“Port–hinterland synergy” means the development of port and hinterland should promote each other. The “dual circulation” development pattern indicates the requirement of exploring the domestic transportation demand and promoting the integration between ports and hinterlands. However, the current research on the synergy level between ports and hinterlands is not enough to meet the needs of constructing a “dual circulation” development pattern, and few studies have explored the influencing factors of port–hinterland synergy level directly, especially in the context of the new development pattern of “dual circulation”. After investigating the synergetic mechanism between ports and hinterlands, this study proposes to further consider the influence of fixed assets allocation and social commodity circulation on the synergy level under the “dual circulation” pattern. So, fixed asset investment and three different forms of commodity circulation activities are selected to represent the corresponding hinterland’s economic activities and added into the evaluation indices. To assess ports’ responsiveness to different kinds of transport demand, throughputs of each port are divided into those of domestic and foreign countries. Then this paper evaluates the level of port–hinterland synergy by the coupling synergy model, and the influence degree of these activities on the synergy level was studied with the partial least squares regression (PLS). The results show that there is heterogeneity in regional and port positioning in the port–hinterland synergy level, and that four selected economic activities’ improvement can enhance the port–hinterland synergy level. Among them, retail industry has the strongest positive effect, followed by tertiary industry, import and export trade, and fixed asset investment.
The China Coastal Bulk Coal Freight Index (CBCFI) is the main indicator tracking the coal shipping price volatility in the Chinese market. This index indicates the variable performance of current status and trends in the coastal coal shipping sector. It is critical for the government and shipping companies to formulate timely policies and measures. After investigating the fluctuation patterns of the shipping index and the external factors in light of forecasting accuracy requirements of CBCFI, this paper proposes a nonlinear integrated forecasting model combining ARMA (Auto-Regressive and Moving Average), GM (Grey System Theory Model) and BP (Back-Propagation) Model Optimized by GA (Genetic Algorithms). This integrated model uses the predicted values of ARMA and GM as the input training samples of the neural network. Considering the shortcomings of the BP network in terms of slow convergence and the tendency to fall into local optimum, it innovatively uses a genetic algorithm to optimize the BP network, which can better exploit the prediction accuracy of the combined model. Thus, establishing the combined ARMA-GM-GABP prediction model. This work compares the short-term forecasting effects of the above three models on CBCFI. The results of the forecast fitting and error analysis show that the predicted values of the combined ARMA-GM-GABP model are fully consistent with the change trend of the actual values. The prediction accuracy has been improved to a certain extent during the observation period, which can better fit the CBCFI historical time series and can effectively solve the CBCFI forecasting problem.
Along with the explosion of ChatGPT, the artificial intelligence question-answering system has been pushed to a climax. Intelligent question-answering enables computers to simulate people’s behavior habits of understanding a corpus through machine learning, so as to answer questions in professional fields. How to obtain more accurate answers to personalized questions in professional fields is the core content of intelligent question-answering research. As one of the key technologies of intelligent question-answering, the accuracy of text matching is related to the development of the intelligent question-answering community. Aiming to solve the problem of polysemy of text, the Enhanced Representation through Knowledge Integration (ERNIE) model is used to obtain the word vector representation of text, which makes up for the lack of prior knowledge in the traditional word vector representation model. Additionally, there are also problems of homophones and polyphones in Chinese, so this paper introduces the phonetic character sequence of the text to distinguish them. In addition, aiming at the problem that there are many proper nouns in the insurance field that are difficult to identify, after conventional part-of-speech tagging, proper nouns are distinguished by especially defining their parts of speech. After the above three types of text-based semantic feature extensions, this paper also uses the Bi-directional Long Short-Term Memory (BiLSTM) and TextCNN models to extract the global features and local features of the text, respectively. It can obtain the feature representation of the text more comprehensively. Thus, the text matching model integrating BiLSTM and TextCNN fusing Multi-Feature (namely MFBT) is proposed for the insurance question-answering community. The MFBT model aims to solve the problems that affect the answer selection in the insurance question-answering community, such as proper nouns, nonstandard sentences and sparse features. Taking the question-and-answer data of the insurance library as the sample, the MFBT text-matching model is compared and evaluated with other models. The experimental results show that the MFBT text-matching model has higher evaluation index values, including accuracy, recall and F1, than other models. The model trained by historical search data can better help users in the insurance question-and-answer community obtain the answers they need and improve their satisfaction.
This work proposed an integrated model combining bagging and stacking considering the weight coefficient for short-time traffic-flow prediction, which incorporates vacation and peak time features, as well as occupancy and speed information, in order to improve prediction accuracy and accomplish deeper traffic flow data feature mining. To address the limitations of a single prediction model in traffic forecasting, a stacking model with ridge regression as the meta-learner is first established, then the stacking model is optimized from the perspective of the learner using the bagging model, and lastly the optimized learner is embedded into the stacking model as the new base learner to obtain the Ba-stacking model. Finally, to address the Ba-stacking model’s shortcomings in terms of low base learner utilization, the information structure of the base learners is modified by weighting the error coefficients while taking into account the model’s external features, resulting in a DW-Ba-stacking model that can change the weights of the base learners to adjust the feature distribution and thus improve utilization. Using 76,896 data from the I5NB highway as the empirical study object, the DW-Ba-Stacking model is compared and assessed with the traditional model in this paper. The empirical results show that the DW-Ba-stacking model has the highest prediction accuracy, demonstrating that the model is successful in predicting short-term traffic flows and can effectively solve traffic-congestion problems.
At present, the existing influence evaluation algorithms often ignore network structure attributes, user interests and the time-varying propagation characteristics of influence. To address these issues, this work comprehensively discusses users’ own influence, weighted indicators, users’ interaction influence and the similarity between user interests and topics, thus proposing a dynamic user influence ranking algorithm called UWUSRank. First, we determine the user’s own basic influence based on their activity, authentication information and blog response. This improves the problem of poor objectivity of initial value on user influence evaluation when using PageRank to calculate user influence. Next, this paper mines users’ interaction influence by introducing the propagation network properties of Weibo (a Twitter-like service in China) information and scientifically quantifies the contribution value of followers’ influence to the users they follow according to different interaction influences, thereby solving the drawback of equal value transfer of followers’ influence. Additionally, we analyze the relevance of users’ personalized interest preferences and topic content and realize real-time monitoring of users’ influence at various time periods during the process of public opinion dissemination. Finally, we conduct experiments by extracting real Weibo topic data to verify the effectiveness of introducing each attribute of users’ own influence, interaction timeliness and interest similarity. Compared to TwitterRank, PageRank and FansRank, the results show that the UWUSRank algorithm improves the rationality of user ranking by 9.3%, 14.2%, and 16.7%, respectively, which proves the practicality of the UWUSRank algorithm. This approach can serve as a guide for research on user mining, information transmission methods, and public opinion tracking in social network-related areas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.