Content authoring

• US 10,394,829 B2
• Filed: 12/08/2015
• Issued: 08/27/2019
• Est. Priority Date: 12/08/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Franceschini, Michele M., Ho, Tin Kam, Lastras-Montano, Luis A., Shmueli, Oded, Soares, Livio
• Primary Examiner(s): Nguyen, Phong H
• Application Number:
  US14/962,456
• Publication Number:
  US 20170161279A1
• Time in Patent Office: 1,358 Days
• Field of Search: 707723, 707732, 707734
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3347 using vector based model
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

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.

Claims

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, one or more of the 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 and which are restricted to a specific area of relatedness with respect to the first selected concept Ci, where the one or more candidate concepts are selected 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.

2. The method of claim 1, wherein selecting one or more of the 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 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.

5. The method of claim 1, 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.

6. The method of claim 1, wherein selecting one or more of the candidate concepts comprises selecting, by the system, at least one candidate concept which is not linked by underlying documents to the first selected concept Ci.

7. 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 concept in the first concept set, wherein i and j are positive integer values; and

selecting, by the system, one or more of the 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 and which are restricted to a specific area of relatedness with respect to the first selected concept Ci, where the one or more candidate concepts are selected 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.

8. The information handling system of claim 7, wherein the set of instructions are executable to select one or more of the 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.

9. The information handling system of claim 7, 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.

10. The information handling system of claim 7, 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.

11. The information handling system of claim 7, 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.

12. The information handling system of claim 7, wherein the set of instructions are executable to select one or more of the candidate concepts by selecting at least one candidate concept which is not linked by underlying documents to the first selected concept Ci.

13. 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 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 to 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, one or more of the candidate concepts for display as recommended concepts which are related to the one or more concepts contained in written content authored by the user based on the similarity measure between each candidate concept and each user concept and which are restricted to a specific area of relatedness with respect to the first selected concept Ci, where the one or more candidate concepts are selected 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.

14. The computer program product of claim 13, 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.