Title:
DATA ANOMALY ANALYSIS METHOD AND SYSTEM EMPLOYING GRAPH ANALYSIS AND COMPUTER DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/051938
Kind Code:
A1
Abstract:
A data anomaly analysis method employing graph analysis comprising: acquiring medical insurance data to be analyzed; constructing a relational heterogeneous graph on the basis of the medical insurance data, wherein the relational heterogeneous graph is constructed by using multiple pieces of node data and an association relationship between the multiple pieces of node data as boundaries; clustering patient node data in the relational heterogeneous graph to extract multiple communities C = {C1, C2, ..., Ck} from the relational heterogeneous graph according to each piece of doctor node data (S106); acquiring multiple pieces of feature data of multiple features of each community Ci; calculating an anomaly detection coefficient of each community Ci according to the multiple pieces of feature data of the multiple features of each community Ci (S110); and determining, according to the anomaly detection coefficient of each community Ci, whether a fraud event has occured. The above method analyzes the relational heterogeneous graph consisting of the medical insurance data, thereby achieving efficient mining of a fraud situation, accurately locating a fraud entity, and improving the accuracy and the flexibility of anomaly analysis of the medical insurance data.
Inventors:
WANG JIANZONG (CN)
HUANG ZHANGCHENG (CN)
KONG LINGWEI (CN)
HUANG ZHANGCHENG (CN)
KONG LINGWEI (CN)
Application Number:
PCT/CN2020/099235
Publication Date:
March 25, 2021
Filing Date:
June 30, 2020
Export Citation:
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06Q40/08
Foreign References:
| CN110766557A | 2020-02-07 | |||
| CN109903169A | 2019-06-18 | |||
| CN109919780A | 2019-06-21 | |||
| CN107145587A | 2017-09-08 |
Other References:
LIU JUAN, BIER ERIC, WILSON AARON, GUERRA-GOMEZ JOHN ALEXIS, HONDA TOMONORI, SRICHARAN KUMAR, GILPIN LEILANI, DAVIES DANIEL: "Graph analysis for detecting fraud, waste, and abuse in health-care data", AI MAGAZINE., AMERICAN ASSOCIATION FOR ARTIFICIAL INTELLIGENCE, LA CANADA, CA, vol. 37, no. 2, 22 June 2016 (2016-06-22), CA, pages 33 - 46, XP055793055, ISSN: 0738-4602
SEO JIWON; MENDELEVITCH OFER: "Identifying frauds and anomalies in Medicare-B dataset", 2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), IEEE, 11 July 2017 (2017-07-11), pages 3664 - 3667, XP033152827, DOI: 10.1109/EMBC.2017.8037652
SEO JIWON; MENDELEVITCH OFER: "Identifying frauds and anomalies in Medicare-B dataset", 2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), IEEE, 11 July 2017 (2017-07-11), pages 3664 - 3667, XP033152827, DOI: 10.1109/EMBC.2017.8037652
Attorney, Agent or Firm:
INTELLECPRO CHINA LIMITED (CN)
Download PDF:
Previous Patent: SCR DENITRATION SYSTEM FOR CEMENT KILN FLUE GAS
Next Patent: DOCUMENT AREA POSITIONING METHOD AND DEVICE
Next Patent: DOCUMENT AREA POSITIONING METHOD AND DEVICE