Interest highlight and recommendation based on interaction in long text reading

Patent metadata

Field	Value
Publication number	US-10691893-B2
Application number	US-201615056492-A
Country	US
Kind code	B2
Filing date	Feb 29, 2016
Priority date	Feb 29, 2016
Publication date	Jun 23, 2020
Grant date	Jun 23, 2020

Abstract

A method, system and computer program product are disclosed for recommending terms in a document based on a specified interaction with the document. In one embodiment, the method comprises displaying a document on a device; detecting a specified interaction with the document displayed on the device; identifying text associated with the specified interaction with the document displayed on the device; performing object recognition with the identified text to recognize one or more defined interested objects; and recommending terms in the document based on the recognized defined interested objects. In an embodiment, the object recognition includes identifying one or more objects from the text, and performing the object recognition with these objects to recognize the one or more interested objects. In an embodiment, one or more terms are extracted from the text, and these terms are partitioned to identify the one or more objects from the text.

First claim

The invention claimed is:

1. A method for recommending terms in a document based on a specified interaction with the document, the method comprising:
displaying a document on a device of a computer system;
detecting, by a text identifier of the computer system, a specified interaction of a user with the document displayed on the device;
identifying, by the text identifier of the computer system, text associated with the specified interaction of the user with the document displayed on the device;
extracting objects from the identified test using natural language processing and an object recognizer of the computer system, including
extracting phrases from the identified text, and
forming objects from the extracted phrases using the natural language processing;

recognizing one or more interested objects, of a determined group of interested objects, from the identified text, including
filtering the formed objects with said determined group of interested objects, to form a filtered group of objects comprising said one or more interested objects from the identified text, including
displaying on the device a first group of interested objects,
the user using the display of the first group of interested objects to add one or more additional interested objects to the first group of interested objects, and to remove one or more of the interested objects of the first group of interested objects form said first group of interested objects to form said determined group of the interested objects, including
displaying a second group of interested objects on the device,
assigning a weight to each of the interested objects in the first and second group of interested objects,
in each of the first and second groups of interested objects, sorting the interested objects in said each group by the weights of the interested objects,
in each of the first and second groups of interestted objects, removing from said each group one or more of the interested objects of said each group based on the weights of the interested objects of said each group, and
the user interacting with the display of the second group of interested objects to move one or more of the interested objects from the second group of interested objects to the first group of interested objects; and

putting into said filtered group of objects ones of the formed objects that are present in the determined group of interested objects; and

recommending terms in the document based on the filtered group of the objects formed from the objects extracted from the identified text.

2. The method according to claim 1 , wherein the forming objects from the extracted phrases include:
partitioning the extracted phrases to identify said objects from the extracted phrases.

3. The method according to claim 1 , wherein the first group of interested objects are derived from defined actions of the user, and the second group of interested objects are obtained from a specified group of people.

4. The method according to claim 1 , wherein the identifying text associated with the specified interaction with the document displayed on the device includes:
using the specified interaction of the user with the specified device to identify an area of the document; and
selecting text in said area of the document.

5. The method according to claim 4 , wherein the specified interaction with the device is a user touching the display of the document on a display screen of the device.

6. The method according to claim 5 , wherein:
a user touching the display of the document on a display screen of the device includes the user touching an area of the display of the document; and
the identified area of the document is a specified area around said touched area.

7. The method according to claim 1 , wherein:
the determined group of interested objects include a first set of interested objects derived form defined actions of the user, and a second set of interested objects obtained from a specified group of people;
the specified interaction with the device is the user touching an area of the display of the document on a display screen of the device;
the identified area of the document includes the touched area of the display of the document, and a larger area around said touched area; and
the putting into said filtered group of objects ones of the formed objects that are present in the determined group of interested objects includes putting into said filtered group of objects ones of the second set of interested objects that do not appear in said touched area of the display and do appear in said larger area around said touched area.

8. The method according to claim 1 , wherein the assigning a weight to each of the interested objects in the first and second groups of ionterested objects includes, when one of the interested objects in the determined group of interested objects matches one of the formed objects, increasing the weight of said one of the interested objects.

9. The method according to claim 1 , for use with one or more databases storing a plurality of interested objects, each of the plurality of interested objects stored in the database having a weight, and wherein:
when any one of the formed objects matches one of the interested objects in said one or more databases, giving the one of the formed objects the weight of the matching one of the interested objects in said one or more databases.

10. A system for recommending terms in a document based on a specified interaction with the document, wherein the document is shown on a display screen of a device, the system comprising:
a memory for storing data, and
one or more processing units connected to the memory for transmitting data to and receiving from the memory, the one or more processing units configured for:
a text identifier for detecting a specified interaction of a user with the document displayed on the device, and identifying text associated with the specified interaction of the user with the document displayed on the device; and
an object recognizer for extracting objects from the identified text using natural language processing and, including
extracting phrases from the identified text, and
forming objects from the extracted phrases using the natural language processing,

the object recognizer for recognizing one or more interested objects, of a determined group of interested objects, from the identified text, including
filtering the formed objects with said determined group of interested objects, to form a filtered group of objects comprising said one or more interested objects from the identified text, including
displaying on the device a first group of interested objects,
using the display of the first group of interested objects to add one or more additional interested objects to the first group of interested objects, and to remove one or more of the interested objects of the first group of interested objects from said first group of interested objects to form said determined group of the interested objects, including
displaying a second group of interested objects on the device,
assigning a weight to each of the interested objects in the first and second groups of interested objects,
in each of the first and second groups of interested objects, sorting the interested objects in said each group by the weights of the interested objects,
in each of the first and second groups of interested objects, removing from said each group one or more of the interested objects of said each group based on the weights of the interested objects of said each group, and
the user interacting with the display of the second group of interested objects to move one or more of the interested objects from the second group o

Assignees

• IBM

Inventors

• Gong Min
• Ni Yuan
• Yan Junchi
• Zhu Hui J

Classifications

• G09G5/00 Primary

  Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators (image data processing or generation, in general G06T) · CPC title

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G09G2354/00

  Aspects of interface with display user · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title