Based on the scheme of multi-objective planning, this paper conducts an in-depth investigation on the design path of interdisciplinary teaching aids for STEAM project-based learning in the context of science education. A multi-objective planning model is constructed, which includes the integration of subject knowledge, the cultivation of students’ ability and cost control, and a multi-objective genetic algorithm is introduced to solve the model. The feasibility of the design path of this paper and the enhancement of students in project-based learning are verified through real cases. Compared with the other three schemes, the interdisciplinary teaching aids production using the mathematics and electricity fusion scheme can maximize the Pareto optimality, i.e., the integration of disciplinary knowledge and the cultivation of students’ abilities are maximized, as well as the goal of minimizing the production cost. The use of this paper’s scheme to produce teaching aids and apply them in course practice can effectively enhance students’ interest in learning and course performance.

With the deterioration of the global economic situation and the stagnation or regression of the development of enterprises, the problem of college students’ employment and entrepreneurship has been particularly prominent in recent years, and it is also one of the key points that can not be ignored in carrying out economic construction. The article realizes the prediction of college students’ entrepreneurship and employment market trends based on ARIMA-LSTM by designing the ARIMA algorithm model and combining it with the LSTM model architecture, taking the college students’ entrepreneurship and employment data from 2010 to 2022 as the research data, and using two evaluation indexes, namely, the mean absolute percentage error (MAPE) and the root mean square error (RMSE), to predict the results. Evaluation. From the analysis results ARIMA model prediction fit is high. Comparing the prediction results of the combined model with those of the LSTM model and the ARIMA model, the comparison results show that the combined model constructed in this paper can effectively fit the linear and nonlinear intertwined and superimposed trends of the time series compared with a single model, and the relative error of prediction is smaller at 33.78, which makes the results more accurate. The combined model can help the management department related to college students’ employment and entrepreneurship make reasonable decisions and improve efficiency.

This paper attempts to conduct a systematic study on the constructions of quantity phrases in modern Chinese on the basis of relevant research results, drawing on the theory of constructive grammar, in order to demonstrate the mechanism of constructions of quantity phrases in modern Chinese. The study firstly researches and analyzes the matching and distribution of quantity phrases as well as the Chinese construct grammar. Then, the study is based on random forests to investigate the constructions of quantifiers. By extracting and labeling six modern Chinese corpora, the analysis is carried out using random forests. On this basis, in order to further analyze the role of the relationship between the constructions of quantifiers, this paper also invokes a multinomial logit regression model for the study. It is found that the construct variant, regional variant, verb immediately following at the end of the sentence, structure initiation, and verb prototypicality are important factors affecting the number word constructions. In addition, the probability of quantifiers was higher when the construction variants were A and D, and sentence initiation while more inclined to co-occur with quantifiers. These findings reveal constraints on quantifier constructions and demonstrate the advantages of combining machine learning methods to analyze Chinese constructions.

Under the support of education digitalization strategy, in order to adapt to the development needs of education modernization, it is necessary to strengthen the research on the application of artificial intelligence technology in the main education of Marxism. Based on this, this paper closely follows the background of the artificial intelligence era, takes Marxist theory as a guide, and builds an intelligent communication platform for Marxist education based on the deep reinforcement learning model and the new media platform, which serves as a key link in the precise communication path of Marxist education. Relying on the state representation model and decision-making model in the deep reinforcement learning algorithm, the platform realizes the intelligent recommendation and dissemination of Marxist education content. The results of the precise communication path show that the intelligent communication platform has good application recognition and perceived satisfaction, and the audience students have a strong sense of belonging and responsibility for Marxist education in the communication, and the average score of the survey on the cultivation of values such as life ideals and political attitudes is above 4.50 points. The precise communication path of Marxist education proposed in this study, as an implementable countermeasure in the new media environment, can help the audience students to establish a correct worldview, life view and values.

The rapid development of the information age has prompted the exchange and sharing of information resources more and more frequently. Aiming at the problem of propagating information data in the center of data network, which is easy to cause congestion and delay, this paper uses deep neural network to research on the optimal path selection method for propagating information. A network traffic prediction model is designed based on multi-task learning and LSTM, and a dynamic multipath load balancing algorithm (FNN-LB) based on feed-forward neural network is proposed to solve the problem of scheduling and allocation of network traffic. The traffic prediction accuracy and generalization ability of the MT-LSTM model are verified, and the prediction mean square error is only 0.573%. Analyzed from several performance metrics, the FNN-LB algorithm improves the network throughput by 2.34% to 10.35% relative to other algorithms, effectively reduces the number of idle and overloaded links, as well as the average network delay and packet loss rate of the rat flow, while the first packet round-trip delay of the rat flow is reduced by more than 12.58%. Therefore, the proposed method in this paper can ensure the transmission quality of communication information data and improve the efficiency of data flow of communication information.

The integration of artificial intelligence and tourism culture industry requires that it is consumer-centered, and everything is based on the fundamental starting point of improving service quality and providing better tourism products. The article explores the impact of AI application on the cultural cognition level of tourists based on the role mechanism of AI and innovative inheritance methods in tourism culture inheritance. The level of tourists’ cultural cognition is quantified through the degree of understanding of tourism culture, the willingness to accept and disseminate tourism culture, the degree of preference and internalization of tourism culture, and the willingness to practice tourism culture, and the relevant research data are obtained through questionnaires. Then the benchmark regression model was constructed by combining the multiple linear regression model with the level of cultural cognition of tourists and the level of AI application as the explanatory variables and core explanatory variables. For every 1 percentage point increase in the level of AI application in tourism cultural heritage, the level of cultural cognition of tourists will increase by 0.419 percentage points. The application of artificial intelligence in tourism culture inheritance can expand the way of tourism culture inheritance and enhance the cultural cognition level of tourists through intelligent transmittable knowledge base.