Elevator advertisement putting effect evaluation method, device and equipment and storage medium
Through the elevator AI camera, the passenger viewing behavior and passenger classification are detected, combined with the impact factor of the target population of the advertisement, the effective delivery rate of elevator advertisements is calculated, and the problem of indirect evaluation of elevator advertisements in the existing technology is solved, and the accuracy is achieved , rapid delivery effect evaluation.
Patent Information
- Application Number
- CN202411172763.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The measurement method of the existing elevator advertising performance evaluation indicators is not direct, there is no unified standard, the index acquisition period is long, and the effective exposure time does not take into account the target theme and the factors influencing passenger attention.
Real-time video images are collected through the elevator AI camera, the passengers' head-up viewing action is detected, the total viewing time is counted, and the influencing factor is determined based on the passenger classification and the target consumer group of advertisements is determined, and the effective advertising delivery rate is calculated.
The direct and accurate evaluation of the elevator advertisement delivery effect is achieved, and the effective delivery rate is calculated through a unified formula. The index acquisition period is short, which is in line with the actual effect.
Smart Images

Figure CN119048170A_ABST
Abstract
Description
Background Art
[0002] With the increase in community elevators, the importance of elevator advertising in the advertising field is becoming more and more obvious. How to quickly determine whether the advertising strategy and effect are effective and accurate, and adjust the advertising strategy and content accordingly is a problem that elevator advertising needs to face.
[0003] Currently, some of the advertising effectiveness indicators can only be calculated through questionnaire surveys, consumer interviews, and post-revenue data analysis. They generally have problems such as indirect measurement methods, no unified standards, and a long indicator acquisition cycle.
[0004] Effective exposure time is an indicator of the effectiveness of existing elevator advertising. Effective exposure time refers to the length of time that an advertisement is actually seen in an elevator. However, this indicator simply calculates the duration of the advertisement, without taking into account that different advertisements target different themes. At the same time, since passengers' attention in an elevator may be affected by many factors (such as looking at their phones, talking, etc.), the actual effective exposure time may be lower than this theoretical value. How to more accurately evaluate the effectiveness of elevator advertising is a problem that needs to be solved at this stage. Summary of the invention
[0005] In order to solve the problems of indirect measurement method, no unified standard, long index acquisition cycle and other issues in traditional elevator advertising effect evaluation indicators, the present invention provides an elevator advertising effect evaluation method, device, equipment and storage medium.
[0006] In a first aspect, the technical solution of the present invention provides a method for evaluating the effect of elevator advertising, comprising the following steps: Get the total viewing time of advertisements by a single elevator passenger during the calculation period; Determine the value of the influencing factor according to the classification of elevator passengers; The total number of people who watched the elevator advertisement during the calculation period is counted. If a passenger enters and exits the elevator and watches the advertisement multiple times during the calculation period, the number is recorded as 1; Get the total playing time of the advertisement in the calculation period; The effective advertising delivery rate is calculated based on the total viewing time of individual elevator passengers, the impact factor, the total number of people, and the total duration of advertising playback.
[0007] As a further limitation of the technical solution of the present invention, the step of obtaining the total viewing time of advertisements by a single elevator passenger within a calculation period includes: Obtain real-time video footage from the elevator AI camera, detect the elevator passengers' upward gaze movements, and count the total viewing time of the passengers.
[0008] As a further limitation of the technical solution of the present invention, the steps of acquiring the real-time video image collected by the elevator AI camera, detecting the elevator passenger's head-up viewing action, and counting the total viewing time of the passenger specifically include: Get the real-time video images collected by the elevator AI camera; Preprocess the video images; The pre-processed image is analyzed for the elevator passenger's head posture. If the elevator passenger's head is facing the advertising display screen and remains facing the set time, it is considered that the advertisement is being viewed and the timing starts. The timing stops when the elevator passenger's head direction changes or leaves the elevator. The length of time the passenger has viewed the advertisement can be obtained.
[0009] As a further limitation of the technical solution of the present invention, the step of determining the value of the influencing factor according to the elevator passenger classification includes: The facial information of the elevator passengers is obtained through the AI camera when they enter the elevator, and the facial information is input into the trained age classification model to obtain the age group results of the elevator passengers; Categorize elevator passengers according to the age group they belong to; Get the target consumer group for each advertising content; Determine the value of the influencing factor based on the target consumer group; Among them, the impact factor of the target consumer group is 1. The farther away from the age group of the target consumer group, the smaller the impact factor value.
[0010] As a further limitation of the technical solution of the present invention, the method also includes: training an age classification model by acquiring facial images of people in different age groups.
[0011] As a further limitation of the technical solution of the present invention, the step of training the age classification model by acquiring face images of different age groups includes: Select a dataset containing facial images of people of different ages; Preprocess the dataset to ensure that face images have consistent size and format; A convolutional neural network model is adopted and the cross entropy loss function is used as the loss function. The stochastic gradient descent algorithm is used as the optimization algorithm. The data set is input into the convolutional neural network model and the prediction value is calculated by forward propagation. Calculate the value of the loss function based on the predicted value and the true value; Perform back propagation to propagate the gradient of the loss function from the output layer to the input layer and update the parameters of the model; The training is stopped until the preset training rounds are reached or the loss function value change rate is less than the set value, and the trained age classification model is output.
[0012] As a further limitation of the technical solution of the present invention, the calculation formula for calculating the effective advertising delivery rate according to the total viewing time of a single elevator passenger, the influence factor, the total number of people and the total advertising playing time is as follows:
[0013] In the formula, Represents the effective delivery rate of advertising. The total number of people who watched the elevator advertisement during the calculation period is, Represents a single person who viewed an ad. Represents the total playing time of the ad calculation cycle. represents the total time the i-th person watched the elevator advertisement during the calculation period, Represents the value of the influence factor of the i-th person.
[0014] In a second aspect, the technical solution of the present invention further provides an elevator advertising delivery effect evaluation device, including a total viewing time acquisition module, an influence factor determination module, a total number of people determination module, a total playback time acquisition module and a calculation module; The total viewing time acquisition module is used to obtain the total viewing time of advertisements within a calculation period of a single elevator passenger; An impact factor determination module, used to determine the value of the impact factor according to the classification of elevator passengers; The total number determination module is used to count the total number of people who watched the elevator advertisement within the calculation period. If a passenger enters and exits the elevator and watches the advertisement multiple times within the calculation period, the number is recorded as 1; The total playing time acquisition module is used to obtain the total playing time of the advertisement within the calculation period; The calculation module is used to calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the influencing factor, the total number of people and the total advertising playing time.
[0015] As a further limitation of the technical solution of the present invention, the total viewing time acquisition module is used to obtain the real-time video images collected by the elevator AI camera, detect the elevator passengers' head-up viewing actions, and count the total viewing time of the passengers.
[0016] As a further limitation of the technical solution of the present invention, the total viewing time acquisition module includes an image acquisition unit, a preprocessing unit and an analysis and processing unit; Image acquisition unit, used to obtain real-time video images collected by the elevator AI camera; A preprocessing unit, used for preprocessing the video images; The analysis and processing unit is used to analyze the head posture of the elevator passenger on the pre-processed image. If the elevator passenger's head is facing the advertising display screen and remains facing the set time, it is considered that the passenger is watching the advertisement and the timing starts; when the direction of the elevator passenger's head changes or the passenger leaves the elevator, the timing stops; the length of time the passenger watches the advertisement can be obtained.
[0017] As a further limitation of the technical solution of the present invention, the impact factor determination module includes an identification unit, a classification unit, a target acquisition unit and a value selection unit; The recognition unit is used to obtain the facial information of the elevator passenger when entering the elevator through the AI camera, input the facial information into the trained age group classification model, and obtain the age group result of the elevator passenger; A classification unit, used for classifying elevator passengers according to the age groups to which the elevator passengers belong; A target acquisition unit, used to acquire the target consumer group for each advertisement content; A value selection unit, used to determine the value of the influencing factor according to the target consumer group; Among them, the impact factor of the target consumer group is 1. The farther away from the age group of the target consumer group, the smaller the impact factor value.
[0018] As a further limitation of the technical solution of the present invention, the device also includes a model training module, which trains an age classification model by acquiring facial images of different age groups, and is specifically used to select a data set containing facial images of multiple age groups; preprocess the data set to ensure that the facial images have consistent size and format; adopt a convolutional neural network model and use a cross entropy loss function as a loss function, use a stochastic gradient descent algorithm as an optimization algorithm, input the data set into the convolutional neural network model, and perform forward propagation to calculate a predicted value; calculate the value of the loss function based on the predicted value and the true value; perform back propagation to propagate the gradient of the loss function from the output layer to the input layer, and update the parameters of the model; until a preset training round is reached or the rate of change of the loss function value is less than a set value, stop training and output the trained age classification model.
[0019] As a further limitation of the technical solution of the present invention, the calculation formula for calculating the effective advertising delivery rate according to the total viewing time of a single elevator passenger, the influence factor, the total number of people and the total advertising playing time is as follows:
[0020] In the formula, Represents the effective delivery rate of advertising. The total number of people who watched the elevator advertisement during the calculation period is, Represents a single person who viewed an ad. Represents the total playing time of the ad calculation cycle. represents the total time the i-th person watched the elevator advertisement during the calculation period, Represents the value of the influence factor of the i-th person.
[0021] In a third aspect, the technical solution of the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the elevator advertising effect evaluation method as described in the first aspect.
[0022] In a fourth aspect, the technical solution of the present invention further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the elevator advertising effect evaluation method as described in the first aspect.
[0023] It can be seen from the above technical solutions that the present invention has the following advantages: the influencing factor parameters are introduced in the calculation process of the effective delivery rate. According to the different target groups of different advertisements, the viewing effects of different people will also be different. The influencing factor represents this difference, which makes the calculation of the effective delivery rate more in line with the actual effect. In summary, the effective delivery rate can be directly calculated by the formula. The effect evaluation index measurement method proposed by this method is direct. It is calculated by a unified formula, so the standard is unified and the index calculation cycle is short.
[0024] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0026] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.
[0027] Figure 2 is a schematic block diagram of an apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0029] like Figure 1 As shown, an embodiment of the present invention provides an elevator advertising effect evaluation method, comprising the following steps: Step 1: Obtain the total viewing time of advertisements by a single elevator passenger during a calculation period; Step 2: Determine the value of the influencing factor according to the classification of elevator passengers; Step 3: Count the total number of people who watched the elevator advertisement during the calculation period. If a passenger enters and exits the elevator and watches the advertisement multiple times during the calculation period, the number is recorded as 1; Step 4: Get the total playing time of the advertisement in the calculation period; Step 5: Calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the impact factor, the total number of people, and the total advertising playing time; the calculation formula is as follows:
[0030] In the formula, Represents the effective delivery rate of advertising. The total number of people who watched the elevator advertisement during the calculation period is, Represents a single person who viewed an ad. Represents the total playing time of the ad calculation cycle. represents the total time the i-th person watched the elevator advertisement during the calculation period, Represents the value of the influence factor of the i-th person.
[0031] This method adds passenger viewing time statistics and crowd influencing factor parameters to the effective exposure time theory, truly counts the effective viewing time of passengers and considers the target subjects of the advertisement, making the calculated indicators more accurate and effective.
[0032] The elevator camera can be used to obtain the advertising viewing time and crowd classification of all passengers in a day, and then the effective advertising delivery rate R can be calculated through the formula. The higher the delivery rate, the better the delivery effect. The minimum calculation period is one day. To make the calculation result more authentic and universal, the calculation period can be extended from one day to one week or one month. The influencing factor parameter is introduced in the calculation process of the effective delivery rate. According to the different target groups of different advertisements, the viewing effect of different people will also be different. The influencing factor represents this difference, which makes the calculation of the effective delivery rate more in line with the actual effect. In summary, the effective delivery rate can be directly calculated by the formula. The effect evaluation index proposed by this method is directly measured. It is calculated by a unified formula, so the standard is unified and the index calculation period is short.
[0033] In some embodiments, the step of obtaining the total viewing time of advertisements by a single elevator passenger in a calculation period includes: Get the real-time video images collected by the elevator AI camera, detect the elevator passengers' looking up and watching actions, and count the total viewing time of the passengers. Specifically include: Step 11: Obtain the real-time video image collected by the elevator AI camera; Step 12: Preprocess the video images, including denoising, contrast enhancement, brightness adjustment, etc., to prepare for subsequent analysis; Step 13: Analyze the head posture of the elevator passenger on the pre-processed image. If the elevator passenger's head is facing the advertising display screen and remains facing the set time, it is considered that the passenger is watching the advertisement and the timing starts. The timing stops when the elevator passenger's head direction changes or leaves the elevator. The length of time the passenger watches the advertisement can be obtained.
[0034] In some embodiments, the step of determining the value of the influencing factor according to the elevator passenger classification includes: Step 21: Obtain the facial information of the elevator passenger when entering the elevator through the AI camera, input the facial information into the trained age group classification model, and obtain the age group result of the elevator passenger; Step 22: Classify the elevator passengers according to their age groups; Step 23: Obtain the target consumer group for each advertising content; Step 24: Determine the value of the influencing factor based on the target consumer group; Among them, the impact factor of the target consumer group is 1. The farther away from the age group of the target consumer group, the smaller the impact factor value.
[0035] Specifically, AI cameras are used to classify people into children (0-12 years old), teenagers (13-19 years old), adults (20-39 years old), middle-aged (40-64 years old), and the elderly (65 years old and above). There will be a target consumer group for advertising, and the impact factor of the target consumer group is 1; the impact factor of the secondary target consumer group is 0.8; and the impact factor of the rest of the population is 0.6.
[0036] In some embodiments, the method further includes: Step 20: training an age classification model by acquiring facial images of people in different age groups, specifically including: Step 201: Select a data set containing facial images of people in multiple age groups; Step 202: preprocessing the data set to ensure that the face images have a consistent size and format; Step 203: adopting a convolutional neural network model and using a cross entropy loss function as a loss function, using a stochastic gradient descent algorithm as an optimization algorithm, inputting the data set into the convolutional neural network model, and performing forward propagation to calculate a predicted value; Step 204: Calculate the value of the loss function according to the predicted value and the true value; Step 205: Perform back propagation to propagate the gradient of the loss function from the output layer to the input layer and update the parameters of the model; Step 206: until the preset training rounds are reached or the loss function value change rate is less than the set value, the training is stopped and the trained age classification model is output.
[0037] The age classification model uses a convolutional neural network (CNN) architecture. First, select a dataset containing facial images of multiple age groups, such as the Adience dataset; preprocess the dataset, including face detection, cropping, normalization, and other steps to ensure that the face images input to the model have consistent size and format; divide the dataset into a training set, a validation set, and a test set. The training set is used for model training, the validation set is used to adjust model parameters and prevent overfitting, and the test set is used to evaluate the final performance of the model; design the CNN network structure as a convolution layer, a pooling layer, an activation function, and a fully connected layer; use the cross entropy loss function (Categorical Crossentropy) as the loss function; use the stochastic gradient descent (SGD) algorithm as the optimization algorithm; input the training set into the model, and perform forward propagation to calculate the predicted value. Calculate the value of the loss function based on the predicted value and the true value. Perform back propagation to propagate the gradient of the loss function from the output layer to the input layer, and update the parameters of the model. Repeat the above steps until the preset training round (epoch) is reached or the loss function value no longer decreases significantly; finally, use the test set to evaluate the performance of the trained model.
[0038] In an embodiment of the present invention, the effect of elevator advertising can be directly calculated only by acquiring data through the elevator camera, and the calculation result is named effective delivery rate R in this method. The full score of effective delivery rate is 100%, and the higher the score, the better the advertising effect. The minimum value of the calculation period is one day. In order to make the calculation result more authentic and universal, the calculation period can be extended from one day to one week or one month. Influence factor parameters are introduced in the calculation process of effective delivery rate. According to the different target groups of different advertisements, the viewing effects of different people will also be different. The influence factor represents this difference, which makes the calculation of effective delivery rate more in line with the actual effect. In summary, the effective delivery rate can be directly calculated by the formula. The effect evaluation index measurement method proposed by this method is direct. It is calculated by a unified formula, so the standard is unified and the index calculation cycle is short.
[0039] like Figure 2 As shown, the technical solution of the present invention also provides an elevator advertising delivery effect evaluation device, including a total viewing time acquisition module, an influence factor determination module, a total number of people determination module, a total playback time acquisition module and a calculation module; The total viewing time acquisition module is used to obtain the total viewing time of advertisements within a calculation period of a single elevator passenger; An impact factor determination module, used to determine the value of the impact factor according to the classification of elevator passengers; The total number determination module is used to count the total number of people who watched the elevator advertisement within the calculation period. If a passenger enters and exits the elevator and watches the advertisement multiple times within the calculation period, the number is recorded as 1; The total playing time acquisition module is used to obtain the total playing time of the advertisement within the calculation period; The calculation module is used to calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the impact factor, the total number of people, and the total advertising playing time. The calculation formula is as follows:
[0040] In the formula, Represents the effective delivery rate of advertising. The total number of people who watched the elevator advertisement during the calculation period is, Represents a single person who viewed an ad. Represents the total playing time of the ad calculation cycle. represents the total time the i-th person watched the elevator advertisement during the calculation period, Represents the value of the influence factor of the i-th person.
[0041] In some embodiments, the total viewing time acquisition module is used to obtain the real-time video image captured by the elevator AI camera, detect the elevator passenger's head-up viewing action, and count the total viewing time of the passenger; the total viewing time acquisition module includes an image acquisition unit, a preprocessing unit, and an analysis and processing unit; Image acquisition unit, used to obtain real-time video images collected by the elevator AI camera; A preprocessing unit, used for preprocessing the video images; The analysis and processing unit is used to analyze the head posture of the elevator passenger on the pre-processed image. If the elevator passenger's head is facing the advertising display screen and remains facing the set time, it is considered that the passenger is watching the advertisement and the timing starts; when the direction of the elevator passenger's head changes or the passenger leaves the elevator, the timing stops; the length of time the passenger watches the advertisement can be obtained.
[0042] In some embodiments, the impact factor determination module includes an identification unit, a classification unit, a target acquisition unit, and a value selection unit; The recognition unit is used to obtain the facial information of the elevator passenger when entering the elevator through the AI camera, input the facial information into the trained age group classification model, and obtain the age group result of the elevator passenger; A classification unit, used for classifying elevator passengers according to the age groups to which the elevator passengers belong; A target acquisition unit, used to acquire the target consumer group for each advertisement content; A value selection unit, used to determine the value of the influencing factor according to the target consumer group; Among them, the impact factor of the target consumer group is 1. The farther away from the age group of the target consumer group, the smaller the impact factor value.
[0043] In some embodiments, the device also includes a model training module, which trains an age classification model by acquiring facial images of different age groups, and is specifically used to select a data set containing facial images of multiple age groups; preprocess the data set to ensure that the facial images have consistent size and format; adopt a convolutional neural network model and use a cross entropy loss function as a loss function, use a stochastic gradient descent algorithm as an optimization algorithm, input the data set into the convolutional neural network model, and perform forward propagation to calculate a predicted value; calculate the value of the loss function based on the predicted value and the true value; perform back propagation to propagate the gradient of the loss function from the output layer to the input layer, and update the parameters of the model; until a preset training round is reached or the rate of change of the loss function value is less than a set value, stop training and output the trained age classification model.
[0044] The embodiment of the present invention also provides an electronic device, which includes: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The communication bus can be used for information transmission between the electronic device and the sensor. The processor can call the logic instructions in the memory to execute the following method: Step 1: Obtain the total viewing time of advertisements in a calculation cycle of a single elevator passenger; Step 2: Determine the value of the influence factor according to the classification of elevator passengers; Step 3: Count the total number of people who watch elevator advertisements in the calculation cycle, wherein if a passenger enters and exits the elevator and watches advertisements multiple times in the calculation cycle, the number of people is recorded as 1; Step 4: Obtain the total playback time of the advertisement in the calculation cycle; Step 5: Calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the influence factor, the total number of people and the total playback time of the advertisement.
[0045] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.
[0046] An embodiment of the present invention provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the method provided by the above method embodiment, for example, including: Step 1: Obtain the total viewing time of advertisements by a single elevator passenger within a calculation period; Step 2: Determine the value of the influence factor according to the classification of elevator passengers; Step 3: Count the total number of people who watch elevator advertisements within the calculation period, where if a passenger enters and exits the elevator and watches advertisements multiple times within the calculation period, the number of people is recorded as 1; Step 4: Obtain the total playback time of the advertisements within the calculation period; Step 5: Calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the influence factor, the total number of people, and the total playback time of the advertisements. It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0047] The embodiment of the elevator advertising delivery effect evaluation device provided in the embodiment of the present invention belongs to the same inventive concept as the elevator advertising delivery effect evaluation method of the above-mentioned embodiments. For details not described in detail in the embodiment of the elevator advertising delivery effect evaluation device, reference can be made to the embodiment of the above-mentioned elevator advertising delivery effect evaluation method.
[0048] The elevator advertising effect evaluation device is a unit and algorithm step of each example described in combination with the embodiments disclosed in this article, which can be implemented by electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0049] Those skilled in the art will appreciate that various aspects of the elevator advertising effect evaluation method can be implemented as a system, method or program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which can be collectively referred to as "circuit", "module" or "system".
[0050] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. A method for evaluating the effect of elevator advertising, characterized in that: The steps include: Get the total viewing time of advertisements by a single elevator passenger during the calculation period; Determine the value of the influencing factor according to the classification of elevator passengers; The total number of people who watched the elevator advertisement during the calculation period is counted. If a passenger enters and exits the elevator and watches the advertisement multiple times during the calculation period, the number is recorded as 1; Get the total playing time of the advertisement in the calculation period; The effective advertising delivery rate is calculated based on the total viewing time of individual elevator passengers, the impact factor, the total number of people, and the total duration of advertising playback.
2. The elevator advertising effect evaluation method according to claim 1 is characterized in that: The steps for obtaining the total viewing time of advertisements during a calculation period of a single elevator passenger include: Obtain real-time video footage from the elevator AI camera, detect the elevator passengers' upward gaze movements, and count the total viewing time of the passengers.
3. The elevator advertising effect evaluation method according to claim 2 is characterized in that: The steps of obtaining the real-time video images collected by the elevator AI camera, detecting the elevator passengers' upward viewing movements, and counting the total viewing time of the passengers include: Get the real-time video images collected by the elevator AI camera; Preprocess the video images; The pre-processed image is analyzed for the elevator passenger's head posture. If the elevator passenger's head is facing the advertising display screen and remains facing the set time, it is considered that the advertisement is being viewed and the timing starts. The timing stops when the elevator passenger's head direction changes or leaves the elevator. The length of time the passenger has viewed the advertisement can be obtained.
4. The elevator advertising effect evaluation method according to claim 3 is characterized in that: The steps of determining the value of the influencing factor according to the elevator passenger classification include: The facial information of the elevator passengers is obtained through the AI camera when they enter the elevator, and the facial information is input into the trained age classification model to obtain the age group results of the elevator passengers; Categorize elevator passengers according to the age group they belong to; Get the target consumer group for each advertising content; Determine the value of the influencing factor based on the target consumer group; Among them, the impact factor of the target consumer group is 1. The farther away from the age group of the target consumer group, the smaller the impact factor value.
5. The elevator advertising effect evaluation method according to claim 4 is characterized in that: The method also includes: training an age classification model by acquiring face images of people in different age groups.
6. The elevator advertising effect evaluation method according to claim 5 is characterized in that: The steps of training the age classification model by acquiring face images of different age groups include: Select a dataset containing facial images of people of different ages; Preprocess the dataset to ensure that face images have consistent size and format; A convolutional neural network model is adopted and the cross entropy loss function is used as the loss function. The stochastic gradient descent algorithm is used as the optimization algorithm. The data set is input into the convolutional neural network model and the prediction value is calculated by forward propagation. Calculate the value of the loss function based on the predicted value and the true value; Perform back propagation to propagate the gradient of the loss function from the output layer to the input layer and update the parameters of the model; The training is stopped until the preset training rounds are reached or the loss function value change rate is less than the set value, and the trained age classification model is output.
7. The elevator advertising effect evaluation method according to claim 6 is characterized in that: The formula for calculating the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the impact factor, the total number of people, and the total advertising playing time is as follows: In the formula, Represents the effective delivery rate of advertising. The total number of people who watched the elevator advertisement during the calculation period is, Represents a single person who viewed an ad. Represents the total playing time of the ad calculation cycle. represents the total time the i-th person watched the elevator advertisement during the calculation period, Represents the value of the influence factor of the i-th person.
8. An elevator advertising effect evaluation device, characterized in that: It includes a total viewing time acquisition module, an impact factor determination module, a total number of people determination module, a total playback time acquisition module and a calculation module; The total viewing time acquisition module is used to obtain the total viewing time of advertisements within a calculation period of a single elevator passenger; An impact factor determination module, used to determine the value of the impact factor according to the classification of elevator passengers; The total number determination module is used to count the total number of people who watched the elevator advertisement within the calculation period. If a passenger enters and exits the elevator and watches the advertisement multiple times within the calculation period, the number is recorded as 1; The total playing time acquisition module is used to obtain the total playing time of the advertisement within the calculation period; The calculation module is used to calculate the effective advertising delivery rate based on the total viewing time of a single elevator passenger, the influencing factor, the total number of people and the total advertising playing time.
9. An electronic device, characterized in that: The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the elevator advertising effect evaluation method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the elevator advertising effect evaluation method as described in any one of claims 1 to 7.
Citation Information
Patent Citations
An improved analysis method of elevator electronic screen advertisement based on face recognition technology
CN109345305A
Method and device for determining information display effect
CN113296861A
Elevator advertisement intelligent management method and system and computer storage medium
CN115034809A
