Keyword extraction method, apparatus and server

  • US 10,878,004 B2
  • Filed: 01/31/2019
  • Issued: 12/29/2020
  • Est. Priority Date: 11/10/2016
  • Status: Active Grant
First Claim
Patent Images

1. A keyword extraction method, comprising:

  • extracting, by a server, a candidate keyword from target text;

    obtaining, by the server for each candidate keyword, each effective feature corresponding to the candidate keyword;

    inputting, by the server, each effective feature corresponding to the candidate keyword to a keyword evaluation model, and obtaining a probability that the candidate keyword belongs to a target keyword by using the keyword evaluation model according to each effective feature corresponding to the candidate keyword and a weighting coefficient respectively corresponding to each effective feature; and

    determining the candidate keyword as the target keyword of the target text based on the probability,wherein the keyword evaluation model is based on a fusion between a gradient boosting decision tree (GBDT) model and a logistic regression (LR) model, andwherein the GBDT model comprises a plurality of decision trees, each leaf node of a decision tree corresponding to a processed effective feature, and a training sample of an LR algorithm, which is trained to obtain the LR model, is constructed according to a prediction result of each training sample of a GBDT algorithm, which is trained to obtain the GBDT model, in each of the plurality of decision trees.

View all claims
    ×
    ×

    Thank you for your feedback

    ×
    ×