Prompting subject matter experts for additional detail based on historical answer ratings

Patent metadata

Field	Value
Publication number	US-9652528-B2
Application number	US-201615064505-A
Country	US
Kind code	B2
Filing date	Mar 8, 2016
Priority date	Jun 30, 2014
Publication date	May 16, 2017
Grant date	May 16, 2017

Abstract

An approach is provided for evaluating a potential post based on historical data. In the approach, historically highly rated attributes that to previously received highly rated posts are identified. The process receives a potential post from an online Subject Matter Expert (SME). The process analyzes the potential post, using a Natural Language Processing (NLP) routine performed by computer processors. The analysis identifies a lack of one or more of the historically highly rated attributes in the potential post. The process then notifies the SME, based on the analysis, regarding the lack of one or more of the historically highly rated attributes in the potential post.

First claim

What is claimed is:

1. A method, in an information handling system comprising a processor and a memory, of evaluating a potential post based on historical data, the method comprising:
identifying, using the processor, a plurality of historically highly rated attributes corresponding to a plurality of previously received highly rated posts, wherein the identifying further comprises selecting the plurality of previously received highly rated posts from a larger plurality of previously received posts;
receiving, via a computer network, the potential post from an online Subject Matter Expert (SME);
analyzing the potential post, using a Natural Language Processing (NLP) routine performed by the processor, wherein the analysis identifies a lack of one or more of the historically highly rated attributes in the potential post;
notifying, based on the analysis, the SME regarding the lack of one or more of the historically highly rated attributes in the potential post;
receiving, in response to the notifying, one or more revised potential posts from the SME; and
including at least one of the one or more revised potential posts in the larger plurality of previously received posts based on an indication received from the SME, wherein the included revised potential post is visible to the end users for evaluation.

2. The method of claim 1 wherein the selecting further comprises:
comparing a composite rating corresponding to each of the larger plurality of previously received posts to a threshold; and
identifying the plurality of previously received highly rated posts based on the comparison, wherein the identified plurality of previously received highly rated posts have composite ratings that at least meet the threshold.

3. The method of claim 2 further comprising:
performing a NLP analysis on the plurality of previously received highly rated posts, wherein the analysis results in the plurality of historically highly rated attributes.

4. The method of claim 3 further comprising:
performing the NLP analysis on the potential post, wherein the analysis results in a plurality of potential post attributes;
comparing the historically highly rated attributes to the potential post attributes; and
identifying the lack of one or more of the historically highly rated attributes in the potential post based on the comparison.

5. The method of claim 4 further comprising:
performing a quality analysis using a qualitative NLP process, wherein the quality analysis is performed on a set of one or more attributes found in the potential post, and wherein the quality analysis identifies one or more shortcomings of the found attributes; and
wherein the notifying further includes notifying the SME regarding the shortcomings identified in the found attributes.

6. The method of claim 2 wherein the composite ratings are based on one or more evaluations received from one or more end users regarding each of the larger plurality of previously received posts.

7. The method of claim 6 wherein the notifying further comprises:
prompting the SME to provide the one or more historically highly rated attributes lacking in the potential post.

Assignees

• IBM
• Int Business Machiens Corp

Inventors

• Allen Corville O
• Allen Joshua S
• Woods Eric

Classifications

• G06F17/30693

  Physics · mapped topic

• G06F17/30728

  Physics · mapped topic

• G06F17/30684 Primary

  Physics · mapped topic

• G06F17/30867

  Physics · mapped topic

• G06F17/30864

  Physics · mapped topic