Resume extraction based on a resume type

• US 10,643,182 B2
• Filed: 03/16/2016
• Issued: 05/05/2020
• Est. Priority Date: 03/16/2016
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Cengiz, Yasin, Spaulding, Kent A., B'Far, Reza, Yin, Xin, Maldonado, Mario S.
• Primary Examiner(s): Ouellette, Jonathan P
• Application Number:
  US15/072,256
• Publication Number:
  US 20170270484A1
• Time in Patent Office: 1,511 Days
• Field of Search: 705 11-912
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 10/1053 Employment or hiring

Abstract

Résumé value extraction based on a résumé type is disclosed. An analysis model, for analyzing a résumé, is selected based on a résumé type of the résumé. An example of a résumé type is a job industry associated with the résumé. Different analysis models are used to analyze résumés corresponding to different résumé types. The analysis model is used to identify résumé values, in the résumé, that correspond to résumé attributes associated with the résumé type. Additionally or alternatively, the analysis model is used to identify segments, in the résumé, that correspond to segment types associated with the résumé type. After a segment type of a particular segment is identified, résumé values within the particular segment are analyzed based on the segment type of the particular segment.

Claims

1. A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:

obtaining a first ré

sumé

associated with a first user;

obtaining a first set of information that is external to and associated with the first ré

sumé

,

wherein obtaining the first set of information comprises one or more of;

identifying a geographical region of the first user, as the first set of information, from a first user profile separate from the first resume;

identifying a job type sought by the first user, as the first set of information, based on the first user profile separate from the first resume;

or

identifying a job posting, as the first set of information, for which the first resume is submitted;

based on the first set of information, determining a first ré

sumé

type, of a plurality of ré

sumé

types, corresponding to the first ré

sumé

;

selecting a first analysis model, of a plurality of analysis models, based on the first ré

sumé

type corresponding to the first ré

sumé

, wherein each of the plurality of analysis models is associated with a respective ré

sumé

type;

applying the first analysis model to extract, from the first ré

sumé

, a first ré

sumé

value corresponding to a first ré

sumé

attribute associated with the first ré

sumé

type;

storing the first ré

sumé

value, or a representation of the first ré

sumé

value, in association with the first ré

sumé

attribute of a first ré

sumé

profile;

obtaining a second ré

sumé

associated with a second user;

obtaining a second set of information that is external to and associated with the second ré

sumé

;

based on the second set of information, determining a second ré

sumé

type, of the plurality of ré

sumé

types, corresponding to the second ré

sumé

;

selecting a second analysis model, of the plurality of analysis models, based on the second ré

sumé

type corresponding to the second ré

sumé

;

applying the second analysis model to extract, from the second ré

sumé

, a second ré

sumé

value corresponding to a second ré

sumé

attribute associated with the second ré

sumé

type, wherein the first analysis model and the second analysis model are different; and

storing the second ré

sumé

value, or a representation of the second ré

sumé

value, in association with the second ré

sumé

attribute of a second ré

sumé

profile.

2. The medium of claim 1, wherein analyzing the first ré

sumé

based on the first analysis model comprises identifying the first ré

sumé

value for associating with the first ré

sumé

attribute corresponding to the first analysis model.

3. The medium of claim 1, wherein analyzing the first ré

sumé

based on the first analysis model comprises identifying a segment for associating with a segment type corresponding to the first analysis model.

4. The medium of claim 1, wherein determining the first ré

sumé

type corresponding to the first ré

sumé

comprises applying a probabilistic model to one or more keywords in the first ré

sumé

.

5. The medium of claim 4, wherein applying the probabilistic model to the one or more keywords in the first ré

sumé

comprises;

determining a statistical distribution of the one or more keywords in the first ré

sumé

;

determining a first number of ré

sumé

s in a training set;

determining a second number of ré

sumé

s of the first ré

sumé

type in the training set;

determining a third number of ré

sumé

s associated with the statistical distribution of the one or more keywords in the training set;

determining a fourth number of ré

sumé

s of the first ré

sumé

s type and associated with the statistical distribution of the one or more keywords in the training set;

determining a likelihood that the first ré

sumé

is of the first ré

sumé

type based on the first number of ré

sumé

s, the second number of ré

sumé

s, the third number of ré

sumé

s, and the fourth number of ré

sumé

s; and

responsive to determining that the likelihood is above a threshold value;

determining that the first ré

sumé

type corresponds to the first ré

sumé

.

6. The medium of claim 1, wherein the operations further comprise:

determining a third ré

sumé

type corresponding to the first ré

sumé

,

wherein the first analysis model is selected based on the first ré

sumé

type and the third ré

sumé

type corresponding to the first ré

sumé

.

7. The medium of claim 1, wherein the first ré

sumé

type corresponding to the first ré

sumé

is a first industry and the second ré

sumé

type corresponding to the second ré

sumé

is a second industry.

8. The medium of claim 1, wherein each of the plurality of analysis models comprises different algorithms.

9. The medium of claim 1, wherein each of the plurality of analysis models comprises a particular algorithm that uses different parameters.

10. The medium of claim 1, wherein the first analysis model is generated based on a set of ré

sumé

s corresponding to the first ré

sumé

type.

11. The medium of claim 1, wherein:

determining the first ré

sumé

type corresponding to the first ré

sumé

comprises applying a probabilistic model to one or more keywords or features in the first ré

sumé

;

analyzing the first ré

sumé

based on the first analysis model comprises;

identifying a segment for associating with a segment type corresponding to the first analysis model;

identifying the first ré

sumé

value for associating with the first ré

sumé

attribute based on the segment type;

the first analysis model is selected based on the first ré

sumé

type and a third ré

sumé

type corresponding to the first ré

sumé

;

the first ré

sumé

type corresponding to the first ré

sumé

is a first industry and the second ré

sumé

type corresponding to the second ré

sumé

is a second industry;

at least two of the plurality of analysis models comprises different algorithms;

at least two of the plurality of analysis models comprises a particular algorithm that uses different parameters;

the first analysis model is generated based on a set of ré

sumé

s corresponding to the first ré

sumé

type;

the operations further comprise;

determining the representation of the first ré

sumé

value; and

storing the representation of the first ré

sumé

value in association with the first ré

sumé

attribute.

12. The medium of claim 1, wherein the first set of information comprises one or more of:

characteristics associated with the first user; and

characteristics associated with a job for which the first resume is submitted.

13. The medium of claim 1, wherein obtaining the first of information comprises identifying the geographical region of the first user, as the first set of information, from the first user profile separate from the first resume.

14. The medium of claim 1, wherein obtaining the first of information comprises identifying the job type sought by the first user, as the first set of information, based on the first user profile separate from the first resume.

15. The medium of claim 1, wherein obtaining the first of information comprises identifying the job posting, as the first set of information, for which the first resume is submitted.

16. A method, comprising:

obtaining a first ré

sumé

associated with a first user;

obtaining a first set of information that is external to and associated with the first ré

sumé

,

wherein obtaining the first set of information comprises one or more of;

identifying a geographical region of the first user, as the first set of information, from a first user profile separate from the first resume;

identifying a job type sought by the first user, as the first set of information, based on the first user profile separate from the first resume;

or

identifying a job posting, as the first set of information, for which the first resume is submitted;

based on the first set of information, determining a first ré

sumé

type, of a plurality of ré

sumé

types, corresponding to the first ré

sumé

;

selecting a first analysis model, of a plurality of analysis models, based on the first ré

sumé

type corresponding to the first ré

sumé

, wherein each of the plurality of analysis models is associated with a respective ré

sumé

type;

applying the first analysis model to extract, from the first ré

sumé

, a first ré

sumé

value corresponding to a first ré

sumé

attribute associated with the first ré

sumé

type;

storing the first ré

sumé

value, or a representation of the first ré

sumé

value, in association with the first ré

sumé

attribute of a first ré

sumé

profile;

obtaining a second ré

sumé

associated with a second user;

obtaining a second set of information that is external to and associated with the second ré

sumé

;

based on the second set of information, determining a second ré

sumé

type, of the plurality of ré

sumé

types, corresponding to the second ré

sumé

;

selecting a second analysis model, of the plurality of analysis models, based on the second ré

sumé

type corresponding to the second ré

sumé

;

applying the second analysis model to extract, from the second ré

sumé

, a second ré

sumé

value corresponding to a second ré

sumé

attribute associated with the second ré

sumé

type, wherein the first analysis model and the second analysis model are different;

storing the second ré

sumé

value, or a representation of the second ré

sumé

value, in association with the second ré

sumé

attribute of a second ré

sumé

profile;

wherein the method is performed by at least one hardware device including a processor.

17. The method of claim 16, wherein analyzing the first ré

sumé

based on the first analysis model comprises identifying the first ré

sumé

value for associating with the first ré

sumé

attribute corresponding to the first analysis model.

18. A system, comprising:

at least one hardware device including a processor; and

the system configured to perform operations comprising;

obtaining a first ré

sumé

associated with a first user;

obtaining a first set of information that is external to and associated with the first ré

sumé

,

wherein obtaining the first set of information comprises one or more of;

identifying a geographical region of the first user, as the first set of information, from a first user profile separate from the first resume;

identifying a job type sought by the first user, as the first set of information, based on the first user profile separate from the first resume;

or

identifying a job posting, as the first set of information, for which the first resume is submitted;

based on the first set of information, determining a first ré

sumé

type, of a plurality of ré

sumé

types, corresponding to the first ré

sumé

;

selecting a first analysis model, of a plurality of analysis models, based on the first ré

sumé

type corresponding to the first ré

sumé

, wherein each of the plurality of analysis models is associated with a respective ré

sumé

type;

applying the first analysis model to extract, from the first ré

sumé

, a first ré

sumé

value corresponding to a first ré

sumé

attribute associated with the first ré

sumé

type;

storing the first ré

sumé

value, or a representation of the first ré

sumé

value, in association with the first ré

sumé

attribute of a first ré

sumé

profile;

obtaining a second ré

sumé

associated with a second user;

obtaining a second set of information that is external to and associated with the second ré

sumé

;

based on the second set of information, determining a second ré

sumé

type, of the plurality of ré

sumé

types, corresponding to the second ré

sumé

;

selecting a second analysis model, of the plurality of analysis models, based on the second ré

sumé

type corresponding to the second ré

sumé

;

applying the second analysis model to extract, from the second ré

sumé

, a second ré

sumé

value corresponding to a second ré

sumé

attribute associated with the second ré

sumé

type, wherein the first analysis model and the second analysis model are different;

storing the second ré

sumé

value, or a representation of the second ré

sumé

value, in association with the second ré

sumé

attribute of a second ré

sumé

profile.

19. The system of claim 18, wherein the first set of information comprises one or more of:

characteristics associated with the first user; and

characteristics associated with a job for which the first resume is submitted.