Advertisement selection

A method comprising:

• receiving advertisements;
• storing the advertisements;
• storing information including at least one of the following:
• information about an 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 a tree-type decision model, the 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 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 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 tree-type decision model;
• evaluating each of the paths of the 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.

An end user rendering system comprising:

• an advertisement database configured to receive and store advertisements associated with advertising campaigns;
• a state database storing 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;
• a decision model optimization module configured to:
• receive a tree-type decision model, the 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 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, and
• optimize the 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 tree type decision model;
• an advertisement decision module configured to:
• receive opportunity tags, where each opportunity tag identifies the location of an advertising opportunity in streamed video from a remote broadcast system and provides information on advertising opportunities;
• evaluate each of the paths of the optimized tree type decision model using the received 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;
• identify the paths where all the targeting criteria are satisfied in the evaluation of the paths;
• and
• 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;
• and
• a rendering module configured to receive a video stream from a broadcast system and 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.

A method of rendering advertisements at an end user rendering system, the method comprising:

• receiving and storing advertisements associated with advertising campaigns in a database;
• storing state 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;
• receiving a tree-type decision model, the 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 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;
• optimizing the 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 tree type decision model;
• receiving 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;
• evaluating each of the paths of the 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;
• identifying the paths where all the targeting criteria are satisfied in the evaluation of the paths;
• selecting 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;
• receiving a video stream from a broadcast system;
• and
• rendering 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.

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, the code comprising:

• code for controlling the computer to receive and storing advertisements associated with advertising campaigns in a database;
• code for controlling the computer to store state 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 a tree-type decision model, the 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 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 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 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 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.

An advertisement selection system comprising:

• a broadcast system for broadcasting advertisements to at least one end user system, the broadcast system comprising a decision model generating module configured to:
• generate a tree-type decision model, the 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 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, and
• globally optimize the tree type decision model based on information stored at the at least one end user system, such that the paths having at least one of the decision nodes where the targeting criteria are not satisfied when evaluated with the information are removed from the tree type decision model;
• at least one end user system comprising a decision model optimization module configured to:
• receive the globally optimized tree-type decision model, and
• locally optimize the tree type decision model based on information stored in the end user system such that the paths having at least one of the decision nodes where the targeting criteria are not satisfied when evaluated with the information are removed from the tree type decision model.

An advertisement selection method comprising:

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

An end user rendering system comprising:

• a decision model optimization module configured to:
• receive a tree-type decision model, the 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 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 tree-type decision model based on information on the end user rendering system or a user 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 tree-type decision model;
• an advertisement decision module to:
• evaluate each of the paths of the 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
• a rendering module to render the at least one advertisement of the selected advertising campaign.

An end user rendering method comprising:

• receiving a tree-type decision model, the 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 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 tree-type decision model based on information on the end user rendering system or a user 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 tree-type decision model;
• evaluating each of the paths of the 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.