Calculation method of crime degree of speech data
A calculation method and speech technology, applied in the field of online speech data suspected crime calculation, which can solve problems such as difficulty in finding theoretical or mathematical model definitions and calculating crime events.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0057] Specific embodiments of the present invention will be described below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the present invention.
[0058] 1. Naive Bayes classifier text data training
[0059] figure 1 It is a screenshot of part of the training data used by the Naive Bayesian classifier to generate the prediction function. There are a total of 200 speech data for training, of which 50 have the semantics of speech unsatisfied, marked as 1. 150 have no speech unsatisfied Semantics, marked as 0. Speech data first undergoes word segmentation (Java-based apache sub-project Lucene combined with IKAnalyzer is used for word segmentation), and the preprocessing of stop words and punctuation is removed. The data is divided into a string field and a class field. The data in the string field is the preprocessed text, and the class field stores the annotation of the text. figure 2 A partial screenshot of the likeli...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com