Blockchain provides new technologies and ideas for the construction of agricultural product traceability system (APTS). However, if data is stored, supervised, and distributed on a multiparty equal blockchain, it will face major security risks, such as data privacy leakage, unauthorized access, and trust issues. How to protect the privacy of shared data has become a key factor restricting the implementation of this technology. We propose a secure and trusted agricultural product traceability system (BCST-APTS), which is supported by blockchain and CP-ABE encryption technology. It can set access control policies through data attributes and encrypt data on the blockchain. This can not only ensure the confidentiality of the data stored in the blockchain, but also set flexible access control policies for the data. In addition, a whole-chain attribute management infrastructure has been constructed, which can provide personalized attribute encryption services. Furthermore, a reencryption scheme based on ciphertext-policy attribute encryption (RE-CP-ABE) is proposed, which can meet the needs of efficient supervision and sharing of ciphertext data. Finally, the system architecture of the BCST-APTS is designed to successfully solve the problems of mutual trust, privacy protection, fine-grained, and personalized access control between all parties.

Named entity recognition is a fundamental subtask for knowledge graph construction and question-answering in the agricultural diseases and pests field. Although several works have been done, the scarcity of the Chinese annotated dataset has restricted the development of agricultural diseases and pests named entity recognition(ADP-NER). To address the issues, a large-scale corpus for the Chinese ADP-NER task named AgCNER was first annotated. It mainly contains 13 categories, 206,992 entities, and 66,553 samples with 3,909,293 characters. Compared with other datasets, AgCNER maintains the best performance in terms of the number of categories, entities, samples, and characters. Moreover, this is the first publicly available corpus for the agricultural field. In addition, the agricultural language model AgBERT is also fine-tuned and released. Finally, the comprehensive experimental results showed that BiLSTM-CRF achieved F₁-score of 93.58%, which would be further improved to 94.14% using BERT. The analysis from multiple aspects has verified the rationality of AgCNER and the effectiveness of AgBERT. The annotated corpus and fine-tuned language model are publicly available at https://doi.org/XXX and https://github.com/guojson/AgCNER.git.

The new shoot density of slash pine serves as a vital indicator for assessing its growth and photosynthetic capacity, while the number of new shoots offers an intuitive reflection of this density. With deep learning methods becoming increasingly popular, automated counting of new shoots has greatly improved in recent years but is still limited by tedious and expensive data collection and labeling. To resolve these issues, this paper proposes a semi-supervised counting network (MTSC-Net) for estimating the number of slash pine new shoots. First, based on the mean-teacher framework, we introduce the improved VGG19 to extract multiscale new shoot features. Second, to connect local new shoot feature information with global channel features, attention feature fusion module is introduced to achieve effective feature fusion. Finally, the new shoot density map and density probability distribution are processed in a fine-grained manner through multiscale dilated convolution of the regression head and classification head. In addition, a masked image modeling strategy is introduced to encourage the contextual understanding of global new shoot features and improve the counting performance. The experimental results show that MTSC-Net outperforms other semi-supervised counting models with labeled percentages ranging from 5% to 50%. When the labeled percentage is 5%, the mean absolute error and root mean square error are 17.71 and 25.49, respectively. These findings demonstrate that our work can be used as an efficient semi-supervised counting method to provide automated support for tree breeding and genetic utilization.

Entity recognition tasks, which aim to utilize the deep learning-based models to identify the agricultural diseases and pests-related nouns such as the names of diseases, pests, and drugs from the texts collected on the internet or input by users, are a fundamental component for agricultural knowledge graph construction and question-answering, which will be implemented as a web application and provide the general public with solutions for agricultural diseases and pest control. Nonetheless, there are still challenges: (1) the polysemous problem needs to be further solved, (2) the quality of the text representation needs to be further enhanced, (3) the performance for rare entities needs to be further improved. We proposed an adversarial contextual embeddings-based model named ACE-ADP for named entity recognition in Chinese agricultural diseases and pests domain (CNER-ADP). First, we enhanced the text representation and overcame the polysemy problem by using the fine-tuned BERT model to generate the contextual character-level embedded representation with the specific knowledge. Second, adversarial training was also introduced to enhance the generalization and robustness in terms of identifying the rare entities. The experimental results showed that our model achieved an F₁ of 98.31% with 4.23% relative improvement compared to the baseline model (i.e., word2vec-based BiLSTM-CRF) on the self-annotated corpus named Chinese named entity recognition dataset for agricultural diseases and pests (AgCNER). Besides, the ablation study and discussion demonstrated that ACE-ADP could not only effectively extract rare entities but also maintain a powerful ability to predict new entities in new datasets with high accuracy. It could be used as a basis for further research on other domain-specific named entity recognition.