Cross-screen optimization of advertising placement

• US 10,667,020 B2
• Filed: 05/21/2018
• Issued: 05/26/2020
• Est. Priority Date: 07/24/2015
• Status: Active Grant

• Current Assignee: Videoamp, Inc.
• Original Assignee: Videoamp, Inc.
• Inventors: Ray, Debajyoti, McCray, Ross, Gullo, David, Prasad, Jay
• Primary Examiner(s): Flynn, Randy A
• Application Number:
  US15/985,634
• Publication Number:
  US 20180270544A1
• Time in Patent Office: 736 Days
• CPC Class Codes: G06Q 30/0264 based upon schedule
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: H04N 21/2385 Channel allocation H04N21/266 takes precedence; Bandwidth allocation H04N21/24 takes precedence ; allocation of channels according to the instantaneous demands of the users in time-division multiplex systems H04J3/1682; admission control, resource allocation in open networks H04L12/5692; arrangements for maintenance or administration in data switching networks involving bandwidth and capacity management H04L41/0896; negotiating bandwidth in wireless networks H04W28/16
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/2543 Billing , e.g. for subscription services payment schemes, architectures or protocols G06Q20/00; e-commerce G06Q30/00; arrangements for billing for the use of broadcast information or broadcast-related information H04H60/21
• CPC Class Codes: H04N 21/25883 being end-user demographical data, e.g. age, family status or address arrangements for identifying locations of users in broadcast systems H04H60/52
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

The current invention relates to a computer-generated method for optimizing placement of advertising content across multiple different devices. The system can allocate advertising campaigns and plans to various inventory types based on the probability of accurate consumer matching. Consumer matching can be achieved by generation of look-alike models in a consumer'"'"'s device graph to predict future consumption behavior. The system includes an interface through which an advertiser can access relevant information about inventory and success of a given placement.

Claims

1. A method for targeting delivery of advertising content to a first consumer across two or more display devices, the method comprising:

receiving a pricepoint and one or more campaign descriptions from an advertiser, wherein each of the campaign descriptions comprises a schedule for delivery of an item of advertising content across two or more devices accessed by the first consumer, wherein the devices include one or more TV'"'"'s and one or more mobile devices, and a target audience, wherein the target audience is defined by one or more demographic factors;

defining a pool of consumers based on a graph of consumer properties, wherein the graph contains information about the two or more TV and mobile devices used by each consumer, demographic and online behavioral data on each consumer and similarities between pairs of consumers, and wherein the pool of consumers comprises consumers having at least a threshold similarity to a member of the target audience;

receiving a list of inventory from one or more content providers, wherein the list of inventory comprises one or more slots for TV and online;

identifying one or more advertising targets, wherein each of the one or more advertising targets comprises a sequence of slots consistent with one or more of the campaign descriptions, and an overall cost consistent with the pricepoint;

allocating the advertising content of the one or more campaign descriptions to the one or more advertising targets;

purchasing two or more slots of advertising inventory wherein one or more slots are delivered within TV content identified as likely to be viewed by the pool of consumers, and one or more slots are delivered online as a result of a real-time decision;

selecting a first device of a first consumer in the pool of consumers;

instructing a first media conduit to deliver the item of advertising content to the first device of the first consumer in the pool of consumers;

generating a look-alike model based on the pool of consumers;

identifying a second device of a second consumer, wherein the pool of consumers does not include the second consumer;

predicting a future consumption behavior of the second consumer based on the look-alike model;

selecting the second device of the consumer to receive the item of advertising content based on the predicted future consumption behavior of the second consumer;

instructing a second media conduit to deliver the item of advertising content to the second device of the second consumer.

2. The method of claim 1, wherein the purchasing of a slot of online inventory is via real-time bidding.

3. The method of claim 1, wherein the purchasing of a slot in programmatic TV inventory is via a bidding method that utilizes TV viewing data for specific devices.

4. The method of claim 1, further comprising calculating a deduplicated reach based on delivery of the item of advertising content to first device of the first consumer and a third device of the first consumer, and adjusting the advertising targets prior to allocating the advertising content a further time in order to improve the deduplicated reach.

5. The method of claim 1, further comprising calculating a frequency of delivery of advertising content to the first consumer, and suspending further delivery of the advertising content to the first consumer if the frequency of delivery exceeds a threshold number.

6. The method of claim 1, further comprising calculating a cost-based efficiency based on delivery of the item of advertising content to first and second devices, and adjusting the advertising targets prior to allocating the advertising content a further time in order to improve the cost-based efficiency.

7. The method of claim 1, wherein the graph of consumer properties includes a set of seed nodes, wherein generating the look-alike model based on the pool of consumers includes:

identifying the set of seed nodes;

generating a set of look-alike nodes based on a characteristic of the set of seed nodes and a similarity metric; and

generating the look-alike model to include the set of look-alike nodes.

8. The method of claim 7, wherein generating the set of look-alike nodes includes:

identifying one or more vectors associated with a candidate node;

comparing the one or more vectors associated with the candidate node with one or more vectors associated with at least one seed node in the set of seed nodes; and

responsive to determining that the one or more vectors associated with the candidate node is similar to the one or more vectors associated with at least one seed node in the set of seed nodes, selecting the candidate node as a look-alike node.

9. A method of optimizing an advertising campaign across a plurality of devices accessible to a first consumer, the method comprising:

determining that the first consumer is a member of a target audience;

identifying a first and second device accessible to the first consumer, wherein the first and second device comprise a TV and a mobile device, respectively;

receiving instructions for purchase of slots for a first and second item of advertising content on the first and second devices, consistent with an advertising budget and the target audience;

bidding on slots for placement of the first and second items of advertising content, wherein the bidding relies on information about the likely success of a bid based on at least the consumer'"'"'s location, and the time of day;

in the event of successful bids on the first and second items of content, selecting the first device and causing a first media conduit to deliver the first item of advertising content to the first device;

selecting the second device and causing a second media conduit to deliver the second item of advertising content to the second device;

receiving feedback on the consumer'"'"'s response to the first and second items of content;

using the feedback to instruct purchase of further slots for the first and second items of advertising content;

generating a look-alike model based on the feedback;

predicting a future consumption behavior of a second consumer based on the look-alike model; and

instructing a second media conduit to deliver the first item of advertising content to the second device of the second consumer based on the predicted future consumption behavior of the second consumer.

10. The method of claim 9, wherein the determining that the first consumer is a member of a target audience comprises matching behavioral and demographic data on the first consumer from a graph of data to parameters of the target audience.

11. The method of claim 9, wherein the bidding includes bidding on TV inventory selected from:

programmatic TV, linear TV, and video-on-demand content.

12. The method of claim 10, wherein the graph of consumer properties includes a set of seed nodes, wherein generating the look-alike model based on the pool of consumers includes:

identifying the set of seed nodes;

generating a set of look-alike nodes based on a characteristic of the set of seed nodes and a similarity metric; and

generating the look-alike model to include the set of look-alike nodes.

13. The method of claim 12, wherein generating the set of look-alike nodes includes:

identifying one or more vectors associated with a candidate node;

comparing the one or more vectors associated with the candidate node with one or more vectors associated with at least one seed node in the set of seed nodes; and

responsive to determining that the one or more vectors associated with the candidate node is similar to the one or more vectors associated with at least one seed node in the set of seed nodes, selecting the candidate node as a look-alike node.

14. A method, comprising:

identifying a pool of consumers based on a graph of consumer properties, wherein the graph contains information about the two or more devices used by each consumer, demographic and online behavioral data on each consumer, wherein the pool of consumers comprises consumers having at least a threshold similarity to a member of a target audience;

selecting a first device of a first consumer in the pool of consumers;

instructing a first media conduit to deliver an item of advertising content to the first device of the first consumer in the pool of consumers;

generating a look-alike model based on the pool of consumers;

identifying a second device of a second consumer, wherein the pool of consumers does not include the second consumer;

predicting a future consumption behavior of the second consumer based on the look-alike model;

selecting the second device of the consumer to receive the item of advertising content based on the predicted future consumption behavior of the second consumer;

instructing a second media conduit to deliver the item of advertising content to the second device of the second consumer.

15. The method of claim 14, further comprising calculating a deduplicated reach based on delivery of the item of advertising content to first device of the first consumer and a third device of the first consumer, and adjusting advertising targets prior to allocating the advertising content a further time in order to improve the deduplicated reach.

16. The method of claim 14, further comprising calculating a frequency of delivery of advertising content to the first consumer, and suspending further delivery of the advertising content to the first consumer if the frequency of delivery exceeds a threshold number.

17. The method of claim 14, further comprising calculating a cost-based efficiency based on delivery of the item of advertising content to first and second devices, and adjusting an advertising target prior to allocating the advertising content a further time in order to improve the cost-based efficiency.

18. The method of claim 14, wherein the graph of consumer properties includes a set of seed nodes, wherein generating the look-alike model based on the pool of consumers includes:

identifying the set of seed nodes;

generating a set of look-alike nodes based on a characteristic of the set of seed nodes and a similarity metric; and

generating the look-alike model to include the set of look-alike nodes.

19. The method of claim 18, wherein generating the set of look-alike nodes includes:

identifying one or more vectors associated with a candidate node;

comparing the one or more vectors associated with the candidate node with one or more vectors associated with at least one seed node in the set of seed nodes; and

responsive to determining that the one or more vectors associated with the candidate node is similar to the one or more vectors associated with at least one seed node in the set of seed nodes, selecting the candidate node as a look-alike node.

20. The method of claim 14, wherein generating the set of look-alike nodes includes:

inferring a likely attribute of a candidate node; and

responsive to the inference, selecting the candidate node as a look-alike node.