A method and system for advertising delivery based on weather warning aircraft

Abstract

This invention discloses an advertising delivery method and system based on a weather warning aircraft, belonging to the field of weather warning technology. The method includes: acquiring historical data of elevator passenger information and determining the attributes of passengers in different time periods; standardizing the attributes and representing each attribute value as a feature vector to integrate the attributes into a data matrix; performing cluster analysis on the data matrix using the K-means algorithm, identifying multiple different groups based on the cluster analysis results, and determining the advertising content corresponding to each group; acquiring the group distribution in different time periods and determining the advertising content for each time period; when the weather warning aircraft does not need to display meteorological science content, the corresponding advertising content is displayed through a second display area. This invention solves the problem of resource waste caused by weather warning aircraft being idle most of the time in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of meteorological early warning technology, and in particular to an advertising delivery method and system based on a meteorological early warning aircraft. Background Technology

[0002] With global climate change, the frequency and intensity of extreme weather events have increased significantly, causing severe impacts on human society and the natural environment. To address these challenges, meteorological monitoring and early warning technologies have developed rapidly, becoming crucial means of ensuring public safety and reducing disaster losses.

[0003] Currently, weather warning machines are generally installed in elevators of residential buildings or offices to broadcast weather warnings when necessary. However, due to the frequency of hazardous weather events, these machines are idle most of the time, resulting in a waste of resources. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an advertising delivery method and system based on weather warning aircraft, which aims to solve the problem that most weather warning aircraft in the prior art are idle, resulting in wasted resources.

[0005] One objective of this invention is to provide an advertising delivery method based on weather warning aircraft, used for advertising delivery via weather warning aircraft distributed in elevators in public areas. Each weather warning aircraft includes a display screen and an image acquisition device mounted on top of the display screen. The display screen has a display area comprising a first display area in the upper half and a second display area in the lower half. The first display area displays meteorological information, and the second display area displays meteorological science content or advertising content. The method includes:

[0006] The system acquires historical data on elevator passenger information collected by the image acquisition device, and determines the passengers and their corresponding attributes in the elevator at different time periods based on the historical data.

[0007] The attribute values ​​of the passenger's attributes are standardized, and each attribute value is represented as a feature vector to integrate the passenger attributes into a data matrix;

[0008] The data matrix is ​​clustered using the K-means algorithm. Based on the results of the clustering analysis, multiple different groups are identified, and the advertising content for the corresponding advertising types of these groups is determined.

[0009] The distribution of the group in different time periods is obtained, and the advertising content of the elevator in each time period is determined. When the weather warning machine does not need to display weather science content, the advertising content is displayed through the second display area.

[0010] Furthermore, in the aforementioned advertising method based on weather warning aircraft, the step of standardizing the attribute values ​​of the passengers includes:

[0011] Obtain the numerical and nominal attributes of the attribute value, and standardize the numerical attribute based on the mean and standard deviation of the numerical attribute;

[0012] The nominal attributes are encoded according to a preset encoding method to standardize the nominal attributes;

[0013] The formula for calculating the standardization of numerical attributes is as follows:

[0014] ;

[0015] in, H The value of the numeric attribute. m The mean of the numerical attribute. s The standard deviation of the numerical attribute.

[0016] Furthermore, in the aforementioned advertising placement method based on weather warning aircraft, the step of using the K-means algorithm to perform cluster analysis on the data matrix and determining multiple different groups based on the cluster analysis results includes:

[0017] Step 1: Obtain the number of clusters that can stabilize the clustering error, and select a preset number of data points from the data matrix as the initial cluster centers;

[0018] Step 2: Calculate the Euclidean distance from each data point in the data matrix to all initial cluster centers, so as to assign the data point to the group containing the nearest initial cluster center;

[0019] Step 3: For each initial cluster center group, calculate the mean of all data points within that initial cluster center group as the target cluster center;

[0020] Repeat steps two and three until the preset number of iterations is reached, resulting in multiple distinct groups with the same number of clusters.

[0021] Furthermore, in the aforementioned advertising delivery method based on weather warning aircraft, the Euclidean distance is calculated using the following formula:

[0022] ;

[0023] in, x i Data points x The i One attribute, r ki It is the initial cluster center r k The i Each attribute.

[0024] Furthermore, in the above-mentioned advertising delivery method based on weather warning aircraft, the formula for calculating the target cluster center is as follows:

[0025] = ;

[0026] in, C j It is the first j A set of data points for a group x yes C j Data points in | C j | is C j The number of data points in the dataset.

[0027] Furthermore, in the aforementioned advertising delivery method based on weather warning aircraft, the step of selecting a preset number of data points from the data matrix as initial cluster centers includes:

[0028] The data points in the data matrix are then mapped to a preset coordinate system after dimensionality reduction processing.

[0029] Identify the outermost target data point, and determine a rectangular area based on the region enclosed by the extension lines of each target data point;

[0030] The circumcircle of the rectangular region is obtained to determine the initial cluster center determination region, and the initial cluster center determination region is divided into multiple initial cluster center determination sub-regions according to the number of initial cluster centers selected.

[0031] Obtain the geometric center location information of the sub-region where the initial cluster center is determined, determine the data points within the preset range of the geometric center location information, and randomly select one of the data points as the initial cluster center.

[0032] Furthermore, the above-mentioned advertising delivery method based on weather warning aircraft further includes:

[0033] Obtain meteorological information within a preset range of the public area, and determine whether the meteorological information contains early warning information;

[0034] When the meteorological information includes early warning information, the meteorological early warning aircraft is controlled to display meteorological science content about the early warning information through the second display area.

[0035] Another objective of this invention is to provide an advertising delivery system based on weather warning aircraft, used for advertising delivery via weather warning aircraft. The weather warning aircraft are distributed in elevators in public areas. Each weather warning aircraft includes a display screen and an image acquisition device mounted on top of the display screen. The display screen has a display area comprising a first display area in the upper half and a second display area in the lower half. The first display area displays meteorological information, and the second display area displays meteorological science content or advertising content. The system includes:

[0036] The acquisition module is used to acquire historical data on elevator passenger information collected by the image acquisition device, and to determine the passengers and their corresponding attributes in the elevator at different time periods based on the historical data.

[0037] A standard module is used to standardize the attribute values ​​of the passenger's attributes and represent each attribute value as a feature vector to integrate the passenger attributes into a data matrix;

[0038] The determination module is used to perform cluster analysis on the data matrix using the K-means algorithm, determine multiple different groups based on the results of the cluster analysis, and determine the advertising content of the advertising type corresponding to the multiple different groups;

[0039] The display module is used to obtain the distribution of groups in different time periods and determine the advertising content of the elevator in each time period. When the weather warning machine does not need to display meteorological science content, the advertising content is displayed through the second display area.

[0040] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0041] Another object of the present invention is to provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method described above.

[0042] This invention acquires historical data on elevator passenger information collected by an image acquisition device, and determines the passengers and their attributes in different time periods based on this data. The attribute values ​​of the passengers are standardized, and each attribute value is represented as a feature vector to integrate the attributes into a data matrix. The K-means algorithm is used to perform cluster analysis on the data matrix, identifying multiple distinct groups and determining the corresponding advertising content for each group. The distribution of these groups over different time periods is obtained, and the advertising content for each time period is determined. When the weather warning system does not need to display meteorological science content, the corresponding advertising content is displayed through a second display area. Playing the corresponding advertising content when the weather warning system is not issuing warning information avoids resource waste. This solves the problem of resource waste caused by the weather warning system being mostly idle in existing technologies. Attached Figure Description

[0043] Figure 1 This is a flowchart of an advertising delivery method based on a weather warning aircraft proposed in the first embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram illustrating the determination of initial cluster centers in an advertising delivery method based on a weather warning aircraft, as proposed in one embodiment of the present invention.

[0045] Figure 3 This is a structural block diagram of an advertising delivery system based on a weather warning aircraft proposed in the third embodiment of the present invention.

[0046] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0048] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] The following will describe in detail, with reference to specific embodiments and accompanying drawings, how to intelligently display corresponding advertising content when the weather warning aircraft is idle.

[0051] Example 1

[0052] Please see Figure 1 The image shows an advertising placement method based on a weather warning aircraft according to the first embodiment of the present invention. The method is used to place advertisements through a weather warning aircraft. The weather warning aircraft are distributed in elevators in public areas. The weather warning aircraft includes a display screen and an image acquisition device installed on the top of the display screen. The display area of ​​the display screen includes a first display area in the upper half and a second display area in the lower half. The first display area is used to display meteorological information, and the second display area is used to display meteorological science content or advertising content. The method includes steps S10 to S13.

[0053] Step S10: Obtain historical data on elevator passenger information collected by the image acquisition device, and determine the passengers and their corresponding attributes in the elevator at different time periods based on the historical data.

[0054] The public areas include areas where elevators are used, such as residential communities or office buildings. Specifically, an image acquisition device, such as a camera, is installed on the top of the early warning system. After the image or video is captured by the image acquisition device, image recognition algorithms can be used to identify the passenger information inside the elevator. This mainly includes the passenger flow in the elevator at different time periods and the main groups of people using the elevator at different time periods. In practice, a large amount of historical data on elevator passenger information will be collected. Due to the regularity of each person's travel, the passengers in each elevator will also show certain regularities. By collecting a large amount of historical data on elevator passenger information, the attributes of the main passengers in the elevator at each time period can be known, such as gender, age, occupation, etc.

[0055] It should be noted that in the embodiments of the present invention, the weather warning aircraft is equipped with an image acquisition device. In some optional embodiments of the present invention, it can also communicate with the camera inside the elevator, thereby retrieving the data collected by the camera to ensure that the personnel information of the passengers in the elevator can be completely collected. In addition, after the image or video data is collected, the data can be identified and analyzed to obtain the attributes of each passenger. How to analyze the image or video data, for example, by using image recognition algorithms, is understandable to those skilled in the art and will not be elaborated here. Furthermore, since the attributes of passengers in the elevator at different time periods are determined by historical data, the attributes can also be manually marked based on the collected information.

[0056] Step S11: Standardize the attribute values ​​of the passenger's attributes and represent each attribute value as a feature vector to integrate the passenger attributes into a data matrix.

[0057] Specifically, standardizing the attributes of each passenger is to eliminate differences in the units of measurement between different attributes. For example, if one attribute is age and another is income, their numerical ranges may differ significantly, thus preventing certain attributes from having an excessive impact on the results.

[0058] Each attribute value is represented as a feature vector to integrate personnel attributes into a data matrix, which helps with subsequent data analysis and processing.

[0059] Specifically, the numerical and nominal attributes of the attribute value are obtained, and the numerical attributes are standardized based on the mean and standard deviation of the numerical attributes;

[0060] The nominal attributes are encoded according to a preset encoding method to standardize the nominal attributes;

[0061] The formula for calculating the standardization of numerical attributes is as follows:

[0062] ;

[0063] in, H The value of the numeric attribute. m The mean of the numerical attribute. s The standard deviation of the numerical attribute.

[0064] Numerical attributes are variables that can be mathematically manipulated, such as age. Through standardization, numerical attributes are transformed into a scale with a mean of 0 and a standard deviation of 1, eliminating the dimensional differences between different attributes. Nominal attributes, on the other hand, are variables representing categories or classes and cannot be directly manipulated mathematically, such as gender (male / female). To incorporate nominal attributes into the data matrix, they typically need to be converted into numerical form through encoding methods, such as one-hot encoding or label encoding.

[0065] Step S12: Use the K-means algorithm to perform cluster analysis on the data matrix, determine multiple different groups based on the cluster analysis results, and determine the advertising content of the advertising type corresponding to the multiple different groups.

[0066] After obtaining the data matrix, cluster analysis can be performed to group different individuals into different groups, thereby recommending corresponding advertising content to each group. Specifically, the step of using the K-means algorithm to perform cluster analysis on the data matrix and determining multiple different groups based on the cluster analysis results includes:

[0067] Step 1: Obtain the number of clusters that can stabilize the clustering error, and select a preset number of data points from the data matrix as the initial cluster centers;

[0068] Step 2: Calculate the Euclidean distance from each data point in the data matrix to all initial cluster centers, so as to assign the data point to the group containing the nearest initial cluster center;

[0069] Step 3: For each initial cluster center group, calculate the mean of all data points within that initial cluster center group as the target cluster center;

[0070] Repeat steps two and three until the preset number of iterations is reached, resulting in multiple distinct groups with the same number of clusters.

[0071] First, an optimal number of clusters that stabilizes the clustering error can be determined, typically using the existing "elbow rule." Then, a predetermined number of data points are selected from the data matrix as initial cluster centers. The Euclidean distance from each data point to all initial cluster centers is calculated to find the closest initial cluster center and assign it to the corresponding group. Specifically, Euclidean distance can be used to determine the distance between the data point and the initial cluster center.

[0072] The formula for calculating Euclidean distance is:

[0073] ;

[0074] in, x i Data points x The i One attribute, r ki It is the initial cluster center r k The i Each attribute.

[0075] For each initial cluster center group, the mean of all data points within the initial cluster center group is calculated as the target cluster center, thereby updating the initial cluster center. Then, steps two and three are repeated, that is, the allocation of data points and the updating of the initial cluster center are repeatedly performed until the change between the new cluster center and the previous cluster center is lower than a certain threshold, or the preset number of iterations is reached, and finally, the same number of groups as the number of clusters is obtained.

[0076] Specifically, the formula for calculating the target cluster center is:

[0077] = ;

[0078] in, C j It is the first j A set of data points for a group x yes C j Data points in | C j | is C j The number of data points in the dataset.

[0079] Step S12: Obtain the group distribution in different time periods and determine the advertising content of the elevator in each time period. When the weather warning machine does not need to display meteorological science content, the advertising content is displayed through the second display area.

[0080] By analyzing passengers at different times, the main groups in each time period can be identified. Based on the group type, the content that the weather warning aircraft needs to broadcast in each time period can be determined. When the weather warning aircraft does not need to display meteorological science content, advertising content is displayed through the second display area of ​​the screen.

[0081] In addition, in some optional embodiments of the present invention, the method further includes:

[0082] Obtain meteorological information within a preset range of the public area, and determine whether the meteorological information contains early warning information;

[0083] When the meteorological information includes early warning information, the meteorological early warning aircraft is controlled to display meteorological science content about the early warning information through the second display area.

[0084] Among them, the display of meteorological science popularization content has the highest priority. For example, if a lightning warning is detected nearby, then lightning warning and safety popularization videos will be actively displayed.

[0085] In summary, the advertising method based on a weather warning aircraft in the above embodiments of the present invention acquires historical data on elevator passenger information collected by an image acquisition device, and determines the passengers and their corresponding attributes in the elevator at different time periods based on the historical data; standardizes the attribute values ​​of the passengers and represents each attribute value as a feature vector to integrate the passenger attributes into a data matrix; uses the K-means algorithm to perform cluster analysis on the data matrix, and determines multiple different groups based on the cluster analysis results, and determines the advertising content of the corresponding advertising types for multiple different groups; obtains the group distribution in different time periods, and determines the advertising content of the elevator in each time period; when the weather warning aircraft does not need to display meteorological science content, the corresponding advertising content is displayed through the second display area. Playing the corresponding advertising content when the weather warning aircraft does not need to issue warning information avoids resource waste. This solves the problem in the prior art where most weather warning aircraft are idle, leading to resource waste.

[0086] Example 2

[0087] This embodiment also proposes an advertising delivery method based on a weather warning aircraft. The difference between the advertising delivery method based on a weather warning aircraft in this embodiment and the advertising delivery method based on a weather warning aircraft in Embodiment 1 is as follows:

[0088] The step of selecting a preset number of data points from the data matrix as initial cluster centers includes:

[0089] The data points in the data matrix are then mapped to a preset coordinate system after dimensionality reduction processing.

[0090] Identify the outermost target data point, and determine a rectangular area based on the region enclosed by the extension lines of each target data point;

[0091] The circumcircle of the rectangular region is obtained to determine the initial cluster center determination region, and the initial cluster center determination region is divided into multiple initial cluster center determination sub-regions according to the number of initial cluster centers selected.

[0092] Obtain the geometric center location information of the sub-region where the initial cluster center is determined, determine the data points within the preset range of the geometric center location information, and randomly select one of the data points as the initial cluster center.

[0093] When selecting initial cluster centers, if the initial cluster centers are too close together, the K-means clustering algorithm may get stuck in a local optimum, leading to inaccurate clustering results. To avoid this problem, it is necessary to ensure that the centroids of the initial cluster centers are at a certain distance from each other. Specifically, the data points in the data matrix are mapped to a preset coordinate system after dimensionality reduction. The preset coordinate system is a two-dimensional coordinate system. To map the high-dimensional data points to the two-dimensional coordinate system, feature dimensionality reduction is performed. Principal component analysis (PCA) can be used. For example, the covariance matrix of the data points is calculated, and eigenvalues ​​and eigenvectors are found by performing eigenvalue decomposition on this matrix. Based on the magnitude of the eigenvalues, the eigenvectors corresponding to the two largest eigenvalues ​​are selected, and the data is projected onto these two principal components. This reduces the dimensionality of the data points to the set dimension.

[0094] Furthermore, the outermost target data point is identified, and a rectangular region is determined based on the area enclosed by the extension lines of each target data point. The circumcircle of the rectangular region is obtained to determine the initial cluster center determination region. The initial cluster center determination region is then divided into multiple initial cluster center determination sub-regions based on the number of initial cluster centers selected. Data points can be divided into regions by mapping to a coordinate system, allowing initial cluster centers to be selected within different regions, ensuring a certain distance between the initial cluster centers. Further, after determining the initial cluster center determination sub-regions, the geometric center position information of the initial cluster center determination sub-regions is obtained. Data points within a preset range of the geometric center position information are identified, and one is randomly selected from these data points as the initial cluster center. First, the geometric center of the initial cluster center determination sub-region is calculated, and data points near the geometric center are used as initial cluster centers. This ensures that the initial cluster centers are actual existing data points while maintaining distance, avoiding the deviation of virtual points. Specifically, the number of equal parts to be divided is determined based on the number of initial cluster centers. For example, when three initial cluster centers are required, the region defined by the initial cluster centers is divided into three equal parts. One point on the horizontal axis of the circle can be selected as the starting point for the division, or the starting point for the division can be determined based on the centroid of the data. For example, the centroid of the dataset can be obtained by calculating the average coordinates of all points. The coordinates of the centroid can be converted into polar coordinates, and the angle between the centroid and the center of the circle can be calculated. Then, the division can begin from this angle.

[0095] For example, such as Figure 2As shown, data points are mapped to a preset coordinate system. In the diagram, they can be displayed using black dots or special markers. In this embodiment, data points are represented by black dots. Then, the outermost target data points A1, A2, A3, and A4 are determined. A rectangular region A is defined by enclosing the target data points A1, A2, A3, and A4. The circumcircle of the rectangular region is used to determine the initial cluster center region S. Then, the region is divided according to the number of clusters. In this embodiment, the number of clusters is selected as 3, thus obtaining the initial cluster center sub-regions S1, S2, and S3. Finally, the geometric center of each is determined, and data points within the range of the geometric center are randomly selected to obtain the final initial cluster center.

[0096] In summary, the advertising method based on a weather warning aircraft in the above embodiments of the present invention acquires historical data on elevator passenger information collected by an image acquisition device, and determines the passengers and their corresponding attributes in the elevator at different time periods based on the historical data; standardizes the attribute values ​​of the passengers and represents each attribute value as a feature vector to integrate the passenger attributes into a data matrix; uses the K-means algorithm to perform cluster analysis on the data matrix, and determines multiple different groups based on the cluster analysis results, and determines the advertising content of the corresponding advertising types for multiple different groups; obtains the group distribution in different time periods, and determines the advertising content of the elevator in each time period; when the weather warning aircraft does not need to display meteorological science content, the corresponding advertising content is displayed through the second display area. Playing the corresponding advertising content when the weather warning aircraft does not need to issue warning information avoids resource waste. This solves the problem in the prior art where most weather warning aircraft are idle, leading to resource waste.

[0097] Example 3

[0098] Please see Figure 3 The image shows an advertising system based on a weather warning aircraft proposed in the third embodiment of the present invention. This system is used for advertising via weather warning aircraft, which are distributed in elevators in public areas. Each weather warning aircraft includes a display screen and an image acquisition device mounted on top of the display screen. The display screen has a first display area in the upper half and a second display area in the lower half. The first display area displays weather information, and the second display area displays weather science content or advertising content. The system includes:

[0099] The acquisition module 100 is used to acquire historical data about elevator passenger information collected by the image acquisition device, and determine the passengers in the elevator and their corresponding attributes in different time periods based on the historical data.

[0100] Standard module 200 is used to standardize the attribute values ​​of the passenger attributes and represent each attribute value as a feature vector to integrate the passenger attributes into a data matrix;

[0101] The determination module 300 is used to perform cluster analysis on the data matrix using the K-means algorithm, determine multiple different groups based on the results of the cluster analysis, and determine the advertising content of the advertising type corresponding to the multiple different groups;

[0102] The display module 400 is used to obtain the distribution of groups in different time periods and determine the advertising content of the elevator in each time period. When the weather warning machine does not need to display meteorological science content, the advertising content is displayed through the second display area.

[0103] Furthermore, in the aforementioned advertising delivery system based on a weather warning aircraft, the step of standardizing the attribute values ​​of the passengers' attributes includes:

[0104] Obtain the numerical and nominal attributes of the attribute value, and standardize the numerical attribute based on the mean and standard deviation of the numerical attribute;

[0105] The nominal attributes are encoded according to a preset encoding method to standardize the nominal attributes;

[0106] The formula for calculating the standardization of numerical attributes is as follows:

[0107] ;

[0108] in, H The value of the numeric attribute. m The mean of the numerical attribute. s The standard deviation of the numerical attribute.

[0109] Furthermore, in the aforementioned advertising delivery system based on weather warning aircraft, the step of using the K-means algorithm to perform cluster analysis on the data matrix and determining multiple different groups based on the cluster analysis results includes:

[0110] Step 1: Obtain the number of clusters that can stabilize the clustering error, and select a preset number of data points from the data matrix as the initial cluster centers;

[0111] Step 2: Calculate the Euclidean distance from each data point in the data matrix to all initial cluster centers, so as to assign the data point to the group containing the nearest initial cluster center;

[0112] Step 3: For each initial cluster center group, calculate the mean of all data points within that initial cluster center group as the target cluster center;

[0113] Repeat steps two and three until the preset number of iterations is reached, resulting in multiple distinct groups with the same number of clusters.

[0114] Furthermore, in the aforementioned advertising delivery system based on weather warning aircraft, the Euclidean distance is calculated using the following formula:

[0115] ;

[0116] in, x i Data points x The i One attribute, r ki It is the initial cluster center r k The i Each attribute.

[0117] Furthermore, in the aforementioned advertising delivery system based on weather warning aircraft, the formula for calculating the target cluster center is:

[0118] = ;

[0119] in, C j It is the first j A set of data points for a group x yes C j Data points in | C j | is C j The number of data points in the dataset.

[0120] Furthermore, in the aforementioned advertising delivery system based on weather warning aircraft, the step of selecting a preset number of data points from the data matrix as initial cluster centers includes:

[0121] The data points in the data matrix are then mapped to a preset coordinate system after dimensionality reduction processing.

[0122] Identify the outermost target data point, and determine a rectangular area based on the region enclosed by the extension lines of each target data point;

[0123] The circumcircle of the rectangular region is obtained to determine the initial cluster center determination region, and the initial cluster center determination region is divided into multiple initial cluster center determination sub-regions according to the number of initial cluster centers selected.

[0124] Obtain the geometric center location information of the sub-region where the initial cluster center is determined, determine the data points within the preset range of the geometric center location information, and randomly select one of the data points as the initial cluster center.

[0125] Furthermore, the aforementioned advertising delivery system based on weather warning aircraft further includes:

[0126] Obtain meteorological information within a preset range of the public area, and determine whether the meteorological information contains early warning information;

[0127] When the meteorological information includes early warning information, the meteorological early warning aircraft is controlled to display meteorological science content about the early warning information through the second display area.

[0128] The functions or operation steps implemented by the above modules are largely the same as those in the above method embodiments, and will not be repeated here.

[0129] Example 4

[0130] In another aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of the method described in any one of Embodiments 1 to 2 above.

[0131] Example 5

[0132] In another aspect, the present invention provides an electronic device, the electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any one of the methods described in Embodiments 1 to 2 above.

[0133] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0134] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0135] More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable storage media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0136] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0137] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0138] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for advertising delivery based on a weather warning aircraft, characterized in that, This method is used for advertising via weather warning aircraft, which are distributed in elevators in public areas. Each weather warning aircraft includes a display screen and an image acquisition device mounted on top of the display screen. The display screen has a first display area in the upper half and a second display area in the lower half. The first display area displays weather information, and the second display area displays weather science content or advertising content. The system acquires historical data on elevator passenger information collected by the image acquisition device, and determines the passengers and their corresponding attributes in the elevator at different time periods based on the historical data. The attribute values ​​of the passenger's attributes are standardized, and each attribute value is represented as a feature vector to integrate the passenger attributes into a data matrix; The data matrix is ​​clustered using the K-means algorithm. Based on the results of the clustering analysis, multiple different groups are identified, and the advertising content for the corresponding advertising types of these groups is determined. The distribution of the group in different time periods is obtained, and the advertising content of the elevator in each time period is determined. When the weather warning machine does not need to display weather science content, the advertising content is displayed through the second display area. The step of performing cluster analysis on the data matrix using the K-means algorithm and determining multiple different groups based on the cluster analysis results includes: Step 1: Obtain the number of clusters that can stabilize the clustering error, and select a preset number of data points from the data matrix as the initial cluster centers; Step 2: Calculate the Euclidean distance from each data point in the data matrix to all initial cluster centers, so as to assign the data point to the group containing the nearest initial cluster center; Step 3: For each initial cluster center group, calculate the mean of all data points within that initial cluster center group as the target cluster center; Repeat steps two and three until the preset number of iterations is reached, resulting in multiple distinct groups with the same number of clusters. The step of selecting a preset number of data points from the data matrix as initial cluster centers includes: The data points in the data matrix are then mapped to a preset coordinate system after dimensionality reduction processing. Identify the outermost target data point, and determine a rectangular area based on the region enclosed by the extension lines of each target data point; The circumcircle of the rectangular region is obtained to determine the initial cluster center determination region, and the initial cluster center determination region is divided into multiple initial cluster center determination sub-regions according to the number of initial cluster centers selected. Obtain the geometric center location information of the sub-region where the initial cluster center is determined, determine the data points within the preset range of the geometric center location information, and randomly select one of the data points as the initial cluster center.

2. The advertising placement method based on a weather warning aircraft according to claim 1, characterized in that, The step of standardizing the attribute values ​​of the passenger's attributes includes: Obtain the numerical and nominal attributes of the attribute value, and standardize the numerical attribute based on the mean and standard deviation of the numerical attribute; The nominal attributes are encoded according to a preset encoding method to standardize the nominal attributes; The formula for calculating the standardization of numerical attributes is as follows: ； in, H The value of the numeric attribute. μ The mean of the numerical attribute. σ The standard deviation of the numerical attribute.

3. The advertising placement method based on a weather warning aircraft according to claim 1, characterized in that, The formula for calculating the Euclidean distance is: ； in, x i Data points x The i One attribute, ρ ki It is the initial cluster center ρ k The i Each attribute.

4. The advertising placement method based on a weather warning aircraft according to claim 3, characterized in that, The formula for calculating the target cluster center is: = ； in, C j It is the first j A set of data points for a group x yes C j Data points in | C j | is C j The number of data points in the dataset.

5. The advertising placement method based on a weather warning aircraft according to claim 1, characterized in that, The method further includes: Obtain meteorological information within a preset range of the public area, and determine whether the meteorological information contains early warning information; When the meteorological information includes early warning information, the meteorological early warning aircraft is controlled to display meteorological science content about the early warning information through the second display area.

6. An advertising delivery system based on a weather warning aircraft, characterized in that, This system is used for advertising via weather warning aircraft, which are distributed in elevators in public areas. Each weather warning aircraft includes a display screen and an image acquisition device mounted on top of the display screen. The display screen has a first display area in the upper half and a second display area in the lower half. The first display area displays weather information, and the second display area displays weather science content or advertising content. This system is used to implement the advertising method based on weather warning aircraft as described in any one of claims 1 to 5. The system includes: The acquisition module is used to acquire historical data on elevator passenger information collected by the image acquisition device, and to determine the passengers and their corresponding attributes in the elevator at different time periods based on the historical data. A standard module is used to standardize the attribute values ​​of the passenger's attributes and represent each attribute value as a feature vector to integrate the passenger attributes into a data matrix; The determination module is used to perform cluster analysis on the data matrix using the K-means algorithm, determine multiple different groups based on the results of the cluster analysis, and determine the advertising content of the advertising type corresponding to the multiple different groups; The display module is used to obtain the distribution of groups in different time periods and determine the advertising content of the elevator in each time period. When the weather warning machine does not need to display meteorological science content, the advertising content is displayed through the second display area.

7. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as described in any one of claims 1 to 5.

Images