Automatic mining method for demand identification template, demand identification method and corresponding device
An automatic mining and demand technology, applied in the computer field, can solve the problems of low query recall rate, consumption of human resources, low efficiency of demand identification templates, etc., and achieve the effect of improving recall rate and saving human resources.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] figure 1 The flow chart of the mining method for the requirement identification template provided by Embodiment 1 of the present invention, as shown in figure 1 As shown, the method includes the following steps:
[0069] Step 101: Determine the query set corresponding to when a preset type of webpage is clicked in the search log.
[0070] In this step, the following two methods can be used:
[0071] The first method: After the webpage type is determined by the existing webpage type identification method, webpages of the preset type are collected, and all queries corresponding to these webpages are determined in the search log to form a query set when they are clicked.
[0072] Among them, the web page classification method based on text features, or the method of calculating the similarity between the web page text feature vector and the feature vector of the preset type can be used to determine the type of each web page in the search log, and then collect the pre-set...
Embodiment 2
[0106] figure 2 The flow chart of the demand identification method provided by Embodiment 2 of the present invention, such as figure 2 As shown, the method includes the following steps:
[0107] Step 201: Match the query to be recognized with each preset type of dictionaries, replace the words in the query to be recognized that match the dictionary with the attribute tags of the corresponding words in the dictionary, and obtain the semantic annotation of the query to be recognized.
[0108] The query to be identified may be a query input by a user on a search interface provided by a search engine.
[0109] In this step, the replacement of the attribute tags for the query to be recognized is similar to the replacement of the attribute tags for the seed query in step 103 of the first embodiment, the difference is that the query to be recognized needs to be matched with the dictionary of each preset type.
[0110] For example: for the query to be identified "China Food Market...
Embodiment 3
[0122] image 3 The structural diagram of the automatic excavation device of the demand identification template provided by Embodiment 3 of the present invention, as shown in image 3 As shown, the apparatus may include: a first selection unit 301 , a second selection unit 302 , a marker replacement unit 303 and a template determination unit 304 .
[0123] The first selection unit 301 determines a set of queries corresponding to when a webpage of a preset type is clicked in the search log.
[0124] Specifically, the query set can be determined in the following two ways:
[0125] The first way: the first selection unit 301 determines the type of the webpage in the search log, collects the webpages of the preset type, and determines that all queries corresponding to the webpage of the preset type are clicked to form a query set. When determining the type of web pages in the search log, a web page classification method based on text features, or an existing method such as calcu...
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