The automated recognition of optical chemical structures, with the help of machine learning, could speed up research and development efforts. However, historical sources often have some level of image corruption, which reduces the performance to near zero. To solve this downside, we need a dependable algorithmic program to help chemists to further expand their research. This paper reports the results of research conducted for the Bristol-Myers Squibb-Molecular Translation competition, which was held on Kaggle and which invited participants to convert old chemical images to their underlying chemical structures, annotated as InChI text; we define this work as molecular translation. We proposed a model based on a transformer, which can be utilized in molecular translation. To better capture the details of the chemical structure, the image features we want to extract need to be accurate at the pixel level. TNT is one of the existing transformer models that can meet this requirement. This model was originally used for image classification, and is essentially a transformer-encoder, which cannot be utilized for generation tasks. On the other hand, we believe that TNT cannot integrate the local information of images well, so we improve the core module of TNT—TNT block—and propose a novel module—Deep TNT block—by stacking the module to form an encoder structure, and then use the vanilla transformer-decoder as a decoder, forming a chemical formula generation model based on the encoder–decoder structure. Since molecular translation is an image-captioning task, we named it the Image Captioning Model based on Deep TNT (ICMDT). A comparison with different models shows that our model has benefits in each convergence speed and final description accuracy. We have designed a complete process in the model inference and fusion phase to further enhance the final results.

The internet has enabled a fundamental change in consumer behaviour and their understanding of e-commerce business. The main objective of the following article is to present the latest trends in the way of client segmentation associated with individual credit evaluation based on machine learning. The first part discusses the current situation and innovations in the way people pay in an omnichannel world. We describe how the absence of physical money has affected society, how it has changed customer purchasing behaviour, and what this change means for the digital economy and marketing. In the background of the rapid development of big data and the Internet technology, the traditional personal credit evaluation method of the commercial bank faces a significant challenge in the evaluation of personal credit. Based on the limitation of the existing personal credit evaluation method, the second part discusses the necessity of the research on the personal credit evaluation based on the machine learning method and then probes into the comprehensive personal credit evaluation dimension and the advanced data acquisition method of the Internet finance company. And then, the data desensitisation and LOF test were carried out by dynamic desensitisation technique. The abnormal value of the tested data and the random forest method supplement the missing value of the data. The importance index is screened by the gradient boosting decision tree method, and the personal credit evaluation score is output through the scorecard model based on logical regression. After that, the model is tested by BP neural network, and the personal credit level is predicted. The personal credit level fosters customer market segmentation.