# US 2017/0255906 A1 · Candidate selection for job search ranking

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0255906 A1
- Document ID: US20170255906A1
- Status: Published application
- Kind: A1
- Application number: 15/061,249
- Filed: 2016-03-04
- Published: 2017-09-07
- Earliest claimed: 2016-03-04
- Assignees: Linkedln Corporation
- Applicants: Linkedln Corporation
- Inventors: Benjamin Hoan Le; Dhruv Arya
- Web page: https://patentgrep.com/patent/US20170255906A1

## CPC

- G06Q 10/1053: Employment or hiring
- G06F 16/24573: {using data annotations, e.g. user-defined metadata}
- G06F 16/24578: {using ranking}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An online social networking system receives a job search query from a member, and retrieves job postings from a database. The system applies a first scoring model to the retrieved job postings, thereby generating a first coarse ranking of the retrieved job postings. The system then identifies a top percentage or number of job postings from the first coarse ranking, and applies a second scoring model to the top percentage or number of job postings, thereby generating a second fine ranking of the retrieved job postings. The system then displays the second fine ranking of the retrieved job postings on a computer display device.

## Claims

### Claim 1

A system comprising:
a computer readable medium having instructions stored thereon, which, when executed by a processor, cause the system to:
receive a job search query from a member of an online social networking service;
retrieve job postings from a database in the online social networking service using the job search query;
apply a first scoring model to the retrieved job postings, thereby generating a first coarse ranking of the retrieved job postings;
identify a top percentage or number of job postings from the first coarse ranking;
apply a second scoring model to the top percentage or number of job postings, thereby generating a second fine ranking of the retrieved job postings; and
display the second fine ranking of the retrieved job postings on a computer display device.

### Claim 2 (depends on 1)

The system of claim 1, wherein the first scoring model comprises a processor-inexpensive filtering of the retrieved job postings, and wherein the second scoring model comprises a processor-expensive filtering of the top percentage or number of job postings.

### Claim 3 (depends on 2)

The system of claim 2, wherein the first scoring model comprises job posting quality features, thereby optimizing a retrieval of relevant job postings; and wherein the job posting quality features comprise one or more of an age of a particular job posting, click through rates for the particular job posting, a job title of the particular job posting, and a premium status of the particular job posting.

### Claim 4 (depends on 3)

The system of claim 3, wherein the first scoring model comprises query-related features comprising a similarity between the job search query and a job title or a similarity between a profile of the member and the job posting.

### Claim 5 (depends on 3)

The system of claim 3, comprising instructions to cause the system to apply a weighting factor to the job posting quality features.

### Claim 6 (depends on 5)

The system of claim 5, comprising instructions for training the weighting factor using a logistic regression.

### Claim 7 (depends on 6)

The system of claim 6, wherein the training comprises classifying the job postings as follows:
generating a job search query and a job posting tuple;
determining a relevancy of the job posting to the job search query in the job search query and job posting tuple;
identifying training data based on a click through rate for the job search query and job posting tuple; and
using the logistic regression for the training.

### Claim 8 (depends on 1)

The system of claim 1, wherein the top percentage or number of job postings comprises a threshold number of documents.

### Claim 9 (depends on 1)

The system of claim 1, wherein the first scoring model comprises an online process.

### Claim 10 (depends on 9)

The system of claim 9, wherein the first scoring model comprises searcher-related features and query-related features; and wherein the searcher-related features and query-related features comprise one or more of a matching percentage between search query terms and job posting terms and a matching percentage between terms from a user's profile and job posting terms.

### Claim 11 (depends on 1)

The system of claim 1, wherein the second scoring model comprises a comparison of the job search query to the job posting and a comparison of a profile of the member and the job posting.

### Claim 12

A process comprising:
receiving a job search query from a member of an online social networking service;
retrieving job postings from a database in the online social networking service using the job search query;
applying a first scoring model to the retrieved job postings, thereby generating a first coarse ranking of the retrieved job postings;
identifying a top percentage or number of job postings from the first coarse ranking;
applying a second scoring model to the top percentage or number of job postings, thereby generating a second fine ranking of the retrieved job postings; and
displaying the second fine ranking of the retrieved job postings on a computer display device.

### Claim 13 (depends on 12)

The process of claim 12, wherein the first scoring model comprises a processor-inexpensive filtering of the retrieved job postings, and wherein the second scoring model comprises a processor-expensive filtering of the top percentage of job postings.

### Claim 14 (depends on 13)

The process of claim 13, wherein the first scoring model comprises job posting quality features, thereby optimizing a retrieval of relevant job postings; and wherein the job posting quality features comprise one or more of an age of a particular job posting, click through rates for the particular job posting, a job title of the particular job posting, and a premium status of the particular job posting.

### Claim 15 (depends on 14)

The process of claim 14, wherein the first scoring model comprises query-related features comprising a similarity between the job search query and a job title.

### Claim 16 (depends on 14)

The process of claim 14, comprising applying a weighting factor to the job posting quality features.

### Claim 17 (depends on 16)

The process of claim 16, comprising training the weighting factor using a logistic regression.

### Claim 18 (depends on 17)

The process of claim 17, wherein the training comprises classifying the job postings as follows:
generating a job search query and a job posting tuple;
determining a relevancy of the job posting to the job search query in the job search query and job posting tuple;
identifying training data based on a click through rate for the job search query and job posting tuple; and
using the logistic regression for the training.

### Claim 19 (depends on 12)

The process of claim 12, wherein the top percentage or number of job postings comprises a threshold number of documents.

### Claim 20 (depends on 12)

The process of claim 12, wherein the first scoring model comprises an online process;
and wherein the first scoring model comprises searcher-related features and query-related features; and wherein the searcher-related features and query-related features comprise one or more of a matching percentage between search query terms and job posting terms and a matching percentage between terms from a user's profile and job posting terms.

### Claim 21 (depends on 12)

The process of claim 12, wherein the second scoring model comprises a comparison of the job search query to the job posting and a comparison of a profile of the member to the job posting.
