System and method for automatically processing candidate resumes and job specifications expressed in natural language into a normalized form using frequency analysis

• US 8,117,024 B2
• Filed: 05/01/2008
• Issued: 02/14/2012
• Est. Priority Date: 05/01/2008
• Status: Active Grant

• Current Assignee: Cielo, Inc.
• Original Assignee: My Perfect Gig, Inc.
• Inventors: Dane, Mark
• Primary Examiner(s): Shaawat, Mussa A
• Application Number:
  US12/113,763
• Publication Number:
  US 20090276209A1
• Time in Patent Office: 1,384 Days
• Field of Search: None
• US Class Current: 704/9
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task

Abstract

Systems and methods for automatically processing candidate resumes and job specifications expressed in natural language into a normalized form using frequency analysis. A database of elements is provided in which each element is expressed in natural language and at least some of which are associated with a corresponding set of synonymous words or phrases. Candidate resumes and job specifications are received in electronic form and expressed in natural language. The candidate resumes and job specifications are analyzed to extract elements expressed in candidate resumes and job specifications. The extracted elements are compared to the database. For each extracted element, the most frequent element or synonym is identified an used as a common form for the extracted element. A set of candidate resumes is matched with a corresponding job specification by comparing the set of elements expressed in common form for the resumes with the set of elements expressed in common form for the job specification.

Claims

1. A method of processing candidate resumes and job specifications to match candidates with job specifications, comprising

providing a database of elements, each element expressed in natural language and at least some of which are associated with a corresponding set of synonymous words or phrases, the elements and the synonymous words or phrases each having a corresponding usage counter;

a server receiving candidate resumes and job specifications in electronic form and expressed in natural language, such that candidates skills and experiences are expressed in words and phrases;

a server analyzing the natural language expression of the candidate resumes and job specifications to extract elements expressed in candidate resumes and job specifications;

a server comparing the extracted elements to the database and updating the usage counters corresponding to the extracted elements such that the relative frequency of the words or phrases expressing skills and experiences is tracked;

a server for each extracted element, determining which of the extracted element or the corresponding set of synonymous words or phrases has the highest usage and using the word, phrase or element with the highest usage as a common form for the extracted element and;

a server matching a set of candidate resumes with a corresponding job specification by comparing the set of elements expressed in common form for the candidate resumes with the set of elements expressed in common form for the job specification.

2. The method of claim 1 wherein the elements, words or phrases in the database are captured from processing candidate resumes and job specifications and as new words or phrases are identified during processing they are subjected to a validation technique and valid elements are added to the database to make it a learning database.

3. The method of claim 1 wherein the received candidate resumes are in disparate formats.

4. The method of claim 1 wherein the estimated workforce supply includes required elements from the job specification.

5. The method of claim 4, further comprising recommending required job elements to be removed from the job specification.

6. The method of claim 1 wherein the elements include products used, tools used, industries, education level attained, role or job title, willingness to travel, or security clearance.