Search

In recent years, the amount of Internet information data has exploded, and the problem of “information overload” has become a huge challenge for Internet development. Through the prior knowledge of the known data distribution, combined with sample training data to estimate the mathematical model of the overall data. Intelligent recommendation methods based on knowledge graphs and Bayesian networks are a hot spot in the current Internet research, and they are of great significance to search engines and e-commerce. This paper studies the fusion of knowledge graph and Bayesian belief network and its application in personalized recommendation and designs a Bayesian network that describes the purchase behavior of users based on the purchase records of customers across the network. User recommendation is the process of fusing knowledge graphs and Bayesian network reasoning. For the design of the recommendation network, a random reasoning algorithm with approximate reasoning is selected in consideration of calculation scale and accuracy. This paper uses the content filtering technology of KNN algorithm to supplement the sparse matrix, which can improve the quality of collaborative filtering recommendation, thereby improving the quality of final recommendation. In this paper, based on the knowledge graph, the EPCA algorithm and the robust recommendation algorithm are merged to form a robust collaborative recommendation model based on Bayesian probability matrix decomposition. The robust recommendation algorithm further improves the robustness of the recommendation algorithm by introducing the suspected users and target items detected by the EPCA algorithm. Research shows that the PS value of the VarSelect SVD algorithm used in this paper is approximately between 0.36 and 1.04. Compared with the first two algorithms, the PS value of VarSelect SVD has been significantly reduced, and the algorithm robustness has been significantly improved.

How to dig out the business perspectives and market rules behind commodity transaction data, explore the relationship between commodities, so as to more scientifically and rationally classify and promote commodity categories and improve commodity sales performance for e-commerce companies has become a recent research hotspot. To this end, this paper proposes to use clustering algorithm to explore the hidden laws of commodity-related big data. This article first consults a large amount of information through the literature survey method, systematically summarizes the relevant theoretical knowledge of the association rule method and clustering algorithm and gives a detailed introduction to its application in the commodity association big data mining. The research in this area has laid a sufficient theoretical foundation; after that, the Apriori algorithm in the association rules and the K-means algorithm in the clustering algorithm were used to carry out the fast clustering algorithm experiment of the commodity-related big data sparse network and the commodity transaction data was introduced in detail. The process of association analysis and cluster analysis; then taking China’s well-known e-commerce platform Jingdong Mall as an example, by investigating the commodity transaction records of Jingdong Mall in the 4th week of July, the association and cluster analysis of its commodity transaction data were found. Among them, mobile phones and Bluetooth earphone, laptops and Bluetooth earphone, laptops and hard disks have the highest correlation and their confidence thresholds have reached 25%, 35 and 40% respectively. Finally, when the clustering results were tested, they were also found in the store. Strengthening the push and shopping guide of highly relevant product combinations on the website pages will increase the sales of products.

As one of the components of root exudates, methyl 3-(4-hydroxyphenyl) propionate (MHPP) not only functions as a nitrification inhibitor in soil but also modulates plant growth and root system architecture (RSA); however, the physiological and molecular mechanisms underlying MHPP-mediated plant growth remain largely unclear. Here, we investigated the effects of MHPP treatment on growth and secondary metabolite accumulation by integrating physiology, transcriptome and metabolome analyses using perilla (Perilla frutescens), a type of medicinal and edible plant. MHPP reduces primary root growth but markedly induces lateral root formation in perilla seedlings. The full-length transcript sequencing combined with the comparative transcriptomic analysis revealed that the differential expression of genes involved in carbon/nitrogen metabolism and secondary metabolism contributed to the MHPP-mediated plant growth. An investigation of the differentially expressed genes showed that MHPP modulates the growth and metabolism of leaves and roots in distinct pathways. The genes involved in the phenylpropanoid metabolism pathway showed opposite expression patterns between the roots and leaves, thereby resulting in the differential accumulation of secondary metabolites in the roots and leaves. Furthermore, the differential expression of PER genes and elevated peroxidase activity in the MHPP-treated roots were responsible for modulating the equilibrium of ROS and the components of lignin and phenolic compounds, thereby affecting plant growth and secondary metabolite accumulation. MHPP modulates RSA and metabolite profiles and improves the contents of medicinal ingredients in perilla plants. These results suggested that the application of MHPP may represent a useful strategy for the medicinal plant cultivation.

Spatially explicit information on electric power consumption (EPC) is crucial for effective electricity allocation and utilization. Many studies have estimated fine-scale spatial EPC based on remotely sensed nighttime light (NTL). However, the spatial non-stationary relationship between EPC and NTL at prefectural level tends to be overlooked in existing literature. In this study, a classification regression method to estimate the gridded EPC in China based on imaging NTL via a Visible Infrared Imaging Radiometer Suite (VIIRS) was described. In addition, owing to some inherent omissions in the VIIRS NTL data, the study has employed the cubic Hermite interpolation to produce a more appropriate NTL dataset for estimation. The proposed method was compared with ordinary least squares (OLS) and geographically weighted regression (GWR) approaches. The results showed that our proposed method outperformed OLS and GWR in relative error (RE) and mean absolute percentage error (MAPE). The desirable results benefited mainly from a reasonable classification scheme that fully considered the spatial non-stationary relationship between EPC and NTL. Thus, the analysis suggested that the proposed classification regression method would enhance the accuracy of the gridded EPC estimation and provide a valuable reference predictive model for electricity consumption.