Data transmission method and system based on wifi6, medium and equipment

Abstract

The invention relates to a wifi6-based data transmission method and system, a medium and equipment, and relates to the field of data transmission, and the method comprises the steps: monitoring a signal intensity parameter of terminal equipment in a target environment where data transmission is carried out through wifi6 equipment; when the signal intensity parameter is smaller than a signal intensity threshold value, performing signal interference scene prediction according to the signal intensity parameter to obtain a signal interference scene; carrying out classification according to the signal interference scene to obtain residence time and a transmission quality attention coefficient; and performing signal enhancement transmission optimization according to the residence time and the transmission quality attention coefficient to obtain an enhancement transmission parameter, and performing enhancement data transmission on the terminal equipment within the residence time. The method can solve the problems that in a traditional method, the signal strength cannot be dynamically adjusted according to different use scenes, and the anti-interference capability is poor, and can meet the use requirements of users in diversified scenes.

Description

Technical Field

[0001] The present invention relates to the field of data transmission, and particularly to a data transmission method, system, medium and device based on Wi-Fi 6. Background Art

[0002] With the development of communication technology, the popularization range of Wi-Fi 6 devices is getting wider and wider, and at the same time, users' requirements for the usage experience of such devices are also getting higher and higher.

[0003] Although the existing Wi-Fi 6 technology can achieve high-speed data transmission between different wireless devices, its penetration is weak, and the signal strength is insufficient when there is occlusion, resulting in poor data transmission quality. It cannot dynamically adjust the signal strength according to different usage scenarios to meet the usage requirements of users' diversified scenarios. There is a technical problem of low data transmission quality in different usage scenarios. Summary of the Invention

[0004] The present invention aims at the technical problem of low data transmission quality in different usage scenarios existing in the traditional data transmission method based on Wi-Fi 6, and provides a data transmission method, system, medium and device based on Wi-Fi 6 to solve it.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a data transmission method based on Wi-Fi 6, including: monitoring the signal strength parameter of a terminal device in a target environment where data is transmitted through a Wi-Fi 6 device, wherein the terminal device performs data transmission with the Wi-Fi 6 device; when the signal strength parameter is less than the signal strength threshold, predicting a signal interference scenario according to the signal strength parameter to obtain a signal interference scenario; classifying the residence time and transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and transmission quality attention coefficient; performing signal enhancement transmission optimization according to the residence time and transmission quality attention coefficient to obtain enhanced transmission parameters, and performing enhanced data transmission on the terminal device within the residence time.

[0007] In an implementation manner, monitoring the signal strength parameter of a terminal device in a target environment where data is transmitted through a Wi-Fi 6 device includes:

[0008] Obtaining a terminal device connected to the Wi-Fi 6 device in a target environment where data is transmitted through the Wi-Fi 6 device;

[0009] Monitoring the signal strength parameter of the terminal device for data transmission through the Wi-Fi 6 device.

[0010] In one embodiment, when the signal strength parameter is less than the signal strength threshold, according to the signal strength parameter, signal interference scenario prediction is performed to obtain a signal interference scenario, including:

[0011] Determine whether the signal strength parameter is less than the signal strength threshold. If not, continue with the monitoring and determination;

[0012] If so, input the signal strength parameter into the pre-trained interference scenario predictor to predict and obtain a signal interference scenario.

[0013] In one embodiment, the pre-training steps of the interference scenario predictor include:

[0014] According to the data transmission records in the target environment within the historical time, collect a set of sample signal strength parameters, and collect the positions of terminal devices under different sample signal strength parameters, which are labeled as sample signal interference scenarios, to obtain a set of sample signal interference scenarios;

[0015] Use a neural network to construct an interference scenario predictor;

[0016] Use the set of sample signal strength parameters and the set of sample signal interference scenarios to perform supervised training and accuracy testing on the interference scenario predictor, and complete the pre-training after meeting the requirements.

[0017] In one embodiment, according to the signal interference scenario, classification of the residence time and transmission quality attention coefficient is performed to obtain the residence time and transmission quality attention coefficient, including:

[0018] According to the terminal device usage records in the target environment within the historical time, collect a set of sample signal interference scenarios;

[0019] Collect the single average residence time of the terminal device in different sample signal interference scenarios, and the average number of operations of the terminal device, to obtain a set of sample residence times and a set of sample operation times;

[0020] Calculate the ratio of each sample operation number to the mean of the set of sample operation numbers as the sample transmission quality attention coefficient, to obtain a set of sample transmission quality attention coefficients;

[0021] Construct a mapping relationship between the set of sample signal interference scenarios and the set of sample residence times and the set of sample transmission quality attention coefficients, to obtain an interference scenario classifier;

[0022] Input the signal interference scenario into the interference scenario classifier, and map and classify to obtain the residence time and transmission quality attention coefficient.

[0023] In one embodiment, according to the residence time and the transmission quality attention coefficient, signal enhancement transmission optimization is performed to obtain enhanced transmission parameters, and enhanced data transmission is performed, including:

[0024] Obtain the enhanced transmission parameter space for the wifi6 device to perform enhanced data transmission, and randomly generate the first enhanced transmission parameter;

[0025] Construct an enhanced transmission function as follows:

[0026]

[0027] where HWF is the transmission fitness, the sum of w1 and w2 is 1, which are the energy consumption weight and the quality weight respectively, P y is the preset energy consumption of the wifi6 device, T is the residence time, P is the actual energy consumption of the wifi6 device under the enhanced transmission parameter, K is the transmission quality attention coefficient, and R is the transmission error rate of data transmission between the wifi6 device and the terminal device under the enhanced transmission parameter;

[0028] According to the first enhanced transmission parameter, analyze and obtain the first actual energy consumption and the first transmission error rate of the wifi6 device for data transmission according to the first enhanced transmission parameter;

[0029] According to the first actual energy consumption and the first transmission error rate, based on the enhanced transmission function, calculate and obtain the first transmission fitness;

[0030] Continue to randomly generate enhanced transmission parameters and calculate the transmission fitness, perform iterative optimization of the enhanced transmission parameters, and after the optimization converges, obtain the enhanced transmission parameter with the maximum transmission fitness, and perform enhanced data transmission to the terminal device within the residence time.

[0031] In one embodiment, according to the first enhanced transmission parameter, analyzing and obtaining the first actual energy consumption and the first transmission error rate of the wifi6 device for data transmission according to the enhanced transmission parameter includes:

[0032] According to the historical operation data of the wifi6 device, collect a sample enhanced transmission parameter set and a sample signal strength parameter set, and collect the average operation energy consumption of the wifi6 device under different sample enhanced transmission parameters, as well as the error rate of data transmission of the terminal device under different sample enhanced transmission parameters and sample signal strength parameters, and label to obtain a sample actual energy consumption set and a sample error rate set;

[0033] Construct the mapping relationship between the sample enhanced transmission parameter set and the sample actual energy consumption set to obtain the energy consumption classification branch;

[0034] Based on deep learning, a transmission performance prediction branch is constructed, using the enhanced transmission parameter set of samples and the sample signal strength parameter set as input features, and the sample bit error rate set as the output feature, for supervised training and testing until the requirements are met;

[0035] Input the first enhanced transmission parameter into the energy consumption classification branch to map and obtain the first actual energy consumption;

[0036] Input the first enhanced transmission parameter and the signal strength parameter into the transmission performance prediction branch, and output to obtain the first bit error rate. In a second aspect, the present invention provides a data transmission system based on Wi-Fi 6. The system is used to execute the data transmission method based on Wi-Fi 6 described in the first aspect. The system includes:

[0037] A terminal signal strength monitoring module for monitoring the signal strength parameter of a terminal device in a target environment where data is transmitted through a Wi-Fi 6 device, where the terminal device transmits data with the Wi-Fi 6 device;

[0038] A signal interference scenario prediction module for predicting a signal interference scenario based on the signal strength parameter when the signal strength parameter is less than the signal strength threshold to obtain a signal interference scenario;

[0039] A signal interference scenario classification module for classifying the residence time and the transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and the transmission quality attention coefficient;

[0040] A signal enhancement transmission optimization module for performing signal enhancement transmission optimization according to the residence time and the transmission quality attention coefficient to obtain enhanced transmission parameters, and performing enhanced data transmission on the terminal device within the residence time.

[0041] In a third aspect, the present invention also provides a storage medium, in which a computer software program is stored, and when the computer software program is executed by a processor, it implements the data transmission method based on Wi-Fi 6 described in the first aspect.

[0042] In a fourth aspect, the present invention also provides an electronic device, including:

[0043] A memory for storing a computer software program;

[0044] A processor for reading and executing the computer software program, and further implementing the data transmission method based on Wi-Fi 6 described in the first aspect.

[0045] In the present invention, within a target environment for data transmission via a Wi-Fi 6 device, the signal strength parameter of a terminal device is monitored to precisely initiate signal enhancement transmission. When the signal strength parameter is less than the signal strength threshold, based on the signal strength parameter, a signal interference scenario prediction is performed to obtain a signal interference scenario, and the signal interference scenario is classified to obtain a residence time and a transmission quality concern coefficient. According to the residence time and the transmission quality concern coefficient, signal enhancement transmission optimization is performed to obtain enhanced transmission parameters, and enhanced data transmission is performed on the terminal device within the residence time, realizing targeted enhanced transmission in different scenarios, greatly improving the anti-interference ability of signal transmission, and avoiding unnecessary power consumption while ensuring signal transmission quality.

[0046] In summary, the present invention achieves the technical effect of improving data transmission quality in different scenarios and meeting the data transmission requirements of users in diverse scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic flowchart of a data transmission method based on Wi-Fi 6 provided by the present invention;

[0048] Figure 2 It is a schematic structural diagram of a data transmission system based on Wi-Fi 6 provided by the present invention;

[0049] Figure 3 It is a schematic diagram of a storage medium provided by the present invention;

[0050] Figure 4 It is a schematic structural diagram of an electronic device provided by the present invention.

[0051] In the drawings, the components represented by the respective reference numerals are described as follows:

[0052] Terminal signal strength monitoring module 11, signal interference scenario prediction module 12, signal interference scenario classification module 13, signal enhancement transmission optimization module 14, storage medium 30, first computer program 31, electronic device 40, memory 41, processor 42, second computer program 43. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0054] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0055] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present invention.

[0056] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a data transmission method based on Wi-Fi 6, which specifically includes the following steps:

[0057] S100: In a target environment where data is transmitted through a Wi-Fi 6 device, monitor the signal strength parameter of the terminal device, where the terminal device transmits data with the Wi-Fi 6 device;

[0058] Transmit data through the Wi-Fi 6 device in the target environment and monitor the signal strength of the terminal device, aiming to collect the signal strength values received by the terminal devices (such as mobile phones, household appliances, etc.) at different distances and in different areas (such as the living room, bedroom, etc.) from the Wi-Fi 6 device (such as a wireless router) in the usage scenario.

[0059] Further, step S100 of the present invention further includes:

[0060] In a target environment where data is transmitted through a Wi-Fi 6 device, obtain the terminal devices connected to the Wi-Fi 6 device;

[0061] Monitor the signal strength parameter of the terminal device transmitting data through the Wi-Fi 6 device.

[0062] In the embodiments of the present application, to monitor the signal strength value received by the terminal device connected to the Wi-Fi 6 device, it is first necessary to obtain the terminal device connected to the Wi-Fi 6 device. Specifically, an AP (wireless controller) can be used to send a Trigger frame (trigger frame) containing a BSRP (buffer status report request), which forces the terminal device to feedback a BSR (buffer status report) on a specified RU (resource unit), and the current active terminal list can be accurately obtained. This method of obtaining the device connected to the terminal is a prior art and will not be elaborated here.

[0063] Next, it is necessary to monitor the signal strength parameter of the data transmission of the terminal device through the Wi-Fi 6 device. The parameter specifically measuring the signal strength can be the power (unit: watt). Specifically, a radio frequency power meter or a vector signal analyzer can be used. A power meter probe is connected to the antenna of the terminal device to capture the instantaneous power of the Wi-Fi 6 signal received by the terminal device in real time as the signal strength data. Using the same method, the strength of the signal transmitted by the Wi-Fi 6 device in real time can also be monitored.

[0064] S20: When the signal strength parameter is less than the signal strength threshold, according to the signal strength parameter, perform signal interference scenario prediction to obtain a signal interference scenario;

[0065] In the embodiments of the present application, signal interference scenario prediction is performed because for different scenarios, due to reasons such as wall occlusion and interference from other signal sources, the strength and interference degree of the Wi-Fi 6 signal are very different, and the user's demand for signal quality is also different in different scenarios (such as bedrooms, studies, etc.). For example, usually when the user is in the bedroom, due to frequent use of terminal devices (such as mobile phones), the requirement for signal quality is generally high, and when in the study, due to less use of terminal devices, the requirement for signal quality is generally low. Therefore, to enhance data transmission in a targeted manner, it is necessary to divide and predict the scenario where the terminal device is located.

[0066] Further, step S200 of the present invention further includes:

[0067] Judge whether the signal strength parameter is less than the signal strength threshold. If not, continue to monitor and judge; if so, input the signal strength parameter into the pre-trained interference scenario predictor to predict and obtain a signal interference scenario.

[0068] In the embodiments of the present application, judging whether the signal strength is less than the signal strength threshold is for targeted enhancement of data transmission, and to minimize power consumption, reduce device heating and aging while ensuring signal transmission quality. The signal strength threshold is the lowest value that the signal strength can take (such as 5W), that is, the lowest signal strength value that can enable the terminal device connected to the Wi-Fi 6 device to receive signals normally.

[0069] Among them, the standard of the "normal transmission signal" can be measured by the bit error rate. For example, it can be defined that the signal transmission is normal when the bit error rate is less than 1%. Then, when the bit error rate of data transmission between the Wi-Fi 6 device and the connected terminal device is lower than 1%, it can be determined that the terminal device can receive the signal normally. Further, the minimum signal strength (such as 5W) that can be taken when the bit error rate of data transmission between the Wi-Fi 6 device and the connected terminal device is less than 1% can be set as the threshold of the signal strength, that is, the minimum signal strength that can be taken under the condition of ensuring the signal transmission quality. Among them, the bit error rate is an index to measure the accuracy of data transmission within a specified time, and the bit error rate = the number of bit errors in transmission / the total number of codes transmitted * 100%.

[0070] Through the signal strength monitoring method described in S100, the signal strength parameter of the terminal device can be obtained, and the signal strength threshold can be determined. When the signal strength parameter, that is, the power, is greater than the set signal strength threshold, it means that the signal transmission quality, that is, the bit error rate, is within the normal range, and continuous monitoring and judgment can be carried out; when the signal strength parameter is less than the set signal strength threshold, it means that the signal transmission quality is poor, that is, the signal is severely interfered, and the signal needs to be enhanced for transmission according to the specific interference situation to ensure the signal transmission quality.

[0071] In this embodiment, the prediction of the signal interference situation is realized through the interference scenario predictor. By inputting the signal strength parameter into the interference scenario predictor, the prediction of the signal interference scenario can be realized. The pre-training steps of the interference scenario predictor include:

[0072] According to the data transmission records in the target environment within the historical time, collect the sample signal strength parameter set, and collect the positions of the terminal devices under different sample signal strength parameters, which are marked as the sample signal interference scenarios, to obtain the sample signal interference scenario set;

[0073] Use a neural network to construct an interference scenario predictor;

[0074] Use the sample signal strength parameter set and the sample signal interference scenario set to perform supervised training and accuracy testing on the interference scenario predictor, and complete the pre-training after meeting the requirements.

[0075] In the embodiments of the present application, the training of the interference scenario predictor is to predict the signal interference scenario based on the input signal strength parameters. Therefore, it is necessary to use the sample data obtained in the actual usage environment to train the interference scenario predictor to ensure its applicability. The sample data includes sample signal strength parameters and the sample signal interference scenarios corresponding to the signal strength parameters. The sample signal strength parameters in this embodiment are the signal strength parameters of the terminal device in the target environment where data is transmitted through the Wi-Fi 6 device; the position of the terminal device is the position where the terminal device for data transmission through the Wi-Fi 6 device is located, such as common living areas like the bathroom, meeting room, and restaurant. Specifically, taking the Wi-Fi 6 device as the origin, a planar space coordinate system can be constructed in the target scenario to determine the position of the terminal device, that is, the sampling point. The distance between each sampling point is 0.5 m, and 100 groups of signal strength parameters are collected at each sampling point each time (such as collecting for 10 s at a sampling frequency of 10 Hz) as the time-series signal strength data, and are labeled according to the position of the corresponding coordinates of each sampling point, such as the bathroom, meeting room, restaurant, etc., as the sample signal interference scenarios. By repeatedly collecting multiple time-series signal strength data at each sampling point, a set of sample signal interference scenarios can be obtained. The set of sample signal interference scenarios is divided into a test set and a validation set for subsequent training of the interference scenario predictor.

[0076] Specifically, the input layer of the interference scenario predictor is the time-series data of the terminal device signal strength parameters; the output layer is the two-dimensional coordinates (x, y) matching the time-series data of the corresponding signal strength parameters and the corresponding interference scenarios.

[0077] In the embodiments of the present application, to construct the interference scenario predictor, the key is to construct the mapping relationship between the time-series data of the signal strength and the spatial coordinates. Specifically, the interference scenario predictor can be built in the way of TCN (Temporal Convolutional Network) + LSTM (Long Short-Term Memory Network).

[0078] Among them, because TCN uses causal convolution and dilated convolution to capture patterns in time, it performs better when dealing with long sequence data, especially in the case of long-term dependencies. For example, TCN can be used to extract the macroscopic propagation pattern of the signal (such as the multipath effect period); while LSTM controls the flow of information through the gating mechanism, so it is good at dealing with short-term dependencies and dynamic changes in the sequence, such as sudden signal fluctuations (such as transient human occlusion). The combination of the two can achieve accurate prediction of the interference scenario. The TCN module can be set with 3 - 6 residual block layers for deep feature extraction. The number of hidden units of the LSTM module can be set to 128 - 256, and it can be set to a two-layer bidirectional structure.

[0079] Next, use the sample signal strength parameter set and the sample signal interference scenario set to supervise the training of the model. During the training of the model, the learning rate is set to 0.001, the optimizer uses Nadam, and the loss function selects the Huber loss (δ = 1.0) to balance the influence of outliers. When training, a pre-trained TCN model (such as WaveNet) can be used to initialize the parameters of the convolutional layer to accelerate convergence; or the initial forget gate bias of the LSTM can be set to 1.0 to enhance long-term memory. Use the accuracy rate as the evaluation criterion for the model. For example, the model training can be set to be qualified when the prediction accuracy rate is greater than 95%. When the accuracy rate reaches the established standard, the pre-training is completed, and an interference scenario predictor is obtained.

[0080] S300: Classify the residence time and the transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and the transmission quality attention coefficient;

[0081] Furthermore, step S300 of the present invention further includes:

[0082] Collect a sample signal interference scenario set according to the usage records of terminal devices in the target environment within the historical time;

[0083] Collect the single average residence time of the terminal device in different sample signal interference scenarios and the average number of operations of the terminal device to obtain a sample residence time set and a sample operation number set;

[0084] Calculate the ratio of each sample operation number to the mean value of the sample operation number set as the sample transmission quality attention coefficient to obtain a sample transmission quality attention coefficient set;

[0085] Construct a mapping relationship between the sample signal interference scenario set and the sample residence time set and the sample transmission quality attention coefficient set to obtain an interference scenario classifier (inputting an interference scenario and outputting a residence time and a transmission quality attention coefficient);

[0086] Input the signal interference scenario into the interference scenario classifier to map and classify to obtain a residence time and a transmission quality attention coefficient.

[0087] In the embodiments of the present application, collecting the set of sample signal interference scenarios is to determine the specific usage scenarios of the terminal device. Then, by calculating the average single stay time and the average number of operations of the terminal device in different signal interference scenarios within a past period (such as 1 month), it is possible to judge the degree of the user's demand for transmission quality in different signal interference scenarios, and obtain the attention coefficients of transmission quality in different signal interference scenarios. Then, according to the mapping relationship between the set of sample signal interference scenarios, the set of sample stay times, and the set of sample transmission quality attention coefficients, an interference scenario classifier can be built. By inputting the signal interference scenario, the stay time and the transmission quality attention coefficient can be predicted.

[0088] The set of sample signal interference scenarios should include all scenarios that can be covered by wifi6 accessible to the terminal device. For example, in a civilian residence, it should include scenarios such as the kitchen, living room, bedroom, bathroom, and study that can be reached by terminal devices (such as mobile phones, computers, etc.) accessing wifi6.

[0089] The average single stay time of the terminal device in different sample signal interference scenarios is the average value of the stay time of each terminal device entering the sample signal interference scenario within a period (such as 1 day) each time in the interference scenario. For example, taking the kitchen as a signal interference scenario, within one day, terminal device A enters the kitchen 3 times, with a total stay time of 6h; terminal device B enters the kitchen 2 times, with a total stay time of 2h. Then, the average single stay time of the terminal device in the sample signal interference scenario of the kitchen is (6h + 2h) / (3 times + 2 times) = 1.6h / time.

[0090] The average number of operations of the terminal device in different sample signal interference scenarios is the average value of the number of operations of each terminal device entering the sample signal interference scenario within a period (such as 1 day) in the interference scenario. For example, taking the kitchen as a signal interference scenario, within one day, terminal device A operates 4 times in the kitchen, terminal device B operates 3 times in the kitchen, and terminal device C operates 2 times in the kitchen. Then, the average number of operations of the terminal device in the sample signal interference scenario of the kitchen is (4 + 3 + 2) / 3 = 3 times.

[0091] In the embodiments of the present application, calculating the ratio of the number of operations of each sample to the mean of the set of the number of sample operations is to determine, based on the number of operations, which sample signal interference scenario the user has a higher demand for signal transmission quality. Obviously, the more frequently the user operates the terminal device in a certain interference scenario, the more the user needs to use the terminal device for signal transmission in this interference scenario. Therefore, the transmission quality concern coefficient in this scenario should also increase accordingly. The specific indicator for measuring the frequency of the user's operation of the terminal device in a certain interference scenario is the ratio of the number of operations of each sample to the mean of the set of the number of sample operations.

[0092] Exemplarily, within one day, the mean of the set of the number of sample operations is 12 times. For sample A (such as the bedroom), the number of operations is 24, and for sample B (such as the kitchen), the number of operations is 6. Then, for sample A, the sample transmission quality concern coefficient is 24 / 12 = 2; for sample B, the sample transmission quality concern coefficient is 6 / 12 = 0.5. Obviously, in this example, the quality concern coefficient of sample A with a larger number of operation values is greater than that of sample B with a smaller number of operation values. By collecting multiple such quality concern coefficients, a set of sample transmission quality concern coefficients can be obtained.

[0093] Furthermore, based on the mapping relationship between the set of signal interference scenarios, the set of residence times, and the set of transmission quality concern coefficients, an interference scenario classifier can be constructed. By inputting the sample signal interference scenario, the residence time and the transmission quality concern coefficient of the terminal device in this signal interference scenario can be obtained.

[0094] Specifically, since all sample parameters are already available, the main task of building the interference scenario classifier is to establish a mapping relationship for extracting the residence time and the transmission quality concern coefficient based on the interference scenario. A relational database such as MySQL can be used for building. Specifically, a table containing fields such as interference scenario description, residence time, and transmission quality coefficient needs to be created in MySQL, and the existing data is inserted into the database. Then, a function is written using a programming language (such as Python) to query the database based on the input interference scenario and extract the residence time and the transmission quality coefficient. In this way, the mapping relationship between the set of signal interference scenarios, the set of residence times, and the set of transmission quality concern coefficients can be realized. After the building is completed, different interference scenarios are used for testing to ensure that the query results are correct.

[0095] Furthermore, since the interference scenario predictor has been trained in the foregoing step S200, by inputting the signal strength parameter, the corresponding interference scenario can be output; then, by inputting the interference scenario into the interference scenario classifier built in this step, the residence time and the transmission quality concern coefficient can be output, so as to realize signal enhancement transmission optimization targeted at different signal strengths and scenarios.

[0096] S400: Perform signal enhanced transmission optimization according to the dwell time and the transmission quality concern coefficient to obtain enhanced transmission parameters, and perform enhanced data transmission on the terminal device within the dwell time.

[0097] Furthermore, step S400 of the present invention further includes:

[0098] Obtain the enhanced transmission parameter space for the wifi6 device to perform enhanced data transmission, and randomly generate the first enhanced transmission parameter;

[0099] Construct an enhanced transmission function as follows:

[0100]

[0101] where HWF is the transmission fitness, the sum of w1 and w2 is 1, which are the energy consumption weight and the quality weight respectively, P y is the preset energy consumption of the wifi6 device, T is the dwell time, P is the actual energy consumption of the wifi6 device under the enhanced transmission parameter, K is the transmission quality concern coefficient, and R is the transmission error rate of data transmission between the wifi6 device and the terminal device under the enhanced transmission parameter;

[0102] In the embodiment of the present application, the signal enhanced transmission optimization is mainly achieved by adjusting the enhanced transmission parameter. Specifically, in this embodiment, it is to adjust the signal transmission intensity, that is, to adjust the signal transmission power of the wifi6 device. To balance the problem of increased energy consumption caused by increased power, this embodiment constructs an enhanced transmission function to calculate the fitness of the enhanced transmission parameter, and obtains the optimal enhanced transmission parameter to balance the quality and energy consumption of signal transmission, where the error rate is used as an index to measure the signal transmission quality.

[0103] First of all, the enhanced transmission parameter space is determined by the inherent parameters of the wifi6 device. For example, in this embodiment, if the enhanced transmission is performed by increasing the transmission power, the upper limit of the enhanced transmission parameter depends on the rated signal emission power of the wifi6 device, such as 10W; the lower limit of the enhanced transmission parameter is the current real-time power, such as 5W. After obtaining the enhanced transmission parameter space, multiple first enhanced transmission parameters (such as 6W, 7W, 8W) are randomly generated within the enhanced transmission parameter space (such as 5 - 10W), and their transmission fitness is calculated respectively through the enhanced transmission function to screen out the optimal enhanced transmission parameter.

[0104] Secondly, the enhanced transmission function is used to calculate the transmission fitness of a Wi-Fi 6 device under a certain enhanced transmission parameter. The first term on the right side of the equation is the energy consumption fitness. An increase in the enhanced transmission parameter will cause an increase in P (the actual energy consumption of the Wi-Fi 6 device under the enhanced transmission parameter) in the equation, resulting in a decrease in the energy consumption fitness, and vice versa. The second term on the right side of the equation is the transmission quality fitness. An increase in the enhanced transmission parameter will cause a decrease in R (the transmission error rate of data transmission between the Wi-Fi 6 device and the terminal device under the enhanced transmission parameter) in the equation, resulting in an increase in the quality fitness, and vice versa. The sum of the two terms on the right side of the equation gives HWF (transmission fitness). In the equation, T (residence time) and K (transmission quality concern coefficient) in a specific interference scenario are constant values greater than 0. For example, in the kitchen scenario, the residence time can be 4h, and the transmission quality concern coefficient can be 0.8. As the specific interference scenario changes, the values of T and K will also change. The larger the T value (residence time) of an interference scenario, the lower its energy consumption fitness; the larger the K value (transmission quality concern coefficient), the higher its transmission quality fitness; and vice versa.

[0105] The w1 and w2 are the energy consumption weight and the quality weight respectively, and the sum of the two is 1, which is used to adjust the weights of energy consumption and quality. If more attention is paid to energy consumption during data transmission, w1 can be set to be greater than w2, such as w1 = 0.7 and w2 = 0.3; if more attention is paid to transmission quality, w1 can be set to be less than w2, such as w1 = 0.4 and w2 = 0.6.

[0106] According to the first enhanced transmission parameter, analyze and obtain the first actual energy consumption and the first transmission error rate of the Wi-Fi 6 device for data transmission according to the first enhanced transmission parameter. It includes:

[0107] According to the historical operation data of the Wi-Fi 6 device, collect the sample enhanced transmission parameter set and the sample signal strength parameter set, and collect the average operation energy consumption of the Wi-Fi 6 device under different sample enhanced transmission parameters, as well as the error rate of data transmission of the terminal device under different sample enhanced transmission parameters and sample signal strength parameters, and label to obtain the sample actual energy consumption set and the sample error rate set;

[0108] Construct the mapping relationship between the sample enhanced transmission parameter set and the sample actual energy consumption set to obtain the energy consumption classification branch;

[0109] Based on deep learning, construct a transmission performance prediction branch, use the sample enhanced transmission parameter set and the sample signal strength parameter set as input features, and use the sample error rate set as output features for supervised training and testing until the requirements are met;

[0110] Input the first enhanced transmission parameter into the energy consumption classification branch to map and obtain the first actual energy consumption;

[0111] Input the first enhanced transmission parameter and the signal strength parameter into the transmission performance prediction branch, and output to obtain the first bit error rate.

[0112] In the embodiments of the present application, after obtaining multiple random first enhanced transmission parameters according to the enhanced transmission parameter space, it is necessary to calculate the transmission fitness of the wifi6 device under these first enhanced transmission parameters to evaluate the enhanced transmission parameter. According to the aforementioned enhanced transmission function, calculating the transmission fitness requires obtaining the actual energy consumption and the bit error rate of data transmission of the wifi6 device under corresponding conditions, that is, the first actual energy consumption and the first transmission bit error rate. The actual energy consumption of the wifi6 device can be calculated by reading the real-time current and voltage, that is, W = UI; and the calculation method of the bit error rate is: bit error rate = number of bit errors in transmission / total number of codes transmitted * 100%.

[0113] Next, by collecting multiple sample enhanced parameters, a sample enhanced transmission parameter set can be obtained; by labeling the average energy consumption of the wifi6 device within a period of time (such as 24h) under each sample enhanced transmission parameter, a sample actual energy consumption set can be obtained. By labeling the bit error rate of data transmission of the terminal device under the sample enhanced transmission parameter and the sample signal strength parameter, a sample bit error rate set can be obtained. The above sample actual energy consumption set and sample bit error rate set are respectively used to build the energy consumption classification branch and the transmission performance prediction branch.

[0114] In the embodiments of the present application, the energy consumption classification branch mainly constructs the mapping relationship between the sample enhanced transmission parameter set and the sample actual energy consumption set. It can also be built using a relational database such as MySQL. Specifically, it is necessary to create a table containing sample enhanced transmission parameters and sample actual energy consumption in MySQL, insert the existing data into the database, and then write a function using a programming language (such as Python) to query the database according to the input enhanced transmission parameter and extract the actual energy consumption. In this way, the mapping relationship between the sample enhanced transmission parameter set and the sample actual energy consumption set can be realized. After the construction is completed, different sample enhanced transmission parameters are used for testing to ensure that the query results are correct.

[0115] Input the first enhanced transmission parameter into the energy consumption classification branch, and the first actual energy consumption can be obtained.

[0116] In the embodiments of the present application, the transmission performance prediction branch mainly predicts the bit error rate in data transmission according to the enhanced transmission parameter and the signal strength parameter. The input features are the sample enhanced transmission parameter set and the sample signal strength parameter set, and the output feature is the sample bit error rate set. A gradient boosting decision tree (GBDT) can be used to build the transmission performance prediction model. GBDT is an iterative decision tree algorithm that constructs a set of weak learners (trees) and accumulates the results of multiple decision trees as the final prediction output.

[0117] Specifically, in the construction of the model, since the goal is to predict the specific value of the bit error rate, a regression-type gradient boosting tree can be selected. The initial setting is that the total number of trees is about 200 (which can be adjusted during the training process); the complexity of each tree is controlled at a medium level (for example, each tree has at most 5 levels); 80% of the data is randomly selected for each training to prevent over-reliance on specific samples. When adding more trees but the validation error no longer decreases, the training is terminated in advance to save time.

[0118] Furthermore, during training, the enhanced transmission parameter set and the sample signal strength parameter set can be input, and the bit error rate predicted by the model is compared with the labeled true bit error rate to evaluate the training level of the model. The evaluation index of the model can be set as the average error, that is, the average gap between all predicted values and the true values (for example, the average error of the bit error rate prediction being less than 0.1% indicates that the prediction is basically accurate). When the average gap between the predicted value and the true value is large, the model parameters are modified and training continues until the model converges to obtain the transmission performance prediction branch.

[0119] Input the first enhanced transmission parameter and the signal strength parameter into the transmission performance prediction branch, and the first bit error rate can be output.

[0120] According to the first actual energy consumption and the first transmission bit error rate, based on the enhanced transmission function, the first transmission fitness is calculated.

[0121] Continue to randomly generate enhanced transmission parameters and calculate the transmission fitness, perform iterative optimization of the enhanced transmission parameters. After the optimization converges, the enhanced transmission parameter with the maximum transmission fitness is obtained, and enhanced data transmission is performed on the terminal device within the residence time.

[0122] Specifically, input the first actual energy consumption (P) and the first transmission bit error rate (R) corresponding to a certain enhanced transmission parameter into the enhanced transmission function under a specific interference scenario (obtaining T value and K value), and define weights w1 and w2, then the corresponding first transmission fitness can be calculated. Input multiple randomly generated enhanced transmission parameters into the enhanced transmission parameter according to the above method, and the transmission fitness corresponding to multiple enhanced transmission parameter values can be obtained. To obtain the optimal enhanced transmission parameter, it is necessary to calculate by inputting a large number of randomly generated enhanced transmission parameters. After each calculation, the range of the input enhanced transmission parameter value is limited according to the distribution interval of the output transmission fitness, and the range of the enhanced transmission parameter value is continuously narrowed until the optimal enhanced transmission parameter is obtained.

[0123] Then, when the corresponding terminal device stays in the interference scenario, enhanced transmission is performed using the enhanced transmission parameter with the maximum transmission fitness. For example, for a certain terminal device (mobile phone), the enhanced transmission parameter with the maximum fitness in a certain interference scenario (such as a kitchen) can be 7W (the transmission fitness is the maximum when data is transmitted to the terminal device when the power of the wifi6 device is 7W).

[0124] Using the enhanced transmission parameter with the maximum transmission fitness can, while enhancing the anti-interference ability and ensuring the transmission quality, also take into account the reduction of energy consumption to reduce the reduction of device lifespan and performance degradation caused by excessive heating during high-power operation of the device.

[0125] Embodiment 2, such as Figure 2 As shown, based on the same inventive concept as the wifi6-based data transmission method provided in Embodiment 1, the embodiment of the present invention also provides a wifi6-based data transmission system, including:

[0126] A terminal signal strength monitoring module 11, configured to monitor the signal strength parameter of a terminal device in a target environment where data is transmitted through a wifi6 device, where the terminal device transmits data with the wifi6 device;

[0127] A signal interference scenario prediction module 12, configured to, when the signal strength parameter is less than the signal strength threshold, perform signal interference scenario prediction according to the signal strength parameter to obtain a signal interference scenario;

[0128] A signal interference scenario classification module 13, configured to classify the residence time and transmission quality concern coefficient according to the signal interference scenario to obtain the residence time and transmission quality concern coefficient;

[0129] A signal enhancement transmission optimization module 14, configured to perform signal enhancement transmission optimization according to the residence time and the transmission quality concern coefficient to obtain an enhanced transmission parameter, and perform enhanced data transmission on the terminal device within the residence time.

[0130] In one embodiment, the terminal signal strength monitoring module 11 is further configured to:

[0131] In a target environment where data is transmitted through a wifi6 device, obtain a terminal device connected to the wifi6 device;

[0132] Monitor the signal strength parameter of the terminal device for data transmission through the wifi6 device.

[0133] In one embodiment, the signal interference scenario prediction module 12 is further configured to:

[0134] Determine whether the signal strength parameter is less than the signal strength threshold. If not, continue to monitor and judge;

[0135] If so, input the signal strength parameter into the pre-trained interference scenario predictor to predict and obtain the signal interference scenario.

[0136] The pre-training steps of the interference scenario predictor include:

[0137] According to the data transmission records in the target environment within the historical time, collect the sample signal strength parameter set, and collect the positions of the terminal devices under different sample signal strength parameters, which are labeled as the sample signal interference scenarios, to obtain the sample signal interference scenario set;

[0138] Use a neural network to construct an interference scenario predictor;

[0139] Use the sample signal strength parameter set and the sample signal interference scenario set to perform supervised training and accuracy testing on the interference scenario predictor, and complete the pre-training after meeting the requirements.

[0140] In one embodiment, the signal interference scenario classification module 13 is further configured to:

[0141] According to the terminal device usage records in the target environment within the historical time, collect the sample signal interference scenario set;

[0142] Collect the single average residence time of the terminal device in different sample signal interference scenarios, as well as the average number of operations of the terminal device, to obtain the sample residence time set and the sample operation number set;

[0143] Calculate the ratio of each sample operation number to the mean of the sample operation number set as the sample transmission quality attention coefficient, to obtain the sample transmission quality attention coefficient set;

[0144] Construct the mapping relationship between the sample signal interference scenario set and the sample residence time set and the sample transmission quality attention coefficient set to obtain an interference scenario classifier;

[0145] Input the signal interference scenario into the interference scenario classifier, and map and classify to obtain the residence time and the transmission quality attention coefficient.

[0146] In one embodiment, the signal enhancement transmission optimization module 14 is further configured to:

[0147] Obtain the enhanced transmission parameter space for the wifi6 device to perform enhanced data transmission, and randomly generate the first enhanced transmission parameter;

[0148] Build an enhanced transmission function as follows:

[0149]

[0150] Among them, HWF is the transmission fitness, the sum of w1 and w2 is 1, which are the energy consumption weight and the quality weight respectively, and P y is the preset energy consumption of the wifi6 device, T is the residence time, P is the actual energy consumption of the wifi6 device under enhanced transmission parameters, K is the transmission quality concern coefficient, and R is the transmission error rate of data transmission between the wifi6 device and the terminal device under enhanced transmission parameters;

[0151] According to the first enhanced transmission parameter, analyze and obtain the first actual energy consumption and the first transmission error rate of the wifi6 device for data transmission according to the first enhanced transmission parameter;

[0152] According to the first actual energy consumption and the first transmission error rate, based on the enhanced transmission function, calculate and obtain the first transmission fitness;

[0153] Continue to randomly generate enhanced transmission parameters and calculate the transmission fitness, perform iterative optimization of the enhanced transmission parameters, after the optimization converges, obtain the enhanced transmission parameter with the maximum transmission fitness, and perform enhanced data transmission on the terminal device within the residence time.

[0154] Embodiment 3, as Figure 3 shown, based on the same inventive concept as the wifi6-based data transmission method provided in Embodiment 1, the embodiment of the present invention also provides a readable storage medium, in which a computer software program is stored, and when the computer software program is executed by a processor, it implements the wifi6-based data transmission method as described in Embodiment 1.

[0155] The storage medium refers to a storage carrier that can store data, including but not limited to SSD (Solid State Drive), HDD (Hard Disk Drive), and flash devices (USB flash drive, memory card), etc.

[0156] Embodiment 4, as Figure 4 shown, based on the same inventive concept as the wifi6-based data transmission method provided in Embodiment 1, the embodiment of the present invention also provides an electronic device, including:

[0157] A memory for storing a computer software program;

[0158] A processor for reading and executing the computer software program, thereby implementing the wifi6-based data transmission method described in Embodiment 1.

[0159] The memory refers to a device in a computer for temporarily storing running programs and data, including but not limited to random access memory (RAM), read-only memory (ROM), virtual memory, etc.

[0160] The processor is a component in a computer that is responsible for executing program instructions, processing data, and controlling the operation of the computer, including but not limited to general-purpose processors, graphics processing units, embedded processors, etc.

Claims

1. A data transmission method based on Wi-Fi 6, characterized in that, The method includes: Monitoring the signal strength parameter of a terminal device in a target environment where data is transmitted through a Wi-Fi 6 device, where the terminal device transmits data with the Wi-Fi 6 device; When the signal strength parameter is less than the signal strength threshold, predicting a signal interference scenario based on the signal strength parameter to obtain a signal interference scenario; Classifying the residence time and the transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and the transmission quality attention coefficient; Performing signal enhancement transmission optimization according to the residence time and the transmission quality attention coefficient to obtain enhanced transmission parameters, and performing enhanced data transmission on the terminal device within the residence time.

2. The data transmission method based on Wi-Fi 6 according to claim 1, wherein Monitoring the signal strength parameter of a terminal device in a target environment where data is transmitted through a Wi-Fi 6 device includes: Obtaining a terminal device connected to the Wi-Fi 6 device in a target environment where data is transmitted through the Wi-Fi 6 device; Monitoring the signal strength parameter of the terminal device transmitting data through the Wi-Fi 6 device.

3. The data transmission method based on Wi-Fi 6 according to claim 1, wherein When the signal strength parameter is less than the signal strength threshold, predicting a signal interference scenario based on the signal strength parameter to obtain a signal interference scenario, including: Judging whether the signal strength parameter is less than the signal strength threshold. If not, continue to monitor and judge; If so, input the signal strength parameter into a pre-trained interference scenario predictor to predict and obtain a signal interference scenario.

4. The data transmission method based on Wi-Fi 6 according to claim 3, wherein The pre-training steps of the interference scenario predictor include: According to the data transmission records in the target environment within a historical time, collecting a set of sample signal strength parameters, and collecting the positions of terminal devices under different sample signal strength parameters, which are labeled as sample signal interference scenarios, to obtain a set of sample signal interference scenarios; Using a neural network to construct an interference scenario predictor; Using the set of sample signal strength parameters and the set of sample signal interference scenarios to perform supervised training and accuracy testing on the interference scenario predictor, and completing pre-training after meeting the requirements.

5. The data transmission method based on Wi-Fi 6 according to claim 1, wherein Classifying the residence time and the transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and the transmission quality attention coefficient, including: According to the terminal device usage records in the target environment within a historical time, collecting a set of sample signal interference scenarios; Collecting the single average residence time of the terminal device in different sample signal interference scenarios and the average number of operations of the terminal device to obtain a set of sample residence times and a set of sample operation times; Calculating the ratio of each sample operation number to the mean of the set of sample operation numbers as the sample transmission quality attention coefficient to obtain a set of sample transmission quality attention coefficients; Constructing a mapping relationship between the set of sample signal interference scenarios, the set of sample residence times, and the set of sample transmission quality attention coefficients to obtain an interference scenario classifier; Inputting the signal interference scenario into the interference scenario classifier to map and classify to obtain the residence time and the transmission quality attention coefficient.

6. The data transmission method based on Wi-Fi 6 according to claim 1, wherein Performing signal enhancement transmission optimization according to the residence time and the transmission quality attention coefficient to obtain enhanced transmission parameters and performing enhanced data transmission, including: Obtain the enhanced transmission parameter space for enhanced data transmission of the Wi-Fi 6 device and randomly generate the first enhanced transmission parameter; Construct an enhanced transmission function as follows: Among them, HWF is the transmission fitness, the sum of w1 and w2 is 1, which are the energy consumption weight and the quality weight respectively, and P y is the preset energy consumption of the wifi6 device, T is the residence time, P is the actual energy consumption of the wifi6 device under enhanced transmission parameters, K is the transmission quality concern coefficient, and R is the transmission error rate of data transmission between the wifi6 device and the terminal device under enhanced transmission parameters; According to the first enhanced transmission parameter, analyze and obtain the first actual energy consumption and the first transmission error rate of the Wi-Fi 6 device for data transmission according to the first enhanced transmission parameter; Based on the enhanced transmission function, calculate and obtain the first transmission fitness according to the first actual energy consumption and the first transmission error rate; Continue to randomly generate enhanced transmission parameters and calculate the transmission fitness, perform iterative optimization of the enhanced transmission parameters. After the optimization converges, obtain the enhanced transmission parameter with the maximum transmission fitness, and perform enhanced data transmission on the terminal device within the residence time.

7. The data transmission method based on Wi-Fi 6 according to claim 6, wherein Analyze and obtain the first actual energy consumption and the first transmission error rate of the Wi-Fi 6 device for data transmission according to the first enhanced transmission parameter, including: According to the historical operation data of the Wi-Fi 6 device, collect a set of sample enhanced transmission parameters and a set of sample signal strength parameters, and collect the average operation energy consumption of the Wi-Fi 6 device under different sample enhanced transmission parameters, as well as the error rate of data transmission of the terminal device under different sample enhanced transmission parameters and sample signal strength parameters, and label to obtain a set of sample actual energy consumption and a set of sample error rates; Construct the mapping relationship between the set of sample enhanced transmission parameters and the set of sample actual energy consumption to obtain the energy consumption classification branch; Based on deep learning, construct a transmission performance prediction branch, use the set of sample enhanced transmission parameters and the set of sample signal strength parameters as input features, and use the set of sample error rates as output features for supervised training and testing until the requirements are met; Input the first enhanced transmission parameter into the energy consumption classification branch to map and obtain the first actual energy consumption; Input the first enhanced transmission parameter and the signal strength parameter into the transmission performance prediction branch, and output to obtain the first error rate.

8. A data transmission system based on Wi-Fi 6, characterized in that, The system is used to execute the method according to any one of claims 1-7. The system includes: A terminal signal strength monitoring module, used to monitor the signal strength parameter of the terminal device in the target environment for data transmission through the Wi-Fi 6 device, where the terminal device performs data transmission with the Wi-Fi 6 device; A signal interference scenario prediction module, used to perform signal interference scenario prediction according to the signal strength parameter when the signal strength parameter is less than the signal strength threshold to obtain the signal interference scenario; A signal interference scenario classification module, used to classify the residence time and the transmission quality attention coefficient according to the signal interference scenario to obtain the residence time and the transmission quality attention coefficient; A signal enhancement transmission optimization module, used to perform signal enhancement transmission optimization according to the residence time and the transmission quality attention coefficient to obtain the enhanced transmission parameter, and perform enhanced data transmission on the terminal device within the residence time.

9. A computer-readable storage medium, characterized in that, The computer software program is stored in the storage medium, and when the computer software program is executed by the processor, it implements the Wi-Fi 6-based data transmission method according to any one of claims 1-7.

10. An electronic device, characterized in that, Including: A memory for storing a computer software program; A processor for reading and executing the computer software program to implement the data transmission method based on wifi6 according to any one of claims 1-7.

Images