Abstract: Techniques are described for automatically generating job descriptions. Job categories are identified for the documents in the job description dataset based on clustering the documents. Sections within each document in the job description dataset are automatically identified, and each identified section is automatically classified. Each type of section is analyzed independently of the other section types using natural language processing, which allows automatic generation of each section of a new job description based on the section-specific data derived from the dataset. Section- and category-specific selective phrases are identified within the job description dataset, and embeddings are generated for the identified selective phrases. A request to generate a new job description for a particular category is received.

Abstract: A data management server computer (“server”) and related methods are disclosed to enhance electronic documents or search processes related to skill data, including skill names, using machine learning techniques. The server is programmed to organize skill names from a dictionary into a knowledge graph. The knowledge graph includes nodes that represent the skill names and words of the skill names and edges that represent syntactic or semantic relationships. The server is programmed to respond to skill-related requests using the knowledge graph and track access patterns of the knowledge graph in responding to the requests. The replies to the request can be generated based on the structure or access patterns of the knowledge graph and used as search results or skill-related data, such as resumes or job descriptions.