Joint data analysis method, device and system and computer readable storage medium

A technology that combines data and analysis methods. It is applied to computer components, computer security devices, and calculations. It can solve problems such as leaking labels, risks in the calculation process, and failure to meet business requirements, so as to improve analysis accuracy and expand analysis dimensions. Effect

Pending Publication Date: 2021-01-15
杭州锘崴信息科技有限公司
View PDF17 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] 1. Many scenarios do not meet business requirements and cannot be fully compliant and legal
[0011] 2. Need to leak labels, features
[0012] 3. There are risks in the calculation process, and one party is likely to obtain the original information data of the other party
[0013] 4. Cannot give full play to the value of data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Joint data analysis method, device and system and computer readable storage medium
  • Joint data analysis method, device and system and computer readable storage medium
  • Joint data analysis method, device and system and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0155] Scenario description: Party A is unwilling to let Party B (and Party C, etc.) know which specific samples, specific features, and how to use the features are used by Party A. Specifically, it is the banking scenario credit scoring model scenario: banks are unwilling to disclose any sample characteristics. That is, the bank (that is, Party A) does not want big data companies (Party B, Party C, etc.) to know the characteristics of which big data companies the bank uses, and the specific usage method cannot be disclosed, because the leakage of specific information may lead to targeted of fraud. This kind of scenario is to use other people's data, but is unwilling to tell others what to use and how to use it.

[0156] Example: The bank is party A, and the bank has a scoring model for credit card applications. This model is obtained by the bank using internal data and internal algorithms. This model cannot meet higher business requirements, so it needs to be improved, esp...

specific Embodiment 2

[0164] Specific embodiment 2: for behavior monitoring

[0165] For example: the bank is party A, and the bank has granted credit cards to several people. It needs to know the behavior characteristics of the grantees to ensure the safety of funds. More income. Common behavioral scoring model for credit cards. This model is obtained by Silver using internal data and internal algorithms. This model has poor timeliness, cannot make full use of external data, and cannot meet higher business requirements. Therefore, it needs to be improved, especially how to use external data to improve compliance. Adopt the scheme of the present invention as follows:

[0166] The first three steps are similar to Example 1, the specific data content is different, but the process is the same

[0167] Step 1: Same as above

[0168] Step 2: Same as above, usually with lots of layers instead of two or three. For convenience, 2 layers are used as an example for description.

[0169] Step 3: Simila...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Disclosed are a joint data analysis method, device and system, and a computer readable storage medium, the method comprises the following steps that a demand initiator generates an ID packet sample set according to a model, and a data provider uses a secure computing environment to establish a mirror image equivalence model according to the ID packet sample set, and the demand initiator can analyze the sample by using the model obtained by joint calculation of the data provider to obtain an analysis result, i.e., the analysis result is directly used, or the original model is improved accordingto the equivalent model. Features associated with multiple parties are obtained through the mirror image equivalent model, the analysis dimension is expanded under the condition of no mutual data leakage, and the analysis accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of big data analysis, in particular to the field of big data multi-center analysis technology, and specifically relates to a joint data analysis method, device, system and computer-readable storage medium. Background technique [0002] The invention belongs to the technical field of data analysis, in particular to the field of big data multi-center analysis technology, and the field requiring protection of original data information. At present, big data is developing rapidly, especially in the field of Internet big data credit investigation, and demand originators, such as banks. Internet finance companies need data from companies in other industries to better conduct business. For example, credit analysis to adapt to the development requirements of the big data era. [0003] In practice, a series of laws and regulations, benefit distribution, safety management, cost and other issues will be encountered wh...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/62G06F21/53G06N20/00G06N20/10G06K9/62
CPCG06F21/6254G06F21/53G06N20/00G06N20/10G06F18/2411G06F18/214
Inventor 李帜王爽郑灏王帅
Owner 杭州锘崴信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap