Model training method and device

By determining the user identity ID embedding vector in the first business model and using it for training of the second business model, the problem of overfitting in cross-service user feature processing is solved, and the training effect of the second business model is improved.

CN113850384BActive Publication Date: 2025-02-28VIVO MOBILE COMM CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111165495.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-30
Publication Date
2025-02-28
Estimated Expiration
2041-09-30

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

The present application discloses a model training method and device, which belongs to the field of data processing technology. The method includes: determining a user identity ID embedding vector according to a first business model corresponding to a first application; using the user ID embedding vector for training a second business model corresponding to a second application; wherein the user ID embedding vector is used to characterize user features corresponding to the user ID.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Semantic matching method and system, equipment and storage medium

    CN112287085A

  • Object recommendation method, device and equipment and storage medium

    CN112597395A