System and method for measurement, planning, monitoring, and execution of out-of-home media

• US 9,058,619 B2
• Filed: 05/17/2012
• Issued: 06/16/2015
• Est. Priority Date: 05/19/2011
• Status: Expired due to Fees

• Current Assignee: Purushottaman Nandakumar, Vinay Chandra
• Original Assignee: Purushottaman Nandakumar, Vinay Chandra
• Inventors: Nandakumar, Purushottaman, Chandra, Vinay
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US13/474,277
• Publication Number:
  US 20130129149A1
• Time in Patent Office: 1,125 Days
• Field of Search: 382/100, 382/103, 382/104, 382/107, 348/143, 348/144, 348/148, 348/149, 348/150, 348/159, 705/14.4, 705/14.41, 705/14.45, 705/14.49, 705/14.5, 705/14.57, 705/14.58, 705/14.62, 705/14.63, 705/14.68
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0266 based on the position of the vehicle
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats

Abstract

The present invention generally relates to a system for measurement, planning, monitoring and execution of advertisements on out-of-home media. The invention provides a method by which greater eyeball content is ensured to out-of-home media assets thereby benefiting advertisers and ensuring efficient advertising budget spend.

Claims

1. A system for effective measurement, planning, monitoring, and execution of out-of-home media assets for advertisements, the system comprising:

a data mapping module provided to enable;

mapping one or more geographical areas to determine presence of and obtain image data of out-of-home media assets present in said area(s);

carrying out sampling at determined key location(s) or junction(s) in said area(s) to obtain static or dynamic image data;

collating and tagging the image data obtained in step (a);

compiling the image data of step (c) and the image data of step (b) to obtain a comprehensive image product;

a data analysis module provided to enable;

subjecting the image product of step (d) to extensive traffic analysis in order to categorise contents thereof based on key data points;

a requirement fit module provided to enable obtaining an advertisement requirement kit from one or more prospective advertiser(s) to determine key advertising requirements;

mapping the advertisement requirements of said one or more prospective advertiser(s) to the image data product of step (d).

2. A system according to claim 1, wherein the data mapping module is provided with means to enable mapping in said area(s) along one or more pre-determined route(s) or along one or more random route(s).

3. A system according to claim 1, wherein the mapping module comprises two-wheeled vehicle helmets provided with high fidelity cameras containing GPS mapping means.

4. A system according to claim 1, wherein the sampling at determined key locations is carried out using two-wheeler vehicle helmets provided with high fidelity cameras containing GPS mapping means.

5. A system according to claim 1, wherein mapping module is further provided with means to form clusters of media assets.

6. A system according to claim 5, wherein the means to form clusters comprise GPS loggers.

7. A system according to claim 1, wherein the image data is stored in a database and periodically updated.

8. A system according to claim 1, further comprising deconstruction means to split the image data of running video into separate image frames.

9. A system according to claim 8, further comprising tagging means to provide individual tags to each image frame to identify location and/or time of image.

10. A system according to claim 8, further comprising tagging means to provide individual tags to each media asset located in each specific cluster.

11. A system according to claim 1, wherein data analysis module comprises means to perform frame-by-frame analysis of the image data to categorise data points including traffic patterns along a route, traffic patterns at one or more location(s) and/or one or more junction(s) in a route, number of vehicles, types of vehicles, occupants of vehicles, pedestrian traffic, stationary traffic, and the like.

12. A system according to claim 1, wherein the data analysis module is provided with a queuing network comprising an estimate of the traffic inflow and/or outflow at each route, means to perturb the estimate in specified limits in order to determine the effect of each estimate on an objective function, means to adjust the estimate by a value that is proportionate to the partial derivative of the estimate in order to determine improvements or variations in the objective function.

13. A system according to claim 1, further comprising means to allot unallocated media assets to existing clusters, or utilize unallocated media assets to form a new cluster.

14. A system according to claim 1, wherein the requirement fit module comprises means for mapping advertiser requirements to image data based on a set of pre-determined parameters.

15. A system according to claim 14, wherein the pre-determined parameters is selected from the group comprising ‘

eyeball’

values, size of media asset, location of media asset, size of cluster, location of cluster, pedestrian demographics, vehicular demographics, and size of clutter surrounding a given media asset.

16. A system according to claim 1, further comprising simulation means whereby advertisers are enabled a real time functionality viewing of proposed media content on a proposed media asset.

17. A system according to claim 1, further comprising alert mechanisms to inform advertiser of eyeballs impacted by an advertisement on one or more selected media assets in dynamic mode.

18. A system according to claim 17, wherein said alert mechanism comprises one or more GPS enabled high fidelity camera(s) located on or around the media asset(s).

19. A method for effective measurement, planning, monitoring, and execution of out-of-home media assets for advertisements, the method comprising:

mapping one or more geographical areas to determine presence of and obtain image data of out-of-home media assets present in said area(s);

carrying out sampling at determined key location(s) or junction(s) in said area(s) to obtain static or dynamic image data;

collating and tagging the image data obtained in step (a);

compiling the image data of step (c) and the image data of step (b) to obtain a comprehensive image product;

subjecting the image product of step (d) to extensive traffic analysis in order to categorise contents thereof based on key data points; and

obtaining an advertisement requirement kit from one or more prospective advertiser(s) to determine key advertising requirements;

mapping the advertisement requirements of said one or more prospective advertiser(s) to the image data product of step (d).

20. A method according to claim 19, wherein mapping of one or more geographical areas comprises identification of said one or more geographical areas, categorization of said areas in order of priority based on information on traffic density, mapping routes of travel in said areas, analyzing the selected routes using an optimal routing model.

21. A method according to claim 19, wherein the optimal routing model comprises creation of a list of junctions or locations, creating clusters of such junctions or locations along pre-determined geographical area parameters, evaluating possible routes within each cluster to estimate travel time, and re-assign junctions and/or locations to clusters in order to improve the estimate of overall travel time.

22. A method according to claim 19, wherein the mapping method includes relays of physical travel along identified routes to obtain video image data in mobile mode along said route.

23. A method according to claim 22, wherein said physical travel is done at pre-determined times of the day.

24. A method according to claim 22, wherein said physical travel is done at random intervals during the day.

25. A method according to claim 19, further comprising sampling at determined key locations or junctions in said areas to obtain static or dynamic image data.

26. A method according to claim 25, wherein said sampling is done by individuals positioned at given junctions or locations at different points of time during a day.

27. A method according to claim 25, wherein the image data is obtained by high-fidelity cameras provided with GPS means located on or around a given media asset or in and around a given junction or location.

28. A method according to claim 19, wherein video image data collected during mapping and/or sampling are tagged with GPS location details and time of image.

29. A method according to claim 19, further comprising converting video image files into a form suitable for deconstruction.

30. A method according to claim 29, wherein the video image files are in .mov form and are converted to .flv form.

31. A method according to claim 19, wherein the video images are split into individual frames to enable detailed analysis of vehicle and pedestrian traffic in respect of each image.

32. A method according to claim 19, wherein each video image file is tagged with an individual id.

33. A method according to claim 31, wherein each individual frame and each media asset located in said individual frame are tagged with respective ids.

34. A method according to claim 33, wherein the images are subjected to tagging a first level classification with a web interface using a node.js application and a database repository made using couchdb.

35. A method according to claim 34, wherein the first level classification is carried out using parameters such as type of vehicle, number of occupants, types of pedestrians, and individual characteristics of each pedestrian, and if desired randomly tagging vehicles and/or pedestrians for further analsyis.

36. A method according to claim 35, further comprising a step of detailed classification of random samples of tagged pedestrians and/or vehicles to determine attributes such as age, appearance, clothing, height and weight, and for vehicles make and model, color, condition and, if visible from license plates, state of origin, and storing the data generated in a central repository.

37. A method according to claim 36, wherein for vehicles, direction of travel is also categorized.

38. A method according to claim 35, further comprising extrapolating GPS coordinates for each tagged entity in an image.

39. A method according to claim 19, wherein each tagged media asset is analysed and data in respect of size, distance of visibility, obstructions, clutter, angle, height, current advertisement content, level presence of and level of illumination are collected and stored in a central data repository.

40. A method according to claim 19, wherein the data analysis step comprises traffic analysis by an analysis of demographic parameters and ‘

eyeball’

content.

41. A method according to claim 40, wherein the traffic patterns are identified in a given geographical area to form a network structure.

42. A method according to claim 40, wherein the traffic analysis is done with a steepest descent estimation model overlaid on a queuing network.

43. A method according to claim 42, wherein the queuing network comprises providing a feasible positive number appropriate for a starting value set in order to estimate traffic inflow and outflow on each route;

perturbing each estimate in increments in order to determine the effect of each estimate on an objective function; and

adjust each estimate a value proportionate to a partial derivation for the estimate.

44. A method according to claim 43, wherein the queuing network is modeled as a Jackson network.

45. A method according to claim 43 wherein the objection function is a square of deviations of estimated junction traffic from the actual junction traffic.

46. A method according to claim 43, wherein the perturbation and adjustment steps are carried out as long as improvements were obtained in the objective function.

47. A method according to claim 19, wherein locations containing media assets are identified in pre-determined area measurements, wherein at each stage of location identification, unassigned media assets are utilized to identify further clusters, and define further locations.

48. A method according to claim 47, further comprising scraping and collecting place data.

49. A method according to claim 48, wherein the place data contains information relating to establishments, landmarks, names of business establishments, designation of areas in municipal directories and the like, and the place data is classified across multiple characteristics.

50. A method according to claim 49, wherein the multiple characteristics include type of establishment as well as specific brands.

51. A method according to claim 19, wherein each media asset cluster is mapped to a route based on specific GPS and directional information to get a mapped site.

52. A method according to claim 51, wherein each mapped site is analysed to determine site influences comprising one or more of traffic at site, demographics of the traffic, site characteristics, specific entities within a pre-determined set(s) of distance from the site, and location characteristics.

53. A method according to claim 52, wherein traffic at site is estimated based on vehicle and/or pedestrian in direction(s) that enable media to be viewed for a junction, and based on a queuing network model where the site is on a thoroughfare.

54. A method according to claim 19 wherein site demographics and eyeball content is estimated by using traffic at site as a base figure for the site, using site characteristics to estimate a factor, within a range of 0.0-1.0, which determines the visibility of the asset, multiplying the site traffic by this factor, using place and location characteristics to estimate refinements for specific demographics, and adding the refinements to the eyeball estimate.

55. A method according to claim 54, wherein the eyeball information obtained includes characteristics chosen from Total Eyeballs per day, Total Eyeballs per day (in a determinate age grouping), Total Eyeballs per day (in a given vehicle), Total Eyeballs per day (for a given personal identification parameter), Number of Schools in 500 m radius, Shopping Area Score—

on a scale of 1-10, and Residential Area Score—

on a scale of 1-10.

56. A method according to claim 19, wherein advertising requirements of specific customers are mapped to media assets, to minimize eyeball costs.

57. A method according to claim 56, wherein a sample set of specific advertising requirements for various types of products, by targeted demographics and timing are collected.

58. A method according to claim 57, wherein the sample requirements are analysed to extract specific characteristics for each requirement, said specific characteristics being one or more of luxury product score, product category, targeted demographic 1, targeted demographic 2, duration of exposure, and preferred location.

59. A method according to claim 58, further comprising collecting and collating expert recommendations based on the sample requirements to identify appropriate assets to advertise on.

60. A method according to claim 59, wherein the requirements, sites and matches are processed through a machine learning algorithm to rank and categorize potential matches for new requirements, the algorithm logic comprising normalizing all site characteristics across the population of sites into a 1-10 scale, identifying candidate site attributes impacting on selection of a site for each requirement characteristic, creating a weighted linear scoring function to rank sites for each requirement, wherein each attribute is initially given an equal weight and then the deviation of recommendations from the rankings by the function is measured, perturbing of the weights to measure the impact of changes in weights on the deviation, modifying the weights based on the perturbation results to improve the objective function, and repeated till no significant improvements were observed.

61. A method according to claim 60, wherein the weighed function is used to create a set of further recommendations of new requirements, further recommendations rated by advertiser, based on said ratings, further refinements carried out to the site characteristics.

62. A method according to claim 19, wherein the mapping is done using two-wheeled vehicle helmets provided with high fidelity cameras containing GPS mapping means.

63. A method according to claim 19, wherein the sampling at determined key locations is carried out using two-wheeler vehicle helmets provided with high fidelity cameras containing GPS mapping means.

64. A method according to claim 19, wherein the image data is stored in a database and periodically updated.

65. A method according to claim 19, further comprising deconstructing the image data of running video into separate image frames.

66. A method according to claim 65, further comprising providing individual tags to each image frame to identify location and/or time of image.

67. A method according to claim 65, further comprising providing individual tags to each media asset located in each specific cluster.

68. A method according to claim 19, wherein a frame-by-frame analysis of the image data is performed to categorise data points including traffic patterns along a route, traffic patterns at one or more location(s) and/or one or more junction(s) in a route, number of vehicles, types of vehicles, occupants of vehicles, pedestrian traffic, stationary traffic, and the like.

69. A method according to claim 19, wherein unallocated media assets are allocated to existing clusters, or utilized to form a new cluster.

70. A method according to claim 19, further comprising enabling simulation for advertisers as a real time functionality viewing of proposed media content on a proposed media asset.

71. A method according to claim 19, further comprising alert mechanisms to inform advertiser of eyeballs impacted by an advertisement on one or more selected media assets in dynamic mode.

72. A method according to claim 71, wherein said alert mechanism comprises one or more GPS enabled high fidelity camera(s) located on or around the media asset(s).

73. A method according to claim 19, wherein the media asset is selected from the group consisting of billboards, moving vehicles, local street furniture.

74. A method according to claim 19, wherein the media content is selected from static advertisement content on billboards, dynamic billboard content on billboards, static advertisement content on vehicles, dynamic advertisement content on vehicles, online internet based media content.

75. A method according to claim 74, wherein for a static advertisement content on a vehicle the method comprises documenting the projected route of the vehicle, estimating eyeballs on said route and aggregating the demographics of the route based on vehicle route.

76. A method according to claim 74, further comprising providing multimedia overlays on moving media to enable dynamic advertisement on vehicles, by estimating the eyeballs on a projected route, slicing the route to create the maximum number of relevant eyeballs for each advertisement, and alternating and displaying advertisements during the route based on GPS co-ordinates.

77. A method according to claim 74, further comprising identifying target segments for a given advertisement, identifying for the vehicle used, the location and place metrics of its reach, and selecting a value that optimizes the number of eyeballs, for utilizing media assets such as newspaper inserts and local cable television advertisements.

78. A method according to claim 74, wherein in order to enhance online media effectiveness through offline media, the method comprises identifying the target segment for the ad, using a “

starter”

display in a specific segment in order to estimate eyeballs, phasing online ads at specific intervals after the starter display, and measuring and fine tuning the clicks per exposure.