An information extraction method, device and storage medium

Abstract

The invention discloses an information extraction method. The method comprises the steps of obtaining target digital description information of a specified type in each piece of text information; andthrough a clustering algorithm, clustering the target digital description information in each piece of the text information, and according to divided types, obtaining final digital description information with unified unit. Meanwhile, the invention furthermore discloses an information extraction apparatus and a storage medium.

Description

technical field [0001] The present invention relates to the field of big data, in particular to an information extraction method, device and storage medium. Background technique [0002] In the field of big data, it is often encountered that it is necessary to extract a certain type of target digital description information from multiple text information, for example, to extract the capacity of each venue from the text description information of multiple venues for how much. However, the digital description information about the number of people in the text description information of different venues may use different description methods. Among them, the digital description information of some venues describes the number of spectators that can be accommodated, and the digital description information of some venues. It describes the number of seats in the venue, etc. There is no unified description rule for the digital description information of different venues; therefore, ...

AI Technical Summary

Problems solved by technology

However, the digital description information about the number of people in the text description information of different venues may use different description methods. Among them, the digital description information of some venues describes the number of spectators that can be accommodated, and the digital description information of some venues. It describes the number of seats in the venue, etc. There is no unified description rule for the digital description information of different venues; therefore, it is impossible to directly extract the specific number of people that can be accommodated, and it is necessary to analyze the characters before and after the number in the digital description information. To extract the target digital description information of the specified category

[0003] In addition, the unit of the identification number in the description information of the target number may not be uniform. The order of magnitude unit of the identification number in the target number description information of some venues is thousands of people, and the order of magnitude unit of the identification number in the target number description information of some venues is ten thousand. Or, the unit of the identification number in the target number description information of some venues is person, and the unit of identification number in the target number description information of some venues is seat, and the unit of identification number in the target number description information of different venues is also not Unified description rules

[0004] In view of the above problems, the existing technology often uses artificial naked eyes to distinguish, but when the amount of text information is large, it will consume a lot of people and time, reducing the efficiency of information extraction

Images