CN117640380A

CN117640380A - Wireless router transmission rate switching method and system

Info

Publication number: CN117640380A
Application number: CN202410103833.4A
Authority: CN
Inventors: 开军; 周武
Original assignee: Shenzhen Chuangling Zhilian Technology Co ltd
Current assignee: Shenzhen Chuangling Zhilian Technology Co ltd
Priority date: 2024-01-25
Filing date: 2024-01-25
Publication date: 2024-03-01
Anticipated expiration: 2044-01-25
Also published as: CN117640380B

Abstract

The present invention relates to the field of wireless communications technologies, and in particular, to a method and a system for switching transmission rates of a wireless router. The method comprises the following steps: acquiring historical wireless signal data and performing topology analysis to acquire a network topology feature matrix; acquiring dynamic signal data and performing time-space sensing signal analysis to acquire a time-space signal map; constructing a space-time perception neural network according to the space-time signal spectrum, and predicting the transmission rate of the equipment to obtain predicted data of the transmission rate of the equipment; performing transmission path genetic optimization based on the equipment transmission rate prediction data and the time-space signal spectrum to obtain optimized transmission path data; acquiring equipment communication frequency band data and calculating a rate compensation value to acquire the rate compensation value; and carrying out dynamic adjustment strategy analysis on the equipment communication frequency band data according to the rate compensation value to obtain a frequency spectrum adjustment strategy. The invention can realize the intelligent switching of the transmission rate of the wireless router, thereby improving the stability and the performance of network connection.

Description

Wireless router transmission rate switching method and system

Technical Field

The present invention relates to the field of wireless communications technologies, and in particular, to a method and a system for switching transmission rates of a wireless router.

Background

With the continuous development of wireless communication technology, the demand for high-speed, stable wireless network connection by users is increasing. Wireless routers, one of the key devices for implementing wireless network connections, have transmission rate switching critical to network performance. However, the optimal choice of transmission rate may vary in different network environments and application scenarios. Therefore, it is necessary to provide a method and system capable of automatically switching transmission rates according to actual requirements.

Disclosure of Invention

Accordingly, the present invention is directed to a wireless router transmission rate switching method, which solves at least one of the above-mentioned problems.

In order to achieve the above object, a method for switching transmission rate of a wireless router includes the following steps:

step S1: acquiring historical wireless signal data, and performing wireless network topology analysis according to the historical wireless signal data so as to acquire a network topology feature matrix;

step S2: acquiring dynamic signal data, and performing space-time perception signal analysis according to the dynamic signal data and a network topology feature matrix, so as to acquire a space-time signal map;

step S3: constructing a space-time perception neural network according to the space-time signal spectrum, and predicting the equipment transmission rate by utilizing the space-time perception neural network so as to obtain equipment transmission rate prediction data;

Step S4: performing transmission path genetic optimization on the basis of the equipment transmission rate prediction data and the time-space signal spectrum, thereby obtaining optimized transmission path data;

step S5: acquiring equipment communication frequency band data, and calculating a rate compensation value according to the optimized transmission path data and the equipment communication frequency band data so as to acquire the rate compensation value;

step S6: and carrying out dynamic adjustment strategy analysis on the equipment communication frequency band data according to the rate compensation value, so as to obtain a frequency spectrum adjustment strategy, and transmitting the frequency spectrum adjustment strategy to a wireless router management cloud platform to execute a transmission rate optimization task.

The invention forms a network topology feature matrix by acquiring historical wireless signal data and performing wireless network topology analysis. This helps the system understand the relative location of devices in the network, the connection strength, and the historical communication patterns. By means of historical data, the system can discover and optimize the connection mode between the devices, and therefore overall network topology efficiency is improved. The historical data analysis provides a basis for the subsequent optimization of the transmission path, so that the system can adjust the transmission path more intelligently and adapt to different network environments. The dynamic signal data reflects the real-time state of the network, and the system can more accurately understand the dynamic change of the network through space-time perception. The space-time perception analysis is helpful for predicting network congestion, so that the system can take corresponding measures to avoid performance degradation. The space-time perception neural network can learn and adapt to the transmission rate of different devices under different space-time conditions, and the prediction accuracy is improved. Through the real-time learning of the neural network, the system can dynamically adjust the transmission rate to adapt to the change of the network state, and the stability of network connection is improved. The genetic optimization algorithm can find the optimal transmission path, reduce the time delay of signal transmission, improve the overall performance of the network and improve the adaptability. By considering the information of the communication frequency band of the device, the system can calculate the rate compensation value more accurately, and performance degradation caused by frequency band collision is avoided. And by combining with the optimization information of the transmission path, the rate compensation value is calculated more comprehensively, so that the adjustment is more intelligent and comprehensive. By transmitting the spectrum adjustment strategy to the cloud platform, the system can realize real-time management and adjustment of the wireless router and adapt to different network environments. The centralized management of the cloud platform enables the system to perform unified optimization and adjustment on the whole network, and improves management efficiency.

Optionally, step S1 specifically includes:

step S11: acquiring historical wireless signal data;

step S12: performing identifier data extraction and signal strength data extraction on the historical wireless signal data, thereby obtaining equipment identifier data and signal strength data;

step S13: performing equipment connection analysis according to the equipment identifier data and the signal strength data, thereby obtaining equipment connection data;

step S14: performing topology construction based on the equipment connection data and the signal intensity data, thereby obtaining a wireless network topology;

step S15: extracting characteristics of a wireless network topology structure, thereby obtaining network topology characteristics;

step S16: and constructing a network topology feature matrix according to the network topology features.

By collecting the historical wireless signal data, the system can analyze the past connection mode, the past use frequency and the past time period of the user equipment, so that the use habit and the trend of the network are known. By extracting the device identifier data, the system is able to uniquely identify each connected device, making subsequent connection analysis and topology construction more accurate. By extracting the signal strength data, the system can know the connection quality between the devices, and provides an important reference for the subsequent network topology construction. Through the device identifier data and the signal strength data, the system can analyze the connection mode between the devices, and know the communication relationship between the devices and the frequently connected devices. The device connection analysis helps to evaluate the load condition of the network, thereby better understanding the busyness and connection strength of the network. Based on the device connection data and the signal intensity data, the system can construct a topological structure of the wireless network, namely a connection relation diagram among devices, and is beneficial to subsequent network topological feature extraction. The topology structure construction enables the system to analyze path information between devices, and provides a basis for optimization of subsequent transmission paths. By extracting features of the topology structure, the system can analyze characteristics of the network, such as centrality, density and the like, and provide references for subsequent network optimization. The extracted features can be used to detect abnormal connections or devices in the network, enhancing the security of the network. The network topology features are expressed in a matrix form, which is helpful for optimizing the data structure and improving the data processing efficiency. The constructed network topology characteristic matrix can be used as the input of models such as a neural network and the like, and necessary data is provided for the establishment of a subsequent space-time perception neural network.

Optionally, step S13 specifically includes:

step S131: classifying and calculating the equipment identifier data to obtain mobile equipment identifier data and static equipment identifier data;

step S132: performing static equipment strength association analysis on the static equipment identifier data and the signal strength data, thereby obtaining static equipment strength data;

step S133: performing mobile equipment strength association analysis on the mobile equipment identifier data and the signal strength data, thereby obtaining mobile equipment strength data;

step S134: and carrying out equipment connection analysis according to the static equipment intensity data and the mobile equipment intensity data, thereby obtaining equipment connection data.

The invention can divide the equipment into the mobile equipment and the static equipment through classifying and calculating the equipment identifier data, so that the system can distinguish the mobile property of the equipment. Distinguishing mobile devices from static devices helps to understand device behavior in different scenarios in the network, e.g., the connection mode of a mobile device while moving may be different from that of a static device. Aiming at static devices, through correlation analysis of signal intensity data, the system can know the connection mode and connection intensity between the static devices, and is beneficial to optimizing network layout. Analyzing the signal strength associations of static devices may help to adjust the layout of the devices, improve signal quality between the devices, and thereby improve network performance. Through correlation analysis with the signal strength data, the system can learn the signal strength changes of the mobile device at different positions, so as to infer the track and the activity range of the mobile device. The strength association analysis of the mobile equipment is beneficial to optimizing seamless switching of the mobile equipment among different positions, and improving user experience. And carrying out equipment connection analysis according to the static equipment strength data and the mobile equipment strength data, wherein the system can realize network load balance and ensure that equipment connection is more balanced in the whole network. The device connection analysis is helpful for optimizing connection stability, reducing problems in connection interruption and data transmission, and improving overall network performance.

Optionally, step S134 specifically includes:

step S1341: constructing a scene static signal coordinate system according to static equipment intensity data;

step S1342: carrying out equipment use frequency region statistics on the mobile equipment intensity data so as to obtain a high-frequency mobile equipment use region and a low-frequency mobile equipment use region;

step S1343: analyzing the potential mobile equipment use area according to the static equipment intensity data and the mobile equipment intensity data, so as to obtain the potential mobile equipment use area;

step S1344: filling the region of the scene static signal coordinate system according to the potential mobile equipment use region, the high-frequency mobile equipment use region and the low-frequency mobile equipment use region, so as to obtain the scene equipment signal coordinate system;

step S1345: and carrying out equipment connection mode analysis on the scene equipment signal coordinate system according to the static equipment intensity data and the mobile equipment intensity data, thereby obtaining equipment connection data.

According to the invention, the static signal coordinate system of the scene is constructed through the static equipment intensity data, the system can know the signal distribution of the static equipment in the space, the layout of the equipment is optimized, and the signal coverage range is improved. The construction of the static signal coordinate system of the scene can extract the characteristics of the scene, and is favorable for customizing and optimizing the network performance of different scenes. Through carrying out frequency of use region statistics on the mobile device intensity data, the system can know the frequency of use of the device in different regions, and is favorable for optimizing resource allocation, so that the device in a high-frequency use region is ensured to be supported by more resources. The statistics of the high-frequency mobile device use area and the low-frequency mobile device use area is helpful for capacity planning so as to meet the device connection requirements of different areas. By potential mobile device usage area analysis, the system can predict future likely device usage areas, helping to make network expansion and optimization preparations ahead of time. Knowledge of the potential use area can help the system optimize services in advance, improving the efficiency of device connection. The regional filling can perfect the spatial information of the signal coordinate system of the scene equipment, so that the spatial information is closer to the use condition of the actual equipment, and the accuracy of the signal coordinate system is improved. The filled scene equipment signal coordinate system can be used for finer network planning so as to adapt to network requirements of different areas. By analyzing the equipment connection mode of the scene equipment signal coordinate system, the system can optimize the connection mode between the equipment and improve the stability and efficiency of connection. The device connection mode analysis is beneficial to realizing load balancing, ensuring uniform device connection distribution in the network and avoiding connection congestion.

Optionally, step S1343 is specifically:

extracting adjacent equipment intensity data from the static equipment intensity data and the mobile equipment intensity data through a scene static signal coordinate system, so as to obtain the adjacent equipment intensity data;

performing score calculation on the intensity data of the adjacent equipment through a potential mobile equipment high-frequency use score formula, so as to obtain a potential mobile equipment high-frequency use score;

and carrying out region division on the high-frequency use scores of the potential mobile equipment and the adjacent equipment strength data according to the scene static signal coordinate system, so as to obtain the use region of the potential mobile equipment.

The invention extracts the intensity data of the adjacent devices through the static signal coordinate system, can capture the relevance between the devices, and can know the influence degree of the devices in space. These data help understand the layout and interrelationships of devices in a scene, providing a basis for understanding network topology. By means of the score calculation, the influence degree of the adjacent devices on the high-frequency use of the potential mobile device can be estimated, and therefore the possible area of the potential high-frequency use is predicted. This score may help quantify the likelihood of potentially high frequency usage areas, providing a way to gauge the relative importance of the various areas. The potential high-frequency use scores and the adjacent equipment intensity data are divided into areas by utilizing a static signal coordinate system, so that the possible equipment use areas can be accurately determined, and a basis is provided for space optimization. The division of the area of potential mobile device usage may help more efficiently allocate network resources within that area to meet the high frequency usage demands that may occur.

Optionally, the potential mobile device high frequency usage score formula in step S1343 is specifically:

；

wherein,score for potential mobile device high frequency usage, < ->For static device signal strength, +.>For mobile device signal strength, +.>Is the distance between the static device signal source and the mobile device signal source,/->Adjusting parameters for errors +.>Weight coefficient for signal strength of static device, +.>For logarithmic adjustment parameters>Is a weight coefficient for the signal strength of the mobile device.

The invention constructs a potential mobile device high-frequency use scoring formula for scoring adjacent device intensity data. The formula fully considers influencing the high-frequency use score of the potential mobile deviceStatic device signal strength +.>Mobile device signal strength +.>Distance of stationary device signal source from mobile device signal source +.>Error adjustment parameter->Weight coefficient of signal intensity of static device +.>Logarithmic adjustment parameters->Weight coefficient of mobile device signal strength +.>A functional relationship is formed:

；

wherein,in part, a +>The signal intensity of the static equipment is logarithm, and the range of the signal can be compressed through the operation, so that the signal change in a large range is smoother. / >Scaling the logarithmized signal by adjusting the parameter +.>The impact of static device signal strength on the score may be adjusted. The result is then square-root-processed, the signal is further smoothed, and by +.>And (5) performing weight adjustment. />In part, a +>The mobile device signal strength is squared to amplify the range of variation of the signal. />Is by parameter->Weight adjustments are made to adjust the impact of mobile device signal strength on the score. />Is to->The cube root operation is performed so that the influence of the signal strength of the mobile device is smoother. />Is a signal strength of the mobile device with respect to distance +.>Is derived to represent the trend of the signal strength of the mobile device, and is used for considering the change condition of the mobile device. In the art, signal processing techniques, spatio-temporal analysis, and the like are commonly employed to analyze potential mobile device high frequency usage scores. By adopting the potential mobile equipment high-frequency use score formula provided by the invention, the potential mobile equipment high-frequency use score can be obtained more accurately.

Optionally, step S4 specifically includes:

step S41: initializing a genetic model according to the space-time perception neural network, so as to obtain a genetic optimization model;

Step S42: constructing a parameter space according to the equipment transmission rate prediction data and the time space signal spectrum;

step S43: carrying out optimal fitness combination selection on the parameter space through a genetic optimization model so as to obtain optimal fitness combination parameters;

step S44: and planning a transmission path of the time signal spectrum according to the optimal fitness combination parameter, so as to obtain optimized transmission path data.

In the invention, the use of the space-time perception neural network can help to personalize and initialize the genetic model, so that the model is more suitable for specific space-time scenes, and the optimization accuracy is improved. The personalization of the initialization can allow the genetic model to converge more quickly to possible optimization solutions, speeding up the overall optimization process. The parameter space is constructed by combining the equipment transmission rate prediction data and the space-time signal spectrum, so that the equipment performance and the space-time variation can be comprehensively considered, and a more comprehensive optimized view angle is provided. The accurate modeling of the network environment can be improved by considering the transmission rate of the equipment and the space-time signal, so that the optimization is more reliable. The genetic optimization model can perform global search, and is helpful to avoid local optimal solutions and improve the probability of finding global optimal solutions through the combination selection of the adaptability of diversity. By selecting fitness combinations, sensitivity analysis can be performed on the parameter space to find the parameter combinations most sensitive to system performance. And the optimal fitness combination parameter is utilized to carry out transmission path planning, so that the communication path between the devices can be optimized, and the data transmission efficiency is improved. The transmission path planning based on the space-time signal spectrum can consider the network condition which changes in real time, so that the optimization scheme is more suitable for the actual environment.

Optionally, step S5 specifically includes:

step S51: acquiring equipment communication frequency band data;

step S52: extracting transmission delay frequency band data according to the equipment communication frequency band data, thereby obtaining transmission delay frequency band data;

step S53: extracting features of the optimized transmission path data so as to obtain optimized path feature data;

step S54: and calculating the rate compensation value of the optimized path characteristic data and the transmission delay frequency band data through a rate compensation value calculation formula, thereby obtaining the rate compensation value.

The invention can know the frequency band used by each device in the communication system by acquiring the device communication frequency band data, is beneficial to avoiding frequency band conflict and improves communication stability. Obtaining communication band data facilitates resource planning to ensure that communications between devices are not interfered with and to optimize communication performance. Extracting the transmission delay frequency band data is helpful for knowing the transmission delay conditions on different frequency bands, so that the transmission path is optimally selected, and the time delay of data transmission is reduced. By considering the transmission delays of different frequency bands, the quality of data transmission can be improved, and timeliness and reliability are ensured. Feature extraction helps to understand key features of the optimized transmission path, such as path length, topology, etc., and provides more informative data for subsequent computation. The extracted feature data can be used for modeling, so that the problem is easier to quantify and understand, and a clearer target is provided for further optimization. The calculation of the rate compensation value can adjust the data transmission rate according to the path characteristics and the transmission delay, so that the data transmission on different frequency bands and paths is more balanced. By calculating the rate compensation value, performance balance can be realized under different conditions, overload of certain paths or frequency bands is avoided, and the efficiency of the whole communication system is improved.

Optionally, the rate compensation value calculation formula in step S54 is specifically:

；

wherein,for the rate compensation value, +.>To optimize the bandwidth of the path +.>To optimize the signal attenuation of the path, +.>For maximum transmission delay value in the network, < >>For the complexity factor of the network topology, +.>Is the signal propagation velocity.

The invention constructs a rate compensation value calculation formula for calculating the rate compensation value of the optimized path characteristic data and the transmission delay frequency band data. The formula fully considers the influence rate compensation valueBandwidth ∈of optimized path>Signal attenuation degree of optimized path +.>Maximum transmission delay value in the network +.>Complexity factor of network topology +.>Signal propagation speed>A functional relationship is formed:

；

wherein,part contains the bandwidth of the path characteristic data>And signal attenuation->Complexity of network topologyCoefficient->The operation is performed. />Representing the product of the path characterization data plus a complexity factor of the network topology. Taking the logarithm ln followed by the square root introduces a nonlinear relationship that can be used to model more complex influencing factors. />Part of which relates to the bandwidth of the path profile >Signal attenuation->And signal propagation speed>Sum of transmission delays->Is a derivative of (a). />Representing the sum of the path characteristic data, for which the derivative of the transmission delay is performed +.>It can be understood that the rate of change of the path characteristic data as a whole with the transmission delay. This derivative term is used to take into account the sensitivity of the path profile as a whole to transmission delays. />Part is transmission delay->A periodic factor is introduced. This can be used to simulate the periodic effects that variations in transmission delay may have. In the art, it is common to use a solidAnd calculating a rate compensation value by technical means such as data analysis and network simulation. By adopting the rate compensation value calculation formula provided by the invention, the rate compensation value can be obtained more accurately.

Optionally, the present specification further provides a wireless router transmission rate switching system for performing the wireless router transmission rate switching method as described above, the wireless router transmission rate switching system including:

the topology analysis module is used for acquiring historical wireless signal data and carrying out wireless network topology analysis according to the historical wireless signal data so as to obtain a network topology feature matrix;

The space-time perception signal analysis module is used for acquiring dynamic signal data, and carrying out space-time perception signal analysis according to the dynamic signal data and the network topology feature matrix so as to acquire a space-time signal map;

the device transmission rate prediction module is used for constructing a space-time perception neural network according to the space-time signal spectrum and predicting the device transmission rate by utilizing the space-time perception neural network so as to obtain device transmission rate prediction data;

the transmission path optimization module is used for carrying out transmission path genetic optimization on the basis of the equipment transmission rate prediction data and the time-space signal spectrum so as to obtain optimized transmission path data;

the rate compensation value calculation module is used for acquiring the equipment communication frequency band data, and calculating the rate compensation value according to the optimized transmission path data and the equipment communication frequency band data so as to obtain a rate compensation value;

and the communication frequency band adjustment module is used for carrying out dynamic adjustment strategy analysis on the equipment communication frequency band data according to the rate compensation value so as to obtain a frequency spectrum adjustment strategy, and transmitting the frequency spectrum adjustment strategy to the wireless router management cloud platform so as to execute a transmission rate optimization task.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of a non-limiting implementation, made with reference to the accompanying drawings in which:

Fig. 1 is a flow chart illustrating steps of a method for switching transmission rate of a wireless router according to the present invention;

FIG. 2 is a detailed step flow chart of step S1 of the present invention;

FIG. 3 is a detailed flowchart illustrating the step S13 of the present invention;

the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

To achieve the above objective, referring to fig. 1 to 3, the present invention provides a method for switching transmission rate of a wireless router, comprising the following steps:

historical wireless signal data, including signal strength, transmission rate, device location, etc., is collected by a monitor or sensor in this embodiment. By analyzing these data, a topology feature matrix of the wireless network including connection relationships between devices, signal propagation paths, and the like is generated. For example, by recording the inter-device communication frequency band and signal strength, the system can build the topology of the network.

in this embodiment, real-time dynamic signal data is acquired, including a real-time communication state between devices in a network, a change in signal strength, and the like. And (3) carrying out space-time perception signal analysis by combining with the network topology feature matrix to generate a space-time signal map. This map reflects the propagation mode and the time-space variation law of the signal in the network.

in this embodiment, a space-time perception neural network is constructed by a deep learning technique. The neural network is trained using historical data to enable it to predict the transmission rate of the device at different locations and times. The neural network considers space-time characteristics such as equipment movement, signal attenuation and the like, and improves the accuracy of transmission rate prediction. For example, the neural network may predict future rates by learning characteristics of signal strength, device location, etc. in the historical data.

in this embodiment, an optimal transmission path is evolved based on the space-time signal spectrum and the predicted data of the transmission rate of the device by using a genetic algorithm. The selection of the path is optimized to maximize the overall transmission efficiency in consideration of the network topology characteristics and the real-time signal data, and is adapted to the dynamic change of the network.

in this embodiment, the current communication frequency band data of the device is collected, and the optimized transmission path data is combined. The rate compensation value is calculated by taking into account the transmission rates of the device in the different frequency bands. This value reflects the impact of different frequency bands on the transmission rate when optimizing the transmission path in order to better balance the overall network performance.

In this embodiment, the calculated rate compensation value is applied to the device communication frequency band data to generate a spectrum adjustment policy. The system generates a frequency band adjustment strategy. This involves reallocating the communications bands between devices to optimize overall network performance. The policy is transmitted to the wireless router management cloud platform, and actual spectrum adjustment is performed to optimize the transmission rate of the device. This involves reconfiguring radio parameters of the device, such as frequency, bandwidth, etc.

Optionally, step S1 specifically includes:

step S11: acquiring historical wireless signal data;

in this embodiment, by disposing a dedicated data collector on the router, historical wireless signal data is periodically recorded and stored. The data includes information about the time stamp, signal strength, frequency, etc. associated with the device communication. The data acquisition can be realized by technical means such as network traffic monitoring and data packet capturing.

in this embodiment, historical wireless signal data is processed from which unique identifier data and signal strength data for the device are extracted. The identifier data may be a MAC address or other unique identifier of the device, while the signal strength data represents signal strength information between the device and the base station. This can be achieved by a data parsing algorithm, ensuring accurate extraction of the required information.

in this embodiment, the device connection analysis is performed using the extracted identifier data and signal strength data. And establishing device connection data by identifying information such as communication modes, connection frequencies and the like between the devices. This helps to understand the relationship between the devices and the communication mode in the network, providing a basis for the subsequent steps.

in this embodiment, a topology structure of the wireless network is constructed based on the device connection data and the signal strength data. This may employ algorithms in graph theory, such as minimum spanning tree algorithms or depth first searches, to determine connectivity relationships and network topology between devices. The topology established helps to understand the hierarchical relationships and communication paths in the network.

in this embodiment, feature extraction is performed on the constructed wireless network topology. This includes features such as node degree, cluster coefficient, network diameter, etc. to describe the structure and nature of the network. These feature extractions may employ a series of algorithms in graph theory to help understand the complexity and stability of the network.

In this embodiment, a network topology feature matrix is constructed based on the extracted wireless network topology features. The matrix is a mathematical representation that converts network structure information into a matrix form that provides input for subsequent data analysis and machine learning. This can be accomplished by mathematical modeling and programming to form a matrix describing the network characteristics.

Optionally, step S13 specifically includes:

in this embodiment, the device identifier data may contain information of the mobile device and the static device. By classifying these data, mobile device identifier data and static device identifier data can be distinguished. This may be done by an algorithm or model, for example using a clustering algorithm to divide the device identifier data into two or more clusters, thereby identifying devices with similar movement patterns or stationary patterns.

the static device identifier data is combined with corresponding signal strength data in this embodiment. By performing correlation analysis on the static device identifier data and the signal strength data, the signal strength characteristics of the static device can be obtained. This may include establishing a connection graph between static devices and inferring a physical location or spatial relationship between the devices based on the signal strength data.

the present embodiment relates to association analysis of mobile device identifier data and corresponding signal strength data. This helps to identify the signal strength pattern and movement pattern of the mobile device. By tracking the signal strength changes of the mobile device at different points in time or locations, it is possible to infer its movement trajectory or frequent areas.

In this embodiment, device connection analysis is performed by combining signal intensity data of the static device and signal intensity data of the mobile device. This may include identifying association patterns between static devices and mobile devices, analyzing the frequency of communication or strength of association between them. Through such analysis, a connection relationship between devices can be established, and the communication mode and the contact manner between the devices in the network can be understood.

Optionally, step S134 specifically includes:

in this embodiment, static device intensity data is used to construct a static signal coordinate system of the scene. By measuring the signal strength of the static device, the signal strength distribution in different areas can be determined. These data can be used to construct a coordinate system in which each coordinate point represents a particular location in the scene and its coordinate values reflect the static device signal strength at that location. Such a scene static signal coordinate system may be used as a basis for subsequent analysis.

in this embodiment, the statistics of the device usage frequency region is performed on the mobile device intensity data. By counting the signal intensity change frequencies of the mobile devices in different areas, the high-frequency mobile device use area and the low-frequency mobile device use area can be identified. This helps understand the activity pattern and popular areas of the mobile device in the scene, providing a basis for subsequent analysis.

in this embodiment, the analysis of the potential mobile device usage area is performed according to the static device intensity data and the mobile device intensity data. By comparing the signal strength changes of the static device and the mobile device, the possible usage area of the mobile device, i.e. the pattern of signal strength changes of the device at different locations, can be deduced. This helps identify possible mobile device active areas.

in this embodiment, the region filling is performed on the static signal coordinate system of the scene according to the potential mobile device use region, the high-frequency mobile device use region and the low-frequency mobile device use region. This means that the known mobile device usage pattern is combined with the scene static signal coordinate system, filling the signal strength information of the respective areas, resulting in a scene device signal coordinate system. This coordinate system may more fully reflect the signal distribution of the devices in the scene.

In this embodiment, device connection mode analysis is performed on the scene device signal coordinate system according to the static device intensity data and the mobile device intensity data. By analyzing the signal strength relationship between the devices, the connection pattern between the devices, i.e., the manner and frequency of communication between them, can be identified. This provides detailed information about interactions between devices, forming device connection data. These data are critical to understanding the relationships and communication modes between devices in a scene.

Optionally, step S1343 is specifically:

in this embodiment, the static device intensity data and the mobile device intensity data are analyzed through a scene static signal coordinate system, and the adjacent device intensity data are extracted. In the coordinate system, with each device position as a node, the signal intensity difference between adjacent nodes is calculated, thereby obtaining the intensity data of the adjacent devices. This ensures that signal variations between devices are captured, providing accurate underlying data for subsequent analysis.

the high frequency usage score formula of the potential mobile device is introduced in the embodiment. By applying the scoring formula to the adjacent device intensity data, a high frequency usage score for each adjacent device combination is calculated. The formula may be based on the frequency, amplitude, or other relevant indicator of the fluctuation of the signal strength. This is to quantify the extent of the high frequency signal variation between devices, providing an evaluation criterion for the subsequent division of regions.

In this embodiment, based on a static signal coordinate system of a scene, the high-frequency use score of the potential mobile device and the intensity data of the adjacent devices are comprehensively analyzed, and region division is implemented. The scene is divided into different areas by defining a division rule, such as setting a score threshold or adopting a clustering algorithm, and each area corresponds to a potential mobile device use area. This ensures that the active areas in the scene can be accurately identified, improving the understanding of the usage patterns of the mobile device.

；

Optionally, step S4 specifically includes:

In this embodiment, the genetic model is initialized using a spatio-temporal perceptual neural network. And learning the space-time perception characteristics through the neural network, and taking the weight of the neural network as an initial parameter of the genetic model. The genetic model can be ensured to consider the space-time dynamic change of the scene in the subsequent optimization process, and the adaptability and generalization capability of the model are improved.

in this embodiment, a parameter space is constructed by combining the device transmission rate prediction data and the spatio-temporal signal pattern. The device transmission rate prediction data reflects the communication performance between devices, while the spatio-temporal signal profile provides a spatio-temporal distribution of signal intensities in the scene. The two are combined to form a parameter space, wherein the parameter space comprises key parameters such as equipment transmission rate, space-time signal strength and the like. This provides a comprehensive optimization space for subsequent genetic optimization.

in this embodiment, the optimal fitness combination is selected in the parameter space by using a genetic optimization model. Genetic algorithms utilize genetic manipulations, such as selection, crossover and mutation, to evolve more fitness parameter combinations. The method aims at finding the optimal parameter combination, so that the model can effectively improve the transmission performance while considering the space-time characteristics.

In this embodiment, a transmission path of the space-time signal spectrum is planned based on the optimal fitness combination parameter. By taking into account the spatio-temporal distribution of the signals in the scene. This includes factors such as signal strength, multipath effects, shadowing, etc., to understand the complexity of the communication environment. An optimal transmission path from a start point to an end point is calculated by using an optimization algorithm, such as a Dijiestra algorithm, in consideration of optimal fitness combination parameters such as a device transmission rate, a space-time signal strength and the like. This ensures that data is transmitted in the shortest path, reducing transmission delay. And optimizing the transmission path to ensure the most effective data transmission in time and space.

Optionally, step S5 specifically includes:

step S51: acquiring equipment communication frequency band data;

in this embodiment, the communication frequency band information of the target device is collected through the wireless communication interface, including the working frequency, the channel width, and the like. And professional equipment or a communication protocol analysis tool is used for ensuring the accuracy of the data. For example, by scanning the radio spectrum, the frequency band usage of the device in different time periods is recorded to obtain comprehensive communication frequency band data.

in this embodiment, the transmission delay frequency band data is extracted according to the device communication frequency band data, so as to obtain the transmission delay frequency band data. Based on the communication frequency band information of the device, the transmission delay information of the data packet is captured through a network monitoring tool or a protocol analyzer. This may involve recording and analyzing the arrival time of the data packets to determine the transmission delay over the different frequency bands. For example, using a network packet grasping tool, the time stamp and arrival order of the data packet are analyzed, and the transmission delay band data is extracted.

In this embodiment, feature extraction is performed on the optimized transmission path data, so as to obtain optimized path feature data. By monitoring the network topology and traffic patterns, features related to transmission path optimization are extracted. This may include information on the topology of the path, the number of hops between nodes, bandwidth utilization, etc. Network analysis tools, such as route tracking and traffic analysis, are used to obtain detailed path characterization data.

In this embodiment, the rate compensation value calculation formula is used to calculate the rate compensation value for the optimized path characteristic data and the transmission delay frequency band data, so as to obtain the rate compensation value. A rate compensation calculation formula is designed, and the influence of transmission delay and path characteristics on the data transmission rate is considered. And substituting the transmission delay frequency band data and the optimized path characteristic data which are extracted previously into a calculation formula to obtain a rate compensation value. For example, a weighted summation approach may be employed to take into account the relative importance of delay and path characteristics to derive a final rate compensation value for optimizing the data transmission path.

；

wherein,part contains the bandwidth of the path characteristic data>And signal attenuation->And complexity factor of the network topology +.>The operation is performed. />Representing the product of the path characterization data plus a complexity factor of the network topology. Taking the logarithm ln followed by the square root introduces a nonlinear relationship that can be used to model more complex influencing factors. />Part of which relates to the bandwidth of the path profile >Signal attenuation->And signal propagation speed>Sum of transmission delays->Is a derivative of (a). />Representing the sum of the path characteristic data, for which the derivative of the transmission delay is performed +.>It can be understood that the rate of change of the path characteristic data as a whole with the transmission delay. This derivative term is used to take into account the sensitivity of the path profile as a whole to transmission delays. />Part is transmission delay->A periodic factor is introduced. This can be used to simulate the periodic effects that variations in transmission delay may have. In the art, the rate compensation value is generally calculated by adopting technical means such as measured data analysis, network simulation and the like. By adopting the rate compensation value calculation formula provided by the invention, the rate compensation can be more accurately obtainedValues.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wireless router transmission rate switching method, comprising the steps of:

2. The method according to claim 1, wherein step S1 is specifically:

step S11: acquiring historical wireless signal data;

3. The method according to claim 2, wherein step S13 is specifically:

4. A method according to claim 3, wherein step S134 is specifically:

5. The method according to claim 4, wherein the step S1343 is specifically:

6. The method according to claim 5, wherein the potential mobile device high frequency usage score formula in step S1343 is specifically:

；

7. The method according to claim 6, wherein step S4 is specifically:

8. The method according to claim 7, wherein step S5 is specifically:

Step S51: acquiring equipment communication frequency band data;

9. The method according to claim 8, wherein the rate compensation value calculation formula in step S54 is specifically:

；

10. A wireless router transmission rate switching system for performing the wireless router transmission rate switching method according to claim 1, the wireless router transmission rate switching system comprising: