# US 2015/0147741 A1 · Learning system self-optimization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2015/0147741 A1 - Document ID: US20150147741A1 - Status: Published application - Kind: A1 - Application number: 14/089,432 - Filed: 2013-11-25 - Published: 2015-05-28 - Earliest claimed: 2013-11-25 - Assignees: Pearson Education, Inc. - Applicants: Pearson Education, Inc. - Inventors: Perry M. Spagnola - Web page: https://patentgrep.com/patent/US20150147741A1 ## CPC - G09B 7/04: characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question or supplying a further explanation - G09B 7/02: of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student - G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B) ## Abstract A method/system for learning system self-optimization is disclosed. The learning system can include a plurality of learning objects that are connected to each other by a plurality of learning vectors. The learning vectors can identify a prerequisite relationship between the connected learning objects and include data indicating a likelihood of success of a student in traversing the learning vector and/or an expected speed for traversing the learning vector. Data generated from a student's traversal of one of the learning vectors can be used to strengthen or weaken the traversed learning vector based on the student experience. ## Claims ### Claim 1 A method of maintaining a learning vector comprising: identifying on a processor a first learning object, wherein the first learning object comprises a first aggregation of learning content, wherein the aggregation of learning content is associated with an assessment; identifying on the processor a second learning object, wherein the second learning object comprises a second aggregation of learning content, wherein the aggregation of learning content is associated with an assessment; identifying on the processor a prerequisite relationship between the first learning object and the second learning object, wherein the first learning object is a prerequisite to the second learning object; generating on the processor a learning vector connecting the first learning object and the second learning object, the learning vector comprising a direction and a strength, wherein the direction of the learning vector indicates that the first learning object is a prerequisite of the second learning object, and the strength of the learning vector indicates a likelihood of a student successfully traversing the learning vector, wherein the strength of the learning vector varies with respect to a student context, wherein the student context describes an attribute of the student; receiving at the processor an input indicative of the traversal of the learning vector, wherein the input identifies a student property and the effectiveness of the learning vector; determining on the processor a value according to a Boolean function, wherein the value comprises a first value if the input indicative of the traversal of the learning vector indicates a desired outcome and wherein the value comprises a second value if the input indicative of the traversal of the learning vector indicates an undesired outcome, and determining if the student context of the student corresponds to a context of a first at least one student that previously traversed the learning vector if the first value is determined; strengthening the learning vector if the first value is determined and if the student context of the student corresponds to the context of the first at least one student that previously traversed the learning vector. ### Claim 2 (depends on 1) The method of claim 1, further comprising retrieving a success threshold, wherein the success threshold is a value, the attainment of which indicates success or failure in the traversal of the learning vector. ### Claim 3 (depends on 2) The method of claim 2, wherein the success threshold comprises a plurality of thresholds. ### Claim 4 (depends on 3) The method of claim 3, wherein some of the thresholds delineate between successful traversal of the learning vector and unsuccessful traversal of the learning vector with respect to different success metrics. ### Claim 5 (depends on 3) The method of claim 3, wherein the learning object comprises a plurality of content objects, each content object containing a portion of the learning content of the learning object. ### Claim 6 (depends on 5) The method of claim 5, wherein each of the content objects of the learning object is associated with at least one of the some of the plurality of success metrics. ### Claim 7 (depends on 4) The method of claim 4, wherein at least one of the some of the plurality of success metrics is indicative of mastery of the lexile content of the learning object. ### Claim 8 (depends on 4) The method of claim 4, wherein at least one of the some of the plurality of success metrics is an indicator of mastery of the quantile content of the learning object. ### Claim 9 (depends on 4) The method of claim 4, further comprising generating the assessment associated with the second learning object, wherein the assessment comprises a plurality of questions directed to the success metrics. ### Claim 10 (depends on 2) The method of claim 2, wherein determining a value according to a Boolean function further comprises comparing the input indicative of the traversal of the learning vector to the success threshold; and wherein the value is assigned if the comparison of the input indicative of the traversal of the learning vector to the success threshold indicates a successful traversal of the learning vector. ### Claim 11 A method of optimizing a learning vector within a learning object network, the method comprising: identifying on a processor an incident learning object, wherein the incident learning object comprises an initial position of a student within the learning object network; identifying on the processor a plurality of potential terminal learning objects, wherein the potential terminal learning objects each comprise an aggregation of learning content associated with an assessment, and wherein the incident learning object is a prerequisite to each of the potential terminal learning objects; identifying on the processor a plurality of learning vectors, each of the plurality of learning vectors extending from the incident learning object to one of the potential terminal learning objects, wherein each of the plurality of learning vectors indicates the prerequisite relationship with the incident learning object and identifies the strength of the learning vector, wherein the strength of the learning vector varies with respect to a student context, wherein the student context describes an attribute of the student; selecting with the processor one of the plurality of potential terminal learning objects as the terminal learning object; providing the terminal learning object to the student; adding an identifier to memory associating the terminal learning object with the student; receiving at the processor an indicator of the completion of the learning object, wherein the indicator identifies a student property and the effectiveness of the learning vector; determining with the processor a value according to a Boolean function, wherein the value comprises a first value if the indicator of the completion of the learning object indicates a desired outcome and wherein the value comprises a second value if the indicator of the completion of the learning object indicates an undesired outcome, determining if the student context of the student corresponds to a context of at least one student that previously traversed the learning vector if the first value is determined; and adjusting the strength of the learning vector according to the value, wherein the learning vector is strengthened if the value comprises the first value and if the student context of the student corresponds to the context of the at least one student that previously traversed the learning vector. ### Claim 12 (depends on 11) The method of claim 11, further comprising retrieving a success threshold, wherein the success threshold is a value, the attainment of which indicates success or failure in the traversal of the learning vector. ### Claim 13 (depends on 12) The method of claim 12, wherein the success threshold comprises a plurality of thresholds. ### Claim 14 (depends on 13) The method of claim 13, wherein some of the thresholds delineate between successful traversal of the learning vector and unsuccessful traversal of the learning vector with respect to different success metrics. ### Claim 15 (depends on 13) The method of claim 13, wherein the learning object comprises a plurality of content objects, each content object containing a portion of the learning content of the learning object. ### Claim 16 (depends on 15) The method of claim 15, wherein each of the content objects of the learning object is associated with at least one of the some of the plurality of success metrics. ### Claim 17 (depends on 14) The method of claim 14, wherein at least one of the some of the plurality of success outcomes is indicative of mastery of the lexile content of the learning object. ### Claim 18 (depends on 14) The method of claim 14, wherein at least one of the some of the plurality of success outcomes is an indicator of mastery of the quantile content of the learning object. ### Claim 19 (depends on 14) The method of claim 14, further comprising generating the assessment associated with the second learning object, wherein the assessment comprises a plurality of questions directed to the success metrics. ### Claim 20 (depends on 12) The method of claim 12, wherein determining a value according to a Boolean function further comprises comparing the input indicative of the traversal of the learning vector to the success threshold; and wherein the value is assigned if the comparison of the input indicative of the traversal of the learning vector to the success threshold indicates a successful traversal of the learning vector ### Claim 21 (depends on 1) The method of claim 1, wherein the first at least one student that previously traversed the learning vector successfully traversed the learning vector. ### Claim 22 (depends on 1) The method of claim 1, further comprising: determining if the student context corresponds to the student context of a second at least one student that previously traversed the learning vector if the second value is determined; and weakening the learning vector if the second value is determined and if the student context of the student corresponds to the context of the second at least one student that previously traversed the learning vector. ### Claim 23 (depends on 22) The method of claim 22, wherein the second at least one student that previously traversed the learning vector unsuccessfully traversed the learning vector. ### Claim 24 (depends on 1) The method of claim 1, further comprising updating the student context to strengthen the identification of a student learning style indicated in the student context and matching the learning style indicated in the context of the first at least one student that previously traversed the learning vector if the first value is determined and if the student context of the student corresponds to the context of the first at least one student that previously traversed the learning vector. ### Claim 25 (depends on 11) The method of claim 11, wherein the first at least one student that previously traversed the learning vector successfully traversed the learning vector. ### Claim 26 (depends on 11) The method of claim 11, further comprising: determining if the student context corresponds to the student context of a second at least one student that previously traversed the learning vector if the second value is determined; and weakening the learning vector if the second value is determined and if the student context of the student corresponds to the context of the second at least one student that previously traversed the learning vector. ### Claim 27 (depends on 26) The method of claim 26, wherein the second at least one student that previously traversed the learning vector unsuccessfully traversed the learning vector. ### Claim 28 (depends on 11) The method of claim 11, further comprising updating the student context to strengthen the identification of a student learning style indicated in the student context and matching the learning style indicated in the context of the first at least one student that previously traversed the learning vector if the first value is determined and if the student context of the student corresponds to the context of the first at least one student that previously traversed the learning vector.