Unlock instant, AI-driven research and patent intelligence for your innovation.

Construction method of image-text knowledge base based on vertical search engine

A construction method and knowledge base technology, applied in the field of graphic knowledge base construction based on vertical search engines, can solve the problem of not being able to provide image-based retrieval, and achieve the effect of improving professionalism

Inactive Publication Date: 2017-05-31
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Text and image retrieval available for follow-up retrieval
This method improves the professionalism of the knowledge base and solves the problem that the knowledge base cannot provide image-based retrieval

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Construction method of image-text knowledge base based on vertical search engine
  • Construction method of image-text knowledge base based on vertical search engine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment one, refer to figure 1 As shown, a method for constructing a graphic knowledge base based on a vertical search engine is characterized in that it includes:

[0026] Step 101. Regularly and directionally crawl webpages of encyclopedia websites in the background of the server.

[0027] Step 102. Analyze the captured web encyclopedia knowledge content, and separate the content of the web page from text and graphics.

[0028] Step 103. Extract texture features, color features, shape features, etc. of the image, and construct image weighted features.

[0029] Step 104. Build an index according to the name of the constructed knowledge base, and associate and store text descriptions, images and image features in the webpage.

[0030] Step 105. Provide text-based retrieval and image feature matching retrieval feedback during retrieval, and the feedback information includes image and text description.

[0031] The server background regularly and directionally grabs...

Embodiment 2

[0036] Embodiment two: reference figure 2 As shown, a method for building a graphic knowledge base based on a vertical search engine is characterized in that it includes:

[0037] In step 201, construct the noun database of plant names and animal names, and give the category of the knowledge base and the corresponding noun database according to the knowledge base to be constructed. For example, construct the flower vocabulary, then list the corresponding flower names.

[0038] In step 202, build a website URL database for directional search, set multiple encyclopedic knowledge websites including Wikipedia Chinese, Baidu Encyclopedia, and Interactive Encyclopedia as the information source of the knowledge base, and then analyze the classification structure of these websites , according to the set theme, select the webpage of the theme category.

[0039] In step 203, the directional information is captured, and the information of the set web page is captured and saved through ...

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

No PUM Login to View More

Abstract

The invention provides a construction method of an image-text knowledge base based on a vertical search engine. The method comprises the following steps: capturing webpages of encyclopedia websites on a background of a server on time and directionally, analyzing contents of captured network encyclopedic knowledge, respectively extracting image-text information in the webpages, extracting textural features, color features, shape features and the like of images to form an image weighting feature, creating an index according to given keywords names based on the image weighting feature, performing association storage on text descriptions, images and image features in the webpages, and finally providing a retrieval mode based on texts and images for a user, wherein a retrieval result comprises image and text descriptions. The invention provides the method for constructing the image-text knowledge base with an image-text inquiry function, so that quick sharing of knowledge is realized.

Description

technical field [0001] The invention relates to the construction of a graphic knowledge base, in particular to a method for building a graphic knowledge base based on a vertical search engine. [0002] technical background [0003] With the rapid growth of the mobile Internet, the demand for searching and querying encyclopedic knowledge through smart terminals is growing rapidly. At present, encyclopedia knowledge is distributed in many related professional websites, such as Wikipedia, Baidu Baike, Hudong Baike. General search engines can be used to obtain relevant knowledge. [0004] These knowledge bases are usually huge in size and rich in pictures and texts. The same knowledge is often distributed in different websites, and it is difficult to obtain comprehensive information of this type of knowledge at one time. At the same time, these encyclopedic knowledge websites only provide classification query and text retrieval functions. Therefore, a vertical search engine is...

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
no application Login to View More
IPC IPC(8): G06F17/30
Inventor 雷方元戴青云赵慧民蔡君魏文国罗建桢
Owner GUANGDONG POLYTECHNIC NORMAL UNIV