Focus on vertical search engines

Vertical search is a professional search engine for a certain industry. It is a subdivision and extension of search engines and an integration of some specialized information in the Web library, extract the required data from the fields for processing and then return it to the user in some form. Compared with the new search engine service model proposed by general search engines, such as the large amount of information, inaccurate query, and insufficient depth, provides valuable information and related services for a specific domain, a specific population, or a specific demand. Compared with general search engines, vertical search engines are more focused, specific, and in-depth. They are specialized, refined, and deep, and industry-specific.

Introduction vertical search engine is a new search engine service model proposed by general search engines, such as large information, inaccurate query, and insufficient depth, provides valuable information and related services for a specific domain, a specific population, or a specific demand. Compared with general search engines, vertical search engines are more focused, specific, and in-depth. They are specialized, refined, and deep, and industry-specific.

Differences between vertical search engines and normal Web Search

The biggest difference between a vertical search engine and a common web search engine is that structured information is extracted from webpage information, that is, unstructured data of webpages is extracted into specific structured information data, for example, web page search is based on the smallest unit of web page, visual-based web page block analysis is based on the smallest unit of Web Page blocks, and vertical search is based on the smallest unit of structured data. The data is then stored in the database for further processing, such as deduplication and classification. The final word segmentation and index are then searched to meet users' needs. During the entire process, data is extracted from unstructured data into structured data, which is returned to users in an unstructured and structured manner after deep processing. A technical expert at Microsoft Research Institute once said: "75% of the content cannot be searched by a search engine ". Vertical search engines are born to improve the search accuracy and query accuracy to a greater extent ". Vertical search engines collect or organize information models and user models in the industry to provide more professional and personalized industry-related services.

Application direction

Vertical search engines have many application directions, such as enterprise database search, supply and demand information search engine, shopping search, real estate search, talent search, mp3 search, image search ...... Almost all types of information in various industries can be further refined into various vertical search engines. For example, it is easier to understand. For example, the overall process of the shopping search engine is roughly as follows: after a webpage is crawled, the product information on the webpage is extracted, and the product name, price, and description are extracted ...... The notebook introduction can even be further subdivided into "brand, model, CPU, memory, hard disk, display ,......" Then, information is cleaned, de-duplicated, classified, analyzed and compared, and data is mined. Finally, user search is provided through word segmentation index, and market quotation report is provided through analysis and mining.

Technology

Vertical search engines generally require the following technologies:

System Structure

1. search engine crawler: crawlers crawl webpages on the Internet. structured Information Extraction Technology or metadata collection technology for web pages: extracting structured data from web pages 3. word Segmentation and indexing: store and index data 4. data Presentation: Because the stored data is not simple webpage data, you need to consider displaying data based on industry needs. other information processing technologies

Technical evaluation

The technical evaluation of vertical search engines should be judged from the following points: 1. comprehensiveness 2. updatability 3. Accuracy 4. The entry threshold for functional vertical search is very low, but the competition threshold is very high. No focus or superb technology is acceptable. Industry portal websites have industry advantages, but they do not have any technical advantages. never imagine that you can recruit a few people to complete all the technologies of vertical search, as a product that requires continuous improvement and can be operated rather than a project, the degree of technical control is one of the important factors for the success of vertical search. Introduction vertical search engine is a new search engine service model proposed by general search engines, such as large information, inaccurate query, and insufficient depth, provides valuable information and related services for a specific domain, a specific population, or a specific demand. Compared with general search engines, vertical search engines are more focused, specific, and in-depth. They are specialized, refined, and deep, and industry-specific.

Differences between vertical search engines and normal Web Search

The biggest difference between a vertical search engine and a common web search engine is that structured information is extracted from webpage information, that is, unstructured data of webpages is extracted into specific structured information data, for example, web page search is based on the smallest unit of web page, visual-based web page block analysis is based on the smallest unit of Web Page blocks, and vertical search is based on the smallest unit of structured data. The data is then stored in the database for further processing, such as deduplication and classification. The final word segmentation and index are then searched to meet users' needs. During the entire process, data is extracted from unstructured data into structured data, which is returned to users in an unstructured and structured manner after deep processing.

A technical expert at Microsoft Research Institute once said: "75% of the content cannot be searched by a search engine ". Vertical search engines are born to improve the search accuracy and query accuracy to a greater extent ". Vertical search engines collect or organize information models and user models in the industry to provide more professional and personalized industry-related services.

 

Vertical search engines have many application directions, such as enterprise database search, supply and demand information search engine, shopping search, real estate search, talent search, map search, mp3 search, image search ...... Almost all types of information in various industries can be further refined into various vertical search engines. For example, it is easier to understand. For example, the overall process of the shopping search engine is roughly as follows: after a webpage is crawled, the product information on the webpage is extracted, and the product name, price, and description are extracted ...... The notebook introduction can even be further subdivided into "brand, model, CPU, memory, hard disk, display ,......" Then, information is cleaned, de-duplicated, classified, analyzed and compared, and data is mined. Finally, user search is provided through word segmentation index, and market quotation report is provided through analysis and mining.

 

Vertical search engines generally require the following technologies:

　　

System Structure

1. Search Engine crawler: crawlers can capture webpages on the Internet.

2. Web structured information extraction technology or metadata collection technology: extracting structured data from web pages

3. Word Segmentation and indexing: store and index data

4. Data Presentation: Because the stored data is not simple webpage data, you need to consider displaying data based on industry needs.

5. Other information processing technologies

 

Technical evaluation of vertical search engines should be determined based on the following points:

 

1. Comprehensiveness

2. Update

3. Accuracy

4. Functionality

Vertical search has a low entry threshold, but the competition threshold is high. No focus or superb technology is acceptable. Industry portal websites have industry advantages, but they do not have any technical advantages. never imagine that you can recruit a few people to complete all the technologies of vertical search, as a product that requires continuous improvement and can be operated rather than a project, the degree of technical control is one of the important factors for the success of vertical search.