BDI modeling method and device based on knowledge graph, equipment and medium

Abstract

The invention relates to a BDI modeling method and device based on a knowledge graph, equipment and a medium. The method comprises the steps that: a simulation task of a simulation model is acquired; perception elements are extracted from the simulation task, and a perception space map is established according to the perception elements; action elements are extracted from the simulation task and the sensing space map, and an action space map is established according to the action elements; cognitive elements are extracted from the simulation task, the perception space map and the action space map, and a cognitive space map is established according to the cognitive elements; according to the perception space map, a belief in BDI is constructed; according to the perception space map, the action space map and the cognitive space map, wishes and intentions in BDI are constructed; and according to the constructed belief, wish, intention and action space atlas, a cognitive behavior atlas of the simulation model agent is modeled. By adopting the method, the behaviors and the relationship between the behaviors can be described, and the method is realized in a mapping low-code mode.

Description

technical field [0001] The present application relates to the technical field of system modeling and simulation, in particular to a BDI modeling method, device, device and medium based on knowledge graphs. Background technique [0002] System simulation is a means of studying the objective world. It abstracts and models objective entities, and forms a complete set of simulation systems by studying entity composition, behavioral logic, processes, rules, and interactive relationships. The field of system simulation is divided into system modeling and system simulation according to subdivided research directions. Adequate system modeling is the basis for system simulation. [0003] In system-oriented modeling, the main modeling method is multi-agent simulation. Multi-agent simulation models each entity, mainly including the entity itself and the internal behavior of the entity. Entity modeling is relatively mature, but Behavioral modeling still needs further research, and no ...

AI Technical Summary

Problems solved by technology

[0003] In system-oriented modeling, the main modeling method is multi-agent simulation. Multi-agent simulation models each entity, mainly including the entity itself and the internal behavior of the entity. Entity modeling is relatively mature, but Behavioral modeling still needs further research, and no mature products or services have been seen so far

[0004] The multi-agent simulation in the prior art, in the modeling framework, mainly focuses on entities, and does not sufficiently describe behaviors and the relationship between behaviors. For example, using behavior tree modeling is only a sequential relationship, without considering other relevant factors. Such as events, states, etc. In terms of modeling implementation, it is mainly based on the way of program code implementation. When it is necessary to modify or expand the modeling, it is necessary to write code from scratch. If it is directly modified, it is necessary to understand the entire code logic and then target it. permanent modification, a slight error may lead to failure to run

Images