发明名称 NETWORK-PROBABILITY RECOMMENDATION SYSTEM
摘要 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.
申请公布号 US2015006454(A1) 申请公布日期 2015.01.01
申请号 US201313932356 申请日期 2013.07.01
申请人 Pearson Education, Inc. 发明人 SUPANC Patrick M.;MARTELLO Pedro;MILLS James;LARUSSON Johann A.;LEWIS Robyn L.
分类号 G06N3/08 主分类号 G06N3/08
代理机构 代理人
主权项 1. A method of generating an individual network-probability based educational path comprising: receiving electronic inputs requesting a recommendation for a user; receiving electronic inputs identifying a user position within a learning network, the learning network comprising a plurality of interconnected nodes identifying learning objectives, wherein the user position comprises the node at which the user is currently located within the learning network, and wherein the nodes are interconnected via a prerequisite relationship, a plurality of the nodes comprising: a task; anda relationship indicator identifying a prerequisite node; retrieving a bounding rule, wherein the bounding rule defines a maximum degree of included removal from the identified position within the learning network; identifying included nodes, wherein included nodes are within the bounding rule; adding an indicator of inclusion to included nodes; retrieving an indicator of node completion status for included nodes, wherein the indicator of node completion status indicates according to a boolean-function whether the user has completed the node; identifying completed nodes; retrieving user node information for completed nodes, wherein the user node information identifies an attribute of user interaction with the completed node; calculating a likelihood of user success for uncompleted included nodes, wherein the likelihood of user success is the likelihood that the user will successfully complete a node, wherein the calculation of the likelihood of user success is based on the retrieved user node information; comparing the likelihoods of user success; and recommending a next node based on the comparison of the likelihoods of user success.
地址 Upper Saddle River NJ US