Unlock instant, AI-driven research and patent intelligence for your innovation.

News event identification method, apparatus and device, and readable storage medium

A news and event technology, applied in the field of data processing, can solve the problems of long recognition time and low accuracy rate, and achieve the effects of improving efficiency, improving accuracy rate, and reducing feature learning time

Pending Publication Date: 2019-05-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solve the technical problems of long identification time and low accuracy in the identification method of news events in the prior art

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
  • News event identification method, apparatus and device, and readable storage medium
  • News event identification method, apparatus and device, and readable storage medium
  • News event identification method, apparatus and device, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 2 The flow chart of the method for identifying news events provided in the first embodiment of this application, such as figure 2 As shown, the executive body of the embodiment of the application is a news event recognition device. The news information recognition device can be integrated in electronic equipment, which can be computers, servers, mobile terminals and other equipment with independent computing and processing capabilities. The method for identifying news events provided in this embodiment includes the following steps.

[0041] Step 201: Use an optimized deep learning model to extract sentence context features of the target news text.

[0042] Among them, the optimized deep learning model is a deep learning model after training the deep learning model with a training set. In this embodiment, the type of the deep learning model is not limited. For example, it may be a convolutional neural network model, a deep neural network model, a recurrent neural net...

Embodiment 2

[0054] image 3 The flowchart of the method for identifying news events provided in the second embodiment of this application, such as image 3 As shown, the method for identifying news events provided in this embodiment is based on the method for identifying news events provided in the first embodiment of this application, and further refines steps 201 to 203, and also includes deep learning The steps of model training. The method for identifying news events provided in this embodiment includes the following steps.

[0055] Step 301: Construct a training set of the deep learning model. The training samples in the training set include: event news information text and non-event news information text.

[0056] further, Figure 4 This is a schematic diagram of the recognition process using the optimized convolutional neural network model in the second embodiment of this application, such as Figure 4 As shown, in this embodiment, the deep learning model is a convolutional neural netwo...

Embodiment 3

[0154] Picture 12 This is a schematic diagram of the structure of the news event identification device provided in the third embodiment of this application, such as Picture 12 As shown, the news event recognition device provided in this embodiment includes: a sentence context feature extraction module 1201, an event subject feature acquisition module 1202, a user search behavior feature acquisition module 1203, and a news event recognition module 1204.

[0155] Among them, the sentence context feature extraction module 1201 is used to extract sentence context features of the target news information text by using an optimized deep learning model. The event subject feature acquisition module 1202 is used to acquire the event subject feature of the target news text. The user search behavior feature obtaining module 1203 is used to obtain the user search behavior feature of the target news text. The news event recognition module 1204 is used to identify whether the target news info...

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 embodiment of the invention provides a news event identification method, device and equipment and a readable storage medium. The method comprises the following steps: extracting sentence context characteristics of a target news information text by adopting an optimized deep learning model; obtaining event main body characteristics and user search behavior characteristics of the target news information text; depending on sentence context features, identifying whether the target news information text is a news event or not by adopting an optimized deep learning model according to the event main characteristics and the user search behavior characteristics; when the target news information text is identified, identifying the news information text; acquiring whether event key characteristics are included or not; subjecting the features to feature learning and recognition through an optimized deep learning model. the optimized deep learning model can integrate feature learning into modeltraining, proper features can be automatically learned from data, the feature learning time is shortened, the recognition efficiency is improved, and the news event recognition accuracy is improved.

Description

Technical field [0001] The embodiments of the application relate to the field of data processing technology, and in particular, to a method, device, device, and readable storage medium for identifying news events. Background technique [0002] With the rapid popularity of the Internet, network information has exploded, and everyone needs to spend a lot of energy to filter the information. When users want to learn about recent events, or pay attention to a certain person or organization, they need to select important information from a large number of unfiltered news. If you can automatically remove non-events (such as advertisements, health knowledge, etc.) from the information, and only present the information containing the event to the user, you can greatly reduce the cost of user information screening, and you can understand the outside world as quickly as possible. Variety. [0003] In the prior art, two information, text content and time stamp, are used to identify whether ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27G06N3/04G06N3/08G06K9/62
Inventor 潘禄陈玉光彭卫华罗雨陈亮陈文浩周辉郑宇宏陈伟娜韩翠云
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD