Method and system for evaluating content for digital displays by measuring viewer responses by demographic segments
The present invention is a method and system for evaluating relative effectiveness of content in a digital signage network, using a series of measurements to compare and evaluate different contents. The measurements are performed on a plurality of input images of the people captured by a plurality of means for capturing images in the vicinity of at least a digital signage. The present invention is a content rating system based on how the audience responds to the digital content in the intended context of digital media network in-store or in other public viewing areas. The present invention allows the measurement of the response to the content for different segments, further allowing for better planning of the content and optimizing the advertising dollars.
1. A method for evaluating relative effectiveness of content in a digital signage network utilizing an audience measurement system that comprises a plurality of means for capturing images that are connected to at least a server through at least a means for video interface and automated video processing algorithms, comprising the following steps of:
a) capturing a plurality of input images of people through the plurality of means for capturing images in the vicinity of at least a digital signage in said digital signage networks,
b) processing said plurality of input images in order to measure behavior patterns of each person in said people, by applying computer vision algorithms to the input images as processes in the computer, in response to a plurality of contents played in the digital signage,
c) tracking a plurality of persons in the vicinity of a digital signage and measuring a conversion rate from the traffic count that measures the number of people in the vicinity of the digital signage to the impression level that measures the actual number of people who viewed the content,
d) gathering audience measurement data by aggregating the measurements for the behavior patterns of said people wherein the measurements comprise traffic count, impression levels, and emotion levels, and wherein impressions comprise leading, lagging, leading and lagging, and complete impressions, wherein emotional levels comprise positive or negative changes in emotion, wherein emotional levels are measured by an emotional change detection sub-module that measures the magnitude of the emotional change, wherein the emotional change is defined as a positive or negative change,
e) comparing an average viewing length for a content and the play length of the content and measuring the completion percentage of viewing the content,
wherein the average viewing length is calculated based on actual time the people spend watching the content through a viewership measurement by applying computer vision algorithms to the input images,
f) extracting characteristic information from the audience measurement data and a media play log of the contents for the digital signage,
g) measuring the response to the content based on different segments and trip type analysis of the people to execute content mix planning based on the measurement, wherein a trip type comprises trip patterns of the people in the vicinity of the digital signage, and wherein the trip type analysis is performed utilizing joined trajectories from tracking the people in the plurality of input images,
h) evaluating the content in context,
wherein the types of measurement are defined differently depending on the intended location of the digital signage,
wherein contextual information includes spatiotemporal information, environmental information, and media consumption information about expected audience members,
and whereby the context normalizes the data output and enhances analysis,
i) using the audience measurement data to calculate a content effectiveness score through an exemplary formula, S=α*W+β*X+γ*Y+δ*Z, wherein W, X, Y, Z are the average number of lagging and leading, lagging, leading, and complete impressions respectively counted in a given time period, wherein α, β, γ, δ are the coefficients assigned to W, X, Y, Z,
j) comparing conversion rates in a funnel model of the people's engagement with products in response to the played contents,
wherein the funnel model is defined as a model for interaction or engagement level of an audience with a content, product, or product category,
wherein interaction and engagement levels of the audience comprise impression and emotion measurements and
wherein the conversion rates between each engagement level in the funnel model are correlated with the effectiveness of the content in influencing the audience in each engagement level,
k) creating an index as a metric index, wherein the index comprises an attraction index, an engagement index, an emotion change index related to emotion levels, a behavior index, or an average impression duration index related to average viewing length, and
l) measuring the relative effectiveness of a content compared to at least another content in the plurality of contents at reaching a targeted audience and the effectiveness of conveying a message based on a comparison of said characteristic information in response to the played contents,
wherein the relative effectiveness accounts for context for the display comprising intended location and audience,
wherein the targeted audience comprises a set of people segmented based on parameters,
wherein the set of people are segmented into the different segments based on parameters comprising demographics, location type, and time-of-day,
m) calculating a set of content evaluation metrics via a content metrics generation module including the content effectiveness score, the conversion rate, the metric index, and the relative effectiveness of the content, and
n) displaying the results of the set of content evaluation metrics via a video interface connected to a computer.
2. The method according to claim 1 , wherein the method further comprises a step of comparing a set of contents by demographics and ranking the contents,
wherein automated computer vision algorithms segments the demographics,
wherein the contents are copy tested for different demographic groups, and
wherein at least a high-performing content is selected for each targeted group based on the ranking.
3. The method according to claim 1 , wherein the method further comprises a step of measuring emotion change of the people in response to the contents.
4. An apparatus for evaluating relative effectiveness of content in a digital signage network, comprising:
a) a plurality of means for capturing images for capturing a plurality of input images of people in the vicinity of at least a digital signage in said digital signage networks, and
b) at least a computer and computer vision algorithms that performs the following steps of:
processing said plurality of input images in order to measure behavior patterns of each person in said people in response to a plurality of contents played in the digital signage,
tracking a plurality of persons in the vicinity of a digital signage and measuring a conversion ratio from the traffic count that measures the number of people in the vicinity of the digital signage to the impression level that measures the actual number of people who viewed the content,
gathering audience measurement data by aggregating the measurements for the behavior patterns of said people,
wherein the measurements comprise traffic count, impression levels, and emotion levels, and
wherein impressions comprise leading, lagging, leading and lagging, and complete impressions, extracting characteristic information from the audience measurement data and a media play log of the contents for the digital signage, wherein emotional levels comprise positive or negative changes in emotion, wherein emotional levels are measured by an emotional change detection sub-module that measures the magnitude of the emotional change, wherein the emotional change is defined as a positive or negative change,
comparing an average viewing length for a content and the play length of the content and measuring the completion percentage of viewing the content,
wherein the average viewing length is calculated based on actual time the people spend watching the content through a viewership measurement by applying computer vision algorithms to the input images,
measuring the response to the content based on different segments and trip type analysis of the people to execute content mix planning based on the measurement,
wherein a trip type comprises trip patterns of the people in the vicinity of the digital signage, and
wherein the trip type analysis is performed utilizing joined trajectories from tracking the people in the plurality of input images,
evaluating the content in context,
wherein the types of measurement are defined differently depending on the intended location of the digital signage,
wherein contextual information includes spatiotemporal information, environmental information, and media consumption information about expected audience members,
and whereby the context normalizes the data output and enhances analysis,
using the audience measurement data to calculate a content effectiveness score through an exemplary formula, S=α*W+β*X+γ*Y+δ*Z, wherein W, X, Y, Z are the average number of lagging and leading, lagging, leading, and complete impressions respectively counted in a given time period, wherein α, β, γ, δ are the coefficients assigned to W, X, Y, Z, comparing conversion rates in a funnel model of the people's engagement with products in response to the played contents,
wherein the funnel model is defined as a model for interaction or engagement level of an audience with a content, product, or product category,
wherein interaction and engagement levels of the audience comprise impression and emotion measurements and
wherein the conversion rates between each engagement level in the funnel model are correlated with the effectiveness of the content in influencing the audience in each engagement level,
creating an index as a metric index, wherein the index comprises an attraction index, an engagement index, an emotion change index related to emotion levels, a behavior index, or an average impression duration index related to average viewing length, and
measuring the relative effectiveness of a content compared to at least another content in the plurality of contents at reaching a targeted audience and the effectiveness of conveying a message based on a comparison of said characteristic information in response to the played contents,
wherein the relative effectiveness accounts for context for the display comprising intended location and audience,
wherein the targeted audience comprises a set of people segmented based on parameters,
wherein the set of people are segmented into the different segments based on parameters comprising demographics, location type, and time-of-day,
calculating a set of content evaluation metrics via a content metrics generation module including the content effectiveness score, the conversion rate, the metric index, and the relative effectiveness of the content, and
displaying the results of the set of content evaluation metrics via a video interface connected to a computer.
5. The apparatus according to claim 4 , wherein the apparatus further comprises a computer for comparing a set of contents by demographics and ranking the contents,
wherein automated computer vision algorithms segments the demographics,
wherein the contents are copy tested for different demographic groups, and
wherein at least a high-performing content is selected for each targeted group based on the ranking.
6. The apparatus according to claim 4 , wherein the apparatus further comprises a computer for measuring emotion change of the people in response to the contents.