0COMMENTS0RECOMMENDS

AR Command & Control Part 2

47
POSTED IN: Building Bridges from R to IBM Watson

Command & Control for VR AR - Part 2 - Knowledge Graphs

 

GOAL: TO BEGIN TO BUILD A FOUNDATION TO LOCATE "IDEAS" on the SCREEN IN FRONT OF AR VIEWER

 

 

 

Examples (Five C's)

cows/business and industrial/agriculture and forestry/livestock cows /animals/cows 
crack/society/crime/property crime/piracy crack /problems/defects/crack 
craft/art and entertainment/visual art and design/art and craft supplies craft /activities/craft 
crash/travel/transports/air travel/air and space accident crash /problems/crash 
cream/food and drink/desserts and baking cream /products/cream 

 

Taxonomy - First Level

Row LabelsCount of travel
technology and computing94
business and industrial76
art and entertainment69
food and drink67
health and fitness66
sports46
science44
law, govt and politics39
home and garden37
finance30
style and fashion29
travel24
society23
education23
automotive and vehicles19
shopping18
hobbies and interests16
pets7
careers6
family and parenting6
religion and spirituality6
technology and computing 3
law, govt and politics 3
real estate3

 

Knowledge Graph - First Level

Row LabelsCount of knowledgegraph
products190
activities93
issues92
people89
organizations45
problems40
accessories39
foods24
factors23
industries21
places20
animals16
concepts15
services12
details12
fields11
vehicles10
considerations8
techniques8
devices7
features7
tools7
tissues6
times6
colors5
materials5
matters5
parts4
statements4
books4
sources3
categories3
body parts3
characters3
applications3
companies3

 

KnowledgeGraph Flag:

http://www.alchemyapi.com/api/entity/textc.html

knowledgeGraph The path through the knowledge graph to the appropriate keyword. Only returned when request parameter is provided: knowledgeGraph=1

 

Curl Example

curl -i "http://gateway-a.watsonplatform.net/calls/text/TextGetCombinedData?extract=keyword,doc-sentiment,entity,taxonomy,concept&apikey=KEYKEYKEYKEY&text=I%20like%20to%20drink%20whiskey&outputMode=json&knowledgeGraph=1"

    "keywords": [
        {
            "knowledgeGraph": {
                "typeHierarchy": "/liquids/beverages/liquors/spirits/whiskey"
            },
            "relevance": "0.916605",
            "text": "whiskey"
        }
    ]

 

 

Code / Data Used:

DATA SOURCE:  http://www.talkenglish.com/vocabulary/top-1500-nouns.aspx - for 1500 nouns

GITHUB - includes source R for processing AND POST PROCESSING CSV - https://github.com/rustyoldrake/Watson_Command_Control

API - http://www.alchemyapi.com/api/entity/textc.html

LATER (non-poor man's method) - http://nlp.stanford.edu/projects/glove/ and https://en.wikipedia.org/wiki/Word2vec

 

 

 

Before you can comment, you need to sign-up or login

About the Author

Ryan Anderson

Ryan Anderson

Hi! I like to play with data, analytics and hack around with robots and gadgets in my garage. Lately I've been learning about machine learning.

About this blog

This is an informal blog that explores tools, code and tricks that group members have developed to engage IBM Watson cognitive computing services - from the R Programming Language. Packages include RCURL to access Watson APIs - for services that include Natural Language Classifier and Speech to Text. THIS IS MY PERSONAL BLOG - it does not represent the views of my employer. Code is presented as 'use at your own risk' (it has lots of bugs)

Created: September 13, 2015

English

Up Next