Method and apparatus for sorting related searches

Patent metadata

Field	Value
Publication number	US-2018189291-A1
Application number	US-201715625936-A
Country	US
Kind code	A1
Filing date	Jun 16, 2017
Priority date	Dec 29, 2016
Publication date	Jul 5, 2018
Grant date	—

Abstract

The present disclosure provides a method and apparatus for sorting related searches RS, wherein the method comprises: obtaining a query and obtaining RSes corresponding to the query; determining estimated click rates of the RSes respectively according to a click estimating model obtained from pre-training; sorting the RSes in a descending order according to the estimated click rates. The solutions of the present disclosure can improve the accuracy of the sorting results.

First claim

What is claimed is:

1 . A method of sorting related searches, wherein the method comprises:
obtaining a query and obtaining related searches corresponding to the query; determining estimated click rates of the related searches respectively according to a click estimating model obtained from pre-training; sorting the related searches based on the estimated click rates.

2 . The method according to claim 1 , wherein,
the determining estimated click rates of the related searches respectively according to a click estimating model obtained from pre-training comprises: for each related search, obtaining a user behavior feature of the related search respectively; considering the obtained feature as input of the click estimating model to obtain the estimated click rate of the related search output by the click estimating model.

3 . The method according to claim 2 , wherein,
the user behavior feature comprises: co-occurrence feature, quality control feature, click feature and semantic feature.

4 . The method according to claim 1 , wherein,
the sorting the related searches based on the estimated click rates comprises: sorting the related searches in a descending order according to the estimated click rates; or respectively determining guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches; sorting all related searches in a descending order according to the guiding capability scores; or respectively determining quality scores of related searches according to quality features of related searches; sorting the related searches by comprehensively considering the estimated click rates and quality scores of the related searches; or respectively determining guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches; respectively determining quality scores of related searches according to quality features of related searches; sorting the related searches by comprehensively considering the guiding capability scores and quality scores of the related searches.

5 . The method according to claim 4 , wherein,
the respectively determining the guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches comprises: performing the following processing for each related search: respectively obtaining click times of related searches further displayed within a recent predetermined time length after the user clicks the related search, adding up the click times, dividing the sum by times of further displaying related searches within the recent predetermined time length after the related search is clicked, to obtain the guiding capability feature of the related search; obtaining the click rate of the related search within the recent predetermined time length; calculating a product of the guiding capability feature of the related search and the click rate of the related search within the recent predetermined time length, and adding up the product with the estimated click rate of the related search after having gone through normalization processing to obtain the guiding capability score of the related search.

6 . The method according to claim 4 , wherein,
the respectively determining quality scores of related searches according to quality features of related searches comprises: as for each related search, determining the quality score of the related search in a fitting manner respectively according to the quality control feature, guiding capability feature and estimated click rate of the related search.

7 . The method according to claim 1 , wherein
the method further comprises: after sorting the related searches, displaying top N related searches after the sorting in a search result page.

8 . A device for sorting related searches, comprising:
at least one processor; and a memory storing instructions, which when executed by the at least one processor, cause the at least one processor to perform operation, the operation comprising: obtaining a query and obtaining related searches corresponding to the query; determining estimated click rates of the related searches respectively according to a click estimating model obtained from pre-training; sorting the related searches based on the estimated click rates.

9 . The device according to claim 8 , wherein,
the operation of determining estimated click rates of the related searches respectively according to a click estimating model obtained from pre-training comprises: for each related search, obtaining a user behavior feature of the related search respectively; considering the obtained feature as input of the click estimating model to obtain the estimated click rate of the related search output by the click estimating model.

10 . The device according to claim 9 , wherein,
the user behavior feature comprises: co-occurrence feature, quality control feature, click feature and semantic feature.

11 . The device according to claim 8 , wherein,
the operation of sorting the related searches based on the estimated click rates comprises: sorting the related searches in a descending order according to the estimated click rates; or respectively determining guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches; sorting all related searches in a descending order according to the guiding capability scores; or respectively determining quality scores of related searches according to quality features of related searches; sorting the related searches by comprehensively considering the estimated click rates and quality scores of the related searches; or respectively determining guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches; respectively determining quality scores of related searches according to quality features of related searches; sorting the related searches by comprehensively considering the guiding capability scores and quality scores of the related searches.

12 . The device according to claim 11 , wherein,
the operation of respectively determining the guiding capability scores of related searches according to the estimated click rates and guiding capability features of the related searches comprises: performing the following processing for each related search: respectively obtaining click times of related searches further displayed within a recent predetermined time length after the user clicks the related search, adding up the click times, dividing the sum by times of further displaying related searches within the recent predetermined time length after the related search is clicked, to obtain the guiding capability feature of the related search; obtaining the click rate of the related search within the recent predetermined time length; calculating a product of the guiding capability feature of the related search and the click rate of the related search within the recent predetermined time length, and adding up the product with the estimated click rate of the related search after having gone through normalization processing to obtain the guiding capability score of the related search.

13 . The device according to claim 11 , wherein,
the operation of respectively determining quality scores of related searches according to quality features of related searches comprises: as for each related search, determining the quality score of the related search in a fi

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Wang Wei
• Gui jia
• Cheng Jun
• Wang Kuipeng

Classifications

• G06F7/08

  Sorting, i.e. grouping record carriers in numerical or other ordered sequence according to the classification of at least some of the information they carry (by merging two or more sets of carriers in ordered sequence G06F7/16) · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06F17/3053 Primary

  Physics · mapped topic