Research on Product Innovation Intention Analysis System Model Based on Computational Thinking

Abstract

The starting point of this study is to improve the realistic problem of high failure rate of product innovation and improve the success rate of product innovation. First, starting from the relationship between user demand and innovation, this study constructs a product innovation-demand screening system model from a macro perspective and describes the circular promotion relationship between demand and innovation. Second, apply computational thinking to further characterize the system model. From the point of view of mining frequent item sets, this paper constructs an analysis model of product innovation intention from a microscopic perspective and makes a correlation analysis of innovation and demand, providing technical support for the combination and screening of innovation and demand. The model runs in a Python environment. This study uses the Apriori algorithm to improve the efficiency of frequent set mining. This model has no specific restrictions on the selected users, the way to select demand data is broad, and the data are easy to obtain. The use of large amounts of data for analysis also reduces the bias of experts and leading users in evaluating and screening innovation intentions. The simulation of the operation and screening efficiency of the product innovation intention analysis model shows that (1) the model runs effectively. (2) The number of innovation intentions screened by the model can be regulated by adjusting only two variables: min_support and min_confidence. However, the number of strong association rules is more sensitive to the adjustment of min_support. (3) The innovation intention analysis model has significantly improved the efficiency of innovation intention screening. (4) Adjusting the innovation portfolio according to the analysis results of innovation intention can make new products more popular.