Public security case and oral supply text naming and extracting method and device based on CRF algorithm

An extraction method and case technology, applied in the field of naming and extraction of public security cases and oral confession texts, can solve the problems of lack of standardized description terms, reduced office efficiency, and more cost, so as to achieve comprehensive and accurate case extraction information, improve case handling efficiency, and facilitate The effect of the query
CN110489739AActive Publication Date: 2019-11-22东莞数汇大数据有限公司
5 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
东莞数汇大数据有限公司
Publication Date
2019-11-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to the technical field of natural language processing and concretely discloses a public security case and oral supply text naming and extracting method and device based on a CRFalgorithm. The method comprises the steps of obtaining data information of a public security case text and a case oral supply, correspondingly integrating the case text and the case oral supply to form text data, and storing the text data in a data table for marking; performing entity word labeling on the text data formed by correspondingly integrating the case text and the case oral supply; carrying out part-of-speech tagging and extracting features according to tagging to establish a basic feature template; inputting the basic feature template, the public security case text and the corpus ofthe case oral supply into a CRF algorithm model for training to obtain a name extraction model; establishing an information data table of urban street conditions in a public security monitoring range; recognizing the newly-added case text and the oral supply information through the naming extraction model and correspondingly mapped to the information data table of the urban street condition for information extraction so that office efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of natural language processing, and specifically discloses a method and a device for extracting names of public security cases and confession texts based on a CRF algorithm. Background technique

[0002] With the rapid development of natural language processing technology, this technology has been widely used in search engines and other related industries, and the public security agencies have accumulated a large amount of case text data information in the long-term informatization process, and the public security departments need to invest more and more Manpower is used to analyze and classify case texts and confession texts.

[0003] At present, since many cases and confessions are described and recorded by different police officers, there are subjective differences in the terminology, and there is no standard description terminology. In order to accurately access the relevant information, the public secur...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More