Method, device and equipmentfor constructing causality knowledge base

Abstract

The invention discloses a construction method, a device, equipment and a computer-readable storage medium of a causality knowledge base. The method comprises the following steps: acquiring text data from a data source and processing the text data into a plurality of statements; The causal sentences with causal relationship are determined from the processed statements, the entity pairs contained inthe causal sentences are identified, and the set containing the identified entity pairs is determined as the causal relationship knowledge base. Entity pair includes cause entity and result entity; At each lapse of a preset period of time from that time when the text data is acquire in the data source, it is judged whet the total amount of data changed in the data source reaches the data amount threshold, if so, the step of acquiring the text data from the data source is executed is returned, and if not, it is determined that it is not necessary to reconstruct the causal relationship knowledge base. Thus, the framework based on eternal learning ensures the real-time validity of causality knowledge base, and further ensures the accuracy of predicting results based on causality knowledge base.

Description

technical field [0001] The present invention relates to the technical field of data analysis, and more specifically, relates to a method, device, equipment and computer-readable storage medium for constructing a causality knowledge base. Background technique [0002] With the rapid development of Internet technology, each user, as the originator of data, presents every "self", which promotes the explosive growth of data. [0003] As a carrier to express self-daily behaviors and social emotions, text data contains a large number of summaries of individual life experiences, including rich correlations between things, and even causal relationships. Causality is the most important form of connection between things, and it is widely used in the fields of economy, medicine, military and security. Usually, in order to realize the result prediction, it is necessary to create a causal relationship knowledge base containing the corresponding entities of the cause and the result, and ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a construction method, device, equipment and computer-readable storage medium of a causal relationship knowledge base, which can solve the problem of poor accuracy in the prediction of the realization results in the existing technical solutions for realizing the construction of the causal relationship knowledge base in the prior art. low problem

Images