Method and system for literacy adaptive content personalization

Patent metadata

Field	Value
Publication number	US-11520840-B2
Application number	US-201916726548-A
Country	US
Kind code	B2
Filing date	Dec 24, 2019
Priority date	Dec 24, 2019
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

The present teaching relates to a method, system, and programming for content personalization. A request is received from a user to obtain a content item. Information indicative of a literacy-level of the user is obtained and the content item to be provided to the user is retrieved. The content item is modified by updating information included in the content item based on the literacy-level of the user to generate an updated content item. The updated content item is provided to the user in response to the request.

First claim

We claim:

1. A method, implemented on a machine having at least one processor, storage, and a communication platform capable of connecting to a network for content personalization, the method comprising:
retrieving, by a content modification engine, content items previously consumed by a user;
detecting, by the content modification engine, via a web-application embedded in one or more webpages, a dwell time associated with the user while consuming each of the content items;
removing, by the content modification engine, based on the dwell times associated with the content items, at least one of the content items on which the user spent less than a threshold dwell time;
obtaining, by the content modification engine, based on remaining content items, information indicative of a literacy-level of the user, wherein the obtained information indicative of the literacy-level of the user is stored in a database;
retrieving, by the content modification engine, according to a request from the user, a first content item to be provided to the user;
generating, by the content modification engine, multiple versions of the first content item
retrieving, from the database based on metadata of the request, the information indicative of the literacy-level of the user, and
updating, based on the literacy-level of the user, information included in the first content item to generate the multiple versions of the first content item;

selecting, by the content modification engine, one of the multiple versions based on a difference between an overall literacy-score of the user indicated by the literacy-level of the user and a literacy-score of the selected version; and
providing, by the content modification engine, via the one or more webpages, the selected version of the first content item to the user in response to the request.

2. The method of claim 1 , wherein the information indicative of the literacy-level of the user includes the overall literacy-score of the user.

3. The method of claim 2 , further comprising:
obtaining, for each of the content items, a readability score in accordance with a testing model;
generating, based on the readability score, a literacy-score for the content item in accordance with a scoring model; and
calculating the overall literacy-score of the user based on the literacy-scores of the content items.

4. The method of claim 2 , further comprising:
refining the literacy-score of the user based on overall literacy-scores of other users, each of whom has consumed content items previously consumed by the user.

5. The method of claim 2 , further comprising:
obtaining one or more content items composed by the user; and
refining the literacy-score of the user based on the one or more content items composed by the user.

6. The method of claim 1 , further comprising:
obtaining a granularity level of updating the first content item;
generating the multiple versions of the first content item by updating the information included in the first content item based on the granularity level; and
selecting one of the one of the multiple versions to correspond to the updated first content item to be provided to the user.

7. A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a content modification engine, cause the content modification engine to perform a method for content personalization, the method comprising:
retrieving content items previously consumed by a user;
detecting, via a web-application embedded in one or more webpages, a dwell time associated with the user while consuming each of the content items;
removing, based on the dwell times associated with the content items, at least one of the content items on which the user spent less than a threshold dwell time;
obtaining, based on remaining content items, information indicative of a literacy-level of the user, wherein the obtained information indicative of the literacy-level of the user is stored in a database;
retrieving, according to a request from the user, a first content item to be provided to the user;
generating multiple versions of the first content item by:
retrieving, from the database based on metadata of the request, the information indicative of the literacy-level of the user, and
updating, based on the literacy-level of the user, information included in the first content item to generate the multiple versions of the first content item;

selecting one of the multiple versions based on a difference between an overall literacy-score of the user indicated by the literacy-level of the user and a literacy-score of the selected version; and
providing, via the one or more webpages, the selected version of the first content item to the user in response to the request.

8. The medium of claim 7 , wherein the information indicative of the literacy-level of the user includes the overall literacy-score of the user.

9. The medium of claim 8 , wherein the instructions, when executed by the content modification engine, cause the content modification engine to further perform:
obtaining, for each of the content items, a readability score in accordance with a testing model;
generating, based on the readability score, a literacy-score for the content item in accordance with a scoring model; and
calculating the overall literacy-score of the user based on the literacy-scores of the content items.

10. The medium of claim 8 , wherein the instructions, when executed by the content modification engine, further cause the content modification engine to perform:
refining the literacy-score of the user based on overall literacy-scores of other users, each of whom has consumed content items previously consumed by the user.

11. The medium of claim 8 , wherein the instructions, when executed by the content modification engine, further cause the content modification engine to perform:
obtaining one or more content items composed by the user; and
refining the literacy-score of the user based on the one or more content items composed by the user.

12. The medium of claim 7 , wherein the instructions, when executed by the content modification engine, further cause the content modification engine to perform:
obtaining a granularity level of updating the first content item;
generating the multiple versions of the first content item by updating the information included in the first content item based on the granularity level; and
selecting one of the one of the multiple versions to correspond to the updated first content item to be provided to the user.

13. A system for content personalization, the system comprising:
a content retrieving unit of a content modification engine implemented by a processor and configured to retrieve content items previously consumed by a user;
a content filtering unit of the content modification engine implemented by the processor and configured to:
detect, via a web-application embedded in one or more webpages, a dwell time associated with the user while consuming each of the content items, and
remove, based on the dwell times associated with the content items, at least one of the content items on which the user spent less than a threshold dwell time;

a literacy level scoring unit of the content modification engine implemented by the processor and configured to obtain, based on remaining content items, information indicative of a literacy-level of the user, wherein the obtained information indicative of the literacy-level of the user is stored in a database;
a web content retrieving unit of the content modification engine implemented by the processor and configured t

Assignees

• Yahoo Assets Llc

Inventors

• Pelleg Dan
• Wolff Ran
• Mejer Avihai

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9538 Primary

  Presentation of query results · CPC title

• G06F16/219

  Managing data history or versioning (querying versioned data G06F16/2474; querying temporal data G06F16/2477) · CPC title