Abstract: A social recommendation method based on a multi-feature heterogeneous graph neural network is provided and includes: extracting attribute information of users and topics to code; processing user coding information and topic coding information through a multi-layer perceptron to obtain initial feature vectors of the users and the topics; establishing a heterogeneous graph by taking the users and the topics as nodes; inputting the heterogeneous graph into a heterogeneous graph neural network to perform information transmission in combination with an attention mechanism, and updating the feature vectors; and performing similarity calculation on the feature vectors of the users, and selecting the user and the topic with the highest similarity with the feature vector of the user for recommendation. Social information can be mined more comprehensively, features of users and interested topics of the users can be deeply fused, and recommendation accuracy and user experience can be improved.

Abstract: A social recommendation method based on a multi-feature heterogeneous graph neural network is provided and includes: extracting attribute information of users and topics to code; processing user coding information and topic coding information through a multi-layer perceptron to obtain initial feature vectors of the users and the topics; establishing a heterogeneous graph by taking the users and the topics as nodes; inputting the heterogeneous graph into a heterogeneous graph neural network to perform information transmission in combination with an attention mechanism, and updating the feature vectors; and performing similarity calculation on the feature vectors of the users, and selecting the user and the topic with the highest similarity with the feature vector of the user for recommendation. Social information can be mined more comprehensively, features of users and interested topics of the users can be deeply fused, and recommendation accuracy and user experience can be improved.

Abstract: An Fe—Ni—P-RE multicomponent alloy plating layer, electrodeposition preparation method, and plating application. The alloy plating layer obtained via electrodeposition contains elements Fe, Ni, P and RE, with the following mass percentages Fe— 16%-65%, Ni— 25%-70%, combined Fe and Ni— 63%-91%, RE 1.6%-25%, and the balance being P. The plating solution mainly contains the following components: ferrous salt, nickel salt, NaH2PO2, RECl3, H3BO3 and Na3C6H5O7. A multicomponent alloy plating layer of different components can be obtained by adjusting the main salt and complexing agent in the plating solution and by adjusting the process Enabled is controllable adjustment to the components of the obtained plating layer while saving costs, improved characteristics such as the thermal expansion coefficient, electrical property, magnetic property, etc., and products and methods very suitable for applications in the field of micro-electronics.

Abstract: Disclosed are a Fe—Ni—P-RE multicomponent alloy plating layer, and electrodeposition preparation method and application thereof. An alloy plating layer obtained via electrodeposition contains elements of Fe, Ni, P and RE, the mass percentage of Fe being 20%-65%, the mass percentage of Ni being 25%-70%, the combined mass percentage of Fe and Ni being 65%-90%, the mass percentage of RE being 2%-25%, and the balance being P. The plating solution mainly contains the following components: ferrous salt, nickel salt, NaH2PO2, RECl3, H3BO3 and Na3C6H5O7. A multicomponent alloy plating layer of different components can be obtained by adjusting the main salt and complexing agent in the plating solution and by adjusting the process. The present invention realizes controllable adjustment to the components of the obtained plating layer while saving costs, and further improves indexes such as the thermal expansion coefficient, electrical property, magnetic property, etc.