Advertisement putting effect analysis method and system and storage medium

Abstract

The invention provides an advertisement putting effect analysis method and system and a storage medium, and relates to the technical field of billboards, and the method comprises the steps: setting a collection device on the front surface of a billboard, collecting face data, analyzing the face data, generating an effective watching evaluation index, equally dividing the billboard into nine regions, and setting the weight of each region. The method comprises the following steps: setting an advertisement putting target weight which comprises a gender weight and an age weight at the same time, extracting picture data of which the single watching time is within an effective watching threshold range, analyzing a face picture collected by a picture data clock through software, obtaining personnel parameters, and displaying the personnel parameters. And a putting weight analysis evaluation index for reflecting the advertisement putting effectiveness after weighting analysis is generated, an advertisement putting effect evaluation index is generated after comprehensive analysis, and an advertisement putting effect grade is output, so that a worker is helped to master the putting effect of the advertising board more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of billboards, and specifically provides a method, a system and a storage medium for analyzing the advertising placement effect. Background Art

[0002] As an important publicity medium, billboards play a role as a bridge connecting brands and consumers. They are not just simple graphic displays, but a combination of creativity and information dissemination. The design of billboards is usually based on eye-catching visual effects and concise written information, aiming to quickly attract the attention of passers-by. In the busy urban life, billboards help brands convey core information in a short time through ingenious color combinations, unique layouts and fascinating images.

[0003] Generally, since billboards cannot be converted into benefits in a short time after being placed, it is difficult to quantitatively analyze their placement effects.

[0004] The above information disclosed in the background art section is applicable to the understanding of the background of the present disclosure, and it may also include information on the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, a system and a storage medium for analyzing the advertising placement effect, so as to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method for analyzing the advertising placement effect, the specific steps include:

[0008] S1. Set a control group, the control group includes 100 randomly selected people aged 16 - 60 years old, let the people in the control group obtain all the information of the billboard, and collect control parameters, the control parameters include control viewing time and control viewing standard deviation, the control viewing time is the average viewing time for all people in the control group to obtain all the information of the billboard, and the control viewing standard deviation is the standard deviation of the time for the people in the control group to obtain all the information of the billboard;

[0009] S2. Conduct a correlation analysis on the control parameters to generate an effective viewing threshold, and the effective viewing threshold is used to reflect the time range required to obtain all the information of the billboard;

[0010] S3. Set up a collection device on the front of the billboard to collect face data. The face data includes a face number and a single viewing time. Perform a correlation analysis on the face number, the single viewing time, and an effective viewing threshold to generate the number of effective viewers, and then perform a correlation analysis on the number of effective viewers to generate an effective viewing evaluation index. The effective viewing evaluation index is used to reflect the degree of the number of people who effectively view the advertisement within the unit passenger flow.

[0011] S4. Divide the billboard into nine regions, set weights for each region, and at the same time set weights for the advertising placement target. The advertising placement target weights include a gender weight and an age weight. The gender weight includes a male weight and a female weight. The age weight includes an elderly weight, a youth weight, a juvenile weight, and a child weight.

[0012] S6. Extract the screen data with the single viewing time within the effective viewing threshold range, analyze the face screens collected in the screen data through software to obtain personnel parameters. The personnel parameters include a regional viewing ratio, a gender ratio, and an age ratio. Perform a correlation analysis on the personnel parameters, the regional weights, the gender weights, and the age weights to generate a placement weight analysis evaluation index TQF.

[0013] S7. Perform a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP. The advertising placement effect evaluation index is used to evaluate the level of the advertising placement effect.

[0014] S8. Compare the advertising placement effect evaluation index with a placement level threshold and output the advertising placement effect level.

[0015] Further, the control viewing time t k is the average viewing time for all personnel in the control group to obtain all the information of the billboard, and the control viewing standard deviation σ k is the standard deviation of the time for the personnel in the control group to obtain all the information of the billboard. Perform a correlation analysis on the control viewing time t k and the control viewing standard deviation σ k to generate an effective viewing threshold θ. The formula is:

[0016] t k - 2 * σ k < θ < t k + 2 * σ k

[0017] The effective viewing threshold θ is used to reflect the time range required to obtain all the information of the billboard.

[0018] Further, a camera device is set on the billboard and connected to the network. Facial data is collected through facial recognition software. The collection time period is 30 days. The collected faces are numbered, and the face number is x i used to represent the i-th collected face, and the single viewing time is t i used to record the time when the face corresponding to the i-th number faces the billboard on the same day. The value range of i is a positive integer from 0 to N.

[0019] Further, a correlation analysis is performed on the face number, single viewing time, and effective viewing threshold θ to generate the number of effective viewers Y i , and the formula is:

[0020]

[0021] Perform a correlation analysis on the number of effective viewers Y i to generate an effective viewing evaluation index YGP. The formula is:

[0022]

[0023] Among them, C is the number of people who pass by and are recognized by the camera device as humans within the 30-day period of collecting facial data, obtained through software analysis and calculation. The effective viewing evaluation index YGP is used to reflect the degree of the number of effective viewers per unit of pedestrian flow.

[0024] Further, the billboard is evenly divided into nine regions, and w j is the weight of the j-th region. j is used to index the region, and the value of j is a positive integer from 1 to 9. The male weight w m is the weight of the advertising placement target occupied by males, and the female weight w f is the weight of the advertising placement target occupied by females. The elderly weight w o , the youth weight w y , the juvenile weight w t , and the child weight w c are the weights of the advertising placement targets occupied by the elderly, youth, juveniles, and children respectively. w m +w f =1, w o +w y +w t +w c =1.

[0025] Further, a correlation analysis is performed on the personnel parameters, regional weights, gender weights, and age weights to generate a placement weight analysis evaluation index TQF. The formula is:

[0026]

[0027] Extract the frame data with the single-viewing time within the effective viewing threshold range, analyze the face frames collected from the frame data through software, re-number a total of M faces, and the regional viewing ratio is the viewing time ratio of the jth region of the pth face, and the gender ratio includes the male ratio X m and the female ratio X f The age ratio includes the elderly ratio Z o the youth ratio Z y the juvenile ratio Z t the child ratio Z c Among them, the time ratio is determined by the ratio of the single-region viewing time to the total viewing time of all regions, and the gender ratio is determined by the gender proportion. People over 55 years old are classified as the elderly, those aged 21 - 54 are classified as the youth, those aged 14 - 20 are classified as juveniles, and those aged 5 - 13 are classified as children. The age of the face is analyzed and classified through the analysis software. Among them, β and γ are the weight factors of gender and age respectively, and β + γ = 1. The delivery weight analysis evaluation index TQF is used to reflect the degree of the effectiveness of the advertisement delivery after the weighted analysis.

[0028] Furthermore, perform a correlation analysis on the delivery weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate the advertisement delivery effect evaluation index GTP. The formula is as follows:

[0029]

[0030] Among them, the advertisement delivery effect evaluation index GTP is used to reflect the degree of the effectiveness of the advertisement delivery on the billboard.

[0031] Furthermore, compare the advertisement delivery effect evaluation index GTP with the delivery level threshold μ, where μ is set to 2.79*C, and output the advertisement delivery effect level. When GTP ≥ μ, it means that the advertisement delivery effect is at the first level, and at this time, the advertisement delivery effect is good and there is no need to improve the advertisement; when μ / 2 ≤ GTP < μ, it means that the advertisement delivery effect is at the second level, and at this time, the advertisement delivery effect is evaluated as average and the content of the billboard needs to be improved; when GTP < μ / 2, it means that the advertisement delivery effect is at the third level and the content and location of the billboard need to be repaired.

[0032] The present invention also provides an advertisement delivery effect analysis system for executing an advertisement delivery effect analysis method, including:

[0033] A control module, used to set a control group. The control group includes 100 randomly selected people aged 16 - 60. Let the people in the control group obtain all the information of the billboard and collect control parameters. The control parameters include control viewing time and control viewing standard deviation;

[0034] An effective viewing threshold analysis module, which conducts a correlation analysis on the control parameters to generate an effective viewing threshold;

[0035] A collection module, used to set a collection device on the front of the billboard to collect face data. The face data includes face numbers and single - viewing times. Conduct a correlation analysis on the face numbers, single - viewing times, and the effective viewing threshold to generate the number of effective viewers, and conduct a correlation analysis on the number of effective viewers to generate an effective viewing evaluation index;

[0036] A weight division module, used to evenly divide the billboard into nine regions, set the weight for each region, and at the same time set the weight of the advertising placement target. The weight of the advertising placement target includes gender weight and age weight. The gender weight includes male weight and female weight. The age weight includes elderly weight, youth weight, juvenile weight, and child weight;

[0037] A weight analysis module, used to extract the picture data with the single - viewing time within the effective viewing threshold range, analyze the face pictures collected in the picture data through software to obtain personnel parameters. The personnel parameters include regional viewing ratio, gender ratio, and age ratio. Conduct a correlation analysis on the personnel parameters, regional weight, gender weight, and age weight to generate a placement weight analysis evaluation index TQF;

[0038] An output module, used to conduct a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP, and compare it with the placement level threshold to output the advertising placement effect level.

[0039] The present invention also provides a storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, an advertising placement effect analysis method is implemented.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] The present invention collects face data by setting a collection device on the front of a billboard, analyzes the face data to generate an effective viewing evaluation index for reflecting the degree of the number of effective views within the unit passenger flow, divides the billboard into nine regions, sets the weight for each region, and simultaneously sets the weight for the advertising placement target. The advertising placement target weight includes gender weight and age weight. The frame data with the single viewing time within the effective viewing threshold range is extracted, and the face frames collected in the frame data are analyzed through software to obtain personnel parameters, and a placement weight analysis evaluation index for reflecting the effectiveness of the advertising placement after weighted analysis is generated. After comprehensive analysis, an advertising placement effect evaluation index is generated and the advertising placement effect level is output, so as to help the staff more accurately grasp the size of the advertising placement effect of the billboard. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0043] Figure 2 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0045] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those skilled in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not indicate any order, quantity, or importance, but are used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before the term cover the elements or objects listed after the term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" not only can represent physical connection but also can include electrical connection, whether direct or indirect. The "left", "right", "up", "down", etc. are only used to represent the relative position relationship. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0046] Embodiment:

[0047] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution:

[0048] A method for analyzing the advertising placement effect, the specific steps include:

[0049] Step 1: Set up a control group. The control group consists of 100 randomly selected people aged 16 - 60. Let the people in the control group obtain all the information of the billboard. Taking the viewing of all the content of the billboard as the standard for obtaining information, collect control parameters. The control parameters include the control viewing time and the control viewing standard deviation. The control viewing time is the average viewing time for all people in the control group to obtain all the information of the billboard, and the control viewing standard deviation is the standard deviation of the time for the people in the control group to obtain all the information of the billboard; the control viewing standard deviation is the population standard deviation, which is obtained by calculating through the standard deviation formula;

[0050] Step 2: Conduct a correlation analysis on the control parameters to generate an effective viewing threshold. The effective viewing threshold is used to reflect the time range required to obtain all the information of the billboard;

[0051] The control viewing time t k is the average viewing time for all people in the control group to obtain all the information of the billboard, and the control viewing standard deviation σ k is the standard deviation of the time for the people in the control group to obtain all the information of the billboard. Conduct a correlation analysis on the control viewing time t k and the control viewing standard deviation σ k to generate an effective viewing threshold θ. The formula is as follows:

[0052] t k - 2 * σ k < θ < t k + 2 * σ k

[0053] According to the law of normal distribution, within the range of two times the standard deviation of the mean, it is the viewing time interval for 95% of the people. This interval is used as the effective viewing threshold. The effective viewing threshold θ is used to reflect the time range required to obtain all the information of the billboard.

[0054] Step 3: Set up a collection device on the front of the billboard to collect face data. The face data includes the face number and the single viewing time. Conduct a correlation analysis on the face number, the single viewing time, and the effective viewing threshold to generate the effective viewing person - times, and conduct a correlation analysis on the effective viewing person - times to generate an effective viewing evaluation index. The effective viewing evaluation index is used to reflect the degree of the number of effective ad - viewing person - times per unit of pedestrian flow;

[0055] Set up a camera device on the billboard and connect it to the network. Collect face data through the OpenFace face recognition software. It can also collect and identify the gender and age of the face and track the eyeballs. The collection time period is 30 days. Number the collected faces. The face number x i is used to represent the i - th collected face, and the single viewing time t iUsed to record the time when the face corresponding to the \(i\)-th number looks directly at the billboard on the same day. The value range of \(i\) is a positive integer from 0 to \(N\). Faces that appear repeatedly within 30 days are discarded as abnormal data.

[0056] Conduct a correlation analysis on the face number, single viewing time, and effective viewing threshold \(\theta\) to generate the number of effective viewers \(Y\). i , and the formula is:

[0057]

[0058] Compare each data with the effective viewing threshold \(\theta\). Each person whose viewing time is within this range is counted as 1.

[0059] For the number of effective viewers \(Y\) i Conduct a correlation analysis to generate the effective viewing evaluation index \(YGP\). The formula is:

[0060]

[0061] Sum up the counts of all people whose viewing time reaches the effective viewing threshold, compare the data with the pedestrian flow within 30 days, and output the effective viewing evaluation index \(YGP\). Among them, \(C\) is the number of people who pass by and are recognized as people by the camera equipment within the 30-day cycle of collecting face data, which is obtained through software analysis and calculation. The effective viewing evaluation index \(YGP\) is used to reflect the degree of the number of people who effectively view the advertisement per unit of pedestrian flow. The larger the value, the higher the proportion of people who effectively view the advertisement.

[0062] Step 4: Divide the billboard into nine regions, set the weight for each region, and at the same time set the weight of the advertising placement target, where the weight of the advertising placement target includes gender weight and age weight. The gender weight includes male weight and female weight, and the age weight includes elderly weight, youth weight, juvenile weight, and child weight.

[0063] Divide the billboard into nine regions, \(w\) j is the weight of the \(j\)-th region, and \(j\) is used to index the region. The value of \(j\) is a positive integer from 1 to 9. The male weight \(w\) m is the weight of the advertising placement target occupied by males, and the female weight \(w\) f is the weight of the advertising placement target occupied by females. The elderly weight \(w\) o , the youth weight \(w\) y , the juvenile weight \(w\) t , and the child weight \(w\) c are the weights of the advertising placement target occupied by the elderly, youth, juveniles, and children respectively. w m +w f =1, wo +w y +w t +w c = 1. The staff designing the billboard set the corresponding weight values according to the importance of the billboard area, the gender weight of the advertising target, and the weights of each age group. The higher the weight value, the higher the proportion of the corresponding target's importance.

[0064] Step 5: Extract the frame data with the single-viewing time within the effective viewing threshold range, analyze the face frames collected from the frame data through software to obtain personnel parameters, where the personnel parameters include the regional viewing ratio, gender ratio, and age ratio. Conduct a correlation analysis on the personnel parameters, regional weights, gender weights, and age weights to generate the placement weight analysis and evaluation index TQF.

[0065] Conduct a correlation analysis on the personnel parameters, regional weights, gender weights, and age weights to generate the placement weight analysis and evaluation index TQF. The formula is as follows:

[0066]

[0067] Determine the magnitude of the placement weight analysis and evaluation index TQF through the weights and data division ratios. The larger the value of the weight analysis and evaluation index TQF, the higher the evaluation score that can be obtained from the collected data under the set weights, that is, the better the advertising placement effect. Extract the frame data with the single-viewing time within the effective viewing threshold range, analyze the face frames collected from the frame data through software, re-number a total of M face frames, and the regional viewing ratio is the viewing time ratio of the j-th region of the p-th face, the gender ratio includes the male ratio X m and the female ratio X f , the age ratio includes the elderly ratio Z o , the youth ratio Z y , the juvenile ratio Z t , and the child ratio Z c . Among them, the time ratio magnitude is determined by the ratio of the single-region viewing time to the total viewing time of all regions, the gender ratio magnitude is determined by the gender proportion. People over 55 years old are classified as the elderly, those aged 21 - 54 are classified as the youth, those aged 14 - 20 are classified as juveniles, and those aged 5 - 13 are classified as children. Analyze and classify the age of the face through the analysis software. Among them, β and γ are the weight factors for gender and age respectively, β + γ = 1. The placement weight analysis and evaluation index TQF is used to reflect the degree of effectiveness of the advertising placement after weighted analysis.

[0068] Step 6: Conduct a correlation analysis on the advertising placement weight analysis and evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP, which is used to evaluate the level of advertising placement effect.

[0069] Step 7: Compare the advertising placement effect evaluation index with the placement level threshold and output the advertising placement effect level.

[0070] The formula for conducting a correlation analysis on the advertising placement weight analysis and evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP is as follows:

[0071]

[0072] Among them, by comprehensively analyzing the advertising placement weight analysis and evaluation index TQF and the effective viewing evaluation index YGP, the larger the values of the comprehensive advertising placement weight analysis and evaluation index TQF and the effective viewing evaluation index YGP, the better the advertising placement effect can be reflected. The advertising placement effect evaluation index GTP is used to reflect the effectiveness degree of advertising on the billboard.

[0073] Compare the advertising placement effect evaluation index GTP with the placement level threshold μ. The placement level threshold is set according to the pedestrian flow data within a certain period of time, and μ is set to 2.79*C. Output the advertising placement effect level. When GTP≥μ, it indicates that the advertising placement effect is at the first level, and at this time, the advertising placement effect is good and there is no need to improve the advertisement; when μ / 2≤GTP<μ, it indicates that the advertising placement effect is at the second level, and at this time, the advertising placement effect is evaluated as average and the content of the billboard needs to be improved; when GTP<μ / 2, it indicates that the advertising placement effect is at the third level, and the content and placement location of the billboard need to be repaired.

[0074] The more times the billboard is seriously watched by people, the more attractive the content of the billboard is, and the better the placement effect. At the same time, the weights of the target audiences of different advertisements are different, and the proportion of the regional weights on the billboard is also different. The higher the number of viewings of the target audience and the longer the viewing time in the important area, the better the advertising placement effect.

[0075] The present invention also provides an advertising placement effect analysis system for executing an advertising placement effect analysis method, including:

[0076] A control module for setting a control group. The control group includes 100 randomly selected people aged 16 - 60. Let the people in the control group obtain all the information of the billboard and collect control parameters, where the control parameters include the control viewing time and the control viewing standard deviation.

[0077] An effective viewing threshold analysis module performs a correlation analysis on control parameters to generate an effective viewing threshold;

[0078] A collection module is used to set a collection device on the front of the billboard to collect face data. The face data includes a face number and a single viewing time. A correlation analysis is performed on the face number, the single viewing time, and the effective viewing threshold to generate the number of effective viewers, and a correlation analysis is performed on the number of effective viewers to generate an effective viewing evaluation index;

[0079] A weight division module is used to evenly divide the billboard into nine regions, set the weight for each region, and at the same time set the weight of the advertising placement target. The weight of the advertising placement target includes a gender weight and an age weight. The gender weight includes a male weight and a female weight. The age weight includes an elderly weight, a youth weight, a juvenile weight, and a child weight;

[0080] A weight analysis module is used to extract the picture data with the single viewing time within the effective viewing threshold range, analyze the face pictures collected in the picture data through software to obtain personnel parameters. The personnel parameters include a regional viewing ratio, a gender ratio, and an age ratio. A correlation analysis is performed on the personnel parameters, the regional weight, the gender weight, and the age weight to generate a placement weight analysis evaluation index TQF;

[0081] An output module is used to perform a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP, and compare it with the placement level threshold to output the advertising placement effect level.

[0082] The present invention also provides a storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, an advertising placement effect analysis method is implemented.

[0083] The above formulas are all dimensionless calculations. The formulas are obtained by software simulation of the collected data to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0084] The above embodiments can be implemented in whole or in part through software, firmware, hardware, or other combinations. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can combine the example units or algorithm steps described in the embodiments disclosed herein and can be implemented through hardware, computer software, or a combination thereof. Whether these functions are executed by hardware, software, or a combination thereof depends on the design constraints of the technical solution.

[0085] The unit described as a separation component may select some or all of the units according to actual needs to implement this embodiment.

[0086] As described above, only the specific embodiments of the present application are provided, but the protection scope of the present application is not limited to the specific embodiments. Those skilled in the art of the present technology can easily think of changes and substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for analyzing the effect of advertising placement, characterized in that The specific steps include: S1. Set up a control group, which includes 100 randomly selected people aged 16 - 60. Let the people in the control group obtain all the information of the billboard, and collect control parameters. The control parameters include control viewing time and control viewing standard deviation. The control viewing time is the average viewing time for all people in the control group to obtain all the information of the billboard, and the control viewing standard deviation is the time standard deviation for the people in the control group to obtain all the information of the billboard; S2. Conduct a correlation analysis on the control parameters to generate an effective viewing threshold, which is used to reflect the time range required to obtain all the information of the billboard; S3. Set up a collection device on the front of the billboard to collect face data. The face data includes face numbers and single - viewing times. Conduct a correlation analysis on the face numbers, single - viewing times, and the effective viewing threshold to generate the number of effective viewings, and then conduct a correlation analysis on the number of effective viewings to generate an effective viewing evaluation index, which is used to reflect the degree of the number of people effectively viewing the advertisement within the unit pedestrian flow; S4. Divide the billboard into nine regions evenly, set the weight for each region, and at the same time set the weight for the advertising placement target. The weight for the advertising placement target includes gender weight and age weight. The gender weight includes male weight and female weight. The age weight includes senior weight, youth weight, juvenile weight, and child weight; S5. Extract the frame data with the single - viewing time within the effective viewing threshold range, analyze the face frames collected in the frame data through software to obtain personnel parameters. The personnel parameters include regional viewing ratio, gender ratio, and age ratio. Conduct a correlation analysis on the personnel parameters, regional weight, gender weight, and age weight to generate a placement weight analysis evaluation index TQF; S6. Conduct a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP, which is used to evaluate the level of the advertising placement effect; S7. Compare the advertising placement effect evaluation index with the placement level threshold and output the advertising placement effect level.

2. The method for analyzing the advertising placement effect according to claim 1, characterized in that: Control viewing time t k Is the average viewing time for all personnel in the control group to obtain all the information of the billboard, and the control viewing standard deviation σ k Is the standard deviation of the time for the personnel in the control group to obtain all the information of the billboard. For the control viewing time t k And the control viewing standard deviation σ k A correlation analysis is performed to generate an effective viewing threshold θ. The formula used is: t k -2*σ k <θ<t k +2*σ k The effective viewing threshold θ is used to reflect the time range required to obtain all the information of the billboard.

3. The method for analyzing the advertising placement effect according to claim 2, wherein: Set up a camera device on the billboard and connect it to the network. Collect face data through face recognition software. The collection time period is 30 days. Number the collected faces, and the face number is x i Used to represent the i-th collected face, and the single viewing time is t i Used to record the time when the face corresponding to the i-th number faces the billboard on the same day. The value range of i is a positive integer from 0 to N.

4. The method for analyzing the effect of advertisement placement according to claim 3, wherein: Conduct a correlation analysis on the face number, single viewing time, and effective viewing threshold θ to generate the number of effective viewers Y i , and the formula is as follows: For the effective viewership Y i Perform a correlation analysis to generate an effective viewership evaluation index YGP, based on the formula: Among them, C is the number of people who pass by and are recognized by the camera device within 30 days of collecting face data, which is obtained through software analysis and calculation. The effective viewing evaluation index YGP is used to reflect the degree of the number of people effectively viewing the advertisement within the unit pedestrian flow.

5. The method for analyzing the advertising placement effect according to claim 4, characterized in that: Divide the billboard into nine equal regions, w j is the weight of the j-th region, where j is used to index the regions and j takes positive integer values from 1 to 9. The male weight w m is the weight of the advertising target for males. The female weight w f is the weight of the advertising target for females. The elderly weight w o , the youth weight w y , the juvenile weight w t , and the child weight w c are the weights of the advertising targets for the elderly, youth, juveniles, and children respectively. w m +w f = 1, w o +w y +w t +w c = 1.

6. The method for analyzing the advertising delivery effect according to claim 5, wherein: Conduct a correlation analysis on the personnel parameters, regional weight, gender weight, and age weight to generate a placement weight analysis evaluation index TQF. The formula is as follows: Extract the frame data with the single-viewing time within the effective viewing threshold range. Analyze the face frames collected from the frame data through software, re-number a total of M faces, and calculate the regional viewing ratio is the viewing time ratio of the j-th region of the p-th face, and the gender ratio includes the male ratio X m and the female ratio X f , the age ratio includes the elderly ratio Z o , the youth ratio Z y , the juvenile ratio Z t , the child ratio Z c . Among them, the time ratio is determined by the ratio of the single-region viewing time to the total viewing time of all regions, and the gender ratio is determined by the gender proportion. People over 55 years old are classified as the elderly, those aged 21 - 54 are classified as the youth, those aged 14 - 20 are classified as juveniles, and those aged 5 - 13 are classified as children. Analyze and classify the age of the face through the analysis software, where β and γ are the weight factors for gender and age respectively, and β + γ = 1. The advertising placement weight analysis evaluation index TQF is used to reflect the degree of effectiveness of the advertising placement after weighted analysis.

7. The method for analyzing the advertising delivery effect according to claim 6, wherein: Conduct a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP. The formula is as follows: Among them, the advertising placement effect evaluation index GTP is used to reflect the effectiveness degree of the advertisement placement on the billboard.

8. The method for analyzing the advertising placement effect according to claim 7, wherein: Compare the advertising placement effect evaluation index GTP with the placement level threshold μ. μ is set to 2.79*C, and output the advertising placement effect level. When GTP≥μ, it indicates that the advertising placement effect is at the first level, and at this time, the advertising placement effect is good and there is no need to improve the advertisement. When μ / 2≤GTP<μ, it indicates that the advertising placement effect is at the second level, and at this time, the advertising placement effect evaluation is average and the content of the billboard needs to be improved. When GTP<μ / 2, it indicates that the advertising placement effect is at the third level, and the content and placement location of the billboard need to be trimmed.

9. An advertising delivery effect analysis system for implementing the advertising delivery effect analysis method described in claim 1, characterized in that, Including: A control module for setting a control group. The control group includes 100 randomly selected people aged 16 - 60. Let the people in the control group obtain all the information of the billboard and collect control parameters. The control parameters include the control viewing time and the control viewing standard deviation; An effective viewing threshold analysis module for performing a correlation analysis on the control parameters to generate an effective viewing threshold; A collection module for setting a collection device on the front of the billboard to collect face data. The face data includes the face number and the single viewing time. Perform a correlation analysis on the face number, the single viewing time, and the effective viewing threshold to generate the effective viewing person-times, and perform a correlation analysis on the effective viewing person-times to generate an effective viewing evaluation index; A weight division module for evenly dividing the billboard into nine regions, setting the weight for each region, and at the same time setting the advertising placement target weights. The advertising placement target weights include the gender weight and the age weight. The gender weight includes the male weight and the female weight. The age weight includes the elderly weight, the youth weight, the juvenile weight, and the child weight; A weight analysis module for extracting the frame data with the single viewing time within the effective viewing threshold range, analyzing the face frames collected in the frame data through software to obtain personnel parameters. The personnel parameters include the regional viewing ratio, the gender ratio, and the age ratio. Perform a correlation analysis on the personnel parameters, the regional weight, the gender weight, and the age weight to generate a placement weight analysis evaluation index TQF; An output module for performing a correlation analysis on the placement weight analysis evaluation index TQF and the effective viewing evaluation index YGP to generate an advertising placement effect evaluation index GTP, and comparing it with the placement level threshold to output the advertising placement effect level.

10. A storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the method described in claim 1 is implemented.

Images