A kind of knowledge retrieval method and its system, computer equipment and readable storage medium

Abstract

The present invention provides a knowledge retrieval method and its system, computer equipment and readable storage medium. The method includes: acquiring knowledge data to be processed, and the knowledge data to be processed includes one of voice information, image information or first text information or more; the knowledge data to be processed is preprocessed to obtain keywords; the keywords are input into a pre-trained deep learning neural network to perform feature retrieval to obtain retrieval results; the retrieval results include the deep learning neural network and Feature knowledge associated with the keyword; output and display the retrieval result. The system, computer equipment and readable storage medium are all carriers for realizing the knowledge retrieval method. By implementing the invention, the speed and accuracy of knowledge retrieval can be improved, and it is convenient for users to understand the related knowledge of the feature more accurately.

Description

technical field [0001] The invention relates to the technical field of question-and-answer retrieval, in particular to a knowledge retrieval method and its system, computer equipment and a readable storage medium. Background technique [0002] Deep learning originates from the research of artificial neural network. The multi-layer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover the distributed characteristics of data. The advantage of deep learning is to use unsupervised or semi-supervised feature learning and hierarchical feature extraction efficient algorithms to replace manual feature acquisition, and through the relationship between the neural networks of each layer, it is convenient for users to understand and acquire features more accurately. related information. [0003] Existing knowledge retrieval methods rely o...

AI Technical Summary

Problems solved by technology

[0003] Existing knowledge retrieval methods rely on searching for features in a huge database. The acquisition speed is slow, and the relevant information of the features cannot be linked, which makes the information obtained after knowledge retrieval limited, and it is not convenient for users to understand more accurately. The relevant knowledge of this feature, so people are in urgent need of knowledge retrieval methods based on deep learning to solve the above problems

Images