Dynamic skill-based content recommendations

• US 9,680,945 B1
• Filed: 06/12/2014
• Issued: 06/13/2017
• Est. Priority Date: 06/12/2014
• Status: Active Grant

• Current Assignee: Audible Incorporated (Amazon.com, Inc.)
• Original Assignee: Audible Incorporated (Amazon.com, Inc.)
• Inventors: Story, Jr., Guy Ashley, Treves, Dikla, Shanahan, Francis Andrew, Stringer, Lisa Marie, Sagar, Aman, Girdhar, Puneet, Rothstein, Jodi
• Primary Examiner(s): Whipple, Brian
• Application Number:
  US14/303,540
• Time in Patent Office: 1,097 Days
• Field of Search: None
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G09B 7/04 characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Systems and methods are disclosed enabling recommendations of content items based on a difficulty of the content item as well as a skill level of the user. Skill-based content recommendations may be utilized, for example, in recommending content to language learners. Skill-based recommendations may be based on a variety of difficulty metrics of the content item, such as vocabulary and complexity of the language (e.g., words per paragraph, syllables per word, etc.), as well as a variety of skill metrics of the user (e.g., as explicitly provided by the user or implicitly determined based on a user'"'"'s interaction with content items). Advantageously, such metrics can enable generation of recommendations based on a multi-dimensional difficulty assessment. Further, difficulty metrics, skill metrics, or the relationship between such metrics may be dynamically updated over time based on continued feedback from users, such that recommendations are dynamically improved.

Claims

1. A system to generate recommendations of content items, the system comprising:

a non-volatile data store including information regarding a plurality of content items, the information including, for a content item of the plurality of content items, a difficulty level representing a difficulty of users in consuming the content item; and

a processor in communication with the non-volatile data store and configured with computer-executable instructions that, when executed by the processor, cause the processor to;

receive a request from a computing device of a user for a recommendation;

select the content item from the plurality of content items based at least in part on a comparison of the difficulty level of the content item and a skill level of the user, wherein the skill level of the user is determined based at least in part on a previous consumption of another content item by the user;

transmit a recommendation for the content item to the computing device of the user;

receive, from the computing device of the user, interaction information determined from monitoring interaction of the user with the computing device, wherein the interaction includes a number of page turns of the content item, and wherein the interaction information includes an indication of a speed at which the user consumes the content item based at least in part on the number of page turns;

determine, based at least in part on the interaction information, a user-specific difficulty of the content item for the user;

modify the difficulty level of the content item based at least in part on the interaction information and the skill level of the user to form a modified difficulty level of the content item;

store the modified difficulty level of the content item in the non-volatile data store; and

select the content item as a recommended content item for a second user based at least in part on the modified difficulty level of the content item.

2. The system of claim 1, wherein the content item comprises at least one of an audiobook, an electronic book, or a video.

3. The system of claim 1, wherein the computer-executable instructions further cause the processor to modify the skill level of the user based at least in part on the interaction information.

4. The system of claim 1, wherein the interaction information further includes at least one of a total duration spent consuming the content item, an average session length of a user in consuming the content item, a frequency at which portions of the content item are repeated by the user, a set of words within the content item for which definitions are viewed by the user, a frequency at which definitions for words within the content item are viewed by the user, whether one or more portions of the content item are highlighted or selected by the user, whether the user completes the content item, or whether the user recommends the content item to other users.

5. The system of claim 1, wherein the difficulty level of the content item is determined based at least in part on a plurality of difficulty metrics.

6. The system of claim 5, wherein the difficulty level of the content item is determined based at least in part on a weighting of the plurality of difficulty metrics.

7. The system of claim 5, wherein the plurality of difficulty metrics include at least one of a format of the content item, vocabulary of the content item, an average number of words per sentence within the content item, an average number of syllables per word within the content item, or an average difficulty rating of the content item by other users.

8. A method for providing content recommendations, the method comprising:

receiving a request from a computing device of a user for a recommendation;

determining, for a first content item, a difficulty level representing a difficulty of users in consuming the first content item;

determining, for a second content item, a difficulty level representing a difficulty of users in consuming the second content item;

selecting a content item from the first content item and the second content item based at least in part on a comparison of the difficulty level of the content item and a skill level of the user;

transmitting a recommendation of the content item to the computing device of the user;

receiving, from the computing device of the user, interaction information that includes an indication of a speed at which the user consumes the content item based at least in part on a number of page turns of the content item;

determining, based at least in part on the interaction information, a user-specific difficulty of the content item for the user;

modifying the difficulty level of the content item based at least in part on the interaction information and the skill level of the user to form a modified difficulty level of the content item; and

selecting the content item as a recommended content item for a second user based at least in part on the modified difficulty level of the content item.

9. The method of claim 8 further comprising determining the skill level of the user based at least in part on a plurality of skill metrics.

10. The method of claim 9, wherein the plurality of skill metrics include at least one of an average speed at which the user consumes content items, an average length of time a user takes in consuming content items, a frequency at which portions of content items are repeated by the user, an average difficulty of vocabulary within content items consumed by the user, a frequency at which definitions for words are viewed by the user, or an average rate of completion of content items by the user.

11. The method of claim 10 further comprising modifying at least one of the plurality of skill metrics based on the interaction information.

12. The method of claim 8, wherein the difficulty level of the content item is based at least in part on feedback regarding the content item received from a plurality of users.

13. The method of claim 8, wherein the difficulty level of the content item is based at least in part on analyzing the content of the content item.

14. The method of claim 8, wherein the difficulty level of the content item is based at least in part on a difficulty level of other content items similar to the content item.

15. The method of claim 8, wherein the content item is selected based at least in part on preferences of the user.

16. The method of claim 8, wherein the interaction information further indicates at least one of:

a length of time that the content item is consumed, or a request to view a definition of a word appearing in the content item.

17. The method of claim 8 further comprising, prior to selecting the content item as the recommended content item for the second user, performing a comparison of the modified difficulty level of the content item and a skill level of the second user, wherein the content item is selected as the recommended content item based at least in part on the comparison.

18. A computer-readable non-transitory storage medium including computer-executable instructions that, when executed by a processor, cause the processor to:

receive a request from a computing device of a user for a recommendation;

determine, for a first content item, a difficulty level representing a difficulty of users in consuming the first content item;

determine, for a second content item, a difficulty level representing a difficulty of users in consuming the second content item;

select a content item from the first content item and the second content item based at least in part on a comparison of the difficulty level of the content item and a skill level of the user in consuming the content item;

transmit a recommendation of the content item to the computing device of the user;

receive, from the computing device of the user, interaction information that includes an indication of a speed at which the user consumes the content item based at least in part on a number of page turns of the content item;

determine, based at least in part on the interaction information, a user-specific difficulty of the content item for the user;

modify the difficulty level of the content item based at least in part on the interaction information to form a modified difficulty level of the content item; and

select the content item as a recommended content item for a second user based at least in part on the modified difficulty level of the content item.

19. The computer-readable, non-transitory storage medium of claim 18, wherein the difficulty level of the content item is determined based at least in part on a plurality of difficulty metrics.

20. The computer-readable, non-transitory storage medium of claim 19, wherein the difficulty level of the content item is determined based at least in part on at least one of a linear or non-linear weighting of the plurality of difficulty metrics.

21. The computer-readable, non-transitory storage medium of claim 18, wherein the difficulty level of the content item is based at least in part on feedback regarding the content item received from a plurality of users.