Network-probability recommendation system

Abstract

A method/apparatus/system for generating a recommendation based on user interactions with nodes and associated tasks within a prerequisite graph. The recommendation is generated by identifying the user's current position within the prerequisite graph and identifying potential next nodes to which the user could move. Based on the user's past interactions with nodes and/or tasks within the prerequisite graph, the user's likelihood of successfully completing the potential next node is calculated, and a recommendation is made based on this calculated likelihood of the user successfully completing the potential next node.

What is claimed is: 
     
         1 . A method of generating an educational path comprising:
 identifying a location of a user at a node within a learning network comprising a plurality of nodes;   retrieving a bounding rule defining a maximum degree of inclusion from the identified location;   calculating a likelihood of the user successfully completing nodes within the bounding rule; and   recommending a next node based on the likelihoods of the user successfully completing nodes within the bounding rule.   
     
     
         2 . The method of  claim 1 , wherein the bounding rule comprises a Markov blanket. 
     
     
         3 . The method of  claim 1 , wherein the plurality of nodes are interconnected via a prerequisite relationship. 
     
     
         4 . The method of  claim 3 , wherein the bounding rule comprises a first rule applicable to prerequisite nodes of the node of the user location and a second rule applicable to nodes for which the node of the user location is a prerequisite. 
     
     
         5 . The method of  claim 3 , wherein the likelihood of the user successfully completing nodes within the bounding rule is based on user interaction with completed nodes, wherein user interaction with completed nodes comprises:
 a number of completed tasks within the identified location of the user;   a number of completed learning activities;   an amount of time user spent on the identified location of the user;   a user score for a practice activity; and   a user score for a challenge activity.   
     
     
         6 . The method of  claim 5 , wherein the likelihood of the user successfully completing nodes is further calculated based on the completion status of prerequisites for a node. 
     
     
         7 . The method of  claim 5 , wherein calculating the likelihood of the user successfully completing nodes within the bounding rule comprises:
 selecting an uncompleted node within the bounding rule;   identifying prerequisite nodes of the selected uncompleted node;   retrieving information comprising node information for the prerequisite nodes;   applying a probability function to the retrieved information; and   applying a probability indicator based on the application of the probability function to the retrieved information to the uncompleted node.   
     
     
         8 . The method of  claim 3 , wherein the likelihood of the user successfully completing nodes is calculated only for nodes for which the node of the user location is a prerequisite. 
     
     
         9 . The method of  claim 1 , further comprising: identifying one or several nodes included within the bounding rule; and retrieving an indicator of completion status for nodes within the bounding rule. 
     
     
         10 . The method of  claim 9 , wherein identifying one or several nodes included within the bounding rule comprises:
 selecting the node of the user location as a starting node;   identifying connected nodes that are connected with the starting node;   comparing the connected nodes to the bounding rule; and   adding an indicator of node status to each of the identified connected nodes.   
     
     
         11 . A system for generating an individual network-probability based educational path, the system comprising:
 one or more hardware servers programmed for:
 identify a location of a user at a node within a learning network comprising a plurality of nodes; 
 retrieving a bounding rule defining a maximum degree of inclusion from the identified location; 
 calculating a likelihood of the user successfully completing nodes within the bounding rule; and 
 recommending a next node based the likelihoods of the user successfully completing nodes within the bounding rule. 
   
     
     
         12 . The system of  claim 11 , wherein the bounding rule comprises a Markov blanket. 
     
     
         13 . The system of  claim 11 , wherein the plurality of nodes are interconnected via a prerequisite relationship. 
     
     
         14 . The system of  claim 13 , wherein the bounding rule comprises a first rule applicable to prerequisites nodes of the node of the user location and a second rule applicable to nodes for which the node of the user location is a prerequisite. 
     
     
         15 . The system of  claim 13 , wherein the likelihood of the user successfully completing nodes within the bounding rule is based on user interaction with completed nodes, wherein the user interaction with completed nodes comprises at least one of:
 a number of completed tasks within the identified location of the user;   a number of completed learning activities;   an amount of time user spent on the identified location of the user;   a user score for a practice activity; and   a user score for a challenge activity.   
     
     
         16 . The system of  claim 15 , wherein the likelihood of the user successfully completing nodes is further calculated based on the completion status of prerequisites for a node. 
     
     
         17 . The system of  claim 15 , wherein calculating the likelihood of the user successfully completing nodes within the bounding rule comprises:
 selecting an uncompleted node within the bounding rule;   identifying prerequisite nodes of the selected uncompleted node;   retrieving information comprising node information for the prerequisite nodes;   applying a probability function to the retrieved information; and   applying a probability indicator based on the application of the probability function to the retrieved information to the uncompleted node.   
     
     
         18 . The system of  claim 12 , wherein the likelihood of the user successfully completing nodes is calculated only for nodes for which the user location is a prerequisite. 
     
     
         19 . The system of  claim 12 , wherein the likelihood of the user successfully completing nodes is calculated for both nodes for which the user location is a prerequisite and for nodes for which the identified user location is not a prerequisite. 
     
     
         20 . The system of  claim 19 , wherein identifying one or several nodes included within the bounding rule comprises:
 selecting the node of the user location as a starting node;   identifying connected nodes that are connected with the starting node;   comparing the connected nodes to the bounding rule; and   adding an indicator of node status to each of the identified connected nodes.