User relevance measure is the foundation and core of heterogeneous information network research. The existing user relevance measure methods still have improvement space due to insufficient multi-dimensional analysis and link analysis. Aiming at the fact, a user relevance measure method combining Latent Dirichlet Allocation (LDA) and meta-path analysis was proposed. Firstly, the LDA was used to model the topic, and the relevance of nodes was analyzed by the node contents in the network. Secondly, the meta-path was introduced to describe the relationship type between nodes, and relevance measure was carried out for users in heterogeneous information network by relevance measure method (DPRel). Thirdly, the relevance of nodes was incorporated into the calculation of user relevance measure. Finally, the experiment was carried out on IMDB real movie dataset, and the proposed method was compared with the collaborative filtering recommendation method embedded in LDA topic model ULR-CF (Unifying LDA and Ratings Collaborative Filtering) and meta-path based similarity method (PathSim).The experimental results show that the proposed method can overcome the drawback of data sparsity and improve the accuracy of user relevance measure.

Concerning the low recommendation accuracy of personalized commodity recommendation methods, a Commodity Recommendation Method Integrating User Trust and Brand Recognition (TBCRMI) was proposed. By analyzing the user's purchase behavior and evaluation behavior, the user's recognition of brands and the activities of users themselves were calculated. Then Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm was used to cluster the users, based on which the user trust relationship was fused, and the nearest neighbors were obtained by Top- K method. Finally, the target user commodity recommendation list was generated based on the nearest neighbors. In order to verify the effectiveness of the algorithm, two datasets (Amazon Food and Unlocked Mobile Phone) were used, User based Collaborative Filtering (UserCF) algorithm, Collaborative Filtering recommendation algorithm with User trust (SPTUserCF) and Merging Trust in Collaborative Filtering (MTUserCF) algorithm were chosen, and the accuracy, recall and F1 value were compared and analyzed. The experimental results show that TBCRMI is superior to the commonly used personalized commodity recommendation methods in either multi-brand comprehensive recommendation or single brand recommendation.

In mass data era, the research on knowledge discovery of massive and distributed data has become the hot spot in both academic field and industry. The problem of load balance is one of the important factors that must be considered in developing a distributed mining algorithm. Therefore, a distributed association rules mining algorithm with load balance based on vertical FP-tree (VFP-LBDM) was proposed in this paper. Vertical frequent pattern tree was used in this algorithm to store items and their associations, and there was no need to combine the local mining results. Therefore, the communication cost was reduced and the processing procedure was also simplified. At the same time, the algorithm used the hybrid architecture in which the central site assigned tasks according to the processing capacity of each local site. It realized the load balance and improved the performance of the algorithm. The experiment shows that the algorithm given in this paper is feasible and has higher efficiency.

Collaborative recommendation is widely used in E-commerce personalized service. But the existing methods cannot provide high level personalized service due to sparse data and cold start. To improve the accuracy of collaborative recommendation, a collaborative recommendation method based on Social Network Analysis (SNA) was proposed in this paper by using SNA to improve the collaborative recommendation methods. The proposed method used SNA technology to analyze the trust relationships between users, then quantified the relationships as trust values to fill the user-item matrix, and used these trust values to calculate the similarity of users. The effectiveness of the proposed method was verified by the experimental analysis. Using trust values to expand the user-item matrix can not only solve the problem of sparse data and cold start effectively, but also improve the accuracy of collaborative recommendation.

To solve the problems such as low level automation and poor adaptability of current entity recognition methods, a Deep Web entity recognition method based on Back Propagation (BP) neural network was proposed in this paper. The method divided the entities into blocks first, then used the similarity of semantic blocks as the input of BP neural network, lastly obtained a correct entity recognition model by training which was based on the autonomic learning ability of BP neural network. It can achieve entity recognition automation in heterogeneous data sources. The experimental results show that the application of the method can not only reduce manual interventions, but also improve the efficiency and the accuracy rate of entity recognition.