Research on Mobile Network User Complaint Warning Method Based on Multimodal Data

Abstract

With the rapid development of information and communication technology, the types of service applications for mobile terminals are becoming increasingly diverse. Each application has varying requirements for network performance, and each user's preferences, usage frequency, and sensitivity are different. When the quality of the operator network cannot meet the specific service needs of users and exceeds the threshold that users can tolerate, it will trigger user complaints. This article proposes a method for mobile network user complaint warning based on multimodal data. The method can be used to identify potential complaint users in the network and reduce the number of user complaints. In this method, a multimodal user level application rating feature dataset is constructed based on multi-source data, combined with factors such as user preferences and usage perception. Then, AI algorithms and great network computing power are used to generate complaint prediction models for different service applications at the user level. By integrating multiple application business complaint models at the user level and comprehensively evaluating user complaint expectations, it is used to improve the accuracy of user complaint warning.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.