Generation common sense reasoning method for strengthening aggregated knowledge guidance

The invention discloses a generation common sense reasoning generation method for strengthening aggregated knowledge guidance. The method comprises the following steps: constructing a concept reasoning graph and a hierarchical concept expansion graph based on a knowledge graph; building a knowledge graph enhanced encoder based on a concept inference graph under the guidance of enhanced aggregation; building a knowledge graph enhanced decoder based on a hierarchical concept expansion graph under the guidance of enhanced aggregation; training a generation common sense reasoning model comprising a knowledge graph enhanced encoder and a knowledge graph enhanced decoder; and generating a common sense reasoning statement by using the trained generated common sense reasoning model. According to the method provided by the invention, a series of problems that the generated statement does not conform to a daily scene, the logic is unreasonable and the like due to the fact that the relationship between concepts is not c