Content authoring

Patent metadata

Field	Value
Publication number	US-11327978-B2
Application number	US-201916406307-A
Country	US
Kind code	B2
Filing date	May 8, 2019
Priority date	Dec 8, 2015
Publication date	May 10, 2022
Grant date	May 10, 2022

Abstract

A method and apparatus are provided for recommending concepts from a first concept set in response to user selection of a first concept Ci by performing a natural language processing (NLP) analysis comparison of vector representations of user concepts contained in written content authored by the user and candidate concepts in a first concept set to determine a similarity measure for each candidate concept, and to select therefrom one or more of the candidate concepts for display as recommended concepts which are related to the user concepts contained in written content authored by the user based on the similarity measure between each candidate concept and each user concept.

First claim

What is claimed is:

1. A method, in an information handling system comprising a processor and a memory, for identifying concepts, the method comprising:
generating, by the system, at least a first concept set comprising one or more candidate concepts extracted from one or more content sources;
processing, by the system, one or more user concepts contained in written content authored by the user;
generating or retrieving, by the system, a vector representation of each user concept and each candidate concept in the first concept set;
performing, by the system, a natural language processing (NLP) analysis comparison of the vector representation of each user concept to a vector representation of each candidate concept in the first concept set to determine a similarity measure between each candidate concept and each user concept by analyzing a vector similarity function sim(Vi,Vj) between (1) a vector representation Vi of a first selected user concept Ci contained in written content authored by the user and (2) one or more vectors Vj for each candidate concept in the first concept set, wherein i and j are positive integer values; and
selecting, by the system, U candidate concepts for display as recommended concepts which are related to the one or more user concepts contained in written content authored by the user based on the similarity measure between each candidate concept and each user concept, where the U candidate concepts are within a specified vicinity of the one or more user concepts contained in written content authored by the user which have the highest similarity measures and are restricted to a specific area of relatedness with respect to the first selected concept Ci, where U is a user specified concept identification parameter that is a positive integer value.

2. The method of claim 1 , wherein selecting U candidate concepts for display comprises selecting a candidate concept that is similar, but not too similar, to the one or more user concepts in the written content authored by the user.

3. The method of claim 1 , wherein processing the one or more user concepts comprises receiving, by the system, a user request to produce a set of recommended concepts related to a first selected concept when a cursor passes over the first selected concept.

4. The method of claim 1 , wherein selecting U candidate concepts comprises constructing, by the system, a ranked list of M candidate concepts sorted by similarity measure for display as the recommended concepts, where M is a user specified concept identification parameter that is a positive integer value.

5. The method of claim 4 , wherein constructing the ranked list of M candidate concepts comprises generating a link addition recommendation to a first concept in the ranked list which is not linked to the first selected concept Ci and which meets a predetermined test for similarity to the first selected concept Ci.

6. The method of claim 4 , wherein constructing the ranked list of M candidate concepts comprises generating a link deletion recommendation to a first concept in the ranked list which is linked to the first selected concept Ci and which meets a predetermined test for dissimilarity to the first selected concept Ci.

7. The method of claim 1 , further comprising selecting, by the system, at least one candidate concept which is not linked by underlying documents to the first selected concept Ci.

8. An information handling system comprising:
one or more processors;
a memory coupled to at least one of the processors;
a set of instructions stored in the memory and executed by at least one of the processors to identify concepts, wherein the set of instructions are executable to perform actions of:
generating, by the system, at least a first concept set comprising one or more candidate concepts extracted from one or more content sources;
processing, by the system, one or more user concepts contained in written content authored by the user;
generating or retrieving, by the system, a vector representation of each user concept and each candidate concept in the first concept set;
performing, by the system, a natural language processing (NLP) analysis comparison of the vector representation of each user concept to a vector representation of each candidate concept in the first concept set to determine a similarity measure between each candidate concept and each user concept by analyzing a vector similarity function sim(Vi,Vj) between (1) a vector representation Vi of a first selected user concept Ci contained in written content authored by the user and (2) one or more vectors Vj for each candidate concepts in the first concept set, wherein i and j are positive integer values; and
selecting, by the system, U candidate concepts for display as recommended concepts which are related to the one or more user concepts contained in written content authored by the user based on the similarity measure between each candidate concept and each user concept, where the U candidate concepts are within a specified vicinity of the one or more user concepts contained in written content authored by the user which have the highest similarity measures and restricted to a specific area of relatedness with respect to the first selected concept Ci, where U is a user specified concept identification parameter that is a positive integer value.

9. The information handling system of claim 8 , wherein the set of instructions are executable to select U candidate concepts for display by selecting a candidate concept that is similar, but not too similar, to the one or more user concepts in the written content authored by the user.

10. The information handling system of claim 8 , wherein the set of instructions are executable to process user information by receiving a user request to produce a set of recommended concepts related to a first selected concept when a cursor passes over the first selected concept.

11. The information handling system of claim 8 , wherein the set of instructions are executable to select U candidate concepts by constructing a ranked list of M candidate concepts sorted by similarity measure for display as the recommended concepts, where M is a user specified concept identification parameter that is a positive integer value.

12. The information handling system of claim 11 , wherein the set of instructions are executable to construct the ranked list of M candidate concepts by generating a link addition recommendation to a first concept in the ranked list which is not linked to the first selected concept Ci and which meets a predetermined test for similarity to the first selected concept Ci.

13. The information handling system of claim 11 , wherein the set of instructions are executable to construct the ranked list of M candidate concepts by generating a link deletion recommendation to a first concept in the ranked list which is linked to the first selected concept Ci and which meets a predetermined test for dissimilarity to the first selected concept Ci.

14. The information handling system of claim 8 , wherein the set of instructions are executable to select at least one candidate concept which is not linked by underlying documents to the first selected concept Ci.

15. A computer program product stored in a computer readable storage medium, comprising computer instructions that, when executed by an information handling system, causes the system to identify concepts by performing actions comprising:
generating, by the system, at least a first concept set comprising one or more candidate concepts extracted from one or more content sources;
processing, by the system, one or more user c

Assignees

• IBM

Inventors

• Franceschini Michele M
• Ho Tin Kam
• Lastras-Montano Luis A
• Shmueli Oded
• Soares Livio

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F16/3347 Primary

  using vector based model · CPC title

• G06F16/93

  Document management systems · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title