Quantitative prediction method and device for qualitative distance description, and readable storage medium

Abstract

The invention discloses a quantitative prediction method and device for qualitative distance description and a readable storage medium, and the method comprises the steps: constructing a sample set of a designated region, each sample of the sample set comprising a qualitative distance description word and a real distance corresponding to the qualitative distance description word; obtaining a distance interval corresponding to each qualitative distance description word in the sample set according to the relationship between the qualitative distance description words of all the samples in the sample set and the real distance; training a quantitative prediction model by using all obtained qualitative distance descriptors and corresponding distance intervals; and inputting the qualitative distance descriptor of a to-be-tested sample in a specified area into the trained quantitative prediction model to obtain a distance interval corresponding to the qualitative distance descriptor of the to-be-tested sample. According to the invention, the qualitative distance description can be converted into the distance quantitative interval, so that the positioning reasonability and accuracy of the target address are improved.

Description

technical field [0001] The invention relates to the field of quantitative prediction, in particular to a quantitative prediction method and device described by qualitative distance, and a readable storage medium. Background technique [0002] The urban public safety alarm system, such as the fire alarm system, has a large amount of police description records. These police description information usually include several common elements, such as time, address, person, event and so on. Among them, the address information is one of the important key elements because it is related to the dispatch plan of the dispatched personnel of the urban public security department. [0003] The address elements in the original police description record information are mostly oral expressions and colloquial descriptions of the parties concerned, and their modes usually include: [0004] The first type: police address element = [predetermined qualitative distance description] <reference ob...

AI Technical Summary

Problems solved by technology

Inaccurate address reasoning will lead to inaccurate allocation of the case to the management agency, or deviation in the deployment plan of the disposal force

[0007] At present, the use of natural language processing technology (NLP technology) to process the description of the police situation is still limited to the extraction of reference objects, pre / post qualitative distance descriptors, vaguely expressing that it is near a certain reference object, and it is not yet possible to quickly , more accurately provide the specific distance from the reference object

In general, after extracting the qualitative distance descriptors, it is inefficient and inaccurate to judge the distance manually

Images