Dynamic feature selection algorithms can improve the time efficiency of processing dynamic data. Aiming at the problem that there are few unsupervised dynamic feature selection algorithms based on fuzzy-rough sets， an Unsupervised Dynamic Fuzzy-Rough set based Feature Selection （UDFRFS） algorithm was proposed under the condition of features arriving in batches. First， by defining a pseudo triangular norm and new similarity relationship， the process of updating fuzzy relation value was performed on the basis of existing data to reduce unnecessary calculation. Then， by utilizing the existing feature selection results， dependencies were adopted to judge if the original feature part would be recalculated to reduce the redundant process of feature selection， and the feature selection was further speeded up. Experimental results show that compared to the static dependency-based unsupervised fuzzy-rough set feature selection algorithm， UDFRFS can achieve the time efficiency improvement of more than 90 percentage points with good classification accuracy and clustering performance.

Concerning the problems that the text representation features in the existing cross-domain sentiment classification method ignore the sentiment information of important words and there is negative transfer during transfer process, a Convolution-Bi-directional Long Short-Term Memory based on Attention mechanism (AC-BiLSTM) model was proposed to realize knowledge transfer. Firstly, the vector representation of text was obtained by low-dimensional dense word vectors. Secondly, after local context features being obtained by convolution operation, the long dependence relationship between the features was fully considered by Bi-directional Long Short-Term Memory (BiLSTM) network. Then, the contribution degrees of different words to the text were considered by introducing attention mechanism, and a regular term constraint was introduced into the objective function in order to avoid the negative transfer phenomenon in transfer process. Finally, the model parameters trained on source domain product reviews were transferred to target domain product reviews, and the labeled data in a small number of target domains were fine-tuned. Experimental results show that compared with AE-SCL-SR (AutoEncoder Structural Correspondence Learning with Similarity Regularization) method and Adversarial Memory Network (AMN) method, AC-BiLSTM method has average accuracy increased by 6.5% and 2.2% respectively, which demonstrates that AC-BiLSTM method can effectively improve cross-domain sentiment classification performance.

Aiming at the problem that the recommendation accuracy is not good enough due to the similarity calculation in traditional collaborative filtering recommendation algorithm, a collaborative filtering recommendation algorithm based on the similarity measurement method of tag weight was proposed. Firstly, the calculation of tag weights in existing algorithm was improved to construct a user-tag weight matrix and an item-tag weight matrix. Secondly, as the recommendation system is based on the user-centered recommendation, the most accurate evaluation and demand of the users were obtained by constructing a user-item association matrix. Finally, according to the user-item bipartite graph, the similarity between users based on the label weight was calculated by the material diffusion algorithm, and the recommendation lists were generated for the target users. The experimental results show that compared with UITGCF (a hybrid Collaborative Filtering recommendation algorithm by combining the diffusion on User-Item-Tag Graph and users' personal interest model), when the sparsity environment is 0.1, the recall, accuracy, F1 score of the proposed algorithm were respectively increased by 14.69%, 9.44% and 17.23%. When the recommendation item number is 10, the three indicators respectively were increased by 17.99%, 8.98%, and 16.27%. The results show that the collaborative filtering recommendation algorithm based on tag weight effectively improves the recommendation results.

Aiming at the problem that multi-label classification algorithms cannot fully utilize the correlation between labels, a new multi-label classification algorithm based on gravitational model namely MLBGM was proposed, by establishing the positive and negative correlation matrices of labels to mine different correlations among labeled. Firstly, by traversing all samples in the training set, k nearest neighbors for each training sample were obtain. Secondly, according to the distribution of labels in all neighbors of each sample, positive and negative correlation matrices were established for each training sample. Then, the neighbor density and neighbor weights for each training sample were calculated. Finally, a multi-label classification model was constructed by calculating the interaction between data particles. The experimental results show that the HammingLoss of MLBGM is reduced by an average of 15.62% compared with 5 contrast algorithms that do not consider negative correlation between labels; on the MicroF1, the average increase is 7.12%; on the SubsetAccuracy, the average increase is 14.88%. MLBGM obtains effective experimental results and outperforms comparison algorithms as it makes full use of the different correlations between labels.

An efficient nonuniform simplification algorithm was proposed. At first, the minimum cube box of the data sets was gained, and it was divided into eight cubes with employment of octree. Then surface variation of local discrete surface and the number of points in nonempty cubes were calculated, and these cubes were divided continually or not according to the two user-specified thresholds. In the end, one point was reserved for each leaf cube. Practical examples show that the efficient method can exactly retain geometric characteristics of original dates and be applicable for complex cloud data.