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

Mobile crowd sensing user income selection method

A mobile crowd sensing and user technology, applied in data processing applications, complex mathematical operations, instruments, etc., can solve the problems of reducing the accuracy of the optimal profit strategy selection method and the actual guiding value

Active Publication Date: 2019-09-13
HARBIN ENG UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ignoring the limitations of bounded rationality, modeling and analyzing user behavior games will deviate from the actual situation, reducing the accuracy and actual guiding value of the final optimal profit strategy selection method

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
  • Mobile crowd sensing user income selection method
  • Mobile crowd sensing user income selection method
  • Mobile crowd sensing user income selection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] The purpose of the present invention can be achieved through the following technical solutions:

[0056] A method for selecting mobile crowd sensing user revenue based on data quality assessment and evolutionary game, said method comprising the following steps:

[0057] The first step is to build the publisher-user evolutionary game model, which is defined as a quadruple, and the details are as follows:

[0058] 1) N=(N u ,N p ) represents both players in the evolutionary game, where N u means user, N p Indicates the publisher;

[0059] 2) W=(uw,pw) represents the choice of the strategies of both players in the game, where uw={uw 1 ,uw 2 ,...,uw n} represents the user's policy set, that is, the set of user data quality, pw={pw 1 ,pw 2 ,...,pw m} represents the strategy set of the publisher, that is, the task incentive set;

[0060] 3) R=(d,q) represents the set of strategy selection probabilities of both parties in the game, where d i Indicates that the publ...

Embodiment 2

[0116] The invention is applicable to the mobile crowd sensing revenue selection method that fully considers the user data quality. The invention models the entire mobile group intelligence sensing process as a publisher-user evolutionary game model, and evaluates the quality of user data therein. The design of various existing mobile crowd sensing revenue selection methods ignores the quality of data submitted by users, and most of the research on revenue games is based on individual rationality, which leads to the failure of user revenue to meet expectations. Based on this, the present invention first models the selection of the benefits of both parties as a publisher-user evolutionary game model; then, calculates the deviation degree of data quality according to the relevant attributes of the user uploaded data, and removes low-quality user data; The user solves the evolutionary strategy solution and conducts stability analysis to obtain the user's optimal profit strategy u...

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 provides a mobile crowd sensing user income selection method. The mobile crowd sensing user income selection method comprises the steps: firstly, selecting and modeling incomes of two parties as a publisher-user evolutionary game model; calculating a data quality deviation degree according to the related attributes of the data uploaded by the user, and removing low-quality user data;and carrying out evolution strategy solution solving and stability analysis on the screened users to obtain user optimal income strategies under different conditions. Compared with the prior art, themobile crowd sensing user income selection method has the advantages that all reasonable users are screened out in the user data evaluation stage; compared with two common anomaly detection methods for performance (namely, a BP method and an SVM method), the mobile crowd sensing user income selection method has the advantages of being high in abnormal data recognition accuracy and data classification accuracy; and meanwhile, under the condition that user data quality is confirmed, high-quality user data are selected as much as possible, so that the maximum benefits of bid winning users are guaranteed, and the overall effectiveness of a sensing platform is guaranteed.

Description

technical field [0001] The invention belongs to the field of mobile group intelligence sensing, and in particular relates to a method for selecting user benefits of mobile group intelligence sensing. Background technique [0002] In recent years, with the development of smart terminal devices, wireless networks and crowd sensing, mobile crowd sensing (Mobile Crowdsensing, MCS) has become a frontier research problem in cross-space and large-scale data sensing, which relies on the Mobile devices and their various sensors are used to complete a large number of perception tasks. Although the research on mobile crowd sensing has made great progress, with the popularization of smart phones, the diversification of user data and the existence of a large number of malicious users, how to ensure the reasonable benefits of users has become an urgent problem to be solved. [0003] Mobile crowd sensing uses the user's existing equipment for sensing, and the quality of the perceived data...

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): G06Q10/06G06Q30/02G06F17/11
CPCG06Q10/06395G06Q30/0226G06F17/11Y02D10/00
Inventor 王慧强邵子豪冯光升吕宏武郭方方
Owner HARBIN ENG UNIV
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