Multi-party collaborative business prediction model updating method for realizing privacy protection
A predictive model and privacy protection technology, applied in the field of information security, can solve problems such as difficulty in meeting privacy protection requirements, single collaborative modeling method, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0050] The following describes the solutions provided in this specification with reference to the drawings.
[0051] As mentioned earlier, multiple data parties need to ensure the privacy of their own data while co-training machine learning models (or predictive models) to prevent leakage of private data. In the proposed collaborative training method, a neutral global server (hereinafter referred to as the server) is set up, and a communication connection is established between each data party and the server, so that the data of all parties can use the server to achieve value integration. In this way, There is no need for direct communication between various data parties, thereby ensuring the privacy and security of the data of all parties to a certain extent.
[0052] specifically, figure 1 Shows a communication architecture diagram of a collaborative training machine learning model according to an embodiment, such as figure 1 As shown, multiple data parties (N are shown in the fi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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