Crowdsourcing-based user demand active prediction method and system
The invention provides a crowdsourcing-based user demand active prediction method and system, and the method comprises the following steps: S1, determining a labeler participating in a crowdsourcing task, and enabling the labeler to receive the crowdsourcing task and complete the task; s2, construct...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
16.03.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides a crowdsourcing-based user demand active prediction method and system, and the method comprises the following steps: S1, determining a labeler participating in a crowdsourcing task, and enabling the labeler to receive the crowdsourcing task and complete the task; s2, constructing a heterogeneous information network according to the user preference information; s3, generatinga user demand data space; s4, respectively learning representation vectors of the user and the demand object through a graph convolutional neural network; s5: performing demand prediction. Accordingto the invention, the user directly participates in information production and knowledge sharing through a crowdsourcing technology, preference information fed back by a crowdsourcing annotator can better reflect the real demand of the user, and the accuracy of a result can be improved by performing demand prediction in combination with the information; the user preference information collected inthe crowdsourcing mode enr |
---|---|
Bibliography: | Application Number: CN202011387991 |