An innovative plant growth monitoring and environmental control platform is designed and implemented in this study. In addition to using multi-band artificial light sources for plant growth and development, an artificial intelligence of things (AIoT) approach is also utilised for environmental parameter monitoring, control, and the recording of plant growth traits and diseases. The five LED bands are white (5000 K), cool white (5500 K), blue (peak: 450 nm), red (660 nm), and light red (630 nm). The tea plant (Camellia sinensis f. formosana) is irradiated using lighting-emitting diodes (LED) composed of bands of different wavelengths. In addition, the number of leaves, contour area of the leaves, and leaf colour during the growth period of two varieties of tea plants (Taicha No. 18 and Taicha No. 8) under different irradiation intensities are analysed. Morphological image processing and deep learning models are simultaneously used to obtain plant growth characterization traits and diseases. The effect of the spectral distribution of the light source on the growth response of tea leaves and the effect of disease suppression are not fully understood. This study depicts how light quality affects the lighting formula changes in tea plants under controlled environments. The experimental results show that in three wavelength ranges (360–500 nm, 500–600 nm, and 600–760 nm), the light intensity ratio was 2.5:2.0:5.5 when the illuminance intensity was about 150 µmol∙m−2∙s−1 with a photoperiod of 20:4 (dark); this enabled more leaves, a smaller contour area of the leaves, and a light green colour of the leaves of the tea plant (Taicha No. 18). In addition, during the lighting treatment, when the ratio of the band with an irradiation intensity of 360–500 nm to that with an irradiation intensity of 500–600 nm was 2:1.5, it resulted in a better leaf disease inhibition effect. When the light intensity was increased to more than 400 µmol∙m−2∙s−1, it had little effect on the growth and development of the tea plants and the inhibition of diseases. The results of the study also found that there was a significant difference between the colour of the leaves and the relative chlorophyll content of the tea trees. Finally, the tea plant growth response data obtained from manual records and automatic records are compared and discussed. The accuracy rates of leaf number and disease were 94% and 87%, respectively. Compared with the results of manual measurement and recording, the errors were about 3–15%, which verified the effectiveness and practicability of the proposed solution. The innovative platform provides a data-driven crop modeling application for plant factories.