A wireless signal optimization method and electronic device

Abstract

This application discloses a wireless signal optimization method and electronic device. It acquires channel state information of each channel within the wireless signal coverage area, as well as location and speed information of each terminal device, at each historical time within the most recent historical time period. Based on a channel capacity prediction model, it determines the predicted channel capacity of each channel at the predicted time. Based on the predicted channel capacity, it optimizes channel switching for the wireless signal transmitter. Based on a location prediction model, it determines the predicted location information of each terminal device at the predicted time. Based on the predicted location information of each terminal device at the predicted time, it optimizes the network access permissions of the terminal devices. This application combines channel capacity prediction and location information prediction for each channel to achieve channel optimization based on prediction information and network access permission optimization for terminal devices. This improves the timeliness and effectiveness of wireless signal optimization.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a wireless signal optimization method and electronic device. Background Technology

[0002] In existing technologies, signal coverage optimization for wireless networks typically relies on channel estimation and network parameter adjustment. These methods predict channel conditions by analyzing the propagation characteristics of wireless signals, such as signal strength and signal-to-noise ratio, and adjust the router's signal coverage and strength accordingly. For example, through channel estimation, a signal transmitter (such as a router) can dynamically select the optimal channel and adjust its transmission power to maximize network coverage and signal quality.

[0003] Traditional wireless signal optimization often relies on static or periodic channel state measurements, resulting in a lag that cannot respond in real time to rapid changes in network conditions. Consequently, existing wireless signal optimization methods suffer from poor real-time performance and ineffective optimization results. Summary of the Invention

[0004] This application provides a wireless signal optimization method and an electronic device to solve the problems of poor real-time performance and unsatisfactory optimization effect in existing wireless signal optimization methods.

[0005] In a first aspect, this application provides a wireless signal optimization method, the method comprising:

[0006] For each historical moment within the historical time period closest to the current moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0007] For each channel, the channel state information of each historical moment of the channel, the location information and speed information of each terminal device are input into a pre-trained channel capacity prediction model. Based on the channel capacity prediction model, the predicted channel capacity of the channel at the prediction moment is determined. Based on the predicted channel capacity of each channel at the prediction moment, the channel switching of the wireless signal transmitter is optimized.

[0008] For each terminal device, the location and speed information of the terminal device at each historical moment are input into a pre-trained location prediction model. Based on the location prediction model, the predicted location information of the terminal device at the predicted moment is determined. Based on the predicted location information of the terminal device at the predicted moment, the network access permissions of the terminal device are optimized.

[0009] The above technical solution has the following advantages or beneficial effects:

[0010] This application first obtains the channel state information of each channel within the wireless signal coverage area, as well as the location and speed information of each terminal device, for each historical time within the most recent historical time period. Then, based on a pre-trained channel capacity prediction model, the predicted channel capacity of each channel at the predicted time is determined. Channel switching for the wireless signal transmitter is optimized based on the predicted channel capacity. Similarly, based on a pre-trained location prediction model, the predicted location information of each terminal device at the predicted time is determined. Network access permissions for the terminal devices are optimized based on the predicted location information of each terminal device at the predicted time. This application combines channel capacity prediction for each channel and location information prediction for each terminal device to achieve channel optimization and network access permission optimization based on prediction information. On the one hand, optimizing the wireless signal based on prediction information improves the timeliness of wireless signal optimization; on the other hand, optimizing the channels of the wireless signal transmitter and optimizing the network access permissions of the terminal devices improves the effectiveness of wireless signal optimization.

[0011] Furthermore, based on the predicted channel capacity of each channel at the prediction time, the channel switching of the wireless signal transmitter is optimized, including:

[0012] For each channel, a predicted score value for the channel is determined based on the predicted channel capacity at the prediction time; the channel of the wireless signal transmitter is switched to a target channel with a predicted score value greater than a preset score threshold.

[0013] Furthermore, if there is no channel with a predicted score greater than a preset score threshold, the method further includes:

[0014] By using Access Control Lists (ACLs), the pre-defined non-critical network access permissions for each terminal device are set to denied.

[0015] Furthermore, optimizing the network access permissions of the terminal device based on its predicted location information at the predicted time includes:

[0016] Based on the predicted position information of the terminal device at the predicted time, the predicted sub-region of the terminal device at the predicted time is determined;

[0017] Based on the pre-defined first network access permissions corresponding to each sub-region, the second network access permissions corresponding to the predicted sub-region are determined; and the network access permissions of the terminal device are set according to the second network access permissions through the Access Control List (ACL).

[0018] Furthermore, the method also includes:

[0019] Based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time, the target signal strength at the predicted time is determined; at the predicted time, the wireless signal transmitter is controlled to transmit a wireless signal according to the target signal strength.

[0020] Furthermore, the process of determining the target signal strength at the predicted time includes:

[0021] The predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time are input into the pre-trained signal strength prediction model. Based on the signal strength prediction model, the target signal strength at the predicted time is determined.

[0022] Furthermore, the training process of the channel capacity prediction model includes:

[0023] The channel state information of each historical moment of the sample channel in the first training set, the location information and speed information of each sample terminal device, and the channel capacity label are input into the channel capacity prediction model to be trained. Based on the channel capacity prediction model, the sample predicted channel capacity of the sample channel at the sample prediction moment is determined. According to the sample predicted channel capacity and the channel capacity label, a first loss value is determined. The channel capacity prediction model to be trained is iteratively trained according to the first loss value. Wherein, the channel capacity label refers to the actual channel capacity of the sample channel at the sample prediction moment.

[0024] Furthermore, the training process of the location prediction model includes:

[0025] The location information, velocity information, and location information label of each historical moment of the sample terminal device in the second training set are input into the location prediction model to be trained. Based on the location prediction model, the sample predicted location information of the sample terminal device at the sample prediction moment is determined. A second loss value is determined according to the sample predicted location information and the location information label. The location prediction model to be trained is iteratively trained according to the second loss value. The location information label refers to the actual location information of the sample terminal device at the sample prediction moment.

[0026] Furthermore, the training process of the signal strength prediction model includes:

[0027] The sample prediction channel capacity of the sample channel in the third training set at the sample prediction time, the predicted location information of each sample terminal device, the access permissions of each network recorded in the Access Control List (ACL) at the sample prediction time, and the signal strength label are input into the signal strength prediction model to be trained. Based on the signal strength prediction model to be trained, the sample signal strength at the sample prediction time is determined. A third loss value is determined according to the sample signal strength and the signal strength label. The signal strength prediction model to be trained is iteratively trained according to the third loss value. The signal strength label refers to the actual signal strength of the wireless signal transmitted by the wireless transmitter at the sample prediction time.

[0028] Secondly, this application provides a wireless signal optimization device, the device comprising:

[0029] The acquisition module is used to acquire, for each historical moment within the historical time period closest to the current moment, the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location information and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0030] The channel optimization module is used to input the channel state information of each historical moment of the channel, the location information and speed information of each terminal device into a pre-trained channel capacity prediction model for each channel, and determine the predicted channel capacity of the channel at the prediction moment based on the channel capacity prediction model; and optimize the channel switching of the wireless signal transmitter according to the predicted channel capacity of each channel at the prediction moment.

[0031] The network optimization module is used to input the location information and speed information of the terminal device at each historical moment into a pre-trained location prediction model for each terminal device, determine the predicted location information of the terminal device at the prediction moment based on the location prediction model, and optimize the network access permissions of the terminal device based on the predicted location information of the terminal device at the prediction moment.

[0032] The channel optimization module is specifically used to determine the predicted score value of each channel based on the predicted channel capacity of the channel at the prediction time; and to control the channel switching of the wireless signal transmitter to the target channel with a predicted score value greater than a preset score threshold.

[0033] The channel optimization module is further configured to, if there is no channel with a predicted score value greater than a preset score threshold, set the access permissions of the pre-set non-critical networks of each terminal device to denied through an Access Control List (ACL).

[0034] The network optimization module is specifically used to determine the predicted sub-region of the terminal device at the predicted time based on the predicted location information of the terminal device at the predicted time; determine the second network access permission corresponding to the predicted sub-region based on the first network access permission corresponding to each pre-set sub-region; and set the network access permission of the terminal device according to the second network access permission through the Access Control List (ACL).

[0035] The device further includes:

[0036] The signal strength optimization module is used to determine the target signal strength at the predicted time based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time; and at the predicted time, control the wireless signal transmitter to transmit a wireless signal according to the target signal strength.

[0037] The signal strength optimization module is specifically used to input the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the prediction time into the pre-trained signal strength prediction model, and determine the target signal strength at the prediction time based on the signal strength prediction model.

[0038] The device further includes:

[0039] The first training module is used to input the channel state information of each sample historical moment of the sample channel in the first training set, the location information and speed information of each sample terminal device, and the channel capacity label into the channel capacity prediction model to be trained; determine the sample predicted channel capacity of the sample channel at the sample prediction moment based on the channel capacity prediction model; determine a first loss value according to the sample predicted channel capacity and the channel capacity label; and iteratively train the channel capacity prediction model to be trained according to the first loss value; wherein, the channel capacity label refers to the actual channel capacity of the sample channel at the sample prediction moment.

[0040] The device further includes:

[0041] The second training module is used to input the location information, velocity information, and location information label of each historical moment of the sample terminal device in the second training set into the location prediction model to be trained; determine the sample predicted location information of the sample terminal device at the sample prediction moment based on the location prediction model; determine a second loss value based on the sample predicted location information and the location information label; and iteratively train the location prediction model to be trained based on the second loss value; wherein, the location information label refers to the actual location information of the sample terminal device at the sample prediction moment.

[0042] The device further includes:

[0043] The third training module is used to input the sample prediction channel capacity of the sample channel in the third training set at the sample prediction time, the predicted location information of each sample terminal device, the access permissions of each network recorded in the Access Control List (ACL) at the sample prediction time, and the signal strength label into the signal strength prediction model to be trained; based on the signal strength prediction model to be trained, determine the sample signal strength at the sample prediction time; determine a third loss value according to the sample signal strength and the signal strength label; and iteratively train the signal strength prediction model to be trained according to the third loss value; wherein, the signal strength label refers to the actual signal strength of the wireless signal transmitted by the wireless signal transmitter at the sample prediction time.

[0044] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0045] Memory, used to store computer programs;

[0046] A processor, used to execute a program stored in memory, implements the method described.

[0047] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described herein.

[0048] Fifthly, this application provides a computer program product comprising an executable program that is executed by a processor to implement the method described. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This application provides a schematic diagram of the first wireless signal optimization process.

[0051] Figure 2 This is a schematic diagram of the second wireless signal optimization process provided in this application;

[0052] Figure 3 A schematic diagram illustrating the process of optimizing network access permissions for terminal devices provided in this application;

[0053] Figure 4 A schematic diagram of the third wireless signal optimization process provided in this application;

[0054] Figure 5 The wireless signal optimization flowchart provided in this application;

[0055] Figure 6 A schematic diagram of the wireless signal optimization device provided in this application;

[0056] Figure 7 A schematic diagram of the electronic device structure provided in this application. Detailed Implementation

[0057] To make the objectives and implementation methods of this application clearer, the exemplary implementation methods of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments of this application. Obviously, the exemplary embodiments described are only some embodiments of this application, and not all embodiments.

[0058] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0059] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0060] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0061] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0063] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the described embodiments and various different variations of embodiments suitable for specific use considerations.

[0064] The following are definitions of terms used in this application:

[0065] Access Control List (ACL): A rule-based network security measure used to control access permissions to network resources.

[0066] Channel State Information (CSI): A set of parameters that describe the characteristics of a wireless channel, including channel capacity, signal attenuation, etc.

[0067] Channel capacity: The maximum transmission rate that a wireless signal can achieve on a specific channel.

[0068] Signal attenuation: The phenomenon that wireless signals gradually weaken during propagation due to factors such as distance and obstacles.

[0069] In existing technologies, signal coverage optimization for wireless networks typically relies on channel estimation and network parameter adjustment. These methods predict channel conditions by analyzing the propagation characteristics of wireless signals, such as signal strength and signal-to-noise ratio, and adjust the router's signal coverage and strength accordingly. For example, through channel estimation, the router can dynamically select the optimal channel and adjust its transmit power to maximize network coverage and signal quality.

[0070] However, existing technologies have some drawbacks:

[0071] Lack of dynamism: Traditional channel estimation methods are often based on static or periodic measurements, which cannot respond in real time to rapid changes in network conditions.

[0072] Ignoring device behavior: Most methods do not take into account the actual movement patterns and behaviors of the device, which may result in signal optimization that does not match the actual needs of the user.

[0073] Insufficient utilization of ACLs: Related technologies neglect the role of Network Access Control Lists (ACLs) in network optimization. ACL rules can precisely control access permissions to network resources, but in current wireless network management, the application of ACL rules is usually based on static configuration and not dynamically combined with channel conditions and user behavior. This results in potentially inflexible allocation of network resources, failing to adapt to changes in user mobility and network conditions.

[0074] To address the aforementioned problems, this application proposes a wireless signal optimization method. Figure 1 The first wireless signal optimization process provided in this application includes the following steps:

[0075] S101: For each historical moment within the historical time period closest to the current moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location information and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0076] S102: For each channel, the channel state information of each historical moment of the channel, the location information and speed information of each terminal device are input into the pre-trained channel capacity prediction model, and the predicted channel capacity of the channel at the prediction moment is determined based on the channel capacity prediction model; the channel switching of the wireless signal transmitter is optimized according to the predicted channel capacity of each channel at the prediction moment.

[0077] S103: For each terminal device, input the location information and speed information of the terminal device at each historical moment into a pre-trained location prediction model, determine the predicted location information of the terminal device at the prediction moment based on the location prediction model, and optimize the network access permissions of the terminal device according to the predicted location information of the terminal device at the prediction moment.

[0078] The wireless signal optimization method provided in this application is applied to an electronic device, which may be a network-side device.

[0079] First, for each historical moment within the most recent historical time period, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location and speed information of each terminal device. The most recent historical time period is, for example, time period T. Divide T into equal historical moments to obtain each historical moment t within that historical time period. Then, for each historical moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location and speed information of each terminal device. The channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio. Optionally, channel state information and location information of each terminal device can be collected using Wi-Fi positioning, GPS, or other sensor technologies. For each terminal device, based on its first location information at the first moment and its second location information at the previous moment, the moving distance can be determined. Based on the ratio of the moving distance to the time interval between the first and previous moments, the speed information of the terminal device at the first moment can be determined. The speed information of each terminal device at that historical moment can be determined using the above method.

[0080] The electronic device is equipped with a pre-trained channel capacity prediction model. For each channel, the channel state information at each historical moment, the location information of each terminal device, and the speed information are input into the pre-trained channel capacity prediction model. Based on the channel capacity prediction model, the predicted channel capacity at the predicted time is determined. Then, the channel switching of the wireless signal transmitter is optimized according to the predicted channel capacity of each channel at the predicted time. Optionally, the channel with the largest predicted channel capacity at the predicted time can be selected as the target channel, and the wireless signal transmitter's channel can be switched to the target channel. It should be noted that if the wireless signal transmitter's channel at the current moment is the target channel, no channel switching is required. Alternatively, channels with a capacity greater than a preset channel capacity threshold can be selected as candidate channels. If the wireless signal transmitter's channel at the current moment is any candidate channel, no channel switching is required; if the wireless signal transmitter's channel at the current moment is not a candidate channel, the wireless signal transmitter's channel is switched to any candidate channel. In this way, when the predicted time arrives, the wireless signal can be transmitted through a high-quality channel, thereby optimizing the wireless signal.

[0081] The electronic device is equipped with a pre-trained location prediction model. For each terminal device, the location and speed information of the terminal device at each historical moment are input into the pre-trained location prediction model. Based on the location prediction model, the predicted location information of the terminal device at the predicted moment is determined. Then, based on the predicted location information of the terminal device at the predicted moment, the network access permissions of the terminal device are optimized. Optionally, the wireless signal coverage area can be divided into different sub-regions, and different sub-regions can correspond to different network access permissions. For example, if the wireless signal coverage area is a school, and the sub-region is a library area, then this sub-region can be set to block access to gaming websites. If the sub-region is an examination room, then this sub-region can be set to block access to teaching system websites, and so on.

[0082] This application first obtains the channel state information of each channel within the wireless signal coverage area, as well as the location and speed information of each terminal device, for each historical time within the most recent historical time period. Then, based on a pre-trained channel capacity prediction model, the predicted channel capacity of each channel at the predicted time is determined. Channel switching for the wireless signal transmitter is optimized based on the predicted channel capacity. Similarly, based on a pre-trained location prediction model, the predicted location information of each terminal device at the predicted time is determined. Network access permissions for the terminal devices are optimized based on the predicted location information of each terminal device at the predicted time. This application combines channel capacity prediction for each channel and location information prediction for each terminal device to achieve channel optimization and network access permission optimization based on prediction information. On the one hand, optimizing the wireless signal based on prediction information improves the timeliness of wireless signal optimization; on the other hand, optimizing the channels of the wireless signal transmitter and optimizing the network access permissions of the terminal devices improves the effectiveness of wireless signal optimization.

[0083] To improve the optimization effect of channel switching for wireless signal transmitters, Figure 2 The second wireless signal optimization process provided in this application includes the following steps:

[0084] S201: For each historical moment within the historical time period closest to the current moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location information and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0085] S202: For each channel, input the channel state information of each historical moment of the channel, the location information and speed information of each terminal device into a pre-trained channel capacity prediction model, and determine the predicted channel capacity of the channel at the prediction moment based on the channel capacity prediction model; for each channel, determine the predicted score value of the channel based on the predicted channel capacity of the channel at the prediction moment; control the channel switching of the wireless signal transmitter to the target channel with a predicted score value greater than a preset score threshold;

[0086] S203: For each terminal device, input the location information and speed information of the terminal device at each historical moment into a pre-trained location prediction model, determine the predicted location information of the terminal device at the prediction moment based on the location prediction model, and optimize the network access permissions of the terminal device according to the predicted location information of the terminal device at the prediction moment.

[0087] In this application, a pre-defined correspondence between predicted channel capacity and predicted score value is established, wherein a larger predicted channel capacity corresponds to a higher predicted score value. Optionally, different predicted channel capacity ranges are pre-defined, each corresponding to a different predicted score value. Different predicted channel capacities within a single predicted channel capacity range correspond to the same predicted score value; for different predicted channel capacity ranges, the range with the largest predicted channel capacity corresponds to a larger predicted score value.

[0088] In this application, the electronic device pre-stores a preset scoring threshold and selects any channel whose score is greater than the preset scoring threshold as the target channel. The wireless signal transmitter is then controlled to switch its channel to the target channel whose predicted score is greater than the preset scoring threshold. It should be noted that if the wireless signal transmitter's current channel is already a target channel with a score greater than the preset scoring threshold, then channel switching is unnecessary.

[0089] In this application, if there is no channel with a predicted score value greater than a preset score threshold, the method further includes:

[0090] By using Access Control Lists (ACLs), the pre-defined non-critical network access permissions for each terminal device are set to denied.

[0091] Non-critical networks can be pre-defined in electronic devices. For example, in a school setting, gaming networks and video networks can be designated as non-critical networks. If no channel has a predicted score greater than a preset score threshold, meaning the quality of all channels is relatively poor at the prediction time, access permissions for the pre-defined non-critical networks on each terminal device can be denied using an Access Control List (ACL). In other words, terminal devices are not allowed to access non-critical networks at the prediction time, thus opening up more resources for other critical networks and further optimizing the channels. It should be noted that terminal devices implement allow or deny access to corresponding websites based on the access permissions specified in the ACL.

[0092] To improve the effectiveness of optimizing network access permissions for terminal devices. Figure 3 The process diagram for optimizing network access permissions for terminal devices provided in this application includes the following steps:

[0093] S301: Based on the predicted position information of the terminal device at the predicted time, determine the predicted sub-region of the terminal device at the predicted time;

[0094] S302: Determine the second network access permission corresponding to the predicted sub-region based on the first network access permission corresponding to each pre-set sub-region; set the network access permission of the terminal device according to the second network access permission through the Access Control List (ACL).

[0095] In this application, the coverage area of ​​the wireless signal is divided into multiple sub-regions. For each terminal device, based on the predicted location information of the terminal device at the predicted time and the regional location information of each of the multiple sub-regions, the predicted sub-region to which the predicted location information of the terminal device at the predicted time belongs can be determined. The electronic device stores a pre-set first network access permission for each sub-region, which includes the access permissions of each network corresponding to the sub-region. After determining the predicted sub-region of the terminal device at the predicted time, a second network access permission for the predicted sub-region is determined based on the pre-set first network access permissions for each sub-region. Then, the network access permissions of the terminal device are set according to the second network access permission through an Access Control List (ACL). That is, each terminal device corresponds to an ACL, and the access permissions of each website included in the ACL are used to restrict the network access of the corresponding terminal device. For example, if the second network access permission for the predicted sub-region is: game websites denied, educational websites allowed, then for terminal devices whose predicted location information is within the predicted sub-region at the predicted time, game websites are set to denied and educational websites are set to allowed.

[0096] Figure 4 The third wireless signal optimization process provided in this application includes the following steps:

[0097] S401: For each historical moment within the historical time period closest to the current moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location information and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0098] S402: For each channel, the channel state information of each historical moment of the channel, the location information and speed information of each terminal device are input into the pre-trained channel capacity prediction model, and the predicted channel capacity of the channel at the prediction moment is determined based on the channel capacity prediction model; the channel switching of the wireless signal transmitter is optimized according to the predicted channel capacity of each channel at the prediction moment.

[0099] S403: For each terminal device, input the location information and speed information of the terminal device at each historical moment into a pre-trained location prediction model, determine the predicted location information of the terminal device at the prediction moment based on the location prediction model, and optimize the network access permissions of the terminal device according to the predicted location information of the terminal device at the prediction moment.

[0100] S404: Determine the target signal strength at the predicted time based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time; at the predicted time, control the wireless signal transmitter to transmit a wireless signal according to the target signal strength.

[0101] In this application, after determining the target channel whose predicted score is greater than a preset score threshold, and after determining the predicted location information and the Access Control List (ACL) of each terminal device at the prediction time, the target signal strength at the prediction time is determined based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the ACL at the prediction time. It should be noted that the ACL can be a single table recording the identifier of each terminal device and its network access permission information at the prediction time; or the ACL can be multiple tables, with one table corresponding to each terminal device.

[0102] To determine the target signal strength at the predicted time, based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time, the predicted channel capacity range corresponding to different signal strengths, the range to which the predicted location information of each terminal device belongs, and the access permissions of each network recorded in the ACL can be pre-stored. Then, the target signal strength at the predicted time is determined according to the corresponding relationships. Finally, at the predicted time, the wireless transmitter is controlled to transmit a wireless signal according to the target signal strength, thereby further improving the wireless signal optimization effect.

[0103] In this application, to improve the accuracy of determining the target signal strength, the process of determining the target signal strength at the prediction time includes:

[0104] The predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time are input into the pre-trained signal strength prediction model. Based on the signal strength prediction model, the target signal strength at the predicted time is determined.

[0105] After deploying a trained signal strength prediction model on electronic devices, and determining the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the prediction time, the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the ACL at the prediction time are input into the signal strength prediction model. Based on the signal strength prediction model, the target signal strength at the prediction time is determined. This improves the accuracy of determining the target signal strength.

[0106] In this application, the training process of the channel capacity prediction model includes:

[0107] The channel state information of each historical moment of the sample channel in the first training set, the location information and speed information of each sample terminal device, and the channel capacity label are input into the channel capacity prediction model to be trained. Based on the channel capacity prediction model, the sample predicted channel capacity of the sample channel at the sample prediction moment is determined. According to the sample predicted channel capacity and the channel capacity label, a first loss value is determined. The channel capacity prediction model to be trained is iteratively trained according to the first loss value. Wherein, the channel capacity label refers to the actual channel capacity of the sample channel at the sample prediction moment.

[0108] Specifically, the channel capacity prediction model is determined to be completed when the number of iterations reaches a preset first threshold, or when the first loss value determined during the iteration training meets the requirements.

[0109] In this application, the training process of the location prediction model includes:

[0110] The location information, velocity information, and location information label of each historical moment of the sample terminal device in the second training set are input into the location prediction model to be trained. Based on the location prediction model, the sample predicted location information of the sample terminal device at the sample prediction moment is determined. A second loss value is determined according to the sample predicted location information and the location information label. The location prediction model to be trained is iteratively trained according to the second loss value. The location information label refers to the actual location information of the sample terminal device at the sample prediction moment.

[0111] Specifically, the location prediction model is considered complete when the number of iterations reaches a preset second threshold, or when the second loss value determined during the iteration training meets the requirements.

[0112] In this application, the training process of the signal strength prediction model includes:

[0113] The sample prediction channel capacity of the sample channel in the third training set at the sample prediction time, the predicted location information of each sample terminal device, the access permissions of each network recorded in the Access Control List (ACL) at the sample prediction time, and the signal strength label are input into the signal strength prediction model to be trained. Based on the signal strength prediction model to be trained, the sample signal strength at the sample prediction time is determined. A third loss value is determined according to the sample signal strength and the signal strength label. The signal strength prediction model to be trained is iteratively trained according to the third loss value. The signal strength label refers to the actual signal strength of the wireless signal transmitted by the wireless transmitter at the sample prediction time.

[0114] Specifically, the signal strength prediction model is considered complete when the number of iterations reaches the preset threshold for the third iteration, or when the third loss value determined during the iteration process meets the requirements.

[0115] Figure 5 The wireless signal optimization flowchart provided in this application includes: real-time data acquisition, inputting data into a prediction model, predicting movement trajectories and channel states, dynamically adjusting ACL rules, adjusting signal coverage of the wireless signal transmitter according to the adjusted ACL rules, and achieving optimized network performance.

[0116] Step 1: Historical data collection and processing.

[0117] Data collection: Use Wi-Fi positioning, GPS or other sensor technologies to collect real-time location and movement trajectory data of the device, as well as channel status information.

[0118] Data preprocessing: The collected data is cleaned to remove outliers and noise, and then normalized to ensure the data is on the same scale. Next, features useful for channel prediction are extracted, such as signal strength, signal quality, equipment speed, and equipment direction of movement.

[0119] Step 2: Channel prediction model training.

[0120] Model selection: Choose a suitable deep learning model, such as a Long Short-Term Memory (LSTM) network, to learn channel characteristics and device mobility patterns.

[0121] Training the model: The model is trained using preprocessed historical data, enabling it to learn from historical data and predict future channel conditions (such as channel capacity, signal attenuation, etc.) and device movement trajectories (such as the future location / movement trajectory of the device).

[0122] Step 3: Define ACL rules.

[0123] Configure ACL rules on the router to control network access. An ACL rule can be a list of multiple rules, and each rule contains three elements:

[0124] (1) Rule number: Used to identify ACL rules. All rules are sorted in order of their numbers.

[0125] (2) Action: Specifies the action to be taken when a packet matches a rule, usually "permit" or "deny";

[0126] (3) Matching items: Defines the matching conditions of the rule, which may include source / destination IP address, port number, protocol type, etc.

[0127] ACL rules can be dynamically adjusted based on channel state prediction and device movement trajectory prediction, specifically as follows:

[0128] (1) Channel state prediction and ACL rules: Channel state prediction can help determine which network resources may be affected, thereby adjusting ACL rules to optimize network performance and resource allocation.

[0129] (2) Device movement trajectory prediction and ACL rules: The prediction of device movement trajectory can be used to predict the future network needs of the device, thereby dynamically adjusting ACL rules to ensure that the device always obtains appropriate network access permissions during movement.

[0130] Step 4: Predict channel state and trajectory.

[0131] Real-time monitoring: Using a trained model, predict the device's movement trajectory and channel status based on the real-time location of the collected data.

[0132] Data analysis: Analyze the prediction results to determine which areas' channel conditions may affect network performance and which devices may enter these areas.

[0133] Step 5: Dynamically adjust ACL rules.

[0134] Correlation Prediction and ACL: Matching predicted channel states and behavior trajectories with ACL rules to determine the rules that need adjustment. Adjustment strategies include:

[0135] (1) If the channel conditions in a certain area are predicted to be poor, the ACL rules can be adjusted to restrict non-critical network access to these areas in order to reserve bandwidth for critical tasks.

[0136] (2) If it is predicted that the device will move to an area that requires specific network access permissions, the ACL rules can be adjusted in advance to grant the device the corresponding access permissions.

[0137] The adjusted ACL rules are applied to the router to restrict or allow network access based on the device's real-time location and predicted movement trajectory, thereby controlling network access.

[0138] Step 6: Dynamically adjust signal coverage.

[0139] Based on device channel state prediction, movement trajectory prediction, and adjusted ACL rules, routers can dynamically adjust signal coverage to optimize network performance. For example, if a decline in channel quality in a certain area is predicted, bandwidth usage by non-critical devices can be restricted in advance through ACL rules, while signal coverage (such as router channel settings and signal strength) is adjusted to ensure the performance of critical devices.

[0140] In this application, the wireless signal transmitter is, for example, a router, and the terminal device is, for example, a mobile phone, a tablet computer, or other such device.

[0141] The following is a specific example to illustrate this.

[0142] Suppose a university campus has deployed a Wi-Fi network, with multiple buildings and outdoor areas. The campus network administrator wants to be able to dynamically adjust the Wi-Fi signal coverage based on students' movement patterns and channel conditions to ensure that students can have a stable network connection anywhere on campus.

[0143] Data collection and processing: Collect real-time location data Preal(t) and movement speed Vreal(t) of student devices.

[0144] Collect channel state information, such as channel capacity Creal(t) and signal attenuation Areal(t).

[0145] Channel prediction model training: Train an LSTM model using historical data to predict the future channel state Cpred(t), as shown in the formula:

[0146] Cpred(t)=f(Sreal(t),Areal(t),SNRreal(t),Vreal(t),Preal(t),…)

[0147] Where Cpred(t) is the predicted channel capacity, Sreal(t) is the real-time signal strength, Areal(t) is the real-time signal attenuation, SNRreal(t) is the real-time signal-to-noise ratio, Vreal(t) is the real-time moving speed of the terminal device, Preal(t) is the real-time location information of the terminal device, and the function f represents the prediction model. It should be noted that if there are n terminal devices, Vreal(t) includes the moving speeds of each of the 1 to n terminal devices; Preal(t) includes the location information of each of the 1 to n terminal devices.

[0148] Movement trajectory prediction model training: Train a trajectory prediction model using students' historical movement data to predict the students' future location Ppred(t), using the formula:

[0149] Ppred(t)=Preal(t)+Vreal(t)*Δt.

[0150] Where Δt represents the time interval.

[0151] Adjusting ACL rules: Dynamically adjusting network access permissions based on student location and predicted channel conditions, for example:

[0152]

[0153]

[0154] Signal coverage adjustment: Signal coverage is dynamically adjusted based on predicted channel conditions, movement trajectories, and adjusted ACL rules. Assume there is a function f that adjusts the signal strength S(t) based on channel prediction Cpred(t), movement trajectory prediction Ppred(t), and ACL rules ACLrules. This function can be expressed as:

[0155] S(t)=f(Cpred(t),Ppred(t),ACLrules).

[0156] Where S(t) is the signal strength at time t, Cpred(t) is the predicted channel capacity at time t, Ppred(t) is the predicted student location at time t, and ACLrules is the set of applied ACL rules. It should be noted that the function f in the S(t) formula can be a pre-trained signal strength prediction model.

[0157] The purpose of this application is to propose an adaptive optimization method for Wi-Fi signals based on device mobility and ACLs. This method overcomes the shortcomings of existing technologies by combining router signal coverage adjustment and dynamic management of ACL rules. Specific advantages of this invention include:

[0158] Real-time performance: By monitoring the movement trajectory of the device and the channel status in real time, the present invention can quickly respond to changes in network conditions and provide more dynamic and real-time signal coverage optimization.

[0159] Personalization: By combining device mobility patterns and behavior prediction, this invention can provide personalized signal coverage for different devices, ensuring that users get the best network experience while on the move.

[0160] Dual enhancement of security and performance: By combining ACL rules with signal coverage adjustments, this invention not only improves network security but also optimizes network performance, ensuring that network resources for critical missions are protected.

[0161] Resource optimization: This invention uses intelligent algorithms to dynamically adjust ACL rules and signal coverage, making more effective use of limited wireless spectrum resources and improving the overall efficiency of the network.

[0162] Automated management: This invention automates network management, reduces manual intervention, and lowers the cost and complexity of network maintenance.

[0163] Through these advantages, this invention not only improves the performance and user experience of wireless networks, but also enhances network security and resource utilization, providing a new solution for the intelligent management of wireless networks.

[0164] Dynamic ACL rule adjustment: Combines real-time channel status and user behavior prediction to dynamically adjust ACL rules to adapt to changes in user mobility and network conditions.

[0165] Optimize network performance: By predicting channel conditions and user movement trajectories, adjust ACL rules and signal coverage in advance to ensure that users always have the best network connection while moving.

[0166] Figure 6 The schematic diagram of the wireless signal optimization device provided in this application includes:

[0167] The acquisition module 61 is used to acquire, for each historical moment within the historical time period closest to the current moment, the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location information and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio;

[0168] The channel optimization module 62 is used to input the channel state information of each historical moment of the channel, the location information and speed information of each terminal device into a pre-trained channel capacity prediction model for each channel, and determine the predicted channel capacity of the channel at the prediction moment based on the channel capacity prediction model; and optimize the channel switching of the wireless signal transmitter according to the predicted channel capacity of each channel at the prediction moment.

[0169] The network optimization module 63 is used to input the location information and speed information of the terminal device at each historical moment into a pre-trained location prediction model for each terminal device, determine the predicted location information of the terminal device at the prediction moment based on the location prediction model, and optimize the network access permissions of the terminal device based on the predicted location information of the terminal device at the prediction moment.

[0170] The channel optimization module 62 is specifically used to determine the predicted score value of each channel based on the predicted channel capacity of the channel at the prediction time; and to control the channel switching of the wireless signal transmitter to the target channel with a predicted score value greater than a preset score threshold.

[0171] The channel optimization module 62 is further configured to, if there is no channel with a predicted score value greater than a preset score threshold, set the access permissions of the pre-set non-critical networks of each terminal device to deny them through an access control list (ACL).

[0172] The network optimization module 63 is specifically used to determine the predicted sub-region of the terminal device at the predicted time based on the predicted location information of the terminal device at the predicted time; determine the second network access permission corresponding to the predicted sub-region based on the first network access permission corresponding to each pre-set sub-region; and set the network access permission of the terminal device according to the second network access permission through the access control list (ACL).

[0173] The device further includes:

[0174] The signal strength optimization module 64 is used to determine the target signal strength at the prediction time based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the prediction time; and at the prediction time, control the wireless signal transmitter to transmit a wireless signal according to the target signal strength.

[0175] The signal strength optimization module 64 is specifically used to input the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the prediction time into the pre-trained signal strength prediction model, and determine the target signal strength at the prediction time based on the signal strength prediction model.

[0176] The device further includes:

[0177] The first training module 65 is used to input the channel state information of each sample historical moment of the sample channel in the first training set, the location information and speed information of each sample terminal device, and the channel capacity label into the channel capacity prediction model to be trained; determine the sample predicted channel capacity of the sample channel at the sample prediction moment based on the channel capacity prediction model; determine a first loss value according to the sample predicted channel capacity and the channel capacity label; and iteratively train the channel capacity prediction model to be trained according to the first loss value; wherein, the channel capacity label refers to the actual channel capacity of the sample channel at the sample prediction moment.

[0178] The device further includes:

[0179] The second training module 66 is used to input the location information, velocity information, and location information label of each historical moment of the sample terminal device in the second training set into the location prediction model to be trained; determine the sample predicted location information of the sample terminal device at the sample prediction moment based on the location prediction model; determine a second loss value based on the sample predicted location information and the location information label; and iteratively train the location prediction model to be trained based on the second loss value; wherein, the location information label refers to the actual location information of the sample terminal device at the sample prediction moment.

[0180] The device further includes:

[0181] The third training module 67 is used to input the sample prediction channel capacity of the sample channel in the third training set at the sample prediction time, the predicted location information of each sample terminal device, the access permissions of each network recorded in the access control list (ACL) at the sample prediction time, and the signal strength label into the signal strength prediction model to be trained; based on the signal strength prediction model to be trained, determine the sample signal strength at the sample prediction time; determine a third loss value according to the sample signal strength and the signal strength label; and iteratively train the signal strength prediction model to be trained according to the third loss value; wherein, the signal strength label refers to the actual signal strength of the wireless signal transmitted by the wireless signal transmitter at the sample prediction time.

[0182] This application also provides an electronic device, such as Figure 7 As shown, it includes: processor 701, communication interface 702, memory 703 and communication bus 704, wherein processor 701, communication interface 702 and memory 703 communicate with each other through communication bus 704.

[0183] The memory 703 stores a computer program, which, when executed by the processor 701, causes the processor 701 to perform any of the above method steps.

[0184] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0185] The communication interface 702 is used for communication between the above-mentioned electronic device and other devices.

[0186] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0187] The processors mentioned above can be general-purpose processors, including central processing units, network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0188] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform any of the above method steps.

[0189] This application provides a computer program product, which includes an executable program that, when executed by a processor, implements the method described herein.

[0190] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0191] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for optimizing wireless signals, characterized in that, The method includes: For each historical moment within the historical time period closest to the current moment, acquire the channel state information of each channel within the wireless signal coverage area at that historical moment, as well as the location and speed information of each terminal device; wherein, the channel state information includes at least one of signal strength, signal attenuation, and signal-to-noise ratio; For each channel, the channel state information of each historical moment of the channel, the location information and speed information of each terminal device are input into a pre-trained channel capacity prediction model. Based on the channel capacity prediction model, the predicted channel capacity of the channel at the prediction moment is determined. Based on the predicted channel capacity of each channel at the prediction moment, the channel switching of the wireless signal transmitter is optimized. For each terminal device, the location and speed information of the terminal device at each historical moment are input into a pre-trained location prediction model. Based on the location prediction model, the predicted location information of the terminal device at the predicted moment is determined. Based on the predicted location information of the terminal device at the predicted moment, the network access permissions of the terminal device are optimized.

2. The method as described in claim 1, characterized in that, Based on the predicted channel capacity of each channel at the predicted time, the channel switching of the wireless signal transmitter is optimized, including: For each channel, a predicted score value for the channel is determined based on the predicted channel capacity at the prediction time; the channel of the wireless signal transmitter is switched to a target channel with a predicted score value greater than a preset score threshold.

3. The method as described in claim 2, characterized in that, If there is no channel with a predicted score greater than a preset score threshold, the method further includes: By using Access Control Lists (ACLs), the pre-defined non-critical network access permissions for each terminal device are set to denied.

4. The method as described in claim 1, characterized in that, Optimizing the network access permissions of the terminal device based on its predicted location information at the predicted time includes: Based on the predicted position information of the terminal device at the predicted time, the predicted sub-region of the terminal device at the predicted time is determined; Based on the pre-defined first network access permissions corresponding to each sub-region, the second network access permissions corresponding to the predicted sub-region are determined; and the network access permissions of the terminal device are set according to the second network access permissions through the Access Control List (ACL).

5. The method as described in claim 2, characterized in that, The method further includes: Based on the predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time, the target signal strength at the predicted time is determined; at the predicted time, the wireless signal transmitter is controlled to transmit a wireless signal according to the target signal strength.

6. The method as described in claim 5, characterized in that, The process of determining the target signal strength at the predicted time includes: The predicted channel capacity of the target channel, the predicted location information of each terminal device, and the access permissions of each network recorded in the Access Control List (ACL) at the predicted time are input into the pre-trained signal strength prediction model. Based on the signal strength prediction model, the target signal strength at the predicted time is determined.

7. The method as described in claim 1, characterized in that, The training process of the channel capacity prediction model includes: The channel state information of each historical moment of the sample channel in the first training set, the location information and speed information of each sample terminal device, and the channel capacity label are input into the channel capacity prediction model to be trained. Based on the channel capacity prediction model, the sample predicted channel capacity of the sample channel at the sample prediction moment is determined. According to the sample predicted channel capacity and the channel capacity label, a first loss value is determined. The channel capacity prediction model to be trained is iteratively trained according to the first loss value. Wherein, the channel capacity label refers to the actual channel capacity of the sample channel at the sample prediction moment.

8. The method as described in claim 1, characterized in that, The training process of the location prediction model includes: The location information, velocity information, and location information label of each historical moment of the sample terminal device in the second training set are input into the location prediction model to be trained. Based on the location prediction model, the sample predicted location information of the sample terminal device at the sample prediction moment is determined. A second loss value is determined according to the sample predicted location information and the location information label. The location prediction model to be trained is iteratively trained according to the second loss value. The location information label refers to the actual location information of the sample terminal device at the sample prediction moment.

9. The method as described in claim 6, characterized in that, The training process of the signal strength prediction model includes: The sample prediction channel capacity of the sample channel in the third training set at the sample prediction time, the predicted location information of each sample terminal device, the access permissions of each network recorded in the Access Control List (ACL) at the sample prediction time, and the signal strength label are input into the signal strength prediction model to be trained. Based on the signal strength prediction model to be trained, the sample signal strength at the sample prediction time is determined. A third loss value is determined according to the sample signal strength and the signal strength label. The signal strength prediction model to be trained is iteratively trained according to the third loss value. The signal strength label refers to the actual signal strength of the wireless signal transmitted by the wireless transmitter at the sample prediction time.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-9.

Images