Crowdsourcing task pricing optimization method and system for mobile platform
A mobile platform and optimization method technology, applied in the field of data analysis, can solve problems such as unreasonable pricing and server pressure
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] Such as figure 1 As shown, the present invention provides a mobile Internet platform crowdsourcing task pricing optimization method. One embodiment of the present invention is to set the price for tasks in the "Photographing and Making Money" APP. "Make money by taking photos" is a self-service model under the mobile Internet. The user downloads the APP, registers as a task demander of the APP, and then receives a task that needs to be photographed from the APP (such as going to a supermarket to check the availability of a certain product), and earns the remuneration specified by the APP for the task.
[0063] (1) Data visualization: collect mobile Internet self-service crowdsourcing data, visualize and preprocess the data;
[0064] This implementation collects the task item data and task demander information data of the "Photograph to Make Money" APP. The completed task item data includes the location (indicated by latitude and longitude), pricing and completion stat...
Embodiment 2
[0104] (2-8) According to the location of the cities displayed in (1), after consulting the data, we obtained the corresponding GDP data of Guangzhou, Shenzhen, Dongguan and Foshan in Guangdong Province in 2016, as shown in Table 3. According to the GDP values of the four cities, the four cities are divided into four levels, as shown in Table 4:
[0105] Table 3 GDP value of cities in Guangdong Province in 2016
[0106] city
[0107] Table 4 GDP grades of cities in Guangdong Province in 2016
[0108] city
[0109] In the described step (2-9), feature expansion includes: extended task demander reputation information (mean value, variance, standard deviation, maximum value, minimum value, mode, mode number, mode number ratio ), the extended linear distance information between the position of the task demander and the task position (mean value, variance, standard deviation, maximum value, minimum value, mode, mode number, mode number ratio), extended task r...
Embodiment 3
[0111] In described step (2-10), use filtering method to carry out feature selection, to the feature in (2-9), utilize variance selection method to carry out feature selection, set threshold value to be 10, select the feature with variance greater than threshold value, as The final selected features are used to optimize the pricing model. There are a total of 39 features selected in this example, mainly including the number of task demanders within the analysis range, the credibility information of task demanders (mean value, variance, standard deviation, maximum value, minimum value, mode, mode number, The proportion of the mode number), the distance information between the position of the task demander and the task position (mean value, variance, standard deviation, maximum value, minimum value, mode number, mode number, mode number proportion), task Demanders can book task quota information (mean value, variance, standard deviation, maximum value, minimum value, mode number...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com