Sensors and analytics for reading comprehension

• US 10,255,906 B2
• Filed: 12/14/2016
• Issued: 04/09/2019
• Est. Priority Date: 12/14/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Johlic, Marc K., Keohane, Susann M., Olsson, Emi K.
• Primary Examiner(s): Yen, Jason T
• Application Number:
  US15/378,470
• Publication Number:
  US 20180160963A1
• Time in Patent Office: 846 Days
• Field of Search: None
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: A61B 5/6822 Neck
• CPC Class Codes: G09B 17/003 electrically operated apparatus or devices
• CPC Class Codes: G09B 5/06 with both visual and audible presentation of the material to be studied
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

An approach is provided that receives, from a neurological sensor worn by a user, words as they are silently read the user. The words being read by the user correspond to a set of actual words that are included in a passage that is being read by the user. The approach compares the words as read by the user with the actual words included in the passage to identify one or more reading mistakes. The reading mistakes are analyzed resulting in a set of feedback that is provided to the user.

Claims

1. A method implemented by an information handling system that includes a processor and a memory accessible by the processor, the method comprising:

receiving, from a neurological sensor worn by a user, a plurality of words as read by the user, wherein the neurological sensor includes one or more electrode sensors attached to the user that capture electrical signals between the user'"'"'s brain and the user'"'"'s vocal cords, and wherein the plurality of words as read by the user correspond to a plurality of actual words included in a passage that is being silently read by the user, and wherein the plurality of words as read by the user and the actual words are stored in the memory;

comparing, by the processor, the plurality of words as read by the user with the plurality of actual words included in the passage, wherein the comparing results in one or more identified mistakes;

identifying a pattern from the identified mistakes;

inputting the pattern to a question answering (QA) system with access to a corpus of currently known reading disability patterns;

receiving, from the QA system, a matching reading disability corresponding to the identified pattern; and

including the matching reading disability in a set of feedback that is provided to the user.

2. The method of claim 1 further comprising:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight; and

including the prioritized mistakes in the set of feedback that is provided to the user.

3. The method of claim 1 further comprising:

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the improvement report in the set of feedback that is provided to the user.

4. The method of claim 1 further comprising:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight;

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the prioritized mistakes and the improvement report in the set of feedback that is provided to the user.

5. An information handling system comprising:

one or more processors;

a memory coupled to at least one of the processors; and

a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions comprising;

receiving, from a neurological sensor worn by a user, a plurality of words as read by the user, wherein the neurological sensor includes one or more electrode sensors attached to the user that capture electrical signals between the user'"'"'s brain and the user'"'"'s vocal cords, and wherein the plurality of words as read by the user correspond to a plurality of actual words included in a passage that is being silently read by the user, and wherein the plurality of words as read by the user and the actual words are stored in the memory;

comparing, by the processor, the plurality of words as read by the user with the plurality of actual words included in the passage, wherein the comparing results in one or more identified mistakes;

identifying a pattern from the identified mistakes;

inputting the pattern to a question answering (QA) system with access to a corpus of currently known reading disability patterns;

receiving, from the QA system, a matching reading disability corresponding to the identified pattern; and

including the matching reading disability in a set of feedback that is provided to the user.

6. The information handling system of claim 5 wherein the actions further comprise:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight; and

including the prioritized mistakes in the set of feedback that is provided to the user.

7. The information handling system of claim 5 wherein the actions further comprise:

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the improvement report in the set of feedback that is provided to the user.

8. The information handling system of claim 5 wherein the actions further comprise:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight;

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the prioritized mistakes and the improvement report in the set of feedback that is provided to the user.

9. A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, performs actions comprising:

receiving, from a neurological sensor worn by a user, a plurality of words as read by the user wherein the neurological sensor includes one or more electrode sensors attached to the user that capture electrical signals between the user'"'"'s brain and the user'"'"'s vocal cords, and, wherein the plurality of words as read by the user correspond to a plurality of actual words included in a passage that is being silently read by the user, and wherein the plurality of words as read by the user and the actual words are stored in the memory;

comparing, by the processor, the plurality of words as read by the user with the plurality of actual words included in the passage, wherein the comparing results in one or more identified mistakes;

identifying a pattern from the identified mistakes;

inputting the pattern to a question answering (QA) system with access to a corpus of currently known reading disability patterns;

receiving, from the QA system, a matching reading disability corresponding to the identified pattern; and

including the matching reading disability in a set of feedback that is provided to the user.

10. The computer program product of claim 9 wherein the actions further comprise:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight; and

including the prioritized mistakes in the set of feedback that is provided to the user.

11. The computer program product of claim 9 wherein the actions further comprise:

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the improvement report in the set of feedback that is provided to the user.

12. The computer program product of claim 9 wherein the actions further comprise:

selecting each of the mistakes, wherein each mistake includes a selected one of the words as read by the user and a selected one of the actual words;

retrieving a set of historical data pertaining to each of the selected mistakes, wherein the set of historical data includes a plurality of past mistakes identified during one or more previous readings by the user;

calculating a weight corresponding to each of the selected mistakes based on the retrieved set of historical data corresponding to each of the respective mistakes;

prioritizing each of the selected mistakes based on each of the selected mistake'"'"'s respective weight;

identifying a plurality of correctly read words from the comparison of the plurality of words as read by the user with the plurality of actual words included in the passage;

retrieving a set of historical data that includes a plurality of past mistakes identified during one or more previous readings by the user;

matching one or more of the correctly read words with one or more past mistakes;

preparing an improvement report based on the matching; and

including the prioritized mistakes and the improvement report in the set of feedback that is provided to the user.