Method, apparatus and device for determining channel parameters, and system

Abstract

The application provides a channel parameter determination method, device, equipment and system, and belongs to the technical field of wireless communication. In the method, an access point collects channel related information of a station, uses the channel related information and an AI model to determine and issue channel parameters used by the access point and the station when communicating to the station to the station. In this way, the channel related information is closely related to the channel parameters, the AI model can directly determine all the channel parameters using the channel related information without iteration, so that the channel parameters can be quickly obtained, and the efficiency of determining the channel parameters is improved.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus, device and system for determining channel parameters. Background Technology

[0002] In wireless networks, the channel parameters used by access points (APs) and stations (STAs) to communicate have a significant impact on network performance, so it is necessary to find suitable channel parameters.

[0003] In related technologies, the AP employs an independent packet probing mechanism to traverse channel parameters. For example, the AP sends probe data packets and determines the channel parameters based on the transmission and reception of these packets. Since there are many types of channel parameters, determining each parameter through a packet probing mechanism may not quickly find suitable parameter values. Summary of the Invention

[0004] This application provides a method, apparatus, device, and system for determining channel parameters, which can improve the efficiency of determining channel parameters. The technical solution adopted is as follows:

[0005] In a first aspect, this application provides a method for determining channel parameters. The method is applied to a first access point in a wireless network. The method includes: obtaining channel-related information of a site associated with the first access point; and sending the channel parameters used by the first access point when communicating with the site based on the channel-related information and a channel parameter model. The channel parameter model is an artificial intelligence (AI) model.

[0006] In the scheme shown in this application, the access point collects channel-related information from the site. Using this channel-related information and an AI model, the access point determines the channel parameters used when communicating with the site. In this way, the channel-related information is closely related to the channel parameters, and the AI ​​model can directly determine all channel parameters using the channel-related information without needing to iterate through the data. Therefore, it can quickly obtain the channel parameters and improve the efficiency of determining them.

[0007] In one alternative approach, the channel parameter model includes a channel-aware model and a first parameter determination model. When determining the channel parameters, the first access point first extracts the channel characteristics corresponding to the station using the channel-aware model and channel-related information. Then, using these channel characteristics and the first parameter determination model, it determines the channel parameters used by the first access point to communicate with the station and sends these channel parameters to the station. This approach, by first sensing the channel characteristics and then calculating the channel parameters, ensures that the channel parameters are closely related to the environment, making the determined channel parameters more environmentally friendly and thus improving network performance.

[0008] In one alternative approach, in a network of multiple access points, a first access point is connected to a second access point. In the first access point, the channel parameter model includes a channel-aware model and a second parameter determination model. When determining the channel parameters, the first access point uses channel-related information and the channel-aware model to determine the channel characteristics corresponding to the site. Then, using these channel characteristics and the first parameter determination model, it determines a subset of the channel parameters used when communicating with the site. The first access point then sends these channel characteristics to the second access point and receives another subset of the channel parameters from the second access point. Finally, the first access point sends the channel parameters to the site. In this way, in a network of multiple access points, the channel parameters are jointly determined by the first and second access points, saving processing resources for the first access point.

[0009] In one alternative approach, in a network of multiple access points, a first access point is connected to a second access point. In the first access point, channel parameters include a channel-aware model. When determining channel parameters, the first access point uses channel-related information and the channel-aware model to determine the channel characteristics corresponding to the site. Then, the first access point sends these channel characteristics to the second access point and receives the channel parameters used by the first access point when communicating with the site, which are then sent by the second access point. The first access point then sends these channel parameters to the site. In this way, in a network of multiple access points, the channel parameters are jointly determined by the first and second access points, saving processing resources for the first access point.

[0010] In one alternative approach, before sending channel characteristics to the second access point, the first access point receives an AI computation enable message from the second access point. This AI computation enable message instructs the first access point to report the channel characteristics. In this way, the second access point performs comprehensive scheduling of the connected access points, and the first access point does not need to determine whether to send channel characteristics, thus reducing processing resources.

[0011] In one alternative approach, before determining the channel parameters based on channel-related information and the channel parameter determination model, the first access point detects that the change in the channel-related information meets the condition for re-determining the channel parameters. In this way, after the channel changes, the channel parameters can be re-determined in a timely manner, making the channel parameters more compatible with the environment.

[0012] In one alternative approach, channel-related information includes one or more of channel information, air interface information, or service information. Since channel information directly reflects channel conditions, using channel information to determine channel parameters can improve the accuracy of the determination. Furthermore, since both air interface information and service information can indirectly reflect channel conditions, using either air interface information or service information to determine channel parameters can improve the accuracy of the channel parameters.

[0013] In one alternative approach, channel characteristics include one or more of the following: signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics. Since these factors are all closely related to network performance, using them to determine channel parameters enables the identification of channel parameters that meet network performance requirements.

[0014] In one alternative approach, channel characteristics may also include one or more of signal-to-noise ratio (SNR), throughput, or signal-to-interference-plus-noise ratio (SINR). Since these factors are all closely related to network performance, using them to determine channel parameters can identify those that meet network performance requirements.

[0015] In one alternative approach, channel parameters include channel-level parameters and / or air interface-level parameters. Since these parameters need to be adaptively adjusted according to the environment and channel to optimize air interface transmission, they are closely related to network performance, and using these parameters for communication can improve network performance.

[0016] Secondly, this application provides a method for determining channel parameters. This method is applied to a second access point in a wireless network, which is connected to other access points in the wireless network. The method includes: receiving channel features sent by a first access point among the other access points, wherein the channel features are determined based on channel-related information of a site associated with the first access point; determining, based on the channel features and a target parameter determination model, some or all channel parameters used by the first access point when communicating with the site, wherein the target parameter determination model is an AI model; and sending the some or all channel parameters to the first access point.

[0017] In the scheme presented in this application, when multiple access points are networked, the second access point acts as the primary access point, possessing stronger computing power, and determines some or all channel parameters for other access points. This conserves the processing resources of other access points.

[0018] In one alternative approach, the second access point further acquires channel features provided by at least one access point, wherein the at least one access point includes the second access point and / or other access points, and the channel features provided by the at least one access point are determined based on channel-related information of the sites associated with the at least one access point. When determining channel parameters for the first access point, the second access point determines some or all of the channel parameters based on the channel features transmitted by the first access point, the channel features provided by the at least one access point, and a target parameter determination model. Thus, when determining channel parameters for the first access point, the second access point also refers to the channel features provided by other access points, thereby improving the accuracy of the channel parameters from a global perspective and ultimately enhancing network performance.

[0019] In one alternative approach, the second access point determines some or all of the channel parameters to be used when communicating with sites associated with the at least one access point, based on the channel characteristics sent by the first access point, the channel characteristics provided by the at least one access point, and a target parameter determination model. If the at least one access point includes other access points, the second access point sends the determined partial or all of the channel parameters to the at least one access point. In this way, the second access point, when determining channel parameters for each access point, also refers to the channel characteristics provided by other access points, thus improving the accuracy of the channel parameters from a global perspective and thereby enhancing network performance.

[0020] In one alternative approach, when the at least one access point includes the second access point, obtaining the channel features provided by the at least one access point includes: obtaining channel-related information of the site associated with the second access point; and determining the channel features corresponding to the site associated with the second access point based on the channel-related information of the site associated with the second access point and a channel awareness model, wherein the channel awareness model is an AI model. Thus, using an AI model to extract channel features enables rapid acquisition of channel features.

[0021] In one alternative approach, before receiving the channel characteristics sent by the first access point among the other access points, the method further includes: broadcasting an AI computing enable message, wherein the AI ​​computing enable message is used to instruct the other access point to report the channel characteristics.

[0022] In one alternative approach, the channel-related information includes one or more of channel information, air interface information, or service information.

[0023] In one alternative approach, the channel characteristics include one or more of the following: signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics.

[0024] The effects of some of the optional methods in the second aspect are described in the first aspect.

[0025] Thirdly, this application provides a channel parameter determination apparatus, which has the function of implementing the first aspect or any optional method of the first aspect described above. The apparatus includes at least one module for implementing the method provided by the first aspect or any optional method of the first aspect.

[0026] Fourthly, this application provides a channel parameter determination apparatus, which has the function of implementing the second aspect or any optional method of the second aspect described above. The apparatus includes at least one module for implementing the method provided by the second aspect or any optional method of the second aspect.

[0027] Fifthly, this application provides an access point, which includes a processor, a memory, and a communication interface. The processor is used to execute program instructions in the memory to implement the method provided in the first aspect or any optional method of the first aspect. The communication interface is used to communicate with other devices (such as other access points or sites).

[0028] In a sixth aspect, this application provides an access point, which includes a processor, a memory, and a communication interface; the processor is used to execute program instructions in the memory to implement the method provided in the second aspect or any of the optional methods of the second aspect, and the communication interface is used to communicate with other devices (such as other access points, optical line terminals (OLTs), or sites).

[0029] In a seventh aspect, this application provides a communication system, the communication system including a first access point and a second access point, the first access point being used to implement the method provided by the first aspect or any optional method of the first aspect, and the second access point being used to implement the method provided by the second aspect or any optional method of the second aspect.

[0030] Eighthly, this application provides a computer-readable storage medium storing at least one program instruction that is read by a processor to cause a first access point to perform the method provided in the first aspect or any alternative manner of the first aspect.

[0031] Ninthly, this application provides a computer-readable storage medium storing at least one program instruction that is read by a processor to cause a second access point to perform the method provided in the second aspect or any alternative manner of the second aspect.

[0032] In a tenth aspect, this application provides a computer program product including program instructions stored in a computer-readable storage medium. A processor of a first access point reads the program instructions from the computer-readable storage medium and executes the program instructions, causing the first access point to perform the method provided in the first aspect or any optional method of the first aspect.

[0033] Eleventhly, this application provides a computer program product including program instructions stored in a computer-readable storage medium. A processor at a second access point reads the program instructions from the computer-readable storage medium and executes the program instructions, causing the second access point to perform the method provided in the second aspect or any optional method of the second aspect. Attached Figure Description

[0034] Figure 1 This is a schematic diagram illustrating factors affecting network performance provided in an exemplary embodiment of this application;

[0035] Figure 2 This is a schematic diagram of packet detection parameters provided in an exemplary embodiment of this application;

[0036] Figure 3 This is a schematic diagram illustrating an application scenario provided by an exemplary embodiment of this application;

[0037] Figure 4 This is a schematic diagram of the architecture of a fiber to the room (FTTR) network provided in an exemplary embodiment of this application;

[0038] Figure 5 This is a schematic diagram of the structure of an access point provided in an exemplary embodiment of this application;

[0039] Figure 6 This is a schematic diagram of another structure of the access point provided in an exemplary embodiment of this application;

[0040] Figure 7 This is a schematic flowchart of a method for determining channel parameters provided in an exemplary embodiment of this application;

[0041] Figure 8 This is a schematic diagram of a channel parameter determination stage provided in an exemplary embodiment of this application;

[0042] Figure 9 This is a schematic diagram of a channel parameter determination framework provided in an exemplary embodiment of this application;

[0043] Figure 10 This is a schematic flowchart of a method for determining channel parameters provided in an exemplary embodiment of this application;

[0044] Figure 11 This is a schematic diagram of access point interaction provided in an exemplary embodiment of this application;

[0045] Figure 12 This is another schematic diagram of the method flow for determining channel parameters provided in an exemplary embodiment of this application;

[0046] Figure 13 This is yet another schematic diagram of a method flow for determining channel parameters provided in an exemplary embodiment of this application;

[0047] Figure 14 This is a schematic diagram illustrating AI model training provided in an exemplary embodiment of this application;

[0048] Figure 15 This is a schematic diagram of a channel parameter determination device provided in an exemplary embodiment of this application;

[0049] Figure 16 This is another schematic diagram of the structure of a channel parameter determination device provided in an exemplary embodiment of this application;

[0050] Figure 17 This is a schematic diagram of the structure of a device provided in an exemplary embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0052] The following explains some terms and concepts involved in the embodiments of this application.

[0053] 1. Machine learning is a method for achieving artificial intelligence. Its goal is to design and analyze algorithms (i.e., models) that allow computers to automatically "learn." These designed algorithms are called machine learning models. Machine learning models are algorithms that automatically analyze data to obtain patterns and use these patterns to predict unknown data. Machine learning models are diverse. Based on whether the model training depends on the labels corresponding to the training data, machine learning models can be divided into: 1. Supervised learning models: Supervised learning models depend on the labels corresponding to the training data; 2. Unsupervised learning models: Unsupervised learning models do not depend on the labels corresponding to the training data.

[0054] 2. Reinforcement learning is a special field in machine learning. It is a process in which an agent continuously learns the optimal policy, makes sequential decisions, and obtains the maximum reward through the interaction between the agent and the environment.

[0055] In layman's terms, reinforcement learning is about learning "what to do (i.e., how to map the current situation into actions) to maximize the numerical reward signal." The agent is not told what actions to take, but must discover on its own which actions will produce the greatest reward through trial and error.

[0056] Reinforcement learning differs from supervised and unsupervised learning in machine learning. Supervised learning is the process of learning from externally provided labeled training data (task-driven), while unsupervised learning is the process of finding hidden structures in unlabeled data (data-driven). Reinforcement learning is a process of finding better solutions through trial and error. The agent must develop existing experience to gain benefits, while also making trials to obtain a better space of action choices in the future (i.e., learning from mistakes).

[0057] 3. Deep learning is a new technological field that emerged during the research of machine learning. Specifically, deep learning is a method in machine learning based on deep representation learning of data. Deep learning interprets data by building neural networks that simulate the human brain to analyze and learn.

[0058] The background of the embodiments of this application is described below.

[0059] In wireless networks, access point deployment location, antenna directionality, and changes in environment and interference can cause network performance fluctuations. Simulations show that network performance fluctuations are at least 30%. Figure 1 As shown. For example, network performance includes, but is not limited to, throughput.

[0060] Antenna directivity refers to the different radiation and reception capabilities of an antenna in different directions in space. Therefore, the antenna direction can be adjusted to improve radiation or reception capabilities. Environmental factors mainly manifest in channel effects, including site movement, and reflection and diffraction of radio frequency signals during transmission. Interference mainly manifests as air interface contention among multiple sites. All of these factors can be reflected in channel parameters; therefore, appropriate channel parameters must be used during communication. In one scheme, such as... Figure 2 As shown, when determining each channel parameter, the AP sends probe data packets. Based on the transmission and reception of these probe data packets, the channel parameters are determined. Figure 2The documentation provides a procedure for setting parameter 1. However, due to the large number of channel parameters, determining each parameter through a packet probing mechanism may not be quick enough to find a suitable value. For example, taking Wi-Fi 7 2x2 multiple-input multiple-output (MIMO) as an example, the channel parameters include 4 types of diversity antennas, 4 types of bandwidth (BW), 2 types of spatial streams (SS), 13 types of modulation and coding schemes (MCS), more than 10 types of transmit power codes (TPC), more than 3 types of precoding methods, and more than 10 types of air interface contention parameters. Relying solely on traversal methods makes it virtually impossible to quickly reach the optimal solution.

[0061] Based on this, embodiments of this application provide a method for determining channel parameters. In this method, channel-related information is used in conjunction with an AI model to quickly obtain channel parameters without having to traverse them one by one. Therefore, it is possible to quickly obtain relatively good channel parameters.

[0062] The application scenarios of the embodiments of this application are described below.

[0063] In one application scenario, a wireless network includes an access point. This wireless network can be a fiber-to-the-home (FTTH) network, and the access point can be an optical network terminal (ONT) or an optical network unit (ONU), or it can be a gateway or router, etc. An AI model is deployed on this access point, and this AI model is used to determine channel parameters.

[0064] In another application scenario, the wireless network comprises multiple access points, forming a network. One of these access points is connected to other access points via fiber optic cables, network cables, power lines, or wirelessly. Each access point deploys an identical AI model, and each access point independently determines channel parameters using its AI model. For example, this application scenario could be an FTTR network.

[0065] Alternatively, the multiple access points may include a primary access point, which is connected to other access points via fiber optic cable, network cable, power line, or wireless connection. These other access points are secondary access points, and there may be one or more of them. The primary access point may be designated as the primary access point during deployment, or it may be selected through negotiation among the multiple access points after they have been deployed and are online. For example, the multiple access points may include a first access point, a second access point, and a third access point, such as... Figure 3 As shown in (a), the network consisting of multiple access points is an FTTR network. The second access point is the main FTTR unit (MFU), and the first and third access points are sub-FTTR units (SFU). Sub-FTTR units are also called FTTR sub-devices. The MFU is also called the main optical network unit (MFU), and the SFU is also called the sub-optical network unit (SFU). The second access point is connected to the first and third access points through an optical distribution network (ODN). Figure 3 As shown in (b), the second access point is connected to the first access point via optical fiber, network cable or power line, and the second access point is connected to the third access point via optical fiber, network cable or power line.

[0066] Optionally, the above Figure 3 In (a), an FTTR network can be deployed in a home and is considered a home FTTR network, or it can be deployed in an enterprise and is considered an enterprise FTTR network.

[0067] It should be noted that among multiple access points, the second access point may use the same connection method as the other access points, or the second access point may use different connection methods when connecting to the other access points. For example, the multiple access points include a first access point, a second access point, and a third access point. The second access point is connected to the first access point via fiber optic cable, and the second access point is connected to the third access point via wireless cable.

[0068] Figure 4 This is a schematic diagram of an FTTR network architecture. In an FTTR network, the master device acts as an ONT (Online Terminal Unit) in both FTTH (Fiber to the Headquarters) and FTTO (Fiber to the Office) networks, connecting to the optical line terminal via ODN (Optical Distribution Network). It also acts as an upstream device for the slave devices, managing them. Slave devices can be deployed in various rooms of a home or office to provide signal to user terminals. Slave devices possess ONT functionality and can also function as wireless access points.

[0069] In an FTTR network, multiple slave devices can be deployed, each connected to the master device via an optical splitter. The master device can manage and configure all slave devices centrally. The master device can also be called a "master gateway," "master optical modem," or "master FTTR device," and the slave devices can also be called "slave gateways," "slave optical modems," or "slave FTTR devices," etc.

[0070] The execution subject of the embodiments of this application is described below.

[0071] The entity executing the method for determining channel parameters is a device for determining channel parameters. Optionally, this device is a hardware device, such as an access point. Optionally, this device is a software device, such as a software program running on the hardware device.

[0072] Optionally, the access point includes a Wi-Fi communication chip and an AI core. The Wi-Fi communication chip can be understood as a single board. It is used to collect channel-related information (mentioned later) and perform Wi-Fi communication processing using channel parameters. The AI ​​core is used to determine the channel characteristics and parameters (mentioned later). The interface between the Wi-Fi communication chip and the AI ​​core can be used to transmit channel-related information and parameters, etc. See one example. Figure 5 The Wi-Fi communication chip is a system-on-a-chip (SoC), and the AI ​​core is integrated on top of the Wi-Fi communication chip. See another example. Figure 6 The Wi-Fi communication chip and the AI ​​core are two separate chips.

[0073] The following describes the process for determining channel parameters.

[0074] 1. First, describe the method and process for the access point to independently determine channel parameters. See [link to documentation]. Figure 7 Steps 701 to 702 are explained using the determination of channel parameters at the first access point as an example. Figure 7 The process is applied to scenarios where a wireless network includes one access point, or a wireless network includes multiple access points, each of which independently determines its channel parameters.

[0075] Step 701: Obtain channel-related information of the site associated with the first access point.

[0076] The sites associated with the first access point refer to sites that use the wireless network service provided by the first access point, or sites that connect to the first access point. These sites include, but are not limited to, mobile phones, tablets, laptops, or smart home devices.

[0077] In this embodiment, the first access point periodically collects channel-related information of the sites associated with it, or collects such information in response to a triggered condition. For each site associated with the first access point, the first access point can obtain the channel-related information of that site. The period can be set based on empirical values. The triggered condition includes, but is not limited to, network performance degradation or a decrease in signal-to-noise ratio.

[0078] In one alternative approach, the first access point includes a Wi-Fi communication chip for communicating with the site. This Wi-Fi communication chip collects channel-related information.

[0079] In one alternative approach, for each site, the channel-related information of that site may include one or more of channel information, air interface information, or service information.

[0080] This section uses the channel-related information of the target site associated with the first access point as an example. Referring to Table 1, this channel information includes one or more of the following: Channel State Information (CSI), Received Signal Strength Indication (RSSI), bandwidth, number of SS (Spatial Streams), or MCS (Multi-Path Fading). CSI describes the signal attenuation factor on each transmission path, including but not limited to channel gain, phase information, or multi-path fading information. RSSI refers to the signal strength received by the first access point from the target site. Bandwidth refers to the bandwidth used by the first access point to communicate with the target site, such as 20MHz or 40MHz. The number of SS refers to the number of spatial streams used by the first access point to communicate with the target site. MCS refers to the modulation and coding scheme used by the first access point to communicate with the target site.

[0081] Air interface information includes one or more of the following: air interface occupancy, interference duty cycle, signal-to-noise ratio (SNR), or enhanced distributed channel access (EDCA) information. Air interface occupancy is the ratio of the amount of data transmitted by the access point to the target site using the air interface to the total amount of data transmitted. Interference duty cycle indicates the magnitude of air interface interference from other sites to the target site over a period of time. EDCA information is the congestion avoidance mechanism used by the target site in the wireless network.

[0082] The service information includes the packet error ratio (PER) and / or retransmission rate. The packet error ratio refers to the rate of error in Media Access Control Protocol (MPDU) data units (MPDUs) sent from the target site to the first access point, which is equal to the number of MPDUs transmitted incorrectly within a certain period divided by the total number of MPDUs sent from the target site to the first access point. The retransmission rate refers to the retransmission rate of MPDUs sent from the first access point to the target site, which is equal to the number of retransmitted MPDUs within a certain period divided by the total number of MPDUs sent from the first access point to the target site.

[0083] The time period mentioned above can be a cycle for acquiring channel-related information, or it can be other custom durations.

[0084] Table 1

[0085] Channel information air interface information Business Information CSI air interface occupancy rate PER RSSI Interference duty cycle retransmission rate Number of SS SNR … MCS EDCA Information … bandwidth … …

[0086] It should be noted that Table 1 is merely an example of channel-related information. The selection of the aforementioned channel-related information is related to the channel parameters to be determined, and this application does not limit the specific channel-related information.

[0087] Step 702: Based on the channel-related information and channel parameter model, send the channel parameters used by the first access point when communicating with the station to the station, wherein the channel parameter model is an AI model.

[0088] In this embodiment, the first access point inputs channel-related information into the channel parameter model, which outputs the channel parameters used by the first access point when communicating with each associated site, i.e., the channel parameters of each site. For each site, the first access point sends the site's channel parameters to the site, thus ensuring that the channel parameters used by both the first access point and the site are consistent.

[0089] Each site has its own channel parameters, which the first access point uses to communicate with the site. For example, the sites associated with the first access point include site 1 and site 2. Site 1 corresponds to channel parameter 1, and site 2 corresponds to channel parameter 2, as shown in Table 2.

[0090] Table 2

[0091] Site logo Channel parameters Site 1 Channel parameter 1 Site 2 Channel parameter 2

[0092] For each site, the channel parameters include channel-level parameters and / or air interface-level parameters. Channel-level parameters refer to parameters related to the channel, while air interface-level parameters refer to parameters related to the air interface, as shown in Table 3. Channel-level parameters include one or more of the following: TPC, antenna selection, bandwidth, MCS, number of SS, or precoding scheme. TPC refers to Transmit Power Codeword, used to adjust the signal transmit power. Antenna selection indicates the antenna directivity. Bandwidth adjusts the service bandwidth, for example, a bandwidth of 40MHz. MCS indicates the MCS used when the first access point communicates with the site. The number of SS indicates the number of MIMO streams. Precoding schemes include cyclic delay diversity (CSD) or beamforming (BF), etc. CSD is a transmit diversity technique that increases signal diversity by introducing cyclic shifts between multiple transmit antennas, thereby improving signal transmission reliability without increasing the number of antennas. Beamforming (BF) is a technique that controls the directional transmission of signals using multiple antenna arrays. Specifically, it involves adjusting the phase and amplitude of each antenna to enhance the signal in a specific direction and weaken it in other directions, thus achieving directional signal transmission. In this precoding method, beamforming can also be obtained not from an AI model, but by sending null data packets (NDPs). NDPs are used for channel detection during beamforming; they are empty data packets without data but contain pilot signals for calculating channel information. After receiving the NDP, the station can estimate the channel information based on the pilot signals and feed it back to the access point to obtain the precoding method.

[0093] Air interface level parameters include one or more of the following: EDCA information, request to send / clear to send (RTS / CTS) information, or MPDU aggregation parameters. Among them, EDCA information and RTS / CTS are generally used together to avoid air interface data transmission conflicts, while MPDU aggregation parameters are used to adjust the size of the transmitted MPDU.

[0094] Table 3

[0095] Channel-level parameters Air interface level parameters TPC EDCA Information Antenna Selection RTS / CTS Information bandwidth MPDU polymerization parameters MCS … Number of SS … Precoding method …

[0096] In one alternative approach, the first access point may use a broadcast method when distributing the channel parameters of the site.

[0097] In one alternative approach, when the first access point sends channel parameters to the station, it can send all channel parameters directly, or it can send only the channel parameters that have changed, while omitting the channel parameters that have not changed. This way, when sending all channel parameters, the station can directly obtain all channel parameters, saving station processing resources; and when sending changed channel parameters, it can save transmission resources.

[0098] In one alternative approach, in step 702, the channel parameter model may include an AI model whose input is channel-related information and whose output is channel parameters. It may also include two AI models: a channel-aware model and a first parameter determination model. The channel-aware model is essentially a feature extraction model, whose input is channel-related information and whose output is channel features. The first parameter determination model takes the channel features as input and outputs channel parameters. The channel-aware model includes, but is not limited to, neural network models such as linear regression and prediction, convolutional neural networks (CNNs), or deep neural networks (DNNs). The first parameter determination model is obtained through machine learning, deep learning, or reinforcement learning.

[0099] For each site associated with the first access point, the first access point inputs the channel-related information of that site into the channel-aware model, and the channel-aware model outputs the channel characteristics corresponding to that site. Alternatively, the first access point inputs the channel-related information of all sites it has acquired into the channel-aware model, and the channel-aware model outputs the channel characteristics corresponding to each of those sites.

[0100] Then, the first access point inputs the channel characteristics corresponding to all the stations into the first parameter determination model, and the first parameter determination model outputs the channel parameters of each station among all the stations. In this way, when determining the channel parameters for each station, the first parameter determination model comprehensively considers the channel characteristics corresponding to each station, so that the determined channel parameters are more closely matched with the current environment.

[0101] Optionally, channel characteristics are features extracted from channel-related information. Referring to Table 4, channel characteristics include, but are not limited to, one or more of the following: signal strength, multipath delay, mobility characteristics, air interface interference messages, or frequency attenuation characteristics. Signal strength is the average strength of the signal transmitted by the first access point receiving the station, which can be obtained using RSSI. Multipath delay refers to the delay of signal transmission on multiple paths, including paths where the first access point directly receives the signal when transmitting it to the station, and paths where the signal is received after reflection or diffraction. Mobility characteristics indicate whether the station has moved. Frequency attenuation characteristics refer to the destructive and constructive characteristics of signal transmission frequency, specifically including line-of-sight (LOS) and / or non-line-of-sight (NLOS) frequency attenuation characteristics. Air interface interference messages include interference duty cycle and / or EDCA.

[0102] Optionally, referring to Table 4, channel characteristics also include one or more of the following: signal-to-noise ratio (SNR), throughput, or signal-to-interference-plus-noise ratio (SINR). SNR is equal to the ratio of signal power to noise power. Throughput refers to the maximum transmission rate supported by the first access point on the uplink and downlink (uplink is the link from the site to the first access point, and downlink is the link from the first access point to the site). SINR is the ratio of signal power to the sum of interference and noise power.

[0103] Table 4

[0104]

[0105] Optionally, before inputting channel-related information into the channel-aware model, the channel-related information is preprocessed, including but not limited to data deduplication or normalization.

[0106] In one alternative approach, the first access point re-determines the channel parameters each time it acquires channel-related information. This is equivalent to first monitoring channel-related information, then determining the channel parameters (a learning process), and then continuing to monitor channel-related information. See [link to previous section]. Figure 8In another alternative approach, after acquiring channel-related information, the first access point can determine whether to re-determine the channel parameters. For example, for a given site, after acquiring the channel-related information, the first access point compares the acquired signal-related information with the previously acquired channel-related information. If the change in each parameter is within the corresponding specified range, the channel parameters for that site are not re-determined. If the change in at least one parameter exceeds the corresponding specified range in the degradation direction, the channel parameters for that site are re-determined. In other words, if the change in amplitude meets the condition for re-determining the channel parameters, step 702 is executed; otherwise, channel-related information continues to be acquired periodically to determine whether to execute step 702. Thus, compared to the previous approach, after monitoring channel-related information, a determination is made regarding whether to re-determine the channel parameters.

[0107] Here, if the channel-related information change of any station on the first access point meets the condition for re-determining the channel parameters, step 702 is executed. This can be either re-determining only the channel parameters of that station or re-determining the channel parameters of all stations.

[0108] Optionally, the channel parameter model can be trained offline and then deployed to the first access point.

[0109] against Figure 7 The process shown is as follows: Figure 9 It also provides a schematic diagram illustrating the interaction between the Wi-Fi communication chip and the AI ​​core. (Corresponding...) Figure 9 It also provides a flowchart of the overall channel parameter determination process, such as Figure 10 As shown, empty data packet transmission refers to the Wi-Fi communication chip sending NDP, channel-related information reporting refers to the Wi-Fi communication chip reporting channel-related information to the AI ​​core, and channel parameter delivery refers to the AI ​​core sending channel parameters to the Wi-Fi communication chip, enabling the Wi-Fi communication chip to communicate with the station using the channel parameters.

[0110] 2. The following describes the method for collaboratively determining channel parameters when multiple access points are networked. In this method, the wireless network includes multiple access points, with the second access point serving as the primary access point and the other access points acting as secondary access points, connected to the second access point via fiber optic cables, network cables, power lines, or wirelessly. When the primary and secondary access points collaboratively determine the channel parameters, a portion of the AI ​​model is deployed on both the primary and secondary access points, such as... Figure 11As shown, the AI ​​model is deployed in a distributed manner across multiple access points. Generally, the primary access point has stronger computing power and is used to determine its own channel parameters and the overall scheduling of the primary and secondary access points. Compared to the primary access point, the secondary access points have weaker computing power and are used to extract channel features and determine some of their own channel parameters or only extract channel features. This explanation uses other access points, including the first access point, as an example.

[0111] See the flowchart for this method. Figure 12 Steps 1201 to 1209 are as follows: Figure 12 This example illustrates how a primary access point determines a subset of channel parameters from a secondary access point. The primary access point is equipped with a channel-aware model and a target parameter determination module. The secondary access points are equipped with a channel-aware model and a second parameter determination module. The second parameter determination module is part of the first parameter determination model mentioned earlier. The input to the second parameter determination model is the channel characteristics corresponding to multiple sites associated with the first access point, and the output is the channel parameters used by the first access point when communicating with each associated site. The target parameter determination model can be the first parameter determination model, or it can be more powerful than the first parameter determination model, comprehensively considering the channel characteristics reported by multiple access points, and its output is the channel parameters used by the access point when communicating with each associated site.

[0112] Step 1201: The first access point obtains channel-related information of each associated site.

[0113] Step 1202: The first access point determines the channel characteristics corresponding to each site based on the channel-related information and the channel awareness model.

[0114] The processing of steps 1201 and 1202 is described above and will not be repeated here.

[0115] Step 1203: The first access point determines a portion of the channel parameters for each site based on the channel characteristics corresponding to each site and the second parameter determination model.

[0116] In this embodiment, the first access point inputs the channel characteristics corresponding to each site into the second parameter determination module, and the second parameter determination model outputs a portion of the channel parameters of each site.

[0117] Step 1204: The first access point sends the channel characteristics corresponding to each station to the second access point.

[0118] In this embodiment, the first access point sends all the determined channel features to the second access point, or sends a portion of the channel features, which is used to determine another portion of the channel parameters of each station.

[0119] Steps 1203 and 1204 are not in any particular order.

[0120] Step 1205: The second access point receives the channel characteristics sent by the first access point.

[0121] Step 1206: The second access point determines another part of the channel parameters of each station based on the channel characteristics and target parameters determined by the first access point.

[0122] In this embodiment, after receiving the channel features sent by the first access point, the second access point inputs the channel features into the target parameter determination model. The target parameter determination model outputs another part of the channel parameters, or all of the channel parameters, used by the first access point when communicating with the associated stations.

[0123] Optionally, for each site, the other portion of channel parameters includes one or more of bandwidth, TPC, or EDCA information. A portion of the channel parameters in step 1203 consists of the channel parameters mentioned above, excluding this other portion of channel parameters.

[0124] Step 1207: The second access point sends the other part of the channel parameters to the first access point.

[0125] Step 1208: The first access point receives the other part of the channel parameters.

[0126] Step 1209: The first access point sends channel parameters to the associated sites. For each site, the first access point will subsequently use the channel parameters of that site to communicate with it.

[0127] In this embodiment, the first access point can broadcast the channel parameters of each station. These channel parameters can be all the channel parameters of each station or the channel parameters that have changed.

[0128] exist Figure 12 In one implementation, the second access point uses the channel features reported by the first access point to determine some channel parameters of the sites associated with the first access point. In another implementation, the channel parameter extraction model in the first access point is only used to extract channel features, and the channel parameters of the sites are all determined by the second access point. In yet another implementation, when determining the channel parameters of the sites associated with the first access point, the second access point also considers channel features provided by other access points; see [link to relevant documentation]. Figure 13 Steps 1301 to 1308 in the illustrated process. Figure 13 The following example illustrates the interaction between the primary access point and two secondary access points.

[0129] Step 1301: The main access point broadcasts an AI computing enable message.

[0130] In this embodiment, the main access point periodically broadcasts AI computing enable messages, or broadcasts AI computing enable messages when it detects a new associated site from the access point or the main access point.

[0131] Step 1302: Each access point receives an AI computing enable message.

[0132] Step 1303: Each access point obtains channel-related information of the associated site, and determines the channel characteristics based on the channel-related information and the channel awareness model.

[0133] The processing procedure for step 1303 is described above and will not be repeated here.

[0134] Step 1304: Each access point sends channel characteristics to the main access point.

[0135] Step 1305: The primary access point receives the channel characteristics sent by each secondary access point.

[0136] Step 1306: The master access point determines the channel parameters of the sites associated with each access point based on the channel characteristics sent by each slave access point, its own determined channel characteristics, and the target parameter determination model.

[0137] In this embodiment, the primary access point inputs the first channel feature and the second channel feature into the target parameter determination model. The target parameter determination model outputs the channel parameters of each site associated with each access point. Here, it can be all the channel parameters of each associated site, or it can be a partial channel parameter. The first channel feature includes the channel features sent from each access point, and the second channel feature is the channel feature determined by the primary access point.

[0138] Step 1307: The primary access point broadcasts the channel parameters of each site associated with the secondary access point.

[0139] In this embodiment, when all channel parameters are determined in step 1306, if no channel parameters are determined from the access point, all channel parameters are broadcast; if only some channel parameters are determined from the access point, only the other part of the channel parameters can be broadcast.

[0140] Alternatively, the primary access point can broadcast only the portion of the channel parameters that have changed, thus saving transmission resources.

[0141] Step 1308: Each access point receives and broadcasts the channel parameters of the associated stations.

[0142] It should be noted that if the channel parameters broadcast by the primary access point overlap with the channel parameters determined by the secondary access point, the secondary access point shall take priority over the channel parameters broadcast by the primary access point.

[0143] exist Figure 13 The example given is the primary access point broadcasting an AI computing enable message. In another implementation, if the secondary access point detects a change in channel-related information that satisfies the condition for re-determining channel parameters, it can also proactively send channel characteristics to the primary access point, which will then re-determine the channel parameters. Yet another implementation combines the first two approaches.

[0144] exist Figure 12 and Figure 13 The concepts of channel-related information, channel characteristics, and channel parameters are described above. Channel parameters and AI computation enable messages are transmitted in the broadcast frame format of the Passive Optical Network (PON) protocol, while channel characteristics are transmitted in the data frame format of the PON protocol. Alternatively, other methods can be used, such as proprietary protocols or over-the-air communication.

[0145] In this embodiment of the application, the channel parameter model is obtained by a training device through machine learning. The training device can be a local computing device or a cloud device.

[0146] The training device performs supervised training (or supervised learning) to obtain the channel-aware model. The process is as follows: Figure 14 As shown, the training device acquires a training dataset and an initial channel-aware model. The training dataset includes multiple channel-related information items and the corresponding channel features for each item. The channel features are labels for the channel-related information items. The training device uses a portion of the channel-related information items from the training dataset along with their corresponding labels to determine the parameters of the initial channel-aware model. Then, it uses another portion of the channel-related information items from the training dataset along with their corresponding labels to test the channel-aware model, thereby obtaining the final channel-aware model.

[0147] Alternatively, the training device can perform unsupervised training (or unsupervised learning) to obtain the channel-aware model. The process is as follows: the training device acquires a training dataset and an initial channel-aware model. The training dataset includes multiple channel-related information items. The training device uses the channel-related information items in the training dataset to discover meaningful information and correlations within these items, thereby obtaining the parameters of the initial channel-aware model.

[0148] The training device can obtain a parameter-determining model through machine learning. This parameter-determining model can be any of the parameter-determining models mentioned above, and the training device can employ supervised training. The process is as follows: Figure 14As shown, the training device acquires a training dataset and an initial parameter determination model. The training dataset includes multiple channel features and the corresponding channel parameters for each channel feature; the channel parameters are the labels of the channel features. The training device uses a subset of the channel features and their corresponding labels from the training dataset to determine the parameters of the initial parameter determination model. Then, it uses another subset of the channel features and their corresponding labels from the training dataset to test the parameter determination model, thus obtaining the final parameter determination model.

[0149] The training device can also employ unsupervised training. The process is as follows: the training device acquires the training dataset and determines the initial parameters of the model. The training dataset includes multiple channel features. The training device uses the channel features in the training dataset to discover meaningful information and correlations within the channel features, thereby obtaining the parameters of the model based on the initial parameters.

[0150] The training device can also obtain parameters to determine the model through reinforcement learning. The embodiments of this application do not limit the implementation process of reinforcement learning.

[0151] This is merely a possible implementation method, and the embodiments of this application do not limit the training method. For example, when the access point has strong capabilities, the channel parameter model can also be obtained by training the access point.

[0152] In this embodiment, after the access point and the site communicate using the newly determined channel parameters, they collect channel-related information when using those parameters. If at least one of the following conditions is met among the multiple collections of channel-related information: a high packet error rate, a high retransmission rate, or a poor signal-to-noise ratio, the collected channel-related information and the adopted channel parameters are uploaded to the training device. The training device then updates the channel parameter model based on this data to obtain an updated model, which is then sent back to the access point. This allows for timely model updates, making the model more compatible with the environment.

[0153] In this embodiment, an AI model is used to determine channel parameters, enabling the determination of all channel parameters at once without sending probe data to determine them one by one. This improves the efficiency of channel parameter determination. Furthermore, by collecting channel-related information during parameter determination, the system comprehensively reflects channel characteristics, enabling white-box analysis of air interface quality. This allows the determined channel parameters to better match the environment, thereby improving network throughput.

[0154] Furthermore, in a network with multiple access points, the distributed deployment of AI models allows the more powerful primary access point to perform computationally demanding tasks, reducing the computational load on secondary access points. Moreover, the primary access point can acquire channel characteristics extracted from each access point, enabling a global consideration when determining channel parameters. This results in more suitable channel parameters for the environment, improving network throughput and reducing latency.

[0155] Figure 15 This is a structural diagram of the channel parameter determination device provided in the embodiments of this application. Figure 15 The illustrated device can be implemented as part or all of the apparatus through software, hardware, or a combination of both. This device is applied to a first access point and is used to implement the method flow executed by the first access point in the embodiments of this application. For example... Figure 15 As shown, the device includes: an acquisition module 1510 and a parameter determination module 1520; wherein,

[0156] The acquisition module 1510 is used to acquire channel-related information of the site associated with the first access point;

[0157] The parameter determination module 1520 is used to send the channel parameters used by the first access point when communicating with the station, based on the channel-related information and the channel parameter model, wherein the channel parameter model is an AI model.

[0158] In one alternative approach, the channel parameter model includes a channel-aware model and a first parameter determination model;

[0159] The parameter determination module 1520 is used for:

[0160] Based on the channel-related information and the channel-aware model, the channel characteristics corresponding to the station are determined;

[0161] Based on the channel characteristics and the first parameter determination model, the channel parameters used by the first access point when communicating with the station are sent to the station.

[0162] In one optional embodiment, the channel parameter model includes a channel-aware model and a second parameter determination model; the parameter determination module 1520 is configured to: determine the channel characteristics corresponding to the site based on the channel-related information and the channel-aware model; determine a portion of the channel parameters based on the channel characteristics and the second parameter determination model; send the channel characteristics to a second access point; receive another portion of the channel parameters sent by the second access point; and send the channel parameters to the site; or...

[0163] The parameter determination module 1520 is used to determine the channel characteristics corresponding to the site based on the channel-related information and the channel awareness model; send the channel characteristics to the second access point; receive the channel parameters sent by the second access point; and send the channel parameters to the site.

[0164] In an alternative embodiment, the parameter determination module 1520 is further configured to receive an AI computation enable message sent by the second access point before sending the channel features to the second access point, wherein the AI ​​computation enable message is used to instruct the first access point to report the channel features.

[0165] In an alternative embodiment, the acquisition module 1510 is further configured to detect that the change magnitude of the channel-related information satisfies the condition for re-determining the channel parameters before sending the channel parameters used by the first access point when communicating with the station based on the channel-related information and the channel parameter model.

[0166] In one alternative approach, the channel-related information includes one or more of channel information, air interface information, or service information.

[0167] In one alternative approach, the channel characteristics include one or more of signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics.

[0168] In one alternative approach, the channel characteristics may further include one or more of signal-to-noise ratio, throughput, or signal-to-interference-plus-noise ratio.

[0169] In one alternative approach, the channel parameters include channel-level parameters and / or air interface-level parameters.

[0170] Figure 16 This is a structural diagram of the channel parameter determination device provided in the embodiments of this application. Figure 16 The illustrated device can be implemented as part or all of the apparatus through software, hardware, or a combination of both. This device is applied to a second access point and is used to implement the method flow executed by the second access point in the embodiments of this application. For example... Figure 16 As shown, the device includes: a communication module 1610 and a determination module 1620; wherein,

[0171] The communication module 1610 is used to receive channel features sent by the first access point among the other access points, wherein the channel features are determined based on channel-related information of the site associated with the first access point;

[0172] The determining module 1620 is used to determine, based on the channel characteristics and the target parameter determining model, some or all of the channel parameters used by the first access point when communicating with the site, wherein the target parameter determining model is an artificial intelligence (AI) model;

[0173] The communication module 1610 is also used to send some or all of the channel parameters to the first access point.

[0174] In an alternative embodiment, the determining module 1620 is further configured to acquire channel features provided by at least one access point, wherein the at least one access point includes the second access point and / or one of the other access points, and the channel features provided by the at least one access point are determined based on channel-related information of the site associated with the at least one access point;

[0175] The determining module 1620 is used to determine some or all of the channel parameters based on the channel characteristics sent by the first access point, the channel characteristics provided by the at least one access point, and the target parameter determining model.

[0176] In an optional manner, the determining module 1620 is further configured to determine, based on the channel characteristics sent by the first access point, the channel characteristics provided by the at least one access point, and the target parameter determining model, some or all of the channel parameters used by the at least one access point when communicating with the site associated with the at least one access point.

[0177] The communication module 1610 is further configured to, when the at least one access point includes an access point among the other access points, send to the at least one access point some or all of the channel parameters determined for the at least one access point.

[0178] In an alternative embodiment, if the at least one access point includes the second access point, the determining module 1620 is further configured to:

[0179] Obtain channel-related information of the site associated with the second access point;

[0180] Based on the channel-related information and channel awareness model of the site associated with the second access point, the channel characteristics corresponding to the site associated with the second access point are determined, wherein the channel awareness model is an AI model.

[0181] In an alternative embodiment, the communication module 1610 is further configured to broadcast an AI computing enable message before receiving channel characteristics sent by the first access point among the other access points, wherein the AI ​​computing enable message is used to instruct the other access points to report channel characteristics.

[0182] In one alternative approach, the channel-related information includes one or more of channel information, air interface information, or service information.

[0183] In one alternative approach, the channel characteristics include one or more of signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics.

[0184] In one alternative approach, the channel characteristics may further include one or more of signal-to-noise ratio, throughput, or signal-to-interference-plus-noise ratio.

[0185] In one alternative approach, the channel parameters include channel-level parameters and / or air interface-level parameters.

[0186] Figure 15 and Figure 16 For a detailed explanation of the process by which the device determines the channel parameters, please refer to the descriptions in the preceding embodiments; they will not be repeated here. Figure 15 The device shown can be the first access point mentioned above. Figure 16 The device shown can be the second access point mentioned above.

[0187] This application also provides a device 100. For example... Figure 17 As shown, device 100 includes: bus 102, processor 104, memory 106, and communication interface 108. Processor 104, memory 106, and communication interface 108 communicate via bus 102. Device 100 is the access point mentioned above. It should be understood that this application does not limit the number of processors and memories in device 100.

[0188] Bus 102 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 17 The bus 102 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 102 may include a path for transmitting information between various components of the device 100 (e.g., memory 106, processor 104, communication interface 108).

[0189] The processor 104 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0190] Memory 106 may include volatile memory, such as random access memory (RAM). Memory 106 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0191] The memory 106 stores executable program code, and the processor 104 executes the executable program code to determine the channel parameters as described above. That is, the memory 106 stores program instructions for executing the method for determining the channel parameters as described above.

[0192] The communication interface 108 is used to enable communication between the device 100 and other devices or communication networks. When the access point is an ONT, the communication interface 108 can be an optical module.

[0193] This application also provides a computer program product, which includes program instructions stored in a computer-readable storage medium. A processor of a first access point reads the program instructions from the computer-readable storage medium and executes the program instructions, causing the first access point to perform the channel parameter determination method described above.

[0194] This application also provides a computer program product, which includes program instructions stored in a computer-readable storage medium. The processor of the second access point reads the program instructions from the computer-readable storage medium and executes the program instructions, causing the second access point to perform the channel parameter determination process described above.

[0195] This application also provides a communication system, which includes the first access point and the second access point mentioned above.

[0196] Those skilled in the art will recognize that the method steps and units described in the embodiments disclosed in this application can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the steps and components of each embodiment have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0197] In the embodiments provided in this application, it should be understood that the disclosed system architecture, apparatus, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, or may be electrical, mechanical, or other forms of connection.

[0198] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0199] Furthermore, the modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or in software.

[0200] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0201] In this application, the terms "first" and "second," etc., are used to distinguish identical or similar items that have substantially the same function and purpose. It should be understood that there is no logical or temporal dependency between "first" and "second," nor does it limit the quantity or execution order. It should also be understood that although the following description uses the terms "first" and "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are merely used to distinguish one element from another. For example, without departing from the scope of the various examples, a first access point can be referred to as a second access point, and similarly, a second access point can be referred to as a first access point. Both a first access point and a second access point can be access points, and in some cases, they can be separate and distinct access points.

[0202] The phrase "at least one" in the preceding text can be understood as one or more.

[0203] The phrase "A and / or B" in the preceding text can be understood to include three cases: A, B, and A and B.

[0204] All channel-related information of the sites involved in this application is authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0205] The above description is merely an exemplary embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining channel parameters, characterized in that, The method is applied to a first access point in a wireless network, and the method includes: Obtain channel-related information of the site associated with the first access point; Based on the channel-related information and channel parameter model, the channel parameters used by the first access point when communicating with the station are sent to the station, wherein the channel parameter model is an artificial intelligence (AI) model.

2. The method according to claim 1, characterized in that, The channel parameter model includes a channel-aware model and a first parameter determination model; The step of sending the channel parameters used by the first access point when communicating with the station, based on the channel-related information and channel parameter model, includes: Based on the channel-related information and the channel-aware model, the channel characteristics corresponding to the station are determined; Based on the channel characteristics and the first parameter determination model, the channel parameters used by the first access point when communicating with the station are sent to the station.

3. The method according to claim 1, characterized in that, The channel parameter model includes a channel-aware model and a second parameter determination model; the step of sending the channel parameters used by the first access point when communicating with the station based on the channel-related information and the channel parameter model includes: Based on the channel-related information and the channel-aware model, determine the channel characteristics corresponding to the site; based on the channel characteristics and the second parameter determination model, determine a portion of the channel parameters; send the channel characteristics to the second access point, receive another portion of the channel parameters sent by the second access point, and send the channel parameters to the site; or... The channel parameter model includes a channel-aware model. The step of sending the channel parameters used by the first access point when communicating with the station, based on the channel-related information and the channel parameter model, includes: Based on the channel-related information and the channel-aware model, the channel characteristics corresponding to the site are determined; the channel characteristics are sent to the second access point, the channel parameters sent by the second access point are received, and the channel parameters are sent to the site.

4. The method according to claim 3, characterized in that, Before sending the channel characteristics to the second access point, the method further includes: The system receives an AI computing enable message sent by the second access point, wherein the AI ​​computing enable message is used to instruct the first access point to report the channel characteristics.

5. The method according to any one of claims 1 to 4, characterized in that, Before sending the channel parameters used by the first access point to communicate with the station based on the channel-related information and channel parameter model, the method further includes: The detected change in the channel-related information satisfies the condition for redetermining the channel parameters.

6. The method according to any one of claims 1 to 5, characterized in that, The channel-related information includes one or more of the following: channel information, air interface information, or service information.

7. The method according to any one of claims 2 to 4, characterized in that, The channel characteristics include one or more of the following: signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics.

8. The method according to claim 7, characterized in that, The channel characteristics also include one or more of signal-to-noise ratio, throughput, or signal-to-interference-plus-noise ratio.

9. The method according to any one of claims 1 to 8, characterized in that, The channel parameters include channel-level parameters and / or air interface-level parameters.

10. A method for determining channel parameters, characterized in that, The method is applied to a second access point in a wireless network, the second access point being connected to other access points in the wireless network, the method comprising: The system receives channel characteristics sent by the first access point among the other access points, wherein the channel characteristics are determined based on channel-related information of the site associated with the first access point. Based on the channel characteristics and target parameter determination model, some or all channel parameters used by the first access point when communicating with the site are determined, wherein the target parameter determination model is an artificial intelligence (AI) model; Send some or all of the channel parameters to the first access point.

11. The method according to claim 10, characterized in that, The method further includes: Obtain channel characteristics provided by at least one access point, wherein the at least one access point includes the second access point and / or one of the other access points, and the channel characteristics provided by the at least one access point are determined based on channel-related information of the site associated with the at least one access point; The method for determining some or all channel parameters used by the first access point when communicating with the site based on the channel characteristics and target parameters includes: Based on the channel characteristics transmitted by the first access point, the channel characteristics provided by the at least one access point, and the target parameter determination model, the partial or all channel parameters are determined.

12. The method according to claim 11, characterized in that, The method further includes: Based on the channel characteristics sent by the first access point, the channel characteristics provided by the at least one access point, and the target parameter determination model, determine some or all of the channel parameters used by the at least one access point when communicating with the station associated with the at least one access point. If the at least one access point includes an access point among the other access points, send some or all of the channel parameters determined for the at least one access point to the at least one access point.

13. The method according to claim 11 or 12, characterized in that, When the at least one access point includes the second access point, obtaining the channel features provided by the at least one access point includes: Obtain channel-related information of the site associated with the second access point; Based on the channel-related information and channel awareness model of the site associated with the second access point, the channel characteristics corresponding to the site associated with the second access point are determined, wherein the channel awareness model is an AI model.

14. The method according to any one of claims 10 to 13, characterized in that, Before receiving the channel characteristics sent by the first access point among the other access points, the method further includes: Broadcast an AI computing enable message, wherein the AI ​​computing enable message is used to instruct the other access points to report channel characteristics.

15. The method according to any one of claims 10 to 14, characterized in that, The channel-related information includes one or more of the following: channel information, air interface information, or service information.

16. The method according to any one of claims 10 to 15, characterized in that, The channel characteristics include one or more of the following: signal strength, multipath delay, mobility characteristics, air interface interference information, or frequency attenuation characteristics.

17. The method according to claim 16, characterized in that, The channel characteristics also include one or more of signal-to-noise ratio, throughput, or signal-to-interference-plus-noise ratio.

18. The method according to any one of claims 10 to 17, characterized in that, The channel parameters include channel-level parameters and / or air interface-level parameters.

19. A device for determining channel parameters, characterized in that, The device is used at a first access point in a wireless network, and the device includes: The acquisition module is used to acquire channel-related information of the site associated with the first access point; The parameter determination module is used to send the channel parameters used by the first access point when communicating with the station, based on the channel-related information and the channel parameter model, wherein the channel parameter model is an artificial intelligence (AI) model.

20. A device for determining channel parameters, characterized in that, The device is used as a second access point in a wireless network, the second access point being connected to other access points in the wireless network, the device comprising: The communication module is used to receive channel characteristics sent by the first access point among the other access points, wherein the channel characteristics are determined based on channel-related information of the site associated with the first access point; The determination module is used to determine, based on the channel characteristics and target parameters, a model to determine some or all of the channel parameters used by the first access point when communicating with the site, wherein the target parameter determination model is an artificial intelligence (AI) model; The communication module is also used to send some or all of the channel parameters to the first access point.

21. An access point, characterized in that, This includes the communication interface, processor, and memory; The communication interface is used to communicate with other devices; The processor is configured to execute program instructions in the memory to perform the method as described in any one of claims 1 to 9 or the method as described in any one of claims 10 to 18.

22. A communication system, characterized in that, Including the first access point and the second access point; The first access point is used to perform the method according to any one of claims 1 to 9; The second access point is used to perform the method according to any one of claims 10 to 18.

23. A computer-readable storage medium, characterized in that, Includes program instructions, which, when executed by the access point, perform the method as described in any one of claims 1 to 9 or the method as described in any one of claims 10 to 18.

Images