Scene Understanding Technology of Intelligent Customer Service Robot Based on Deep Learning

As a value-added service that improves the efficiency of online customer service, customer service robots have been well received by sellers in recent years. Because the robot strives to free the customer service staff from the heavy consulting services in the past, thereby reducing the seller’s operating costs and improving the quality of online services. The purpose of this article is to study the intelligent customer service robot scene understanding technology based on deep learning. It mainly introduces some commonly used models and training methods of deep learning and the application fields of deep learning. Analyzed the problems of the traditional Encoder-Decoder framework, and introduced the chat model designed in this paper based on these problems, that is, the intelligent chat robot model (T-DLLModel) obtained by combining the neural network topic model and the deep learning language model. Conduct an independent question understanding experiment based on question retelling and a question understanding experiment combined with contextual information on the dialogue between online shopping customer service and customers. The experimental results show that when the similarity threshold is 0.4, the method achieves better results, and an F value of 0.5 is achieved. The semantic similarity calculation method proposed in this paper is better than the traditional method based on keywords and semantic information, especially when the similarity threshold increases, the recall rate of this paper is significantly better than the traditional method. The method in this article has a slightly better answer sorting effect on the real customer service dialogue data than the method based on LDA.

A Method of Recommending Physical Education Network Course Resources Based on Machine Learning Algorithms

Aiming at the problem of difficult selection of physical education online course resources, a method of recommending online course resources based on machine learning algorithms is proposed. The information recommendation model is established through the expression of a collaborative filtering algorithm and resource feedback matrix. According to the feedback score of any user on the same data resource in the project set, the interest matching degree is established by comparative analysis, and the matching degree is substituted into the cosine similarity function to calculate the similarity threshold between each item and so on, calculate the similarity threshold number of all items, select the project resource that best matches the user according to the threshold number, and complete the recommendation. The experimental results show that the recommended method of physical education network curriculum resources based on machine learning algorithm is relatively excellent in recommendation accuracy and efficiency; this method can realize the innovation of higher physical education network curriculum teaching mode.

Climatic clustering and longitudinal analysis with impacts on food, bioenergy, and pandemics

Predicted growth in world population will put unparalleled stress on the need for sustainable energy and global food production, as well as increase the likelihood of future pandemics. In this work, we identify high-resolution environmental zones in the context of a changing climate and predict longitudinal processes relevant to these challenges. We do this using exhaustive vector comparison methods that measure the climatic similarity between all locations on earth at high geospatial resolution. The results are captured as networks, in which edges between geolocations are defined if their historical climates exceed a similarity threshold. We then apply Markov clustering and our novel Correlation of Correlations method to the resulting climatic networks, which provides unprecedented agglomerative and longitudinal views of climatic relationships across the globe. The methods performed here resulted in the fastest (9.37 × 1018 operations/sec) and one of the largest (168.7 × 1021 operations) scientific computations ever performed, with more than 100 quadrillion edges considered for a single climatic network. Correlation and network analysis methods of this kind are widely applicable across computational and predictive biology domains, including systems biology, ecology, carbon cycles, biogeochemistry, and zoonosis research.

Chromatographic Fingerprinting Based on Column Switching Technology for Quality Evaluation of Tianmeng Oral Liquid

Separation power was limited when the conventional high-performance liquid chromatography (HPLC) fingerprinting method based on a single column was used to analyze very complex traditional Chinese medicine (TCM) preparations. In this research, a novel HPLC fingerprinting method based on column switching technology by using a single pump was established for evaluating the quality of Tianmeng oral liquid (TMOL). Twelve batches of TMOL samples were used for constructing HPLC fingerprints. Compared with the 16 common peaks in fingerprinting with a single column, 25 common peaks were achieved with two columns connected through a six-way valve. The similarity analysis combined with bootstrap method was applied to determine the similarity threshold, which was 0.992 to distinguish expired samples and unexpired samples. Principal component analysis (PCA) and hierarchical clustering analysis (HCA) were also applied to classify the TMOL samples, and results revealed that expired and unexpired samples are classified into two categories. The HPLC fingerprinting based on column switching technology with better separation power and higher peak capacity could characterize chemical composition information more comprehensively, providing an effective and alternative method to control and evaluate the quality of TMOL, which would offer a valuable reference for other TCM preparations.

Ranking the Biases: The Choice of OTUs vs. ASVs in 16S rRNA Amplicon Data Analysis Has Stronger Effects On Diversity Measures Than Rarefaction and Similarity Threshold

BackgroundAdvances in the analysis of amplicon sequence datasets have introduced a methodological shift in how research teams investigate microbial biodiversity, away from the classification and downstream analyses of traditional operational taxonomic units (OTUs), and towards the usage of amplicon sequence variants (ASVs). While ASVs have several inherent properties that make them desirable compared to OTUs, questions remain as to the influence that these pipelines have on the ecological patterns being assessed, especially when compared to other methodological choices made when processing data (e.g. rarefaction) and computing diversity indices. ResultsWe compared the respective influences of using ASVs vs. OTU-based pipelines, rarefaction of the community table, and OTU similarity threshold (97% vs. 99%) on the ecological signals detected in freshwater invertebrate and environmental (sediment, seston) 16S rRNA data sets, determining the effects on alpha diversity, beta diversity and taxonomic composition. While the choice of OTU vs. ASV pipeline significantly influenced unweighted alpha and beta diversities and changed the ecological signal detected, weighted indices such as the Shannon index, Bray-Curtis dissimilarity, and weighted Unifrac scores were not impacted by the pipeline followed. By comparison, OTU threshold and rarefaction had a minimal impact effect on all measurements, although rarefaction improved overall signals, especially in OTU-based datasets. The identification of major classes and genera identified revealed significant discrepancies across methodologies. ConclusionWe provide a list of recommendations for the analysis of 16S rRNA amplicon data. We notably recommend the use of ASVs when analyzing alpha-diversity patterns, especially in species-rich or environmental samples. Abundance weighted alpha- and beta-diversity indices should also be preferred compared to ones based on the presence-absence of biological units.

A Hybrid Recommendation Method Integrating the Social Trust Network and Local Social Influence of Users

Recommendation system plays an indispensable role in helping users make decisions in different application scenarios. The issue about how to improve the accuracy of a recommendation system has gained widespread concern in both academic and industry fields. To solve this problem, many models have been proposed, but most of them usually focus on a single perspective. Different from the existing work, we propose a hybrid recommendation method based on the users’ social trust network in this study. The proposed method has several advantages over conventional recommendation solutions. First, it offers a reliable two-step way of determining reference users by employing direct trust between users in the social trust network and setting a similarity threshold. Second, it improves the traditional collaborative filtering (CF) method based on a Pearson Correlation Coefficient (PCC) to reduce extreme values in prediction. Third, it introduces a personalized local social influence (LSI) factor into the improved CF method to further enhance the prediction accuracy. Seventy-one groups of random experiments based on the real dataset Epinions in social networks verify the proposed method. The experimental results demonstrate its feasibility, effectiveness, and accuracy in improving recommendation performance.

Ghost Detection and Removal Based on Two-Layer Background Model and Histogram Similarity

Detecting and removing ghosts is an important challenge for moving object detection because ghosts will remain forever once formed, leading to the overall detection performance degradation. To deal with this issue, we first classified the ghosts into two categories according to the way they were formed. Then, the sample-based two-layer background model and histogram similarity of ghost areas were proposed to detect and remove the two types of ghosts, respectively. Furthermore, three important parameters in the two-layer model, i.e., the distance threshold, similarity threshold of local binary similarity pattern (LBSP), and time sub-sampling factor, were automatically determined by the spatial-temporal information of each pixel for adapting to the scene change rapidly. The experimental results on the CDnet 2014 dataset demonstrated that our proposed algorithm not only effectively eliminated ghost areas, but was also superior to the state-of-the-art approaches in terms of the overall performance.

Weighted z-Distance-Based Clustering and Its Application to Time-Series Data

Clustering is the practice of dividing given data into similar groups and is one of the most widely used methods for unsupervised learning. Lee and Ouyang proposed a self-constructing clustering (SCC) method in which the similarity threshold, instead of the number of clusters, is specified in advance by the user. For a given set of instances, SCC performs only one training cycle on those instances. Once an instance has been assigned to a cluster, the assignment will not be changed afterwards. The clusters produced may depend on the order in which the instances are considered, and assignment errors are more likely to occur. Also, all dimensions are equally weighted, which may not be suitable in certain applications, e.g., time-series clustering. In this paper, improvements are proposed. Two or more training cycles on the instances are performed. An instance can be re-assigned to another cluster in each cycle. In this way, the clusters produced are less likely to be affected by the feeding order of the instances. Also, each dimension of the input can be weighted differently in the clustering process. The values of the weights are adaptively learned from the data. A number of experiments with real-world benchmark datasets are conducted and the results are shown to demonstrate the effectiveness of the proposed ideas.