Search

Single-task recommendation algorithms have problems such as sparse data, cold start and unstable recommendation effect. Multi-task recommendation algorithms can jointly model multiple types of user behaviour data and additional information, to better explore the user’s interests and needs in order to improve the recommendation effect and user satisfaction, which provides a new way of thinking to solve a series of problems existing in single-task recommendation algorithms. Firstly, the development background and trend of multi-task recommendation algorithms are sorted out. Secondly, the implementation steps of the multi-task recommendation algorithm and the construction principle are introduced, and the advantages of multi-task learning with data enhancement, feature identification, feature complementation and regularization effect are elaborated. Then, the application of multi-task learning methods in recommendation algorithms with different sharing models is introduced, and the advantages and disadvantages of some classical models and the relationship between tasks are summarized. Then, the commonly used datasets and evaluation metrics for multi-task recommendation algorithms are introduced, and the differences and connections with other recommendation algorithms in terms of dataset evaluation metrics are elaborated. Finally, it is pointed out that multi-task learning has shortcomings such as negative migration, parameter optimization conflicts, poor interpretability, etc., and an outlook is given to the combination of multi-task recommendation algorithms with reinforcement learning, convex function optimization methods, and heterogeneous information networks.

According to the corrosion damage of heat exchange tube plate of ammonia condense separator in coking ammonium sulfide production，the corrosion resistance characteristics of the surface passivation film of tube sheet TA9 alloy were studied by total immersion test and electrochemical analysis.Using scanning electron microscope (SEM) and X-ray energy dispersive spectrometer (EDS)，the corrosion products of samples after total immersion test were analyzed under different temperature conditions in ammonia solution containing S2-，Cl-，F-anions or a mixture of these anions，respectively.The corrosion rate of TA9 alloy and the corrosion resistance characteristics of the surface passivation film were investigated using an electrochemical workstation.Results showed that the general corrosion and pitting corrosion of TA9 alloy gradually increased with the increase of temperature，and there was no obvious difference in the macroscopic morphology of corrosion under the action of different anions at same temperature and the corrosion products were titanium oxides.The corrosion rate of the TA9 alloy was greatly affected by temperature.In an ammonia aqueous solution mixed with three anions，when the temperature was increased from 20 ℃to 90 ℃，the corrosion rate increased from 1.059 97 μm/a to 10.619 74 μm/a，so the corrosion rate increased nearly 10 times.As the temperature rose to 50 ℃，the protective performance of the passivation film to the material decreased.At the same temperature，when fluoride ions existed alone，the resistanceRof the passive film on the electrode surface changed significantly，and the redox reaction on the electrode surface was the most violent，resulting in the fastest dissolution rate of the passivation film on the electrode surface and the highest corrosion rate of TA9 alloy.