A Method for Predicting the Development Effect of Homogeneous Platforms Based on Generative Adversarial Imitation Learning

Abstract

The invention discloses a method for predicting the development effect of a homogenous platform based on generative confrontational imitation learning. First, a complete industrial map is constructed for the intelligent networked automobile industry, and the entities and relationships in the industrial map are mapped to a low-dimensional vector space; and then Build a path reasoning model based on generative confrontational imitation learning; then train the path discriminator so that the path discriminator can distinguish the difference between the path generated by the path generator and the path collected by the path sampler as much as possible; extract the The characteristics of time-series economic indicators; finally, based on the semantic features of the path generated by the path generator and the characteristics of time-series economic indicators, combined with policies, industrial layout, and economic indicators, the development effects of each region are predicted under the guidance of government homogeneity. The invention avoids artificially designing reward functions, and predicts the development effect of each region under the guidance of homogeneity from multiple perspectives such as regional policy, regional industrial layout, and regional economic indicators.

Description

technical field [0001] The invention belongs to the technical field of generative confrontational imitation learning and knowledge map, and relates to a method for predicting development effects, in particular to a method for predicting the development effect of a homogenous platform based on generative confrontational imitation learning, combined with the industrial layout of each region, for each region To predict the development effect in order to stand out under the homogenization phenomenon. Background technique [0002] With the rapid development of Internet technology, the scale of knowledge graph is also increasing. Large-scale knowledge graphs play a supporting role in many applications, such as question answering systems, intelligent recommendations, and trend predictions. A complete map of the intelligent connected vehicle industry in Hubei Province, which includes factors such as industrial structure, industrial distribution, industrial division of labor, and in...

AI Technical Summary

Problems solved by technology

However, this method needs to design different reward functions for different data sets, and the commonly used terminal reward functions will also cause reward sparsity.

Images