Method and device for excavating badcase of search engine
A search engine and confidence technology, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as failure to timely and accurately find badcase, low efficiency, etc., and achieve the effect of improving efficiency and accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] figure 1 The flow chart of the mining method of the search engine badcase provided by Embodiment 1 of the present invention, such as figure 1 As shown, the method may include the following steps:
[0052] Step 101: extract a certain number of sessions from the session log as samples, and extract feature vectors describing search quality from each session of the samples.
[0053] Session refers to the time period during which the user communicates with the interactive system. It usually refers to the time elapsed from entering the interactive system to exiting the system, and there is still a certain room for manipulation. In the embodiment of the present invention, a session in the session log contains the behavior information of the user using the search engine.
[0054] The session logs of search engines are massive, and may be T (1T=1024G) level files per day, so in this step, only a certain number of sessions need to be extracted as samples, for example, 600 sessi...
Embodiment 2
[0086] figure 2 The search engine badcase mining device provided for the second embodiment of the present invention includes a preprocessing unit 200 and a mining unit 210, such as figure 2 As shown, the preprocessing unit 200 specifically includes a sample feature extraction module 201, a sample clustering module 202, and a confidence determination module 203, and the mining unit 210 specifically includes a query feature extraction module 211, a query category determination module 212, and a bad case discrimination module 213 .
[0087] The sample feature extraction module 201 extracts a certain number of sessions from the session logs as samples, and extracts feature vectors describing search quality from each session of the samples.
[0088] The sample clustering module 202 uses the feature vectors of each session to cluster the samples.
[0089] The confidence determination module 203 determines the confidence of each category obtained by clustering by the sample clust...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com