Method, apparatus, device and storage medium for providing content in application

An electronic device, comprising:

• at least one processing unit;
• and
• at least one memory coupled to the at least one processing unit and storing instructions executable by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform operations comprising:
• receiving a first-type interaction event between a user of an application and content provided in the application, wherein the user is associated with a second operating system environment;
• determining, based on the first-type interaction event and an event model, an initial prediction of whether the user performs a second-type interaction event associated with the content, the event model describing an association relationship between the first-type interaction event performed by the user and the second-type interaction event performed by the user, wherein the event model is trained based on a first reference interaction data set from a first operating system that provides conversion feedback within a first time period;
• receiving conversion feedback data from a server associated with the second operating system environment at a time subsequent to the determining of the initial prediction, the second operating system environment providing conversion feedback within a second time period greater than the first time period;
• updating the initial prediction to obtain a corrected prediction by incorporating the received conversion feedback data;
• and
• adjusting a provision action of providing the content in the application based on the corrected prediction.

A non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, performs operations comprising:

• receiving a first-type interaction event between a user of an application and content provided in the application, wherein the user is associated with a second operating system environment;
• determining, based on the first-type interaction event and an event model, an initial prediction of whether the user performs a second-type interaction event associated with the content, the event model describing an association relationship between the first-type interaction event performed by the user and the second-type interaction event performed by the user,
• wherein the event model is trained based on a first reference interaction data set from a first operating system that provides conversion feedback within a first time period;
• receiving conversion feedback data from a server associated with the second operating system environment at a time subsequent to the determining of the initial prediction, the second operating system environment providing conversion feedback within a second time period greater than the first time period;
• updating the initial prediction to obtain a corrected prediction by incorporating the received conversion feedback data;
• and
• adjusting a provision action of providing the content in the application based on the corrected prediction.