Specialty fruits have emerged as the essential category in the e-commerce market of agricultural products. A significant trend has demonstrated the brand development in recent years. The brand-building strategies can often be required to steadily enhance the quality of the specialty fruits, in order to fully meet the growing, diversified, and personalized demands of the consumer market. The massive data of consumer reviews can be accumulated over time on e-commerce platforms, profoundly reflecting the consumers' purchasing preferences, consumption psychology, and behavioral patterns. There is a direct correlation among the quality of products, market competitive advantages, and the dynamic evolution of brand influence. Alternatively, multimodal sentiment analysis can be expected to evaluate the field of e-commerce sales. However, the existing challenges still remained in the processing efficiency of the massive multimodal evaluation with the high computational complexity in big data environments; Severe information redundancy is commonly found during multimodal fusion, resulting in the enormous computational resource consumption. The overall performance has been impaired by the importance differences and complementarity of different modalities, such as the text and images in various scenarios of fruit sales evaluation. In this study, a hierarchical dynamic neighborhood sentiment analysis was proposed to effectively alleviate the semantic gap and representation inconsistency among different modalities, in order to overcome these technical bottlenecks. An image-text fusion mechanism was aligned and then constructed to significantly reduce the redundancy of the feature information. A low-rank image-text fusion mechanism was also utilized to substantially improve the computational efficiency. In contrast, the hierarchical dynamic neighborhood fusion mechanism was designed to comprehensively capture the rich contextual information of neighborhood nodes at various levels in a hierarchical structure. A bottom-up iterative optimization was obtained for the deep fusion and collaborative enhancement of the multi-granularity features. In experimental dataset construction, the large-scale evaluation data of specialty fruit sales were systematically collected from two major e-commerce platforms, JD.com and Taobao. A multimodal review dataset was then constructed to cover the multiple categories of specialty fruits, including navel oranges, pomelos, and apples. As such, the multidimensional information was captured after construction, such as the text reviews, product images, and user ratings. The experiment was carried out to fully validate the superior performance. There were the high classification accuracies of 90.76% and 89.45%, and macro-F1 scores of 78.75% and 85.04% on the specialty fruit sales evaluation datasets from JD.com and Taobao e-commerce platforms, respectively, demonstrating the excellent performance; The tasks of the single-modal text classification was performed better in the text feature extraction and semantic understanding; Specifically, the accuracy was improved by 15.56% and 8.62%, respectively, while the macro-F1 scores increased by 1.88% and 4.25%, respectively, compared with the bidirectional encoder representations from transformers-bidirectional long short-term memory (BERT-BiLSTM) baseline model. In addition. The multimodal fusion strategy was verified for its effectiveness and advancement in the tasks of multimodal fusion. The accuracy was improved by 10.27% and 5.14%, respectively, while the macro-F1 scores increased by 2.77% and 3.00%, respectively, compared with the Distribution-based Feature Recovery and Fusion (DRF). The computational efficiency was equally outstanding after optimization. The total testing time was reduced by 18.93% and 15.14%, respectively, compared with the tensor fusion network (TFN), fully proving the efficiency and scalability in the practical applications. The robustness and practicality of data evaluation can be expected to solve the class imbalance problem, in order to enrich the theoretical framework of natural language processing. The finding can also provide a feasible technical solution for the multimodal sentiment analysis of fruit e-commerce sales evaluations.

A rice potted seedling throwing machine is required for high stability in high-speed operation, high adaptability to different seedling ages, as well as a low damage rate in the seedling-taking device. In this study, a cam progressive ejecting-out seedling-taking device was designed for the rice potted seedling, according to the quadratrix curve and parallel four-bar mechanism. The quadratrix curve was taken as the profile curve of the return section and lifting section of the seedling-taking cam. While the elliptic curve was used as the contour curve of the rotary section of the seedling extraction cam. The trajectory equations of the return section, lifting section, and rotary section of the seedling-taking top-bar were established to determine the profile curve of the seedling-taking cam. Subsequently, the kinematic model of the seedling-taking top-bar mechanism and a single-group seedling-taking top-bar were established to determine the downward motion relationship between the seedling-taking top-bar and the potted seedling tray. As such, the horizontal movement of the seedling-taking top-bar was analyzed to determine the relationship between the rotational speed of the seedling-taking top-bar mechanism. The ejection state of the rice potted seedling was further explored during the initial seedling-taking stage. Furthermore, the maximum limit rotational speed of the seedling-taking top-bar mechanism was ultimately determined in conjunction with actual operations. A systematic investigation was implemented to explore the effects of different factors on the working performance of the seedling-taking device. Yexiangyouhang 1573, Huanghuazhan, and Yongyou 12 were selected as the test varieties. Taking the seedling age (two-leaf one-heart, three-leaf, and three-leaf one-heart), moisture content seedlings (40%, 50%, and 60%), and seedling-taking frequency (4, 6, and 8 times/s) as test factors, orthogonal experiments were conducted with the success rate and damage rate of seedling-taking as evaluation indexes. The specific experiments were carried out in the Key Laboratory of Modern Agricultural Equipment at Jiangxi Agricultural University. The experiment results indicated that the success rates of seedling-taking ranged from 95.68% to 100% for the three rice varieties. The damage rate of seedling-taking was ranged from 0.45% to 3.80%. At the same time, the seedling age shared the greatest impact on the success rate and damage rate of seedling-taking, while the moisture content seedlings and seedling-taking frequency presented relatively smaller effects. A negative correlation was observed between the damage rate and success rate of seedling-taking. The seedling-taking device was used for the subsequent optimization. Data analysis was used to determine the optimal combination of test factors. An optimal combination was achieved with three-leaf one-heart seedling age, 50% moisture content, and a seedling-taking frequency of 4 times/s. The average success rate of seedling-taking for the variety Yongyou 12 was 99.78%, and the average damage rate of seedling-taking was 0.22%. The seedling-taking device can effectively improve the existing seedling-taking mechanisms of seedling-throwing machines. The finding can provide the key technologies and core components for the subsequent development of efficient, low-damage, and orderly rice potted seedling throwing machines.

Extensive data analysis can greatly contribute to the evaluation of featured agricultural products, in order to improve and optimize the agricultural products and marketing strategies. Since there are fewer open-source strongly labeled datasets in Chinese, it is still challenging to find strongly labeled datasets in the domains. In addition, manual labeling is costly and time-consuming at present. In this study, a weakly supervised deep learning was proposed to evaluate big data on featured agricultural products from different dimensions. Firstly, the primary process was used to crawl consumers' evaluation information of some featured agricultural products from the online sales platform by incremental crawler; Secondly, a theme model was selected to define the implicit themes and theme keywords in the evaluation big data; Thirdly, the pseudo-labels were generated on different evaluation dimensions for the big data, according to a combination of syntactic dependency and lexicon-based sentiment judgment; Finally, a multi-label multi-categorization deep learning model was constructed to propose a weakly supervised framework in the evaluation big data with different evaluation dimensions. The pseudo-labeled dataset was utilized to perform the weakly supervised learning. The trained model was used to directly evaluate agricultural products. Only one model was needed to predict the consumers' emotional attitudes on different evaluation dimensions, due to the multitasking structure of the model. In the experiment, a large amount of store and evaluation information was first collected from websites related to specialty agricultural products. The incremental crawlers were adopted to form a multi-source heterogeneous extensive dataset and then stored in the database. Different websites were employed to make the dataset more representative and better eliminate the bias of different user groups, compared with a single source. Heterogeneity indicated that the data from different platforms in the dataset shared different focuses and data composition structures. The heterogeneous data was transformed from multiple sources to obtain an extensive dataset of characteristic agricultural products. Subsequently, "Hongxin pomelo" and "Purple garlic" were used as keywords to retrieve the comments from the database. The experimental dataset was obtained to verify the final prediction and comparative analysis of the model. The results showed that the improved model was achieved in 89.2% accuracy and 80.3% F1-score on the Hongxin pomelo dataset, respectively, whereas, there was an increase in the 7.1 percentage points accuracy and 11.5 percentage points F1-score over Random Forest. Compared with the Transformer model, the accuracy increased by 5.6 percentage points and F1-score by 2 percentage points, respectively, while parameters were reduced by 92%. The product evaluation dimensions and consumer concerns were efficiently extracted from massive reviews. The findings can provide the data support to improve agricultural product quality and sales service.