Swarm intelligence perception system user recommendation method
A crowd-sensing system, a technology for recommending users, applied in data processing applications, instruments, resources, etc., can solve the problems of low information utilization, high task push overhead, etc., and achieve the effect of large benefits and effective user recommendation
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2018-05-15
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of crowd-sensing system optimization, and in particular relates to a method for recommending users of the crowd-sensing system, which is used to reduce task pushing costs and improve the platform revenue of the crowd-sensing system. Background technique
[0002] At present, the crowd-sensing system has a large number of registered users, which causes the problem of excessive network overhead for platform push tasks. At the same time, due to the different interests and preferences of users in the swarm intelligence network system and the uneven quality of users, the utilization rate of task push information is too low. A feasible way to solve the above problems is to evaluate the data quality of registered users and use relevant recommendation methods to obtain high-quality user groups. User data quality is usually fixed during the execution of a task, which can measure the performance of the user in the tas...
Examples
Embodiment Construction
[0046] The method of the present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.
[0047] Such as figure 1 Shown is the feedback status of different users when the crowd sensing system (platform) releases a task. When the platform Platform releases a task, there are three different types of user groups in the user Mobile Users, namely the normal user Preferred User, the uninterested user User Non-interested User and malicious user MaliciousUser, aiming at the Information Push pushed by the platform, the behaviors of these three types of users are respectively submitting feedback quotation Reply Budget, not participating and feedback quotation Reply Budget.
[0048] Below to figure 1 The model shown takes the ambient temperature detection task in a certain area as an example to illustrate the implementation process of the present invention.
[0049] In the group intelligence sensing task of environmenta...