Career path recommendation engine

Patent metadata

Field	Value
Publication number	US-11074521-B2
Application number	US-201815941280-A
Country	US
Kind code	B2
Filing date	Mar 30, 2018
Priority date	Mar 30, 2018
Publication date	Jul 27, 2021
Grant date	Jul 27, 2021

Abstract

In an example embodiment, profile and/or usage data of a social networking service is leveraged to automatically generate potential career paths for users of the social networking service. Additionally, specific recommendations as to actions the users can take to increase their odds of progressing along particular career paths can be determined, and these recommendations can be shared with users. Both recommendations may be performed in a manner that is scalable for personalized service.

First claim

What is claimed is:

1. A system comprising:
a computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to:
obtain a set of training data comprising a plurality of social networking service profiles;
extract, from the plurality of social networking service profiles, one or more positions held currently and in the past by social networking service members corresponding to the social networking service profiles;
create a career path graph data structure, the career path graph data structure comprising a plurality of nodes and edges between nodes, each node in the career path graph data structure corresponding to a different one of the one or more positions, and each edge in the career path data structure indicating that there were n or more occurrences in the training data where the positions represented by the nodes on either side of the edge were contained in the same social networking service profile;
cluster the career path graph data structure, using a clustering algorithm, to generate one or more clusters of nodes, each cluster representing a potential career path;
for each potential career path, use a first machine learning algorithm to train weights in a career path model corresponding to the potential career path by submitting the training data and labels assigned to the training data into the first machine learning algorithm;
submit a candidate user profile into a given career path model, outputting a baseline prediction indicating a likelihood of a user corresponding to the candidate user profile progressing down a career path corresponding to the given career path model;
alter the candidate user profile and resubmit the altered candidate user profile to the given career path model to obtain a revised prediction;
compare the revised prediction to the baseline prediction from the given career path model; and
in response to a determination that the difference between the revised prediction to the baseline prediction exceeds a predetermined threshold, recommend to the user corresponding to the candidate user profile an activity related to the altered portion of the candidate user profile.

2. The system of claim 1 , wherein the training data further comprises user activity and/or behavioral information.

3. The system of claim 1 , wherein the weights trained by the first machine learning algorithm are weights assigned to features of the training data.

4. The system of claim 3 , wherein one or more of the features are extracted directly from the training data.

5. The system of claim 3 , wherein one or more of the features are computed from information extracted from the training data.

6. The system of claim 1 , wherein the instructions further cause the system to extract includes forming a set of tables, each table corresponding to a particular position found in a social networking service profile and each entry in the table containing another position found in at least n social networking service profiles along with the particular position.

7. The system of claim 6 , wherein each entry in each table further indicates n.

8. A computerized method comprising:
obtaining a set of training data comprising a plurality of social networking service profiles;
extracting, from the plurality of social networking service profiles, one or more positions held currently and in the past by social networking service members corresponding to the social networking service profiles;
creating a career path graph data structure, the career path graph data structure comprising a plurality of nodes and edges between nodes, each node in the career path graph data structure corresponding to a different one of the one or more positions, and each edge in the career path data structure indicating that there were n or more occurrences in the training data where the positions represented by the nodes on either side of the edge were contained in the same social networking service profile;
clustering the career path graph data structure, using a clustering algorithm, to generate one or more clusters of nodes, each cluster representing a potential career path;
for each potential career path, using a first machine learning algorithm to train weights in a career path model corresponding to the potential career path by submitting the training data and labels assigned to the training data into the first machine learning algorithm;
submitting a candidate user profile into a given career path model, outputting a baseline prediction indicating a likelihood of a user corresponding to the candidate user profile progressing down a career path corresponding to the given career path model;
altering the candidate user profile and resubmitting the altered candidate user profile to the given career path model to obtain a revised prediction;
comparing the revised prediction to the baseline prediction from the given career path model; and
in response to a determination that the difference between the revised prediction to the baseline prediction exceeds a predetermined threshold,
recommending to the user corresponding to the candidate user profile an activity related to the altered portion of the candidate user profile.

9. The computerized method of claim 8 , wherein the training data further comprises user activity and/or behavioral information.

10. The computerized method of claim 8 , wherein the weights trained by the first machine learning algorithm are weights assigned to features of the training data.

11. The computerized method of claim 10 , wherein one or more of the features are extracted directly from the training data.

12. The computerized method of claim 10 , wherein one or more of the features are computed from information extracted from the training data.

13. The computerized method of claim 8 , further comprising forming a set of tables, each table corresponding to a particular position found in a social networking service profile and each entry in the table containing another position found in at least n social networking service profiles along with the particular position.

14. The computerized method of claim 13 , wherein each entry in each table further indicates n.

15. A non-transitory machine-readable storage medium comprising instructions which, when implemented by one or more machines, cause the one or more machines to perform operations comprising:
obtaining a set of training data comprising a plurality of social networking service profiles;
extracting, from the plurality of social networking service profiles, one or more positions held currently and in the past by social networking service members corresponding to the social networking service profiles;
creating a career path graph data structure, the career path graph data structure comprising a plurality of nodes and edges between nodes, each node in the career path graph data structure corresponding to a different one of the one or more positions, and each edge in the career path data structure indicating that there were n or more occurrences in the training data where the positions represented by the nodes on either side of the edge were contained in the same social networking service profile;
clustering the career path graph data structure, using a clustering algorithm, to generate one or more clusters of nodes, each cluster representing a potential career path;
for each potential career path, using a first machine learning algorithm to train weights in a career path model corresponding to the potential career path by submitting the training data and labels assigned to the training data into the first machine l

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Xie Wanyan
• Li Yue
• Weber Eric
• Kuang Yanjin
• Huang Shen

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06F16/285

  Clustering or classification · CPC title

• G06Q10/1053 Primary

  Employment or hiring · CPC title

• G06Q50/01

  Physics · mapped topic