Abstract: A deep learning-based method for fusing multi-source urban energy data and a storage medium are provided to perform data fusion on multi-source urban energy data found in big data and perform multi-scale and multimodal information fusion by using a cross-modal transformer, thereby implementing cross-modal mutual fusion of multi-source heterogeneous types of data to obtain a fused feature for prediction of a quantity of energy that will be used in the future and a quantity of energy that needs to be produced. The present disclosure proposes a multi-scale cooperative multimodal transformer architecture to enhance an effect of representation learned from an unaligned multimodal sequence. Not only there is a higher degree of correlation in multi-source urban energy data fusion, but also a system becomes more lightweight.

Abstract: According to a transformer-architecture-based method and system for IoT for and smart control of urban integrated energy, urban integrated energy IoT information acquired by a terminal from different areas is output to a server after being standardized into a sequence signal, where energy demand prediction is performed through learning of a deep learning network configured on the server, a smart control network is configured and built by using the deep learning network, real-time prediction processing is performed on the urban integrated energy IoT information acquired in real time, and a result is uploaded to a workstation for reviewing. Based on the transformer architecture, the deep learning network is combined with a fast Fourier transform algorithm and inverse transform on a sequence, and an FFT-Attention mechanism is proposed. Compared with a conventional transformer architecture, frequency domain information of a sequence is given more emphasis.

Abstract: A method for determining the pore size and pore size distribution of a filtration membrane comprises: selecting a group of fluorescent pellets having different diameters and emission wavelengths as a reference; plotting the standard curve between the concentration and fluorescence intensity for each fluorescent pellet at its emission wavelength; uniformly dispensing a group of fluorescent pellets as a reference substance in water to prepare a mixed suspension of which the mass concentration of each fluorescent pellet; using the filter membrane to be tested to perform one-time filtration on the mixed suspension prepared, then performing fluorescence detection on the obtained filtrate, calculating the concentration of each fluorescent pellet in the filtrate the retention rate of the filtration membrane to be tested for each fluorescent pellet; and calculating the pore size and pore size distribution of the filter membrane to be tested accordingly.

Abstract: The application belongs to the field of nucleic acid editing, in particular to the field of clustered regularly interspaced short palindromic repeats (CRISPR) technology. In particular, the application provides a Cas effector protein, a fusion protein with the Cas effector protein, and a nucleic acid molecule encoding the same. Also provided are a compound and a composition for nucleic acid editing (e.g., gene or genome editing) with the protein or the nucleic acid molecule, and a method for nucleic acid editing (e.g., gene or genome editing) using the protein.

Abstract: The present invention discloses a method for expressing a target gene and its special specific DNA molecule. The specific DNA molecule provideds in the present invention has a nucleotide sequence as shown at positions 7 to 589 of SEQ ID No.: 1 from the 5? end in the sequence listing. The experiment proves that the specific DNA molecule provided in the present invention may start the target gene (such as mCrylAb gene, the nucleotide sequence thereof is shown at positions 7 to 1881 from the 5? end of SEQ ID No.: 2 in the sequence listing) in various tissues of rice, maize and Arabidopsis thaliana, and shows that the specific DNA molecule is a constitutive expression promoter. The invention has important application value.