Back to results
US 10,650,692 B2Granted
Entropy-based sequences of educational modules
AssigneePearson Education, Inc.
InventorRandall Barnhart
Life of this patent
Estimating the term…
Abstract
Techniques disclosed herein can determine sequences for educational units by evaluating entropies of multiple potential sequences and biasing selection of next units towards those associated with high sequence entropies. Further, an analysis can determine which units are under-represented (relative to a target proportion) in a past sequence and bias towards inclusion of an under-represented unit in the sequence. The available units that are considered for potential selection can include those matched to a learner's skill (e.g., such that all pre-requisite units have been mastered but the unit itself has not been mastered). Thus, techniques can generate sequences of units that promote unit variation and nonetheless conform to relative unit frequencies and skill level appropriateness.
Claims20
A system, comprising:
- a database coupled to a network and storing:
- a plurality of past sequences of educational software content objects, each associated with a file type;
- and
- a plurality of educational-item file types;
- a first client user device coupled to a network, and running a software application receiving, from a user interface, at least one user input including:
- a set of educational software content objects;
- and
- a target proportion of the file type within the set of educational software content objects;
- a server comprising a computing device coupled to the network and including at least one processor executing within a memory instructions which, when executed, cause the system to:
- receive, from the first client user device, the set of educational software content objects and the target proportion;
- determine, according to at least one characteristic of each of the set of educational software content objects, the file type;
- automatically generate a metadata identifying a file type identifier for each educational software content object in the set of educational software objects;
- select a past sequence from the plurality of past sequences within the database;
- identify, within the past sequence, a series of file type identifiers;
- calculate a score for selecting an educational-item file type from a set of educational-item file types by:
- generating a potential sequence that automatically appends the file type identifier to the past sequence;
- determining an entropy of the potential sequence;
- and
- determining a total number of the file type identifier in the past sequence or the potential sequence;
- select the educational-item file type from the set of educational-item file types in the database, according to the score;
- append the educational-item file type to the past sequence;
- identify, within the set of educational software content objects, a plurality of educational software content objects including the metadata matching the educational-item file type;
- select, using a random number generator, an educational software content object from the plurality of educational software content objects in the database;
- determine a sequence of previously presented educational content software objects on a second client user device to a user operating the second client user device;
- and
- transmit the educational software content object selected by the server to the second client user device for display on the second user device.
23 more elements
A system, comprising:
- a server comprising a computing device coupled to a network and including at least one processor executing within a memory instructions which, when executed, cause the system to:
- receive, from the first client user device coupled to the network:
- a set of educational software content objects;
- and
- a target proportion of a file type within the set of educational software content objects;
- determine, according to at least one characteristic of each of the set of educational software content objects, the file type;
- automatically generate a metadata identifying a file type identifier for each educational software content object in the set of educational software objects;
- select a past sequence from a plurality of past sequences of educational software content objects, each associated with a file type, and stored within a database coupled to the network;
- identify, within the past sequence, a series of file type identifiers;
- calculate a score for selecting an educational-item file type from a plurality of educational-item file types stored in the database by:
- generating a potential sequence that automatically appends the file type identifier to the past sequence;
- determining an entropy of the potential sequence;
- and
- determining a total number of the file type identifier in the past sequence or the potential sequence;
- select the educational-item file type from the set of educational-item file types in the database, according to the score;
- append the educational-item file type to the past sequence;
- identify, within the set of educational software content objects, a plurality of educational software content objects including the metadata matching the educational-item file type;
- select, using a random number generator, an educational software content object from the plurality of educational software content objects in the database;
- determine a sequence of previously presented educational content software objects on a second client user device to a user operating the second client user device;
- and
- transmit the educational software content object selected by the server to the second client user device for display on the second user device.
18 more elements
A method, comprising the steps of:
- receiving, by a server comprising a computing device coupled to a network and including at least one processor executing within a memory instructions, from the first client user device coupled to the network:
- a set of educational software content objects;
- and
- a target proportion of a file type within the set of educational software content objects;
- determining, by the server, according to at least one characteristic of each of the set of educational software content objects, the file type;
- automatically generating, by the server, a metadata identifying a file type identifier for each educational software content object in the set of educational software objects;
- selecting, by the server, a past sequence from a plurality of past sequences of educational software content objects, each associated with a file type, and stored within a database coupled to the network;
- identifying, by the server, within the past sequence, a series of file type identifiers;
- calculating, by the server a score for selecting an educational-item file type from a plurality of educational-item file types stored in the database by:
- generating a potential sequence that automatically appends the file type identifier to the past sequence;
- determining an entropy of the potential sequence;
- and
- determining a total number of the file type identifier in the past sequence or the potential sequence;
- selecting, by the server, the educational-item file type from the set of educational-item file types in the database, according to the score;
- appending, by the server, the educational-item file type to the past sequence;
- identifying, by the server, within the set of educational software content objects, a plurality of educational software content objects including the metadata matching the educational-item file type;
- selecting, by the server using a random number generator, an educational software content object from the plurality of educational software content objects in the database;
- determining, by the server, a sequence of previously presented educational content software objects on a second client user device to a user operating the second client user device;
- and
- transmitting, by the server, the educational software content object selected by the server to the second client user device for display on the second user device.
17 more elements
Dependencies are inferred from the claim text.