Public opinion analysis method and device, equipment and storage medium

A technology for public opinion analysis and event description, which is applied in the fields of equipment and storage media, devices, and public opinion analysis methods, and can solve the problems of high cost, difficulty in ensuring timeliness, and low efficiency.

Pending Publication Date: 2022-04-26
IFLYTEK CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, this application provides a public opinion analysis method, device, equipment, and storage medium to solve the problems of low efficiency, high cost, and difficulty in ensuring timeliness of existing manual analysis methods. The technical solution is as follows:

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
  • Public opinion analysis method and device, equipment and storage medium
  • Public opinion analysis method and device, equipment and storage medium
  • Public opinion analysis method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0078] see figure 2 , which shows a schematic flowchart of the public opinion analysis method provided in the embodiment of the present application, the method may include:

[0079] Step S201: Obtain several text data.

[0080] The text data in this embodiment may be text data that needs to be analyzed in any scene.

[0081] Optionally, some text data can be text data obtained by transcribing voice data (for example, human-to-human dialogue voice, man-machine dialogue voice, etc.), or text data obtained directly through some means (for example, Some text data crawled from the web).

[0082] Step S202: Process each text data into a structured event description to obtain several structured event descriptions.

[0083] Such as figure 2 As shown, after obtaining several text data, structural processing is performed on each text data to obtain a structured event description.

[0084] Optionally, the structured event description can include, but is not limited to: event type ...

no. 2 example

[0098] Through the public opinion analysis method provided in the first embodiment, it can be seen that processing each text data into a structured event description is the basis for subsequent clustering, statistics, and generation of early warning texts. In view of this, this embodiment uses a text data As an example (the processing process of each text data is the same), the implementation process of processing text data into a structured event description is mainly introduced.

[0099] Optionally, the process of processing target text data to be processed into a structured event description may include: processing the target text data into a structured event description based on a pre-trained data structure model.

[0100] Based on the pre-trained data structured model, processing the target text data into a structured event description includes: the first step and the second step.

[0101] Step 1: Obtain target text data.

[0102] Step 2: Input the target text data into ...

no. 3 example

[0122] The structure of the data structured model will be described below in conjunction with the above-mentioned second embodiment, and on the basis of the description of the structure of the data structured model, the processing of the target text data into a structured event description based on the data structured model process is introduced.

[0123] In this embodiment, the training text data marked with event types and structured event descriptions are used to make the event types predicted for the training text data consistent with the event types marked for the training text data, and to make the predictions for the training text data The structured event description tends to be consistent with the structured event description annotated by the training text data. The data structured model obtained by the target training is introduced as an example.

[0124] optional, such as Figure 5 As shown, the data structured model may include: a text feature vector acquisition m...

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 provides a public opinion analysis method and device, equipment and a storage medium, and the method comprises the steps: obtaining a plurality of pieces of text data, processing each piece of text data into a structured event description, and obtaining a plurality of structured event descriptions; if no event class exists at present, clustering the plurality of structured event descriptions to obtain a plurality of event classes, and if the event classes exist at present, classifying the structured event descriptions into the event classes to which the structured event descriptions belong; and counting the event occurrence number corresponding to each event class, and when determining that the corresponding event class meets a preset early warning condition based on the event occurrence number, outputting an early warning document corresponding to the corresponding event class. According to the public opinion analysis method provided by the invention, the public opinion information can be automatically, timely and accurately mined from mass data.

Description

technical field [0001] The present application relates to the technical field of natural language processing, and in particular to a public opinion analysis method, device, equipment and storage medium. Background technique [0002] With the development of technologies such as the Internet and big data, all walks of life are generating massive amounts of data all the time. How to mine valuable information from these massive amounts of data in real time has attracted more and more attention from the industry. [0003] In some scenarios, it is necessary to conduct public opinion analysis on the massive data generated by the scene, in order to dig out public opinion events from it. Take the government affairs 12345 scenario as an example. In this scenario, tens of thousands of customer service data are generated every day. Various public opinion events are buried in these data. Timely acquisition of these event information can help the government better govern and adjust policy...

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): G06F16/35G06F16/2458G06F40/216
CPCG06F16/35G06F40/216G06F16/2465G06F2216/03
Inventor 刘启元
Owner IFLYTEK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap