Signal coverage optimization method and device, equipment and medium

Abstract

The invention relates to a signal coverage optimization method and device, computer equipment and a storage medium. The method comprises the following steps: carrying out human traffic monitoring on a target area through a plurality of different monitoring devices to obtain monitoring data corresponding to each monitoring device, carrying out data fusion processing on the monitoring data to generate corresponding human traffic fusion data, and then, based on the human traffic fusion data, carrying out data fusion processing on the human traffic fusion data; and predicting the pedestrian flow of the target area in a future preset time period, generating a corresponding prediction result, further determining a target signal coverage strategy of the target area according to the prediction result, and optimizing the signal coverage of the target area based on the target signal coverage strategy. By adopting the method, the signal coverage optimization accuracy in the target area can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a signal coverage optimization method, apparatus, computer equipment and storage medium. Background Art

[0002] With the development of society, people's demand for network usage is becoming more and more obvious, and the requirements for network quality are getting higher and higher. In complex environments such as large shopping malls, office buildings and public places, the network coverage status of signal coverage devices (such as distributed antenna systems, DAS) faces many challenges.

[0003] In traditional distributed antenna systems, the intelligence level is relatively low and they cannot dynamically adapt to changes in user density and signal requirements, which leads to problems such as uneven signal coverage and waste of resources.

[0004] How to improve the accuracy of signal coverage optimization and enhance user experience is an urgent problem to be solved at this stage. Summary of the invention

[0005] Based on this, it is necessary to provide a signal coverage optimization method, device, computer equipment and storage medium that can improve the accuracy of signal coverage optimization in the target area in response to the above technical problems.

[0006] A signal coverage optimization method, comprising:

[0007] Monitor the flow of people in the target area through a variety of different monitoring devices, and obtain the monitoring data corresponding to each monitoring device;

[0008] Perform data fusion processing on the monitoring data to generate corresponding human flow fusion data;

[0009] Based on the fusion data of human flow, the human flow in the target area in the future preset time period is predicted and the corresponding prediction results are generated;

[0010] According to the prediction results, the target signal coverage strategy of the target area is determined, and the signal coverage of the target area is optimized based on the target signal coverage strategy.

[0011] Optionally, according to the prediction result, a target signal coverage strategy of the target area is determined, and based on the target signal coverage strategy, the signal coverage of the target area is optimized, including:

[0012] According to the prediction results, determine the flow direction of people in the target area in the preset time period in the future;

[0013] Based on the direction of human flow, determine the target signal coverage strategy of the corresponding signal coverage device, the target signal coverage strategy includes the target transmission power and the target transmission direction;

[0014] Adjust the transmission power and transmission direction of the signal coverage equipment to the target transmission power and target transmission direction to optimize the signal coverage of the target area.

[0015] Optionally, based on the flow direction of people, a target signal coverage strategy of a corresponding signal coverage device is determined, including:

[0016] Obtain the current transmission power and current transmission direction of the signal coverage device in the target area;

[0017] Determine the transmission power increment and transmission direction increment according to the direction of human flow;

[0018] Based on the current transmit power and the transmit power increment, a target transmit power is obtained;

[0019] Based on the current launch direction and the launch direction increment, the target launch direction is obtained.

[0020] Optionally, before performing data fusion processing on the monitoring data, the method further includes:

[0021] Perform data cleaning on each monitoring data separately;

[0022] Each monitoring data after cleaning is normalized respectively.

[0023] Optionally, data fusion processing is performed on the monitoring data to generate corresponding people flow fusion data, including:

[0024] Get the device weight corresponding to each monitoring device;

[0025] Based on the weight of each device and the corresponding monitoring data, the fusion data of the flow of people in the target area is generated.

[0026] Optionally, based on the fusion data of the flow of people, the flow of people in the target area in a preset time period in the future is predicted, including:

[0027] Split the fusion data of human flow into time and generate time series data;

[0028] Extract features from each time series data to generate feature data corresponding to the time series data;

[0029] Input feature data into the pre-trained prediction model to predict passenger flow.

[0030] Optionally, before predicting the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, the method further includes:

[0031] Determine the number of cluster centers and initial cluster centers corresponding to the fusion data of human flow;

[0032] Assign the fusion data of each person flow to the nearest initial cluster center to obtain a cluster group;

[0033] Update the initial cluster center based on the fusion data of the flow of people in each cluster group;

[0034] Based on the updated cluster centers, clustering is continued until the cluster centers converge to obtain the user density distribution in the target area;

[0035] Based on the fusion data of human flow, the human flow of the target area in a preset future period is predicted to generate corresponding prediction results, including: based on the user density distribution and the fusion data of human flow, the human flow of the target area in a preset future period is predicted to obtain the user density distribution corresponding to the human flow of the target area in the preset future period.

[0036] A signal coverage optimization device, comprising:

[0037] A monitoring module is used to monitor the flow of people in a target area through a variety of different monitoring devices and obtain monitoring data corresponding to each monitoring device;

[0038] The fusion module is used to perform data fusion processing on the monitoring data to generate corresponding human flow fusion data;

[0039] A prediction module is used to predict the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, and generate corresponding prediction results;

[0040] The optimization module is used to determine the target signal coverage strategy of the target area according to the prediction result, and optimize the signal coverage of the target area based on the target signal coverage strategy.

[0041] A computer device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of any of the methods described above when executing the computer program.

[0042] A computer-readable storage medium stores a computer program, which implements the steps of any of the above methods when executed by a processor.

[0043] The above-mentioned signal coverage optimization method, device, equipment and medium monitor the flow of people in the target area through a variety of different monitoring devices, obtain the monitoring data corresponding to each monitoring device, and perform data fusion processing on the monitoring data to generate corresponding fusion data of human flow, and then predict the flow of people in the target area in the future preset time period based on the fusion data of human flow, generate corresponding prediction results, and further determine the target signal coverage strategy of the target area based on the prediction results, and optimize the signal coverage of the target area based on the target signal coverage strategy. Therefore, in the process of signal coverage optimization, the data collected by different monitoring devices are combined, and the predicted data fusion is performed, and then when making predictions, the monitoring data of different dimensions are combined for prediction, and signal coverage optimization is performed, which can improve the accuracy of signal coverage optimization in the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is an application scenario diagram of a signal coverage optimization method in an embodiment;

[0045] Figure 2 A schematic diagram of a flow chart of a signal coverage optimization method in an embodiment;

[0046] Figure 3 It is a structural block diagram of a signal coverage optimization device in one embodiment;

[0047] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The signal coverage optimization method provided in this application can be applied to Figure 1In the application environment shown. Among them, the monitoring device 102 communicates with the server 104 through the network. The server 104 monitors the flow of people in the target area through a variety of different monitoring devices 102, obtains the monitoring data corresponding to each monitoring device, and performs data fusion processing on the monitoring data to generate corresponding fusion data of the flow of people, and then predicts the flow of people in the target area in the future preset time period based on the fusion data of the flow of people, generates corresponding prediction results, and further determines the target signal coverage strategy of the target area based on the prediction results, and optimizes the signal coverage of the target area based on the target signal coverage strategy. Among them, the monitoring device 102 can be but is not limited to various infrared sensors, temperature and humidity sensors, air pressure sensors, cameras, etc., and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0050] In one embodiment, Figure 2 As shown, a signal coverage optimization method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0051] Step S202: Monitor the flow of people in the target area through a variety of different monitoring devices to obtain monitoring data corresponding to each monitoring device.

[0052] Among them, the monitoring equipment can be used to monitor and collect human flow, for example, it can be the various sensors, cameras, etc. mentioned above.

[0053] In this embodiment, various monitoring devices can be installed in advance at various locations in the target area, and sensors and cameras can be arranged in various areas of the railway station. Various sensors and multiple cameras are arranged in some key areas (such as waiting halls, boarding gates, etc.). For example, each monitoring device is connected to the server through a network (such as Bluetooth, wireless network) to monitor data in real time and transmit it to the server.

[0054] In this embodiment, different monitoring devices may collect different data, such as human flow, human flow density, temperature, etc. Specifically, the infrared sensor provides human flow and body temperature information, and the camera provides image data of crowd density and flow direction.

[0055] In this embodiment, each monitoring data is marked in the form of a timestamp to facilitate subsequent data analysis and processing.

[0056] In a specific embodiment, the camera can perform video stream analysis through computer vision technology (such as YOLO, OpenCV, etc.) to identify and track crowd density and flow direction. Specifically, the camera transmits the captured image data to the image processing module, processes the image using a deep learning algorithm, and generates a heat map showing the density of people in different areas.

[0057] Step S204, performing data fusion processing on the monitoring data to generate corresponding pedestrian flow fusion data.

[0058] In this embodiment, after acquiring the monitoring data of each monitoring device, the server can fuse the data collected by different monitoring devices at the same time node according to the timestamp to obtain the fused human flow data.

[0059] Step S206: Based on the fusion data of the flow of people, predict the flow of people in the target area in a preset time period in the future, and generate corresponding prediction results.

[0060] In this embodiment, the server can predict the flow of people in a preset time period in the future based on the acquired flow fusion data, such as predicting the flow of people in the target area in the next 10 minutes or 20 minutes through a neural network model to obtain the corresponding prediction results, and then optimize the signal coverage to improve the experience of network users.

[0061] Step S208: determining a target signal coverage strategy for the target area according to the prediction result, and optimizing the signal coverage of the target area based on the target signal coverage strategy.

[0062] In this embodiment, after the server predicts the crowd flow prediction results of the target area in a preset time period in the future based on the crowd flow fusion data, it can determine the target signal coverage strategy for the corresponding target area, such as the power and direction of the signal coverage equipment, and then optimize the signal coverage of the target area.

[0063] In the above signal coverage optimization method, the flow of people in the target area is monitored by a variety of different monitoring devices, and the monitoring data corresponding to each monitoring device is obtained. The monitoring data is fused to generate corresponding fusion data of the flow of people, and then based on the fusion data of the flow of people, the flow of people in the target area in the future preset time period is predicted to generate corresponding prediction results. Further, based on the prediction results, the target signal coverage strategy of the target area is determined, and the signal coverage of the target area is optimized based on the target signal coverage strategy. Therefore, in the process of signal coverage optimization, the data collected by different monitoring devices are combined, and the predicted data is fused. Then, when making predictions, the monitoring data of different dimensions are combined for prediction, and signal coverage optimization is performed, which can improve the accuracy of signal coverage optimization in the target area.

[0064] In one of the embodiments, before performing data fusion processing on the monitoring data, the above method may further include: performing data cleaning on each monitoring data; and performing normalization processing on each cleaned monitoring data.

[0065] In this embodiment, after acquiring the monitoring data collected by each monitoring device, the server may first perform a preprocessing operation on the monitoring data to remove impurity data in the data, thereby improving the accuracy of subsequent data processing.

[0066] Specifically, the server may first perform data cleaning on each monitoring data to remove noise and outliers.

[0067] In a specific embodiment, the server may perform data cleaning including removing missing values ​​and outliers to ensure the accuracy and consistency of the data. For example, the server may detect whether the data corresponding to each time node is complete, thereby determining whether the data is missing, and supplement the missing values ​​by interpolation. In addition, the server may detect and process outliers based on a pre-set statistical method, such as using a box plot to identify outliers, and process them by interpolation or mean replacement.

[0068] Furthermore, the server can normalize the cleaned monitoring data separately, and convert the monitoring data of different sensors into a unified format for subsequent fusion. For example, the infrared sensor data and the camera data are normalized so that they can be compared under the same dimension.

[0069] In a specific embodiment, the server may perform normalization processing through minimum-maximum normalization and Z-score standardization.

[0070] Among them, the minimum-maximum normalization process can be expressed by the following formula:

[0071]

[0072] Among them, X represents the original data, X min and X max They represent the minimum and maximum values ​​of the data respectively, and X` represents the normalized data.

[0073] Z-score standardization can be expressed by the following formula:

[0074]

[0075] Among them, X represents the original data, μ and σ represent the mean and standard deviation of the data respectively, and X` represents the standardized data.

[0076] In one of the embodiments, performing data fusion processing on the monitoring data to generate corresponding human flow fusion data may include: obtaining device weights corresponding to each monitoring device; and generating human flow fusion data of the target area based on the weights of each device and the corresponding monitoring data.

[0077] In this embodiment, the server may use algorithms such as weighted averaging or Kalman filtering to perform data fusion on the pre-processed data.

[0078] In a specific embodiment, the fusion process can be expressed as:

[0079]

[0080] Among them, x i represents the data of the i-th sensor (monitoring device), w i is the corresponding device weight, and n is the number of sensors (monitoring devices). The device weight can be adjusted according to the reliability and importance of the sensor (monitoring device) to reflect the contribution of different sensors in the overall monitoring.

[0081] In one of the embodiments, based on the fusion data of human flow, predicting the human flow in the target area in a preset time period in the future can include: dividing the fusion data of human flow by time to generate time series data; extracting features from each time series data to generate feature data corresponding to the time series data; inputting the feature data into a pre-trained prediction model to predict human flow.

[0082] In this embodiment, after the server performs data fusion processing and obtains the corresponding people flow fusion data, the data can be segmented according to time series to generate corresponding time series data. For example, the data can be segmented according to time periods (such as hours, days, weeks).

[0083] Furthermore, the server extracts feature data from the segmented time series data to generate corresponding feature data.

[0084] In this embodiment, the server extracts feature data from the time series data, which may specifically include mean, variance and peak processing, etc., to generate corresponding feature data.

[0085] Furthermore, the server can input the obtained feature data into a pre-trained prediction model to perform pedestrian flow prediction.

[0086] In a specific embodiment, the server may obtain monitoring data of the target area in a historical time period and use the data for model training to obtain a trained prediction model.

[0087] Specifically, the server may determine a suitable time series analysis model as an initial prediction model, such as an ARIMA (Auto Regressive Integrated Moving Average) model or an LSTM (Long Short-Term Memory) neural network.

[0088] Furthermore, the server may perform preprocessing, data fusion, segmentation and feature extraction on the acquired historical monitoring data, and then divide the acquired historical feature data into training set data, validation set data and test set data.

[0089] In a specific embodiment, the historical feature data may be divided into 70% training set data, 15% validation set data, and 15% test set data. It will be appreciated by those skilled in the art that this is only an example, and in other embodiments, other ratios may be used, and this application does not limit this.

[0090] Furthermore, the server can apply the training set data to perform model training, and verify it through the validation set data, and apply the test set data to perform data testing.

[0091] In this embodiment, the server may evaluate the accuracy and robustness of the model through a cross-validation method.

[0092] In one of the embodiments, before predicting the flow of people in the target area in a preset time period in the future based on the fusion data of human flow, the above method may also include: determining the number of cluster centers and the initial cluster center corresponding to the fusion data of human flow; assigning each fusion data of human flow to the initial cluster center closest to obtain a cluster group; updating the initial cluster center according to the fusion data of human flow of each cluster group; based on the updated cluster center, continuing clustering until the cluster centers converge, obtaining the user density distribution of the target area.

[0093] In this embodiment, the server may perform user density distribution clustering by using a clustering algorithm, such as a K-means clustering algorithm.

[0094] Specifically, the server may determine the verified K value, ie, the cluster center data, according to the actual situation of the target area. For example, K=3 represents a high-density area, a medium-density area, and a low-density area.

[0095] Furthermore, the server randomly selects K data points as initial cluster centers.

[0096] Furthermore, the server can distribute the fusion data of each person flow to the nearest initial cluster center to obtain a cluster group.

[0097] In a specific embodiment, the server assigns each person flow fusion data to the nearest initial cluster center, which can be determined by using the following formula:

[0098]

[0099] Where d is the distance, x is i For human traffic fusion data, c j is the cluster center.

[0100] Furthermore, the server updates the initial cluster centers according to the fusion data of the flow of people in each cluster group, which may include: determining the data mean corresponding to each cluster group according to the fusion data of the flow of people in each cluster group; and updating each initial cluster center to the cluster center determined by the data mean.

[0101] In a specific embodiment, the server may determine the data mean corresponding to each cluster group by the following formula:

[0102]

[0103] Among them, N j is cluster group c j The number of people flow fusion data in .

[0104] In this embodiment, the server can continue clustering based on the updated cluster center until the cluster center converges to obtain the user density distribution of the target area, that is, determine the high-density area, medium-density area and low-density area of ​​the target area to obtain the user density distribution in the target area.

[0105] In this embodiment, based on the crowd flow fusion data, the crowd flow of the target area in a future preset period is predicted to generate corresponding prediction results, which may include: based on the user density distribution and the crowd flow fusion data, the crowd flow of the target area in a future preset time period is predicted to obtain the user density distribution corresponding to the crowd flow of the target area in the future preset time period.

[0106] Specifically, the server may predict the user density distribution in a future preset time period based on the user density distribution and the crowd flow fusion data to obtain the corresponding user density distribution.

[0107] In one of the embodiments, a target signal coverage strategy for a target area is determined based on prediction results, and the signal coverage of the target area is optimized based on the target signal coverage strategy, which may include: determining the direction of pedestrian flow in the target area in a preset time period in the future based on the prediction results; determining the target signal coverage strategy for the corresponding signal coverage device based on the direction of pedestrian flow, the target signal coverage strategy including target transmission power and target transmission direction; adjusting the transmission power and transmission direction of the signal coverage device to the target transmission power and target transmission direction to optimize the signal coverage of the target area.

[0108] In a specific embodiment, the server may automatically adjust the transmission power and the transmission power of the signal coverage device (such as an antenna) according to the prediction result.

[0109] Specifically, the server determines the direction of human flow in the target area in a preset time period in the future based on the prediction results, and analyzes the user density of the target area, namely, high-density area, medium-density area and low-density area.

[0110] Furthermore, the server may determine the target signal coverage strategy, ie, the target transmission power and the target transmission direction, of the corresponding signal coverage device according to different user density conditions.

[0111] In a specific embodiment, after identifying a high-density area, the server increases the transmission power of the signal coverage device in the area to ensure that the signal strength meets the user's needs.

[0112] In one specific embodiment, upon identifying a low-density area, the server reduces transmit power to save energy.

[0113] In a specific embodiment, the server may dynamically adjust the transmission direction of the signal coverage device according to the flow direction of people.

[0114] In one of the embodiments, determining the target signal coverage strategy of the corresponding signal coverage device based on the direction of human flow may include: obtaining the current transmission power and the current transmission direction of the signal coverage device in the target area; determining the transmission power increment and the transmission direction increment according to the direction of human flow; obtaining the target transmission power based on the current transmission power and the transmission power increment; and obtaining the target transmission direction based on the current transmission direction and the transmission direction increment.

[0115] In this embodiment, the target transmit power may be determined by the following formula:

[0116] P new =P current +ΔP

[0117] Among them, P new is the target transmission power, P current is the current transmission power, and ΔP is the transmission power increment. In this embodiment, the target transmission direction can be determined by the following formula:

[0118] θ new =θ current +Δθ

[0119] Among them, θ new is the target launch direction, θ current is the current launch direction, and △θ is the launch direction increment.

[0120] In this embodiment, after the server determines the target transmission direction and target transmission power, it obtains the target signal coverage strategy, and then can adjust the transmission power and transmission direction of the signal coverage device to the target transmission power and target transmission direction to optimize the signal coverage of the target area.

[0121] In a specific embodiment, the server may also dynamically optimize the signal coverage strategy, that is, the server continuously monitors and adjusts the signal coverage to ensure the signal service quality during peak periods, trough periods, and emergency situations.

[0122] Specifically, during peak hours (such as morning and evening peaks), the server will automatically increase the signal coverage and transmission power based on real-time data. For example, the server may increase the transmission power from 100mW to 200mW to ensure that the signal strength meets user needs; at the same time, the server will dynamically adjust the coverage of the signal coverage device according to the direction and density of passenger flow to ensure that the signal can cover all areas where passengers gather. During low periods (such as late at night), the server will automatically reduce the transmission power and signal coverage to save resources, such as reducing the transmission power from 100mW to 50mW to reduce unnecessary signal coverage; at the same time, the server will reduce the coverage of the signal coverage device based on sensor data to ensure that the signal is concentrated in areas where there are still passengers.

[0123] In a specific embodiment, in the event of an emergency (such as a flight delay or emergency), the server will quickly adjust the signal coverage strategy. For example, after the server identifies an emergency through real-time monitoring data, it will immediately increase the signal coverage of the relevant area. For example, if the passenger flow in a certain area suddenly increases, the system will quickly adjust the transmission power and direction of the signal coverage device in the area to ensure signal stability.

[0124] Furthermore, in emergencies, the server will prioritize signal coverage in the affected areas and may temporarily reduce signal strength in other areas.

[0125] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0126] In one embodiment, Figure 3 As shown, a signal coverage optimization device is provided, comprising: a monitoring module 100, a fusion module 200, a prediction module 300 and an optimization module 400, wherein:

[0127] The monitoring module 100 is used to monitor the flow of people in a target area through a variety of different monitoring devices, and obtain monitoring data corresponding to each monitoring device.

[0128] The fusion module 200 is used to perform data fusion processing on the monitoring data to generate corresponding pedestrian flow fusion data.

[0129] The prediction module 300 is used to predict the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, and generate corresponding prediction results.

[0130] The optimization module 400 is used to determine a target signal coverage strategy for the target area according to the prediction result, and optimize the signal coverage of the target area based on the target signal coverage strategy.

[0131] In one embodiment, the optimization module 400 may include:

[0132] The submodule for determining the direction of human flow is used to determine the direction of human flow in the target area in a preset time period in the future according to the prediction results.

[0133] The target signal coverage strategy determination submodule is used to determine the target signal coverage strategy of the corresponding signal coverage device based on the direction of human flow. The target signal coverage strategy includes target transmission power and target transmission direction.

[0134] The adjustment submodule is used to adjust the transmission power and transmission direction of the signal coverage device to the target transmission power and target transmission direction to optimize the signal coverage of the target area.

[0135] In one embodiment, the target signal coverage strategy determination submodule may include:

[0136] The acquisition unit is used to acquire the current transmission power and current transmission direction of the signal coverage device in the target area.

[0137] The increment determination unit is used to determine the transmission power increment and the transmission direction increment according to the direction of human flow.

[0138] The target transmit power determination unit is used to obtain the target transmit power based on the current transmit power and the transmit power increment.

[0139] The target emission direction determination unit is used to obtain the target emission direction based on the current emission direction and the emission direction increment.

[0140] In one embodiment, before the fusion module 200 performs data fusion processing on the monitoring data, the signal coverage optimization device may further include:

[0141] The data cleaning module is used to clean each monitoring data separately.

[0142] The normalization processing module is used to perform normalization processing on each monitoring data after cleaning.

[0143] In one embodiment, the fusion module 200 may include:

[0144] The weight acquisition submodule is used to obtain the device weight corresponding to each monitoring device.

[0145] The fusion submodule is used to generate the fusion data of the flow of people in the target area based on the weight of each device and the corresponding monitoring data.

[0146] In one embodiment, the prediction module 300 may include:

[0147] The segmentation submodule is used to segment the fused traffic data according to time to generate time series data.

[0148] The feature extraction submodule is used to extract features from each time series data and generate feature data corresponding to the time series data.

[0149] The prediction submodule is used to input feature data into the pre-trained prediction model to predict the flow of people.

[0150] In one embodiment, before the prediction module 300 predicts the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, the signal coverage optimization device may further include:

[0151] The cluster center determination module is used to determine the number of cluster centers and the initial cluster center corresponding to the pedestrian flow fusion data.

[0152] The cluster group determination module is used to assign the fusion data of each flow of people to the nearest initial cluster center to obtain a cluster group.

[0153] The updating submodule is used to update the initial cluster center according to the flow fusion data of each cluster group.

[0154] The clustering iteration module is used to continue clustering based on the updated cluster centers until the cluster centers converge to obtain the user density distribution of the target area.

[0155] In this embodiment, the prediction module 300 is used to predict the flow of people in the target area in a future preset time period based on the user density distribution and the fusion data of the flow of people, and obtain the user density distribution corresponding to the flow of people in the target area in the future preset time period.

[0156] For the specific definition of the signal coverage optimization device, please refer to the definition of the signal coverage optimization method above, which will not be repeated here. Each module in the above-mentioned signal coverage optimization device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0157] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data, human flow fusion data, prediction results and signal coverage strategies. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a signal coverage optimization method is implemented.

[0158] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a signal coverage optimization method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0159] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0160] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: monitoring the flow of people in a target area by using a plurality of different monitoring devices to obtain monitoring data corresponding to each monitoring device; performing data fusion processing on the monitoring data to generate corresponding fusion data of the flow of people; predicting the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, and generating corresponding prediction results; determining a target signal coverage strategy for the target area according to the prediction results, and optimizing the signal coverage of the target area based on the target signal coverage strategy.

[0161] In one of the embodiments, when the processor executes the computer program, it determines the target signal coverage strategy of the target area according to the prediction results, and optimizes the signal coverage of the target area based on the target signal coverage strategy, which may include: determining the direction of human flow in the target area in a preset time period in the future according to the prediction results; determining the target signal coverage strategy of the corresponding signal coverage device based on the human flow direction, the target signal coverage strategy including the target transmission power and the target transmission direction; adjusting the transmission power and the transmission direction of the signal coverage device to the target transmission power and the target transmission direction to optimize the signal coverage of the target area.

[0162] In one of the embodiments, when the processor executes a computer program, it is implemented to adjust to the direction of human flow and determine the target signal coverage strategy of the corresponding signal coverage device, which may include: obtaining the current transmission power and the current transmission direction of the signal coverage device in the target area; determining the transmission power increment and the transmission direction increment according to the direction of human flow; obtaining the target transmission power based on the current transmission power and the transmission power increment; obtaining the target transmission direction based on the current transmission direction and the transmission direction increment.

[0163] In one of the embodiments, before the processor executes the computer program to perform data fusion processing on the monitoring data, the following steps may also be implemented: performing data cleaning on each monitoring data; and performing normalization processing on each cleaned monitoring data.

[0164] In one of the embodiments, when the processor executes the computer program, it implements data fusion processing on the monitoring data to generate corresponding pedestrian flow fusion data, which may include: obtaining the device weight corresponding to each monitoring device; based on the weight of each device and the corresponding monitoring data, generating pedestrian flow fusion data of the target area.

[0165] In one of the embodiments, when the processor executes the computer program, it realizes prediction of the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, which can include: dividing the fusion data of the flow of people by time to generate time series data; extracting features of each time series data to generate feature data corresponding to the time series data; inputting the feature data into a pre-trained prediction model to predict the flow of people.

[0166] In one of the embodiments, when the processor executes the computer program, before predicting the flow of people in the target area in a preset time period in the future based on the fusion data of human flow, the following steps can also be implemented: determining the number of cluster centers and the initial cluster center corresponding to the fusion data of human flow; assigning each fusion data of human flow to the initial cluster center closest to obtain a cluster group; updating the initial cluster center according to the fusion data of human flow of each cluster group; and continuing clustering based on the updated cluster center until the cluster centers converge to obtain the user density distribution of the target area.

[0167] In this embodiment, when the processor executes the computer program, it predicts the flow of people in a future preset period of the target area based on the fusion data of the flow of people, and generates corresponding prediction results, which may include: predicting the flow of people in a future preset time period of the target area based on the user density distribution and the fusion data of the flow of people, and obtaining the user density distribution corresponding to the flow of people in the future preset time period of the target area.

[0168] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: monitoring the flow of people in a target area by using a variety of different monitoring devices to obtain monitoring data corresponding to each monitoring device; performing data fusion processing on the monitoring data to generate corresponding fusion data of the flow of people; based on the fusion data of the flow of people, predicting the flow of people in the target area in a preset time period in the future, and generating corresponding prediction results; determining a target signal coverage strategy for the target area according to the prediction results, and optimizing the signal coverage of the target area based on the target signal coverage strategy.

[0169] In one of the embodiments, when the computer program is executed by the processor, it is implemented to determine the target signal coverage strategy of the target area according to the prediction results, and optimize the signal coverage of the target area based on the target signal coverage strategy, which may include: determining the direction of human flow in the target area in a preset time period in the future according to the prediction results; determining the target signal coverage strategy of the corresponding signal coverage device based on the human flow direction, the target signal coverage strategy including the target transmission power and the target transmission direction; adjusting the transmission power and the transmission direction of the signal coverage device to the target transmission power and the target transmission direction to optimize the signal coverage of the target area.

[0170] In one of the embodiments, when the computer program is executed by the processor, it implements a target signal coverage strategy for determining the corresponding signal coverage device based on the direction of human flow, which may include: obtaining the current transmission power and the current transmission direction of the signal coverage device in the target area; determining the transmission power increment and the transmission direction increment according to the direction of human flow; obtaining the target transmission power based on the current transmission power and the transmission power increment; and obtaining the target transmission direction based on the current transmission direction and the transmission direction increment.

[0171] In one of the embodiments, before the computer program is executed by the processor to perform data fusion processing on the monitoring data, the following steps may also be implemented: data cleaning is performed on each monitoring data; and each cleaned monitoring data is normalized.

[0172] In one of the embodiments, when the computer program is executed by the processor, data fusion processing is performed on the monitoring data to generate corresponding pedestrian flow fusion data, which may include: obtaining the device weight corresponding to each monitoring device; based on the weight of each device and the corresponding monitoring data, generating pedestrian flow fusion data of the target area.

[0173] In one of the embodiments, when the computer program is executed by the processor, it is implemented to predict the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, which may include: dividing the fusion data of the flow of people by time to generate time series data; extracting features from each time series data to generate feature data corresponding to the time series data; inputting the feature data into a pre-trained prediction model to predict the flow of people.

[0174] In one of the embodiments, when the computer program is executed by the processor, before predicting the flow of people in the target area in a preset time period in the future based on the fusion data of human flow, the following steps can also be implemented: determining the number of cluster centers and the initial cluster center corresponding to the fusion data of human flow; assigning each fusion data of human flow to the initial cluster center closest to obtain a cluster group; updating the initial cluster center according to the fusion data of human flow of each cluster group; and continuing clustering based on the updated cluster center until the cluster centers converge to obtain the user density distribution of the target area.

[0175] In this embodiment, when the computer program is executed by the processor, it predicts the flow of people in a future preset period of the target area based on the fusion data of the flow of people, and generates corresponding prediction results, which may include: predicting the flow of people in a future preset time period of the target area based on the user density distribution and the fusion data of the flow of people, and obtaining the user density distribution corresponding to the flow of people in the future preset time period of the target area.

[0176] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0177] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0178] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A signal coverage optimization method, characterized in that: include: Monitor the flow of people in the target area by using a variety of different monitoring devices to obtain monitoring data corresponding to each monitoring device; Performing data fusion processing on the monitoring data to generate corresponding human flow fusion data; Based on the fusion data of the flow of people, predict the flow of people in the target area in a preset time period in the future, and generate corresponding prediction results; According to the prediction result, a target signal coverage strategy for the target area is determined, and based on the target signal coverage strategy, the signal coverage of the target area is optimized.

2. The method according to claim 1, characterized in that Determining a target signal coverage strategy for the target area according to the prediction result, and optimizing the signal coverage of the target area based on the target signal coverage strategy, includes: Determine the direction of human flow in the target area in a preset time period in the future according to the prediction result; Based on the direction of human flow, determine a target signal coverage strategy for a corresponding signal coverage device, wherein the target signal coverage strategy includes a target transmission power and a target transmission direction; The transmission power and transmission direction of the signal coverage device are adjusted to the target transmission power and target transmission direction to optimize the signal coverage of the target area.

3. The method according to claim 2, characterized in that The determining of a target signal coverage strategy of a corresponding signal coverage device based on the flow direction of people includes: Obtain the current transmission power and current transmission direction of the signal coverage device in the target area; Determine the transmission power increment and the transmission direction increment according to the flow direction of the people; Obtaining a target transmit power based on the current transmit power and the transmit power increment; Based on the current emission direction and the emission direction increment, a target emission direction is obtained.

4. The method according to claim 1, characterized in that: Before performing data fusion processing on the monitoring data, the method further includes: Performing data cleaning on each of the monitoring data respectively; The cleaned monitoring data are respectively normalized.

5. The method according to claim 1, characterized in that The performing data fusion processing on the monitoring data to generate corresponding people flow fusion data includes: Obtaining a device weight corresponding to each of the monitoring devices; Based on the weight of each device and the corresponding monitoring data, the pedestrian flow fusion data of the target area is generated.

6. The method according to claim 1, characterized in that The predicting of the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people includes: Divide the fused human flow data by time to generate time series data; Extracting features from each of the time series data to generate feature data corresponding to the time series data; The feature data is input into a pre-trained prediction model to perform pedestrian flow prediction.

7. The method according to claim 1, characterized in that Before predicting the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, the method further includes: Determine the number of cluster centers and the initial cluster center corresponding to the human flow fusion data; Allocating each of the crowd flow fusion data to the nearest initial cluster center to obtain a cluster group; Update the initial cluster center based on the fusion data of the flow of people in each cluster group; Based on the updated cluster centers, clustering is continued until the cluster centers converge to obtain the user density distribution of the target area; The method predicts the flow of people in a future preset period of the target area based on the crowd flow fusion data and generates a corresponding prediction result, including: predicting the flow of people in a future preset time period of the target area based on the user density distribution and the crowd flow fusion data, and obtaining the user density distribution corresponding to the flow of people in the future preset time period of the target area.

8. A signal coverage optimization device, characterized in that: The device comprises: A monitoring module, used to monitor the flow of people in the target area through a variety of different monitoring devices, and obtain monitoring data corresponding to each monitoring device; A fusion module is used to perform data fusion processing on the monitoring data to generate corresponding human flow fusion data; A prediction module, used to predict the flow of people in the target area in a preset time period in the future based on the fusion data of the flow of people, and generate a corresponding prediction result; An optimization module is used to determine a target signal coverage strategy for the target area according to the prediction result, and optimize the signal coverage of the target area based on the target signal coverage strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images