Method and system for measuring effectiveness of a marketing campaign on digital signage

• US 10,296,936 B1
• Filed: 09/12/2008
• Issued: 05/21/2019
• Est. Priority Date: 09/26/2007
• Status: Active Grant

• Current Assignee: Videomining Corporation
• Original Assignee: Videomining Corporation
• Inventors: Saurabh, Varij, Sharma, Rajeev, Jung, Namsoon
• Primary Examiner(s): Brockington, III, William S
• Application Number:
  US12/283,606
• Time in Patent Office: 3,903 Days
• Field of Search: 705 10, 705 729
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0246 Traffic

Abstract

The present invention is a system and method for measuring effectiveness of a marketing campaign on digital signage on many different signage networks, by measuring the efficiency of the campaign at reaching targeted audience and the effectiveness of conveying the message. This invention provides a solution to the challenges created by wide variety of measurements and lack of accuracy. By using automated audience measurement, the current invention is able to collect, large, statistically significant data for analysis. Non-intrusive, computer based measurement also ensure that the data is free from any biases. The media content rating system will provide a quantitative measure of how many people did the campaign reach and what effect did it have. The data will be available at the aggregate level, at network level and down to the screen level.

Claims

1. A computer-implemented method for measuring an effectiveness of a marketing campaign on digital signage on signage networks using a set of video processing units, comprising the following steps of:

a) building a vision processing unit by capturing a plurality of input images of a plurality of people by a plurality of cameras in a vicinity of a sampled digital signage in the signage networks, wherein the plurality of cameras are connected to at least a video interface, which transfers the plurality of input images to at least a computer,

b) processing by means of a segmentation analysis and a path analysis the plurality of input images in order to measure a set of behavior patterns and a set of demographics of each person in the plurality of people,

c) gathering a set of audience measurement data by aggregating measurements for the set of behavior patterns and the set of demographics of each person in the plurality of people, wherein the set of behavior patterns are determined from the path analysis, and wherein the set of demographics are determined from the segmentation analysis,

d) getting a media play log for individual networks from a media server that provides content to the sampled digital signage,

e) analyzing and extracting a set of characteristic information from the segmentation analysis and the path analysis based on a set of estimated parameters from the set of audience measurement data, wherein the segmentation analysis uses a demographic composition measurement method, wherein the path analysis analyzes a set of trajectories of the plurality of people, and wherein the set of trajectories are joined from multiple images,

f) processing the set of characteristic information by reformatting and transferring the set of characteristic information to a media campaign rating system and combining the set of characteristic information with the media play log to generate exposure related measurements,

g) measuring an efficiency of the marketing campaign at reaching a targeted audience and the effectiveness of the marketing campaign at conveying a message based on the set of characteristic information, wherein a demographics measurement is used to target a particular demographic group for the marketing campaign, and

h) producing metrics comprising a first engagement index for the sampled digital signage, including impression lengths and a plurality of spot lengths;

a second engagement index for the content, calculated as a complete impression divided by a total impression;

a third engagement index for the content, calculated as a lagging impression divided by the total impression;

an attraction index for the content, calculated as a leading impression divided by the total impression;

a point of engagement or a lag in point, which is a point in a time axis when most impressions started, and a point of disengagement or a lead off point, which is a second point in the time axis when most impressions ended.

2. The method according to claim 1, wherein the method further comprises measuring traffic of the plurality of people by using a second path analysis to calculate a total number of people who were exposed to the content, wherein traffic data is analyzed to measure variations during a predefined window of time, comprising time-of-day, day-of-week, and seasons.

3. The method according to claim 1, wherein the method further comprises measuring impression levels by detecting an act of viewing the content by an audience, and by collecting a total viewing time garnered by the marketing campaign, whereby an analysis of the total viewing time garnered by the marketing campaign is used for measuring the effectiveness of the marketing campaign.

4. The method according to claim 1, wherein the method further comprises measuring impression levels and analyzing a measured impression in detail, wherein a detailed analysis of the measured impression identifies points that an audience finds most engaging and second points that the audience finds most disengaging, and wherein the detailed analysis of the measured impression indicates a start time and an end time of impression, an impression length, a gender of a viewer, an age of the viewer, and an ethnicity of the viewer.

5. The method according to claim 4, further comprising combining the start time and the end time of the measured impression through computer vision algorithms resulting in a plurality of impression types, comprising leading impression, lagging impression, leading and lagging impression, and complete impression.

6. The method according to claim 1, wherein the method further comprises measuring the effectiveness of the marketing campaign by detecting a set of emotional changes in an audience in response to a stimulus, wherein the set of emotional changes is determined from a facial expression analysis.

7. The method according to claim 1, wherein the method further comprises filtering a set of audience data to get data specific to the marketing campaign, comprising the following steps of:

a) getting a set of screen level audience data by time,

b) gathering a play log of times when contents belonging to the marketing campaign are played, and

c) intersecting the set of audience data with the play log.

8. The method according to claim 1, wherein the method further comprises aggregating the set of audience measurement data from a screen level to a campaign level, comprising the following steps of:

a) aggregating a set of measurements over time for a screen,

b) aggregating a screen level measurement for a network measurement, and

c) aggregating the network measurement for a campaign measurement, whereby the campaign measurement comprises traffic counts, impression lengths, and demographics generated using vision based technologies.

9. The method according to claim 1, wherein the method further comprises utilizing a rule application logic module for analyzing and extracting the set of characteristic information based on the set of estimated parameters from the set of audience measurement data and applying the set of characteristic information for measuring the efficiency of the marketing campaign, whereby the rule application logic module enables an adjustment in the analysis and extraction of the set of characteristic information to be done in a structured and dynamic way.

10. An apparatus for measuring an effectiveness of a marketing campaign on digital signage on signage networks, comprising:

a) at least a camera that captures a plurality of input images of a plurality of people in the vicinity of a sampled digital signage in said signage networks, and

b) at least a computer configured to;

process said plurality of input images by means of a segmentation analysis and a path analysis in order to measure a set of behavior patterns and a set of demographics of each person in the plurality of people,

gather a set of audience measurement data by aggregating measurements for the set of behavior patterns and the set of demographics of each person in the plurality of people, wherein the set of behavior patterns are determined from the path analysis, and wherein the set of demographics are determined from the segmentation analysis,

get a media play log for individual networks from a media server that provides content to the sampled digital signage,

analyze and extract a set of characteristic information from the segmentation analysis and the path analysis based on a set of estimated parameters from the set of audience measurement data, wherein the segmentation analysis uses a demographic composition measurement method, wherein the path analysis analyzes a set of trajectories of the plurality of people, and wherein the set of trajectories are joined from multiple images,

process the set of characteristic information by reformatting and transferring the set of characteristic information to a media campaign rating system and combining the set of characteristic information with the media play log to generate exposure related measurements, and

measure an efficiency of the marketing campaign at reaching a targeted audience and the effectiveness of the marketing campaign at conveying a message based on the set of characteristic information, wherein a demographics measurement is used to target a particular demographic group for the marketing campaign, and

produce metrics comprising a first engagement index for the sampled digital signage, including impression lengths and a plurality of spot lengths;

a second engagement index for the content, calculated as a complete impression divided by a total impression;

a third engagement index for the content, calculated as a lagging impression divided by the total impression;

an attraction index for the content, calculated as a leading impression divided by the total impression;

a point of engagement or a lag in point, which is a point in a time axis when most impressions started, and a point of disengagement or a lead off point, which is a second point in the time axis when most impressions ended.

11. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to measure traffic of the plurality of people by using a second path analysis to calculate a total number of people who were exposed to the content, wherein traffic data is analyzed to measure variations during a predefined window of time, comprising time-of-day, day-of-week, and seasons.

12. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to measure impression levels by detecting an act of viewing the content by an audience and by collecting a total viewing time garnered by the marketing campaign, whereby an analysis of the total viewing time garnered by the marketing campaign is used for measuring the effectiveness of the marketing campaign.

13. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to measure impression levels and analyze a measured impression in detail, wherein a detailed analysis of the measured impression identifies points that an audience finds most engaging and second points that the audience finds most disengaging, and wherein the detailed analysis of the measured impression indicates start time and end time of impression, an impression length, a gender of a viewer, an age of the viewer, and an ethnicity of the viewer.

14. The apparatus according to claim 13, wherein the apparatus further comprises the computer configured to combine the start time and the end time of the measured impression through computer vision algorithms resulting in a plurality of impression types, comprising leading impression, lagging impression, leading and lagging impression, and complete impression.

15. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to measure the effectiveness of the marketing campaign by detecting a set of emotional changes in an audience in response to a stimulus, wherein the set of emotional changes is determined from a facial expression analysis.

16. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to filter a set of audience data to get data specific to the marketing campaign by:

a) getting a set of screen level audience data by time,

b) gathering a play log of times when contents belonging to the marketing campaign are played, and

c) intersecting the set of audience data with the play log.

17. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to aggregate the set of audience measurement data from a screen level to a campaign level by:

a) aggregating a set of measurements over time for a screen,

b) aggregating a screen level measurement for a network measurement, and

c) aggregating the network measurement for a campaign measurement, whereby the campaign measurement comprises traffic counts, impression lengths, and

demographics generated using vision based technologies.

18. The apparatus according to claim 10, wherein the apparatus further comprises the computer configured to utilize a rule application logic module to analyze and extract the set of characteristic information based on the set of estimated parameters from the set of audience measurement data and apply the set of characteristic information to measure the efficiency of the marketing campaign, whereby the rule application logic module enables an adjustment in the analysis and extraction of the set of characteristic information to be done in a structured and dynamic way.