CN111860350A - Anti-fraud device and method integrating face recognition and voice recognition - Google Patents
Anti-fraud device and method integrating face recognition and voice recognition Download PDFInfo
- Publication number
- CN111860350A CN111860350A CN202010716878.0A CN202010716878A CN111860350A CN 111860350 A CN111860350 A CN 111860350A CN 202010716878 A CN202010716878 A CN 202010716878A CN 111860350 A CN111860350 A CN 111860350A
- Authority
- CN
- China
- Prior art keywords
- fraud
- database
- module
- face recognition
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000002265 prevention Effects 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims description 21
- 230000009471 action Effects 0.000 claims description 15
- 230000006399 behavior Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000013459 approach Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000006698 induction Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000003405 preventing effect Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 7
- 230000036541 health Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Human Computer Interaction (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a fraud prevention device and a fraud prevention method integrating face recognition and voice recognition, wherein the fraud prevention device comprises a face recognition module, a pickup module, a voice analysis module, a main processing module and a background server, wherein the face recognition module, the pickup module and the voice analysis module are respectively connected with the main processing module, and the main processing module is connected with the background server. The invention has the beneficial effects that: 1. the anti-fraud device provided by the invention has effective reminding and preventing effects on possible fraud conditions by analyzing and judging the face and the chat records; 2. if a fraud condition occurs, the fraud prevention device of the invention stores face information and chat contents of a fraudster, can be used as an effective basis for alarming, provides more effective case solving information for police, and can also establish a background suspicious fraud personnel face database.
Description
Technical Field
The invention relates to the field of data processing, in particular to a fraud prevention device and method integrating face recognition and voice recognition.
Background
In recent years, people-related economic fraud cases specially aiming at the old are frequent, so that many old people are deeply harmed, and the old people living alone are easier to be cheated.
At present, fraud-proof software and devices and a bracelet capable of preventing telecommunication fraud are available on the market by analyzing conversation and short message contents; there are devices for putting fraud in hearing aids, but fraud prevention bands cannot prevent face-to-face fraud and fraud prevention hearing aids are not useful for the elderly who do not need to use hearing aids.
Disclosure of Invention
The invention provides a fraud prevention device integrating face recognition and voice recognition, which comprises a face recognition module, a pickup module, a voice analysis module, a main processing module and a background server, wherein the face recognition module, the pickup module and the voice analysis module are respectively connected with the main processing module, and the main processing module is connected with the background server;
the face recognition module: when a person approaches the fraud prevention device, the face recognition module rotates through the holder, opens the camera to perform face recognition and compares the face recognition with a face database in the database, and judges whether the person is trusted, suspicious and untrusted;
pickup module: the system is used for performing remote sound pickup and noise elimination functions;
a voice analysis module: the system is used for carrying out intelligent voice recognition and comparing with keywords in a database, judging whether the chat content is fraud or not and counting high-frequency names appearing in the chat content;
a main processing module: the system comprises a face recognition module, a control pickup module, a control voice analysis module and a background server, wherein the face recognition module, the control pickup module, the control voice analysis module and the background server are used for communication; the background server: and the background server performs matching through voiceprint analysis and a suspected fraud voiceprint library.
As a further improvement of the invention, the background server can match the audio intelligent analysis with the fraud model database, can also collect suspicious fraud sound sources and text information, and forms the fraud model database through machine learning; the background server can generate different prompts according to fraud modes, and the old people are informed by voices when the old people are possibly cheated.
The invention discloses a fraud prevention method integrating face recognition and voice recognition, which comprises the following steps:
step 201: the face recognition module detects that a person approaches, and starts the face recognition module;
Step 203: when the face is identified as an untrusted person, the face data is uploaded to a background server, the background server is matched with a database of suspicious persons in the database, if the face data is matched with the database of suspicious persons in the database, the suspicious persons are judged to be fraud, a notification device starts to execute the step 205, and fraud monitoring actions are prevented; if not, judging the person is a stranger;
step 204: for strangers, performing real-time voice recognition, and analyzing whether keywords appear in the fraud prevention database; counting the repeatedly occurring nouns, uploading to a background server for analysis, and if database keywords occur, entering step 205 to execute anti-fraud monitoring; if no keyword in fraud prevention appears, continuing monitoring until a stranger leaves the human body induction range;
step 205: performing fraud prevention monitoring;
step 206: performing an anti-fraud action;
step 207: and finishing monitoring.
As a further improvement of the present invention, in step 202, the face recognition module has a cloud platform function, and opens the camera, so that the face recognition module can track the human body to rotate, and perform face recognition on the coming person.
As a further improvement of the present invention, in step 202, trusted people in the database can enter through the fraud prevention device, and untrusted people can also be added to the trusted people face library of the database through the mobile phone client and the PC terminal.
As a further improvement of the present invention, in the step 203, the face recognition module cannot recognize the face due to various reasons, and also processes according to the stranger condition.
As a further improvement of the present invention, in the step 205, the fraud prevention monitoring comprises the following steps performed in sequence:
voiceprint analysis and matching step: synchronously uploading the recording and the real-time audio data to a background server, matching the background server with a suspected fraud voiceprint library through voiceprint analysis, entering a step 206 when matching occurs, and executing a fraud prevention action;
intelligent audio analysis and matching: the background server matches the audio intelligent analysis with the fraud model database, and if the audio intelligent analysis matches the fraud model database, the method proceeds to step 206 to execute the anti-fraud action.
As a further improvement of the present invention, in step 205, the method further includes performing the following steps: in the audio intelligent analysis and matching step, the fraud voiceprint data and fraud mode data source material sources of the suspected fraud voiceprint database comprise fraud sound source data and document data stored inside a public security, fraud sound source data and document data collected by a network server, and documents of fraud cases on a network.
As a further improvement of the present invention, in said step 206, the anti-fraud action comprises performing the following steps:
the first step is as follows: the anti-fraud device informs the family/guardian of the old through a telephone/mobile phone application program to prevent fraud, and the family/guardian can monitor the field condition in real time through a network and a mobile phone application to obtain the record for judging the fraud behavior; therefore, whether fraud behaviors are possible or not is judged manually, and if the fraud behaviors are judged, the deceived family can be contacted as soon as possible and alarm processing is carried out;
the second step is as follows: the anti-fraud device can contact the old through a telephone, inform the old to prevent fraud through synthesized audio, and enable the old to be alert;
the third step: the background server can push similar fraud case videos to the fraud prevention device and the mobile phone client for the old and the relatives to watch, and the fraud prevention capability is improved.
The invention has the beneficial effects that: 1. the anti-fraud device provided by the invention has effective reminding and preventing effects on possible fraud conditions by analyzing and judging the face and the chat records; 2. if a fraud condition occurs, the fraud prevention device of the invention stores face information and chat contents of a fraudster, can be used as an effective basis for alarming, provides more effective case solving information for police, and can also establish a background suspicious fraud personnel face database.
Drawings
FIG. 1 is a functional block diagram of the present invention;
fig. 2 is a flow chart of the present invention.
Detailed Description
As shown in fig. 1, the present invention discloses a fraud prevention apparatus integrating face recognition and voice recognition, which comprises a face recognition module 101, a sound pickup module 102, a voice analysis module 103, a main processing module 104, and a background server 105, wherein the face recognition module 101, the sound pickup module 102, and the voice analysis module 103 are respectively connected to the main processing module 104, and the main processing module 104 is connected to the background server 105;
the face recognition module 101: when a person approaches the fraud prevention device, the face recognition module can rotate through the holder, open the camera for face recognition and compare with a face database in the database, and judge whether to trust the person, suspect and untrusted person; the sound pickup module 102: the system is used for performing remote sound pickup and noise elimination functions;
the voice analysis module 103: the system is used for carrying out intelligent voice recognition and comparing with keywords in a database, judging whether the chat content is fraud or not and counting high-frequency names appearing in the chat content;
the main processing module 104: the system comprises the functions of storing, displaying, communicating, inputting, controlling the face recognition module 101, the sound pickup control module 102, the voice analysis control module 103 and the background server 105;
the backend server 105: the backend server 105 performs matching through voiceprint analysis and suspected fraud voiceprint library.
The background server 105 can match the audio intelligent analysis with the fraud model database, can also collect information such as suspicious fraud sound sources and texts, and forms the fraud model database through machine learning; background server 105 may generate different prompts according to fraud patterns and voice-notify the elderly when they may be deceived.
As shown in fig. 2, the present invention also discloses a fraud prevention method integrating face recognition and voice recognition, comprising the following steps:
step 201: when the face recognition module detects that a person approaches, the face recognition module 101 is started;
step 203: when the face is identified as an untrusted person, the face data is uploaded to the background server 105, matching is performed through the background server 105 and a suspicious person database in the database, if the match is determined as a fraud suspicious person, the notification device starts to execute step 205, and fraud prevention monitoring action is performed; if not, judging the person is a stranger;
step 204: for strangers, real-time voice recognition is carried out, whether the keyword in the fraud prevention database appears or not is analyzed, and the method comprises the following steps: transfer accounts, account numbers, passwords, loans "; counting the repeated nouns, uploading to the background server 105 for analysis, and if a database keyword occurs, entering step 205 to perform anti-fraud monitoring; if no keyword in fraud prevention appears, continuing monitoring until a stranger leaves the human body induction range;
for stranger conversations, the system counts the high frequency of occurring nouns and uploads the noun to the background server 105 for noun analysis. If the 'XX health care products' frequently appear, the 'XX health care products' are uploaded to the background server 105 for searching, and the evaluation of the health care products is judged whether to have passed marketing and fraud behaviors through searching and intelligent analysis of the background server 105. Initiating a fraud prevention action 206 if present;
stranger face features and images are uploaded to the background server 105 for the old man family/guardian mobile client or the PC client to check and set as trusted persons; after the face of the stranger is uploaded, the times and frequency of visiting the old man can be counted, and family/guardians are pushed to prevent strangers visiting the old man at high frequency.
The keywords in the fraud prevention database are derived from: 1. the background server 105 issues the intelligent identification; 2. the old man family/guardian is added to the mobile phone client or the PC client.
Step 205: fraud prevention monitoring;
step 206: performing an anti-fraud action;
step 207: and finishing monitoring.
In step 202, the face recognition module 101 has a cloud platform function, turns on the camera, can track the human body to rotate, and performs face recognition on the coming person.
In step 202, the trusted people in the database can enter through the fraud prevention device, and can also add the untrusted people to the trusted people face library of the database through the mobile phone client and the PC terminal.
In step 203, the face recognition module 101 cannot recognize the face due to various reasons, and also processes the face according to the situation of a stranger.
In said step 205, said fraud prevention monitoring comprises performing the following steps in sequence:
voiceprint analysis and matching step: synchronously uploading the recorded sound and the real-time audio data to the background server 105, matching the background server 105 with a suspected fraud voiceprint library through voiceprint analysis, entering step 206 when matching occurs, and executing fraud prevention action;
intelligent audio analysis and matching: background server 105 matches the audio intelligence analysis with the fraud model database, and if the audio intelligence analysis matches the fraud model database, step 206 is performed to prevent fraud.
In the audio intelligent analysis and matching step, the fraud voiceprint data and fraud mode data source material sources of the suspected fraud voiceprint database comprise fraud sound source data and document data stored inside a public security, fraud sound source data and document data collected by a network server, and documents of fraud cases on a network.
The suspected fraud voiceprint library performs voiceprint analysis on the obtained sound source, performs intelligent machine learning on the obtained document data to obtain a fraud model database, extracts fraud-preventing keywords and issues the fraud-preventing keywords to the fraud-preventing device.
In said step 206, the anti-fraud action comprises performing the steps of:
the first step is as follows: the anti-fraud device informs the family/guardian of the old through a telephone/mobile phone application program to prevent fraud, and the family/guardian can monitor the field condition in real time through a network and a mobile phone application to acquire the record for judging fraud behaviors; therefore, whether fraud behaviors are possible or not is judged manually, and if the fraud behaviors are judged, the deceived family can be contacted as soon as possible and alarm processing is carried out;
the second step is as follows: the anti-fraud device can contact the old through a telephone, inform the old to prevent fraud through synthesized audio (TTS) and enable the old to be alert; such as: you good, people just chatting with you may have XX fraud, XX negotiable possibilities, if the other party requests money transfer, contracts, account number password, etc. please be cautious. Such prompts would provide different voice prompts depending on the type of fraud analyzed by backend server 105.
The third step: the backend server 105 will push similar fraud case videos to the fraud prevention device and the mobile phone client for the old and the relatives to watch, thereby improving the anti-fraud capability.
The invention has the beneficial effects that: 1. the anti-fraud device provided by the invention has effective reminding and preventing effects on possible fraud conditions by analyzing and judging the face and the chat records; 2. if a fraud condition occurs, the fraud prevention device of the invention stores face information and chat contents of a fraudster, can be used as an effective basis for alarming, provides more effective case solving information for police, and can also establish a background suspicious fraud personnel face database.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A anti-fraud device integrating face recognition and voice recognition is characterized in that: the voice recognition system comprises a face recognition module (101), a pickup module (102), a voice analysis module (103), a main processing module (104) and a background server (105), wherein the face recognition module (101), the pickup module (102) and the voice analysis module (103) are respectively connected with the main processing module (104), and the main processing module (104) is connected with the background server (105);
the face recognition module (101): when a person approaches the fraud prevention device, the face recognition module rotates through the holder, opens the camera to perform face recognition and compares the face recognition with a face database in the database, and judges whether the person is trusted, suspicious and untrusted;
pickup module (102): the system is used for performing remote sound pickup and noise elimination functions;
speech analysis module (103): the system is used for carrying out intelligent voice recognition and comparing with keywords in a database, judging whether the chat content is fraud or not and counting high-frequency names appearing in the chat content;
main processing module (104): the system comprises the functions of storing, displaying, communicating, inputting, controlling the face recognition module (101), the control pickup module (102), the control voice analysis module (103) and the background server (105) for communication;
the backend server (105): the background server (105) matches the suspected fraud voiceprint library through voiceprint analysis.
2. The fraud prevention apparatus of claim 1, wherein: the background server (105) can match the audio intelligent analysis with a fraud model database, can also collect suspicious fraud sound sources and text information, and forms a fraud model database through machine learning; the background server (105) generates different prompts according to fraud modes, and notifies the old people by voice when the old people are probably cheated.
3. A fraud prevention method integrating face recognition and voice recognition is characterized by comprising the following steps:
step 201: the face recognition module detects that a person approaches, and starts the face recognition module (101);
step 202, the human face recognition module (101) is used for recognizing the human face of the coming person, the human face recognition module (101) is firstly compared with the human face library of the person in the database, if the human face exists in the database, the person is judged to be a trusted person, the anti-fraud device stops monitoring, if the human face does not exist in the database, the person is judged to be an untrusted person, and the step 203 is carried out.
Step 203: when the face is identified as an untrusted person, the face data is uploaded to a background server (105), the background server (105) is matched with a database of suspicious persons in the database, if the face data is matched with the database of suspicious persons in the database, the suspicious persons are judged to be fraud, a notification device starts to execute a step 205, and fraud prevention monitoring action is performed; if not, judging the person is a stranger;
step 204: for strangers, performing real-time voice recognition, and analyzing whether keywords appear in the fraud prevention database; counting the repeatedly occurring nouns, uploading to a background server (105) for analysis, and if a database keyword occurs, entering step 205 to execute anti-fraud monitoring; if no keyword in fraud prevention appears, continuing monitoring until a stranger leaves the human body induction range;
step 205: performing fraud prevention monitoring;
step 206: performing an anti-fraud action;
step 207: and finishing monitoring.
4. The fraud prevention method of claim 3, wherein in step 202, the face recognition module (101) has a cloud platform function, turns on a camera, can track the human body to rotate, and performs face recognition on the coming person.
5. The fraud prevention method as claimed in claim 3, wherein in said step 202, trusted people can enter into the database through the fraud prevention device, and untrusted people can be added into the database through the mobile phone client and PC terminal.
6. The fraud prevention method of claim 3, wherein in said step 203, the face recognition module (101) fails to recognize the face for various reasons and also processes according to stranger conditions.
7. The anti-fraud method of claim 3, wherein in said step 205, said anti-fraud monitoring comprises performing the following steps in sequence:
voiceprint analysis and matching step: synchronously uploading the recorded sound and the real-time audio data to a background server (105), matching the background server (105) with a suspected fraud voiceprint library through voiceprint analysis, entering a step 206 when matching occurs, and executing a fraud prevention action;
intelligent audio analysis and matching: the background server (105) matches the audio intelligent analysis and fraud model database at the same time, and if the audio intelligent analysis and fraud model database match, step 206 is performed to perform anti-fraud actions.
8. The fraud prevention method as claimed in claim 7, wherein in said audio intelligent analysis and matching step, the fraud voiceprint data, fraud mode data source material sources of suspected fraud voiceprint database comprise fraud sound source data and document data stored inside public security, fraud sound source data and document data collected by network server, documents of fraud cases on network.
9. The anti-fraud method of claim 3, wherein in said step 206, the anti-fraud action comprises performing the steps of:
the first step is as follows: the anti-fraud device informs the family/guardian of the old through a telephone/mobile phone application program to prevent fraud, and the family/guardian can monitor the field condition in real time through a network and a mobile phone application to obtain the record for judging the fraud behavior; therefore, whether fraud behaviors are possible or not is judged manually, and if the fraud behaviors are judged, the deceived family can be contacted as soon as possible and alarm processing is carried out;
the second step is as follows: the anti-fraud device can contact the old through a telephone, inform the old to prevent fraud through synthesized audio, and enable the old to be alert;
the third step: the background server (105) can push similar fraud case videos to the fraud prevention device and the mobile phone client for the old and the relatives to watch, and the fraud prevention capability is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010716878.0A CN111860350A (en) | 2020-07-23 | 2020-07-23 | Anti-fraud device and method integrating face recognition and voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010716878.0A CN111860350A (en) | 2020-07-23 | 2020-07-23 | Anti-fraud device and method integrating face recognition and voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860350A true CN111860350A (en) | 2020-10-30 |
Family
ID=72950313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010716878.0A Pending CN111860350A (en) | 2020-07-23 | 2020-07-23 | Anti-fraud device and method integrating face recognition and voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860350A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201681438U (en) * | 2010-05-07 | 2010-12-22 | 深圳市飞瑞斯科技有限公司 | Video monitoring system of automatic teller machine |
| CN103310339A (en) * | 2012-03-15 | 2013-09-18 | 凹凸电子（武汉）有限公司 | Identity recognition device and method as well as payment system and method |
| CN103731832A (en) * | 2013-12-26 | 2014-04-16 | 黄伟 | System and method for preventing phone and short message frauds |
| CN104427091A (en) * | 2013-08-22 | 2015-03-18 | 鸿富锦精密工业（深圳）有限公司 | Phone fraud prevention system and method |
| CN108055508A (en) * | 2017-12-19 | 2018-05-18 | 天津天地伟业信息***集成有限公司 | Monitoring system with face recognition function and monitoring method thereof |
| TWM565361U (en) * | 2018-04-02 | 2018-08-11 | 華南商業銀行股份有限公司 | Fraud detection system for financial transaction |
| CN109598110A (en) * | 2018-12-10 | 2019-04-09 | 北京羽扇智信息科技有限公司 | A kind of recognition methods of user identity and device |
| CN110348409A (en) * | 2019-07-16 | 2019-10-18 | 广州国音智能科技有限公司 | A kind of method and apparatus that facial image is generated based on vocal print |
-
2020
- 2020-07-23 CN CN202010716878.0A patent/CN111860350A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201681438U (en) * | 2010-05-07 | 2010-12-22 | 深圳市飞瑞斯科技有限公司 | Video monitoring system of automatic teller machine |
| CN103310339A (en) * | 2012-03-15 | 2013-09-18 | 凹凸电子（武汉）有限公司 | Identity recognition device and method as well as payment system and method |
| CN104427091A (en) * | 2013-08-22 | 2015-03-18 | 鸿富锦精密工业（深圳）有限公司 | Phone fraud prevention system and method |
| CN103731832A (en) * | 2013-12-26 | 2014-04-16 | 黄伟 | System and method for preventing phone and short message frauds |
| CN108055508A (en) * | 2017-12-19 | 2018-05-18 | 天津天地伟业信息***集成有限公司 | Monitoring system with face recognition function and monitoring method thereof |
| TWM565361U (en) * | 2018-04-02 | 2018-08-11 | 華南商業銀行股份有限公司 | Fraud detection system for financial transaction |
| CN109598110A (en) * | 2018-12-10 | 2019-04-09 | 北京羽扇智信息科技有限公司 | A kind of recognition methods of user identity and device |
| CN110348409A (en) * | 2019-07-16 | 2019-10-18 | 广州国音智能科技有限公司 | A kind of method and apparatus that facial image is generated based on vocal print |
Non-Patent Citations (2)
| Title |
|---|
| 刘红星;刘山葆;: "声纹识别和意图理解技术在电信诈骗检测中的应用研究", 广东通信技术, no. 07 * |
| 肖军;: "电信网络诈骗犯罪侦防中的关键技术研究", 中国人民公安大学学报(自然科学版), no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10810510B2 (en) | Conversation and context aware fraud and abuse prevention agent | |
| US11528450B2 (en) | Secure nonscheduled video visitation system | |
| CN109769099B (en) | Method and device for detecting abnormality of call person | |
| CN104834849B (en) | Dual-factor identity authentication method and system based on Application on Voiceprint Recognition and recognition of face | |
| US9800721B2 (en) | Multi-party conversation analyzer and logger | |
| US9728191B2 (en) | Speaker verification methods and apparatus | |
| US20220224795A1 (en) | Detecting robocalls using biometric voice fingerprints | |
| US20040001142A1 (en) | Method for suspect identification using scanning of surveillance media | |
| US20070299671A1 (en) | Method and apparatus for analysing sound- converting sound into information | |
| CN108012037B (en) | Management system for dialing telephone outside prison | |
| US20200389554A1 (en) | Caller identification in a secure environment using voice biometrics | |
| KR20180050968A (en) | on-line test management method | |
| CN109346085B (en) | Prison supervision platform based on voiceprint recognition | |
| CN110349586B (en) | Telecommunication fraud detection method and device | |
| US11418757B1 (en) | Controlled-environment facility video communications monitoring system | |
| TWM565361U (en) | Fraud detection system for financial transaction | |
| CN110868501A (en) | Fraud prevention method based on voice recognition and fraud prevention hearing aid | |
| JP2007266944A (en) | Telephone terminal and caller verification method | |
| KR101480103B1 (en) | Access control apparatus and method using face recognition | |
| CN114971627A (en) | Data monitoring system and method based on computer network | |
| TWI691923B (en) | Fraud detection system for financial transaction and method thereof | |
| WO2018187555A1 (en) | System and method for providing suicide prevention and support | |
| CN107729737A (en) | Identity information acquisition method and wearable device | |
| CN111860350A (en) | Anti-fraud device and method integrating face recognition and voice recognition | |
| US11606461B2 (en) | Method for training a spoofing detection model using biometric clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |