Automatic marking based head word extracting method and device
A technology of automatic labeling and extraction method, applied in the computer field, can solve the problems of central word deviation, time-consuming and laborious, infeasible, etc., and achieve the effect of high accuracy
Inactive Publication Date: 2016-04-27
BEIJING QIHOO TECH CO LTD +1
View PDF6 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] At present, the method of extracting central words is mainly through manual labeling: manual labeling of central words can only be applied to a very small number of query words, and manual labeling is obviously not feasible when the number of query words is huge, and manual labeling The extraction of central words cannot be automated, so it has the following disadvantages: (1) it requires more manpower, time, and time-consuming; (2) everyone’s evaluation standards are different, resulting in deviations in the marked central words; (3) it cannot Automatically extract the center word of the query word; (4) not suitable for the center word extraction of a large number of query words
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0025] Such as figure 1 As shown, an embodiment of the present invention provides a method for extracting a central word based on automatic labeling, including:
[0026] Step 110, from the search records, multiple query words corresponding to the same address clicked in multiple search behaviors are obtained. In this embodiment, the url (address) click log is generated through the user's multiple search behaviors, and the log form...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an automatic marking based head word extracting method and device. The method comprises: obtaining multiple query words corresponding to a same address clicked in multiple searching behaviors from a searching record; performing word segmentation on the query words to obtain multiple words; calculating feature attributes of the words; screening from the words according to the feature attributes, and using the screened words as the head word of at least one query word in the multiple query words. According to the invention, the head word can be accurately extracted from the query words, the query words with the head word can be used for training a model for extracting a head word of the query words, the model is used for automatically extracting the head word of the query words, and extracting speed and accuracy are both very high, and subsequent fast query recommending based on the head word can be facilitated.
Description
technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for extracting central words based on automatic labeling. Background technique [0002] Query word recommendation is based on the query words currently searched by the user, through machine learning algorithms, to extract the core words of the query words, and recommend other query words that the user is most likely to be interested in. [0003] At present, the way to extract central words is mainly through manual labeling: manual labeling of central words can only be applied to a very small number of query words, and manual labeling is obviously not feasible when the number of query words is huge, and manual labeling The extraction of central words cannot be automated, so it has the following disadvantages: (1) it requires more manpower, time, and time-consuming; (2) everyone’s evaluation standards are different, which leads to deviations in the mar...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/951G06F40/258
Inventor 刘鎏伍兆盖肖峰
Owner BEIJING QIHOO TECH CO LTD