Intelligent management method and system for distribution of city-level outdoor advertising boards

Abstract

The invention discloses a city-level outdoor advertising board distribution intelligent management method and system, and belongs to the technical field of advertising management. The method comprises the following steps: collecting various data related to outdoor advertisements, and preprocessing the data; performing data mining on the collected data, and extracting feature data related to an outdoor advertisement distribution decision; constructing an intelligent outdoor advertising board distribution decision model based on a neural network; training the model by using the feature data; and predicting the new feature data based on the trained intelligent outdoor advertising board distribution decision model to obtain the distribution condition of the outdoor advertising boards, and performing intelligent management on the outdoor advertising board distribution according to the distribution condition. According to the method, various factor data are comprehensively considered, the intelligent outdoor advertising board distribution decision model is constructed based on the neural network, intelligent management of outdoor advertisements is facilitated, construction of the outdoor advertisements is safer, the subsequent maintenance cost is reduced, and urban managers can plan the outdoor advertising boards more reasonably.

Description

Technical Field

[0001] The present invention relates to the technical field of advertising management, and more specifically to a city-level outdoor billboard distribution intelligent management method and system. Background Art

[0002] With the development of the economy, the use of advertisements has become more and more widespread. Various forms of advertisements have emerged one after another, playing an important role in society. Among them, outdoor advertising is one of the most common forms of advertising. It is not only large in number, but also widely distributed. Billboards are an important technical means for promoting information. In order to achieve better publicity effects and meet planning requirements, they are generally set up in places with high traffic and good sight lines in the city. Due to the large number of urban areas, outdoor advertisements are small and scattered in urban spaces, making it difficult to plan outdoor advertisements, and the effect of advertising distribution planning is not good. At the same time, outdoor advertising construction itself also requires a lot of safety management. Regional managers cannot know the outdoor advertising information and its safety conditions in the entire city or region, which leads to unreasonable urban outdoor advertising planning.

[0003] Therefore, how to plan outdoor billboards more reasonably and better manage outdoor advertisements intelligently is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of this, the present invention provides a city-level outdoor billboard distribution intelligent management method and system that solves at least some of the above-mentioned technical problems, which is conducive to more reasonable planning of outdoor billboards and better intelligent management of outdoor advertisements.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] In a first aspect, an embodiment of the present invention provides a city-level outdoor billboard distribution intelligent management method, the method comprising the following steps:

[0007] S1. Collect various data related to outdoor advertising and pre-process the data;

[0008] S2. Perform data mining on the collected data to extract feature data related to outdoor advertising distribution decisions;

[0009] S3, build a smart outdoor billboard distribution decision model based on neural network;

[0010] S4, using the feature data to train the smart outdoor billboard distribution decision model;

[0011] S5. Predict new feature data based on the trained intelligent outdoor billboard distribution decision model to obtain the distribution of outdoor billboards, and intelligently manage the outdoor advertising distribution according to the distribution.

[0012] Preferably, in step S1, the data related to outdoor advertising includes: geographic data, meteorological data, population data, traffic data, video data and sensor data.

[0013] Preferably, in step S1, preprocessing the data includes: data cleaning, deduplication and missing value processing.

[0014] Preferably, in step S2, the characteristic data related to the distribution decision include: billboard location characteristics, billboard safety characteristics, environmental factor characteristics, weather factor characteristics and historical data characteristics.

[0015] Preferably, in step S3, the intelligent outdoor billboard distribution decision model constructed based on the convolutional neural network has a structure including: an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer.

[0016] Preferably, the fully connected layer comprises multiple hidden layers and neurons.

[0017] Preferably, the activation function of the smart outdoor billboard distribution decision model uses ReLU and sigmoid functions, the model is compiled using the compile method, the optimizer is the Adam optimizer, and the loss function is the binary cross entropy; the evaluation indicators are one or more of accuracy, precision, recall and F1 score.

[0018] In a second aspect, an embodiment of the present invention further provides a city-level outdoor billboard distribution intelligent management system, which applies the above-mentioned city-level outdoor billboard distribution intelligent management method to realize intelligent management of outdoor advertisements. The system includes:

[0019] Data collection module, used to collect various data related to outdoor advertising and pre-process the data;

[0020] A data mining module is used to perform data mining on the collected data and extract feature data related to outdoor advertising distribution decisions;

[0021] Model building module, used to build a smart outdoor billboard distribution decision model based on neural network;

[0022] A model training module, used to train the smart outdoor billboard distribution decision model using the feature data;

[0023] The model application module is used to predict new feature data based on the trained intelligent outdoor billboard distribution decision model, obtain the distribution of outdoor billboards, and intelligently manage the distribution of outdoor advertisements according to the distribution.

[0024] Compared with the prior art, the present invention has at least the following beneficial effects:

[0025] The present invention provides a city-level outdoor billboard distribution intelligent management method and system, which comprehensively considers multiple factors and data, builds an intelligent outdoor billboard distribution decision model based on a neural network, and applies the intelligent outdoor billboard distribution decision model to facilitate intelligent management of outdoor advertisements, which is beneficial to making outdoor advertising construction safer, reducing subsequent maintenance costs, and facilitating city managers to plan outdoor billboards more reasonably.

[0026] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0027] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0030] Figure 1 A schematic flow chart of a method for intelligent management of city-level outdoor billboard distribution provided in an embodiment of the present invention.

[0031] Figure 2 A schematic diagram of the working principle of the intelligent outdoor billboard distribution decision model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0033] In the description of the present invention, it should be noted that: in some processes described in the specification and drawings of this application, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be performed in the order in which they appear in this document or may be performed in parallel. In addition, various serial numbers are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0034] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1:

[0036] See also Figure 1 As shown, the present invention provides a city-level outdoor billboard distribution intelligent management method, which mainly includes the following steps:

[0037] S1. Collect various data related to outdoor advertising and pre-process the data;

[0038] S2. Perform data mining on the collected data to extract feature data related to outdoor advertising distribution decisions;

[0039] S3, build a smart outdoor billboard distribution decision model based on neural network;

[0040] S4, using the mined feature data to train the smart outdoor billboard distribution decision model;

[0041] S5. Predict new feature data based on the trained intelligent outdoor billboard distribution decision model to obtain the distribution of outdoor billboards, and intelligently manage the outdoor advertising distribution according to the distribution.

[0042] The specific implementation methods of the method of the present invention are described in detail below:

[0043] (1) Dataset preparation:

[0044] Collect a sample data set containing data on each factor, and perform preprocessing steps such as data cleaning, deduplication, and missing value processing. The specific data includes:

[0045] 1. Geographic Information System (GIS) data. GIS data can provide information about geographic location, topography, surrounding environment, etc. You can use the data provided by the GIS database or map service provider to analyze the geographic characteristics and surrounding environment of the billboard location.

[0046] 2. Meteorological data: Meteorological departments or meteorological websites provide a wealth of meteorological data, including wind speed, wind force, temperature, etc. Historical meteorological data can be collected and combined with field surveys and monitoring data to analyze the changing trends and laws of environmental factors.

[0047] 3. Population and traffic data, collect data on latitude and longitude, traffic index, population statistics, population density, traffic flow, commercial zoning, etc.

[0048] 4. Video data: Use surveillance cameras to monitor the billboards in real time and collect video image data including the billboards. At the same time, through the video surveillance system, potential safety issues can be discovered in time and corresponding measures can be taken to deal with them.

[0049] 5. Sensor data, such as; Tilt angle sensor data, a tilt sensor can be used to measure the tilt angle of the billboard; installed at key locations of the billboard structure to monitor the tilt of the billboard. Vibration sensor data, a vibration sensor can be used to monitor the vibration frequency and amplitude of the billboard to assess the stability and safety of the billboard. Wind speed sensor data, a wind speed sensor can measure the wind speed in the environment to assess the impact of wind on the billboard; it can be installed in a fixed position near the billboard to monitor changes in wind speed in the environment.

[0050] (2) Data mining:

[0051] Feature engineering is the process of extracting, converting and selecting features from raw data to facilitate the training and prediction of machine learning models. In feature engineering, this embodiment mines the intrinsic information of the data to extract features that are helpful for model prediction to improve the performance and generalization ability of the model. The extracted feature data includes:

[0052] 1. Billboard location characteristics: longitude and latitude. The geographical location of the billboard is an important feature, which is related to the surrounding environment, population density, traffic flow, etc. Altitude. Altitude is related to factors such as climate and temperature.

[0053] 2. Billboard safety features: The billboard's state tilt angle, vibration frequency, and environmental wind speed and wind force are related. The billboard's vibration frequency is affected by factors such as the surrounding environment and traffic flow. Excessive vibration frequency may cause the billboard to be unstable and pose a safety hazard. Vibration frequency safety factor features may include factors such as surrounding traffic flow and road conditions.

[0054] 3. Environmental factors: Traffic flow, the traffic flow of surrounding roads will affect the exposure and effect of billboards. Population density, surrounding residents and densely populated areas can provide more target audiences. Commercial area distribution, the distribution of surrounding commercial areas is related to the commercial value of billboards.

[0055] 4. Weather factors: Weather factors such as temperature, humidity, and wind speed can affect the stability and safety of billboards. Weather forecast data and predictions of future weather conditions can help adjust billboard operation strategies.

[0056] 5. Historical data features: Historical billboard revenue data. Past billboard revenue is related to future advertising effectiveness. Historical security incident data. Past security incidents can provide useful information about billboard security.

[0057] 6. Other characteristics: Seasonal factors: different seasons may have different advertising effects and safety risks. Surrounding attractions and activities: whether there are attractions and activities nearby can affect the exposure rate and number of audiences of billboards.

[0058] (3) A smart outdoor billboard distribution decision model is constructed based on a neural network, preferably a convolutional neural network (CNN). The number of nodes in the input layer matches the dimension of the feature, and the complexity and learning ability of the model are increased by adding hidden layers. The model is constructed using the Keras deep learning framework, and the model specifically includes:

[0059] 1. Input layer: Design an appropriate input layer to process the input data. For image data, it is usually a three-dimensional shape (width, height, number of channels), and for time series data, it is a two-dimensional or three-dimensional shape (time step, feature dimension, number of channels). The input layer accepts feature data related to the outdoor billboard, including the billboard location, surrounding environment, weather conditions, etc. These feature data are two-dimensional or three-dimensional.

[0060] 2. Convolutional layer and pooling layer: used to improve the representation ability of the model. Add a Flatten layer before the fully connected layer to flatten the feature map. The convolution layer is used to extract feature information. The input data is convoluted by a sliding convolution kernel to generate a feature map. The pooling layer is used to reduce the dimension of the feature map, reduce the amount of calculation and retain important information. It is preferred to use the maximum pooling or average pooling operation.

[0061] 3. Fully connected layer, for classification or regression tasks. The output of the pooling layer is flattened into a one-dimensional vector as the input of the fully connected layer. The fully connected layer is used to learn the relationship between features. It can contain multiple hidden layers and neurons (for example, a hidden layer with 64 neurons and a hidden layer with 128 neurons), and nonlinearity is introduced through activation functions.

[0062] 4. Output layer: The output layer is determined according to the task requirements. It can be one node for a binary classification task (such as whether a billboard is safe), or multiple nodes for a multi-classification task (such as the distribution area of ​​billboards). For binary classification tasks, the sigmoid activation function is preferably used; for multi-classification tasks, the softmax activation function is preferably used.

[0063] (4) Compile the model:

[0064] Compile the model using the loss function and optimizer. Specifically:

[0065] 1. Select the activation function. The activation function of the model preferably uses ReLU and sigmoid functions.

[0066] 2. Select an optimizer: Select an optimizer that is suitable for the model and data to adjust the weights of the model to minimize the loss function. In this embodiment, the Adam optimizer is preferably used, which can effectively adjust the learning rate and adapt to different data sets and model structures.

[0067] 3. Select the loss function: Select a suitable loss function according to the task type of the model. In this embodiment, for binary classification tasks, the binary_crossentropy loss function is preferably used; for multi-classification tasks, the categorical_crossentropy loss function is preferably used; for regression tasks, the mse loss function is preferably used.

[0068] 4. Select evaluation metrics: Select one or more metrics to evaluate the performance of the model. For classification problems, the preferred evaluation metrics include accuracy, precision, recall, and F1 score.

[0069] 5. Compile Model: Compile the model using the optimizer, loss function, and evaluation metric selected above.

[0070] In this embodiment, the formula of the model can be expressed as:

[0071] Y=β0+β1X1+β2X2+…+βn*Xn+ε

[0072] Among them, Y represents the distribution of billboards, X1 to Xn represent the selected feature variables, β0 to βn represent the regression coefficients of the model, and ε represents the error term.

[0073] (5) Model training:

[0074] First, use the train_test_split function to split the dataset into a training set and a test set. Then, use the fit method to train the model, specifying the number of training rounds and the batch size. Finally, use the predict method to predict the test set and calculate the accuracy rate as the evaluation indicator based on the prediction results.

[0075] The specific code of the method of the present invention is given below:

[0076] import tensorflow as tf

[0077] from sklearn.model_selection import train_test_split

[0078] from sklearn.metrics import accuracy_score

[0079] #Data Preparation

[0080] X=#feature variable matrix, dimension is n×m

[0081] Y=#target variable vector, dimension is n×1

[0082] #Data partitioning

[0083] X_train,X_test,y_train,y_test=train_test_split(X,Y,test_size=0.2,random_state=0)

[0084] #Build

[0085] model=tf.keras.models.Sequential([

[0086] tf.keras.layers.Dense(64,activation='relu',input_shape=(n,)),

[0087] tf.keras.layers.Dense(128,activation='relu'),

[0088] tf.keras.layers.Dense(1,activation='sigmoid') ])

[0090] # Compile the model

[0091] from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense # Create a sequential model

[0092] model=Sequential()

[0093] #Add convolutional layer and pooling layer

[0094] model.add(Conv2D(32,(3,3),activation='relu',

[0095] input_shape=(img_height,img_width,img_channels)))

[0096] model.add(MaxPooling2D(pool_size=(2,2)))

[0097] #Add more convolutional and pooling layers

[0098] model.add(Conv2D(64,(3,3),activation='relu'))

[0099] model.add(MaxPooling2D(pool_size=(2,2)))

[0100] #Flatten the feature map into a one-dimensional vector

[0101] model.add(Flatten())

[0102] #Add fully connected layer

[0103] model.add(Dense(64,activation='relu'))

[0104] #Output layer

[0105] model.add(Dense(1,activation='sigmoid'))

[0106] # Compile the model

[0107] model.compile(optimizer='adam',loss='binary_crossentropy',

[0108] metrics = ['accuracy'])

[0109] #Print model structure

[0110] model.summary()

[0111] model.compile(optimizer='adam',

[0112] loss = 'binary_crossentropy',

[0113] metrics = ['accuracy'])

[0114] #Model training

[0115] model.fit(X_train,y_train,epochs=10,batch_size=32)

[0116] #Model prediction

[0117] y_predicted=model.predict(X_test)

[0118] y_predicted=[1ifpred>=0.5else 0forpred in y_predicted]

[0119] #Model evaluation

[0120] accuracy=accuracy_score(y_test,y_predicted).

[0121] Finally, in this embodiment, the distribution of outdoor billboards is obtained according to the intelligent outdoor billboard distribution decision model. According to the obtained distribution, the outdoor advertising distribution can be intelligently managed; including: advertising security management, content management, value management and prediction suggestions, etc.; wherein:

[0122] The safety management of outdoor advertising mainly relies on data such as the billboard’s tilt angle, vibration frequency, ambient wind speed, and wind force, and uses intelligent hardware and environment to comprehensively predict its safety.

[0123] Outdoor advertising content management mainly relies on videos to determine whether there are illegal advertisements, and monitors public service advertisements, paid advertisements, etc.

[0124] The management of outdoor advertising value is mainly related to the surrounding environment, population density, traffic flow, etc. Traffic flow: The traffic flow of surrounding roads affects the exposure rate and effect of billboards. Population density: Surrounding residents and densely populated areas can provide more target audiences. The distribution of commercial areas: The distribution of surrounding commercial areas is related to the commercial value of billboards and social factors such as the education level, purchasing power, and age of the population.

[0125] Outdoor advertising forecasting suggestions, scoring each outdoor billboard and giving safety suggestions. At the same time, suggestions are given to management based on geographic location information, population data, weather data, etc., so that outdoor advertising can be increased in specific locations.

[0126] From the description of the above embodiments, those skilled in the art can know that the present invention provides a city-level outdoor billboard distribution intelligent management method, which comprehensively considers environmental factors such as tilt angle, vibration frequency safety factors, height, wind speed, wind force, and social factors such as people's education level, purchasing power, and population age, and constructs an intelligent outdoor billboard distribution decision model based on a neural network. The distribution of outdoor billboards can be obtained by applying the intelligent outdoor billboard distribution decision model, which is convenient for intelligent management of outdoor advertisements and has broad application prospects; the specific advantages are reflected in:

[0127] 1. It is convenient to plan outdoor billboards more reasonably and help improve the effect of outdoor advertising;

[0128] 2. It is conducive to making outdoor advertising construction safer and reducing subsequent maintenance costs;

[0129] 3. Allow regional managers to clearly understand the use of outdoor billboards.

[0130] 4. Provide management with forecasts of outdoor advertising safety and suggest addresses where outdoor advertising can be set up.

[0131] Embodiment 2:

[0132] The present invention also provides a city-level outdoor billboard distribution intelligent management system, which is applied to a city-level outdoor billboard distribution intelligent management method in the above embodiment to realize intelligent management of outdoor advertisements; the system includes:

[0133] Data collection module, used to collect various data related to outdoor advertising and pre-process the data;

[0134] A data mining module is used to perform data mining on the collected data and extract feature data related to outdoor advertising distribution decisions;

[0135] Model building module, used to build a smart outdoor billboard distribution decision model based on neural network;

[0136] A model training module, used to train the smart outdoor billboard distribution decision model using the feature data;

[0137] The model application module is used to predict new feature data based on the trained intelligent outdoor billboard distribution decision model, obtain the distribution of outdoor billboards, and intelligently manage the distribution of outdoor advertisements according to the distribution.

[0138] The implementation principle and technical effects of the system provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment, which will not be repeated here.

[0139] Embodiment 3:

[0140] An embodiment of the present invention also provides a storage medium on which one or more programs readable by a computing device are stored. The one or more programs include instructions. When the instructions are executed by the computing device, the computing device executes a city-level outdoor billboard distribution intelligent management method in the above embodiment.

[0141] In the embodiment of the present invention, the storage medium may be, for example, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples of storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination thereof.

[0142] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems or computer program products, etc. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0143] It should be noted that the word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several distinct components, and by means of a suitably programmed computer.

[0144] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0145] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A city-level outdoor billboard distribution intelligent management method, characterized in that: The method comprises the following steps: S1. Collect various data related to outdoor advertising and pre-process the data; S2. Perform data mining on the collected data to extract feature data related to outdoor advertising distribution decisions; S3, build a smart outdoor billboard distribution decision model based on neural network; S4, using the feature data to train the smart outdoor billboard distribution decision model; S5. Predict new feature data based on the trained intelligent outdoor billboard distribution decision model to obtain the distribution of outdoor billboards, and intelligently manage the outdoor advertising distribution according to the distribution.

2. A city-level outdoor billboard distribution intelligent management method according to claim 1, characterized in that: In step S1, the data related to outdoor advertising includes: geographic data, meteorological data, population data, traffic data, video data and sensor data.

3. A city-level outdoor billboard distribution intelligent management method according to claim 1, characterized in that: In step S1, preprocessing the data includes: data cleaning, deduplication and missing value processing.

4. A city-level outdoor billboard distribution intelligent management method according to claim 1, characterized in that: In step S2, the characteristic data related to the distribution decision include: billboard location characteristics, billboard safety characteristics, environmental factor characteristics, weather factor characteristics and historical data characteristics.

5. The method for intelligent management of city-level outdoor billboard distribution according to claim 1, characterized in that: In step S3, the intelligent outdoor billboard distribution decision model is constructed based on a convolutional neural network, and its structure includes: an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer.

6. A city-level outdoor billboard distribution intelligent management method according to claim 5, characterized in that: The fully connected layer includes multiple hidden layers and neurons.

7. A city-level outdoor billboard distribution intelligent management method according to claim 5, characterized in that: The activation function of the smart outdoor billboard distribution decision model uses ReLU and sigmoid functions, the model is compiled using the compile method, the optimizer is the Adam optimizer, and the loss function is the binary cross entropy; the evaluation indicators are one or more of the accuracy, precision, recall, and F1 score.

8. A city-level outdoor billboard distribution intelligent management system, characterized in that: The method for intelligent management of the distribution of city-level outdoor billboards as claimed in any one of claims 1 to 7 is applied to realize intelligent management of outdoor advertisements, and the system comprises: Data collection module, used to collect various data related to outdoor advertising and pre-process the data; A data mining module is used to perform data mining on the collected data and extract feature data related to outdoor advertising distribution decisions; Model building module, used to build a smart outdoor billboard distribution decision model based on neural network; A model training module, used to train the smart outdoor billboard distribution decision model using the feature data; The model application module is used to predict new feature data based on the trained intelligent outdoor billboard distribution decision model, obtain the distribution of outdoor billboards, and intelligently manage the distribution of outdoor advertisements according to the distribution.

Images