Multi-state wireless network signal dynamic imaging system and method based on element universe

Abstract

The invention discloses a multi-state wireless network signal dynamic imaging system and method based on meta universe, and relates to the technical field of wireless communication. According to the method, a spatial dimension prediction model and a time dimension prediction model are combined, and spatial distribution of wireless network signals is accurately predicted through a data fusion technology; the reliability and the accuracy of wireless network signals are improved by dynamically adjusting a reference weight optimization prediction result; according to the invention, by collecting the real-time network requirements of the user including the video traffic and the file uploading and downloading and the real-time requirements of the user on the wireless network signal quality, intelligent and dynamic network signal quality evaluation can be realized, and the network quality in different use scenes can meet the personalized requirements; through the signal intensity heat map and sound prompt, a user can timely obtain feedback related to wireless network signal quality, and the user is helped to find an area with the best signal in a complex environment, so that more optimized network experience is realized.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a metaverse-based polymorphic wireless network signal dynamic imaging system and method thereof. Background Art

[0002] With the rapid development of wireless communication technology, wireless networks have become an indispensable part of modern life and work. The quality of wireless network signals directly affects the network connection speed and stability of devices. Especially in the environment where smart devices are widely used, the importance of wireless network quality becomes more and more prominent. However, due to the complexity of the network environment, the quality of wireless network signals may fluctuate greatly at different locations and times. How to monitor and optimize the quality of wireless network signals in real time has become the key to improving the user's network experience.

[0003] Currently, the optimization and management of wireless network signals mostly rely on static configuration and manual adjustment of routers or network management systems, lacking the ability of dynamic adjustment and intelligent prediction. In indoor and complex environments, wireless network signals are affected by many factors, including interference from obstacles such as walls, furniture, and electrical appliances, as well as network load requirements of different devices. Therefore, traditional wireless network signal management methods are often unable to cope with these changes, resulting in problems such as uneven signal coverage, unstable connections, and network congestion.

[0004] In view of the above problems, it is necessary to propose a metaverse-based polymorphic wireless network signal dynamic imaging system and method. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the background technology and to propose a polymorphic wireless network signal dynamic imaging system and method based on metaverse.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a metaverse-based polymorphic wireless network signal dynamic imaging system, comprising a data acquisition module, a spatial distribution prediction module, an edge computing module, a central computing module and a display guidance module.

[0007] The data acquisition module is the data input end of the wireless network signal dynamic visualization imaging device, including a signal data acquisition unit arranged at each wireless network signal source and a user data acquisition unit, an environmental data acquisition unit and a network load data acquisition unit arranged in the wireless network signal dynamic visualization imaging device.

[0008] The signal data acquisition unit acquires characteristic data of the wireless network signal source through sensors arranged at each wireless network signal source, including signal strength, signal spectrum width, signal-to-noise ratio and bit rate of the primary rays emitted by each wireless network signal source; And by calculating the signal strength, signal spectrum width, signal-to-noise ratio and bit rate of the primary rays, the signal quality evaluation index of the primary rays sent by each wireless network signal source is obtained.

[0009] The user data acquisition unit obtains the precise coordinates of the user of the wireless network signal dynamic visualization imaging device through GPS and indoor positioning; and records the real-time wireless network signal strength of the wireless network signal dynamic visualization imaging device in real time through a signal receiver.

[0010] The environmental data acquisition unit obtains the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device and outputs it to the edge computing module. The camera of the wireless network signal dynamic visualization imaging device captures the environmental image, and the obstacles and interference sources that affect the signal propagation are identified based on the computer vision algorithm. The position coordinates of the obstacles and interference sources that affect the signal propagation in the camera coordinate system of the visual sensor are obtained.

[0011] The collected position and size data of obstacles and interference sources are spatially processed, and the position coordinates of the obstacles and interference sources in the camera coordinate system of the visual sensor are spatially transformed to obtain their coordinates in the spatial coordinate system.

[0012] As a preferred embodiment of the present invention, the network load data acquisition unit is connected to the user's mobile network terminal including mobile phones, tablet computers, and sports bracelets via Bluetooth, and obtains its network bandwidth demand parameters, including video stream data flow, submitted file data upload volume, submitted file data download volume, file upload speed, file download speed, and available network bandwidth. The network quality score value is obtained by calculating the network bandwidth demand parameters. The network demand characteristic value is obtained by calculating the signal quality evaluation index of each wireless network signal source, the distance from the user to each wireless network signal source, and the network quality score value.

[0013] According to the network demand characteristic value, it is determined whether the user's signal quality demand is met. According to the network demand characteristic value, an adjustment signal is obtained.

[0014] The spatial distribution prediction module establishes spatial dimension prediction models and temporal dimension prediction models, predicts the spatial distribution of wireless network signals from the spatial perspective and temporal dimension respectively, and fuses the models based on reference weights to obtain the optimal prediction distribution that conforms to the actual situation.

[0015] The topographic map of the environment in which the wireless network signal dynamic visualization imaging device is located is obtained, and the data is fused with the position coordinates of obstacles and interference sources that affect signal propagation in the camera coordinate system of the visual sensor to obtain a spatial model, and the spatial model is divided into several spatial units of different sizes.

[0016] As a preferred method of the present invention, a spatial dimension prediction model is established based on the spatial model, and lines are connected between all wireless network signal sources and all corner points of the spatial unit to simulate the propagation path of the wireless signal. And the shielding area of ​​obstacles and interference sources is generated according to the connection between the propagation path and the edge of the obstacle.

[0017] Obstacles and interference sources that affect signal propagation acquired by the environmental data acquisition unit are identified and marked, and the material refractive index and diffraction index are obtained according to the geometric shape, size and surface material of each obstacle and interference source.

[0018] Establish a wireless signal propagation model to evaluate the impact of obstacles and interference sources on the propagation of wireless network signals. According to the wireless signal propagation model, the direct radiation determinant, diffraction determinant and reflection determinant of the signal source and a certain corner point of the space unit with respect to the obstacle are obtained.

[0019] By combining the direct radiation determinator, diffraction determinator and reflection determinator, a preset formula is used to calculate the signal loss caused by direct radiation in the propagation path of the wireless signal emitted by the wireless network signal source to a corner point in the space unit.

[0020] As a preferred embodiment of the present invention, the specific process of establishing a time dimension prediction model based on the space model is as follows: Whenever it is detected that the user's precise coordinates coincide with the coordinates of a corner point in the space unit, that is, when the user passes through a corner point of the space unit, the user data collection unit records the real-time wireless network signal strength and coincidence time at the user's precise coordinates.

[0021] With the acquisition time as the horizontal axis and the signal strength RSSI as the vertical axis, a wireless network signal strength-time graph is established for each spatial unit corner point in the spatial model.

[0022] The signal strength is decomposed into three parts through periodic decomposition technology: trend part, periodic part and residual part.

[0023] The signal strength at each point in the space model is predicted through the trend part, the periodic part and the residual part, and the predicted wireless network signal strength of each point in the space model is obtained.

[0024] As a preferred embodiment of the present invention, data fusion is performed on the prediction results obtained by the spatial dimension prediction model and the temporal dimension prediction model. The specific process is as follows: Generate an adjustment weight vector and set the initial value of the adjustment weight therein so that the adjustment range is 0 to 1. Each adjustment weight corresponds to the coordinates of a corner point of the spatial model.

[0025] The calculation results of the spatial dimension prediction model and the temporal dimension prediction model are weighted and summed by adjusting the weights to obtain the final signal strength prediction value after data fusion.

[0026] The edge computing module evaluates whether the signal strength prediction result at the user's location is reliable, and determines whether the user can be accurately guided based on the spatial distribution of the final signal strength prediction value.

[0027] The prediction results of the spatial distribution prediction module are retrieved to obtain the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device and the predicted value of the final signal strength at this coordinate. The prediction error between the predicted value of the final signal strength and the actual wireless network signal strength is calculated by a preset formula, and the guidance signal and the adjustment signal are obtained according to the prediction error.

[0028] The central computing module dynamically adjusts the reference weights of the spatial dimension prediction model and the temporal dimension prediction model in the model fusion process according to the calculation results of the edge computing module, and sends the adjustment results to the spatial distribution prediction module to dynamically update the prediction results.

[0029] As a preferred embodiment of the present invention, when the central operation module obtains the adjustment signal, the specific value of the prediction error is obtained, and the updated value of the adjustment weight is obtained through a preset function.

[0030] The final signal strength prediction of each spatial unit coordinate is updated according to the updated adjustment weight.

[0031] The display guidance module presents the analysis results of the wireless network signal to the user in the form of visualization and voice, helping the user to understand the signal situation more intuitively and perform corresponding operations.

[0032] As a preferred method of the present invention, the updated final signal strength prediction value is obtained, and the final signal strength prediction value of the signal type of different protocols is converted into RGB color value by color coding and output to the spatial model, and the wireless network signal strength prediction result of each area is generated for visual output, and each protocol is assigned a specific color to generate a visualization diagram of the wireless network signal strength prediction result. Among them, the signal types of different protocols include: any one or a combination of multiple items of Wifi wireless fidelity signal, Bluetooth signal, NFC near-field communication signal, Zigbee signal, RFID radio frequency identification signal and cellular network protocol communication signal. According to the final signal strength prediction value of the signal type of different protocols, the brightness of the corresponding RGB color value is matched to each other, and the change trend of the final signal strength prediction value of the signal type of different protocols is displayed by the brightness of the RGB color value.

[0033] As a preferred method of the present invention, the signal heat map is superimposed on the real environment through a dynamic visualization imaging device of a wireless network signal, and is synchronized with the real environment through simulation to establish a digital twin mapping of the virtual environment and the actual environment of the wireless network signal strength.

[0034] As a preferred embodiment of the present invention, when the adjustment signal and the guidance signal are simultaneously identified, it is determined that the user has a need to improve the wireless network signal strength, and the precise coordinates of the user of the wireless network signal dynamic visualization imaging device are obtained. The optimal forward direction for improving the wireless network signal strength is calculated by the obtained precise coordinates and the final signal strength prediction value.

[0035] The optimal forward direction is projected in a highlighted form on the display portion of the wireless network signal dynamic visualization imaging device. Furthermore, when the user's forward direction is consistent with the optimal forward direction, a preset voice prompt is played to guide the user to continue forward.

[0036] In a second aspect, the present invention provides a method for dynamic imaging of polymorphic wireless network signals based on a metaverse, comprising the following steps: Step 1: Data collection; Acquire characteristic data of wireless network signal sources through sensors; obtain signal quality evaluation index through calculation of signal strength, spectrum width, signal-to-noise ratio and bit rate; Obtain the user's precise coordinates through GPS and indoor positioning; record the real-time wireless network signal strength through the signal receiver; obtain the signal strength of the user's current location through real-time signal strength recording; The camera captures the environment image and identifies obstacles and interference sources; obtains the position coordinates of obstacles and interference sources in the camera coordinate system; and converts the coordinates in the camera coordinate system into coordinates in the space coordinate system through space conversion operations; Connecting to a mobile terminal via Bluetooth to obtain network bandwidth requirement parameters; obtaining a network quality score by calculating the network bandwidth requirement parameters; The network demand characteristic value is calculated by combining the signal quality evaluation index, the distance from the user to the signal source and the network quality score; The characteristic value of network demand is obtained by calculating signal quality, distance and network quality.

[0037] Step 2: Construct a spatial dimension prediction model and a temporal dimension prediction model; Obtain a topographic map, fuse the location coordinates of obstacles and interference sources, build a spatial model and divide it into spatial units; obtain a spatial model and spatial units through data fusion; Construct a spatial dimension prediction model, simulate the wireless signal propagation path, generate shielding areas for obstacles and interference sources; calculate signal loss; obtain direct radiation determinants, diffraction determinants, and reflection determinants through the wireless signal propagation model; calculate signal loss through a preset formula; Construct a time dimension prediction model, record the signal strength and time when the user passes through the corner point of the spatial unit, and establish a signal strength-time graph; decompose the signal strength into a trend part, a periodic part, and a residual part; and obtain the predicted wireless network signal strength through periodic decomposition technology.

[0038] Step 3: Model fusion; The prediction results of the spatial dimension and the temporal dimension are weighted and summed by adjusting the weight vector to obtain the final signal strength prediction value; the final signal strength prediction value after data fusion is obtained by weighted summation.

[0039] Step 4: Evaluation of prediction results and generation of guidance signals; Retrieve the prediction results and calculate the prediction error; calculate the prediction error between the final signal strength prediction value and the actual signal strength through a preset formula; generate a guidance signal and an adjustment signal based on the prediction error.

[0040] Step 5: Update prediction results and adjust weights; Dynamically adjust the reference weights of the spatial dimension and temporal dimension prediction models according to the adjustment signal; By adjusting the weights, the final signal strength prediction value of each spatial unit is updated.

[0041] Step 6: Display and guidance; The analysis results are presented to the user in the form of visualization and voice. The signal strength prediction values ​​of different protocols are converted into RGB color values ​​through color coding to generate a visualization diagram. The change trend of signal strength is displayed through the light and dark changes of RGB color values. The signal heat map is superimposed on the real environment to establish a digital twin mapping of the virtual environment and the actual environment; when adjustment signals and guidance signals are detected, the optimal direction of travel is calculated and projected; and voice prompts are played.

[0042] The beneficial effects of the present invention are: 1. The present invention combines the spatial dimension prediction model and the time dimension prediction model to accurately predict the spatial distribution of wireless network signals through data fusion technology. Through detailed modeling of factors such as obstacles and interference sources, the system can evaluate the changes in signal strength in real time and adjust the signal provision strategy according to user needs. By dynamically adjusting the reference weight, the system can optimize the prediction results, improve the reliability and accuracy of wireless network signals, and ensure that users can obtain stable network quality in different environments; 2. The present invention can realize intelligent and dynamic network signal quality evaluation by collecting users' real-time network demands including video traffic, file upload and download, and their real-time demands for wireless network signal quality. Through the coordinated work of the network load data acquisition unit and the signal data acquisition unit, the system can adjust the signal demand according to the current needs of the users, thereby monitoring and adjusting the transmission quality of the wireless network signal in real time, ensuring that the network quality in different usage scenarios meets personalized needs; 3. The present invention uses a dynamic visualization imaging device for wireless network signals based on the Metaverse to visualize the wireless network signal strength in the user's environment in real time, and provides an intuitive operation interface through a display guidance module. Through signal strength heat maps and sound prompts, users can obtain timely feedback on the quality of wireless network signals, helping users find the area with the best signal in a complex environment, thereby achieving a more optimized network experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the system architecture of a metaverse-based polymorphic wireless network signal dynamic imaging system provided in an embodiment of the present invention; Figure 2 A topographic map of the environment in which the wireless network signal dynamic visualization imaging device provided in an embodiment of the present invention is located; Figure 3 A schematic diagram of a wireless signal propagation model provided in an embodiment of the present invention; Figure 4 It is a graph of original signal strength-time of a wireless network signal provided in an embodiment of the present invention; Figure 5 A schematic diagram of a trend portion obtained by periodic decomposition provided in an embodiment of the present invention; Figure 6 A schematic diagram of a periodic part obtained by periodic decomposition provided in an embodiment of the present invention; Figure 7 A schematic diagram of a residual part obtained by periodic decomposition provided in an embodiment of the present invention; Figure 8 A schematic diagram of visualizing a wireless network signal strength prediction result provided in an embodiment of the present invention.

[0044] Fig. 9 A method flow chart of a method for dynamic imaging of polymorphic wireless network signals based on the metaverse provided in an embodiment of the present invention; DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0047] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A or scheme B, or schemes that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0049] See also Figure 1 As shown, a metaverse-based polymorphic wireless network signal dynamic imaging system includes a data acquisition module, a spatial distribution prediction module, an edge computing module, a central computing module and a display guidance module.

[0050] The data acquisition module is the data input end of the wireless network signal dynamic visualization imaging device, including a signal data acquisition unit arranged at each wireless network signal source and a user data acquisition unit, an environmental data acquisition unit and a network load data acquisition unit arranged in the wireless network signal dynamic visualization imaging device.

[0051] The signal data acquisition unit obtains characteristic data of the wireless network signal source through sensors arranged at each wireless network signal source. The specific process is as follows: Get all wireless network signal sources and number them. The number symbol is , ;in is the total number of wireless network signal sources.

[0052] Get the signal strength of the primary rays emitted by each wireless network signal source , signal spectrum width , signal-to-noise ratio and bit rate ; By formula: ; Calculate the signal quality evaluation index of the primary rays sent by each wireless network signal source .

[0053] in is the preset influence coefficient, , and is the preset weight coefficient; , and are the normalized maximum values ​​of signal spectrum width, signal-to-noise ratio and bit rate respectively.

[0054] The higher the signal quality assessment index, the better the signal source The better the network signal quality provided.

[0055] The user data acquisition unit obtains the precise coordinates of the user of the wireless network signal dynamic visualization imaging device through GPS and indoor positioning. ; Real-time wireless network signal strength recorded by the signal receiver in real time by the dynamic visualization imaging device of the wireless network signal .

[0056] The environmental data acquisition unit obtains the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device. The wireless network signal dynamic visualization imaging device captures the environmental image through its camera, and identifies obstacles and interference sources that affect signal propagation based on computer vision algorithms.

[0057] Furthermore, the position coordinates of the obstacles and interference sources that affect signal propagation in the camera coordinate system of the visual sensor are obtained. .

[0058] The obstacles and interference sources that affect signal propagation include: Physical obstacles: building structures including walls, doors, windows, columns, floors, and ceilings; Physical interference sources: interference sources that produce shielding and reflection effects, including elevators and large electrical appliances Power interference sources: interference sources that generate strong electromagnetic fields, including high-voltage power lines and large electrical equipment; Equipment interference sources: Interference sources that cause signal conflicts include microwave ovens, televisions, and cordless phones.

[0059] The collected position and size data of obstacles and interference sources are spatially processed, and the position coordinates of the obstacles and interference sources in the camera coordinate system of the visual sensor are spatially transformed to obtain their coordinates in the spatial coordinate system. The conversion formula is: ; in is the rotation matrix and T is the translation vector.

[0060] The network load data acquisition unit is connected to the user's mobile network terminal such as mobile phone, tablet computer, sports bracelet, etc. through Bluetooth, and obtains its network bandwidth demand parameters, including video stream data flow. , the amount of uploaded file data submitted , the amount of data downloaded for submitted files , File upload speed , file download speed and available network bandwidth .

[0061] By default formula: ; Calculate network quality score ; Get the straight-line distance d(i) from the user to each wireless network signal source, By default formula: ; Calculate the network demand characteristic value When the network demand characteristic value Greater than the preset threshold When the network demand characteristic value is , it is determined that the user's signal quality requirement is not met, and an adjustment signal is output to the display guidance module; Less than the preset threshold Min When the user's signal quality requirement is determined to have been met, no adjustment signal is output to the display guidance module.

[0062] It should be noted that the user's demand for wireless network signal quality is not static, but dynamically adjusted according to their personal network transmission needs. For example, users who are conducting high-definition network video conferences have higher requirements for wireless network signal quality; in contrast, users who are only conducting simple text chats have relatively lower requirements for wireless network signal quality. In order to achieve accurate judgment, the network load data acquisition unit and the signal data acquisition unit work together to analyze the specific wireless network signal strength requirements of each user, and based on this, evaluate whether the wireless network signal strength of the user's current environment meets the usage requirements.

[0063] The spatial distribution prediction module establishes spatial dimension prediction models and temporal dimension prediction models, predicts the spatial distribution of wireless network signals from the spatial perspective and temporal dimension respectively, and fuses the models based on reference weights to obtain the optimal prediction distribution that conforms to the actual situation.

[0064] See also Figure 2 As shown, a topographic map of the environment in which the wireless network signal dynamic visualization imaging device is located is obtained, and data is fused with the position coordinates of obstacles and interference sources that affect signal propagation in the camera coordinate system of the visual sensor to obtain a spatial model, and the spatial model is divided into a number of spatial units of size a×a×a, where a is a preset unit control side length.

[0065] Based on the spatial model, the specific process of establishing the spatial dimension prediction model is as follows: Connect all wireless network signal sources and all corner points of the space unit to simulate the propagation path of the wireless signal. And generate the shielding area of ​​obstacles and interference sources based on the connection between the propagation path and the edge of the obstacle.

[0066] Identify and mark obstacles and interference sources that affect signal propagation obtained by the environmental data acquisition unit, and use number symbols to All recorded obstacles and interference sources are numbered, and a preset material refractive index is matched according to the surface material of each obstacle and interference source. , matching a preset diffraction index according to the geometry and size of each obstacle and interference source ; Where m is the total number of obstacles and interference sources.

[0067] See also Figure 3 As shown, a wireless signal propagation model is established to evaluate the impact of obstacles and interference sources on the propagation of wireless network signals, assuming three wireless network signal propagation modes: direct, diffraction and reflection.

[0068] Direct: Wireless network signal source The propagation path of a corner point (x, y, z) of the spatial unit does not collide with any blocking object, and it is determined that direct impact occurs, and the direct impact determination symbol is output. ; Otherwise, output the direct judgment symbol ; Diffraction: Wireless Network Signal Source The propagation path to a corner point (x, y, z) of the spatial unit encounters an obstacle , and obstacles When the magnitude of the size is less than or equal to the preset multiple of the wavelength of the electromagnetic wave emitted by the wireless network signal source, it is determined that diffraction occurs and a diffraction determination symbol is output. ; Otherwise, output the diffraction determinant ; Reflection: Wireless Network Signal Source The propagation path to a corner point (x, y, z) of the spatial unit encounters an obstacle , and the magnitude of the obstacle size is greater than the preset multiple of the wavelength of the electromagnetic wave emitted by the wireless network signal source, it is determined that emission occurs and the reflection determination symbol is output. ; Otherwise, output the reflection determinant ; By default formula: ; Calculate wireless network signal sources Signal loss caused by direct radiation during the propagation path of a wireless signal transmitted to a corner point (x, y, z) in a spatial unit , signal loss caused by diffraction Signal loss due to reflections ; in is a preset constant, is the ratio of pi; Wireless network signal source The distance from a corner point (x, y, z) in the spatial unit. is the free space propagation loss constant; where Wireless network signal source The frequency of For obstacles The diffraction index reflects the obstacles The geometric shape and size of is the reflection constant, For obstacles The reflection coefficient represents the reflection properties of the material and surface medium ,in For obstacles The refractive index of the surface material; is the refractive index of air.

[0069] By default formula: ; Calculate the spatially predicted wireless network signal strength at each point (x, y, z) in the spatial model ;in They represent direct radiation, diffraction and scattering respectively.

[0070] It should be noted that in the process of wireless signal propagation in coverage analysis, the most critical factor affecting the wireless signal reception field strength is obstacles or interference sources. The presence of obstacles leads to non-line-of-sight propagation such as reflection and diffraction of wireless signals, which greatly affects the strength of the received signal. Therefore, it is necessary to carry out detailed modeling of the building scene and use appropriate data calculations to simulate the propagation of wireless network signals in the building scene.

[0071] Based on the spatial model, the specific process of establishing the time dimension prediction model is as follows: Whenever the user's precise coordinates are detected Coincident with the coordinates (x, y, z) of a corner point in the space unit, that is, when the user passes through a corner point of the space unit, the real-time wireless network signal strength at (x, y, z) is recorded once by the user data collection unit and coincidence time .

[0072] Record the acquisition time t, location coordinates (x, y, z) and specific values ​​of real-time signal strength .

[0073] See also Figure 4 As shown, the acquisition time t is the horizontal axis and the signal strength is The vertical axis is used to establish a wireless network signal strength-time graph for each spatial unit corner point (x, y, z) in the spatial model.

[0074] See also Figure 5 , Figure 6 and Figure 7 As shown, the signal strength is converted into Divided into three parts: Trend part , Periodic part and the residual part .

[0075] Right now .

[0076] The trend part Represents the long-term trend of signal strength; the periodic part Represents the fluctuation of signal strength due to periodic factors; residual part Represents the unexplained portion of the signal strength, including data noise and unusual fluctuations.

[0077] It should be noted that since network usage behavior has a certain distribution pattern in the time dimension, the wireless network signal strength at each location also shows fluctuations in the time dimension. The trend part represents the long-term change trend of the wireless network signal strength. It reflects the overall directional change of the data over time, that is, whether the data is rising, falling, or remaining stable. The trend part is usually used to identify long-term change patterns, such as the wireless network signal strength rising or falling month by month with the addition of signal sources or the improvement of wireless network service levels. The periodic part represents the regular fluctuations of the wireless network signal strength due to periodic factors. These fluctuations are usually caused by periodic network usage behavior, such as a sudden increase in the demand for wireless network signals in the office area during workdays. The residual part is the part of the wireless network signal strength data left after removing the trend and periodic components, which usually contains random noise, incidental events, or unpredictable fluctuations. The residual noise reflects the random factors in the data, which may be caused by accidental factors or data measurement errors.

[0078] The signal strength at each point (x, y, z) in the spatial model is predicted through the trend part, the periodic part and the residual part. The specific process is: extrapolate the historical periodic fluctuation pattern and calculate the periodic part at the current time t Based on the fluctuation probability distribution of the residual part, a certain residual part forecast value at the current moment is randomly generated .

[0079] By default formula: ; Calculate the points in the spatial model Predicted wireless network signal strength .

[0080] in For the current moment, The exact coordinates of the last time the user was detected With coordinates The moment of coincidence; For the trend part The first derivative with respect to time; Furthermore, the prediction results obtained by the spatial dimension prediction model and the temporal dimension prediction model are fused. The specific process is as follows: Generate an adjustment weight vector: ; And let the initial value of the elements, that is, the adjustment weight, be 0.5, and the adjustment range is 0 to 1. is the total number of corner points of the spatial unit in the spatial model, where the elements Each corresponds to a spatial corner point coordinate (x, y, z), By default formula: ; Calculate the final signal strength prediction value after data fusion .

[0081] The edge computing module evaluates whether the signal strength prediction result at the user's location is reliable, and determines whether the user can be accurately guided based on the spatial distribution of the final signal strength prediction value.

[0082] Retrieve the prediction results of the spatial distribution prediction module to obtain the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device and the exact coordinates of the corresponding user The final signal strength prediction value .in ; ; ; By default formula: ; Calculate the prediction error between the final signal strength prediction value and the actual wireless network signal strength .

[0083] when ) is less than the preset threshold, the user is determined to be at The signal strength prediction result is reliable and the guidance signal is output; when When the user's location is less than the preset threshold, The signal strength prediction result is unreliable and an adjustment signal is output.

[0084] The central computing module dynamically adjusts the reference weights of the spatial dimension prediction model and the temporal dimension prediction model in the model fusion process according to the calculation results of the edge computing module, and sends the adjustment results to the spatial distribution prediction module to dynamically update the prediction results.

[0085] When the central operation module obtains the adjustment signal, the prediction error is obtained The specific value of , and through the preset function: ; Adjust weight To update. is the initial value of the adjusted weight, where is the preset learning rate.

[0086] Final signal strength prediction for each spatial unit coordinate (x, y, z) based on the updated adjustment weights to update.

[0087] It should be noted that, in essence, the final signal strength prediction value is based on the signal strength under ideal conditions calculated by the model, and there is an error between it and the actual signal distribution. The purpose of updating the adjustment weight is to output multiple adjustment weights for different areas to minimize this error. And save the reliable adjustment weights as the common adjustment weights when the user is active in each area, and directly call the adjustment weights the next time the user enters the area.

[0088] The display guidance module is responsible for presenting the analysis results of the wireless network signal to the user in the form of visualization and voice, helping the user to understand the signal situation more intuitively and perform corresponding operations.

[0089] See also Figure 8 As shown, the updated final signal strength prediction value is obtained, and the final signal strength prediction values ​​of signal types of different protocols are converted into RGB color values ​​by color coding and output to the spatial model, and the wireless network signal strength prediction results of each area are generated for visual output. Each protocol is assigned a specific color to generate a visual schematic diagram of the wireless network signal strength prediction results. Among them, the signal types of different protocols include: any one or a combination of Wifi wireless fidelity signals, Bluetooth signals, NFC near-field communication signals, Zigbee signals, RFID radio frequency identification signals, and cellular network protocol communication signals.

[0090] Furthermore, the final signal strength prediction values ​​of the signal types of different protocols are matched to the brightness of the corresponding RGB color values, and the change trend of the final signal strength prediction values ​​of the signal types of different protocols is displayed through the brightness of the RGB color values.

[0091] Furthermore, the signal heat map is superimposed on the real environment through the dynamic visualization imaging device of the wireless network signal, and synchronized with the real environment through simulation to establish a digital twin mapping of the virtual environment and the actual environment of the wireless network signal strength.

[0092] Furthermore, when the adjustment signal and the guidance signal are recognized at the same time, it is determined that the user has a need to improve the wireless network signal strength, and the precise coordinates of the user of the wireless network signal dynamic visualization imaging device are obtained. Based on the acquired precise coordinates and final signal strength prediction value Calculate the optimal direction to improve the wireless network signal strength. The specific process is: The final signal strength prediction value The partial derivatives of the spatial coordinates (x, y, z) along the coordinate axes x, y and z are: ; Calculate the rate of change of signal strength in each direction in space, that is, the gradient of signal strength.

[0093] The preset user's goal is to move in the direction of increasing signal strength, and calculate the inner product of the moving direction and the signal gradient: ; Record the maximum The direction of progress ;in is the inner product operator. By presetting the formula Get the best direction to ensure the best network experience.

[0094] The best direction to move forward The display is projected on the display part of the wireless network signal dynamic visualization imaging device in the form of a highlighted display. And when the user's forward direction is consistent with the optimal forward direction, a preset voice prompt is played to guide the user to continue forward.

[0095] See also Fig. 9 As shown, a method for dynamic imaging of polymorphic wireless network signals based on Metaverse includes the following steps: Step 1: Data collection; Acquire characteristic data of wireless network signal sources through sensors; obtain signal quality evaluation index through calculation of signal strength, spectrum width, signal-to-noise ratio and bit rate; Obtain the user's precise coordinates through GPS and indoor positioning; record the real-time wireless network signal strength through the signal receiver; obtain the signal strength of the user's current location through real-time signal strength recording; The camera captures the environment image and identifies obstacles and interference sources; obtains the position coordinates of obstacles and interference sources in the camera coordinate system; and converts the coordinates in the camera coordinate system into coordinates in the space coordinate system through space conversion operations; Connecting to a mobile terminal via Bluetooth to obtain network bandwidth requirement parameters; obtaining a network quality score by calculating the network bandwidth requirement parameters; The network demand characteristic value is calculated by combining the signal quality evaluation index, the distance from the user to the signal source and the network quality score; The characteristic value of network demand is obtained by calculating signal quality, distance and network quality.

[0096] Step 2: Construct a spatial dimension prediction model and a temporal dimension prediction model; Obtain a topographic map, fuse the location coordinates of obstacles and interference sources, build a spatial model and divide it into spatial units; obtain a spatial model and spatial units through data fusion; Construct a spatial dimension prediction model, simulate the wireless signal propagation path, generate shielding areas for obstacles and interference sources; calculate signal loss; obtain direct radiation determinants, diffraction determinants, and reflection determinants through the wireless signal propagation model; calculate signal loss through a preset formula; Construct a time dimension prediction model, record the signal strength and time when the user passes through the corner point of the spatial unit, and establish a signal strength-time graph; decompose the signal strength into a trend part, a periodic part, and a residual part; and obtain the predicted wireless network signal strength through periodic decomposition technology.

[0097] Step 3: Model fusion; The prediction results of the spatial dimension and the temporal dimension are weighted and summed by adjusting the weight vector to obtain the final signal strength prediction value; the final signal strength prediction value after data fusion is obtained by weighted summation.

[0098] Step 4: Evaluation of prediction results and generation of guidance signals; Retrieve the prediction results and calculate the prediction error; calculate the prediction error between the final signal strength prediction value and the actual signal strength through a preset formula; generate a guidance signal and an adjustment signal based on the prediction error.

[0099] Step 5: Update prediction results and adjust weights; Dynamically adjust the reference weights of the spatial dimension and temporal dimension prediction models according to the adjustment signal; By adjusting the weights, the final signal strength prediction value of each spatial unit is updated.

[0100] Step 6: Display and guidance; The analysis results are presented to the user in the form of visualization and voice. The signal strength prediction values ​​of different protocols are converted into RGB color values ​​through color coding to generate a visualization diagram. The change trend of signal strength is displayed through the light and dark changes of RGB color values. The signal heat map is superimposed on the real environment to establish a digital twin mapping of the virtual environment and the actual environment; when adjustment signals and guidance signals are detected, the optimal direction of travel is calculated and projected; and voice prompts are played.

Claims

1. A polymorphic wireless network signal dynamic imaging system based on Metaverse, characterized in that: It includes data acquisition module, spatial distribution prediction module, edge computing module and central computing module; The data acquisition module is the data input end of the wireless network signal dynamic visualization imaging device, including a signal data acquisition unit arranged at each wireless network signal source and a user data acquisition unit, an environment data acquisition unit and a network load data acquisition unit arranged in the wireless network signal dynamic visualization imaging device; The spatial distribution prediction module establishes a spatial model, a spatial dimension prediction model, and a temporal dimension prediction model, predicts the spatial distribution of wireless network signals from the spatial perspective and the temporal dimension respectively, and fuses the models based on the reference weights to obtain the optimal prediction distribution that conforms to the actual situation; The edge computing module retrieves the prediction results of the spatial distribution prediction module, obtains the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device and the predicted value of the final signal strength at this coordinate; calculates the prediction error between the predicted value of the final signal strength and the actual wireless network signal strength through a preset formula, and obtains the guidance signal and the adjustment signal according to the prediction error; The central computing module dynamically adjusts the reference weights of the spatial dimension prediction model and the temporal dimension prediction model during the model fusion process according to the prediction error and adjustment signal obtained by the edge computing module, and optimizes the prediction results by dynamically adjusting the reference weights.

2. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized in that: Also includes display guidance module: The display guidance module presents the analysis results of wireless network signals to users in the form of visualization and voice, helping users to understand the signal conditions more intuitively and perform corresponding operations; Obtain the updated final signal strength prediction value, convert the final signal strength prediction value of the signal type of different protocols into RGB color values ​​by color coding and output them to the spatial model, generate the wireless network signal strength prediction results of each area for visual output, assign a specific color to each protocol, and generate a visual schematic diagram of the wireless network signal strength prediction results; The signal types of different protocols include: any one or a combination of Wifi wireless fidelity signals, Bluetooth signals, NFC near-field communication signals, Zigbee signals, RFID radio frequency identification signals, and cellular network protocol communication signals; According to the final signal strength prediction values ​​of signal types of different protocols, the brightness of the corresponding RGB color values ​​is matched, and the change trend of the final signal strength prediction values ​​of signal types of different protocols is displayed through the brightness of the RGB color values; The signal heat map is superimposed on the real environment through the dynamic visualization imaging device of the wireless network signal, and synchronized with the real environment through simulation to establish a digital twin mapping of the virtual environment and the actual environment of the wireless network signal strength; When the adjustment signal and the guidance signal are identified at the same time, it is determined that the user has a need to improve the wireless network signal strength, and the precise coordinates of the user of the wireless network signal dynamic visualization imaging device are obtained; the optimal forward direction for improving the wireless network signal strength is calculated by the obtained precise coordinates and the final signal strength prediction value; The optimal forward direction is projected in a highlighted form on the display part of the wireless network signal dynamic visualization imaging device; and when the user's forward direction is consistent with the optimal forward direction, a preset voice prompt is played to guide the user to continue moving forward.

3. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized by: The signal data acquisition unit acquires characteristic data of the wireless network signal source through sensors arranged at each wireless network signal source, including signal strength, signal spectrum width, signal-to-noise ratio and bit rate of the primary rays emitted by each wireless network signal source; And by calculating the signal strength, signal spectrum width, signal-to-noise ratio and bit rate of the primary rays, the signal quality evaluation index of the primary rays sent by each wireless network signal source is obtained.

4. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized by: The user data acquisition unit obtains the precise coordinates of the user of the wireless network signal dynamic visualization imaging device through GPS and indoor positioning; and records the real-time wireless network signal strength of the wireless network signal dynamic visualization imaging device in real time through a signal receiver.

5. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized by: The environmental data acquisition unit obtains the actual wireless network signal strength at the location of the wireless network signal dynamic visualization imaging device and outputs it to the edge computing module; the environmental image is captured by the camera of the wireless network signal dynamic visualization imaging device, and obstacles and interference sources that affect signal propagation are identified based on a computer vision algorithm; the position coordinates of the obstacles and interference sources that affect signal propagation in the camera coordinate system of the visual sensor are obtained; The collected position and size data of obstacles and interference sources are spatially processed, and the position coordinates of the obstacles and interference sources in the camera coordinate system of the visual sensor are spatially transformed to obtain their coordinates in the spatial coordinate system.

6. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized by: The network load data acquisition unit is connected to the user's mobile network terminal including mobile phone, tablet computer, sports bracelet via Bluetooth, and obtains its network bandwidth demand parameters, including video stream data flow, submitted file data upload volume, submitted file data download volume, file upload speed, file download speed and available network bandwidth; the network quality score value is obtained by calculating the network bandwidth demand parameters; the network demand characteristic value is obtained by calculating the signal quality evaluation index of each wireless network signal source, the distance from the user to each wireless network signal source and the network quality score value; According to the network demand characteristic value, it is determined whether the user's signal quality demand is met; and the adjustment signal is obtained according to the network demand characteristic value.

7. According to claim 1, a metaverse-based multi-state wireless network signal dynamic imaging system is characterized in that: The specific process of establishing the spatial model by the spatial distribution prediction module is as follows: Obtain a topographic map of the environment in which the wireless network signal dynamic visualization imaging device is located, and fuse the data with the position coordinates of obstacles and interference sources that affect signal propagation in the camera coordinate system of the visual sensor to obtain a spatial model, and divide the spatial model into a number of spatial units of different sizes; Based on the spatial model, spatial dimension prediction models and time dimension prediction models are established.

8. The polymorphic wireless network signal dynamic imaging system based on the metaverse according to claim 7, characterized in that: The specific process of establishing a spatial dimension prediction model is as follows: Connect all wireless network signal sources and all corner points of the space unit to simulate the propagation path of the wireless signal; and generate shielding areas for obstacles and interference sources based on the connection between the propagation path and the edge of the obstacle; Identify and mark the obstacles and interference sources that affect signal propagation acquired by the environmental data acquisition unit, and obtain the material refractive index and diffraction index according to the geometric shape, size and surface material of each obstacle and interference source; A wireless signal propagation model is established to evaluate the impact of obstacles and interference sources on the propagation of wireless network signals. Based on the wireless signal propagation model, the direct determinant, diffraction determinant and reflection determinant of the obstacle between the signal source and a corner point of the spatial unit are obtained. By combining the direct radiation determinator, diffraction determinator and reflection determinator, a preset formula is used to calculate the signal loss caused by direct radiation in the propagation path of the wireless signal emitted by the wireless network signal source to a corner point in the space unit.

9. The polymorphic wireless network signal dynamic imaging system based on the metaverse according to claim 7, characterized in that: Whenever it is detected that the precise coordinates of the user coincide with the coordinates of a corner point in the space unit, that is, when the user passes through a corner point of the space unit, the real-time wireless network signal strength and coincidence time at the precise coordinates of the user are recorded once by the user data collection unit; With the acquisition time as the horizontal axis and the signal strength RSSI as the vertical axis, a wireless network signal strength-time graph is established for each spatial unit corner point in the spatial model; The signal strength is decomposed into three parts through periodic decomposition technology: trend part, periodic part and residual part; The signal strength at each point in the spatial model is predicted through the trend part, the periodic part and the residual part to obtain the predicted wireless network signal strength at each point in the spatial model; The prediction results obtained by the spatial dimension prediction model and the time dimension prediction model are fused to generate an adjustment weight vector, and the initial value of the adjustment weight is set so that the adjustment range is 0 to 1; each adjustment weight corresponds to the coordinates of a corner point of the spatial model; The calculation results of the spatial dimension prediction model and the temporal dimension prediction model are weighted and summed by adjusting the weights to obtain the final signal strength prediction value after data fusion.

10. A method for dynamic imaging of polymorphic wireless network signals based on metaverse, characterized in that: The following steps are involved: Step 1: Data collection; Acquire characteristic data of wireless network signal sources through sensors; obtain signal quality evaluation index through calculation of signal strength, spectrum width, signal-to-noise ratio and bit rate; Obtain the user's precise coordinates through GPS and indoor positioning; record the real-time wireless network signal strength through the signal receiver; obtain the signal strength of the user's current location through real-time signal strength recording; The camera captures the environment image and identifies obstacles and interference sources; obtains the position coordinates of obstacles and interference sources in the camera coordinate system; and converts the coordinates in the camera coordinate system into coordinates in the space coordinate system through space conversion operations; Connecting to a mobile terminal via Bluetooth to obtain network bandwidth requirement parameters; obtaining a network quality score by calculating the network bandwidth requirement parameters; The network demand characteristic value is calculated by combining the signal quality evaluation index, the distance from the user to the signal source and the network quality score; By calculating the signal quality, distance and network quality, the characteristic value of network demand is obtained; Step 2: Construct a spatial dimension prediction model and a temporal dimension prediction model; Obtain a topographic map, fuse the location coordinates of obstacles and interference sources, build a spatial model and divide it into spatial units; obtain a spatial model and spatial units through data fusion; Construct a spatial dimension prediction model, simulate the wireless signal propagation path, generate shielding areas for obstacles and interference sources; calculate signal loss; obtain direct radiation determinants, diffraction determinants, and reflection determinants through the wireless signal propagation model; calculate signal loss through a preset formula; Construct a time dimension prediction model, record the signal strength and time when the user passes through the corner point of the space unit, and establish a signal strength-time graph; Decompose the signal strength into a trend part, a periodic part and a residual part; obtain the predicted wireless network signal strength through the periodic decomposition technology; Step 3: Model fusion; The prediction results of the spatial dimension and the time dimension are weighted and summed by adjusting the weight vector to obtain the final signal strength prediction value; the final signal strength prediction value after data fusion is obtained by weighted summation; Step 4: Evaluation of prediction results and generation of guidance signals; Retrieve the prediction results and calculate the prediction error; Calculate the prediction error between the final signal strength prediction value and the actual signal strength through a preset formula; generate a guidance signal and an adjustment signal according to the prediction error; Step 5: Update prediction results and adjust weights; Dynamically adjust the reference weights of the spatial dimension and temporal dimension prediction models according to the adjustment signal; By adjusting the weights, the final signal strength prediction value of each spatial unit is updated; Step 6: Display and guidance; Present the analysis results to users in visual and voice forms; The signal strength prediction values ​​of different protocols are converted into RGB color values ​​through color coding to generate a visual schematic diagram; The changing trend of signal strength is displayed through the light and dark changes of RGB color values; The signal heat map is superimposed on the real environment to establish a digital twin mapping of the virtual environment and the actual environment; when adjustment signals and guidance signals are detected, the optimal direction of travel is calculated and projected; and voice prompts are played.

Images