Abstract: A system is designed to crawl known job listings web pages and extract the job listing URLs. A machine learning model is trained to recognize job listings and extract relevant information for the job listings. The model can separate multiple job listings on a single page. The machine learning model can further predict the likelihood of new jobs being added or existing job postings expiring. By using the prediction, the system can subsequently verify that a job expected to expire has expired and remove the same from the results. Similarly, the system can crawl websites with a high likelihood of new job postings without having to crawl the entire internet to maintain an up to date job listing repository.
Abstract: Methods and systems receive machine-readable input data describing a job listing or employment opportunity. The system scans the input data and software algorithms process it to predict specific information required by a particular html schema. To predict the information required by the schema, in one aspect, the system applies machine learning tools, for example, prediction models, which may be generated from training data selected from large job listing data collections, and specifically adapted and tuned for each field of interest, for example, job description, job location, and salary. This information is used to generate structured data, for example, html code, consistent with the schema for automatic insertion into a web page to comply with the schema and make the listing widely available to automated search processes.
Type:
Grant
Filed:
August 27, 2018
Date of Patent:
January 11, 2022
Assignee:
JOBIAK LLC
Inventors:
Venkata Janapareddy, Kenneth B. Baldwin, Jim Shur, Elie Raad
Abstract: Methods and systems receive machine-readable input data describing a job listing or employment opportunity. The system scans the input data and software algorithms process it to predict specific information required by a particular html schema. To predict the information required by the schema, in one aspect, the system applies machine learning tools, for example, prediction models, which may be generated from training data selected from large job listing data collections, and specifically adapted and tuned for each field of interest, for example, job description, job location, and salary. This information is used to generate structured data, for example, html code, consistent with the schema for automatic insertion into a web page to comply with the schema and make the listing widely available to automated search processes.
Type:
Application
Filed:
August 27, 2018
Publication date:
February 27, 2020
Applicant:
Jobiak LLC
Inventors:
Venkata Janapareddy, Kenneth B. Baldwin, Jim Shur, Elie Raad