Mobile phone signal intelligent control method and system based on application scene

Abstract

The invention discloses a mobile phone signal intelligent control method and system based on an application scene. The method comprises the following steps: acquiring a device connection identifier of a user in a target area, user signal strength, a user communication demand and environment information; determining the position coordinates of the equipment according to the equipment connection identifier and the user signal intensity, and visualizing the user space distribution characteristics in a thermodynamic diagram mode to obtain a density distribution diagram; dividing the density distribution diagram into homogenized blocks by adopting a density clustering algorithm; according to the signal intensity, extracting a signal use condition of the homogenized block, and generating a signal use matrix; calculating a signal attenuation coefficient according to the position coordinates and the environment information; fusing the signal using matrix and the signal attenuation coefficient to obtain block signal intensity, comparing the block signal intensity with a user communication demand, and calculating a signal intensity increment; and according to the signal intensity increment, adopting a time sequence prediction model to generate a signal intensity adjustment instruction for the homogenized block. According to the method, the optimal configuration of the mobile phone signal resources is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile phone signal control, and in particular to a method and system for intelligently controlling mobile phone signals based on application scenarios. Background Art

[0002] In today's highly connected world, mobile communications have become an integral part of people's daily lives. With the widespread use of smartphones and other mobile devices, users are increasingly demanding high-quality, stable signals, especially in densely populated areas such as business centers, residential areas, and transportation hubs. However, the complex and changeable user behaviors and environmental conditions in these areas pose great challenges to signal management. For example, in a business district on a weekday, the density of people during lunch time and during rush hour is significantly different, which not only affects the demand for network resources by users in a specific area, but also puts forward different requirements for signal coverage. At the same time, factors such as the height and distribution of buildings, changes in terrain, and weather conditions will have a direct impact on signal propagation, resulting in insufficient or excessive signal coverage in some places. Faced with such a complex environment, the traditional unified signal adjustment strategy is difficult to meet actual needs, which may lead to network congestion in some areas and idle resources in other areas. Therefore, how to dynamically divide and manage each block in real time according to user density and usage to achieve the optimal configuration of signal resources has become a key issue that needs to be solved in current mobile communication technology.

[0003] In an existing mobile phone signal control technology, the system first collects data on user density and signal usage by deploying multiple fixed sensors throughout the area. These sensors periodically send information to the central processing unit, including the number of users at the current location, the type of applications being used, and the frequency of network requests. After receiving this data, the central processing unit integrates and analyzes it to determine the overall distribution of users in the entire area. Next, the central processing unit divides the entire dense area into several blocks based on pre-set standards (such as the average number of users per square kilometer). Each block is regarded as an independent management unit, and its signal strength is adjusted uniformly based on the comprehensive data reported by all sensors within the block. For example, if the number of users in a block exceeds a preset threshold, the signal transmission power of the block is automatically increased; conversely, if the number of users is below a certain level, the signal strength is appropriately reduced to save resources.

[0004] This existing signal control technology relies on fixed sensors and preset standards to divide areas and adjust signal strength, making it difficult to respond in real time to rapid changes in user behavior and the environment. Due to lagging data updates, fixed evaluation intervals, and insufficient consideration of local aggregation characteristics, this technology performs poorly in dynamically adapting to emergencies and complex scenarios and cannot achieve true refined management and efficient resource utilization. At the same time, it lacks personalized optimization for different application scenarios, further limiting its effectiveness.

[0005] In summary, in the existing technology, there is a problem that it is impossible to divide and manage each area in real time and dynamically according to user density and usage conditions to achieve the optimal allocation of signal resources. Summary of the Invention

[0006] The present invention provides a mobile phone signal intelligent control method and system based on application scenarios to divide and manage each area in real time and dynamically according to user density and usage conditions, and achieve the optimal allocation of mobile phone signal resources.

[0007] In a first aspect, to solve the above technical problems, the present invention provides a mobile phone signal intelligent control method based on application scenarios, including: Obtaining device connection identifiers, user signal strengths, user communication requirements, and environmental information of users in a target area; Determining the position coordinates of devices according to the device connection identifiers and the user signal strengths, and visualizing the user spatial distribution characteristics in a heat map manner to obtain a density distribution map; Using a density clustering algorithm to divide the density distribution map into multiple homogeneous areas with similar user density characteristics; Extracting the signal usage conditions of user devices in the homogeneous areas according to the user signal strengths to generate a signal usage matrix; Calculating the signal attenuation coefficient of the homogeneous area according to the position coordinates and the environmental information; Fusing the signal usage matrix and the signal attenuation coefficient to obtain the area signal strength, and comparing it with the user communication requirements and calculating the signal strength increment; According to the signal strength increment, using a time series prediction model to generate a signal strength adjustment instruction for the homogeneous area.

[0008] In an optional implementation manner, the determining the position coordinates of devices according to the device connection identifiers and the user signal strengths, and visualizing the user spatial distribution characteristics in a heat map manner to obtain a density distribution map includes: Determining the position coordinates corresponding to the connection identifier of each device through a triangulation algorithm according to the user signal strength to obtain the device positions; Use the kernel density estimation algorithm to calculate the spatial distribution density of the device positions and generate a device density matrix for the target area; According to the value range of the device density matrix, use a preset color scale mapping rule to convert the density values into corresponding color values; Use a heat map rendering algorithm to map the color values onto a geographic coordinate system to generate a density distribution map; Among them, the spatial distribution density is calculated by the following formula: Among them, the density value is converted into the corresponding color value by the following formula: Among them, represents the density estimate value at the density estimate value at, represents a preset bandwidth parameter, represents the position coordinates of the th device, represents the number of devices, and represent the preset minimum color value and maximum color value, represents the th density value of the device density matrix, and represent the minimum density value and maximum density value in the device density matrix, represents the kernel function.

[0009] In an alternative embodiment, the step of using a density clustering algorithm to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics includes: Initialize all devices in the density distribution map as unvisited points; Calculate the corresponding neighborhood point number for each unvisited point and a preset core point radius one by one; Compare the number of neighborhood points with a preset minimum number of points. When the number of neighborhood points is greater than the minimum number of points, mark the corresponding unvisited point as a core point, create a new clustering cluster, and add the core point and the unvisited points within the core point radius to the clustering cluster; When there are other core points in the clustering cluster, merge all the clustering clusters corresponding to the core points together to obtain a clustering result; Calculate the density variance of the clustering cluster according to the clustering result. If the density variance is less than a preset variance threshold, the corresponding clustering cluster meets the homogenization condition, and a homogeneous block is obtained; Calculate the feature similarity of the user density within the homogeneous block, and determine the boundary range of the homogeneous block through the convex hull algorithm to generate a homogeneous block with similar user density characteristics; Among them, the feature similarity of the user density within the block is calculated by the following formula: Among them, represents the feature similarity of the homogeneous block and ; represents the unvisited point, and represent the homogeneous block and at the point ; represents the overlapping area of the homogeneous block and .

[0010] In an alternative embodiment, the method for extracting the signal usage of the user equipment in the homogeneous block according to the user signal strength and generating a signal usage matrix includes: Calculate the average signal strength, signal strength variance, and signal usage frequency of all devices in the block according to the signal strength in the homogeneous block; Use the average signal strength, the signal strength variance, and the signal usage frequency as the row vectors of the matrix to generate a signal usage matrix, where the number of rows of the matrix is equal to the number of homogeneous blocks, and the number of columns of the matrix is 3, corresponding to the average signal strength, the signal strength variance, and the signal usage frequency respectively.

[0011] In an alternative embodiment, the method for calculating the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information includes: Calculate the distance between the homogeneous block and the preset base station position according to the position coordinates of the homogeneous block; Calculate the signal attenuation factor according to the obstacle type and the number of obstacles in the environmental information; Calculate the signal attenuation coefficient according to the distance and the signal attenuation factor; Among them, the signal attenuation factor is calculated by the following formula: Among them, the signal attenuation coefficient is calculated by the following formula: Among them, represents the signal attenuation factor, and Indicates the heights of the preset transmitting antenna and receiving antenna, Indicates the preset signal frequency, Indicates the number of obstacles, Indicates the obstacle impact constant matched according to the obstacle type, Indicates the distance, Indicates the preset path loss exponent, Indicates the signal attenuation coefficient.

[0012] In an alternative embodiment, the fusing the signal using a matrix and the signal attenuation coefficient to obtain the block signal strength, and comparing with the user communication requirement and calculating the signal strength increment includes: Weightedly fusing the signal using the matrix and the signal attenuation coefficient to obtain the block signal strength; Subtracting the block signal strength from the user communication requirement to calculate the signal strength increment; Wherein, the block signal strength is calculated by the following formula: Wherein, is the block signal strength, 、 、 and Indicate the preset weight coefficients, Indicates the average signal strength in the signal usage matrix, Indicates the signal strength variance in the signal usage matrix, Indicates the signal usage frequency in the signal usage matrix, Indicates the signal attenuation coefficient.

[0013] In an alternative embodiment, according to the signal strength increment, using a time series prediction model to generate a signal strength adjustment instruction for the homogenized block includes: Taking the signal strength increment and the pre-stored historical signal strength increment as time series and inputting them into a pre-trained time series prediction model to predict the change trend of the signal strength increment in the future time period; Generating a signal strength adjustment instruction according to the prediction result, including adjusting the transmission power of the base station, adjusting the antenna direction and switching the frequency resource.

[0014] In a second aspect, the present invention provides a mobile phone signal intelligent control system based on an application scenario, including: A data acquisition module, configured to acquire the device connection identifier, user signal strength, user communication requirement and environmental information of users in the target area; A location determination module, configured to determine the location coordinates of a device based on the device connection identifier and the user signal strength, and visualize the user space distribution characteristics in the form of a heat map to obtain a density distribution map; A block division module, configured to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics by using a density clustering algorithm; A signal matrix generation module, configured to extract the signal usage of user devices in the homogeneous block based on the user signal strength, and generate a signal usage matrix; An attenuation coefficient calculation module, configured to calculate the signal attenuation coefficient of the homogeneous block based on the location coordinates and the environmental information; A signal increment calculation module, configured to fuse the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and compare it with the user communication requirement to calculate the signal strength increment; An instruction generation module, configured to generate a signal strength adjustment instruction for the homogeneous block by using a time series prediction model according to the signal strength increment. In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the application scenario-based intelligent control method for mobile phone signals described in any one of the above.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the application scenario-based intelligent control method for mobile phone signals described in any one of the above.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) By obtaining the device connection identifier, user signal strength, user communication requirement, and environmental information of users in the target area, and combining the triangulation algorithm and kernel density estimation, the present invention accurately determines the device location and generates a density distribution map, significantly improving the recognition accuracy and visualization effect of the user space distribution.

[0017] (2) The present invention uses a density clustering algorithm to divide the density distribution map into homogeneous blocks with similar user density characteristics, and combines the signal usage matrix and the signal attenuation coefficient to calculate the block signal strength, realizing the refined management and dynamic optimal allocation of mobile phone signal resources.

[0018] (3) The present invention predicts the change trend of signal strength increment in a future time period through a time series prediction model, and generates a signal strength adjustment instruction, including adjusting the transmission power of the base station, the antenna direction, and frequency resources, effectively solving the problem of uneven signal resource allocation and improving the signal management efficiency.

[0019] (4) The present invention dynamically adjusts the signal resource configuration by fusing multi-source data, combining the communication requirements of users and environmental information, significantly improving the accuracy and flexibility of signal management and optimizing the user experience.

[0020] In summary, the present invention obtains the device connection identifier, signal strength, communication requirements, and environmental information of users in the target area, determines the device location and generates a density distribution map; uses a density clustering algorithm to divide the density distribution map into homogeneous blocks, extracts the signal usage situation to generate a signal usage matrix; calculates the signal attenuation coefficient in combination with environmental information, fuses the signal usage matrix and the attenuation coefficient to obtain the block signal strength, and compares it with the communication requirements of users to calculate the signal strength increment; based on the increment, a time series prediction model is used to generate a signal strength adjustment instruction. The present invention realizes the dynamic optimization configuration of mobile phone signal resources, improves the signal management efficiency, and solves the problem that traditional signal control methods cannot respond to user behavior and complex environmental changes in real time. Description of the Drawings

[0021] Figure 1 is a schematic flowchart of a mobile phone signal intelligent control method based on an application scenario provided by the first embodiment of the present invention; Figure 2 is a schematic structural diagram of a mobile phone signal intelligent control system based on an application scenario provided by the second embodiment of the present invention. Specific Embodiments

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Referring to Figure 1 , the first embodiment of the present invention provides a mobile phone signal intelligent control method based on an application scenario, including the following steps: S11, obtaining the device connection identifier, user signal strength, user communication requirements, and environmental information of users in the target area; S12, determining the position coordinates of the device according to the device connection identifier and the user signal strength, and visualizing the user spatial distribution characteristics in a heat map manner to obtain a density distribution map; S13. Use the density clustering algorithm to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics; S14. Extract the signal usage conditions of the user devices in the homogeneous block according to the user signal strength, and generate a signal usage matrix; S15. Calculate the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information; S16. Fuse the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and compare it with the user communication requirements and calculate the signal strength increment; S17. According to the signal strength increment, use a time series prediction model to generate a signal strength adjustment instruction for the homogeneous block.

[0024] In step S11, obtain the device connection identifier, user signal strength, user communication requirements, and environmental information of the users in the target area.

[0025] First, the device connection identifier is obtained through the unique identification code of the mobile device, specifically including the International Mobile Equipment Identity (IMEI) or MAC address. The user signal strength is collected by the base station and realized by using the Received Signal Strength Indicator (RSSI) technology. The user communication requirements are determined by analyzing the real-time traffic data, application types, and network request frequencies of the users, and are specifically extracted from the background management system of the network operator. The environmental information includes obstacle types, weather conditions, and terrain features, and is obtained through Geographic Information System (GIS) and remote sensing technologies. The acquisition methods of these data involve real-time monitoring of the base station, analysis of network data streams, and collection and processing technologies of geographic information. The device connection identifier is used to identify and locate the user device, the user signal strength reflects the signal reception quality of the device, the user communication requirements characterize the degree of use of network resources by the users, and the environmental information evaluates the attenuation factors in the signal propagation process.

[0026] In step S12, determine the position coordinates of the device according to the device connection identifier and the user signal strength, and use a heat map method to visualize the user spatial distribution characteristics to obtain a density distribution map.

[0027] In a specific implementation manner, the determining the position coordinates of the device according to the device connection identifier and the user signal strength, and using a heat map method to visualize the user spatial distribution characteristics to obtain a density distribution map includes: According to the user signal strength, determine the position coordinates corresponding to the connection identifier of each device through the triangulation algorithm to obtain the device position; Use the kernel density estimation algorithm to calculate the spatial distribution density of the device positions to generate a device density matrix of the target area; According to the numerical range of the device density matrix, convert the density value into a corresponding color value by using a preset color scale mapping rule; Use a heat map rendering algorithm to map the color value onto a geographic coordinate system to generate a density distribution map; Among them, the spatial distribution density is calculated by the following formula: Among them, the density value is converted into a corresponding color value by the following formula: Among them, represents the density estimate at represents a preset bandwidth parameter, represents the th device's position coordinate, represents the number of devices, represents the color value, and represent the preset minimum color value and maximum color value, represents the th density value of the device density matrix, and represent the minimum density value and maximum density value in the device density matrix, represents the kernel function.

[0028] Specifically, in step S12, determine the position coordinates of the device according to the device connection identifier and the user signal strength, and visualize the user spatial distribution characteristics in a heat map manner to obtain a density distribution map. In the specific implementation process, first, determine the position coordinates of each device by using the user signal strength and the triangulation algorithm. The triangulation algorithm is based on the signal strengths received by multiple base stations, calculates the attenuation degree of the signal strength to determine the distances between the device and each base station, and then solves the accurate position coordinates of the device through geometric methods. This process involves the conversion formula between signal strength and distance, that is, the signal strength is inversely proportional to the square of the distance. Specifically, it is realized by using the received signal strength indication (RSSI) and the path loss model to calculate the relative position of the device. The specific formula is: Solve the position coordinates of the device by combining the signal strength data of multiple base stations through this formula .

[0029] Assume that the coordinates of three wireless access points (APs) are known as , and and the corresponding signal strength values , and , the signal strength can be converted into distance through the following formula. The relationship between signal strength and distance usually adopts the log-distance path loss model: where represents the estimated distance from the device to the th AP, is the signal strength value of the th wireless access point, is the signal strength at a preset reference distance, is the path loss exponent, usually taking values between 2 and 4. According to the principle of trilateration, the geographical location of the device can be solved by the following system of equations: By solving this system of equations, the geographical location coordinates of the device can be obtained.

[0030] After obtaining the position coordinates of the device, the kernel density estimation algorithm is used to calculate the spatial distribution density of the device position, generating the device density matrix of the target area. The kernel density estimation algorithm obtains the device distribution density in the target area by performing weighted calculations on the positions of each device in space. The specific formula is: where represents the density estimation value at position , represents the number of devices, is the preset bandwidth parameter, used to control the smoothness of the kernel function, represents the position coordinates of the th device, is the kernel function, adopting the Gaussian kernel function form: By calculating the device density value at each position in the target area using this formula, the device density matrix is generated.

[0031] Next, according to the numerical range of the device density matrix, the preset color scale mapping rule is used to convert the density value into the corresponding color value. The specific formula is: where represents the converted color value, represents the density value at the th row and the th column in the device density matrix, and represent the minimum and maximum density values in the device density matrix, and represent the preset minimum and maximum color values. Through this formula, the density values are mapped into the color space to generate a color matrix corresponding to the density values.

[0032] Finally, a heat map rendering algorithm is used to map the color values onto the geographic coordinate system to generate a density distribution map. The heat map rendering algorithm matches each color value in the color matrix with the corresponding position in the geographic coordinate system and generates a visual heat map through image rendering technology.

[0033] This step converts the discrete device location data into a continuous density distribution map through a triangulation algorithm and a kernel density estimation algorithm, intuitively showing the spatial distribution characteristics of users. The generation process of the heat map involves the calculation of density values, color mapping, and image rendering, and can provide visual support for subsequent homogeneous block division and signal strength adjustment.

[0034] In step S13, a density clustering algorithm is used to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics.

[0035] In a specific implementation manner, the using a density clustering algorithm to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics includes: Initialize all devices in the density distribution map as unvisited points; Calculate the corresponding neighborhood points for each unvisited point and a preset core point radius one by one; Compare the neighborhood points with a preset minimum number of points. When the neighborhood points are greater than the minimum number of points, mark the corresponding unvisited point as a core point, create a new clustering cluster, and add the core point and the unvisited points within the core point radius to the clustering cluster; When there are other core points in the clustering cluster, merge all the clustering clusters corresponding to the core points together to obtain the clustering result; Calculate the density variance of the clustering cluster according to the clustering result. If the density variance is less than a preset variance threshold, the corresponding clustering cluster meets the homogeneous condition to obtain a homogeneous block; Calculate the feature similarity of the user density within the homogeneous block according to the homogeneous block, and determine the boundary range of the homogeneous block through a convex hull algorithm to generate a homogeneous block with similar user density characteristics; Among them, the feature similarity of the user density within the block is calculated by the following formula: Among them, represents a homogeneous block and feature similarity indicating unvisited points and indicating homogeneous blocks and at point the density value indicating homogeneous block and the overlapping area

[0036] Specifically, first, all devices are initialized as unvisited points, and the corresponding number of neighborhood points is calculated based on each unvisited point and the preset core point radius. The calculation of the number of neighborhood points is based on the Euclidean distance between the target point and its neighboring points to determine whether it is within the core point radius. Let the unvisited point be and the neighborhood point set be Then the formula for calculating the number of neighborhood points is: where represents the set of all device positions is the preset core point radius is an indicator function. When the Euclidean distance between point and point is less than or equal to , the function value is 1, otherwise it is 0. Point is all other device position points in except the current unvisited point

[0037] Compare the calculated number of neighborhood points with the preset minimum number of points . If , then mark point as a core point and create a new cluster , and add the core point and all unvisited points within its core point radius to the cluster . If there are other core points in the cluster , then merge all the clusters corresponding to the core points together to obtain the clustering result

[0038] In the clustering result, calculate the density variance of each cluster and determine whether the density variance meets the homogeneous condition. The formula for calculating the density variance is: where Represents the density variance, Represents a point The density value at, Represents a clustering cluster The average density value of, Represents a clustering cluster.

[0039] If the clustering cluster The density variance of, Is less than the preset variance threshold 𝜃, then it is considered that this clustering cluster meets the homogenization condition, and a homogenized block is obtained.

[0040] Next, calculate the feature similarity of the user density within the homogenized block. Let the density matrices of the homogenized blocks And Be respectively And , then the formula for the feature similarity Is: This formula calculates the sum of the minimum density values in the overlapping region of the blocks And , and normalizes it to the square root of the product of the density values of the two blocks, to obtain a quantified value of the feature similarity, where, Represents the overlapping region of the homogenized blocks And .

[0041] Finally, determine the boundary range of the homogenized block through the convex hull algorithm. The convex hull algorithm generates a homogenized block with similar user density characteristics by constructing the minimum convex polygon of the point set and including the device position points within the homogenized block. The calculation of the convex hull is based on the geometric distribution of the device position points, ensuring that the boundary range of the block can completely cover the user-dense area.

[0042] This step divides the density distribution map into multiple homogenized blocks with similar user density characteristics through the density clustering algorithm and the convex hull algorithm. This process can identify user-dense areas and sparse areas, providing a basis for regional division for the optimal allocation of signal resources.

[0043] In step S14, according to the user signal strength, extract the signal usage situation of the user devices in the homogenized block, and generate a signal usage matrix.

[0044] In a specific implementation manner, the extracting the signal usage situation of the user devices in the homogenized block according to the user signal strength and generating a signal usage matrix includes: According to the signal strength within the homogenized block, calculate the average signal strength, signal strength variance, and signal usage frequency of all devices in this block; Taking the average signal strength, the variance of the signal strength, and the signal usage frequency as row vectors of a matrix, a signal usage matrix is generated, where the number of rows of the matrix is equal to the number of homogeneous blocks, and the number of columns of the matrix is 3, corresponding to the average signal strength, the variance of the signal strength, and the signal usage frequency respectively.

[0045] Specifically, first, for each homogeneous block , the signal strength data of all devices within it are extracted , where represents the homogeneous block . Based on these signal strength data, the average signal strength , the variance of the signal strength , and the signal usage frequency of this block are calculated.

[0046] The calculation formula for the average signal strength is: The calculation formula for the variance of the signal strength is: Where represents the th signal strength data, represents the average signal strength, represents the variance of the signal strength, represents the number of signal strength data.

[0047] The calculation of the signal usage frequency is based on the number of connections of the device within a preset time window, and the specific formula is: Where represents the number of connections of the device within the preset time window .

[0048] Taking the calculated average signal strength , the variance of the signal strength , and the signal usage frequency as row vectors of a matrix, a signal usage matrix is generated. The number of rows of the matrix is equal to the number of homogeneous blocks, and the number of columns of the matrix is 3, corresponding to the average signal strength, the variance of the signal strength, and the signal usage frequency respectively.

[0049] This step quantifies the signal usage of user equipment in each homogeneous block through statistical analysis of signal strength data. The generation of the signal usage matrix provides comprehensive information on the average signal strength, fluctuations, and device connection frequency within the block, providing data support for subsequent optimal allocation of signal resources.

[0050] In step S15, calculate the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information.

[0051] In a specific implementation manner, the calculating the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information includes: Calculate the distance between the homogeneous block and the preset base station position according to the position coordinates of the homogeneous block; Calculate the signal attenuation factor according to the obstacle type and the number of obstacles in the environmental information; Calculate the signal attenuation coefficient according to the distance and the signal attenuation factor; Among them, the signal attenuation factor is calculated by the following formula: Among them, the signal attenuation coefficient is calculated by the following formula: Among them, represents the signal attenuation factor, and represent the heights of the preset transmitting antenna and receiving antenna, represents the preset signal frequency, represents the number of obstacles, represents the obstacle impact constant matched according to the obstacle type, represents the distance, represents the preset path loss exponent, represents the signal attenuation coefficient.

[0052] Specifically, first, for each homogeneous block , from its position coordinates and the preset base station position calculate the Euclidean distance between them , and the calculation formula is: The distance represents the physical distance between the homogeneous block and the base station, which is used for subsequent calculation of the signal attenuation coefficient.

[0053] Next, calculate the signal attenuation factor according to the obstacle type and the number of obstacles in the environmental information The type of obstacle is represented by a preset obstacle influence constant indicating the number of obstacles representing the number of obstacles between the block and the base station. The signal attenuation factor is calculated by the formula: where is the number of obstacles, is the constant matching the obstacle type. This formula quantifies the attenuation effect of obstacles on the signal through the logarithmic relationship between the number of obstacles and the distance.

[0054] Finally, according to the signal attenuation factor , the preset transmitting antenna height , the receiving antenna height , the signal frequency and the path loss exponent , the signal attenuation coefficient is calculated. The formula for the signal attenuation coefficient is: This formula synthesizes the effects of distance, antenna height, signal frequency and path loss exponent, and quantifies the attenuation degree of the signal during propagation.

[0055] This step quantifies the signal attenuation coefficient of each homogeneous block through the position coordinates and environmental information. The calculation of the signal attenuation coefficient provides a basis for the subsequent optimization and adjustment of the signal strength, helps to identify the areas with large signal attenuation, and thus realizes the precise allocation of signal resources.

[0056] In step S16, the block signal strength is obtained by fusing the signal usage matrix and the signal attenuation coefficient, and is compared with the user's communication requirement to calculate the signal strength increment.

[0057] In a specific implementation manner, obtaining the block signal strength by fusing the signal usage matrix and the signal attenuation coefficient and comparing it with the user's communication requirement to calculate the signal strength increment includes: Performing weighted fusion on the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength; Calculating the difference between the block signal strength and the user's communication requirement to obtain the signal strength increment; where the block signal strength is calculated by the following formula: where is the block signal strength, , , and represents a preset weight coefficient, represents the average signal strength in the signal usage matrix, represents the variance of signal strength in the signal usage matrix, represents the signal usage frequency in the signal usage matrix, represents the signal attenuation coefficient.

[0058] Specifically, in step S16, the block signal strength is obtained by fusing the signal usage matrix and the signal attenuation coefficient, and compared with the user communication requirement to calculate the signal strength increment. For each homogeneous block, its average signal strength, signal strength variance and signal usage frequency are extracted from the signal usage matrix, and the signal attenuation coefficient of this block is obtained simultaneously. Through the way of weighted fusion, the block signal strength is calculated , and the calculation formula is: where, , , and are preset weight coefficients, representing the contribution degrees of the average signal strength, signal strength variance, signal usage frequency and signal attenuation coefficient in the calculation of the block signal strength respectively. This formula comprehensively evaluates the actual signal strength of the block by weighted fusion of the signal usage matrix and the signal attenuation coefficient.

[0059] Next, compare the block signal strength with the user communication requirement to calculate the signal strength increment . The calculation formula of the signal strength increment is: where, represents the user communication requirement of block , which is usually preset according to the number of users, service type or other requirement indicators. The signal strength increment represents the gap between the current block signal strength and the user requirement. A positive value indicates insufficient signal strength, and a negative value indicates excessive signal strength.

[0060] This step quantifies the actual signal strength of the block by weighted fusion of the signal usage matrix and the signal attenuation coefficient, and combines with the user communication requirement to calculate the signal strength increment. The calculation of the signal strength increment provides a direct basis for the subsequent optimal allocation of signal resources, helps identify the areas with insufficient or excessive signals, so as to achieve precise signal adjustment.

[0061] In step S17, according to the signal strength increment, a time series prediction model is used to generate a signal strength adjustment instruction for the homogeneous block.

[0062] In a specific implementation manner, the generating a signal strength adjustment instruction for the homogeneous block according to the signal strength increment by using a time series prediction model includes: Taking the signal strength increment and the pre-stored historical signal strength increments as a time series and inputting them into a pre-trained time series prediction model to predict the change trend of the signal strength increment in a future time period; Generating a signal strength adjustment instruction according to the prediction result, including adjusting the transmission power of the base station, adjusting the antenna direction, and switching frequency resources.

[0063] Specifically, first, the signal strength increment at the current time point and the pre-stored historical signal strength increments are taken as a time series and input into a pre-trained time series prediction model. Let the length of the time series be , the input data is , where represents the signal strength increment at the current time point. The output of the time series prediction model is the predicted value of the signal strength increment in a future time period .

[0064] The time series prediction model usually adopts algorithms such as ARIMA (Autoregressive Integrated Moving Average Model) or LSTM (Long Short-Term Memory Network). Taking the ARIMA model as an example, its prediction formula is: where, is the autoregressive coefficient, is the moving average coefficient, is the error term, and are the orders of autoregression and moving average respectively, and k is the prediction step.

[0065] According to the prediction result , a signal strength adjustment instruction is generated. If the predicted value is positive, it means that the signal strength at the future time point is insufficient, and the adjustment instruction includes increasing the transmission power of the base station, adjusting the antenna direction, or switching frequency resources; if the predicted value is negative, it means that the signal strength at the future time point is excessive, and the adjustment instruction includes reducing the transmission power of the base station, adjusting the antenna direction, or releasing frequency resources.

[0066] This step uses a time series prediction model to predict in advance the change trend of the signal strength increment and generate a signal strength adjustment instruction. The implementation of the adjustment instruction can effectively optimize the signal resource allocation, avoid the situation of insufficient or excessive signal strength, and improve the user communication experience. This process combines time series analysis technology and signal optimization strategies to achieve accurate prediction and dynamic adjustment of future signal requirements.

[0067] To facilitate the understanding of the present invention, some preferred embodiments of the present invention will be further described below.

[0068] The working process of the present invention will be described below by taking a relatively common scenario as an example. For the specific implementation manner of the present invention, refer to Figure 1 , a mobile phone signal intelligent control method based on an application scenario, comprising the following steps: In a specific case, for the mobile phone signal optimization requirement in a certain business district, first obtain the device connection identifier, user signal strength, user communication requirement and environmental information of the users in the target area. By using the triangulation algorithm and the kernel density estimation algorithm, determine the position coordinates of the device and generate a density distribution map. The density distribution map shows that the user density in the business district is significantly higher during the lunch time and the evening rush hour than other times, and the user density in the peak area reaches 3.5 people per square meter. The density distribution map is divided into 5 homogeneous blocks by using the density clustering algorithm, and the similarity of the user density characteristics within the blocks is higher than 0.85, meeting the homogeneous conditions.

[0069] According to the signal strength data, extract the average signal strength, signal strength variance and signal usage frequency of each homogeneous block to generate a signal usage matrix. The results show that the average signal strength of block A is -75 dBm, the signal strength variance is 15, and the signal usage frequency is 25 times per minute; the average signal strength of block B is -80 dBm, the signal strength variance is 20, and the signal usage frequency is 30 times per minute. Combining the environmental information, calculate the signal attenuation coefficient of each block. The signal attenuation coefficient of block A is 2.5, and the signal attenuation coefficient of block B is 3.0, mainly because there are more reinforced concrete buildings in block B.

[0070] Fuse the signal usage matrix and the signal attenuation coefficient to calculate the block signal strength. The block signal strength of block A is 85, and the block signal strength of block B is 70. Compare the block signal strength with the user communication requirement. The signal strength increment of block A is 5, and the signal strength increment of block B is 15, indicating that the signal strength of block B is insufficient and needs to be optimized and adjusted.

[0071] Using a time - series prediction model, the current and historical signal strength increments are input to predict the changing trend of the signal strength increment in the future time period. The model prediction results show that the signal strength increment in Block B will gradually increase to 20 within the next 30 minutes. According to the prediction results, signal strength adjustment instructions are generated, including increasing the transmission power of the base station by 20%, adjusting the antenna direction by 10 degrees, and switching to a frequency resource in a higher frequency band.

[0072] After signal adjustment, the signal strength in Block B is increased to - 75 dBm, the signal strength increment is reduced to 5, and the communication needs of users are met. At the same time, the signal strength in Block A remains stable, and there is no situation of resource idleness or over - adjustment. This case realizes the dynamic optimization configuration of signal resources through an intelligent mobile phone signal control method based on the application scenario, improves the user communication experience in the commercial area, and verifies the effectiveness and practicality of the method.

[0073] Refer to Figure 2 , the second embodiment of the present invention provides an intelligent mobile phone signal control system based on the application scenario, including: A data acquisition module, configured to acquire device connection identifiers, user signal strengths, user communication requirements, and environmental information of users in the target area; A location determination module, configured to determine the position coordinates of the device according to the device connection identifier and the user signal strength, and visualize the user spatial distribution characteristics in the form of a heat map to obtain a density distribution map; A block division module, configured to divide the density distribution map into multiple homogeneous blocks with similar user density characteristics by using a density clustering algorithm; A signal matrix generation module, configured to extract the signal usage conditions of user devices in the homogeneous block according to the user signal strength to generate a signal usage matrix; An attenuation coefficient calculation module, configured to calculate the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information; A signal increment calculation module, configured to fuse the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and compare it with the user communication requirement and calculate the signal strength increment; An instruction generation module, configured to generate signal strength adjustment instructions for the homogeneous block by using a time - series prediction model according to the signal strength increment.

[0074] It should be noted that an intelligent mobile phone signal control device based on the application scenario provided in the embodiment of the present invention is used to execute all the process steps of an intelligent mobile phone signal control method based on the application scenario in the above - mentioned embodiment. Their working principles and beneficial effects correspond one by one, so they will not be elaborated here.

[0075] An embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a mobile phone signal intelligent control program based on an application scenario. When the processor executes the computer program, the steps in the above-mentioned embodiments of various mobile phone signal intelligent control methods based on application scenarios are implemented, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as a mobile phone signal intelligent control module based on an application scenario.

[0076] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0077] The electronic device can be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0078] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0079] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and invoking the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0080] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0081] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0082] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A mobile phone signal intelligent control method based on application scenarios, characterized in that, Including: Obtaining the device connection identifier, user signal strength, user communication requirements, and environmental information of users within the target area; Determining the position coordinates of the device based on the device connection identifier and the user signal strength, and visualizing the user spatial distribution characteristics in the form of a heat map to obtain a density distribution map; Dividing the density distribution map into multiple homogeneous blocks with similar user density characteristics by using a density clustering algorithm; Extracting the signal usage conditions of the user devices in the homogeneous block according to the user signal strength to generate a signal usage matrix; Calculating the signal attenuation coefficient of the homogeneous block according to the position coordinates and the environmental information; Fusing the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and comparing it with the user communication requirements and calculating the signal strength increment; Generating a signal strength adjustment instruction for the homogeneous block by using a time series prediction model according to the signal strength increment.

2. The intelligent mobile phone signal control method based on application scenarios according to claim 1, wherein The determining the position coordinates of the device based on the device connection identifier and the user signal strength, and visualizing the user spatial distribution characteristics in the form of a heat map to obtain a density distribution map includes: Determining the position coordinates corresponding to the connection identifier of each device by using a triangulation algorithm according to the user signal strength to obtain the device position; Calculating the spatial distribution density of the device positions by using a kernel density estimation algorithm to generate a device density matrix of the target area; Converting the density value into a corresponding color value by using a preset color scale mapping rule according to the numerical range of the device density matrix; Rendering the color value onto a geographic coordinate system by using a heat map rendering algorithm to generate a density distribution map; Wherein, the spatial distribution density is calculated by the following formula: Wherein, the density value is converted into a corresponding color value by the following formula: Among them, represents the density estimate value at represents the preset bandwidth parameter, represents the th position coordinate of the device, represents the number of devices, represents the color value, and represent the preset minimum color value and maximum color value, represents the th density value of the device density matrix, and represent the minimum density value and maximum density value in the device density matrix, represents the kernel function.

3. The intelligent mobile phone signal control method based on application scenarios according to claim 1, characterized in that The dividing the density distribution map into multiple homogeneous blocks with similar user density characteristics by using a density clustering algorithm includes: Initializing all devices in the density distribution map as unvisited points; Calculating the corresponding neighborhood points one by one according to the unvisited points and a preset core point radius; Comparing the number of neighborhood points with a preset minimum number of points. When the number of neighborhood points is greater than the minimum number of points, marking the corresponding unvisited point as a core point, creating a new clustering cluster, and adding the core point and the unvisited points within the core point radius to the clustering cluster; When there are other core points in the clustering cluster, merging all the clustering clusters corresponding to the core points together to obtain a clustering result; Calculating the density variance of the clustering cluster according to the clustering result. If the density variance is less than a preset variance threshold, the corresponding clustering cluster meets the homogenization condition to obtain a homogeneous block; Calculating the feature similarity of the user density within the block according to the homogeneous block, and determining the boundary range of the homogeneous block by using a convex hull algorithm to generate a homogeneous block with similar user density characteristics; Wherein, the feature similarity of the user density within the block is calculated by the following formula: Among them, represents the homogeneous block and the feature similarity, represents the unvisited point, and represents the homogeneous block and at the point the density value, represents the overlapping area of the homogeneous blocks and ​ 4. The intelligent control method for mobile phone signals based on application scenarios according to claim 1, characterized in that, The extracting the signal usage conditions of the user devices in the homogeneous block according to the user signal strength to generate a signal usage matrix includes: Calculate the average signal strength, signal strength variance, and signal usage frequency of all devices within the homogenized block based on the signal strength within the homogenized block; Use the average signal strength, the signal strength variance, and the signal usage frequency as row vectors of a matrix to generate a signal usage matrix, where the number of rows of the matrix is equal to the number of homogenized blocks, and the number of columns of the matrix is 3, corresponding to the average signal strength, the signal strength variance, and the signal usage frequency respectively.

5. The intelligent control method for mobile phone signals based on application scenarios according to claim 1, wherein, The calculating the signal attenuation coefficient of the homogenized block according to the position coordinates and the environmental information includes: Calculate the distance between the homogenized block and the preset base station position according to the position coordinates of the homogenized block; Calculate the signal attenuation factor according to the obstacle type and the number of obstacles in the environmental information; Calculate the signal attenuation coefficient according to the distance and the signal attenuation factor; Among them, the signal attenuation factor is calculated by the following formula: Among them, the signal attenuation coefficient is calculated by the following formula: wherein, represents a signal attenuation factor, and represent the heights of a preset transmitting antenna and a receiving antenna, represents a preset signal frequency, represents the number of obstacles, represents an obstacle influence constant matched according to the obstacle type, represents the distance, represents a preset path loss exponent, represents a signal attenuation coefficient.

6. The intelligent control method for mobile phone signals based on application scenarios according to claim 1, characterized in that The fusing the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and comparing with the user communication requirement and calculating the signal strength increment includes: Perform weighted fusion on the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength; Calculate the difference between the block signal strength and the user communication requirement to obtain the signal strength increment; Among them, the block signal strength is calculated by the following formula: Among them, is the block signal strength, , , and represent preset weight coefficients, represents the average signal strength in the signal usage matrix, represents the signal strength variance in the signal usage matrix, represents the signal usage frequency in the signal usage matrix, represents the signal attenuation coefficient.

7. The intelligent control method for mobile phone signals based on application scenarios according to claim 1, wherein The generating a signal strength adjustment instruction for the homogenized block by using a time series prediction model according to the signal strength increment includes: Input the signal strength increment and the pre-stored historical signal strength increment as a time series into a pre-trained time series prediction model to predict the change trend of the signal strength increment in the future time period; Generate a signal strength adjustment instruction according to the prediction result, including adjusting the transmission power of the base station, adjusting the antenna direction, and switching frequency resources.

8. An intelligent mobile phone signal control system based on application scenarios, characterized in that, Include: A data acquisition module, configured to acquire the device connection identifier, user signal strength, user communication requirement, and environmental information of users within the target area; A position determination module, configured to determine the position coordinates of the device according to the device connection identifier and the user signal strength, and visualize the user space distribution characteristics in the form of a heat map to obtain a density distribution map; A block division module, configured to divide the density distribution map into multiple homogenized blocks with similar user density characteristics by using a density clustering algorithm; A signal matrix generation module, configured to extract the signal usage conditions of the user devices in the homogenized block according to the user signal strength to generate a signal usage matrix; An attenuation coefficient calculation module, configured to calculate the signal attenuation coefficient of the homogenized block according to the position coordinates and the environmental information; A signal increment calculation module, configured to fuse the signal usage matrix and the signal attenuation coefficient to obtain the block signal strength, and compare with the user communication requirement and calculate the signal strength increment; An instruction generation module, configured to generate a signal strength adjustment instruction for the homogenized block by using a time series prediction model according to the signal strength increment.

9. An electronic device, characterized in that, Comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, when the processor executes the computer program, it implements the method for intelligent control of mobile phone signals based on application scenarios according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for intelligent control of mobile phone signals based on application scenarios according to any one of claims 1 to 7.

Images