Resource allocation method and device based on artificial intelligence, electronic equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a resource allocation method and device based on artificial intelligence, electronic equipment and a medium, and the method comprises the steps: extracting a capability label of a tagger from a tagger portrait, and when determining to allocate a plurality of to-be-tagged resources, classifying each to-be-tagged resource to obtain a category, therefore, difficulty prediction is carried out on each to-be-labeled resource based on the category to obtain the labeling difficulty, the prediction accuracy of the labeling difficulty is improved, then a labeling model is established based on the multiple capability labels and the multiple labeling difficulties, convex optimization solution is carried out on the labeling model, and the labeling model with known labeling parameters is obtained. And finally, on the basis of a labeling model with known labeling parameters, the labeling accuracy of each labeling person on the to-be-labeled resources can be calculated, so that the to-be-labeled resources are allocated on the basis of the labeling accuracy. According to the method and the device, the capability label of the tagger is matched with the tagging difficulty of the to-be-tagged resource, so that the accuracy of tagging the to-be-tagged resource is improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based resource allocation method, device, electronic equipment and medium. Background technique [0002] Crowdsourcing refers to the practice that a company or organization outsources the work tasks performed by employees in the past to a non-specific public network in a free and voluntary manner. The tasks of crowdsourcing are usually undertaken by individuals, but the distribution of crowdsourcing tasks is urgently needed. solved problem. [0003] In the process of implementing the present invention, the inventors found that in common crowdsourcing tagging systems, the taggers' acquisition tasks are often randomly generated. However, the random generation method does not take into account the annotator's preference and professional level differences, and the difficulty of the resources to be annotated is also uneven. It is eas...

AI Technical Summary

Problems solved by technology

However, the random generation method does not take into account the annotator's preference and professional level differences, and the difficulty of the resources to be annotated is also uneven. It is easy to push resources that the annotator is not good at or not interested in to the annotator, resulting in poor annotation quality

Images