Time sequence knowledge graph reasoning method, device and equipment based on attention mechanism

Abstract

The invention relates to a time sequence knowledge graph reasoning method and device based on an attention mechanism, computer equipment and a storage medium. The method comprises the steps of obtaining neighborhood information of each entity in each time period by constructing a knowledge graph snapshot of each time period in a time sequence knowledge graph; aggregating neighborhood information corresponding to all relations of the plurality of entities through a neighborhood aggregator to obtain neighborhood feature representation of each entity; an attention weight matrix containing multi-head information is determined through a time sequence event encoder based on an attention mechanism according to the neighborhood feature representation of a target entity at the current moment and the neighborhood feature representation of the target entity at the historical moment, and then a time entity representation sequence of the historical information is selectively concerned; obtaining the implicit vector representation of the target entity updated by the time sequence event encoder at the current moment; and performing coding scoring on the time sequence event encoder according to the implicit vector representation through the feedforward neural network and the multi-classification-layer network to realize time sequence knowledge graph reasoning.

Description

technical field [0001] The present application relates to the technical field of knowledge graphs, and in particular, to a time-series knowledge graph reasoning method, apparatus, computer equipment and storage medium based on an attention mechanism. Background technique [0002] In recent years, Knowledge Graph (KG), as a structured semantic knowledge base, uses a symbolic formal way to describe concepts and their interrelationships in the physical world, which has become a research hotspot in academia and industry. Then, over time, new knowledge may come from rapidly generated and evolving data in various news media and social software, which needs to be continuously added to the KG to reflect the evolution of the knowledge base over time. . Therefore, how to record the facts that change over time and study the trend of their changes is of great significance. The knowledge reasoning of the data-driven time-series KG under the above background can be compared with the exi...

AI Technical Summary

Problems solved by technology

These methods can continuously reason about the facts of future event graphs, however, they cannot simulate the occurrence of recurring events and the inference of key facts on future events.

Jin proposed a recurrent event network (RecurrentEvent Network, RE-NET), which can better solve the problem that the existing dynamic graph model is difficult to reason about high concurrency events at multiple time points, and can analyze the time correlation of dynamic graphs in the full time domain. However, historical reasoning relies on RNN and its variants LSTM and its variants to simulate historical evolution laws, and relies on the entity representation of multi-relational neighborhood aggregation concurrent events

However, although they can well explain the law of historical development and change, these methods cannot correctly explain the historical basis of reasoning related to specific prediction problems, and lack the problem of poor historical reasoning ability when faced with long history dependence

Images