System and method for normalizing a resume

• US 6,874,002 B1
• Filed: 07/03/2001
• Issued: 03/29/2005
• Est. Priority Date: 07/03/2000
• Status: Expired due to Fees

• Current Assignee: Talemetry, Inc. (Jobvite Incorporated)
• Original Assignee: MagnaWare, Inc. (Jobvite Incorporated)
• Inventors: Peleus, Joakim F., Villanueva, Claro
• Primary Examiner(s): Alam, Shahid
• Assistant Examiner(s): TRUONG, CAM Y T
• Application Number:
  US09/898,171
• Time in Patent Office: 1,365 Days
• Field of Search: 707 1- 3, 707/6, 707/10, 707/204, 715/536, 715/513, 715/505, 715/523, 207 1- 3, 207/10, 207/206
• US Class Current: 707/812
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: Y10S 707/947 Human resources
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99955 Archiving or backup

Abstract

A computer based system and method for creating a standardized or normalized resume format, extracting resume information from the normalized resume, and automatically inputting the resume information into a resume database.

Claims

1. A computer implemented method of transferring alien free-text, unstructured multi-lingual information from a resume to a discreet information categorization, comprising:

a) pre processing a resume using lexical and content analysis to;

i) determine the language of the resume;

ii) determine the origin of the resume;

iii) determine to layout and general topology of the resume; and

iv) determine the discreet type of the resume based on the determined language, layout and topology of the resume;

b) selecting a processing template based on steps a.i. to a.iv. and inputting the template into memory, said template having a discreet (predetermined) number of layouts, topologies and categories and sets or series of sections of text information for each category;

c) providing a set of default templates per determined language when the lexical and content analysis fails to determine the layout, topology and type of the resume;

d) implementing the default templates to allow the system to extract the most important information on the resume allowing an automated contact generation and response to a resume originator,

e) automatically generating a contact or response to the resume originator by either electronic or paper based means;

f) normalizing the resume by using the template to associate each resume content section with a discreet information category thereby creating a plurality of normalized resume contents; and

g) automatically transferring each normalized resume content to a resume data section within a discreet data store comprising a database or a tagged data store including XML in which each said resume data section is identified by a storage section identifier comprising a fieldname or a tag-name mapped to the normalized resume content.

2. The method of claim 1 in which at least one keyword matches a sequence of characters within a resume heading or a resume content.

3. The method of claim 1 in which one syntactical language categorization matches a sequence of characters section within a resume heading.

4. The method of claim 1 in which one syntactical language categorization matches a sequence of characters section within a resume content.

5. The method of claim 1 in which the resume is in a language other than English.

6. The method of claim 1, wherein in step d) if a resume type determined that a default template is used, then the default template is based on the determined language.

7. The method according to claim 6, wherein implementing the default template comprises searching for alternative lexical and language structures, layouts, topologies and keywords of a group to associate a resume content with the category associated with the group.

8. The method according to claim 6, wherein step f) further comprises:

identifying any unmatched resume content not associated with any group of alternative layouts, topologies and keywords;

searching the unmatched resume content for a field locator; and

associating the unmatched resume content with a fieldname corresponding to the field locator if the field locator is found in the unmatched resume content.

9. The method according to claim 8, wherein the field locator comprises a sequence of characters that is indicative of resume content in resumes.

10. The method according to claim 1, wherein step a.iv. of determining a resume type comprises locating a parcel identifier in the resume, wherein the parcel identifier is a unique character string that is indicative of a particular job board.

11. A system for transferring free text, unstructured, multi-lingual information from a resume to a discreet data store comprising:

means for inputting a resume into a memory, said resume being of unknown language and having a plurality of resume contents;

means for pre processing the resume using lexical and content analysis to determine the language of the resume;

means for pre processing the resume to determine a resume type based on the language and the lexical and content analysis of the resume;

means for selecting a processing template based on the resume type, and inputting the template into memory, the template having a discreet number of layouts, topologies and categories and sets or series of sections of text information for each category;

means for normalizing the resume by using the template to associate each resume content section with a discreet information category thereby creating a plurality of normalized resume contents;

means for automatically transferring each normalized resume content to a data section within a discreet data store comprising a database or a tagged data store including XML in which each said resume data section is identified by a storage section identifier comprising a fieldname or a tag-name mapped to the normalized resume content; and

means for an automated resume response mechanism to a resume originator using either electronic or paper based.

12. A computer readable medium having program code recorded thereon that, when executed, causes a computing system to transfer free text, multi-lingual information from a resume to a data store, the program code comprising:

code for inputting a resume, of unknown origin, content and format, into memory, said resume having a plurality of language, layout and contents;

code for preprocessing the resume, using lexical and content analysis, to determine the origin and language of the resume;

code for preprocessing the resume to determine a resume type based on the determined language, origin, layout and topology of the resume;

code for selecting a template based on the determined type of resume and inputting the template into memory, said template having a discreet number of layouts, topologies and categories and sets or series of sections of text information for each category;

code for selecting a default template when the resume type cannot be determined to allow the system to extract the most important information on the resume allowing an automated contact generation and response to the resume originator;

code for automatically transferring each normalized resume content to a data section within a discreet data store comprising a database or a tagged data store including XML in which each said resume data section is identified by a storage section identifier comprising a fieldname or a tag-name mapped to the normalized resume content; and

code for automatically generating a contact or response to a resume originator using either electronic or paper based means.