This exploration aims to investigate the employment and entrepreneurship of college students. College students majoring in information and computing sciences in Xinxiang City are taken as the research object. A machine learning model for college students’ employment and entrepreneurship is established. Experiments are conducted using Python language and a machine learning framework. First, based on the employment and entrepreneurship indexes of college students in machine learning, the initial data of college students’ training quality evaluation are obtained from the educational administration system, library management system, college evaluation materials, and questionnaire survey. Then, the combination weighting method is adopted to determine the index weight, quantify the data, and modify the parameters of the data provided by the framework. The Gaussian kernel is selected as the kernel function, and the sample data used by the machine learning model are labeled. Finally, the sample data are employed to train and test the model. After the consistency test, the model reaches the optimal value after 7 iterations, with an error rate of 0.01 and an accuracy rate of 99%. The final error rate of entrepreneurship and innovation model based on machine learning is less than 0.1, which is consistent with the actual situation. The model can meet the requirements of college students’ entrepreneurship and employment evaluation. It proves that it can be applied to the research of college students’ employment and entrepreneurship and has certain theoretical guidance and practical significance for the evaluation of college students’ employment and entrepreneurship level.

Entrepreneurship education activities in colleges and universities play an important role in improving students’ innovation ability. Therefore, this paper has important practical value to evaluate the innovation and entrepreneurship ability of college students. At present, most studies use qualitative research methods, which is inefficient. Even if quantitative analysis is adopted, it is mostly linear analysis, which is inconsistent with the actual situation. In order to improve the application level of genetic algorithm to the innovation and entrepreneurship ability of universities based on BP neural network, this paper studies the evaluation model of innovation and entrepreneurship ability of universities. Based on the simple analysis of the current situation of university innovation and entrepreneurship ability evaluation and the application progress of BP neural network, combined with the actual situation of university innovation and entrepreneurship, this paper constructs the innovation and entrepreneurship evaluation index, uses BP neural network to build the evaluation model, and uses genetic algorithm to optimize and improve the shortcomings of BP neural network. Then, the experimental analysis and application design are carried out. The results show that the improved algorithm is basically consistent with the predicted value, small error, and fast convergence. When it is used in the evaluation of innovation and entrepreneurship ability, quantitative analysis results can be obtained, which provides a certain reference for the development of enterprises.

The current collegiate innovation and entrepreneurship information network works in a centralized manner, and there is a centralized trust dilemma. Malicious administrators can use their own rights to achieve public and private purposes. To solve this problem, a blockchain technology based on decentralization was introduced into the innovation as well as an entrepreneurship information platform for college students. It is critical to understand how to assess the usefulness of blockchain in innovation and entrepreneurship information platforms. This research mixes it with the current popular artificial intelligence trend and offers a neural network to assess the value of blockchain technology in terms of creativity and as an entrepreneurship information platform. The contents are as follows: (1) an application value evaluation method with an improved residual neural network is proposed. First, an improved data pooling layer is constructed by using three consecutive convolutional layers in series. The approach then has a significant feature learning ability by increasing the receptive field, thanks to an atrous residual block that combines atrous convolution and the residual block. Finally, the dropout method is introduced to avoid the negative impact of overfitting. (2) An application value evaluation method based on skip connection and residual network is proposed. With the inception module, this method creates a better data pooling layer and adds residual connections. The skip connection line is built in the residual block, which improves the residual block’s learning efficiency for feature information. The ordinary convolution in the residual block with a skip connection line is replaced with atrous convolution, and an atrous residual block with a skip connection line is designed. Finally, to construct a neural network, the two designed leftover blocks are connected end-to-end.