Behavior knowledge extracting method and device combining reasoning and semi-automatic learning

Abstract

The invention provides a behavior knowledge extracting method and device combining reasoning and semi-automatic learning. Aiming at massive open source texts, a small amount of behavior knowledge extracting models and semantic relation among behavior knowledge are utilized to incrementally obtain behavior premises, behavior results and time sequence relations among behaviors from texts. The behavior premises, the behavior results and the time sequence relations among behaviors are respectively obtained on the basis of Bootstrapping, and on the basis of the semantic relation among behavior knowledge, knowledge reasoning is used in Bootstrapping for knowledge extracting. By the method, behavior knowledge extracting efficiency and quality are increased, automatic behavior modeling and analyzing aiming at massive texts in different fields can be achieved.

Description

technical field [0001] The invention belongs to the technical field of computer science, and specifically relates to a method and device for extracting behavior knowledge based on a small amount of initial behavior knowledge extraction templates combined with reasoning and semi-automatic learning, and is used for incrementally acquiring behavior knowledge from massive texts. Background technique [0002] Behavior knowledge is a very important type of knowledge, which has very important applications in many fields involving behavior modeling, analysis and prediction. With the development and popularization of Internet technology, massive texts accumulated on the Internet bring data support to the work of behavioral knowledge acquisition, but also pose severe technical challenges. [0003] Previous work on behavioral knowledge extraction generally used methods based on supervised learning or manual rules. Representative works include: Sil et al. ("Extracting action and event s...

AI Technical Summary

Problems solved by technology

The previous behavioral knowledge extraction methods mainly have the following shortcomings: (1) they need a large amount of manually labeled corpus or completely rely on manual construction of extraction templates, resulting in low efficiency; (2) only extract behavioral premise and result knowledge, ignoring the behavior The extraction of the relationship between behaviors, especially to obtain important behavioral knowledge such as the temporal relationship between behaviors; (3) only extracting each kind of behavioral knowledge alone, cannot use the semantic association between behavioral knowledge to promote the mutual expansion of different behavioral knowledge

Images