Feature generation and model selection for generalized linear models
US-9292550-B2 · Mar 22, 2016 · US
US9679492B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9679492-B2 |
| Application number | US-201314051061-A |
| Country | US |
| Kind code | B2 |
| Filing date | Oct 10, 2013 |
| Priority date | Oct 10, 2013 |
| Publication date | Jun 13, 2017 |
| Grant date | Jun 13, 2017 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An online educational publishing platform generates an effective grade point average for respective users of the platform by aggregating data describing educational activities of the users. The educational activity data includes users' interactions with pages of content distributed by the online educational platform, as well as data retrieved from user profiles of the users and external databases. The educational activity data is filtered into a plurality of categories and scored based on scoring metrics associated with the categories. Using the scored user activity data, the publishing platform generates the effective grade point averages. Each user may have multiple eGPAs whose value depends on how the eGPA was generated. Accordingly, an eGPA provides a quantitative representation of a student's academic engagement, achievements, and experiences.
Opening claim text (preview).
What is claimed is: 1. A method for generating an effective grade point average for users of an online educational platform, the method comprising: receiving data describing educational activities of each of a plurality of users on the online educational platform, the educational activities comprising passive, active, or recall interactions by the plurality of users with pages of content distributed by the online educational platform; filtering the received data into a plurality of categories, each category associated with a weight and a scoring metric for scoring the data associated with the category; scoring the filtered data by the online educational platform using the scoring metric associated with the categories; generating, by the online educational platform, an effective grade point average for each user determined based on a sum of the scores assigned to the data weighted by the weights associated with the categories; detecting a completion of a new educational activity by one of the plurality of users on the online educational platform, the new educational activity comprising a defined set of passive, active, or recall interactions by the user with pages of content distributed by the online educational platform; and responsive to detecting the completion of the new educational activity by the user: receiving data describing the passive, active, or recall interactions by the user with the pages of content; identifying a category of the plurality of categories associated with the new educational activity; scoring the new educational activity using the scoring metric associated with the identified category; recalculating the effective grade point average of the user based on a weighted sum of the generated effective grade point average and the score assigned to the new educational activity weighted based on the weight associated with the identified category; and reporting the recalculated effective grade point average to the user. 2. The method of claim 1 , further comprising: retrieving data describing educational activities of each of the plurality of users from a user profile of the respective user; and scoring the data retrieved from the user profile; wherein generating the effective grade point average for each user further comprises generating the effective grade point average based on the scores of the data retrieved from the user profile. 3. The method of claim 1 , further comprising: retrieving data describing educational activities of each of the plurality of users from external sources; and scoring the data retrieved from the external sources; wherein generating the effective grade point average for each user further comprises generating the effective grade point average based on the scores of the data retrieved from the external sources. 4. The method of claim 1 , further comprising: ranking a set of users applying for a same job through the online educational platform based on the effective grade point average of each of the users in the set; and displaying the ranking to a user in the set of users. 5. The method of claim 1 , further comprising: ranking a set of users applying for a same scholarship through the online educational platform based on the effective grade point average of each of the users in the set; and displaying the ranking to a user in the set of users. 6. The method of claim 1 , wherein the educational activities comprise at least one of reading a document distributed by the online educational platform, creating user-generated content by the online educational platform, and taking a test distributed by the online educational platform. 7. The method of claim 1 , further comprising: filtering the effective grade point averages of the users based on user profile data of the users; and ranking the users corresponding to the effective grade point averages in the filtered set based on the effective grade point averages. 8. The method of claim 7 , wherein the user profile data comprises data selected from a group consisting of a school attended by a user, a major of a user, a graduation year of a user, and a location of a user. 9. The method of claim 1 , wherein recalculating the effective grade point average comprises: applying a time decay factor to the scored data based on an amount of time between completion of respective educational activities corresponding to the scored data and a completion of the new educational activity; and generating the recalculated effective grade point average based on the time decayed data. 10. The method of claim 1 , further comprising: selecting the weight associated with each category based on user profile data of the user; wherein the effective grade point average is recalculated by weighting the data describing the educational activities and the data describing the new educational activity by the selected weights. 11. A non-transitory computer-readable storage medium storing computer program instructions for generating an effective grade point average for users of an online educational platform, the computer program instructions comprising instructions for: receiving data describing educational activities of each of a plurality of users on the online educational platform, the educational activities comprising passive, active, or recall interactions by the plurality of users with pages of content distributed by the online educational platform; filtering the received data into a plurality of categories, each category associated with a weight and a scoring metric for scoring the data associated with the category; scoring the filtered data by the online educational platform using the scoring metric associated with the categories; generating, by the online educational platform, an effective grade point average for each user determined based on a sum of the scores assigned to the data weighted by the weights associated with the categories; detecting a completion of a new educational activity by one of the plurality of users on the online educational platform, the new educational activity comprising a defined set of passive, active, or recall interactions by the user with pages of content distributed by the online educational platform; and responsive to detecting the completion of the new educational activity by the user: receiving data describing the passive, active, or recall interaction by the user with the pages of content; identifying a category of the plurality of categories associated with the new educational activity; scoring the new educational activity using the scoring metric associated with the identified category; recalculating the effective grade point average of the user based on a weighted sum of the generated effective grade point average and the score assigned to the new educational activity weighted based on the weight associated with the identified category; and reporting the recalculated effective grade point average to the user. 12. The non-transitory computer readable storage medium of claim 11 , the computer program instructions further comprising instructions for: retrieving data describing educational activities of each of the plurality of users from a user profile of the respective user; and scoring the data retrieved from the user profile; wherein generating the effective grade point average for each user further comprises generating the effective grade point average based on the scores of the data retrieved from the user profile. 13. The non-transitory computer readable storage medium of claim 11 , the computer program instructions further comprising instructions for: retrieving data describing educational a
Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.