Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sensitive data detection cloud service method and cloud service platform

A technology for sensitive data and cloud services, applied in unstructured text data retrieval, electronic digital data processing, natural language data processing, etc. The effect of reducing costs and barriers

Pending Publication Date: 2020-09-15
SHANGHAI GUAN AN INFORMATION TECH
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the technology still doesn't meet the needs of all different types of businesses

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
  • Sensitive data detection cloud service method and cloud service platform
  • Sensitive data detection cloud service method and cloud service platform
  • Sensitive data detection cloud service method and cloud service platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] see figure 1 Step diagram, a method for sensitive data detection cloud service of the present invention, comprises the following steps:

[0069] S01, the enterprise uploads training samples;

[0070] Through the data interface opened by the service provider, the enterprise uploads the training samples to the service provider.

[0071] The training samples mentioned above refer to the internal document set provided by the enterprise, and the enterprise needs to provide a document set similar to its content according to the type of sensitive data that it hopes to find on the Internet. Training sample file formats include but are not limited to Office files (docx / elsx / pptx / csv), scripts (sh / sql / java), web pages (html / css), data (json / log), text (txt), etc.

[0072] S02, the server uses training samples to perform model training to generate a target model;

[0073] This step is the core step, see figure 2 , using AI technologies in the field of natural language process...

Embodiment 2

[0099] see image 3 , the present invention also discloses a sensitive data detection cloud service platform, which integrates powerful document collection capabilities and model service capabilities by deploying collectors and models on the cloud. combine Figure 4 , the business process of the cloud service platform to provide services to enterprises includes the following core modules:

[0100] Data interface module: used for enterprises to upload training samples;

[0101] Model training module: used for model training using training samples to obtain Bert+BiLSTM classification model;

[0102] Model prediction module: used to use the model to predict Internet documents and obtain prediction results;

[0103] The prediction result return module is used to return the suspected documents in the prediction result to the enterprise.

Embodiment 3

[0105] On the basis of Embodiment 1 and Embodiment 2, this embodiment provides a storage medium in which multiple instructions are stored, and the instructions are suitable for being loaded and executed by a processor, and the multiple instructions are:

[0106] Data interface for enterprises to upload training samples;

[0107] Model training, which is used to perform model training using training samples to generate a target model; the specific execution process of this instruction is:

[0108] see figure 2 , using AI technologies in the field of natural language processing, including Bert and BiLSTM, the entire modeling process can be fully automated without human intervention.

[0109] Because the model to be established belongs to the predicted classification model, it is necessary to establish a positive and negative sample set. The training samples provided by the enterprise are used as positive samples. Negative samples can be created with any other document set, as ...

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

The invention discloses a sensitive data detection cloud service method and a cloud service platform, and the method comprises the following steps: S01, an enterprise uploads a training sample, and the enterprise uploads the training sample to a service side through a data interface opened by the service side; S02, the service side performs model training by using the training sample to obtain a Bert+BiLSTM classification model; s03, the server predicts the internet document by using the Bert+BiLSTM classification model to obtain a prediction result; and S04, the service party returns the suspected document in the prediction result to the enterprise. Sensitive data detection service is provided for an enterprise in a cloud service mode, the cost and threshold for the enterprise to obtain service are reduced, and repeated investment is avoided; large, medium and small enterprises can obtain detection services with the same standard through the service, the safety of network data is integrally improved, and great social significance is achieved.

Description

technical field [0001] The invention relates to the technical field of computer data security, in particular to a sensitive data detection cloud service method and a cloud service platform. Background technique [0002] Enterprise internal data is a high-value intangible asset, and data leakage incidents have occurred frequently in recent years. The rapid dissemination and large volume of Internet information brings great difficulties to enterprises in finding and recovering data, often resulting in huge economic losses. [0003] At present, large enterprises need to spend a lot of money to purchase software and hardware systems and operation and maintenance services provided by third parties, while small and medium-sized enterprises are unable to pay, resulting in high data security maintenance costs for large enterprises, and small and medium-sized enterprises are directly naked, and there is a big data security problem Hidden danger. Technically, keyword matching techno...

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): G06F16/35G06K9/62G06N3/04G06F40/151
CPCG06F16/35G06F40/151G06N3/044G06N3/045G06F18/214
Inventor 周晓勇梁淑云刘胜马影陶景龙王启凡魏国富徐明殷钱安余贤喆
Owner SHANGHAI GUAN AN INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products