<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Exploring rural employment and entrepreneurship of undergraduate graduates in the context of rural revitalization strategy is conducive to providing human resources for rural revitalization. This paper starts from the Gaussian mixture model, introduces the specific principle of the Gaussian mixture model, then introduces the EM algorithm under the data mining algorithm, and points out that the EM algorithm is often used as an iterative optimization method for great likelihood estimation, and explains the principle and process steps of the algorithm in detail. The EM algorithm is used to solve the logarithmic great likelihood estimate of the Q function with conditional probability density function, and then the EM algorithm is applied to the Gaussian mixture model to update the values of its parameters, and the performance of the EM-GMM algorithm is also evaluated. Finally, the EM-GMM algorithm analyzes the impact of employment unit preference and employment promotion policies on the undergraduate graduates of four universities in a certain area. From the performance evaluation, the algorithm’s accuracy in this paper is 94.54%, which is 21.29 and 5.02 percentage points higher than that of the K-means-EM algorithm and FCM-EM algorithm, respectively. Regarding employment unit preference, 45.82% and 22.09% of undergraduate graduates are more inclined to be employed in township government agencies, state-owned enterprises, and institutions. Promoting rural employment and entrepreneurship of undergraduate graduates requires strengthening employment guidance and employment concept correction to provide fresh blood for rural revitalization.</p>
</abstract>

Exploring rural employment and entrepreneurship of undergraduate graduates in the context of rural revitalization strategy is conducive to providing human resources for rural revitalization. This paper starts from the Gaussian mixture model, introduces the specific principle of the Gaussian mixture model, then introduces the EM algorithm under the data mining algorithm, and points out that the EM algorithm is often used as an iterative optimization method for great likelihood estimation, and explains the principle and process steps of the algorithm in detail. The EM algorithm is used to solve the logarithmic great likelihood estimate of the Q function with conditional probability density function, and then the EM algorithm is applied to the Gaussian mixture model to update the values of its parameters, and the performance of the EM-GMM algorithm is also evaluated. Finally, the EM-GMM algorithm analyzes the impact of employment unit preference and employment promotion policies on the undergraduate graduates of four universities in a certain area. From the performance evaluation, the algorithm’s accuracy in this paper is 94.54%, which is 21.29 and 5.02 percentage points higher than that of the K-means-EM algorithm and FCM-EM algorithm, respectively. Regarding employment unit preference, 45.82% and 22.09% of undergraduate graduates are more inclined to be employed in township government agencies, state-owned enterprises, and institutions. Promoting rural employment and entrepreneurship of undergraduate graduates requires strengthening employment guidance and employment concept correction to provide fresh blood for rural revitalization.

Research on rural employment and entrepreneurship of undergraduates in the context of a rural revitalization strategy

College and University Cooperation Department

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Exploring rural employment and entrepreneurship of undergraduate graduates in the context of rural revitalization strategy is conducive to providing human...

Research on rural employment and entrepreneurship of undergraduates in the context of a rural revitalization strategy

Publié en ligne: 26 juil. 2023

Pages: -

Reçu: 14 sept. 2022

Accepté: 03 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00097

Mots clés
Gaussian mixture model, EM-GMM algorithm, Great likelihood estimation, Employment entrepreneurship

© 2023 Liang Chang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on rural employment and entrepreneurship of undergraduates in the context of a rural revitalization strategy

Publié en ligne: 26 juil. 2023

Pages: -

Reçu: 14 sept. 2022

Accepté: 03 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00097

Mots clésGaussian mixture model, EM-GMM algorithm, Great likelihood estimation, Employment entrepreneurship

© 2023 Liang Chang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Gaussian mixture model, EM-GMM algorithm, Great likelihood estimation, Employment entrepreneurship