Data desensitization method and device and readable storage medium
A data desensitization and desensitization technology, applied in the field of data processing, can solve the problems of poor data availability, time-consuming, high computational complexity, and achieve the effect of wide applicability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 2
[0072] The second embodiment of the present invention provides a data desensitization device, such as figure 2 shown, including:
[0073] A sensitive data labeling module, configured to label the sensitive data in the data file through a pre-trained labeling model according to the obtained data file submitted by the user, so as to obtain the labeling file;
[0074] An evaluation module, configured to evaluate the desensitization algorithm matching the file type of the marked file by using preset evaluation rules;
[0075] The desensitization module is configured to desensitize the marked file according to the desensitization algorithm selected by the user from the evaluation results.
[0076] In this embodiment, the evaluation module can be integrated into the sensitive data labeling module, such as image 3 As shown, it includes sample data selection, pre-desensitization, pre-desensitization effect evaluation, desensitization algorithm determination, and final desensitizat...
Embodiment 3
[0080] The third embodiment of the present invention proposes an implementation case of a data desensitization method, such as Figure 4 As shown, this example takes the data desensitization of a bank's customer loan information as an example, including the following steps:
[0081] Step 1: Obtain the loan information of a bank customer submitted by the user. For example, the submitted information is an EXCEL form, including name, gender, ID number, place of origin, loan amount, loan date, and contact information. Determine the application scenario as the financial industry Scenes.
[0082] Step 2: According to the financial industry scenario, mark non-sensitive data as gender, place of origin, loan amount, and loan date, and sensitive data as name, ID number, and contact information, and then grade the marked sensitive data, such as 3, 9, and 9 respectively .
[0083] Step 3: Randomly sample data at a ratio of 15%, judge it as text content, and use 8 built-in types (K anony...
Embodiment 4
[0088] The fourth embodiment of the present invention proposes an implementation case of a data desensitization method, such as Figure 5 As shown, this example illustrates the data desensitization of social network pictures for analyzing personal preferences as an example, including the following steps:
[0089] Step 1: Obtain the collection of social network pictures submitted by users. The submitted information is a folder containing multiple jpg files. The content of the pictures covers faces, landscapes, animals, food, cars, and social industry scenes are selected.
[0090] Step 2: Label non-sensitive data as scenery, animals, food, and cars according to social industry scenarios, and sensitive data as faces, and their sensitivity levels are 9 respectively.
[0091] Step 3: Randomly sample sample data at a ratio of 10%, judge it as the content of the picture, and realize the pre-desensitization operation through two built-in (face-changing and Gaussian blur) algorithms fo...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com