Octember - Social Graph Based People Recommender with Amazon Neptune and Textract

- OCR(Optical Character Recognition, i.e, Amazon Textract) 기술을 활용한 명함 관리 및 Graph database(Amazon Neptune)을 이용한 인맥 추천 서비스 개발 사례 소개
- https://github.com/aws-samples/social-graph-based-people-recommender-using-amazon-neptune-and-textract

Transcript

1. Sungmin Kim Solutions Architect, AWS OctemberTM on AWS
2. What to be expected • Understanding Customers • Legacy Architecture • To-Be Architecture • Amazon Textract - Easily extract text and data from Biz. cards • Amazon Elasticsearch Service – Search Biz. cards • Amazon Neptune – Find and connect People You May Know • Demo
3. OctemberTM Mission Your People Are Your Most Important Asset!
4. OctemberTM Competitor Trend
5. As-Is Pain Points ① 명함 이미지의 문자 인식 자동화 ② 이미지 처리/검색/인맥 추천 서비스의 독립적인 운영 및 배포 ③ 소셜네트워크 데이터 분석 시스템 구축 upload a biz card image search store a biz card image Image Store (Files) Text Store (RDS) Typists extract text data from biz card images return search results store text data
6. Whiteboard Architecture
7. /search To-Be /pymk Bizcard Image S3 Object Creation Event S3 Object Path API Gateway S3 API Gateway API Gateway S3 S3 JSON Kinesis Data Streams Lambda function Elasticsearch Service ElastiCache ElastiCache Lambda function Kinesis Data Firehose Lambda function Lambda function Neptune DynamoDB Textract
8. Amazon Textract 거의 모든 문서에서 텍스트와 데이터를 손쉽게 추출 Extract data quickly & accurately No code or templates to maintain { Start Date: 1/15/2009 End Date: 6/30/2013 Employer Name: Any Company Position Held: Head Baker Reason for leaving: Family relocated} Full Name: First: John Middle: X Last: Doe Date of Birth: MM: 01 DD: 01 YYYY: 1971 Gender: Male: True Female: False Form Table Text Output
9. API Gateway S3 Lambda function Textract DynamoDB Kinesis Data Streams S3 To-Be: 명함 이미지 자동 인식 { name: “OOO”, jobtitle: “OOO”, mobile: ’ooo-xxx-xxx” email: “xyz@xxx”, address: “OOO” } S3 Object Creation S3 Object Path Bizcard Image json
10. Amazon Elasticsearch Service 완전 관리, 확장 가능 및 보안형 Elasticsearch 서비스
11. API Gateway S3 Lambda function Textract Kinesis Data Streams S3 Kinesis Data Streams Kinesis Data Firehose Elasticsearch Service Lambda function API Gateway ElastiCache S3 To-Be: 명함 검색 서비스 DynamoDB /search
12. Amazon Neptune 클라우드용으로 구축된 빠르고 안정적인 그래프 데이터베이스 Social Networking Recommendation Engines Fraud Detection Knowledge Graphs
13. Lambda function Neptune API Gateway S3 Lambda function Textract Kinesis Data Streams S3 Kinesis Data Streams Lambda function API Gateway ElastiCache To-Be: 인맥 추천 서비스 DynamoDB /pymk
14. How To Solve Pain Point (1) /pymk Bizcard Image API Gateway S3 API Gateway API Gateway S3 S3 Kinesis Data Streams Lambda function Elasticsearch Service ElastiCache ElastiCache Lambda function Kinesis Data Firehose Lambda function Lambda function Neptune DynamoDB Textract 명함 이미지의 문자 인식 자동화 /search
15. How To Solve Pain Point (2) /search /pymk Bizcard Image API Gateway S3 API Gateway API Gateway S3 S3 Kinesis Data Streams Lambda function Elasticsearch Service ElastiCache ElastiCache Lambda function Kinesis Data Firehose Lambda function Lambda function Neptune DynamoDB Textract 명함 이미지 처리 검색 서비스 인맥 추천 서비스
16. How To Solve Pain Point (3) /search /pymk Bizcard Image API Gateway S3 API Gateway API Gateway S3 S3 Kinesis Data Streams Lambda function Elasticsearch Service ElastiCache ElastiCache Lambda function Kinesis Data Firehose Lambda function Lambda function Neptune DynamoDB Textract 소셜네트워크 데이터 분석 시스템 구축
17. AWS Well-Architecture Framework Performance efficiency Cost optimization Security Reliability Operational excellence Set of questions you can use to evaluate how well an architecture is aligned to AWS best practices https://wa.aws.amazon.com/wat.map.en.html
18. /search Is Well-Architected? /pymk Bizcard Image S3 Object Creation Event S3 Object Path API Gateway S3 API Gateway API Gateway S3 S3 JSON Kinesis Data Streams Lambda function Elasticsearch Service ElastiCache ElastiCache Lambda function Kinesis Data Firehose Lambda function Lambda function Neptune DynamoDB Textract
19. DEMO
20. Demo: 명함 이미지 이름 직함 주소 전화번호 e-mail
21. Demo: 시나리오 https://github.com/aws-samples/social-graph-based-people-recommender-using-amazon-neptune-and-textract Edy Kim (edy) Poby Kim (poby) Rody Park (rody) Harry Jang (harry) Crong Lee (crong) Pororo Kim (pororo)
22. Demo: PYMK(People You May Know) Edy Kim (edy) Poby Kim (poby) Rody Park (rody) Harry Jang (harry) Crong Lee (crong) Pororo Kim (pororo) https://github.com/aws-samples/social-graph-based-people-recommender-using-amazon-neptune-and-textract
23. AWS의 다양하고 폭넓은 서비스
24. Learn More • Automatically extract text and structured data from documents with Amazon Textract • https://tinyurl.com/yyz6b7qb • Let Me Graph That For You – Part 1 – Air Routes • https://tinyurl.com/yxwh2yl7 • Building an NLP-powered search index with Amazon Textract and Amazon Comprehend • https://tinyurl.com/y4jomub2