The Knowledge Graph describes the concepts, entities and their relationships in the objective world in a structured form, expresses Internet information in a form closer to the human cognitive world, and provides a better organization, management and understanding of the Internet Ability to massive information. The above paragraph is a paragraph I copied from the 2018 Knowledge Graph Development Report. It is described in human words that ordinary people can understand: Knowledge Graph is to discover the connections between all things in the world. Technically, the data is stored in the form of a triple of <subject, relation, object>.
I don't know if you have such a feeling. If you learn a lot of knowledge fragments in a certain field, but you can't connect them, these knowledge fragments will not deepen your understanding of this field. And if you can connect them to form a knowledge network, it is very likely that you are an expert in this field. Because you have a knowledge network in this field in your mind, you can know where the boundaries of this field are . Knowledge graph is to connect knowledge to form a knowledge network.
Application scenarios of knowledge graph:
Knowledge graphs are mainly divided into two categories:
general knowledge graphs and domain knowledge graphs. The general knowledge graph mainly needs the breadth of knowledge, while the domain knowledge graph needs the depth of knowledge.
- The most common application scenario of general knowledge graph is: search engine,
- The application scenarios of domain knowledge graphs are relatively rich and diverse: various industries such as justice, medical care, finance, e-commerce, etc. can build their own knowledge graphs, and these knowledge graphs can be used for intelligent question answering, decision-making assistance, risk avoidance, etc.
Of course, the above are only the scenarios where the knowledge graph is most used, and there are some potential application scenarios, such as the combination of knowledge graph and deep learning. The new and young concept of knowledge graph is waiting for everyone to explore more application possibilities.
Introduction to the construction of knowledge graph
Here I will not introduce the detailed version of the knowledge map construction process?