Text based schema discovery and information extraction

• US 7,930,322 B2
• Filed: 05/27/2008
• Issued: 04/19/2011
• Est. Priority Date: 05/27/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: MacLennan, C. James
• Primary Examiner(s): Vital; Pierre M
• Assistant Examiner(s): OBISESAN, AUGUSTINE KUNLE
• Application Number:
  US12/127,017
• Publication Number:
  US 20090300043A1
• Time in Patent Office: 1,057 Days
• Field of Search: None
• US Class Current: 707/804
• CPC Class Codes: G06F 16/211 Schema design and management
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models

Abstract

Various technologies and techniques are disclosed for text based schema discovery and information extraction. Documents are analyzed to identify sections of the documents and a relationship between the sections. Statistics are stored regarding occurrences of items in the documents. A probabilistic model is generated based on the stored statistics. A database schema is generated with a plurality of tables based upon the probabilistic model. The documents are analyzed against the probabilistic model to determine how the documents map to the tables generated from the database schema. The tables are populated from the documents based on a result of the analysis against the probabilistic model.

Claims

1. A method for creating a database schema from unstructured documents comprising the steps of:

accessing an unstructured document;

extracting information from the unstructured document using text mining, the extracted information comprising terms, phrases and sentiments;

analyzing the extracted information to identify sections of the unstructured document;

storing statistics regarding an occurrence of items in the unstructured document, the items comprising the extracted information and identified sections;

repeating the accessing, extracting, analyzing, and storing steps for a plurality of unstructured documents;

creating a probabilistic model based on the statistics stored for the plurality of unstructured documents;

generating a database schema using the probabilistic model;

receiving user modifications to the probabilistic model;

updating the probabilistic model based upon the user modifications; and

generating a database based on the database schema generated using the probabilistic model.

2. The method of claim 1, wherein the document is analyzed using machine learning techniques.

3. The method of claim 1, wherein the document is analyzed using heuristics.

4. The method of claim 1, wherein the database schema is used to map data from the document to database tables.

5. The method of claim 1, wherein the items for which statistics are stored include terms.

6. The method of claim 1, wherein the items for which statistics are stored include fields.

7. The method of claim 1, wherein the items for which statistics are stored include lists.

8. The method of claim 1, wherein the items for which statistics are stored include sections.

9. The method of claim 1, wherein the analyzing step further comprises analyzing the extracted information to identify relationships between different sections of the document.

10. The method of claim 1, wherein during the extracting step, one or more dictionaries are utilized to aid in the extracting.

11. The method of claim 1, further comprising the steps of:

using the probabilistic model to generate analytical objects.

12. A computer storage medium having computer-executable instructions for causing a computer to perform steps comprising:

accessing an unstructured document;

extracting information from the unstructured document using text mining, the extracted information comprising terms, phrases and sentiments;

analyzing the extracted information to identify sections of the unstructured document;

storing statistics regarding an occurrence of items in the unstructured document, the items comprising the extracted information and identified sections;

repeating the accessing, extracting, analyzing, and storing steps for a plurality of unstructured documents;

creating a probabilistic model based on the statistics stored for the plurality of unstructured documents;

generating a database schema using the probabilistic model;

receiving user modifications to the probabilistic model;

updating the probabilistic model based upon the user modifications; and

generating a database based on the database schema generated using the probabilistic model.

13. The computer storage medium of claim 12, wherein the document is analyzed using machine learning techniques.

14. The computer storage medium of claim 12, wherein the document is analyzed using heuristics.