Heuristic-Q: A Privacy Data Pricing Method Based on Heuristic Reinforcement Learning

With the development of big data applications in recent years, the value of personal data has received more and more attention. How to balance the conflict between data value development and personal privacy protection is an urgent problem to be solved. In response to the above contradictions, the market proposed a private data transaction mechanism to realize the commercial use of private data. However, existing private data transaction mechanisms still have deficiencies in some respects. In order to seek pricing strategies that maximize total revenue, this paper designs and constructs a privacy data dynamic pricing model from the perspective of data collectors, introduces heuristic reinforcement learning ideas, and proposes a pricing strategy algorithm based on heuristic functions. Finally, the simulation experiment of the proposed pricing model and strategy learning algorithm is carried out, and its performance is analyzed. The simulation results confirm that the algorithm can help data collectors get higher returns in the process of limited private data transactions.