×

Scalable user intent mining using a multimodal restricted boltzmann machine

  • US 9,910,930 B2
  • Filed: 12/31/2014
  • Issued: 03/06/2018
  • Est. Priority Date: 12/31/2014
  • Status: Active Grant
First Claim
Patent Images

1. A method for scalable user intent mining implemented by at least one processor, comprising:

  • detecting named entities from a plurality of query logs in a public query log dataset, wherein the public query log dataset stores the plurality of query logs from a plurality of websites;

    based on the detected named entities, generating corresponding features of the plurality of query logs;

    applying a multimodal restricted boltzmann machine (RBM) on the corresponding features of the plurality of query logs to train a public multimodal RBM;

    generating a plurality of public query representations;

    receiving a search query from a user;

    determining whether there are a plurality of history queries of the user;

    when there is no history query of the user, predicting user intent using the public multimodal RBM; and

    when there are the plurality of history queries of the user, applying the public multimodal RBM on the plurality of history queries of the user to train a personalized multimodal RBM, and predicting the user intent using the personalized multimodal RBM, so that an accuracy of predicting the user intent is improved by using the personalized multimodal RBM.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×