Elevator media delivery management system based on Internet of Things

Abstract

The invention discloses an elevator media delivery management system based on the Internet of Things, relates to the technical field of elevator media management, and forms a core architecture of the elevator media delivery management system based on the Internet of Things through mutual cooperation of three groups of algorithm units. The advertisement effect index AEi is calculated by comprehensively considering multiple influence factors such as advertisement putting cost, return income and different durations of different advertisements, so that a manager can intuitively understand the actual performance of each advertisement in the elevator media putting system, and the advertisement effect index AEi is obtained by comparing the AEi values of different advertisements. By means of the method, which advertisements are better in performance on elevator media can be visually known, scientific and reliable data support is provided for resource distribution in a media putting management system, the advertisement putting strategy can be adjusted based on different advertisement effect indexes AEi of different advertisements, dynamic monitoring and adjustment on different advertisements put in an elevator are completed, and the advertisement putting efficiency is improved. More efficient advertisement resource allocation is carried out, and the advertisement putting effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator media management, and in particular to an elevator media delivery and management system based on the Internet of Things. Background Art

[0002] Elevator advertising is a new type of advertising media, referring to advertisements produced and displayed on the interior walls of urban building elevators. Elevator advertising varies, primarily in commercial and residential elevators, and primarily takes the form of photo frames installed within the elevator cabin. With technological advancements, elevator advertising has also evolved into electronic elevator advertising, featuring displays installed within the elevator interior. Electronic elevator advertising is a video advertisement displayed to people while they are riding in an elevator. Compared to print ads, elevator video ads offer high target audience concentration, mandatory exposure, and high reach, effectively capturing audience attention within the enclosed space of an elevator.

[0003] For example, Chinese invention CN202411274517.X discloses an elevator media delivery management system and method based on the Internet of Things. The key technical point is that only age and gender data are analyzed when analyzing the information of people inside the elevator. It can be applied to areas with large traffic flow, has good use effect, and has good prospects for use.

[0004] However, after the above-mentioned cited documents place advertisements in elevators, it is difficult to comprehensively consider the placement costs, return benefits, and different durations of different advertisements placed in elevators, and to evaluate the placement effects of different advertisements. In other words, it is difficult to dynamically monitor the placement effects of different advertisements after multiple advertisements are placed in the elevator in order to more efficiently allocate advertising resources in the media placement management system. As a result, the placement effect of advertisements in elevators is relatively low.

[0005] Therefore, there is an urgent need for an elevator media delivery management system based on the Internet of Things to solve the above problems. Summary of the Invention

[0006] The purpose of the present invention is to provide an elevator media delivery and management system based on the Internet of Things to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an elevator media delivery management system based on the Internet of Things, the management system comprising the following steps: Data collection: Passenger images are captured through the high-definition camera in the data collection module. The age Ei of the i-th person entering the elevator is calculated using the facial age estimation algorithm based on LBP and HOG features. The return Gi and the cost Ci of advertising i generated by the product through elevator media advertising are obtained through market reports and uploaded to the database. Data preprocessing: transferring the data information in the database to the data processing module for decoding preprocessing to obtain the parameters involved in the calculation in the calculation processing module; Calculation and analysis: Substitute the parameter value obtained after decoding preprocessing into the advertising dynamic priority value algorithm unit of the calculation processing module and calculate the advertising dynamic priority value DPi of different advertisements in the elevator. Substitute the calculated advertising dynamic priority value DPi as an input parameter into the advertising estimated display duration algorithm unit of the calculation processing module to calculate the advertising estimated display duration ATi; The calculated advertising dynamic priority value DPi and the estimated advertising display duration ATi are input as input parameters into the advertising effect index algorithm unit of the calculation processing module to calculate different advertising effect indexes AEi for different advertisements and upload them to the database; Elevator advertising resources are allocated through the resource allocation module.

[0008] Optionally, the elevator advertising resource allocation specifically includes: In the database, an effective threshold value Y1 of the advertising effect index AEi is set to 20%, and a good threshold value Y2 of the advertising effect index AEi is set to 60%. Different advertising effect indexes AEi calculated for different advertisements in the elevator are compared with the effective threshold value Y1 and the good threshold value Y2. Advertisements with an advertising effect index AEi less than the effective threshold value Y1 are classified into interval one, advertisements with an advertising effect index AEi greater than the effective threshold value Y1 and less than the good threshold value Y2 are classified into interval two, and advertisements with an advertising effect index AEi greater than the good threshold value Y2 are classified into interval three. For advertisements in interval 3, the advertisements with the largest advertising effect index AEi value are played in order during a playback cycle of the elevator media; For ads in interval 2, in one playback cycle of the elevator media, ads with the largest advertising effect index (AEi) are placed after ads in interval 3, and their playback duration is extended to 1.2 times the normal time. For advertisements in interval one, in a playback cycle of the elevator media, advertisements with larger advertising effect index AEi values ​​are placed behind advertisements in interval two, and advertising investors are reminded that the revenue effect of this advertisement is low.

[0009] Optionally, the management system includes a data collection module, a data processing module, a calculation processing module and a resource allocation module.

[0010] Optionally, the calculation and processing module includes an advertisement dynamic priority value algorithm unit, an advertisement estimated display duration algorithm unit, and an advertisement effect index algorithm unit.

[0011] Optionally, the advertisement dynamic priority value algorithm unit is as follows: ; in: DPI stands for Dynamic Priority of Advertising; Gi represents the return on advertising i, which is the total revenue generated by the product through elevator media after the product has invested in elevator media advertising; Ci represents the cost of advertising i; Ej represents the average age of passengers in the elevator; Em represents the median age of passengers in the elevator; Es represents the standard deviation of the age of passengers in the elevator; Ni represents the number of times ad i is displayed in the elevator in one day; N max Represents the number of times the ad with the most impressions in elevators was shown in a day; In the formula calculation: This part represents the ratio between the return Gi of ad i and its delivery cost Ci. The size of the ratio represents the economic benefit of advertising after the delivery of ad i, and has a direct positive impact on the formula result, the dynamic priority value DPi of the advertisement. This part reflects the matching degree between the advertisement and the target audience in the elevator by multiplying the deviation between the average age Ej of the passengers in the elevator and the median age Em of the passengers in the elevator by the inverse of the standard deviation Es of the age of the passengers in the elevator; This part represents the number of times Ni that ad i is displayed in the elevator in one day and the number of times N that the ad with the most displays in the elevator in one day is displayed max The negative quadratic exponential power of the ratio between them reflects the impact of display frequency on the dynamic priority of ads. As the number of displays increases, the priority of ads will gradually decrease.

[0012] Optionally, the calculation formula for the average age Ej of passengers in the elevator is as follows: ; in: Ej represents the average age of passengers in the elevator; Ei represents the age of the i-th person entering the elevator. It is calculated by the facial age estimation algorithm using LBP and HOG features after the high-definition camera on the elevator advertising box captures the passenger image. n represents the total number of people entering the elevator in one day; In the formula calculation: The age of the i-th person entering the elevator is calculated by the face age estimation algorithm using LBP and HOG features. The age Ei is added up and divided by the total number of people entering the elevator in one day, n, to get the average age Ej of the passengers in the elevator. Optionally, the algorithm unit for the estimated advertisement display duration is as follows: ; in: ATi represents the estimated display duration of the ad, which is the estimated display duration of ad i in the next day; Di represents the basic display duration of ad i, which is the total display duration of ad i on the previous day; α represents the adjustment coefficient; DPI stands for Dynamic Priority of Advertising; DP avg Represents the average value of the dynamic priority of elevator advertising; In the formula calculation: This part represents the deviation of the advertising priority index from the average level. When the advertising dynamic priority value DPi is higher than the average value DP of the dynamic priority value of the elevator advertising avg When , the deviation is positive, and the formula This part is a positive number greater than 1, indicating that the dynamic priority of the ad is higher, and the estimated display time ATi of the ad is increased; When the advertising dynamic priority value DPi is lower than the average value DP of the advertising dynamic priority value in the elevator avg When the deviation is negative, the formula This part is a positive number between 0 and 1, indicating that the dynamic priority of the ad is low, and the estimated display time ATi of the ad is reduced; The adjustment coefficient α is used to control the impact of the dynamic priority value DPi on the expected display duration ATi of the advertisement. It can be self-adjusted with the elevator media delivery management system: When advertisers want to reduce advertising costs while maintaining a certain advertising effect, they can reduce the value of α to shorten the display time of the ad, thereby reducing the delivery cost while ensuring advertising coverage.

[0013] Optionally, the advertising effect index algorithm unit is as follows: ; in: AEi stands for Advertising Effectiveness Index; ATi represents the actual display duration of ad i; ATi max Represents the display duration of the longest advertisement in the elevator; ATi minRepresents the display duration of the advertisement with the shortest display duration in the elevator; DPI stands for Dynamic Priority of Advertising; DP max Represents the maximum value of all dynamic priority values ​​of ads DP min Represents the minimum value among all advertisement dynamic priority values; In the formula calculation: This part divides the advertising dynamic priority value DPi by The normalized value is between 0 and 1, which more intuitively shows the contribution of the advertising dynamic priority value DPi to the advertising effect index AEi in the formula calculation. When the advertising dynamic priority value DPi increases, the value of this product term will become higher, indicating that the higher the advertising dynamic priority value DPi, the more positive the calculation of the advertising effect index AEi. This part represents the normalized position of the actual display duration ATi of ad i relative to the display duration of all ads, using the display duration ATi of the longest display duration ad in the elevator max Subtract the actual display time ATi of ad i and divide it by the display time ATi of the longest display ad in the elevator max Compared with the display time of the advertisement with the shortest display time in the elevator, ATi min The difference between the two results is a number between 0 and 1, which represents the relative position of the actual display duration ATi of ad i relative to the entire display duration range; The longer the actual display time ATi of ad i is, The smaller the value of this part of the numerator is, the smaller the value of the calculated advertising effect index AEi is; On the contrary, when the actual display time ATi of ad i is smaller, The larger the value of this numerator, the larger the value of the calculated advertising effectiveness index AEi.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention forms the core architecture of an elevator media delivery management system based on the Internet of Things through the mutual cooperation of three groups of algorithm units. It comprehensively considers multiple influencing factors such as the delivery cost, return on investment, and the different durations of different advertisements, and calculates the advertising effect index AEi, so that managers can intuitively understand the actual performance of each advertisement in the elevator media delivery system. By comparing the AEi values ​​of different advertisements, it can intuitively understand which advertisements perform better on elevator media, providing scientific and reliable data support for the allocation of resources in the elevator media delivery management system. It can adjust the advertising delivery strategy based on the different advertising effect indexes AEi of different advertisements, and dynamically monitor and adjust different advertisements delivered in the elevator, so that more efficient advertising resource allocation can be carried out on the advertising display screen in the elevator, thereby improving the advertising delivery effect.

[0015] The present invention calculates different advertising effect indexes AEi for different advertisements and uploads them to the database, and compares them with the effective threshold Y1 and the good threshold Y2: Advertisements with an advertising effectiveness index AEi less than the effective threshold Y1 are classified into interval 1. Advertisements in interval 1 are placed after those in interval 2 in the order of their larger advertising effectiveness index AEi values ​​during a playback cycle of the elevator media, and advertising investors are reminded that the revenue effect of these ads is low. Advertisements with an advertising effect index AEi greater than the effective threshold Y1 and less than the good threshold Y2 are classified into interval 2. Advertisements in interval 2 are placed after ads in interval 3 in the order of their larger advertising effect index AEi values ​​during a playback cycle of the elevator media, and their playback duration is extended by 1.2 times the normal time. Advertisements with an advertising effect index AEi greater than a good threshold Y2 are classified into interval 3. Advertisements in interval 3 are played in order of the advertisements with the largest advertising effect index AEi in a playback cycle of the elevator media. Compared with the traditional elevator media delivery management with multiple advertisements played in a loop and no priority order, this scientific and reliable advertising resource allocation method can dynamically monitor and adjust different advertisements delivered in elevators, and is worthy of promotion and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of an elevator media delivery management system based on the Internet of Things; Figure 2 This is a schematic diagram of the overall structure of an elevator media delivery management system based on the Internet of Things. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] For example 1, please refer to Figures 1 to 2 The present invention provides an elevator media delivery management system based on the Internet of Things, comprising the following steps: Data collection: Passenger images are captured through the high-definition camera in the data collection module. The age Ei of the i-th person entering the elevator is calculated using the facial age estimation algorithm based on LBP and HOG features. The return Gi and the cost Ci of advertising i generated by the product through elevator media advertising are obtained through market reports and uploaded to the database. Data preprocessing: transferring the data information in the database to the data processing module for decoding preprocessing to obtain the parameters involved in the calculation in the calculation processing module; Calculation and analysis: Substitute the parameter value obtained after decoding preprocessing into the advertising dynamic priority value algorithm unit of the calculation processing module and calculate the advertising dynamic priority value DPi of different advertisements in the elevator. Substitute the calculated advertising dynamic priority value DPi as an input parameter into the advertising estimated display duration algorithm unit of the calculation processing module to calculate the advertising estimated display duration ATi; The calculated advertising dynamic priority value DPi and the estimated advertising display duration ATi are input as input parameters into the advertising effect index algorithm unit of the calculation processing module to calculate different advertising effect indexes AEi for different advertisements and upload them to the database; Elevator advertising resources are allocated through a resource allocation module. The effective threshold value Y1 of the advertising effect index AEi is set to 20% in the database, and the good threshold value Y2 of the advertising effect index AEi is set to 60%. The different advertising effect indexes AEi calculated for different advertisements in the elevator are compared with the effective threshold value Y1 and the good threshold value Y2. Advertisements with an advertising effect index AEi less than the effective threshold value Y1 are classified into interval one, advertisements with an advertising effect index AEi greater than the effective threshold value Y1 and less than the good threshold value Y2 are classified into interval two, and advertisements with an advertising effect index AEi greater than the good threshold value Y2 are classified into interval three. For advertisements in interval 3, the advertisements with the largest advertising effect index AEi value are played in order during a playback cycle of the elevator media; For ads in interval 2, in one playback cycle of the elevator media, ads with the largest advertising effect index (AEi) are placed after ads in interval 3, and their playback duration is extended to 1.2 times the normal time. For advertisements in interval one, in a playback cycle of the elevator media, advertisements with larger advertising effect index AEi values ​​are placed behind advertisements in interval two, and advertising investors are reminded that the revenue effect of this advertisement is low.

[0019] In this embodiment: The present invention forms the core architecture of an elevator media delivery management system based on the Internet of Things through the mutual cooperation of three groups of algorithm units. It comprehensively considers multiple influencing factors such as the delivery cost, return on investment, and the different durations of different advertisements, and calculates the advertising effect index AEi, so that managers can intuitively understand the actual performance of each advertisement in the elevator media delivery system. By comparing and analyzing the AEi values ​​of different advertisements, it can intuitively understand which advertisements perform better on elevator media, providing scientific and reliable data support for the allocation of resources in the media delivery management system. It can adjust the advertising delivery strategy based on the different advertising effect indexes AEi of different advertisements, and dynamically monitor and adjust different advertisements delivered in the elevator, so that more efficient advertising resource allocation can be carried out on the advertising display screen in the elevator, thereby improving the advertising delivery effect. The invention is worthy of promotion and use.

[0020] See also Figures 1 to 2 , the advertising dynamic priority value algorithm unit is as follows: ;

[0021] in: DPI stands for Dynamic Priority of Advertising; Gi represents the return on advertising i, which is the total revenue generated by the product through elevator media after the product has invested in elevator media advertising; Ci represents the cost of placing ad i, which is obtained by adding the production cost of the ad to the rental fee of the elevator media ad for one quarter. As the denominator, the higher the production cost, the lower the dynamic priority of the ad, reflecting that the system tends to prefer more cost-effective products when selecting ads; Ej represents the average age of passengers in the elevator, which is the average age of all passengers in the elevator in one day; Em represents the median age of passengers in the elevator, which is the median age of all passengers in the elevator in one day; Es represents the standard deviation of the age of passengers in the elevator; it is the standard deviation calculated from the average age Ej of all passengers in the elevator; Ni represents the number of times ad i is displayed in an elevator in one day, obtained from the elevator media database; N max Represents the number of times the advertisement with the most impressions in elevators in one day was displayed, obtained from the elevator media database; In the formula calculation: This part represents the ratio between the return Gi of ad i and its delivery cost Ci. The size of the ratio represents the economic benefit of advertising after the delivery of ad i, and has a direct positive impact on the formula result, the dynamic priority value DPi of the advertisement. This part reflects the matching degree between the advertisement and the target audience in the elevator by multiplying the deviation between the average age Ej of the passengers in the elevator and the median age Em of the passengers in the elevator by the inverse of the standard deviation Es of the age of the passengers in the elevator; This part is processed by +1 to prevent the denominator from approaching zero. If the absolute value of the deviation is calculated directly without +1 processing, when Es is very small (close to zero), the influence of the passenger's age in the formula will become very large, affecting the calculation of the advertising dynamic priority value DPi; An important principle of advertising delivery is to accurately locate the target audience. By considering age deviation, the system can more accurately evaluate the degree of match between the advertisement and the passengers in the elevator, and thus select advertisements that can arouse the audience's interest and resonance for delivery. That is, the larger the age deviation, that is, the more targeted the advertisement is to a specific age group, and when the age group is close to the average age of the passengers in the elevator, the higher the dynamic priority value DPi of the advertisement will be. This helps to ensure that the advertisement can accurately reach the target audience and improve the advertising effect.

[0022] Frequent display of the same advertisement can easily lead to aesthetic fatigue and resistance among viewers, thus reducing the effectiveness of the advertisement. This part represents the number of times Ni that ad i is displayed in the elevator in one day and the number of times N that the ad with the most displays in the elevator in one day is displayed max The negative quadratic exponential power of the ratio between them reflects the impact of display frequency on the dynamic priority of ads. As the number of displays increases, the priority of ads will gradually decrease. By considering the attenuation effect of display frequency, the system can more reasonably allocate the number of ad displays, ensuring that ads maintain a certain level of exposure while also maintaining the audience's interest and enthusiasm. This helps avoid audience fatigue caused by frequently seeing the same ads and improves the viewing experience and effect of ads.

[0023] The calculation formula for the average age Ej of passengers in the elevator is as follows: ;

[0024] in: Ej represents the average age of passengers in the elevator; Ei represents the age of the i-th person entering the elevator. It is calculated by the facial age estimation algorithm using LBP and HOG features after the high-definition camera on the elevator advertising box captures the passenger image. n represents the total number of people entering the elevator in one day; In the formula calculation: The age Ei of the i-th person entering the elevator is calculated using the face age estimation algorithm using LBP and HOG features. The average age Ej of the passengers in the elevator is obtained by adding up these ages and dividing them by the total number of people entering the elevator in one day, n.

[0025] In this embodiment: By comprehensively considering influencing factors such as the return on advertisement i Gi, the cost of advertisement i Ci, the average age of passengers in the elevator Ej, and the number of times advertisement i is displayed in the elevator per day Ni, the dynamic priority value DPi of the advertisement is calculated and uploaded to the database. By analyzing the different dynamic priority values ​​DPi of different advertisements, the delivery value of different advertisements can be accurately evaluated, and the allocation of advertising resources can be adjusted according to the evaluation results. For advertisements with higher dynamic priority values ​​DPi, the elevator media delivery management system can give them more display opportunities and higher exposure, while for advertisements with lower dynamic priority values ​​DPi, their display times will be appropriately reduced to avoid resource waste. This resource allocation method can ensure that advertising resources are used more reasonably and improve the overall effectiveness of advertising.

[0026] With the support of Internet of Things technology, the elevator media delivery management system can also obtain relevant information such as the age group and gender of passengers in the elevator in real time, and adjust the advertising delivery strategy accordingly. This enables advertisements to reach the target audience more accurately, improve the accuracy and effectiveness of advertising delivery, and provide scientific and reliable data support for the information management and decision-making of construction project progress.

[0027] See also Figures 1 to 2 The algorithm unit for the estimated ad display duration is as follows: ;

[0028] in: ATi represents the estimated display duration of the ad, which is the estimated display duration of ad i in the next day; Di represents the basic display duration of ad i, which is the total display duration of ad i on the previous day; α represents the adjustment coefficient; DPI stands for Dynamic Priority of Advertising; DP avg Represents the average value of the dynamic priority of elevator advertising; In the formula calculation: This part represents the deviation of the advertising priority index from the average level. When the advertising dynamic priority value DPi is higher than the average value DP of the dynamic priority value of the elevator advertising avg When , the deviation is positive, and the formula This part is a positive number greater than 1, indicating that the dynamic priority of the ad is higher, and the estimated display time ATi of the ad is increased; When the advertising dynamic priority value DPi is lower than the average value DP of the advertising dynamic priority value in the elevator avg When the deviation is negative, the formula This part is a positive number between 0 and 1, indicating that the dynamic priority of the ad is low, and the estimated display time ATi of the ad is reduced; The adjustment coefficient α is used to control the impact of the dynamic priority value DPi on the expected display duration ATi of the advertisement. It can be self-adjusted with the elevator media delivery management system. For example: When advertisers want to reduce advertising costs while maintaining a certain advertising effect, they can reduce the value of α to shorten the display time of the ad, thereby reducing the advertising cost while ensuring the advertising coverage rate. When the elevator media delivery management system finds that the conversion rate of a certain advertisement (that is, the proportion of viewers taking actions such as purchasing and consulting after seeing the advertisement) is high, it will increase the value of α to further increase the exposure opportunities of the advertisement.

[0029] The calculation formula for the average dynamic priority value of elevator advertising is as follows: ;

[0030] in: DP avg Represents the average value of the dynamic priority of elevator advertising; DPi t Represents the dynamic priority value of the t-th advertisement; N adv Represents the total number of advertisements in elevators; In the formula calculation: By adding the dynamic priority values ​​DPi of different advertisements in the elevator and dividing it by the total number of advertisements in the elevator N adv , get the average value DP of all advertisement dynamic priority values ​​in the elevator avg ; In this embodiment: Comprehensively consider the basic display duration Di of ad i, the dynamic priority value DPi of ad, and the average value DP of the dynamic priority value of ad in the elevator avgBased on multiple influencing factors such as the audience's viewing time, the estimated display time ATi of different advertisements is calculated and uploaded to the database. The elevator media delivery management system can more reasonably allocate the display time of different advertisements in the elevator to more effectively utilize the advertising resources in the elevator. Compared with the traditional elevator media delivery management with no priority order and multiple advertisements played in a loop, it can make real-time adjustments to multiple advertisement delivery strategies based on the estimated display time ATi. For example, for advertisements with a long display time but poor audience feedback, the system can reduce their display frequency or replace them with other more popular advertisements. This flexible delivery strategy helps to maximize advertising effects and user satisfaction, improve the economic benefits of elevator advertising, and provide scientific and reliable data support for elevator media advertising delivery management.

[0031] See also Figures 1 to 2 , the advertising effect index algorithm unit is as follows: ;

[0032] in: AEi stands for Advertising Effectiveness Index; ATi represents the actual display duration of ad i; ATi max Represents the display duration of the longest advertisement in the elevator; ATi min Represents the display duration of the advertisement with the shortest display duration in the elevator; DPI stands for Dynamic Priority of Advertising; DP max Represents the maximum value of all dynamic priority values ​​of ads DP min Represents the minimum value among all advertisement dynamic priority values; In the formula calculation: This part represents the normalization of the impact of the advertising dynamic priority value DPi on the advertising effect index by dividing the advertising dynamic priority value DPi by The normalized value is between 0 and 1, which more intuitively shows the contribution of the advertising dynamic priority value DPi to the advertising effect index AEi in the formula calculation. When the advertising dynamic priority value DPi increases, the value of this product term will become higher, indicating that the higher the advertising dynamic priority value DPi, the more positive the calculation of the advertising effect index AEi. This part represents the normalized position of the actual display duration ATi of ad i relative to the display duration of all ads, using the display duration ATi of the longest display duration ad in the elevator max Subtract the actual display time ATi of ad i and divide it by the display time ATi of the longest display ad in the elevatormax Compared with the display time of the advertisement with the shortest display time in the elevator, ATi min The difference between the two results is a number between 0 and 1, which represents the relative position of the actual display duration ATi of ad i relative to the entire display duration range; The longer the actual display time ATi of ad i is, The smaller the value of this part of the numerator is, the smaller the value of the calculated advertising effect index AEi is; On the contrary, when the actual display time ATi of ad i is smaller, The larger the value of this numerator, the larger the value of the calculated advertising effectiveness index AEi.

[0033] In this embodiment: Comprehensively consider the actual display time ATi of advertisement i and the average display time ATi of all advertisements in the elevator avg The advertising effectiveness index AEi is calculated based on multiple influencing factors such as the advertising dynamic priority value DPi, so that managers can intuitively understand the actual performance of each advertisement in the elevator media delivery system. It provides an indicator for comprehensively evaluating the advertising effectiveness of multiple advertisements in the elevator. By comparing the AEi values ​​of different advertisements, the elevator media delivery department can intuitively understand which advertisements perform better on the elevator media. Based on the different advertising effectiveness indexes AEi of different advertisements, the advertising delivery strategy can be adjusted. For advertisements with lower AEi values, advertisers can consider increasing their display time, improving their dynamic priority, or changing their delivery time period and floor to improve advertising effectiveness, providing scientific and reliable data support for the allocation of resources in the media delivery management system.

[0034] The effective threshold value Y1 of the advertising effect index AEi is set to 20%, and the good threshold value Y2 of the advertising effect index AEi is set to 60%. The different advertising effect indexes AEi calculated for different advertisements in the elevator are compared with the effective threshold value Y1 and the good threshold value Y2; Advertisements with an advertising effectiveness index AEi less than the effective threshold Y1 are classified into interval 1; Advertisements with an advertising effect index AEi greater than the effective threshold Y1 and less than the good threshold Y2 are classified into interval 2; Advertisements with an advertising effectiveness index AEi greater than a good threshold Y2 are classified into interval three; Elevator advertising resource allocation: For advertisements in interval 3, the advertisements with the largest advertising effect index AEi value are played in order during a playback cycle of the elevator media; For ads in interval 2, in one playback cycle of the elevator media, ads with the largest advertising effect index (AEi) are placed after ads in interval 3, and their playback duration is extended to 1.2 times the normal time. For advertisements in interval one, in a playback cycle of the elevator media, advertisements with larger advertising effect index AEi values ​​are placed behind advertisements in interval two, and advertising investors are reminded that the revenue effect of the advertisement is low and the advertising video needs to be re-arranged or the advertising placement needs to be abandoned.

[0035] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An elevator media delivery management system based on the Internet of Things, characterized by: The management system comprises the following steps: Data collection: Passenger images are captured through the high-definition camera in the data collection module. The age Ei of the i-th person entering the elevator is calculated using the facial age estimation algorithm based on LBP and HOG features. The return Gi and the cost Ci of advertising i generated by the product through elevator media advertising are obtained through market reports and uploaded to the database. Data preprocessing: transferring the data information in the database to the data processing module for decoding preprocessing to obtain the parameters involved in the calculation in the calculation processing module; Calculation and analysis: Substitute the parameter value obtained after decoding preprocessing into the advertising dynamic priority value algorithm unit of the calculation processing module and calculate the advertising dynamic priority value DPi of different advertisements in the elevator. Substitute the calculated advertising dynamic priority value DPi as an input parameter into the advertising estimated display duration algorithm unit of the calculation processing module to calculate the advertising estimated display duration ATi; The calculated advertising dynamic priority value DPi and the estimated advertising display duration ATi are input as input parameters into the advertising effect index algorithm unit of the calculation processing module to calculate different advertising effect indexes AEi for different advertisements and upload them to the database; Elevator advertising resources are allocated through the resource allocation module.

2. The elevator media delivery and management system based on the Internet of Things according to claim 1, characterized in that: The elevator advertising resource allocation specifically includes: In the database, an effective threshold value Y1 of the advertising effect index AEi is set to 20%, and a good threshold value Y2 of the advertising effect index AEi is set to 60%. Different advertising effect indexes AEi calculated for different advertisements in the elevator are compared with the effective threshold value Y1 and the good threshold value Y2. Advertisements with an advertising effect index AEi less than the effective threshold value Y1 are classified into interval one, advertisements with an advertising effect index AEi greater than the effective threshold value Y1 and less than the good threshold value Y2 are classified into interval two, and advertisements with an advertising effect index AEi greater than the good threshold value Y2 are classified into interval three. For advertisements in interval 3, the advertisements with the largest advertising effect index AEi value are played in order during a playback cycle of the elevator media; For ads in interval 2, in one playback cycle of the elevator media, ads with the largest advertising effect index (AEi) are placed after ads in interval 3, and their playback duration is extended to 1.2 times the normal time. For advertisements in interval one, in a playback cycle of the elevator media, advertisements with larger advertising effect index AEi values ​​are placed behind advertisements in interval two, and advertising investors are reminded that the revenue effect of this advertisement is low.

3. The elevator media delivery and management system based on the Internet of Things according to claim 1, characterized in that: The management system includes a data collection module, a data processing module, a calculation processing module and a resource allocation module.

4. The elevator media delivery and management system based on the Internet of Things according to claim 3, characterized in that: The calculation processing module includes an advertisement dynamic priority value algorithm unit, an advertisement estimated display duration algorithm unit, and an advertisement effect index algorithm unit.

5. The elevator media delivery and management system based on the Internet of Things according to claim 4, characterized in that: The advertisement dynamic priority value algorithm unit is as follows: ； in: DPI stands for Dynamic Priority of Advertising; Gi represents the return on advertising i, which is the total revenue generated by the product through elevator media after the product has invested in elevator media advertising; Ci represents the cost of advertising i; Ej represents the average age of passengers in the elevator; Em represents the median age of passengers in the elevator; Es represents the standard deviation of the age of passengers in the elevator; Ni represents the number of times ad i is displayed in the elevator in one day; N max Represents the number of times the ad with the most impressions in elevators was shown in a day; In the formula calculation: This part represents the ratio between the return Gi of ad i and its delivery cost Ci. The size of the ratio represents the economic benefit of advertising after the delivery of ad i, and has a direct positive impact on the formula result, the dynamic priority value DPi of the advertisement. This part reflects the matching degree between the advertisement and the target audience in the elevator by multiplying the deviation between the average age Ej of the passengers in the elevator and the median age Em of the passengers in the elevator by the inverse of the standard deviation Es of the age of the passengers in the elevator; This part represents the number of times Ni that ad i is displayed in the elevator in one day and the number of times N that the ad with the most displays in the elevator in one day is displayed max The negative quadratic exponential power of the ratio between them reflects the impact of display frequency on the dynamic priority of ads. As the number of displays increases, the priority of ads will gradually decrease.

6. The elevator media delivery and management system based on the Internet of Things according to claim 5, characterized in that: The calculation formula for the average age Ej of passengers in the elevator is as follows: ； in: Ej represents the average age of passengers in the elevator; Ei represents the age of the i-th person entering the elevator. It is calculated by the facial age estimation algorithm using LBP and HOG features after the high-definition camera on the elevator advertising box captures the passenger image. n represents the total number of people entering the elevator in one day; In the formula calculation: The age Ei of the i-th person entering the elevator is calculated using the face age estimation algorithm using LBP and HOG features. The average age Ej of the passengers in the elevator is obtained by adding up these ages and dividing them by the total number of people entering the elevator in one day, n.

7. The elevator media delivery and management system based on the Internet of Things according to claim 6, characterized in that: The algorithm unit for the estimated ad display duration is as follows: ； in: ATi represents the estimated display duration of the ad, which is the estimated display duration of ad i in the next day; Di represents the basic display duration of ad i, which is the total display duration of ad i on the previous day; α represents the adjustment coefficient; DPI stands for Dynamic Priority of Advertising; DP avg Represents the average value of the dynamic priority of elevator advertising; In the formula calculation: This part represents the deviation of the advertising priority index from the average level. When the advertising dynamic priority value DPi is higher than the average value DP of the dynamic priority value of the elevator advertising avg When , the deviation is positive, and the formula This part is a positive number greater than 1, indicating that the dynamic priority of the ad is higher, and the estimated display time ATi of the ad is increased; When the advertising dynamic priority value DPi is lower than the average value DP of the advertising dynamic priority value in the elevator avg When the deviation is negative, the formula This part is a positive number between 0 and 1, indicating that the dynamic priority of the ad is low, and the estimated display time ATi of the ad is reduced; The adjustment coefficient α is used to control the impact of the dynamic priority value DPi on the expected display duration ATi of the advertisement. It is adjusted automatically by the elevator media delivery management system: When advertisers want to reduce advertising costs while maintaining a certain advertising effect, they can reduce the value of α to shorten the display time of the ad, thereby reducing the delivery cost while ensuring the advertising coverage.

8. The elevator media delivery and management system based on the Internet of Things according to claim 7 is characterized in that: The advertising effect index algorithm unit is as follows: ； in: AEi stands for Advertising Effectiveness Index; ATi represents the actual display duration of ad i; ATi max Represents the display duration of the longest advertisement in the elevator; ATi min Represents the display duration of the advertisement with the shortest display duration in the elevator; DPI stands for Dynamic Priority of Advertising; DP max Represents the maximum value of all dynamic priority values ​​of ads DP min Represents the minimum value among all advertisement dynamic priority values; In the formula calculation: This part divides the advertising dynamic priority value DPi by The normalized value is between 0 and 1, which intuitively shows the contribution of the advertising dynamic priority value DPi to the advertising effect index AEi in the formula calculation. When the advertising dynamic priority value DPi increases, the value of this product term becomes higher, indicating that the higher the advertising dynamic priority value DPi, the more positive the calculation of the advertising effect index AEi. This part represents the normalized position of the actual display duration ATi of ad i relative to the display duration of all ads, using the display duration ATi of the longest display duration ad in the elevator max Subtract the actual display time ATi of ad i and divide it by the display time ATi of the longest display ad in the elevator max Compared with the display time of the advertisement with the shortest display time in the elevator, ATi min The difference between the two results is a number between 0 and 1, which represents the relative position of the actual display duration ATi of ad i relative to the entire display duration range; The longer the actual display time ATi of ad i is, The smaller the value of this part of the numerator is, the smaller the value of the calculated advertising effect index AEi is; On the contrary, when the actual display time ATi of ad i is smaller, The larger the value of this numerator, the larger the value of the calculated advertising effectiveness index AEi.

Images