A method for training a semantic vector-based information retrieval model in the field of artificial intelligence includes: obtaining a first training data set and a second training data set, the first training data includes a first query text, a first retrieval text corresponding to the first query text and having a positive label, and a second retrieval text corresponding to the first query text and having a negative label; updating a first information retrieval model based on the first training data set, to obtain a second information retrieval model; and updating the second information retrieval model based on the second training data set, to obtain a third information retrieval model.