Abstract
With the development of society, many industries and professions are more comprehensive and intersecting. Different industries have their own requirements for students with comprehensive backgrounds. For graduates, they may not know the skills required for various occupations, or what kind of jobs and occupations they can take based on their existing knowledge and skills, even how to acquire these abilities after they know the requirements of the jobs they want. In this chapter, authors combine the existing method to predict hot jobs with the analysis of knowledge map, aiming to achieve accurate recommendation of learning path for those who want to find a job. This chapter will help job hunters gradually master skills, and ultimately achieve the goal of optimizing resource allocation and saving social resources.
TopBackground
According to the “China Employment Report 2017”, 56.7% of the fresh graduates indicated that their jobs were totally different from their majors. Only 25% of graduates had jobs directly related to what they had learned, while the rest graduates’ jobs were partially linked to their majors. In addition, the latest statistics in 2018 saw an increase in the proportion of graduates whose jobs were related to their majors, but still less than 50%. And relevant research showed that salary (59.1%), promotion space (53.5%), and work prospect (34.6%) were the three most important factors affecting the employment of fresh graduates, which proved that most of those people did not consider their abilities and knowledge first, but their needs when looking for jobs. It's also worth noting that one of the most important abilities companies pay attention to when recruiting is work experience. For those graduates who have no working experience, they have to find ways to meet other requirements of the company.
In view of the problems reflected in the data, this article intends to recommend learning paths to graduates by combining text mining and knowledge map, so as to help them acquire the necessary knowledge better. The main technologies used include text mining, knowledge map, random walk method, etc. And this article reviews the literature on these aspects, which provides a basis for the proposed method.
Key Terms in this Chapter
CNKI: CNKI (China National Knowledge Infrastructure) is a key national information construction project under the lead of Tsinghua University and has built a comprehensive China Integrated Knowledge Resources System, including journals, doctoral dissertations, masters' theses, proceedings, newspapers, yearbooks, statistical yearbooks, ebooks, patents, standards and so on.
Knowledge Map: A knowledge map is a navigation system for knowledge (both explicit and coded knowledge and implicit knowledge), and shows important dynamic links between different knowledge stores.
Big Data: A field that treats ways to analyze, systematically extract information from, or otherwise deal with data sets that are too large or complex to be dealt with by traditional data-processing application software.
Recommendation Method: A method which can automatically recommend relevant items that user would prefer.
Random Walk Method: A method of random sampling in which the number of paces between sample points is determined by random numbers, usually drawn from random-number tables, and from each sample point a right-angle turn determines the direction of the next point, a coin being tossed to decide whether to turn left or right.
Text Mining: The process of exploring and analyzing large amounts of unstructured text data aided by software that can identify concepts, patterns, topics, keywords and other attributes in the data.
Learning Path: An effective way to provide the necessary knowledge and skills for job seekers by applying random walk method.