Information Extraction Software 

General Introduction to Information Extraction Software

Colander is a cooking utensil with perforations for draining off liquids and rinsing food. In dealing with Word documents we also need a tool like colander to filter out the contents we want.

Information extraction software is a tool just like colander which can read specified word documents in quantity, and convert specified contents into files in Excel format. When you need repeatedly copy and paste contents from word document into a new table, the information extraction software can work for you. How to Purchase

There are two ways of using the information extraction software: the users purchase the information extraction software，read the contents from word document by themselves, or entrust Yuantai data management company to process the information extraction. Users can also freely experience the service of information extraction online. Operation Direction

To experience online extraction, your computer needs the following operating environment:
1. .net Framework 2.0
2. Allow the browser to download ActiveX controls; understand the operational environment Settings
3. Download installation files, install extraction software. Download
If your computer meets the above conditions, you can experience extraction software directly, with one document each time and just 10 times one day.

If you want to experience such information extraction software permanently, you can purchase this service online. Long-term application methods

Application
University library builds papers’ index with information extraction software from students who submit their graduation theses;
Government agency generates roster or list with information extraction software from the application forms submitted from other agencies;
Large regional company builds some new statistical reports with information extraction software after receiving the reports from its branch companies;
Government agencies can automatically generate the table of government public information by information extraction software when submitting it.

Application Examples
A personnel administration department, which is responsible for checking submitted application forms on talented persons’ training, will issue the relevant funds after careful verification. The submitted materials usually cover two sets with one in paper and one in electronic version. To prepare for the experts’ assessment, department staff has to draw up a roster which contains the entire names of applicants. Normally, the office worker needs to open every application form, to look for the applicant's name, sex, education, unit, training condition, and the applicant's background etc. The staff must spend 3 to 5 minutes to finish an application form, constantly copying and pasting, and he will spend a whole day for dealing with 100 such applications. Besides, intense concentration is required, otherwise long time will be spent if the stuff also answers the phone or handles other business meanwhile. Yet it can be finished within a few minutes with information extraction software, which automatically generates a roster in Excel format.
University library needs to receive graduation theses, build index for future retrieval. But each year thousands of paper workload does discourage the staff, who can easily accomplish this job by using the information extraction software. University library can install a paper receiving entry, such as E-mail or FTP upload window, and after receiving students’ uploading papers, it can automatically generate theses index via information extraction software.

A branch company regularly needs to write a performance report in Word format, containing statistics, and its superior company collects these data, generates report form in Excel format for further statistical analysis. Manual data collecting needs constantly to open every performance report and copy its contents into a new form, which consumes a lot of time. With information extraction software, the related contents can be automatically read.

According to Government Regulations on Public Information, various administration departments should submit public files for government information in public viewing places such as archives, libraries etc. Archives and other departments will make catalogue for those files for future retrieval. The workload will be hard if the documents are huge. Using information extraction software can automatically process the received electronic documents and generate machine-readable catalogue.

To correctly use information extraction software, a document template with embedded XML tags should be used. Such document template can be designed by users themselves, or entrusted by Yuantai Company.

Example: University library reads related contents from a graduation thesis and generates index.
Example: two students’ papers in Word document.

Example: Using information extraction software can automatically generate papers index in Excel format.
Papers Index

Name	Title	College	Speciality	Grade	Instructor	Date
Tomas	Information Exchange Based on the metadata	Computer College	E-Commerce	2006	Brown	Aug, 2010.
Henry	XML Application in Document Management	Computer College	Software Engineering	2005	James	Aug, 2009
…

Example: A government department reads contents from application forms and generates a roster. The following are two application forms.

Funding Application Form

 

Funding Application Form

In the past when we fill in these application forms, we usually copy the contents of each item by hand, and paste them in the corresponding column. The mouse clicks between the Word and the Excel repeatedly, copying and pasting all the time. Why not use information extraction software to process them automatically?

Use information extraction software to automatically read relevant content and generate a roster.

Roster

Name	Application Category	Graduation colleges	Gender	Nationality	Date of Birth	Birthplace	Application Project	Present Technical position	Total Sum
John Smith	Private	Peking University	Male	Han	Nov,22, 1977	Xujiahui district ,Shanghai	Material Engineering research	Senior Engineer	20,000
Jean Truman	Going Abroad	Liaoining University	Female	Korean	Dec 1, 1978	Shenyang City, Liaoning province	Agricultural statistics comparison	Senior engineer	40,000
…

Example: As grass-roots companies report their performance, the superior company will automatically read relevant contents from the reports.
Example: Performance Report from the First Branch

Example: Performance Report from the Second Company, in Word document

Example: using information extraction software will automatically generate sales and leasing statistics in Excel format.

Housing Sales and Leasing Statistics

Company name	Sales month	Sales number	Sales area	Sales amount	Sales commissions	Lease number	Lease area	Lease amount	Lease commission
The 1st branch	1	20	2000	2000000	20000	12	1200	12000	1200
The 1st branch	2	19	1900	1900000	19000	11	1100	11000	1100
The 2nd branch	1	10	1000	100000	10000	6	600	6000	600
The 2nd branch	2	9	900	900000	9000	5	500	5000	500

Example:  When grass-roots companies submit documents, the superior department will automatically read related files.
Example: Documents of a certain bureau or a committee in Word document

Example: using information extraction software will automatically generate submitted documents directory in Excel format
Documents Directory Submitted

Sending authority	Document title	Sending date	File No.	keywords
xx Bureau of Inner Mongolia	Notice on strengthening the safety production	September 5, 2010	Supervised by Inner Mongolia × Bureau【 2010】No.11	Economy; safety production; notice
x x Committee of Inner Mongolia	Notice on improving management level	August 12, 2010	Supervised by Inner Mongolia × Committee【 2010】No.1211	Investment; management; notice