Wireless channel assessment method and device, electronic equipment and storage medium
Through the prediction model, the communication quality of the wireless channel is evaluated, and the error problem caused by untimely evaluation of the wireless channel is solved, and the quality of wireless communication is improved.
Patent Information
- Application Number
- CN202310857128.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-12
- Publication Date
- 2025-01-14
AI Technical Summary
In wireless communication scenarios, the device cannot evaluate the wireless channel in time, resulting in errors in the channel evaluation results and affecting the communication quality.
By pre-constructing a prediction model, using channel parameter information of different periods of the wireless channel as training samples, model parameters are determined, used to characterize the channel parameter distribution rules, and real-time evaluation and selection of high-quality channels are performed based on the predicted channel parameter information.
Accurate and timely evaluation of wireless channels is achieved, communication quality is improved, channel evaluation error is reduced, and additional equipment and cost requirements are reduced.
Smart Images
Figure CN119316077A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a wireless channel assessment method, device, electronic device and storage medium. Background Art
[0002] At present, in wireless communication scenarios, in order to improve communication quality, wireless channels are usually evaluated to select wireless channels with better channel quality for wireless communication and improve communication quality. When evaluating wireless channels, the device cannot connect to the Internet, so the device needs to scan all channels during idle time to find the wireless channel with the least interference and switch to the wireless channel for communication.
[0003] However, in actual applications, the idle time of the device is relatively short. When the channel needs to be switched, the channel evaluation time corresponding to the referenced wireless channel evaluation result is relatively long from the current time, and the channel evaluation result lacks timeliness and has certain evaluation errors, which affects the subsequent communication quality. Summary of the invention
[0004] The embodiments of the present application provide a wireless channel assessment method, device, electronic device and storage medium, which can perform wireless channel assessment in real time and accurately, and solve the technical problem of assessment errors caused by untimely wireless channel assessment.
[0005] In a first aspect, an embodiment of the present application provides a wireless channel assessment method, including:
[0006] Obtaining a channel identifier and a target evaluation period for each wireless channel;
[0007] Input the channel identifier and the target evaluation period into a pre-built prediction model, and output channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model uses the channel parameter information of the wireless channel in different periods as training samples in advance, and uses the training samples to perform model training to determine corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods;
[0008] The channel evaluation results of each wireless channel are determined based on the channel parameter prediction information, so as to select a target channel for connection in the target evaluation period based on the channel evaluation results.
[0009] In a second aspect, an embodiment of the present application provides a wireless channel assessment device, including:
[0010] An acquisition module, used to determine the channel identification and target evaluation period of each wireless channel;
[0011] An estimation module is used to input the channel identifier and the target evaluation period into a pre-built prediction model, and output channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model uses the channel parameter information of the wireless channel in different periods as training samples in advance, and uses the training samples to perform model training to determine corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods;
[0012] A selection module is used to determine the channel evaluation results of each wireless channel based on the channel parameter prediction information, so as to select a target channel for connection in the target evaluation period based on the channel evaluation results.
[0013] In a third aspect, an embodiment of the present application provides an electronic device, including:
[0014] memory and one or more processors;
[0015] The memory is used to store one or more programs;
[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the wireless channel assessment method as described in the first aspect.
[0017] In a fourth aspect, an embodiment of the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the wireless channel assessment method as described in the first aspect.
[0018] The embodiment of the present application obtains the channel identifier and target evaluation period of each wireless channel; inputs the channel identifier and target evaluation period into a pre-built prediction model, outputs the channel parameter prediction information of each wireless channel in the target evaluation period, and the prediction model pre-uses the channel parameter information of the wireless channel in different time periods as training samples, and uses the training samples to train the model, and determines the corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different time periods; based on the channel parameter prediction information, the channel evaluation results of each wireless channel are determined, so as to select the target channel for connection in the target evaluation period based on the channel evaluation results. The above-mentioned technical means are adopted, and the prediction model is trained by pre-using the channel parameter information of different time periods of the wireless channel, and the channel parameter prediction information of the target evaluation period is predicted based on the channel parameter information of the historical time period and the prediction model, so as to evaluate the channel communication quality according to the predicted channel parameter prediction information, and realize accurate and timely wireless channel evaluation. Then, according to the channel evaluation results, a wireless channel with relatively good channel communication quality can be selected for connection, thereby improving the quality of wireless communication. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 is a flow chart of a wireless channel assessment method provided in Example 1 of the present application;
[0020] Figure 2 is a flow chart of the prediction model training in Example 1 of the present application;
[0021] Figure 3 is a flow chart of wireless channel assessment in Embodiment 1 of the present application;
[0022] Figure 4 It is a structural diagram of a wireless channel assessment device provided in Embodiment 2 of the present application;
[0023] Figure 5 It is a structural schematic diagram of an electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.
[0025] The wireless channel evaluation method provided in the present application aims to evaluate the channel communication quality according to the predicted channel parameter information based on the channel parameter information of the historical period and the channel parameter information of the target evaluation period predicted by the prediction model, thereby improving the accuracy and timeliness of the wireless channel evaluation.
[0026] In the relevant wireless channel assessment scheme, taking the connection scenario between the access device and the wireless WiFi router as an example, in order to find a better wireless channel, the access device needs to scan all channels (2.4G and 5G), and the scanning time can be as short as about 5S or as long as more than 10S. During the scanning, the access device cannot be connected to the Internet. In order to avoid affecting the normal use of the access device, the above-mentioned full-channel scanning operation will only be performed when it is idle (not connected to the Internet).
[0027] However, in actual use scenarios, wireless WiFi, whether for home or commercial use, is rarely completely idle according to the data collected by the access device, that is, there are few opportunities for channel scanning. Therefore, the access device mainly relies on channel scanning when it is just powered on, and then uses the rare idle time in the work project to scan the channels. This will cause the access device to be unable to understand the real-time wireless channel situation, and can only select the wireless channel based on the channel parameter information collected when the device was turned on or idle in the past, and there is a certain channel evaluation error. If you want to understand the communication quality of each wireless channel in real time, you need to add an additional wireless network card specifically for channel scanning, which will undoubtedly increase the additional cost of use. Based on this, a wireless channel evaluation method of an embodiment of the present application is provided to solve the technical problem of evaluation errors caused by untimely wireless channel evaluation.
[0028] Embodiment 1:
[0029] Figure 1 A flowchart of a wireless channel assessment method provided in Embodiment 1 of the present application is given. The wireless channel assessment method provided in this embodiment can be executed by a wireless channel assessment device, which can be implemented by software and / or hardware. The wireless channel assessment device can be composed of two or more physical entities, or it can be composed of one physical entity. Generally speaking, the wireless channel assessment device can be a wireless network access device such as a computer, a mobile phone, a tablet, a smart board, etc.
[0030] The following description is made by taking the wireless network access device as an example of the subject of executing the wireless channel assessment method. Figure 1 , the wireless channel assessment method specifically includes:
[0031] S110, obtaining a channel identifier and a target evaluation period of each wireless channel;
[0032] S120, inputting the channel identifier and the target evaluation period into a pre-built prediction model, outputting channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model pre-uses channel parameter information of wireless channels in different periods as training samples, and uses the training samples to perform model training, and determines corresponding model parameters, wherein the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods;
[0033] S130. Determine channel evaluation results of each wireless channel based on the channel parameter prediction information, and select a target channel for connection in the target evaluation period based on the channel evaluation results.
[0034] In the process of wireless channel evaluation, the embodiment of the present application predicts the channel parameter information of the access device of the wireless network in the future according to the channel parameter information collected in different historical time periods in the past, and obtains the channel parameter information of the time period in which the access device needs to perform channel evaluation. Among them, a prediction model is pre-constructed for the prediction of channel parameters. When performing channel parameter prediction, the channel identifier of the wireless channel to be predicted and the time period to be predicted are obtained, and the time period is defined as the target evaluation time period. The channel identifier and the target evaluation time period are input into the prediction model, and the channel parameter information of the target evaluation time period is obtained by prediction of the prediction model, which is defined as the channel parameter prediction information.
[0035] For example, in order to predict the channel parameter information of each available channel between the access device and the wireless access point (such as a Wi-Fi router) at 12:00 on the same day, the channel identifiers of each available channel of the wireless access point and the target evaluation period (12:00) are obtained, and they are input into the prediction model to obtain the channel parameter prediction information of each available channel predicted at 12:00 on the same day. In this way, channel evaluation of each available channel is performed, and the channel with the best evaluation is selected and defined as the target channel. The access device connects to the target channel at 12:00 on the same day to achieve a better wireless communication effect.
[0036] It should be noted that when the access device communicates wirelessly with the wireless access point, the interference of the wireless channel has certain regularity at different time periods. Based on the distribution regularity of the wireless channel interference at different time periods, the channel parameter information of the wireless channel can be predicted.
[0037] Taking the use scenarios of conference boards and educational boards as examples, the working environment of the former is mainly corporate conference rooms, while the working environment of the latter is mainly schools or educational venues. According to on-site feedback and actual collected data, the interference of its wireless channels has a relatively large regularity. For example, in the environment of the conference room, the wireless network is particularly busy during the working hours on weekdays, and relatively idle at other times; and the educational environment is similar, the network environment is relatively busy during the lecture period, and relatively idle at other times. In addition, in the same environment, the working status of other devices (such as working channels, signal strength, work busyness, etc.) is also relatively stable, that is, the interference of the network environment also has a regularity to follow.
[0038] Based on this feature, the channel parameter information of each wireless channel in different time periods is obtained as the training sample of the prediction model for model training, and the distribution law of the channel parameter information of each wireless channel in different time periods is obtained. The prediction model can predict the channel parameter prediction information of the target estimation time period based on this law.
[0039] Then, the channel quality of each wireless channel is evaluated through the channel parameter prediction information provided by the prediction model, and the channel evaluation results of each wireless channel in the target evaluation period are determined. Based on the channel evaluation results, the corresponding target channel connection can be selected in the target evaluation period. Since the channel parameter prediction information of the wireless channel is predicted according to the distribution law of the channel parameter information of the wireless channel in different time periods, the channel evaluation results obtained in this way can avoid evaluation errors, improve the accuracy of channel evaluation, and optimize communication quality. At the same time, the channel parameter information is provided by prediction for wireless channel evaluation. Compared with the method of directly using the channel parameter information collected in the past idle period for wireless channel evaluation, the real-time performance of the channel evaluation can be improved, and the accuracy of the wireless channel evaluation can be further improved.
[0040] Specifically, refer to Figure 2 , a flowchart for constructing a prediction model in an embodiment of the present application is provided. Before executing the above-mentioned wireless channel assessment method, training samples are collected in advance for prediction model training. The training samples include a first sample and a second sample. The first sample is collected during a specified idle period and contains channel parameter information of each wireless channel. The second sample is collected during the operation of the device and contains channel parameter information of the main channel.
[0041] It is understandable that since the access device cannot connect to other devices when scanning all available channels, it is necessary to perform full channel scanning when the access device is in an idle period. If the access device is connected to the network, it can only scan the channel to which the current access device is connected (i.e., the main channel). Based on this, by monitoring whether the access device is currently in an idle state (not connected to other devices), if so, the channel parameter information of all channels is collected to obtain a first sample; if not, the channel parameter information of the main channel is collected to obtain a second sample.
[0042] Optionally, the designated idle period includes a device startup period and a period when the device is not connected to other nodes. Generally speaking, when the access device is powered on, the access device is in an idle state, so a full channel scan is performed. Afterwards, during the operation of the access device, according to the set idle state judgment rule, when the device is not connected to other nodes for a set period of time, it is determined that it is in an idle state, and the access device performs a full channel scan.
[0043] For full channel scanning, the current time, channel identifier, channel bandwidth, channel congestion (Busy Time), channel noise floor, channel load, channel noise floor, number of channel base station subsystems (number of BSS-IDs) and signal strength of each wireless channel can be obtained. For main channel scanning, the type of channel parameter information obtained is consistent with full channel scanning, but only the channel parameter information of the main channel part is obtained. For example, the currently available wireless channels are 1-11 for 2.4G, 36, 40, 44, 48... for 5G, and the main channel is 36. Then the first sample collects the channel parameter information of all available channels, and the second sample only collects the channel parameter information of the main channel 36.
[0044] The channel parameter information of each wireless channel in different time periods obtained based on the above channel scanning can be used as training samples for model training. Among them, according to the characteristics of the Wi-Fi protocol and the actual test situation, the above-mentioned channel parameters directly determine the channel quality of the corresponding wireless channel (the interference degree of the channel). The prediction model determines the distribution law of the channel parameter information of each wireless channel in different time periods based on the training sample. And determine the influence parameters of the actual channel parameter information of the same channel in the historical time period on the channel parameter prediction information of the target evaluation time period, so as to obtain the prediction parameters of the prediction model. For example, according to the distribution law of the channel parameter information of channel A in different time periods, its channel parameter information a0 at 12:00 in the historical time period is determined, and the influence parameter of its channel parameter information a0 in the historical time period on the channel parameter prediction information a1 of the target evaluation time period is α, then the channel parameter prediction information a1 can be obtained through the prediction model, and the calculation formula is as follows:
[0045] a1=α*a0
[0046] In this way, the prediction of channel parameter information can be achieved. It should be noted that in practical applications, the prediction model can adaptively set corresponding model parameters according to the distribution law of channel parameter information in different time periods and the influence of historical channel parameter information on channel parameter prediction information, and determine the corresponding model parameters through model training for subsequent model prediction. The prediction model can be trained using a convolutional neural network (CNN). The embodiment of the present application does not impose fixed restrictions on the specific training method of the prediction model, which will not be elaborated here.
[0047] Afterwards, based on the prediction model, when it is necessary to predict the channel parameter information of the wireless channel in the target estimation period, the corresponding channel identifier and the target estimation period can be input, and then the corresponding predicted channel parameter prediction information can be output through the prediction model.
[0048] Since the channel parameters of each wireless channel at different historical periods are mainly collected, such as channel congestion, channel noise floor, channel load, number of channel base station subsystems, and channel strength, the information type of the channel parameter prediction information includes any one or more of channel congestion, channel noise floor, channel load, number of channel base station subsystems, and channel strength. Therefore, the model input and output of the prediction model are shown in Table 1 below:
[0049] Table 1: Prediction model input and output
[0050]
[0051] Referring to Table 1 above, according to actual prediction requirements, the model input may also include channel bandwidth information. By providing more comprehensive model input information, more accurate prediction results may be obtained.
[0052] Optionally, the using the training samples to perform model training includes:
[0053] The training samples are converted into numerical data according to set conversion rules, and the prediction model is trained based on the numerical data.
[0054] In order to improve the efficiency of model training and prediction, after collecting training samples, it is necessary to convert some non-numerical data of the training samples into numerical data. For example, May 20 can be converted into the number of days starting from May 1; 0-1 o'clock can be represented by 0, 1-2 o'clock can be represented by 1, and so on; bandwidth 20M is represented by 0, 40M is represented by 1, 80M is represented by 2, and so on. Based on the above numerical training samples, the system can start the model training thread and save the model parameters after the training is completed. Then the channel parameters of the future time period can be predicted.
[0055] For example, to predict the channel parameters of 36 channels with 20M / 40M bandwidth at 0-1 / 1-2 on January 22, the input to the above model is as follows:
[0056] 21,0,36,0
[0057] 21,1,36,0
[0058] 21,0,36,1
[0059] 21,1,36,1
[0060] Based on the above model input, the model will predict the numerical channel parameter prediction information in the above four cases, namely the numerical information of Busy Time, noise floor, load, BSS number and signal strength. The numerical representation of model input and output information facilitates the model to calculate, display and store, improves model training and calculation efficiency, and enhances user experience.
[0061] Based on the above channel parameter prediction information, the channel evaluation results of each wireless channel in different time periods in the future can be obtained according to the channel evaluation algorithm, and the channel selection of the target evaluation period can be performed based on the channel evaluation results.
[0062] Wherein, determining the channel assessment result of each wireless channel based on the channel parameter prediction information includes:
[0063] Obtain the influencing factor of the channel parameter prediction information of each information type, calculate the channel quality score of the wireless channel based on the influencing factor and the corresponding channel parameter prediction information of each information type, and use the channel quality score as the channel evaluation result. The influencing factor represents the influence weight of the channel parameter prediction information of the corresponding information type on the channel evaluation result.
[0064] According to the influence of different channel parameter information on the channel evaluation results, accurate channel evaluation results can be obtained by weighted calculation. Among them, the channel congestion has the greatest impact (accounting for 50%) and is negatively correlated with the channel quality (that is, the greater the channel congestion, the lower the channel score). The channel congestion is related to the clock frequency of the main chip. The general statistical method is that the system sends M packets continuously, and N packets are blocked. The system calculates the interval between continuous packet transmissions based on its own clock frequency, and then multiplies it by N to get the channel congestion. The channel noise floor has the second largest impact on the channel score (accounting for 20%), which is negatively correlated with the channel quality. The channel load has an impact of 15% on the channel score and is positively correlated with the channel quality. The number of channel BSSs has an impact of 10% on the channel score and is negatively correlated with the channel quality. The signal strength has an impact of 5% on the channel score and is positively correlated with the channel quality.
[0065] Based on the characteristics of the above-mentioned channel parameter information, the influence factors of the corresponding channel parameter prediction information are adaptively set, and then the channel quality scores of each channel parameter prediction information are obtained by weighted calculation. Finally, the wireless channel with the highest channel quality score is selected as the target channel of the access device for connection during the target estimation period to ensure good communication effects in real time. The proportion of the influence factors can be adjusted according to the actual test situation, and the weighted calculation formula can also be adaptively set. The embodiment of the present application does not impose fixed restrictions on the specific calculation method, which will not be elaborated here.
[0066] Afterwards, when the access device is connected to the target channel during the target estimation period, channel parameter information of the target channel is further collected, and the prediction model is trained based on the channel parameter information to correct the model parameters of the prediction model.
[0067] Reference Figure 3 The training samples obtained after the main channel scan and the idle full channel scan can be used to build a prediction model to evaluate the channel quality and provide reference information for channel switching decisions. After that, every set period of time, the channel parameter information of the target channel currently accessed by the access device is collected, and the prediction model is trained using this part of the channel parameter information to make the model prediction result closer to the actual channel parameter information.
[0068] For example, when the system starts running, only the channel parameter information obtained by the main channel scan and the full channel scan during idle time in the past day is collected as a training sample to train the prediction model, and the model is used to predict the channel parameter prediction information. After that, one day of collected data will be added every day (that is, the channel parameter information obtained by the main channel scan and the full channel scan during idle time in the past day), and this part of information will be used as a training sample to correct the prediction model. As the data increases, the prediction model will become closer and closer to reality and can better reflect the actual channel quality. After each data update, the model training thread needs to be restarted, and then the channel parameter prediction information is predicted for the future time period. So far, by continuously accumulating collected data to train the prediction model, the prediction model can grasp the channel parameter prediction distribution law of each wireless channel in different time periods more accurately, and the predicted channel parameter information is also more accurate. In this way, the accuracy of wireless channel evaluation is further improved and the communication quality is improved.
[0069] In the above, by obtaining the channel identifier and target evaluation period of each wireless channel; inputting the channel identifier and target evaluation period into a pre-built prediction model, outputting the channel parameter prediction information of each wireless channel in the target evaluation period, the prediction model pre-uses the channel parameter information of the wireless channel in different periods as training samples, and uses the training samples to train the model, and determines the corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods; based on the channel parameter prediction information, the channel evaluation results of each wireless channel are determined, so as to select the target channel for connection in the target evaluation period based on the channel evaluation results. By adopting the above technical means, by pre-training the prediction model with the channel parameter information of different periods of the wireless channel, the channel parameter prediction information of the target evaluation period is predicted based on the channel parameter information of the historical period and the prediction model, so as to evaluate the channel communication quality according to the predicted channel parameter prediction information, and realize accurate and timely wireless channel evaluation. Then, according to the channel evaluation results, a wireless channel with relatively better channel communication quality can be selected for connection, thereby improving the quality of wireless communication.
[0070] Embodiment 2:
[0071] Based on the above embodiments, Figure 4 This is a schematic diagram of the structure of a wireless channel assessment device provided in Embodiment 2 of the present application. Figure 4 The wireless channel assessment device provided in this embodiment specifically includes: an acquisition module 21, an estimation module 22 and a selection module 23.
[0072] The acquisition module 21 is used to determine the channel identification and target evaluation period of each wireless channel;
[0073] The estimation module 22 is used to input the channel identifier and the target evaluation period into a pre-built prediction model, and output the channel parameter prediction information of each wireless channel in the target evaluation period. The prediction model uses the channel parameter information of the wireless channel in different periods as training samples in advance, and uses the training samples to perform model training to determine the corresponding model parameters. The model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods;
[0074] The selection module 23 is used to determine the channel evaluation results of each wireless channel based on the channel parameter prediction information, so as to select the target channel for connection in the target evaluation period based on the channel evaluation results.
[0075] Furthermore, the training samples include a first sample and a second sample, the first sample is collected during a specified idle period and includes channel parameter information of each wireless channel, and the second sample is collected during the operation of the device and includes channel parameter information of the main channel.
[0076] Furthermore, the designated idle period includes a period when the device is powered on and a period when the device is not connected to other nodes.
[0077] Furthermore, the using the training samples to perform model training includes:
[0078] The training samples are converted into numerical data according to set conversion rules, and the prediction model is trained based on the numerical data.
[0079] Further, determining the channel evaluation result of each wireless channel based on the channel parameter prediction information includes:
[0080] Obtain the influencing factor of the channel parameter prediction information of each information type, calculate the channel quality score of the wireless channel based on the influencing factor and the corresponding channel parameter prediction information of each information type, and use the channel quality score as the channel evaluation result. The influencing factor represents the influence weight of the channel parameter prediction information of the corresponding information type on the channel evaluation result.
[0081] Furthermore, the information type of the channel parameter prediction information includes any one or more of channel congestion level, channel noise floor, channel load, number of channel base station subsystems and channel strength.
[0082] Further, after selecting a target channel for connection in the target evaluation period based on the channel evaluation result, the method further includes:
[0083] Channel parameter information of the target channel is collected, and the prediction model is trained based on the channel parameter information to correct the model parameters of the prediction model.
[0084] In the above, by obtaining the channel identifier and target evaluation period of each wireless channel; inputting the channel identifier and target evaluation period into a pre-built prediction model, outputting the channel parameter prediction information of each wireless channel in the target evaluation period, the prediction model pre-uses the channel parameter information of the wireless channel in different periods as training samples, and uses the training samples to train the model, and determines the corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods; based on the channel parameter prediction information, the channel evaluation results of each wireless channel are determined, so as to select the target channel for connection in the target evaluation period based on the channel evaluation results. By adopting the above technical means, by pre-training the prediction model with the channel parameter information of different periods of the wireless channel, the channel parameter prediction information of the target evaluation period is predicted based on the channel parameter information of the historical period and the prediction model, so as to evaluate the channel communication quality according to the predicted channel parameter prediction information, and realize accurate and timely wireless channel evaluation. Then, according to the channel evaluation results, a wireless channel with relatively better channel communication quality can be selected for connection, thereby improving the quality of wireless communication.
[0085] The wireless channel assessment device provided in the second embodiment of the present application can be used to execute the wireless channel assessment method provided in the above-mentioned first embodiment, and has corresponding functions and beneficial effects.
[0086] Embodiment three:
[0087] Embodiment 3 of the present application provides an electronic device, referring to Figure 5The electronic device includes: a processor 31, a memory 32, a communication module 33, an input device 34 and an output device 35. The number of processors in the electronic device can be one or more, and the number of memories in the electronic device can be one or more. The processor, memory, communication module, input device and output device of the electronic device can be connected via a bus or other means.
[0088] As a computer-readable storage medium, the memory can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the wireless channel assessment method described in any embodiment of the present application (for example, the acquisition module, the estimation module and the selection module in the wireless channel assessment device). The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.
[0089] The communication module is used for data transmission.
[0090] The processor executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory, that is, implements the above-mentioned wireless channel assessment method.
[0091] The input device can be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device can include display devices such as display screens.
[0092] The electronic device provided above can be used to execute the wireless channel assessment method provided in the above embodiment 1, and has corresponding functions and beneficial effects.
[0093] Embodiment 4:
[0094] An embodiment of the present application also provides a storage medium containing computer executable instructions, which are used to execute a wireless channel evaluation method when executed by a computer processor. The wireless channel evaluation method includes: obtaining a channel identifier and a target evaluation period of each wireless channel; inputting the channel identifier and the target evaluation period into a pre-constructed prediction model, and outputting channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model pre-uses the channel parameter information of the wireless channel in different time periods as training samples, and uses the training samples to perform model training to determine corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different time periods; determining a channel evaluation result of each wireless channel based on the channel parameter prediction information, so as to select a target channel for connection in the target evaluation period based on the channel evaluation result.
[0095] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.
[0096] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application, whose computer executable instructions are not limited to the wireless channel assessment method described above, can also execute related operations in the wireless channel assessment method provided in any embodiment of the present application.
[0097] The wireless channel assessment device, storage medium and electronic device provided in the above embodiments can execute the wireless channel assessment method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the wireless channel assessment method provided in any embodiment of the present application.
[0098] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.
Claims
1. A wireless channel assessment method, characterized in that: include: Obtaining a channel identifier and a target evaluation period for each wireless channel; Input the channel identifier and the target evaluation period into a pre-built prediction model, and output channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model uses the channel parameter information of the wireless channel in different periods as training samples in advance, and uses the training samples to perform model training to determine corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods; The channel evaluation results of each wireless channel are determined based on the channel parameter prediction information, so as to select a target channel for connection in the target evaluation period based on the channel evaluation results.
2. The wireless channel assessment method according to claim 1, characterized in that: The training samples include a first sample and a second sample. The first sample is collected during a specified idle period and includes channel parameter information of each wireless channel. The second sample is collected during the operation of the device and includes channel parameter information of the main channel.
3. The wireless channel assessment method according to claim 2, characterized in that: The designated idle period includes a period when the device is powered on and a period when the device is not connected to other nodes.
4. The wireless channel assessment method according to claim 1, characterized in that: The using the training samples to perform model training includes: The training samples are converted into numerical data according to set conversion rules, and the prediction model is trained based on the numerical data.
5. The wireless channel assessment method according to claim 1, characterized in that: The determining the channel evaluation result of each wireless channel based on the channel parameter prediction information includes: Obtain the influencing factor of the channel parameter prediction information of each information type, calculate the channel quality score of the wireless channel based on the influencing factor and the corresponding channel parameter prediction information of each information type, and use the channel quality score as the channel evaluation result. The influencing factor represents the influence weight of the channel parameter prediction information of the corresponding information type on the channel evaluation result.
6. The wireless channel assessment method according to claim 5, characterized in that: The information type of the channel parameter prediction information includes any one or more of channel congestion level, channel noise floor, channel load, number of channel base station subsystems and channel strength.
7. The wireless channel assessment method according to claim 1, characterized in that: After selecting a target channel for connection in the target evaluation period based on the channel evaluation result, the method further includes: Channel parameter information of the target channel is collected, and the prediction model is trained based on the channel parameter information to correct the model parameters of the prediction model.
8. A wireless channel assessment device, characterized in that: include: An acquisition module, used to determine the channel identification and target evaluation period of each wireless channel; An estimation module is used to input the channel identifier and the target evaluation period into a pre-built prediction model, and output channel parameter prediction information of each wireless channel in the target evaluation period, wherein the prediction model uses the channel parameter information of the wireless channel in different periods as training samples in advance, and uses the training samples to perform model training to determine corresponding model parameters, and the model parameters are used to characterize the channel parameter distribution law of each wireless channel in different periods; A selection module is used to determine the channel evaluation results of each wireless channel based on the channel parameter prediction information, so as to select a target channel for connection in the target evaluation period based on the channel evaluation results.
9. An electronic device, characterized in that: include: memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the wireless channel assessment method as described in any one of claims 1-7.
10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the wireless channel assessment method according to any one of claims 1 to 7 when executed by a computer processor.