Abstract： Chlorophyll fluorescence imaging, as an efficient means of obtaining plant photosynthesis and physiological state information, is often used in many fields such as smart agricultural information perception. The current large-scale chlorophyll fluorescence imaging technology lacks the mechanistic connection with the microscopic leaf-level chlorophyll fluorescence imaging, ignoring the impact of imaging angle and leaf age on chlorophyll fluorescence imaging, which limits its application in large-scale agricultural intelligence assessment and role in decision-making. Aiming at the above problems, this paper designed a set of chlorophyll fluorescence acquisition equipment capable of multi-angle imaging to explore the relationship between chlorophyll fluorescence imaging, imaging angle and leaf age.A total of 60 leaves of epipremnum aureum,camphor and euonymus, representing vines, trees and shrubs were subjected to imaging experiments, and the fluorescence intensity, F_v/F_mand R_fd three typical fluorescence indicators were analyzed. The experimental results show that the imaging angle has a significant impact on the chlorophyll fluorescence imaging, and the increase of the imaging angle will lead to the decrease of the fluorescence parameter value, and the effect on different types of plants is also different. Leaf age also affects chlorophyll fluorescence imaging, and the imaging parameters of growing leaves are better than those of mature leaves.

Abstract：Global digitization has entered a period of accelerated development, and China's digitization process is in full swing. The deep application and wide penetration of the new generation of information network technologies represented by the Internet of Things, big data, cloud computing and artificial intelligence in the agricultural field has a profound impact on the innovation and upgrading of the agricultural industry. Therefore, digitalization and intelligence of agriculture is an inevitable trend of modern agriculture development, and an inevitable measure for Chinese agriculture to plug in the wings of science and technology. Planting industry is related to the national economy and people's livelihood. The digitalization and intelligence of planting industry is the central link of the digitalization construction of the whole agricultural industry chain and the main component of modern farm.

Abstract： Fruit fly is a kind of quarantine pest that attracts much attention at home and abroad. There are many kinds of fruit flies. Different kinds of fruit flies are similar in shape and size, which is difficult to identify. In addition, in practical applications, it is difficult to identify fruit flies due to the lack of information about shielding, view-point, changing light and shadow and other factors. This study proposes a bilinear pooled attention network for fruit fly classification to learn effective discriminant characteristics. The network is composed of two parts: saliency feature module and cross-layer bilinear feature module. Saliency feature module realizes feature enhancement by filtering enhancement processing of two different convolution layers. Cross-layer bilinear module is based on bilinear pooling fusion features, determines the attention location, and mines discriminant features. Experiments on fruit fly’s data set with natural environment background show that the method is effective and has good practical application prospect.

Abstract： With the development of agricultural big data and smart agriculture, in the face of massive agricultural text data, the demand for building knowledge graph and other natural language processing applications has gradually increased. At present, the entity corpus and entity labeling system in the agricultural field are still in a blank state. When dealing with agricultural texts, we are faced with such problems as how to define the category and scope of entities. Based on this problem, this paper takes the agricultural thesaurus as the scientific basis, proposes the agricultural text data entity labeling criteria for the construction of agricultural knowledge graph, covering a variety of agricultural entities such as crops, pests and weeds, and constructs a self-annotation corpus based on agricultural text based on the labeling principles of the criteria, and carries out experimental verification to prove the effectiveness of the criteria. This criterion provides a referential labeling specification for the construction of agricultural entity corpus and corpus support for agricultural entity recognition.