Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Conditional random field algorithm prediction result backflow training method for automatic news splitting

A conditional random field and prediction result technology, applied in computing, computer components, instruments, etc., can solve problems such as underfitting, time-consuming, and incorrect understanding of news, and achieve enhanced training, improved accuracy, and labor saving corrections The effect of labeling time

Active Publication Date: 2020-06-02
CHENGDU SOBEY DIGITAL TECH CO LTD
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If a large amount of training data is completely manually labeled (artificially label SS, BS, MS, ES labels), it will take a lot of time, and there may also be incorrect understanding of the news and wrong labeling
However, if a large amount of training data is not used for training, underfitting will occur due to insufficient training set

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Conditional random field algorithm prediction result backflow training method for automatic news splitting
  • Conditional random field algorithm prediction result backflow training method for automatic news splitting
  • Conditional random field algorithm prediction result backflow training method for automatic news splitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and are not intended to limit the present invention, that is, the described embodiments are only some of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present ...

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

PUM

No PUM Login to View More

Abstract

The invention discloses a conditional random field algorithm prediction result backflow training method for automatic news splitting. The method comprises the steps of 1, carrying out datamation on anews program video; step 2, training a conditional random field model and carrying out label prediction on the news program video needing label prediction to obtain a news story of the news program video; 3, collecting in-out point information of news stories of the news program video; 4, periodically utilizing the collected in-out point information of the news stories, combining a heuristic rule,automatically correcting scene layer feature data in the old scene layer feature data table, and storing the corrected scene layer feature data into a CRF training data table; and 5, retraining the conditional random field model according to the last training time and the data size in the CRF training data table. According to the method, the accuracy of the conditional random field algorithm canbe improved, and the label prediction time of the subsequent manual correction scene layer algorithm is saved.

Description

technical field [0001] The invention belongs to the field of automatic stripping of radio and television news, in particular to a conditional random field algorithm prediction result reflux training method for automatic news stripping, which performs reflux training by automatically correcting and marking the predicted result data label, and is suitable for automatic stripping of radio and television news . Background technique [0002] In recent years, with the rapid development of TV news programs, the attention of TV news programs has gradually increased. As an important way of carrying information, TV news plays a very important role in timely reporting and guiding public opinion. TV news is usually broadcast as a whole program, but as viewers and video editors gradually increase their demand for quick retrieval of certain content of video reports, the function of automatically splitting broadcast and TV news also appears accordingly. [0003] Conditional random field ...

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

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/41G06F18/22G06F18/241G06F18/214
Inventor 张诚王炜温序铭杨瀚
Owner CHENGDU SOBEY DIGITAL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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