Inferring skills associated with a job

Abstract

Techniques for associating a specific skill with a job posting are described. In an example, disclosed is a system having a standardization database and a skills database. The system can extract textual features from a job posting, and select a specific skill for the job posting from a plurality of skills. Moreover, a job title for the job posting can be selected from a plurality of standardized job titles. Furthermore, an affinity score can be accessed for specific skill based on the selected job title. The system can determine a skill frequency score associated with the specific skill. The system can calculate a confidence score of the specific skill based on the textual features, the affinity score, and the skill frequency score. Subsequently, the system can store, in the skills database, an association of the specific skill with the job posting when the confidence score is above a predetermined threshold.

What is claimed is: 
     
         1 . A computer system, comprising:
 a processor;   a storage device;   a memory device holding an instruction set executable on the processor to cause the computer system to perform operations comprising:
 extract textual features from a job posting on an online system having a plurality of members; 
 select, using the extracted textual features, a specific skill from a plurality of skills associated with the job posting; 
 select, using the extracted textual features, a job title for the job posting from a plurality of standardized job titles; 
 access an affinity score for the specific skill, the affinity score being based on a likelihood that the specific skill is associated with the selected job title; 
 determine a skill frequency score associated with the specific skill, the skill frequency score being based on the specific skill being included in profile data of one or more members in the plurality of members that are associated with the selected job title; 
 calculate a confidence score of the specific skill being associated with the job posting based on the textual features, the affinity score, and the skill frequency; and 
   a user interface causing a presentation of the specific skill to a member of the online system when the confidence score is above a predetermined threshold.   
     
     
         2 . The system of  claim 1 , wherein instruction set executable on the processor further causes the computer system to perform operations comprising:
 select the job posting from a plurality of job postings on the online system; and   count a number of instances of the specific skill being included in a job title section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         3 . The system of  claim 2 , wherein the instruction set executable on the processor further causes the computer system to perform operations comprising:
 count a number of instances of the specific skill being included in a job description section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         4 . The system of  claim 2 , wherein the instruction set executable on the processor further causes the computer system to perform operations comprising:
 count a number of instances of the specific skill being included in a desired skills section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         5 . The system of  claim 1 , further comprising a skills database storing an association between a skill and a job posting, wherein the instruction set executable on the processor further causes the computer system to perform operations comprising:
 store, in the skills database, an association of the specific skill with the job posting when the confidence score is above the predetermined threshold.   
     
     
         6 . The system of  claim 5 , wherein the instruction set executable on the processor further causes the computer system to perform operations comprising:
 determine, using the textual features, a factor associated with the job posting;   access, from the skills database, a second affinity score for the specific skill, the second affinity score being based on a likelihood that the specific skill is associated with the determined factor; and   update the confidence score based on the second affinity score.   
     
     
         7 . The system of  claim 1 , further comprising:
 a standardization database storing a plurality of job postings and the plurality of standardized job titles; and   a member database storing profile data of the plurality of members of the online system, the profile data of a member in the plurality of members having skills listed on a profile page of the member.   
     
     
         8 . The system of  claim 7 , wherein the job posting is accessed from the standardization database, wherein the job posting includes a standardized company name, a standardized industry, a standardized title, a standardized job description, and one or more standardized desired skills. 
     
     
         9 . The system of  claim 7 , wherein the profile data is accessed from the member database. 
     
     
         10 . The system of  claim 7 , wherein the instruction set executable on the processor further causes the computer system to perform operations comprising:
 count a number of instances of the specific skill being listed on a profile page of a member having the selected job title, wherein the skill frequency score is further based on the number of instances.   
     
     
         11 . The system of  claim 7 , wherein the skill frequency score is further based on the specific skill being listed on a profile page of one or more members in the plurality of members that are associated with the selected job title. 
     
     
         12 . The system of  claim 1 , wherein the online system is a social network system including a job hosting service, and wherein the job posting is posted on the job hosting service. 
     
     
         13 . A computer-implemented method, comprising:
 extracting textual features from a job posting on an online system having a plurality of members;   selecting, using the extracted textual features, a specific skill from a plurality of skills associated with the job posting;   selecting, using the extracted textual features, a job title for the job posting from a plurality of standardized job titles;   accessing an affinity score for the specific skill, the affinity score being based on a likelihood that the specific skill is associated with the selected job title;   determining a skill frequency score associated with the specific skill, the skill frequency score being based on the specific skill being included in profile data of one or more members in the plurality of members that are associated with the selected job title;   calculating a confidence score of the specific skill being associated with the job posting based on the textual features, the affinity score, and the skill frequency; and   presenting, in a user interface, the specific skill to a member of the online system when the confidence score is above a predetermined threshold.   
     
     
         14 . The method of  claim 13 , further comprising:
 selecting the job posting from a plurality of job postings on the online system; and   counting a number of instances of the specific skill being included in a job title section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         15 . The method of  claim 14 , further comprising:
 counting a number of instances of the specific skill being included in a job description section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         16 . The method of  claim 14 , further comprising:
 counting a number of instances of the specific skill being included in a desired skills section of other job postings in the plurality of job postings, wherein the skill frequency score is further based on the number of instances.   
     
     
         17 . The method of  claim 13 , further comprising:
 determining, using the textual features, a factor associated with the job posting;   accessing a second affinity score for the specific skill, the second affinity score being based on a likelihood that the specific skill is associated with the determined factor; and   updating the confidence score based on the second affinity score.   
     
     
         18 . A non-transitory computer-readable medium storing executable instructions thereon, which, when executed by a processor, cause the processor to perform operations including:
 extracting textual features from a job posting on an online system having a plurality of members;   selecting, using the extracted textual features, a specific skill from a plurality of skills associated with the job posting;   selecting, using the extracted textual features, a job title for the job posting from a plurality of standardized job titles;   accessing an affinity score for the specific skill, the affinity score being based on a likelihood that the specific skill is associated with the selected job title;   determining a skill frequency score associated with the specific skill, the skill frequency score being based on the specific skill being included in profile data of one or more members in the plurality of members that are associated with the selected job title;   calculating a confidence score of the specific skill being associated with the job posting based on the textual features, the affinity score, and the skill frequency; and   presenting, in a user interface, the specific skill to a member of the online system when the confidence score is above a predetermined threshold.   
     
     
         19 . The computer-readable medium of  claim 18 , the operations further comprising:
 selecting the job posting from a standardization database storing a plurality of job postings on the online system and the plurality of standardized job titles.   
     
     
         20 . The computer-readable medium of  claim 18 , wherein determining the skill frequency score comprises accessing the profile data from a member database storing profile data of the plurality of members of the online system, the profile data of a member in the plurality of members having skills listed on a profile page of the member.