Classification recognition method based on URL (uniform resource locator)
A classification recognition and category technology, applied in the Internet field, can solve problems such as storage overload, inability to crawl and index in advance, inability to complete online service requests, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] In Internet advertising matching, the current practice is to crawl the media pages, classify the web pages according to their text content by means of parsing and classification, and store the classifications in one-to-one correspondence with the URLs of the web pages in the index file. , when there is an advertisement request, go to the index to find the category information of the corresponding URL and then select the matching advertisement. The method of storing all web page URLs will lead to an overload of storage capacity, and all pages must be processed and classified offline, and new pages that have not been processed will not be classified in time, so that online service requests cannot be completed.
[0031] Aiming at these bottlenecks, the method proposed by the present invention assumes that classification structure information may exist in URLs, and a cluster of webpage content where similar URLs are located may correspond to similar classifications. The idea...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 