Product recommendation processing method and device

The invention provides a product recommendation processing method and device, and the method comprises the steps: obtaining the input indexes of a plurality of products; inputting the input indexes of the plurality of products into a pre-trained target product recommendation model to obtain efficiency values of the plurality of products output by the target product recommendation model; sorting the plurality of products according to the efficiency values of the plurality of products to obtain a first sorting result, and performing secondary sorting on the first sorting result in combination with the sales volumes of the plurality of products to obtain a second sorting result; and determining a target recommended product according to the second sorting result, thereby solving the problem that it is difficult to determine comprehensive evaluation only by using a weight coefficient to measure an important relationship among numerous indexes when product recommendation is performed by using an index weight compre