US 12,079,777 B2
Job description generation based on machine learning
Yuri Yerastov, San Mateo, CA (US); Mohan Reddy, Fremont, CA (US); Sean Thomas Hinton, Vancouver (CA); Mykhailo Timonin, Vancouver (CA); Sergey Bukharov, Vancouver (CA); and Rupert Cosulich, Vancouver (CA)
Assigned to SkyHive Technologies Holdings Inc., Palo Alto, CA (US)
Filed by SkyHive Technologies Holdings Inc., Palo Alto, CA (US)
Filed on Jun. 6, 2022, as Appl. No. 17/833,744.
Application 17/833,744 is a continuation of application No. 17/364,699, filed on Jun. 30, 2021, granted, now 11,373,146.
Prior Publication US 2023/0004941 A1, Jan. 5, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/1053 (2023.01); G06F 40/20 (2020.01); G06F 40/30 (2020.01); G06N 5/022 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 10/1053 (2013.01) [G06F 40/20 (2020.01); G06F 40/30 (2020.01); G06N 5/022 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of automatically generating job descriptions, comprising:
obtaining, by a processor, a dependency graph for each skill name of a plurality of skill names, each dependency graph having a node for each word in the skill name and an edge representing a syntactic relationship between words in two nodes of the dependency graph connected by the edge;
obtaining, by the processor, hypernym tree data comprising hypernym trees each including a node for each meaning of one or more meanings of a word and an edge indicating a semantic relationship between two meanings,
a first hypernym tree of the hypernym trees including nodes for meanings of different words,
a second hypernym tree of the hypernym trees including nodes for different meanings of the same word;
assigning, to a dependency graph for a skill name of the plurality of skill names, a meaning of a specific word selected from the skill name based on the hypernym tree that includes nodes associated with the specific word;
building a skill knowledge graph with a plurality of skill nodes representing skill names by connecting dependency graphs based at least in part on distances between nodes of the hypernym trees for meanings that are assigned to the dependency graphs;
performing syntactic or semantic parsing, on a plurality of job descriptions comprising text data, to identify, within the plurality of job descriptions, a plurality of phrases;
identifying, based at least in part on the skill knowledge graph, for each job category of a plurality of job categories, a job category-specific set of selective phrases, from the plurality of phrases, that are selective for the job category, including being non-selective for other job categories;
receiving a request to generate a new job description;
identifying a particular job category of the plurality of job categories for the new job description; and
in response to receiving the request:
generating, for a job description section type of a plurality of job description section types, a corresponding section in a generated job description by including, in the corresponding section, one or more phrases from a section-specific set of selective phrases that are specific to the job description section type, including being non-selective for other job description section types, of a job category-specific set of selective phrases that are specific to the particular job category;
returning the generated job description as a response to the request.