Method and device for pushing rights and interests

Abstract

The embodiment of the invention provides a method and device for pushing rights and interests. The method and the device can be generally used in various business scenes of to-be-pushed rights and interests. According to the method, thoughts of meta learning and reinforcement learning are combined, different business scenes serve as tasks of meta learning, and a machine learning scheme of a multi-scene dynamic decision optimal strategy is obtained by combining advantage design of reinforcement learning long-term income maximization decision, so that activity modeling of a short period and a new business scene becomes possible. During online operation, the service coding network adopts an online strategy, only a small amount of service data is needed to quickly adapt to a new service scene, a coding representation carrying service scene information is obtained, decision-making of the pushing strategy is carried out based on the coding representation, and the relevance between the pushing strategy and the service scene is further improved. The network parameters in the intelligent agent can also be updated by adopting an off-line strategy, so that the availability of the model is improved.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular to a method and device for pushing rights. Background technique [0002] With the development of Internet technology, integration has gradually become the development trend of various network platforms. The integration of the platform can link various related business parties together and realize business intercommunication. For example, the payment platform can connect multiple payment channels and access multiple payment scenarios, such as shopping scenarios, utility and gas bill payment scenarios, phone bill recharge scenarios, and takeaway scenarios, etc. These scenarios can be jumped to the current payment platform through relevant platform links, or can be accessed through small programs or micro-apps embedded in the payment platform. The payment channel can be, for example, credit card payment, savings card payment, online loan platform ...

AI Technical Summary

Problems solved by technology

The unified model is suitable for scenarios with rich historical data, and the effect is poor for scenarios with insufficient or no data, which may not meet the business requirements, and the training process may be complicated, and it is necessary to continuously collect data to retrain the model

Modeling for different scenarios usually requires maintaining multiple models, for example, the number of models is equal to the number of scenarios, the cost of training and maintenance is high, and when the scene data is small, the model cannot be trained or the trained model is not accurate enough

Images