Mobile application description and authority fidelity judging method and device based on depth learning
A mobile application and deep learning technology, applied in the field of mobile applications, can solve the problems of long training model, inability to judge fidelity, high correlation, etc., and achieve the effect of rich semantic information
Active Publication Date: 2019-01-29
杭州嘉洁网络科技有限公司
View PDF4 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In addition, because this type of model is unsupervised learning, there will be correlations that do not exist in practice but are highly relevant, and training the model takes a long time
In particular, all existing technologies only consider the one-to-one relationship between description and authority, and cannot determine the overall fidelity
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
[0060] It should be noted that if there is a directional indication (such as up, down, left, right, front, back...) in the embodiment of the present invention, the directional indication is only used to explain that it is in a specific posture (as shown in the drawings). If the specific posture changes, the relative positional relationship, movement, etc. of the components below will also change the directional indication accordingly.
[0...
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
Login to View More Abstract
The invention discloses a mobile application description and authority fidelity judging method and device based on depth learning. The device is used for realizing the method. The method comprises thefollowing steps: a description text is preprocessed by transforming a description clause of the mobile application A into a word vector matrix used by a depth neural network for classification; eachsentence s [belong to] S corresponds to zero or more permissions, using the trained depth neural network model to output the classification class of each sentence, each class represents a kind of permission, integrating the class output of all the description sentences of mobile application A, assuming Y is the predicted permission set of mobile application A corresponding to the class output of the model, and judging the description of mobile application and the fidelity of permission. As that invention obtain richer semantic information, simple lexical analysis and grammatical analysis, moreaccurate fidelity judgment result are obtained.
Description
Technical field [0001] The present invention relates to the technical field of mobile applications, in particular to a method and device for determining the fidelity of mobile application description and authority based on deep learning. Background technique [0002] As a product of the organic combination of traditional Internet technology, mobile communication technology and smart terminals, the mobile Internet is an extension and evolution direction of the traditional Internet, and it has developed rapidly due to its high portability advantages. Mobile applications are the core of the development of the mobile Internet. In 2016, the number of mobile applications increased significantly year-on-year. According to the latest data, as of March 2017, the number of applications available in the Google Play app store alone has exceeded 2.8 million. It is true that the mobile Internet integrates the advantages of mobile communication anytime and anywhere communication with the openn...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/35G06F17/27G06F21/56G06N3/04
CPCG06F21/562G06F40/289G06F40/30G06N3/045
Inventor 陈亮冯缨岚郑子彬
Owner 杭州嘉洁网络科技有限公司