Personalized syllabus generation using sub-concept sequences

An apparatus, comprising:

• at least one processor;
• and
• a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
• computer readable program code configured to receive input identifying a goal of a student, wherein the goal indicates (i) a target concept to be learned by the student and (ii) a desired expertise corresponding to the target concept;
• computer readable program code configured to receive input indicating constraints of the student for reaching the identified goal, wherein the constraints comprise (i) a time budget corresponding to a length of time the student is willing to expend to learn the target concept and (ii) an effort budget corresponding to a level of effort the student is willing to expend to learn the target concept over the length of time;
• computer readable program code configured to identify a base knowledge of the student with respect to the target concept, wherein the base knowledge comprises base knowledge categories each having a base knowledge value;
• and
• computer readable program code configured to generate a syllabus unique to and for the student to reach the identified goal within the indicated constraints in view of the base knowledge of the student with respect to the target concept, wherein the syllabus comprises a sequence of sub-concepts to be learned for reaching the identified goal and a lecture module recommended for learning each of the sub-concepts in the sequence, wherein each lecture module comprises a source for learning a corresponding sub-concept and a degree of hardness for the corresponding sub-concept, wherein the syllabus is generated by:
• producing a plurality of alternative sequences of sub-concepts for reaching the identified goal, each sequence of sub-concepts having both a determined, corresponding (i) effort cost and (ii) time cost, wherein determining the corresponding effort cost and time cost comprises identifying relationships between sub-concepts of one alternative sequence and sub-concepts of another alternative sequence, wherein the identifying the relationships comprises utilizing a machine learning system that is trained using a training set of information comprising historical information from previous students who learned at least sub-concepts of the target concept and makes predictions about new relationships once trained, wherein the producing the plurality of alternative sequences comprises determining concept units included in learning the target concept, determining a relationship between the concept units included in learning the target concept, and generating a knowledge graph comprising a plurality of nodes, each corresponding to one of the concept units and edges, each connecting two of the plurality of nodes and representing a relationship between the connected two of the plurality of nodes;
• and
• determining, from the plurality of alternative sequences of sub-concepts, a particular one of the sequences of sub-concepts that both reaches the target concept at the desired expertise and fulfills the indicated constraints.

A computer program product, comprising:

• a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code executable by a processor and comprising:
• computer readable program code configured to receive input indicating constraints of the student for reaching the identified goal, wherein the constraints comprise (i) a time budget corresponding to a length of time the student is willing to expend to learn the target concept and (ii) an effort budget corresponding to a level of effort the student is willing to expend to learn the target concept over the length of time;
• computer readable program code configured to identify a base knowledge of the student with respect to the target concept, wherein the base knowledge comprises base knowledge categories each having a base knowledge value;
• and
• computer readable program code configured to generate a syllabus unique to and for the student to reach the identified goal within the indicated constraints in view of the base knowledge of the student with respect to the target concept, wherein the syllabus comprises a sequence of sub-concepts to be learned for reaching the identified goal and a lecture module recommended for learning each of the sub-concepts in the sequence, wherein each lecture module comprises a source for learning a corresponding sub-concept and a degree of hardness for the corresponding sub-concept, wherein the syllabus is generated by:
• producing a plurality of alternative sequences of sub-concepts for reaching the identified goal, each sequence of sub-concepts having both a determined, corresponding (i) effort cost and (ii) time cost, wherein determining the corresponding effort cost and time cost comprises identifying relationships between sub-concepts of one alternative sequence and sub-concepts of another alternative sequence, wherein the identifying the relationships comprises utilizing a machine learning system that is trained using a training set of information comprising historical information from previous students who learned at least sub-concepts of the target concept and makes predictions about new relationships once trained, wherein the producing the plurality of alternative sequences comprises determining concept units included in learning the target concept, determining a relationship between the concept units included in learning the target concept, and generating a knowledge graph comprising a plurality of nodes, each corresponding to one of the concept units and edges, each connecting two of the plurality of nodes and representing a relationship between the connected two of the plurality of nodes;
• and
• determining, from the plurality of alternative sequences of sub-concepts, a particular one of the sequences of sub-concepts that both reaches the target concept at the desired expertise and fulfills the indicated constraints.

A method, comprising:

• identifying a target topic to be learned;
• identifying alternative sequences of sub-topics within the target topic, wherein each alternative sequence comprises a plurality of sub-topics that can be learned to learn the target topic and wherein each alternative sequence comprises at least one sub-topic different from at least one another alternative sequence, wherein the identifying the alternative sequences comprises determining concept units included in learning the target topic, determining a relationship between the concept units included in learning the target topic, and generating a knowledge graph comprising a plurality of nodes, each corresponding to one of the concept units and edges, each connecting two of the plurality of nodes and representing a relationship between the connected two of the plurality of nodes;
• learning relationships between sub-topics of one alternative sequence and sub-topics of another alternative sequence, wherein the learned relationships indicate an effort difference between one sub-topic of one alternative sequence and a sub-topic of another alternative sequence, wherein the learning the relationships comprises utilizing a machine learning system that is trained using a training set of information comprising historical information from previous students who learned at least sub-topics of the target topic and makes predictions about new relationships once trained;
• and
• generating, based upon the learned relationships, a recommended course sequence that is within a predetermined effort level, wherein the recommended course sequence comprises (i) one of the alternative sequences of sub-topics (ii) a learning source for learning each of the sub-topics, and (iii) a degree of hardness for learning each of the sub-topics.