A data open sharing-oriented software access behavior data feature representation method

A technology oriented to data and data characteristics, applied in the field of big data, can solve problems such as design dependencies and omissions

Active Publication Date: 2019-06-28
FUDAN UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as today's software functions become more and more complex, there are lags and limitations in manually designed indicators: lag means that experts usually need to have a certain analysis and understanding of software

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
  • A data open sharing-oriented software access behavior data feature representation method
  • A data open sharing-oriented software access behavior data feature representation method
  • A data open sharing-oriented software access behavior data feature representation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific implementation of the method is shown below with example data (see Table 1) containing 5 access records of 1 user.

[0048] Training phase:

[0049] (1) Software access behavior data preprocessing: This group of software access behavior data includes 1 category attribute: port, and 2 numerical attributes: access duration and file size. According to the time information, the user's software access behavior sequence data s=1 ,e 2 ,e 3 >. Among them, e 1 ={(1,80,0.3,3.21),(2,80,0.5,0.15)} contains two events 1 and 2, e 2 Contains 3 and 4 two events, e 3 Contains the 5th event;

[0050] (2) Single-moment behavior data encoding: e 1 As an example, encode daily behavior data. First, perform feature representation on the first event (1,80,0.3,3.21): (a) map the accessed data ID through the embedding layer to obtain its embedding vector (0.1,-0.3); (b) classify Type attributes are mapped through the embedding layer one by one. In this example, there are on...

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 belongs to the technical field of big data, and particularly relates to a data open sharing-oriented software access behavior data feature representation method. According to the method,a software access behavior data sequence of a user is directly received, and a feature representation vector of the behavior data sequence is output. According to the invention, a single-moment behavior data encoder is designed for summarizing multiple groups of behavior data in a single time point and extracting important behavior events by using a self-attention mechanism; And the summarized single-time-point data is input into the recurrent neural network to represent the behavior sequence, and finally the feature representation of the whole sequence is extracted from the behavior sequence. The parameters of the single-time-point encoder and the recurrent neural network are trained by using the prediction codes, and the generative adversarial network is added to improve the model effect, so that the user access behavior can be analyzed, the use requirement of the user can be known, the software access behavior can be supervised in time, and a safety guarantee can be provided for pushing data autonomous opening.

Description

technical field [0001] The invention belongs to the technical field of big data, and in particular relates to a feature learning method for software access behavior sequence data. Background technique [0002] With the gradual emergence of the strategic and commercial value of data resources, the open sharing of data resources has attracted more and more attention from researchers and industry professionals. During the promotion and implementation of the data self-government and open model with the data box as the basic unit of data openness and sharing, how to ensure that data users use the data in the data box in accordance with the regulations, supervise the behavior of data users in a timely manner, and prevent such as record tampering, second The loss of data value and privacy leakage caused by malicious operations such as sub-distribution is a difficult point that we need to solve at present. [0003] Usually, the analysis and monitoring of software access behavior ca...

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
IPC IPC(8): G06K9/62G06K9/46H04L29/06
Inventor 熊贇张尧朱扬勇
Owner FUDAN UNIV
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