Multi-thread data retrieval method based on AI technology and access method of retrieved data

Abstract

The invention discloses a multi-thread data retrieval method based on an AI technology and an access method of retrieved data. The retrieval method comprises the following steps: preprocessing file data, and forming a connected tree representing a file relationship based on file abundance and file association strength; performing feature extraction on the input retrieval information to obtain a corresponding retrieval keyword; distributing a first group of threads for current retrieval, wherein the first group of threads are used for performing target file retrieval based on the keyword; searching and determining a search basic file according to the keyword; and distributing a second group of threads for the current retrieval, carrying out batch calling-in selection on related files by the second group of threads based on the connected tree, and respectively carrying out relevancy calculation on the called-in files and the input semantic information by adopting a plurality of threads.

Description

technical field [0001] The invention relates to the field of big data and information technology, in particular to multi-threaded data retrieval based on AI technology and a method for accessing the retrieved data. Background technique [0002] In today's world, a new round of scientific and technological revolution represented by information technology is in the ascendant, information technology innovation is changing with each passing day, and the wave of informatization characterized by digitization, networking, and intelligence is booming. Informatization is profoundly changing people's production and lifestyle. [0003] With the development of artificial intelligence and big data, the storage, indexing and accessing of massive data is a problem that people must solve. Moreover, with the exponential growth of data volume, people's demand for accurate data is becoming stronger and stronger. [0004] Therefore, efficient query and retrieval capabilities in massive data sc...

AI Technical Summary

Problems solved by technology

Although there are many semantic retrieval methods in the prior art, these retrieval methods are all based on artificial intelligence analysis models, which require a large amount of labeled data to train the models, and the model operation is complex, and the amount of information input for retrieval is relatively large. At the same time, the amount of calculation required is large, the requirements for the system are high, and because the contents of the documents are all-encompassing, and the language expressions are very different, the model becomes more and more complex, but it is also difficult to adapt to the rapid growth of the document speed.

Images