Anti-fraud method and anti-fraud hearing aid based on voice recognition

A speech recognition and speech recognition model technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of fraud judgment, lack of speech recognition function, old people falling into the trap of fraudsters, etc.

Pending Publication Date: 2020-06-05
李干群
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current hearing aids only have a very simple information transmission function, without voice recognition function, and cannot make fraud judgments. Sometimes the elderly will easily fall into the trap of fraudsters. You can consider using hearing aids to obtain the content of calls between the elderly and criminals. And use voice recognition technology to analyze and judge the content of the call, so as to prevent the elderly from being cheated

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
  • Anti-fraud method and anti-fraud hearing aid based on voice recognition
  • Anti-fraud method and anti-fraud hearing aid based on voice recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 , the present invention provides a kind of anti-fraud method based on speech recognition, and described method comprises steps:

[0065] S1: Obtain the call content through the hearing aid.

[0066] In this step, the content of the call between the user and the call partner is acquired through the hearing aid, so as to facilitate subsequent analysis and judgment of the call content.

[0067] S2: Using the classifier on the hearing aid to analyze the call content.

[0068] In this step, a classifier is preset on the hearing aid, and a preset speech recognition model is pre-stored in the classifier, and the classifier compares with the preset speech recognition model after acquiring the call content. Among them, there are at least two preset speech recognition models, which are: fraud call content model and marketing call content model, and the classifier compares each call content obtained with all preset speech recognition models in turn, so as to obtai...

Embodiment 2

[0080] In the embodiment of the present application, after the classifier on the hearing aid is used to analyze the call content, a step is further included:

[0081] judging whether the call content triggers a preset keyword;

[0082] When a preset keyword is triggered, the classifier judges it to be similar to the preset speech recognition model;

[0083] When the preset keyword is not triggered, the classifier judges it as normal content.

[0084] In the embodiment of the present application, considering that at some point, the hearing aid may acquire more call content, if compared with the preset speech recognition model one by one, it will increase the amount of data processing, you can first use the hearing aid The classifier performs keyword judgment after analyzing the call content.

[0085] For example, if the keywords are "money" and "payment", when these keywords appear in the call content, you can directly enter the step of making similar judgments between the cl...

Embodiment 3

[0087] In the embodiment of the present application, after the judging that the call content is promotional content or fraudulent content, further steps are included:

[0088] Judging whether the voice of the call content is similar to the preset family member voiceprint database;

[0089] When it is judged that the two are similar, it is judged that the content of the call is normal;

[0090] When it is judged that the two are not similar, continue to judge that the call content is a promotional content or a fraudulent content.

[0091] In the embodiment of the present application, the voiceprint library of family members can be stored in the hearing aid in advance. When it is judged as fraud or sales promotion, it can be compared with the voice in the voiceprint library of family members. If it is the voice of a family member, the fraud or suspicion of marketing. This operation can prevent the embarrassing situation when discussing some high-frequency words such as "money"...

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 an anti-fraud method and anti-fraud hearing aid based on voice recognition. The method comprises the following steps: obtaining call content through the hearing aid; analyzingthe call content by using a classifier on the hearing aid; judging whether the call content is similar to a preset voice recognition model or not; when the two contents are similar, judging that the call content is sales promotion content or fraud content; when the two contents are not similar, judging that the call content is normal content; when it is judged that the call content is sales promotion content, obtaining related negative information of the sales promotion content, pushing the related negative information of the sales promotion content to family members of the user; when judgingthat the call content is the fraud content, shielding the hearing aid and sending alarm information to the family members of the user; and when the call content is judged to be the normal content, continuing the normal work of the hearing aid. According to the method and the hearing aid provided by the invention, the call content of the hearing aid can be filtered by upgrading the function of thehearing aid, so that the risk that the old are fraudulent is reduced.

Description

technical field [0001] The invention belongs to the technical field of fraud prevention, and in particular relates to a fraud prevention method based on speech recognition and a fraud prevention hearing aid. Background technique [0002] At present, we are slowly entering an aging society, but the elderly lack self-protection awareness and are easy to believe in deceptive lies, which will not only cause property losses, but also cause huge physical and mental damage. Although people are already aware of the dangers of fraudulent behavior, it is worth noting that in today's social life, various successful cases of fraudulent behavior will continue to be exposed. Therefore, it is urgent to prevent such fraudulent behavior at the scientific and technological level. Especially for the elderly. [0003] At present, many elderly people often wear hearing aids for auxiliary calls. When outsiders talk to the elderly, they must use the hearing aids as a medium to exchange informatio...

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): H04W12/12G10L15/08G10L25/51H04W12/128
CPCH04W12/12G10L15/08G10L25/51G10L2015/088
Inventor 不公告发明人
Owner 李干群
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