be called a system chip (System on a Chip, SoC). Whether each device is independently arranged on different chips or integrated and arranged on one or more chips often depends on the needs of product design. The embodiment of the present application does not limit the implementation form of the foregoing devices.

In a seventh aspect, the present application further provides a processor configured to execute the above-mentioned various methods. In the process of executing these methods, the process of sending the above information and receiving the above information in the above method can be understood as the process of outputting the above information by the processor and the process of receiving the input of the above information by the processor. When outputting the above information, the processor outputs the above information to the transceiver for transmission by the transceiver. After the above information is output by the processor, other processing may be required before reaching the transceiver. Similarly, when the processor receives the above-mentioned input information, the transceiver receives the above-mentioned information and inputs it to the processor. Furthermore, after the transceiver receives the above information, the above information may need to be processed before being input to the processor.

Based on the above principles, for example, receiving the performance evaluation value of the first channel access method mentioned in the foregoing method may be understood as the processor inputting the performance evaluation value of the first channel access method.

For the sending and receiving operations involved in the processor, if there is no special description, or if it does not conflict with its actual function or internal logic in the relevant description, it can be understood more generally as the processor output and reception, Input and other operations, rather than the transmission and reception operations directly performed by the radio frequency circuit and antenna.

During implementation, the above-mentioned processor may be a processor dedicated to performing these methods, or may be a processor that executes computer instructions in a memory to perform these methods, such as a general-purpose processor. The above-mentioned memory can be a non-transitory (non-transitory) memory, such as a read-only memory (Read Only Memory, ROM), which can be integrated with the processor on the same chip, or can be respectively arranged on different chips. The embodiment does not limit the type of the memory and the arrangement of the memory and the processor.

In an eighth aspect, the present application further provides a communication system, where the system includes at least one first device and at least one second device according to the above aspect. In another possible design, the system may further include other devices that interact with the first device and the second device in the solution provided by the present application.

In a ninth aspect, the present application provides a computer-readable storage medium for storing instructions, and when the instructions are executed by a computer, the method described in any one of the first to fifth aspects above is implemented.

In a tenth aspect, the present application further provides a computer program product including instructions, which, when run on a computer, implement the method described in any one of the first to fifth aspects above.

In the eleventh aspect, the present application provides a chip system, the chip

The chip system includes a processor and an interface, where the interface is used to acquire programs or instructions, and the processor is used to call the programs or instructions to realize or support the first device to realize the functions involved in the first aspect, or to call the The above programs or instructions are used to realize or support the second device to realize the functions involved in the second aspect, or to call the programs or instructions to realize or support the first device to realize the functions involved in the third aspect, or to call The program or instruction is used to implement or support the second device to implement the functions involved in the fourth aspect, or is used to call the program or instruction to implement or support the second device to implement the functions involved in the fourth aspect. For example, at least one of the data and information involved in the above methods is determined or processed. In a possible design, the chip system further includes a memory, and the memory is configured to store necessary program instructions and data of the terminal. The system-on-a-chip may consist of chips, or may include chips and other discrete devices.

Description of drawings

FIG. 1 is a schematic structural diagram of a communication system provided by an embodiment of the present application;

FIG. 2 is a schematic structural diagram of an AP and STA provided in an embodiment of the present application;

FIG. 3 is a state transition diagram when a terminal device adopts a CSMA/CA mechanism to decide whether to access a channel provided by an embodiment of the present application;

FIG. 4 is a state transition diagram when a terminal device uses a neural network to decide whether to access a channel provided by an embodiment of the present application;

FIG. 5 is an interactive schematic diagram of a method for determining a channel access mode provided in an embodiment of the present application;

FIG. 6 is an interactive schematic diagram of another method for determining a channel access mode provided in an embodiment of the present application;

FIG. 7 is a schematic diagram of a frame format of an information unit provided by an embodiment of the present application;

FIG. 8 is an interactive schematic diagram of another method for determining a channel access mode provided in an embodiment of the present application;

FIG. 9 is a schematic flowchart of a method for determining a channel access mode provided in an embodiment of the present application;

FIG. 10 is an interactive schematic diagram of another method for determining a channel access method provided in an embodiment of the present application;

FIG. 11 is an interactive schematic diagram of another method for determining a channel access method provided in an embodiment of the present application;

Fig. 12 is a schematic structural diagram of a communication device provided by an embodiment of the present application;

FIG. 13 is a schematic structural diagram of another communication device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

First, in order to better understand the method for determining the channel access mode disclosed in the embodiment of the present application, the communication system to which the embodiment of the present application is applicable is described.

1. Communication system.

Please refer to FIG. 1 . FIG. 1 is a schematic structural diagram of a communication system provided by an embodiment of the present application. The communication system may include but not limited to one access point (access point, AP) and three stations (station, STA). The number and form of devices shown in FIG. 1 are for example, and do not constitute a limitation to the embodiment of the present application. In practical applications, two or more APs and three or more STAs may be included. The communication system shown in Figure 1 uses AP 101, STA 1021, STA 1022, and STA 1023. The AP 101 can provide wireless services for STA 1021, STA 1022, and STA 1023, and the communication link between each STA and the AP shares a channel As an example to illustrate. Among them, AP101 in Figure 1 is an example of a base station, and STA 1021, STA 1022, and STA 1023 are examples of mobile phones.

In the embodiment of the present application, a schematic structural diagram of an AP and a STA is shown in FIG. 2 . Both the AP and the STA include a processor, a Media Access Control (MAC) module, a transceiver, and an antenna. The MAC module includes a first module and a second module. The first module refers to a module that uses the carrier-sense multiple access with collision avoidance (CSMA/CA) mechanism to decide whether to access the channel. The second module is Refers to the module that uses the neural network to decide whether to access the channel. At a certain moment, the STA or AP can only select one module from the first module and the second module to decide whether to access the channel. The transceiver is used to realize the sending and receiving function through the antenna.

In the embodiment of the present application, the above-mentioned communication system may be a wireless local area network (Wireless local area network, WLAN) or a cellular network, or other wireless communication systems that support multiple links for parallel transmission. The embodiment of the present application mainly takes the deployment of IEEE 802.11 network as an example for illustration, and various aspects involved in the present application can be extended to other networks using various standards or protocols, for example, BLUETOOTH (Bluetooth), high-performance wireless LAN (high performance radio LAN, HIPERLAN) (a wireless standard similar to the IEEE 802.11 standard, used primarily in Europe), and wide area networks (WANs), personal area networks (PANs), or other networks now known or later developed. Thus, the various aspects presented herein can be applied to any suitable wireless network, regardless of the coverage area and wireless access protocol used.

In this embodiment of the application, the STA has a wireless transceiver function, can support 802.11 series protocols, and communicate with an AP or other STAs. For example, the STA can be any user communication device that allows the user to communicate with the AP and then communicate with the WLAN, such as including but not limited to, tablet computers, desktops, laptops, notebook computers, ultra-mobile personal computers (Ultra-mobile Personal Computer, UMPC), handheld computers, netbooks, personal digital assistants (Personal Digital Assistant, PDA), mobile phones and other user equipment that can be connected to the Internet, or IoT nodes in the Internet of Things, or vehicle communication devices in the Internet of Vehicles. Optionally, the STA may also be chips and processing systems in the above terminal devices.

In the embodiment of the present application, the AP is a device that provides services for STAs, and can support 802.11 series protocols. For example, an AP can be a communication entity such as a communication server, a router, a switch, or a network bridge, or an AP can include various forms of macro base stations, micro base stations, relay stations, etc. Of course, an AP can also be a chip in these various forms of equipment and a processing system, thereby realizing the methods and functions of the embodiments of the present application.

In order to facilitate understanding of the embodiments disclosed in the present application, the following two points are explained.

(1) The scenarios in the embodiments disclosed in this application are described by taking the scenario of a Wi-Fi network in a wireless communication network as an example. It should be noted that the solutions in the embodiments disclosed in this application can also be applied to other wireless communication networks , the corresponding names may also be replaced by names of corresponding functions in other wireless communication networks.

(2) Embodiments disclosed in the application will present various aspects, embodiments or features of the application around a system including a plurality of devices, components, modules, and the like. It is to be understood and appreciated that the various systems may include additional devices, components, modules, etc. and/or may not include all of the devices, components, modules etc. discussed in connection with the figures. Additionally, combinations of these schemes can also be used.

2. Explanation of terms involved in the embodiments of this application.

In wireless networks such as short-distance transmission network systems and wireless fidelity (Wi-Fi) systems, channels are shared. In a distributed scenario, there is no central node to uniformly schedule and coordinate all nodes in the network, and the nodes directly decide whether to access the shared channel. At present, the terminal device can use the CSMA/CA mechanism or the neural network to decide whether to access the channel, so as to avoid shared channel conflicts. The following describes the detailed process of terminal equipment using the CSMA/CA mechanism and neural network decision-making to access the channel:

1. The terminal device uses the CSMA/CA mechanism to decide whether to access the channel.

FIG. 3 is a state transition diagram when a terminal device adopts the CSMA/CA mechanism to decide whether to access a channel. As shown in FIG. 3 , the terminal device is in an idle state (idle) when there is no new message to be sent. When the terminal device has a new message to send, the new message first enters the Distributed Inter-frame Spacing (DIFS) state. In the DIFS state, the terminal device listens to the channel for a preset time, and once it detects that the channel is idle for a continuous time, a new message enters a contention state. The terminal device continues to listen to the channel in the "contention" state, and each time the listening channel is idle, the back-off (Back off, BOF) value will be reduced by "1", until the BOF is reduced to "0", the terminal device will use the new The message is transferred to the sending state, that is, the "TX" state, and the message is sent to the receiving end. If the terminal device is in the listening process of the "contention" state, once it detects that the channel is busy, it will enter the waiting state, that is, the "hold" state. In the "hold" state, the terminal device performs channel monitoring. Once the channel monitoring is idle, it returns to the "DIFS" state, otherwise it stays in the "hold" state.

After the terminal device sends the message, if the receiving end receives it correctly, the receiving end replies an acknowledgment (Acknowledge, ACK) to the terminal device. After the terminal device receives the ACK, the value of the contention window (Contention Window, CW) returns to the minimum value, that is, CW _min , and the CW _min is specified by the protocol standard. If the receiving end does not receive the message correctly within the preset time, the terminal device will receive a negative acknowledgment (Negative Acknowledge, NAK) from the receiving end, and the CW will be doubled at this time, that is, CW=min(2*CW, CW _min ) . Therefore, the time for the terminal device to be in the "contention" state will be longer, thereby avoiding conflicts.

The terminal device adopts the CSMA/CA mechanism to decide whether to access the channel, which can also be called the distributed coordination function (Distributed Coordination Function, DCF).

2. The terminal device uses the neural network to decide whether to access the channel.

FIG. 4 is a state transition diagram of a terminal device using a neural network to decide whether to access a channel. As shown in Figure 4, different from the above Figure 3, if the terminal device detects that the channel is idle in the "DIFS" state, the terminal device uses the current environment information as the input of the neural network, and obtains information about whether to connect to the neural network output. The result of entering the channel. The neural network is obtained by the terminal device by training it based on a large amount of historical environmental information. The environmental information can be all states that can be collected by the Media Access Control (MAC) layer and the Physical (PHY) layer, such as channel listening results, packet loss, etc.

When the output value of the neural network a=1, the terminal device determines to access the channel; when a=0, the terminal device determines to return to the "DIFS" state and continue to listen to the channel. If the terminal device listens to the channel being idle in the "DIFS" state, the terminal device uses the neural network again to determine whether to access the channel, otherwise, the terminal device keeps listening to the channel. If the receiving end correctly receives the message from the terminal device, it will send an ACK to the terminal device, and the terminal device will receive the ACK and return to the idle state; if the receiving end does not receive the message from the terminal device within the preset time, then Send a NAK to the terminal device, the terminal device receives the NAK, and returns to the "DIFS" state.

However, in the above-mentioned CSMA/CA mechanism, the terminal equipment avoids collisions through randomization, which has defects such as large time delay and poor fairness. The neural network that decides whether to access the channel is obtained through a large amount of environmental data training. If the real environmental information is quite different from the training data, the channel access results output by the neural network will deviate from the real results, and there will always be conflicts or no packets will be sent. The phenomenon. In addition, when a terminal device uses a neural network to decide whether to access a channel, the terminal device needs to have relatively large computing power, and the terminal device consumes a lot of power.

At present, if the terminal device uses the neural network to decide whether to access the channel, when the power consumption of the terminal device is low, the terminal device can switch the channel access mode to use the CSMA/CA mechanism to decide whether to access the channel. If the interference situation of the terminal device changes, the terminal device can also switch the current channel access mode. If the terminal device uses the current channel access mode to decide whether to access the channel, but always determines not to send packets, or always conflicts, the terminal device can also switch the current channel access mode. That is to say, when a terminal device decides to access a channel, it needs to select an appropriate channel access method to improve system throughput and reduce communication delay.

In this embodiment of the present application, when the first device is an access point (Access Point, AP), the second device is a station (station, STA); when the first device is a STA, the second device is an AP.

3. The method for determining the channel access mode.

An embodiment of the present application provides a method 100 for determining a channel access mode. FIG. 5 is an interactive schematic diagram of the method 100 for determining a channel access mode. The method 100 for determining a channel access mode is described from the perspective of interaction between a first device and a second device. The channel access mode determination method 100 includes but not limited to the following steps:

S101. The second device trains the neural network to obtain the performance evaluation value of the first channel access method. The first channel access method refers to using the neural network to decide the site STA to access the channel, and the performance evaluation value includes the accuracy and loss of the neural network. at least one of the values.

It can be understood that the neural network is a neural network used when deciding whether an STA accesses a channel, and deciding whether an STA accesses a channel refers to deciding whether an STA accesses a channel. The first access method refers to using the neural network to decide the access channel of the STA, so the neural network is also the neural network used when the first access method is used to decide the access channel. The neural network is a neural network trained by the STA or the access point AP according to a large amount of historical environment information.

In an optional implementation manner, the condition for triggering the second device to train the neural network may be that a state in the network changes. For example, the number of nodes served by the network changes, services served in the network change significantly, and network performance changes (such as an increase in packet loss rate), etc. If the condition for training the neural network is triggered, the second device trains the neural network.

The algorithm used by the second device to train the neural network may be gradient descent algorithm, Newton algorithm, conjugate gradient method, quasi-Newton method, Levenberg-Marquardt (Levenberg-Marquardt) algorithm, and so on. The embodiment of the present application does not limit the algorithm for training the neural network.

When the second device trains the neural network, the current environment information is used as the input of the neural network, and the neural network outputs performance evaluation values. When the second device uses different methods to train the neural network, the performance evaluation values output by the neural network are different. For example, the second device uses a reinforcement learning algorithm to train the neural network, and the performance evaluation value output by the neural network is a loss value. For another example, when the second device uses gradient descent to train the neural network, the performance evaluation value output by the neural network is accuracy and loss value. Therefore, the performance evaluation value includes at least one of the accuracy and loss value of the neural network.

Among them, accuracy is a value in the range of 0 to 1, and the accuracy is used to reflect the accuracy of neural network training. The closer the value of accuracy is to 1, the higher the accuracy of the neural network parameters of the trained neural network is. The loss value reflects the error between the output of the neural network and the target value given the input of the neural network. The smaller the loss value, the better the training result of the neural network parameters. The embodiment of this application does not specify the range of the loss value.

In addition, when the second device trains the neural network, the neural network also outputs neural network parameters of the neural network. The neural network parameters include the structure, weight, and bias of the neural network. The neural network parameters are used to decide the STA access channel.

It can be seen that the second device can obtain the performance evaluation value of the first channel access mode by training the neural network that decides the STA access channel.

S102. The second device sends the performance evaluation value of the first channel access mode.

Understandably, the second device sends the performance evaluation value of the first channel access manner to the first device, so that the first device determines the channel access manner of the STA according to the performance evaluation value.

S103. The first device receives the performance evaluation value of the first channel access mode.

Understandably, the first device receives the performance evaluation value of the first channel access manner from the second device.

S104. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value. The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide STAs to access a channel.

When the performance evaluation value is accuracy, the first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the accuracy, or determines the channel access method of the STA according to the accuracy and the first channel access method used by the STA. The accuracy of the channel access mode determines the channel access mode of the STA from the first channel access mode and the second channel access mode. When the performance evaluation value is a loss value, the first device determines the channel of the STA from the first channel access mode and the second channel access mode according to the loss value and the loss value of the first channel access mode used by the STA access method. When the performance evaluation value is the accuracy and the loss value, the first device selects the accuracy or the loss value to determine the channel access mode of the STA.

Wherein, the accuracy of the first channel access method used by the STA refers to: the accuracy of the neural network used by the STA when using the first channel access method to decide to access a channel last time. The loss value of the first channel access method used by the STA refers to the loss value of the neural network used by the STA when it uses the first channel access method to decide to access a channel last time.

The specific implementation manner of determining the channel access mode of the STA from the first channel access mode and the second channel access mode by the first device according to the accuracy or the loss value can be referred to as follows:

Embodiment 1. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to accuracy.

The first device determines the channel access mode of the STA according to the accuracy and the magnitude of the first preset value. That is to say, the first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value, including: when the accuracy is greater than the first preset value, the first device , determining that the channel access method of the STA is the first channel access method; when the accuracy is less than or equal to the first preset value, the first device determines that the channel access method of the STA is the second channel access method. The first preset value is preset by the first device, and the first preset value is greater than 0 and less than 1.

It can be understood that when the accuracy is greater than the first preset value, it indicates that the accuracy of the trained neural network has reached the expected value, so that the first device determines that the channel access mode of the STA is the first channel access mode, that is, determines that the STA uses the neural network The network decides to access the channel; when the accuracy is less than or equal to the first preset value, it indicates that the accuracy of the trained neural network has not reached the expected value, so that the first device determines that the channel access mode of the STA is the second channel access mode, namely It is determined that the STA uses the carrier sense collision avoidance mechanism to decide to access the channel.

It can be seen that when the performance evaluation value obtained by the first device is accuracy, when the accuracy of the trained neural network reaches the expected value, it can be determined that the channel access mode of the STA is the first channel access mode. When the accuracy does not reach the expected value, it is determined that the channel access mode of the STA is the second channel access mode, so that the STA adopts an appropriate channel access mode to decide to access the channel.

Embodiment 2. The first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the accuracy and the accuracy of the first channel access method used by the STA.

The first device determines the channel access mode of the STA according to the first value, where the first value is a value obtained by subtracting the accuracy of the first channel access mode used by the STA from the obtained accuracy. That is to say, the first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value, including: the first device determines the STA channel access method when the first value is greater than the second preset value , determine that the channel access method of the STA is the first channel access method; when the first value is less than or equal to the second preset value, the first device determines that the channel access method of the STA is the second channel access method.

The second preset value is greater than zero, indicating that the accuracy obtained by the first device is greater than the accuracy of the first channel access method used by the STA, that is, the accuracy of the trained neural network is greater than the accuracy of the neural network used by the STA. The first value is greater than the second preset value, indicating that the accuracy of the trained neural network is greater than the accuracy of the neural network used by the STA and exceeds the expected value, so that the first device determines that the channel access method of the STA is the first channel access method ; The first value is less than or equal to the second preset value, indicating that the accuracy of the trained neural network is greater than the accuracy of the neural network used by the STA and does not exceed the expected value, that is, the STA is not suitable for using the first channel access method to make access decisions channel, so that the first device determines that the channel access mode of the STA is the second channel access mode.

It can be seen that the first device determines the channel access method of the STA from the first channel access method or the second channel access method according to the degree to which the obtained accuracy is greater than the accuracy of the first channel access method used by the STA. . Therefore, the STA can adopt an appropriate channel access method to decide to access the channel.

Embodiment 3. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the loss value and the loss value of the first channel access mode used by the STA.

The first device determines the channel access mode of the STA according to the first value, where the first value is a value obtained by subtracting the obtained loss value from the loss value of the first channel access mode used by the STA. The first device determines the channel access mode of the STA according to the first value, which is the same as that in Embodiment 2 above, that is, the first device determines that the channel access mode of the STA is the first channel access mode when the first value is greater than the second preset value. Mode: the first device determines that the channel access mode of the STA is the second channel access mode when the first value is less than or equal to the second preset value.

The second preset value is greater than zero, indicating that the loss value of the first channel access method used by the STA is greater than the loss value obtained by the first device, then the error of the trained neural network is smaller than that of the first channel access method used by the STA. The error of the neural network used. The first value is greater than the second preset value, indicating that the error of the trained neural network is smaller than the error of the neural network used by the STA in the first channel access method and reaches the expected value, so that the first device determines the channel access of the STA. The input method is the first channel access method; the first value is less than or equal to the second preset value, indicating that the error of the trained neural network is less than the error of the neural network used by the STA in the first channel access method. When the expected value is reached, the first device determines that the channel access mode of the STA is the second channel access mode.

It can be seen that, according to the extent to which the error of the trained neural network is smaller than the error of the neural network used by the STA in the first channel access mode, the first device determines the STA from the first channel access mode and the second channel access mode. channel access method. Therefore, the STA can adopt an appropriate channel access method to decide to access the channel.

In the embodiment of the present application, the first device may also select from the first channel access method and the second channel access method according to other functional relationships between the obtained loss value and the accuracy of the first access method used by the STA. Determine the channel access mode of the STA. The embodiment of the present application does not limit the embodiment manner in which the first device determines the channel access mode of the STA according to the obtained loss value and the accuracy of the first access mode used by the STA.

In the embodiment of the present application, the second device trains the neural network that decides the STA access channel, obtains the performance evaluation value of the first channel access mode, and sends the performance evaluation value to the first device. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value. The first means is to determine the channel access mode of the STA according to the performance evaluation value of the first channel access mode. That is to say, when the performance of the trained neural network is good, the first device determines that the STA uses the neural network to decide to access the channel; when the performance of the trained neural network is poor, the first device determines that the STA does not use the neural network to decide to access the channel, and Adopt the CSMA/CA mechanism to decide the access channel. Therefore, the STA adopts the appropriate channel access method to decide to access the channel, which can reduce the channel conflict or packet loss rate when the STA sends data, thereby improving the system throughput and reducing the communication delay.

When the computing power of the STA in the network is not large enough, the STA cannot train the neural network that decides to access the channel, and the AP trains the neural network that determines the channel that the STA accesses. Therefore, the embodiment of the present application also proposes a method 200 for determining a channel access mode by taking the first device as an AP and the second device as an STA as an example. FIG. 6 is an interactive schematic diagram of the method 200 for determining a channel access mode. The method 200 for determining the channel access mode is described from the perspective of interaction between the AP and the STA. The channel access mode determination method 200 includes but not limited to the following steps:

S201. AP trains the neural network to obtain the performance evaluation value of the first channel access method. The first channel access method refers to using the neural network to decide the station STA to access the channel. The performance evaluation value includes the accuracy and loss value of the neural network. at least one of .

In the embodiment of the present application, for the implementation manner of training the neural network by the AP, refer to the implementation manner of training the neural network by the second device in S101 above, and details are not repeated here.

S202. The AP sends the performance evaluation value of the first channel access mode to the STA.

S203. The STA receives the performance evaluation value of the first channel access mode from the AP.

S204. The STA determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value. The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide STAs to access a channel.

In this embodiment of the present application, the STA determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value. , the implementation manner of determining the channel access mode of the STA from the first channel access mode and the second channel access mode will not be repeated here.

S205. When the determined channel access mode is different from the current channel access mode of the STA, the STA sends the determined channel access mode to the AP.

When the determined channel access mode is different from the current channel access mode, the STA sends the determined channel access mode to the AP, so as to request the AP to switch the current channel access mode to the determined channel access mode.

Exemplarily, the current channel access mode of the STA is the first channel access mode, and the channel access mode determined by the STA according to the performance evaluation value is the second channel access mode, then the STA sends the second channel access mode to the AP, To request the AP to switch the current first channel access mode of the STA to the second channel access mode.

Exemplarily, the current channel access mode of the STA is the second channel access mode, and the channel access mode determined by the STA according to the performance evaluation value is the first channel access mode, then the STA sends the first channel access mode to the AP, To request the AP to switch the current second channel access mode of the STA to the first channel access mode.

S206. The AP receives the channel access mode from the STA.

S207. The AP updates the channel access mode status table according to the channel access mode. The channel access mode status table includes the identity of each STA among the multiple STAs associated with the AP, and whether each STA supports the first channel access mode. , the current channel access mode of each STA.

In an optional implementation manner, after the AP receives the channel access method from the STA, it learns that the received channel access method is compatible with the STA's current channel access method in the channel access method status table. The current channel access mode of the STA is different, so as to determine whether to agree with the STA to switch the current channel access mode to the received channel access mode.

In another optional implementation, after the AP receives the channel access method from the STA, the default STA requests to switch the current channel access method to the received channel access method, so that the AP determines whether to agree with the STA to use the current channel access method The access mode is switched to the channel access mode of receiving.

Understandably, if the AP agrees with the STA to switch the current channel access mode to the received channel access mode, then the AP locally stores the channel access mode status table according to the received channel access mode. The updating of the channel access mode status table by the AP according to the received channel access mode means that the AP updates the current channel access mode of the STA in the channel access mode status table to the received channel access mode.

Wherein, the channel access mode status table includes the identity of each STA among the multiple STAs associated with the AP, whether each STA supports the first channel access mode, and the current channel access mode of each STA. The channel access mode supported by each STA is the first channel access mode or the second channel access mode.

Exemplarily, the channel access mode status table locally stored by the AP is shown in Table 1 below. In the channel access mode state table, the identities of each STA among the 3 STAs associated with the AP are identification #1, identification #2, and identification #3, and the identification is the Media Access Control layer (Media Access Control, MAC ) logo. Both STA#1 and STA#2 respectively corresponding to the identifier #1 and the identifier #2 support the first channel access method, and STA#3 corresponding to the identifier #3 does not support the first channel access method. That is, both STA#1 and STA#2 can use the first channel access method to decide to access the channel, while STA#3 can only use the second channel access method to decide to access the channel. The current channel access modes of STA#1, STA#2, and STA#3 are the first channel access mode, the second channel access mode, and the second channel access mode. If the AP receives the first channel access method from STA#2, and the AP agrees that STA#2 will switch the current second channel access method to the first channel access method, then the AP will switch the current access method of STA#2 to The access method is updated to the first channel access method.

Table 1

Whether the STA supports the first channel access method to decide to access the channel can be carried in the UHT capabilities element. The UHT capabilities element is carried in the wireless frame sent by the STA to the AP during the process of associating the STA with the AP. The frame format of the UHT capabilities element can be seen in Figure 7, that is, the UHT capabilities element includes the first channel access mode support subfield, and the first channel access mode support subfield is used to indicate whether the STA supports the first channel access The method decides to access the channel.

In an optional implementation manner, when the AP agrees with the STA to switch the current channel access mode to the received channel access mode, the AP can also combine the current channel access mode of each of the multiple STAs associated with the AP with the The received channel access methods are all updated to the received channel access methods of other STAs, so that all STAs associated with the AP use the received channel access methods to decide to access channels, further improving System throughput, and reduce communication delay.

Exemplarily, the STAs associated with the AP are STA#1, STA#2, and STA#3. STA#1, STA#2, and STA#3 all support using the first channel access method to decide to access the channel. STA#1 The current channel access mode of STA#2 is the second channel access mode, and the current channel access mode of STA#3 is the first channel access mode. The AP receives the first channel access method from STA#2, that is, the AP learns that STA#2 requests to switch the current second channel access method to the first channel access method. When the AP agrees with STA#2 to switch the current second channel access method to the first channel access method, it updates the current channel access method of STA#2 in the channel status table to the first channel access method, and changes the channel status to the first channel access method. The current channel access method of STA#1 in the table is also updated to the first channel access method, so that both STA#1 and STA#2 use the first channel access method determined by STA#2 to decide to access the channel, thus having It is beneficial to improve the throughput of the system and reduce the communication delay.

S208. The AP sends second indication information to the STA, where the second indication information is used to instruct the AP to agree to update the channel access mode of the STA to a determined channel access mode.

Optionally, when the AP updates the current channel access mode of the STA in the channel access mode state table and also updates the current channel access mode of other STAs, the AP can also send the updated channel access mode to other STAs. access mode, so that other STAs switch the current channel access mode to this channel access mode.

S209. The STA receives second indication information from the AP.

S210. The STA switches the current channel access mode to a determined channel access mode.

Through the second indication information, the STA determines that the AP agrees to switch the current channel access mode to the determined channel access mode for the STA, so that the STA switches the current channel access mode to the determined channel access mode. Furthermore, the STA can use a certain channel access method to decide to access the channel.

In this embodiment of the present application, the STA may also determine whether the STA needs to update the channel access parameter when the determined channel access mode is the first channel access mode. Wherein, the channel access parameters may include the neural network structure and neural network parameters of the trained neural network. The neural network structure includes: neural network type (such as fully connected neural network, convolutional neural network, recurrent neural network, etc.), the number of neural network layers, the number of neurons in each layer, and the activation function of each layer. Neural network parameters include weight and bias.

When the channel access mode determined by the STA is the first channel access mode, the implementation of determining whether the STA needs to update the channel access parameters is as follows:

In an optional implementation manner, if the STA determines that the channel access method of the STA is the first channel access method according to the accuracy, the STA may also send the first channel access method to the AP when the accuracy is greater than the third preset value. Instructions. The first indication information is used to indicate that the STA needs to update the channel access parameters. The third preset value is greater than the first preset value. That is to say, when the accuracy of the trained neural network is much greater than the expected value, the STA determines that the channel access method is the first channel access method, and the STA needs to update the parameters of the neural network, and indicates to the AP that the STA needs to use the first indication information. Update the parameters of the neural network.

In another optional implementation manner, if the STA determines that the channel access mode of the STA is the first channel access mode according to the above-mentioned first value, the STA may also report to the second channel access mode when the first value is greater than the fourth preset value. The second device sends first indication information. The first indication information is used to indicate that the STA needs to update the channel access parameter. That is to say, when the accuracy of the trained neural network is greater than the accuracy of the neural network used by STA far beyond the expected value, or the error of the trained neural network is much smaller than the error of the neural network used by STA far beyond the expected value When , the STA determines that the channel access mode is the first channel access mode, and the STA needs to update the parameters of the neural network, and indicates to the AP that the STA needs to update the parameters of the neural network through the first indication information.

Therefore, the AP may also receive the first indication information from the STA, and learn through the first indication information that the STA needs to update the channel access parameter. Furthermore, the AP unicasts the channel access parameters to the STA. Then the STA receives the channel access parameters from the AP, and updates the neural network according to the channel access parameters to obtain the updated neural network, so that the STA uses the updated neural network to decide to access the channel.

In yet another implementation, if the AP also updates the current second channel access mode of other STAs associated with the AP to the first channel access mode, the AP can also broadcast channel access parameters to such STAs, so as to Such STAs are made to update the neural network according to the received channel access parameters, and decide to access the channel according to the updated neural network.

In the embodiment of the present application, the AP trains the neural network used to decide the STA access channel, obtains the performance evaluation value of the STA access channel decision by using the neural network, and sends the performance evaluation value to the STA. Therefore, the STA determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value. When the determined channel access mode is different from the current channel access mode, the STA sends the determined channel access mode to the AP to request the AP to agree to switch the current channel access mode to the determined channel access mode. When the AP agrees with the STA to switch the current channel access mode to the definite channel access mode, it informs the STA through indication information, so that the STA adopts the definite channel access mode to decide to access the channel. It can be seen that the channel access mode finally adopted by the STA is determined according to the performance evaluation value of the first channel access mode. That is to say, when the performance of the trained neural network is good, the STA determines that the STA uses the neural network to decide to access the channel; when the trained neural network has poor performance, the first device determines that the STA does not use the neural network to decide to access the channel, but uses CSMA The /CA mechanism decides to access the channel. Therefore, the STA adopts the appropriate channel access method to decide to access the channel, which can reduce the channel conflict or packet loss rate when the STA sends data, thereby improving the system throughput and reducing the communication delay.

When the STA in the network has strong computing power, the STA can train the neural network that decides to access the channel. Therefore, the embodiment of the present application also proposes a method 300 for determining a channel access mode by taking the first device as an STA and the second device as an AP as an example. FIG. 8 is an interactive schematic diagram of the method 300 for determining a channel access mode. The method 300 for determining the channel access mode is described from the perspective of interaction between the AP and the STA. The channel access mode determination method 300 includes but not limited to the following steps:

S301. The STA trains the neural network to obtain the performance evaluation value of the first channel access method. The first channel access method refers to the use of the neural network to decide the access channel of the station STA. The performance evaluation value includes the accuracy and loss value of the neural network. at least one of .

In the embodiment of the present application, the implementation manner of training the neural network by the STA may refer to the implementation manner of training the neural network by the second device in S101 above, and details are not repeated here.

S302. The STA sends the performance evaluation value of the first channel access mode to the AP.

S303. The AP receives the performance evaluation value of the first channel access mode from the STA.

S304. The AP determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value.

In this embodiment of the present application, the AP determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value. , the implementation manner of determining the channel access mode of the STA from the first channel access mode and the second channel access mode will not be repeated here.

S305. When the determined channel access mode is different from the current channel access mode of the STA, the AP updates the channel access mode status table.

Understandably, the AP may determine whether the determined channel access mode is the same as the current channel access mode of the STA based on the current channel access mode of the STA in the channel channel access mode state table. When the determined channel access mode is different from the current channel access mode of the STA, the AP determines that the STA needs to switch the current channel access mode to the determined channel access mode. Therefore, the AP updates the current channel access mode of the STA in the channel access mode status table to the determined channel access mode.

In the embodiment of the present application, the implementation manner of updating the channel access mode state table by the AP may refer to the implementation manner of updating the channel access mode state table in S206 above, and details are not repeated here.

S306. The AP sends the determined channel access mode to the STA.

Understandably, after the AP updates the current channel access mode of the STA in the channel access mode state table to the determined channel access mode, it sends the determined channel access mode to the STA, so that the STA switches the current channel access mode It is a definite channel access method.

S307. The STA receives the channel access mode from the AP.

S308. The STA switches the current channel access mode to the channel access mode.

The channel access mode received by the STA is determined by the AP based on the performance evaluation value, and the channel access mode is different from the current channel access mode of the STA, so the STA switches the current channel access mode to the received channel access mode , so that the STA uses the channel access method determined by the AP to decide to access the channel, that is, the STA uses the appropriate channel access method to decide to access the channel, which can improve the system throughput and reduce the communication delay.

In an optional implementation manner, the AP determines that the channel access mode of the STA is the first channel access mode according to the accuracy or the above-mentioned first value, and determines that the STA needs to change the channel access mode according to the implementation of the method 200 for determining the channel access mode. When channel access parameters are set, the AP sends first indication information to the STA, where the first indication information is used to indicate that the STA needs to update the channel access parameters. Therefore, the STA updates the neural network according to the channel access parameters corresponding to the trained neural network to obtain an updated neural network, and then the STA uses the updated neural network to decide to access a channel.

In the embodiment of the present application, the STA trains the neural network for deciding to access the channel, obtains the performance evaluation value of the first channel access mode, and sends the performance evaluation value to the AP. The AP determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value. When the determined channel access mode is different from the current channel access mode of the STA, the AP sends the determined channel access mode to the STA. Therefore, the STA switches the current channel access mode to the determined channel access mode, and then the STA adopts the channel access mode determined by the AP to decide to access the channel. The determined channel access method is determined by the AP according to the performance evaluation value of the first channel access method. Therefore, the STA adopts the appropriate channel access method to decide to access the channel, which can improve system throughput and reduce communication delay.

The embodiment of the present application also provides a method 400 for determining a channel access mode. FIG. 9 is a schematic flowchart of the method 400 for determining a channel access mode. The method 400 for determining a channel access mode is described from the perspective of the first device. The channel access mode determination method 400 includes but not limited to the following steps:

S401. The first device trains the neural network, and obtains the performance evaluation value of the first channel access method. The first channel access method refers to using the neural network to decide the site STA to access the channel, and the performance evaluation value includes the accuracy and loss of the neural network. at least one of the values.

In the embodiment of the present application, the first device trains the neural network and obtains the performance evaluation value of the first channel access method. Refer to the above S101 where the second device trains the neural network to obtain the performance evaluation value of the first channel access method. The implementation manner will not be repeated here.

S402. The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide STAs to access a channel.

In this embodiment of the present application, the first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method. The implementation manner will not be repeated here.

It can be seen that in the embodiment of the present application, the first device trains the neural network that decides the STA access channel, obtains the performance evaluation value of the first channel access method, and based on the performance evaluation value, selects the first channel access method and the second channel access method. In the channel access mode, determine the channel access mode of the STA. In this way, the STA can adopt an appropriate channel access method to decide to access the channel, which is conducive to improving the system throughput and reducing the communication delay.

When the computing power of the STA in the communication system is small, and the communication overhead of the STA is large, the STA cannot train the neural network that decides to access the channel, and cannot determine the channel access method of the STA. Therefore, the embodiment of the present application also proposes a method 500 for determining a channel access mode by taking the first device as an AP and the second device as an STA as an example. FIG. 10 is an interactive schematic diagram of the method 500 for determining a channel access mode. The method 500 for determining the channel access mode is described from the perspective of interaction between the AP and the STA. The channel access mode determination method 500 includes but not limited to the following steps:

S501. AP trains the neural network to obtain the performance evaluation value of the first channel access method. The first channel access method refers to using the neural network to decide the station STA to access the channel. The performance evaluation value includes the accuracy and loss value of the neural network. at least one of .

In the embodiment of the present application, the AP trains the neural network to obtain the performance evaluation value of the first channel access method. Please refer to the implementation of the second device training the neural network in S101 above to obtain the performance evaluation value of the first channel access method. way, no more details.

S502. The AP determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide STAs to access a channel.

In the embodiment of the present application, the AP determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method. For details, refer to the first device in S104 above. The implementation manner of determining the channel access mode of the STA will not be repeated here.

S503. When the determined channel access mode is different from the current channel access mode of the STA, the AP updates the channel access state table.

The AP may determine whether the determined channel access mode is the same as the current channel access mode of the STA according to the locally stored channel access mode state table. When the determined channel access mode of the AP is different from the current channel access mode of the STA, the AP determines that the STA needs to switch the channel access mode, so it also updates the current channel access mode of the STA in the channel access mode status table to the determined one. Channel access method to keep the same channel access method as STA. For the channel access mode status table, reference may be made to the above description, and details will not be repeated here.

In an optional implementation manner, the AP determines that the channel access mode of the STA is the first channel access mode, and according to the implementation mode in the channel access mode determination method 200 described above, when it is determined that the STA needs to update the channel access parameter , sending first indication information to the STA, where the first indication information is used to indicate that the STA needs to update the channel access parameter. Therefore, by receiving the first indication information from the first device, the STA knows that it needs to update the channel access parameters.

When the AP determines that the STA needs to update the channel access parameters, it sends the channel access parameters corresponding to the trained neural network to the STA. The channel access parameters are as described above and will not be repeated here.

S504. The AP sends the determined channel access mode to the STA.

S505. The STA receives the channel access mode from the AP.

S506. The STA switches the current channel access mode to the channel access mode.

After receiving the channel access method from the AP, the STA will switch the current channel access method to the received channel access method by default, and then use the received channel access method to decide to access the channel.

In an optional implementation manner, the STA receives channel access parameters from the AP, uses the channel access parameters to update the neural network, obtains an updated neural network, and uses the updated neural network to decide to access a channel.

In the embodiment of the present application, the AP trains the neural network that decides the STA access channel, obtains the performance evaluation value of the first channel access method, and according to the performance evaluation value, selects the first channel access method and the second channel access method , determine the channel access mode of the STA. When the determined channel access mode is different from the current channel access mode of the STA, the AP sends the determined channel access mode to the STA. Thus, the STA switches the current channel access mode to the channel access mode determined by the AP, and uses the determined channel access mode to decide to access the channel. In this way, the channel access method adopted by the STA is determined by the AP according to the first performance evaluation value, that is, the STA adopts an appropriate channel access method to decide to access the channel, which can improve the throughput of the system and reduce the communication delay.

When the STA in the communication system has better computing power and supports higher communication overhead, the STA can train the neural network used to decide the access channel, and determine the channel access mode according to the training result. Therefore, this embodiment of the present application proposes a method 600 for determining a channel access mode by taking the first device as an STA and the second device as an AP as an example. FIG. 11 is an interactive schematic diagram of the method 600 for determining a channel access mode. The method 600 for determining the channel access mode is described from the perspective of interaction between the AP and the STA. The channel access mode determination method 600 includes but not limited to the following steps:

S601. The STA trains the neural network to obtain the performance evaluation value of the first channel access method. The first channel access method refers to using the neural network to make decisions about the station STA's access to the channel. The performance evaluation value includes the accuracy and loss value of the neural network. at least one of .

In the embodiment of the present application, the STA trains the neural network to obtain the performance evaluation value of the first channel access method. For example, refer to the implementation of the second device training the neural network in S101 above to obtain the performance evaluation value of the first channel access method. way, no more details.

S602. The STA determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode. The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide STAs to access a channel.

In the embodiment of the present application, the STA determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method. For details, please refer to the first device in S104 above. The implementation manner of determining the channel access mode of the STA will not be repeated here.

In an optional implementation manner, the STA determines that the channel access mode of the STA is the first channel access mode, and according to the implementation mode in the channel access mode determination method 200 described above, when determining that the STA needs to update the channel access parameters , sending first indication information to the AP, where the first indication information is used to indicate that the STA needs to update the channel access parameter.

S603. When the determined channel access mode is different from the current channel access mode of the STA, the STA converts the current channel access mode into the determined channel access mode, and sends the determined channel access mode to the AP.

When the determined channel access method is different from the current channel access method, the STA switches the channel access method and sends the determined channel access method to the AP so that the AP knows that it has switched the current channel access method For the determined channel access method.

In an optional implementation manner, the channel access method determined by the STA is the first channel access method, and when the STA needs to update the channel access parameters, the STA updates the neural network according to the channel access parameters corresponding to the trained neural network. network to obtain the updated neural network. Therefore, the STA adopts the updated neural network to decide to access the channel.

S604. The AP receives the channel access mode from the STA.

S605. The AP updates the channel access mode state table according to the channel access mode.

After the AP receives the channel access mode from the STA, it can learn that the received channel access mode is different from the current channel access mode of the STA according to the channel access mode state table stored by the AP, so that the channel access mode The current channel access mode of the STA is updated to the received channel access mode, thereby maintaining the same channel access mode as the STA. The channel access mode status table can be referred to above, and will not be repeated here.

In an optional implementation manner, the AP may also receive first indication information from the STA, where the first indication information is used to indicate that the STA needs to update the neural network parameters. Then, if the AP updates the current channel access methods of other STAs when updating the current channel access methods of STAs, the AP can also train the neural network used to The channel access parameters are sent to other STAs that have updated the current channel access mode, so that other STAs also update the neural network according to the received channel access parameters, and use the updated neural network to decide to access the channel.

In the embodiment of the present application, the STA trains the neural network that decides to access the channel by itself, obtains the performance evaluation value of the first channel access method, and based on the performance evaluation value, selects the first channel access method and the second channel access method , determine the channel access mode of the STA. When the determined channel access mode is different from the current channel access mode of the STA, the STA switches the current channel access mode to the determined channel access mode, so as to use the determined channel access mode to decide to access the channel. Therefore, the STA decides to access the channel by using the channel access method determined according to the performance evaluation value, that is, adopts the appropriate channel access method to decide the access channel, which can improve the throughput of the system and reduce the communication delay.

4. Communication device.

In order to realize the various functions in the method provided by the above-mentioned embodiments of the present application, the first device or the second device may include a hardware structure and/or a software module, and realize the above-mentioned functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. various functions. Whether one of the above-mentioned functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

As shown in FIG. 12 , the embodiment of the present application provides a communication device 1200 . The communication device 1200 may be a component of the first device (eg, integrated circuit, chip, etc.), or a component of the second device (eg, integrated circuit, chip, etc.). The communication device 1200 may also be another communication unit, configured to implement the method in the method embodiment of the present application. The communication device 1200 may include: a communication unit 1201 and a processing unit 1202 . Optionally, a storage unit 1203 may also be included.

In a possible design, one or more units in Figure 12 may be implemented by one or more processors, or by one or more processors and memory; or by one or more processors and a transceiver; or by one or more processors, memories, and a transceiver, which is not limited in this embodiment of the present application. The processor, memory, and transceiver can be set independently or integrated.

The communication device 1200 has the function of realizing the first device described in the embodiment of the present application, and optionally, the communication device 1200 has the function of realizing the second device described in the embodiment of the present application. For example, the communication device 1200 includes a first device that executes the modules or units or means (means) corresponding to the steps of the first device described in the embodiment of this application, and the functions or units or means (means) can be implemented by software, Or it may be realized by hardware, it may also be realized by executing corresponding software by hardware, and it may also be realized by a combination of software and hardware. For details, further reference may be made to the corresponding descriptions in the foregoing corresponding method embodiments.

In a possible design, a communication device 1200 may include:

The communication unit 1201 is configured to receive a performance evaluation value of a first channel access method; the first channel access method refers to using a neural network decision-making station STA to access a channel, and the performance evaluation value includes the exact channel access value of the neural network. At least one of degree and loss value;

The processing unit 1202 is configured to determine the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value; the second channel access mode refers to A carrier sensing collision avoidance mechanism is used to make a decision on the STA access channel.

In an optional implementation manner, the processing unit 1202 determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value, specifically for: When the accuracy is greater than a first preset value, determine that the channel access method of the STA is the first channel access method; when the accuracy is less than or equal to a first preset value, determine that the The channel access mode of the STA is the second channel access mode.

In another optional implementation manner, the processing unit 1202 determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value, specifically for : When the first value is greater than a second preset value, determine that the channel access mode of the STA is the first channel access mode; the second preset value is greater than zero; when the first value is less than or equal to the first channel access mode When two preset values are used, it is determined that the channel access mode of the STA is the second channel access mode. Wherein, the first value is the accuracy minus the accuracy of the first channel access method used by the STA; or, the first value is the first channel access method used by the STA The loss value of the input mode minus the value of the loss value.

In an optional implementation manner, when the processing unit 1202 determines that the channel access mode of the STA is the first channel access mode, it may also be configured to: when the accuracy is greater than a third preset value, send The second device sends first indication information; the first indication information is used to indicate that the STA needs to update a channel access parameter; the third preset value is greater than the first preset value.

In another optional implementation manner, when the processing unit 1202 determines that the channel access mode of the STA is the first channel access mode, it may also be configured to: when the first value is greater than a fourth preset value , sending first indication information to the second device, where the first indication information is used to indicate that the STA needs to update a channel access parameter; the fourth preset value is greater than the second preset value.

In an optional implementation manner, the processing unit 1202 is further configured to: when the determined channel access mode is different from the current channel access mode of the STA, send the Definite channel access method.

In an optional implementation manner, the communication device 1200 is the STA, and the communication unit 1201 can also receive second indication information from the second device; the second indication information is used to indicate that the second The device agrees to switch the channel access mode of the first device to the determined channel access mode; the processing unit 1202 may also switch the channel access mode of the first device to the determined channel access mode .

In another optional implementation manner, the communication device 1200 is an access point AP, and the processing unit 1202 may also update the channel access mode status table according to the determined channel access mode; the channel access mode The state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

In an optional implementation manner, the communication device 1200 is the STA, and the communication unit 1201 can also receive channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network The processing unit 1202 may also update the neural network according to the channel access parameters to obtain an updated neural network.

The embodiment of the present application and the method embodiment shown above are based on the same idea, and the technical effects they bring are also the same. For specific principles, please refer to the description of the above-mentioned embodiment, and will not repeat them here.

In another possible design, a communication device 1200 may include:

The processing unit 1202 is used to train the neural network and obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network to decide the station STA to access the channel; the performance evaluation value includes the At least one of the accuracy and loss values of the neural network;

The communication unit 1201 is configured to send the performance evaluation value of the first channel access manner.

In an optional implementation manner, the communication unit 1201 is further configured to receive a channel access mode from the first device; the channel access mode is determined by the first device according to the performance evaluation value.

In an optional implementation manner, the communication device 1200 is an access point AP, and the processing unit 1202 may also update a channel access mode status table; the channel access mode status table includes the The identity of each STA among the multiple STAs, whether each STA supports the first channel access mode, and the current channel access mode of each STA; the communication unit 1201 is also used to send the first device Sending second indication information; the second indication information is used to instruct the second device to agree to the first transposition to switch the channel access mode of the first device to the determined channel access mode.

In an optional implementation manner, the communication device 1200 is the STA, and the processing unit 1202 may also switch the channel access mode of the second device to the determined channel access mode.

In an optional implementation manner, the communication device 1200 is an access point AP, and the communication unit 1201 is further configured to: receive first indication information from the first device, where the first indication information is used to indicate The STA needs to update the channel access parameters; send the channel access parameters; the channel access parameters include the neural network structure parameters and neural network parameters of the neural network.

In another optional implementation manner, the communication device 1200 is an access point AP, and the communication unit 1201 may also receive first indication information from the first device, where the first indication information is used to indicate the The STA needs to update channel access parameters; the processing unit 1202 can also update the neural network according to the channel access parameters corresponding to the neural network, to obtain an updated neural network.

The embodiments of the present application and the method embodiments shown above are based on the same idea, and the technical effects brought about by them are also the same. For specific principles, please refer to the description of the above-mentioned embodiments, and details will not be repeated here.

In yet another possible design, a communication device 1200 may include:

The processing unit 1202 is configured to train a neural network and obtain a performance evaluation value of a first channel access method; the first channel access method refers to using the neural network decision-making station STA to access a channel, and the performance evaluation value includes at least one of an accuracy and a loss value of the neural network;

The processing unit 1202 is further configured to determine the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode; The second channel access mode refers to using a carrier sense collision avoidance mechanism to decide the channel access of the STA.

In another optional implementation manner, the processing unit 1202 determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value, specifically for : When the first value is greater than a second preset value, determine that the channel access mode of the STA is the first channel access mode; the second preset value is greater than zero; when the first value is less than or equal to the first channel access mode When the preset value is three, it is determined that the channel access mode of the STA is the second channel access mode. in. The first value is the accuracy minus the accuracy of the first channel access method used by the STA; or, the first value is the first channel access method used by the STA The value of the loss value minus the loss value.

In an optional implementation manner, when the processing unit 1202 determines that the channel access mode of the STA is the first channel access mode, it is further configured to: when the accuracy is greater than a third preset value, send The second device sends first indication information; the first indication information is used to indicate that the STA needs to update a channel access parameter; the second preset value is greater than the first preset value.

In another optional implementation manner, when the processing unit 1202 determines that the channel access mode of the STA is the first channel access mode, it is further configured to: when the first value is greater than a fourth preset value , sending first indication information to the second device, where the first indication information is used to indicate that the STA needs to update a channel access parameter; the fourth preset value is greater than the second preset value.

In an optional implementation manner, when the determined channel access mode is different from the current channel access mode of the STA, the processing unit 1202 may also send the determined channel access mode to the second device through the communication unit 1201. Channel access method.

In an optional implementation manner, the communication device 1200 is an access point AP, and the processing unit 1202 may also update a channel access mode status table; the channel access mode status table includes the The identity of each STA among the multiple STs, whether each STA supports the first channel access mode, and the current channel access mode of each STA.

In an optional implementation manner, the communication device 1200 is the STA, and the processing unit 1202 may also switch the channel access mode of the first device to the determined channel access mode.

In another optional implementation manner, the communication device 1200 is the AP, and the communication unit 1201 may also send a channel access parameter, where the channel access parameter includes a neural network of the neural network of the neural network Structural parameters and neural network parameters.

In an optional implementation manner, the communication device 1200 is the STA, and the processing unit 1202 may also update the neural network according to channel access parameters corresponding to the neural network to obtain an updated neural network; The channel access parameters include neural network structure parameters and neural network parameters of the neural network of the neural network.

In yet another possible design, a communication device 1200 may include:

a communication unit 1201, configured to receive a channel access mode from the first device;

The processing unit 1202 is configured to switch the current channel access mode to the channel access mode; the channel access mode is the performance evaluation value of the first device according to the first channel access mode, from the first determined in the channel access method and the second channel access method;

In an optional implementation manner, the communication unit 1201 is also configured to receive channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network; the processing unit 1202 is also configured to Updating the neural network according to the channel access parameters to obtain an updated neural network.

In yet another possible design, a communication device 1200 may include:

A processing unit 1202, configured to update a channel access mode status table according to the channel access mode;

The first channel access method refers to using the neural network to decide the STA access channel; the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel; the performance evaluation a value comprising at least one of an accuracy and a loss value of said neural network;

The channel access mode status table includes the identity of each STA in the multiple STAs associated with the first device, whether each STA in the multiple STAs supports the first channel access mode, and each STA in the multiple STAs supports the first channel access mode. The current channel access mode of the STA.

In an optional implementation manner, the communication unit 1201 is further configured to: receive first indication information from the first device, where the first indication information is used to indicate that the STA needs to update channel access parameters; Among the multiple STAs associated with the second device, STAs other than the STA send channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network.

The embodiment of the present application also provides a communication device 1300 , and FIG. 13 is a schematic structural diagram of the communication device 1300 . The communication device 1300 may be a first device or a second device, or may be a chip, a chip system, or a processor that supports the first device to implement the above method, or may be a chip or a chip that supports the second device to implement the above method. system, or processor, etc. The device can be used to implement the methods described in the above method embodiments, and for details, refer to the descriptions in the above method embodiments.

The communication device 1300 may include one or more processors 1301 . The processor 1301 may be a general-purpose processor or a special-purpose processor. For example, it may be a baseband processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or a central processing unit (Central Processing Unit, CPU). The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control communication devices (such as base stations, baseband chips, terminals, terminal chips, DU or CU, etc.), execute software programs, and process Data for Software Programs.

Optionally, the communication device 1300 may include one or more memories 1302, on which instructions 1304 may be stored, and the instructions may be executed on the processor 1301, so that the communication device 1300 executes the above method Methods described in the Examples. Optionally, data may also be stored in the memory 1302 . The processor 1301 and the memory 1302 can be set separately or integrated together.

The memory 1302 may include but not limited to hard disk (hard disk drive, HDD) or solid-state drive (solid-state drive, SSD) and other non-volatile memory, random access memory (Random Access Memory, RAM), erasable and programmable Read-only memory (Erasable Programmable ROM, EPROM), read-only memory (Read-Only Memory, ROM) or portable read-only memory (Compact Disc Read-Only Memory, CD-ROM), etc.

Optionally, the communication device 1300 may further include a transceiver 1305 and an antenna 1306 . The transceiver 1305 may be called a transceiver unit, a transceiver, or a transceiver circuit, etc., and is used to realize a transceiver function. The transceiver 1305 may include a receiver and a transmitter, and the receiver may be called a receiver or a receiving circuit for realizing a receiving function; the transmitter may be called a transmitter or a sending circuit for realizing a sending function.

The communication device 1300 is a first device: the processor 1301 is used to execute S104 in the channel access mode determination method 100, and is used to perform S401 and S402 in the channel access mode determination method 400; the transceiver 1305 is used to perform S103 in the method 100 for determining a channel access mode.

The communication device 1300 is a second device: the processor 1301 is configured to execute S101 in the method 100 for determining a channel access mode. The transceiver 1305 is configured to execute S102 in the method 100 for determining a channel access mode.

In another possible design, the processor 1301 may include a transceiver for implementing receiving and sending functions. For example, the transceiver may be a transceiver circuit, or an interface, or an interface circuit. The transceiver circuits, interfaces or interface circuits for realizing the functions of receiving and sending can be separated or integrated together. The above-mentioned transceiver circuit, interface or interface circuit may be used for reading and writing code/data, or the above-mentioned transceiver circuit, interface or interface circuit may be used for signal transmission or transfer.

In yet another possible design, optionally, the processor 1301 may store instructions 1303, and the instructions 1303 run on the processor 1301, and may cause the communication device 1300 to execute the methods described in the foregoing method embodiments. The instruction 1303 may be fixed in the processor 1301, in this case, the processor 1301 may be implemented by hardware.

In yet another possible design, the communication device 1300 may include a circuit, and the circuit may implement the function of sending or receiving or communicating in the foregoing method embodiments. The processor and the transceiver described in the embodiment of the present application can be implemented in integrated circuit (integrated circuit, IC), analog IC, radio frequency integrated circuit RFIC, mixed signal IC, application specific integrated circuit (application specific integrated circuit, ASIC), printed circuit board (printed circuit board, PCB), electronic equipment, etc. The processor and transceiver can also be fabricated using various IC process technologies such as complementary metal oxide semiconductor (CMOS), nMetal-oxide-semiconductor (NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (Bipolar Junction Transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

The embodiment of the present application and the method embodiments shown in the channel access method determination method 100 to the channel access method determination method 600 above are based on the same idea, and the technical effects they bring are also the same. For specific principles, please refer to the above channel access method determination method The description of the embodiment shown in 100 to the method for determining the channel access mode 600 will not be repeated here.

The present application also provides a computer-readable storage medium for storing computer software instructions, and when the instructions are executed by a communication device, the functions of any one of the above method embodiments are realized.

The present application also provides a computer program product, which is used for storing computer software instructions, and when the instructions are executed by a communication device, the functions of any one of the above method embodiments are realized.

The present application also provides a computer program, which, when running on a computer, can realize the functions of any one of the above method embodiments.

In the above embodiments, all or part may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on the computer, all or part of the interactions or functions described in the embodiments of the present application will be generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (for example, a solid state drive (solid state drive, SSD)) etc.

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims

A method for determining a channel access method, characterized in that the method includes:

The first device receives the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network decision-making station STA to access the channel, and the performance evaluation value includes the accuracy and loss of the neural network at least one of the values;

The first device determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value;

The second channel access manner refers to using a carrier sense collision avoidance mechanism to decide on channel access by the STA.
The method according to claim 1, wherein the first device determines the channel access of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value ways, including:

The first device determines that the channel access mode of the STA is the first channel access mode when the accuracy is greater than a first preset value;

The first device determines that the channel access mode of the STA is the second channel access mode when the accuracy is less than or equal to the first preset value.
The method according to claim 1, wherein the first device determines the channel access of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value ways, including:

The first device determines that the channel access mode of the STA is the first channel access mode when the first value is greater than a second preset value; the second preset value is greater than zero;

The first device determines that the channel access mode of the STA is the second channel access mode when the first value is less than or equal to the second preset value;

The first value is the accuracy minus the accuracy of the first channel access method used by the STA; or,

The first value is a value obtained by subtracting the loss value from the loss value of the first channel access mode used by the STA.
The method according to claim 2, wherein when the first device determines that the channel access mode of the STA is the first channel access mode, the method further comprises:

The first device sends first indication information to the second device when the accuracy is greater than a third preset value; the first indication information is used to indicate that the STA needs to update channel access parameters;

The third preset value is greater than the first preset value.
The method according to claim 3, wherein when the first device determines that the channel access mode of the STA is the first channel access mode, the method further comprises:

When the first value is greater than a fourth preset value, the first device sends first indication information to the second device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The fourth preset value is greater than the second preset value.
The method according to any one of claims 1 to 5, characterized in that the method further comprises:

When the determined channel access mode is different from the current channel access mode of the STA, the first device sends the determined channel access mode to the second device.
The method according to claim 6, wherein the first device is the STA, and the method further comprises:

The first device receives second indication information from the second device; the second indication information is used to instruct the second device to agree to switch the channel access mode of the first device to the determined Channel access method;

The first device switches the channel access mode of the first device to the determined channel access mode.
The method according to claim 6, wherein the first device is an access point (AP), and the method further comprises:

The first device updates a channel access mode status table according to the determined channel access mode;

The channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel of each STA. access method.
According to the method according to any one of claims 4 to 7, the first device is the STA, wherein the method further comprises:

The first device receives channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network;

The first device updates the neural network according to the channel access parameters to obtain an updated neural network.
A method for determining a channel access method, characterized in that the method includes:

The second device trains the neural network to obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network to decide the station STA to access the channel; the performance evaluation value includes the neural network at least one of precision and loss;

The second device sends the performance evaluation value of the first channel access manner.
The method according to claim 10, characterized in that the method further comprises:

The second device receives a channel access mode from the first device; the channel access mode is determined by the first device according to the performance evaluation value.
The method according to claim 11, wherein the second device is an access point (AP), and the method further comprises:

The second transposition updates the channel access mode state table; the channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first A channel access method, the current channel access method of each STA;

The second device sends second indication information to the first device; the second indication information is used to instruct the second device to allow the first device to switch the channel access mode of the first device to The determined channel access method.
The method according to claim 11, wherein the second device is the STA, and the method further comprises:

The second device switches the channel access mode of the second device to the determined channel access mode.
The method according to any one of claims 10 to 13, wherein the second device is an access point AP; the method further comprises:

The second device receives first indication information from the first device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The second device sends channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network.
The method according to claim 10, or 11, or 13, wherein the second device is the STA; the method further comprises:

The second device receives first indication information from the first device, where the first indication information is used to indicate that the second device needs to update channel access parameters;

The second device updates the neural network according to the channel access parameters corresponding to the neural network to obtain an updated neural network.
A method for determining a channel access method, characterized in that the method includes:

The first device trains the neural network to obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network decision-making station STA to access the channel, and the performance evaluation value includes the neural network At least one of the accuracy and loss values of the network;

The first device determines the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method;

The second channel access manner refers to using a carrier sense collision avoidance mechanism to decide on channel access by the STA.
The method according to claim 16, wherein the first device determines the channel access of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value ways, including:

The first device determines that the channel access mode of the STA is the first channel access mode when the accuracy is greater than a first preset value;

The first device determines that the channel access mode of the STA is the second channel access mode when the accuracy is less than or equal to a first preset value.
The method according to claim 16, wherein the first device determines the channel access of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value ways, including:

The first device determines that the channel access mode of the STA is the first channel access mode when the first value is greater than a second preset value; the second preset value is greater than zero;

The first device determines that the channel access mode of the STA is the second channel access mode when the first value is less than or equal to a third preset value;

The first value is the accuracy minus the accuracy of the first channel access method used by the STA; or,

The first value is a value obtained by subtracting the loss value from the loss value of the first channel access mode used by the STA.
The method according to claim 17, wherein when the first device determines that the channel access mode of the STA is the first channel access mode, the method further comprises:

The first device sends first indication information to the second device when the accuracy is greater than a third preset value; the first indication information is used to indicate that the STA needs to update channel access parameters;

The second preset value is greater than the first preset value.
The method according to claim 18, wherein when the first device determines that the channel access mode of the STA is the first channel access mode, the method further comprises:

When the first value is greater than a fourth preset value, the first device sends first indication information to the second device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The fourth preset value is greater than the second preset value.
The method according to any one of claims 16 to 20, further comprising:

When the determined channel access mode is different from the current channel access mode of the STA, the first device sends the determined channel access mode to the second device.
The method according to claim 21, wherein the first device is an access point (AP); the method further comprises:

The first device updates the channel access mode state table;

The channel access mode state table includes the identity of each STA among the multiple STs associated with the first device, whether each STA supports the first channel access mode, and the current channel of each STA. access method.
The method according to claim 21, wherein the first device is the STA; the method further comprises:

The first device switches the channel access mode of the first device to the determined channel access mode.
The method according to any one of claims 16 to 22, wherein the first device is the AP; the method further comprises:

The first device sends a channel access parameter, where the channel access parameter includes a neural network structure parameter and a neural network parameter of the neural network of the neural network.
The method according to any one of claims 16 to 21, or 23, wherein the first device is the STA; the method further comprises:

The first device updates the neural network according to the channel access parameters corresponding to the neural network to obtain an updated neural network;

The channel access parameters include neural network structural parameters and neural network parameters of the neural network of the neural network.
A method for determining a channel access method, characterized in that the method includes:

The second device receives the channel access mode from the first device;

The second device switches the current channel access mode to the channel access mode;

The channel access method is determined by the first device from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method;

The first channel access method refers to using the neural network decision-making station STA to access the channel;

The second channel access method refers to using a carrier sense conflict avoidance mechanism to decide the STA access channel;

The performance evaluation value includes at least one of an accuracy and a loss value of the neural network.
The method according to claim 26, further comprising:

The second device receives channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network;

The second device updates the neural network according to the channel access parameters to obtain an updated neural network.
A method for determining a channel access method, characterized in that the method includes:

The second device receives the channel access mode from the first device;

The second device updates a channel access mode status table according to the channel access mode;

The channel access method is determined by the first device from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method;

The first channel access method refers to using the neural network decision-making station to access the channel by the STA;

The second channel access method refers to using a carrier sense conflict avoidance mechanism to decide the STA access channel;

The performance evaluation value includes at least one of an accuracy and a loss value of the neural network;

The channel access mode status table includes the identity of each STA in the multiple STAs associated with the first device, whether each STA in the multiple STAs supports the first channel access mode, and each STA in the multiple STAs supports the first channel access mode. The current channel access mode of the STA.
The method according to claim 28, further comprising:

The second device receives first indication information from the first device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The second device sends channel access parameters to STAs other than the STA among the multiple STAs associated with the second device;

The channel access parameters include neural network structure parameters and neural network parameters of the neural network.
A communication device, characterized in that the communication device includes:

A communication unit, configured to receive a performance evaluation value of a first channel access method; the first channel access method refers to using a neural network decision-making station STA to access a channel, and the performance evaluation value includes the accuracy of the neural network and at least one of loss value;

A processing unit, configured to determine the channel access method of the STA from the first channel access method and the second channel access method according to the performance evaluation value; the second channel access method refers to using The carrier sense collision avoidance mechanism decides the channel to be accessed by the STA.
The device according to claim 30, wherein the processing unit determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value , specifically for:

When the accuracy is greater than a first preset value, determine that the channel access mode of the STA is the first channel access mode;

When the accuracy is less than or equal to the first preset value, determine that the channel access mode of the STA is the second channel access mode.
The device according to claim 30, wherein the processing unit determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value , specifically for:

When the first value is greater than a second preset value, determine that the channel access mode of the STA is the first channel access mode; the second preset value is greater than zero;

When the first value is less than or equal to the second preset value, determine that the channel access mode of the STA is the second channel access mode;

The first value is the accuracy minus the accuracy of the first channel access method used by the STA; or,

The first value is a value obtained by subtracting the loss value from the loss value of the first channel access mode used by the STA.
The device according to claim 31, wherein when the processing unit determines that the channel access mode of the STA is the first channel access mode, it is further configured to:

When the accuracy is greater than a third preset value, sending first indication information to the second device; the first indication information is used to indicate that the STA needs to update channel access parameters;

The third preset value is greater than the first preset value.
The device according to claim 32, wherein when the processing unit determines that the channel access mode of the STA is the first channel access mode, it is further configured to:

When the first value is greater than a fourth preset value, sending first indication information to the second device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The fourth preset value is greater than the second preset value.
The device according to any one of claims 30 to 34, wherein the processing unit is further configured to:

When the determined channel access mode is different from the current channel access mode of the STA, sending the determined channel access mode to the second device.
The device according to claim 35, wherein the device is the STA, and the processing unit is further configured to:

Receive second indication information from the second device through the communication unit; the second indication information is used to instruct the second device to agree to switch the channel access mode of the device to the determined channel access mode input method;

switching the channel access mode of the device to the determined channel access mode.
The device according to claim 35, wherein the device is an access point AP, and the processing unit is further configured to:

Updating the channel access mode status table according to the determined channel access mode;

The channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, and the current channel of each STA. access method.
The device according to any one of claims 33 to 36, wherein the first device is the STA, and the processing unit is further configured to:

Receive channel access parameters through the communication unit; the channel access parameters include neural network structure parameters and neural network parameters of the neural network;

Updating the neural network according to the channel access parameters to obtain an updated neural network.
A communication device, characterized in that the communication device includes:

The processing unit is used to train the neural network and obtain the performance evaluation value of the first channel access method; the first channel access method refers to using the neural network to decide the station STA to access the channel; the performance evaluation value includes the neural network At least one of the accuracy and loss values of the network;

A communication unit, configured to send the performance evaluation value of the first channel access manner.
The device according to claim 39, wherein the communication unit is further used for:

Receive a channel access mode from the first device; the channel access mode is determined by the first device according to the performance evaluation value.
The device according to claim 40, wherein the device is an access point AP, and the processing unit is further configured to:

Updating the channel access mode state table; the channel access mode state table includes the identity of each STA among the multiple STAs associated with the first device, whether each STA supports the first channel access mode, The current channel access mode of each STA;

Sending second indication information to the first device; the second indication information is used to indicate that the device agrees to switch the channel access mode of the first device to the determined channel access mode by the first device Way.
The device according to claim 40, wherein the device is the STA, and the processing unit is further configured to:

switching the channel access mode of the device to the determined channel access mode.
The device according to any one of claims 39 to 42, wherein the device is an access point AP; the communication unit is also used for:

receiving first indication information from the first device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

Sending channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network.
The device according to claim 39, or 40, or 42, wherein the device is the STA; the processing unit is further configured to:

receiving first indication information from the first device through the communication unit, where the first indication information is used to indicate that the device needs to update channel access parameters;

The neural network is updated according to the channel access parameters corresponding to the neural network to obtain an updated neural network.
A communication device, characterized in that the communication device includes:

A processing unit, configured to train a neural network, and obtain a performance evaluation value of a first channel access method; the first channel access method refers to using the neural network decision-making station STA to access a channel, and the performance evaluation value includes the At least one of the accuracy and loss value of the neural network;

The processing unit is further configured to determine the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value of the first channel access mode; the second channel access mode The two-channel access mode refers to using a carrier sense collision avoidance mechanism to decide the STA access channel.
The device according to claim 45, wherein the processing unit determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value , specifically for:

When the accuracy is greater than a first preset value, determine that the channel access mode of the STA is the first channel access mode;

When the accuracy is less than or equal to the first preset value, determine that the channel access mode of the STA is the second channel access mode.
The device according to claim 45, wherein the processing unit determines the channel access mode of the STA from the first channel access mode and the second channel access mode according to the performance evaluation value , specifically for:

When the first value is greater than a second preset value, determine that the channel access mode of the STA is the first channel access mode; the second preset value is greater than zero;

When the first value is less than or equal to a third preset value, determine that the channel access mode of the STA is the second channel access mode;

The first value is the accuracy minus the accuracy of the first channel access method used by the STA; or,

The first value is a value obtained by subtracting the loss value from the loss value of the first channel access mode used by the STA.
The device according to claim 46, wherein when the processing unit determines that the channel access mode of the STA is the first channel access mode, the processing unit is further configured to:

When the accuracy is greater than a third preset value, sending first indication information to the second device; the first indication information is used to indicate that the STA needs to update channel access parameters;

The second preset value is greater than the first preset value.
The device according to claim 47, wherein when the processing unit determines that the channel access mode of the STA is the first channel access mode, the processing unit is further configured to:

When the first value is greater than a fourth preset value, sending first indication information to the second device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

The fourth preset value is greater than the second preset value.
The device according to any one of claims 45 to 49, wherein the processing unit is further configured to:

When the determined channel access mode is different from the current channel access mode of the STA, sending the determined channel access mode to the second device.
The device according to claim 50, wherein the device is an access point (AP); and the processing unit is further configured to:

Update the channel access mode status table;

The channel access mode state table includes the identity of each STA among the multiple STs associated with the device, whether each STA supports the first channel access mode, and the current channel access mode of each STA. Way.
The device according to claim 50, wherein the device is the STA; and the processing unit is further configured to:

switching the channel access mode of the device to the determined channel access mode.
The device according to any one of claims 45 to 51, wherein the device is the AP; the communication unit is further configured to:

Sending channel access parameters, where the channel access parameters include neural network structure parameters and neural network parameters of the neural network of the neural network.
According to any one of claims 45 to 50, or the device described in 51, wherein the device is the STA; the processing unit is further configured to:

updating the neural network according to the channel access parameters corresponding to the neural network to obtain an updated neural network;

The channel access parameters include neural network structural parameters and neural network parameters of the neural network of the neural network.
A communication device, characterized in that the communication device includes:

a communication unit, configured to receive a channel access method from the first device;

a processing unit, configured to switch the current channel access mode to the channel access mode;

The channel access method is determined by the first device from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method; the first channel access method The access method refers to using the neural network to decide the access channel of the station STA; the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the access channel of the STA; the performance evaluation value includes the STA access channel of the neural network At least one of precision and loss value.
The device according to claim 55, wherein the processing unit is further used for:

Receive channel access parameters; the channel access parameters include neural network structure parameters and neural network parameters of the neural network;

Updating the neural network according to the channel access parameters to obtain an updated neural network.
A communication device, characterized in that the communication device includes:

a communication unit, configured to receive a channel access method from the first device;

A processing unit, configured to update the channel access mode status table according to the channel access mode;

The channel access method is determined by the first device from the first channel access method and the second channel access method according to the performance evaluation value of the first channel access method; the first channel access method The access method refers to using the neural network to decide the STA access channel; the second channel access method refers to using the carrier sense conflict avoidance mechanism to decide the STA access channel;

The performance evaluation value includes at least one of the accuracy and loss value of the neural network; the channel access mode state table includes identifiers of multiple STAs associated with the first device, the multiple STAs The channel access mode supported by each STA, and the current channel access mode of each STA.
The device according to claim 57, wherein the communication unit is further used for:

receiving first indication information from the first device, where the first indication information is used to indicate that the STA needs to update channel access parameters;

sending channel access parameters to STAs other than the STA among the multiple STAs associated with the device;

The channel access parameters include neural network structure parameters and neural network parameters of the neural network.
A communication device, characterized in that it includes a processor and a transceiver, the transceiver is used to communicate with other communication devices; the processor is used to run a program, so that the communication device implements any one of claims 1 to 9 The method described in item 1, or, so that the communication device implements the method described in any one of claims 10 to 15, or, so that the communication device implements the method described in any one of claims 16 to 25, Or, to make the communication device implement the method in claim 26 or 27, or to make the communication device implement the method in claim 28 or 29.
A computer-readable storage medium, the computer-readable storage medium stores instructions, and when it is run on a computer, the method described in any one of claims 1 to 9 is executed; or any one of claims 10 to 15 A method described in one is carried out; Or the method described in any one of claim 16 to 25 is carried out; Or the method described in claim 26 or 27 is carried out; Or the method described in claim 28 or 29 is carried out .
A computer program product comprising instructions which, when run on a computer, cause the method of any one of claims 1 to 9 to be performed; or the method of any one of claims 10 to 15 to be performed; or The method of any one of claims 16 to 25 is performed; or the method of claim 26 or 27 is performed; or the method of claim 28 or 29 is performed.