| Title | 一种面向第三方支付平台的欺诈识别方法及装置 |
| Alternative Title | Fraud identification method and device for third-party payment platform
|
| Author | |
| First Inventor | 吴垠
|
| Original applicant | 南方科技大学
|
| First applicant | 南方科技大学
|
| Address of First applicant | 518055 广东省深圳市南山区桃源街道学苑大道1088号
|
| Current applicant | 南方科技大学
|
| Address of Current applicant | 518055 广东省深圳市南山区桃源街道学苑大道1088号 (广东,深圳,南山区)
|
| First Current Applicant | 南方科技大学
|
| Address of First Current Applicant | 518055 广东省深圳市南山区桃源街道学苑大道1088号 (广东,深圳,南山区)
|
| Application Number | CN202211109852.5
|
| Application Date | 2022-09-13
|
| Open (Notice) Number | CN115439128A
|
| Date Available | 2022-12-06
|
| Status of Patent | 实质审查
|
| Legal Date | 2022-12-23
|
| Subtype | 发明申请
|
| SUSTech Authorship | First
|
| Abstract | 本发明所提供的一种面向第三方支付平台的欺诈识别方法及装置，包括：接收第三方支付平台发送的待识别数据，将所述待识别数据输入预先训练的人工神经网络，所述人工神经网络由均衡数据集训练而成；在所述人工神经网络中对所述待识别数据进行分类，得到数据分类结果；所述均衡数据集包括真实欺诈降维数据、真实风险降维数据、真实普通降维数据、扩增欺诈降维数据以及扩增风险降维数据。本发明通过使用均衡数据集训练的人工神经网络对待识别数据进行分类，得到数据分类结果，由于均衡数据集内的数据包括三个类别，并且对真实欺诈降维数据和真实风险降维数据进行了扩增，使得各类别的数据量相差不大，进而使得在识别新数据时分类结果更加准确。 |
| Other Abstract | The invention provides a fraud identification method and device for a third-party payment platform, and the method comprises the steps: receiving to-be-identified data transmitted by the third-party payment platform, inputting the to-be-identified data into a pre-trained artificial neural network which is trained by a balanced data set; classifying the to-be-identified data in the artificial neural network to obtain a data classification result; the balanced data set comprises real fraud dimensionality reduction data, real risk dimensionality reduction data, real common dimensionality reduction data, amplified fraud dimensionality reduction data and amplified risk dimensionality reduction data. According to the method, the to-be-identified data is classified by using the artificial neural network trained by the balanced data set to obtain the data classification result, the data in the balanced data set comprises three categories, and the real fraud dimensionality reduction data and the real risk dimensionality reduction data are amplified, so that the difference between the data volumes of the categories is small, and the data classification accuracy is improved. And thus, the classification result is more accurate when new data is identified. |
| IPC Classification Number | G06Q20/40
; G06Q20/08
; G06K9/62
; G06N3/08
|
| INPADOC Legal Status | （ENTRY INTO FORCE OF REQUEST FOR SUBSTANTIVE EXAMINATION）[2022-12-23][CN]
|
| INPADOC Patent Family Count | 1
|
| Extended Patent Family Count | 1
|
| Priority date | 2022-09-13
|
| Patent Agent | 朱阳波
|
| Agency | 深圳市君胜知识产权代理事务所(普通合伙)
|
| URL | [Source Record] |
| Data Source | PatSnap
|
| Document Type | Patent |
| Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/531954 |
| Department | School of System Design and Intelligent Manufacturing |
| Recommended Citation GB/T 7714 |
吴垠,程佳一,杨思宇,等. 一种面向第三方支付平台的欺诈识别方法及装置.
|
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment