- Functionality for detecting new company web sites and validating existing URLs.

- Customized for specific customer requirements

- URL Detection starts with what all Yellow Pages offer - Company's Basic Data including company name, address, phon number.

- This information provides the foundation for us to generate URL candidates and match them with very high accuracy.

- URL Detection can be automatically validated when all matches are found with respect to the baseline listing information

- Manual Validation is recommended when only partial matches are found with respect to the baseline listing information through the included User Interface 

- Web Crawler retrieves files from the Internet based on a list of start pages - called seeds.

- The seeds constitue the initial queue of documents that the crawler will fetch, and then as each document is retrieved it is analyzed for links that should be added to the initial queue.

- Web Crawler is the foundation for other components of the content enrichment suite and forms a solid foundation to an advanced data mining system. 

- Web Crawler specializes in retrieving yellow information that is of utmost importance to online directories and IYPs.

- Entity Extraction finds more information about companies from their web sites.

- Entity Extraction finds keywords, images, company descriptions, videos, menus, phone numbers, email addresses, location information, payment types, opening hours, etc...

- This module comes with a baseline set of entities and can be highly customized for specific customer requirements

- Supports many different languages including English, Spanish, French, German.  

- Keyword Suggestion automatically generates relevant keywords for categories and companies within your taxonomy or current directory

- Has functionality for automatic generation of relevant keywords for every category and the companies within each and every heading

- Delivered with a fully functional baseline and can be highly customized for specific customer requirements

- Automatic generation of suggested keywords on company and category level based on detailed analysis of data crawled from company websites

- Performs an automatic  language detection and supports many different languages 

- Yellow Web Search (YWS) is a search module that can easily be integrated to extend your existing search solution with all content that is available on the Internet

- YWS makes use of all company information that exists on the company web site and uses it in search processing

- YWS refines the search process and the ranking process to yield better results

- YWS also enables local web search on company web sites to increase the search result relevance

- YWS delivers Yellow Search with integrated Web Search

- One of the major differences between online directories and print directories is the structure of an optimal taxonomy for the web

- In Print, publishers typically have between 2,500 up to 7,000 categories or headings.

- Experience has proven that for online Yellow Pages the optimal number of categories or headings is between 400 up to 1,500.

- Taxonomy Compression is a solution for automatic clustering of categories which simplifies the process of taxonomy compression while assuring the best quality of the resulting taxonomy set.

- This is based on a deep analysis of all information about the companies within each category or heading