Advertisement selection

• US 8,656,426 B2
• Filed: 04/12/2010
• Issued: 02/18/2014
• Est. Priority Date: 09/02/2009
• Status: Active Grant

• Current Assignee: Synamedia Limited
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Leigh, Tony, Shelton, Ian R., Whinmill, Trevor, Ahmed, Martin, Martin, Christopher, Wilson, James, Dyke, Simon, Spencer, Matt
• Primary Examiner(s): Sterrett, Jonathan G
• Assistant Examiner(s): Swartz, Stephen S
• Application Number:
  US13/138,984
• Publication Number:
  US 20120072282A1
• Time in Patent Office: 1,408 Days
• Field of Search: 705/14.49, 725/32, 725/34, 725/46
• US Class Current: 725/34
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: H04N 21/262 Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists scheduling strategies for dispatcher in multiprogramming arrangements G06F9/4881; arrangements for scheduling broadcast services or broadcast-related services H04H60/06; flow control in packet networks H04L47/10; establishing a time schedule or organising the servicing of application requests H04L67/62
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

An end-user rendering system including an advertisement database to receive advertisements, and store the advertisements therein, a state database to store information, a decision model optimization module to receive a tree-type decision model and optimize the tree-type decision model based on at least some of the information stored in the state database, an advertisement decision module to evaluate the optimized tree-type decision model and select an advertising campaign, the selected advertising campaign having at least one advertisement, and a rendering module to render the at least one advertisement of the selected advertising campaign. Related apparatus and methods are also described.

Claims

1. An end-user rendering system in an environment comprising a broadcast Headend and a plurality of other end-user rendering systems, the broadcast Headend being operative to globally optimize a tree-type decision model and send the globally optimized tree-type decision model to the end-user rendering system and the other end-user rendering systems for local optimization, the end-user rendering system including computer processing machinery to:

receive advertisements;

store the advertisements in an advertisement database;

store, in a state database, information including at least one of the following;

information about the end-user rendering system, information about a display device operationally connected to the end-user rendering system, information about a user of the end-user rendering system, a history of the advertisements previously rendered by the end-user rendering system;

receive the globally optimized tree-type decision model at the end-user rendering system from the broadcast Headend for local optimization at the end-user rendering system, the globally optimized tree-type decision model enabling selection of at least one advertising campaign from a plurality of advertising campaigns based on evaluating a collection of targeting criteria, each one of the advertising campaigns having at least one of the targeting criteria which must be fulfilled for the one advertising campaign to be selected, at least some of the advertising campaigns having at least one of the targeting criteria in common, the globally optimized tree-type decision model including a plurality of paths emerging from a root node via a plurality of decision nodes terminating in a plurality of terminal nodes, the terminal nodes representing the advertising campaigns for selection and the decision nodes representing the targeting criteria so that for each one of the paths, the one path includes the at least one targeting criterion of the one advertising campaign terminating the one path, the at least some advertising campaigns having the at least one targeting criterion in common sharing at least one of the decision nodes; and

optimize the globally optimized tree-type decision model in the end-user rendering system, yielding a locally optimized tree-type decision model, based on at least some of the information stored in the state database such that the paths having at least one of the decision nodes where the targeting criteria are not satisfied when evaluated with the at least some information are removed from the globally optimized tree-type decision model;

evaluate each of the paths of the locally optimized tree-type decision model by evaluating the targeting criteria of at least one of the decision nodes in a direction from the root node to the terminal nodes;

identify the paths where all the targeting criteria are satisfied in the evaluation of the paths; and

select an advertising campaign from the advertising campaigns of the terminal nodes of the identified paths, the selected advertising campaign having at least one advertisement; and

render the at least one advertisement of the selected advertising campaign.

2. The system according to claim 1, wherein the at least some information evaluated in order to yield the locally optimized tree-type decision model are static factors which do not change at least until a new globally optimized tree-type decision model is received.

3. The system according to claim 1, wherein the computer processing machinery is operative to optimize the globally optimized tree-type decision model for at least one of the advertising campaigns that has reached a maximum number of impressions by removing the paths including the at least one advertising campaign from the globally optimized tree-type decision model.

4. The system according to claim 1, wherein:

each of the paths has a priority-rating; and

the computer processing machinery is operative to select the advertising campaign from a highest priority-rating path of the identified paths.

5. A method in an environment comprising a broadcast Headend, an end-user rendering system and a plurality of other end-user rendering systems, the broadcast Headend being operative to globally optimize a tree-type decision model and send the globally optimized tree-type decision model to the end-user rendering system and the other end-user rendering systems for local optimization, the method including the end-user rendering system performing the following steps with computer processing machinery:

receiving advertisements;

storing the advertisements in an advertisement database;

storing, in a state database, information including at least one of the following;

information about the end-user rendering system, information about a display device operationally connected to the end-user rendering system, information about a user of the end-user rendering system, a history of the advertisements previously rendered by the end-user rendering system;

receiving the globally optimized tree-type decision model at the end-user rendering system from the broadcast Headend for local optimization at the end-user rendering system, the globally optimized tree-type decision model enabling selection of at least one advertising campaign from a plurality of advertising campaigns based on evaluating a collection of targeting criteria, each one of the advertising campaigns having at least one of the targeting criteria which must be fulfilled for the one advertising campaign to be selected, at least some of the advertising campaigns having at least one of the targeting criteria in common, the globally optimized tree-type decision model including a plurality of paths emerging from a root node via a plurality of decision nodes terminating in a plurality of terminal nodes, the terminal nodes representing the advertising campaigns for selection and the decision nodes representing the targeting criteria so that for each one of the paths, the one path includes the at least one targeting criterion of the one advertising campaign terminating the one path, the at least some advertising campaigns having the at least one targeting criterion in common sharing at least one of the decision nodes;

optimizing the globally optimized tree-type decision model in the end-user rendering system, yielding a locally optimized tree-type decision model, based on at least some of the stored information such that the paths having at least one of the decision nodes where the targeting criteria are not satisfied when evaluated with the at least some information are removed from the globally optimized tree-type decision model;

evaluating each of the paths of the locally optimized tree-type decision model by evaluating the targeting criteria of at least one of the decision nodes in a direction from the root node to the terminal nodes;

identifying the paths where all the targeting criteria are satisfied in the evaluation of the paths;

selecting an advertising campaign from the advertising campaigns of the terminal nodes of the identified paths, the selected advertising campaign having at least one advertisement; and

rendering the at least one advertisement of the selected advertising campaign.

6. A non-transient storage medium storing computer program code for controlling a computer to implement a method of rendering advertisements at an end user rendering system in an environment including a broadcast Headend, an end-user rendering system and a plurality of other end-user rendering systems, the broadcast Headend being operative to globally optimize a tree-type decision model and send the globally optimized tree-type decision model to the end-user rendering system and the other end-user rendering systems for local optimization, the code comprising:

code for controlling the computer to receive and store advertisements associated with advertising campaigns in an advertisement database;

code for controlling the computer to store, in a state database, information comprising at least one of;

information about the end user rendering system, information about a display device operationally connected to the end user rendering system, information about a user of the end user rendering system, and a history of the advertisements previously rendered by the end user rendering system;

code for controlling the computer to receive the globally optimized tree-type decision model at the end-user rendering system from the broadcast Headend for local optimization at the end-user rendering system, the globally optimized tree-type decision model enabling selection of at least one advertising campaign from a plurality of advertising campaigns based on evaluating a collection of targeting criteria, each one of the advertising campaigns having at least one of the targeting criteria which must be fulfilled for the one advertising campaign to be selected, at least some of the advertising campaigns having at least one of the targeting criteria in common, the globally optimized tree type decision model including a plurality of paths emerging from a root node via a plurality of decision nodes terminating in a plurality of terminal nodes, the terminal nodes representing the advertising campaigns for selection and the decision nodes representing the target criteria so that for each one of the paths, the one path includes the at least one target criterion of the one advertising campaign terminating the one path, the at least some advertising campaigns having the at least one targeting criterion in common sharing at least one of the decision nodes;

code for controlling the computer to optimize the globally optimized tree type decision model in the end-user rendering system, yielding a locally optimized tree-type decision model, based on at least some of the stored state information such that the paths having at least one of the decision nodes where the targeting criteria are not satisfied when evaluated with the at least some information are removed from the globally optimized tree type decision model;

code for controlling the computer to receive opportunity tags, each opportunity tag identifying the location of advertising opportunities in streamed video from a remote broadcast system and providing information on advertising opportunities;

code for controlling the computer to evaluate each of the paths of the locally optimized tree type decision model using the received opportunity tags to evaluate the targeting criteria of at least one of the decision nodes in a direction from the root node to the terminal nodes;

code for controlling the computer to identify the paths where all the targeting criteria are satisfied in the evaluation of the paths;

code for controlling the computer to select an advertising campaign for each opportunity tag from the advertising campaigns of the terminal nodes of the identified paths and in dependence upon the advertising opportunity, the selected advertising campaign having at least one advertisement associated therewith;

code for controlling the computer to receive a video stream from a broadcast system; and

code for controlling the computer to render the at least one advertisement of the selected advertising campaign for each opportunity tag at the location in the video stream identified in the respective opportunity tag for display to the user.