Neural networking system and methods
AssigneePearson Education, Inc.
InventorPerry M. Spagnola
Life of this patent
Estimating the term…
Abstract
A method/apparatus/system for generating a request for improvement of a data object in a neural network is described herein. The neural network contains a plurality of data objects each made of an aggregation of content. The data objects of the neural network are interconnected based on one or several skill levels embodied in the content of the data objects via a plurality of connecting vectors. These connecting vectors can be generated and/or modified based on data collected from the iterative transversal of the connecting vectors by one or several users of the neural network.
Claims20
A machine learning system for generating a request for improvement of a data object in a neural network, the system comprising:
- a database server comprising:
- a plurality of data objects comprising an aggregation of content associated with an assessment, wherein the plurality of data objects are included in a neural network;
- information associated with the data objects and identifying an aspect of the therewith associated data object;
- a supervisor device configured to remotely access the database server and to edit one or several of the plurality of data objects;
- a content management server configured to:
- identify a set of the plurality of data objects;
- output a query requesting information relating to at least one of the set of the plurality of data objects from the database server;
- identify a plurality of connecting vectors, wherein each of the plurality of connecting vectors connects two of the set of the plurality of data objects in a prerequisite relationship, wherein each of the plurality of connecting vectors comprises a direction identifying the hierarchy of the prerequisite relationship and a magnitude, wherein the magnitude of at least one of the plurality of connecting vector is the aggregate of binary indicators based on a user experience with the at least one of the plurality of connecting vectors generated via machine learning from iterated traversals of the connecting vector;
- determine a deficiency in the content of at least one of the data objects based on the magnitude of at least one connecting vector of the at least one of the data objects;
- and
- alert the supervisor device to trigger modification of the at least one of the data objects having a determined deficiency.
A method of generating a request for improvement of a data object in a neural network, the method comprising:
- identifying a plurality of data objects stored in at least one database, wherein each of the data objects comprises an aggregation of content associated with an assessment, wherein the plurality of data objects are included in a neural network;
- identifying a plurality of connecting vectors stored in at least one vector database, wherein each of the plurality of connecting vectors connects two of the plurality of data objects and identifies a prerequisite relationship between the connected two of the plurality of data objects, wherein each of the plurality of connecting vectors comprises a direction identifying the prerequisite relationship and a magnitude, wherein the magnitude of at least one of the plurality of connecting vector is the aggregate of binary indicators based on a user experience with the at least one of the plurality of connecting vectors generated via machine learning from iterated traversals of the connecting vector;
- and
- determining a deficiency in the content of at least one of the data objects based on the magnitude of at least one connecting vector of the at least one of the data objects.
Dependencies are inferred from the claim text.