Exploring the spatial and temporal changes in vegetation net primary productivity (NPP) and analyzing its complex relationship with influencing factors is crucial for assessing the carbon absorption capability of vegetation. However, most of the existing studies have been conducted from a temporal or spatial perspective, resulting in an unclear characterization of the spatio-temporal divergence between NPP and the main influencing factors. This paper tries to break through the lack of research on the spatiotemporal heterogeneity of the relationship between NPP and influencing factors and proposes a joint spatiotemporal analysis method that integrates natural and anthropogenic factors, uses correlation analysis to determine their relationship with NPP, then combines GeoDetector (GD) and Geographically Weighted Regression (GWR), and carries out an empirical study based on the data of 2001-2017, taking Yunnan Province as an example, to reveal the characteristics of influencing factors’ divergence in different time and space. The results indicate that: (1) NPP in Yunnan Province experienced fluctuations and increases from 2001 to 2017. (2) NDVI, precipitation, and temperature exert a substantial influence on the spatial and temporal variation of NPP, although this impact is diminishing. (3) Solar radiation, topography, and land use are secondary factors that affect the spatial and temporal differentiation of NPP, but their influence is increasing. (4) From 2001 to 2010, land use transfer was the main cause of NPP loss, but from 2010 to 2017, land use transfer was the main cause of NPP gain. The collective effect of anthropogenic activities and natural factors is considerably more substantial than the influence of any individual factor. This study aims to improve our understanding of how the NPP responds to climate change and urbanization. Additionally, it seeks to clarify spatial and temporal variations in NPP and identify its primary drivers. Furthermore, it can serve as a useful scientific foundation and point of reference for improving the performance of ecosystem carbon sinks and achieving carbon neutrality.

Mountainous area account for 94% in Yunnan, China. Among them, cultivated land only 16.20%. In order to classify and protect cultivated land contiguous, take Huaping , a typical mountainous area as an example, and integrates the entropy weight method, TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and spatial autocorrelation method to construct a zoning method based on CLQE (Cultivated Land Quality Evaluation). The results showed that the CLQE was divided into five grades. Class 1 and Class 2 was higher, respectively accounting for 24.98% and 29.98% of the total cultivated land area, Class 3 and Class 4 was accounting for 23.17% and 13.76%, Class 5 was the worst, accounting for 8.11%. In terms of layout, it can be divided into 4 areas, key protected areas are distributed in Class 1 and 2, accounting for 52.52% of the total, suitable adjustment areas are distributed in Class 1, 2 and 3, accounting for 9.02%, key control areas are distributed in Class 3 and 4, accounting for 25.41%, reduce reserved areas are distributed in Class 4 and 5, accounting for 13.05%. The results are consistent with the actual situation, and provide a feasible method for cultivated land classification and zoning protection.

In order to break the difficult realistic predicament of the promoting special agricultural product, so that, the agricultural product resources can be effectively promoted, the survey based on the mobile GIS technology architecture, integrated application of mobile Internet technology and JavaScript dynamic, interactive technology, having the aid of Android Studio development tools to design and implement a set of special agricultural products promotion system based on Android. The system adopts the four-tier architecture model of the database layer, platform layer, business logic layer and application layer to achieve high cohesion and low coupling characteristics of the system. Based on the comprehensive application of technology architecture of mobile GIS and various technologies, solving the deficiency of two-dimensional presentation of agricultural product promotion information for the traditional mobile terminal system. The practical application in Fumin county shows that the system has the advantages of strong real-time dynamic interaction and vivid visualization of information, it has effectively built a visual, interactive platform of mobile communication between supply and demand sides for local agricultural product promotion to increase the application level of rural information technology, helping rural agricultural development and raising farmers' income have important application value and practical significance.

With the rapid development of Internet of Things technology in recent years, speech recognition technology based on artificial intelligence and Internet of Things has gradually penetrated into various fields.In the traditional field of smart home systems, users generally need to manually set function scenes, which are time-consuming and labor-intensive and inconvenient for human-machine system interaction. In order to better meet the needs of people's intelligent life, to provide users with better control experience on smart home appliances, improve the quality of intelligent home life. This article designed a smart home control system that uses iOS as the core, voice recognition module as the interactive means, and MQTT communication protocol as data transfer.The system uses speech recognition technology based on artificial intelligence and deep learning to improve the recognition rate of speech input, achieve perfect interaction between humans and computers, and enable users to truly experience the intelligent and humanized characteristics of smart home systems.

The rapid development of urbanization has changed the type of underlying surface within the city and affected the temperature changes in the city. Mastering the relationship between urban temperature and the temperature of the different underlying surface is the basis for improving the urban heat island effect. To this end, select the school with representative urban characteristics to study the relationship between urban temperature and urban underlying surface types under different weather conditions. The Chenggong Campus of Yunnan Normal University in Kunming, Yunnan Province is the typical urban research object. Extracting the underlying surface type data of four main active areas such as grassland, water surface, bare soil and asphalt by means of artificial field measurement, and analyzed. The experimental results show that under different underlying conditions, the influence of environmental climatic conditions on urban temperature is different. This shows that in urban planning, the rational planning and design of different underlying surface types can effectively solve the urban heat island and rain island effect problem.