CN113538015A - Anti-fraud method, system and device based on image scene recognition - Google Patents
Anti-fraud method, system and device based on image scene recognition Download PDFInfo
- Publication number
- CN113538015A CN113538015A CN202110888410.4A CN202110888410A CN113538015A CN 113538015 A CN113538015 A CN 113538015A CN 202110888410 A CN202110888410 A CN 202110888410A CN 113538015 A CN113538015 A CN 113538015A
- Authority
- CN
- China
- Prior art keywords
- image
- client
- information
- image information
- fraud
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 238000012502 risk assessment Methods 0.000 claims description 42
- 238000012216 screening Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 230000001537 neural effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012015 optical character recognition Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The invention provides an anti-fraud method, a system and a device based on image scene recognition, which are applied to the field of image recognition anti-fraud; and analyzing and resolving the personal face image information authorized and uploaded by the client, and obtaining the risk evaluation degree of the client through a model algorithm by combining the image information and other information of the client in the past.
Description
Technical Field
The invention relates to the field of image recognition anti-fraud, in particular to an anti-fraud method, system and device based on image scene recognition.
Background
With the rapid development of information technology, software data is integrated into daily life, and great convenience is brought to people. However, data islanding, data falsification and information leakage follow the situation, and in order not to hurt the benefit of users, the software data system must be perfected, and anti-fraud is part of the wind control system.
The existing anti-fraud wind control platform comprises three parts of information extraction, information display and information verification. The information extraction is generally composed of a voice signal extraction technology, an optical character recognition technology, a crawler and semantic analysis, the information display is visualized according to the extracted information, and logic judgment is mainly used in the aspect of information verification. However, the existing anti-fraud wind control platform has unreliable data source and risks being tampered, the way for acquiring data is single, the safety of data transmission and calculation processes cannot be guaranteed, and when the data volume is too large, the calculated amount is judged by using logic, so that the efficiency is affected.
In view of the above, the invention provides an anti-fraud method and system based on image scene recognition and a cooperative device thereof, which perform analysis and analysis by using personal face image information uploaded by a client through authorization, and further obtain the risk assessment degree of the client through a model algorithm.
Disclosure of Invention
The invention aims to solve the reliability problem of anti-fraud, and provides an anti-fraud method, system and device based on image scene recognition.
The invention provides an anti-fraud method based on image scene recognition, which comprises the following steps:
when a client is connected with the system through WIFI and/or other wireless connection modes for the first time, the system prompts the client to authorize himself in a pop-up window mode so as to upload personal face image information into the system, and the system collects the image information;
after the system records the image, the system analyzes components in the picture based on image model information, separates character elements and background elements in the image, emphatically identifies the background elements in the image, and transmits the background elements and the image information to a server;
after detecting the image model information and the background elements, the system inputs the corresponding data of the image information and scans the classification of the image in a system database, and compares the uploaded photo information with the previous information one by one so as to combine the relevant information related to the client in the system;
the system utilizes a model algorithm arranged on the system, and the risk assessment probability of the client is judged through calculation of a corresponding formula, wherein the risk assessment probability is divided into three grades, namely low grade, medium grade and high grade.
Furthermore, the system inputs the corresponding data of the image information and scans the classification of the image in the system database after detecting the image model information and the background element, and compares the uploaded photo information with the previous information one by one, thereby combining the relevant information about the client in the system.
Further, the system is provided with a convolutional neural model algorithm for training the image recognition system.
Further, the step of the system providing the client risk assessment through a model algorithm comprises:
the system scans the image and combines the related information of the previous customer image;
the system uses a model identification comparison algorithm to calculate the risk assessment of the client;
and the system judges according to the calculated result, if the obtained risk assessment of the client is of a medium-high degree, the client is regarded as a fraud group, and if the obtained risk assessment of the client is of a low degree, the client is regarded as a non-fraud group.
Further, the model recognition comparison algorithm applied by the system is as follows:
，
wherein
Is the vector value of the entire image information,
a vector value that is single image information;
the invention also provides an anti-fraud system based on image scene recognition, which comprises the following steps:
an input section for the input section configured to input authorized image information and user identification information and/or image information for which unauthorized input is rejected, which are provided by the customer;
the acquisition part is used for carrying out corresponding detection scanning on the image information input into the system so as to acquire more specific information of a client from the image information;
the notification part is used for feeding back the scanned client image information and calculating the degree of the risk assessment probability and the like.
Further, the input section includes:
a viewing module: screening and eliminating image information uploaded by a client;
a logging module: and inputting the information of the image which can be input after the screening is eliminated into the system.
Further, the acquisition section includes:
a scanning module: scanning and analyzing the image information which can be recorded into the client after screening and removing;
an integration module: searching the corresponding previous image information record of the client and comparing the previous image information record with the image information which is synchronously scanned and analyzed so as to combine the past image information with the current image information of the client for summarizing;
further, the notification unit includes:
an operation module: substituting the summarized information about the client into a model algorithm to obtain a risk assessment result of the client;
an evaluation module: dividing the risk assessment degree of the client into three grades of low grade, medium grade and high grade;
the invention also provides an anti-fraud device based on image scene recognition, which comprises:
an input unit for inputting authorized image information and user identification information provided by a client and/or rejecting unauthorized image information
The acquisition unit is used for carrying out corresponding detection scanning on the image information input into the system so as to acquire more specific information of a client from the image information;
and the notification unit is used for feeding back the scanned client image information and calculating the degree of the risk evaluation probability and the like.
The invention provides an anti-fraud method, system and device based on image scene recognition, which have the following beneficial effects:
1. the invention applies a convolutional neural network model algorithm to enhance the capability of the system for image recognition.
2. The invention calculates and calculates the probability of risk assessment of the client by using a model algorithm, thereby effectively reducing the risk to be borne by the system.
Drawings
FIG. 1 is a general flow chart of an embodiment of an anti-fraud method based on image scene recognition according to the present invention;
FIG. 2 is a general flow diagram of an embodiment of an anti-fraud system based on image scene recognition according to the present invention;
FIG. 3 is a general flowchart of an embodiment of an anti-fraud apparatus based on image scene recognition according to the present invention;
the implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for anti-fraud based on image scene recognition in an embodiment of the present invention includes:
when a client is connected with the system through WIFI and/or other wireless connection modes for the first time, the system prompts the client to authorize himself in a pop-up window mode so as to upload personal face image information into the system, and the system collects the image information;
after the system records the image, the system analyzes components in the picture based on image model information, separates character elements and background elements in the image, emphatically identifies the background elements in the image, and transmits the background elements and the image information to a server;
after detecting the image model information and the background elements, the system inputs the corresponding data of the image information and scans the classification of the image in a system database, and compares the uploaded photo information with the previous information one by one so as to combine the relevant information related to the client in the system;
the system utilizes a model algorithm arranged on the system, and the risk assessment probability of the client is judged through calculation of a corresponding formula, wherein the risk assessment probability is divided into three grades, namely low grade, medium grade and high grade.
In a specific embodiment: the client is connected with the system through WIFI and/or other wireless connection modes, and uploads personal face image information to the system; after the system records the image information of the client, automatically analyzing the image information components of the client, separating the character elements from the background elements, emphasizing and identifying the background elements, and simultaneously transmitting the image information to a system scanning server; the scanning server scans the image information and searches the classification of the image in the system database from the server at the same time, compares the image information with similar image information or the previous image information one by one, and finally distinguishes the relevant information related to the client by combining the system; the system utilizes a model algorithm arranged on the system, calculates by a corresponding formula and calculates the risk assessment degree of a client, wherein the risk assessment degree is divided into three grades, namely low grade, medium grade and high grade.
In one embodiment: the system inputs corresponding data of image information and scans the classification of the image in a system database after detecting image model information and background elements, and compares the uploaded photo information with the previous information one by one, thereby combining the relevant information about the client in the system.
In this embodiment: the system scans the database image information to better effectively categorize the customer's image information than the customer's image information.
In a specific embodiment: a fraud prevention method based on image scene recognition is characterized in that a system records information related to an image of a client and scans and searches information similar to the image of the client from a database of the system so as to know the image information of the client more clearly.
In one embodiment: the system is provided with a convolutional neural model algorithm for training the image recognition system.
In this embodiment: the convolutional neural model algorithm acts to enhance the image recognition capability of the system.
In a specific embodiment: an anti-fraud method based on image scene recognition is characterized in that a convolution neural model arranged in a system provides an algorithm, and the algorithm is gradually promoted to be refined from the most coarsened recognition of an image.
In one embodiment: the step of providing the client risk assessment by the system through the model algorithm comprises:
the system scans the image and combines the related information of the previous customer image;
the system uses a model identification comparison algorithm to calculate the risk assessment of the client;
and the system judges according to the calculated result, if the obtained risk evaluation degree of the client is a medium-high degree, the client is regarded as a fraud group, and if the obtained risk evaluation degree of the client is a low degree, the client is regarded as a non-fraud group.
In this embodiment: the model algorithm evaluates the risk degree of the client, and a more accurate risk evaluation degree of the client can be calculated through a model recognition comparison algorithm;
in a specific embodiment: a system utilizes an identification comparison algorithm to calculate the risk evaluation degree of a client through a convolution neural model, and then judges whether the client is a fraud group; and if the obtained risk assessment degree of the client is a medium-high degree, the client is considered as a fraud group, and if the obtained risk assessment degree of the client is a low degree, the client is considered as a non-fraud group.
In one embodiment: the model standard identification comparison algorithm applied by the system is as follows:
in this embodiment: the model recognition comparison algorithm applied by the convolutional neural network is used for calculating the more accurate degree of the client risk assessment degree and the like;
in a specific embodiment: a system utilizes an identification comparison algorithm to calculate the risk evaluation degree of a client through a convolution neural model, and then judges whether the client is a fraud group; and if the obtained risk assessment degree of the client is a medium-high degree, the client is considered as a fraud group, and if the obtained risk assessment degree of the client is a low degree, the client is considered as a non-fraud group.
Referring to fig. 2, an anti-fraud apparatus based on image scene recognition according to an embodiment of the present invention includes:
the input part 1 is used for inputting authorized image information and user identification information provided by a client and/or rejecting unauthorized image information;
the acquisition part 2 is used for carrying out corresponding detection scanning on image information input into the system so as to acquire more specific information of customers from the image information;
the notification unit 3 feeds back the scanned image information of the client and calculates the degree of risk evaluation.
In a specific embodiment: the client is connected with the system through WIFI and/or other wireless connection modes, and uploads personal face image information to the input part 1; the input part 1 automatically analyzes the image information components after recording the client image information, separates the character elements from the background elements, emphasizes and identifies the background elements, and transmits the image information to the system scanning server; the acquisition part 2 scans the image information and searches the classification of the image in the system database from the server at the same time, compares the image information with similar image information or the previous image information one by one, and finally distinguishes the relevant information related to the client by combining the system; the notification unit 3 calculates the risk assessment degree of the client by using a model algorithm provided therein and using a corresponding formula, and the risk assessment degree is classified into three levels, i.e., low, medium, and high.
In one embodiment: the input section 1 is comprised of a,
a viewing module: screening and eliminating image information uploaded by a client;
a logging module: and inputting the information of the image which can be input after the screening is eliminated into the system.
In this embodiment: the input section 1 functions to input authorized image information and user identification information provided by a client and/or reject unauthorized image information.
In a specific embodiment: an anti-fraud device based on image scene recognition is characterized in that an inspection module of an input part 1 screens and eliminates image information uploaded by a client, and an input module inputs the screened and eliminated recordable image information into a system.
In one embodiment: the acquisition section 2 is provided with a plurality of acquisition sections,
a scanning module: scanning and analyzing the image information which can be recorded into the client after screening and removing;
an integration module: the corresponding previous image information records of the client are searched and compared with the image information analyzed by synchronous scanning so as to combine the past image information with the current image information of the client for summary.
In this embodiment: the acquisition part 2 is used for carrying out corresponding detection scanning on the image information input into the system so as to acquire more specific information of customers from the image information.
In a specific embodiment: a fraud-preventing device based on image scene recognition is characterized in that a scanning module is used for scanning and analyzing image information which can be recorded into a client after being screened and eliminated, an integrating module is used for searching and comparing a corresponding client previous image information record with image information which is synchronously scanned and analyzed, and the previous image information record and the current client image information record are combined to be summarized.
In one embodiment: the notification section 3 is comprised of a notification section,
an operation module: substituting the summarized information about the client into a model algorithm to obtain the risk assessment degree of the client;
an evaluation module: dividing the risk assessment degree of the client into three grades of low grade, medium grade and high grade;
in this embodiment: the notification unit 3 is configured to feed back the scanned image information of the client and calculate the degree of risk evaluation.
In a specific embodiment: an operation module is used for substituting summarized information related to a client into a model algorithm to obtain the risk assessment degree of the client, and an evaluation module is used for dividing the risk assessment degree of the client into three grades, namely low grade, medium grade and high grade.
An anti-fraud system based on image scene recognition in an embodiment of the present invention includes:
an input unit A for inputting authorized image information and user identification information and/or unauthorized image information provided by the client
The acquisition unit B is used for carrying out corresponding detection scanning on the image information input into the system so as to acquire more specific information of a client from the image information;
and the notification unit C is used for feeding back the scanned client image information and calculating the degree of the risk evaluation degree of the client image information.
In a specific embodiment: the client is connected with the system through WIFI and/or other wireless connection modes, and uploads personal face image information to the input part; the input unit A automatically analyzes the image information components of the client after recording the image information of the client, separates the character elements from the background elements, emphasizes and identifies the background elements, and simultaneously transmits the image information to a system scanning server; the acquisition unit B searches the classification of the image in the system database from the server while scanning the image information, compares the image information with similar image information or past image information one by one, and finally distinguishes the relevant information related to the client by combining the system; the notification unit C calculates the risk assessment degree of the client by using a model algorithm arranged in the notification unit C and a corresponding formula, and the risk assessment degree is divided into three grades, namely low grade, medium grade and high grade.
To sum up the above
The client is connected with the system through WIFI and/or other wireless connection modes, and uploads personal face image information to the system; after the system records the image information of the client, automatically analyzing the image information components of the client, separating the character elements from the background elements, emphasizing and identifying the background elements, and simultaneously transmitting the image information to a system scanning server; the scanning server scans the image information and searches the classification of the image in the system database from the server at the same time, compares the image information with similar image information or the previous image information one by one, and finally distinguishes the relevant information related to the client by combining the system; the system utilizes a model algorithm arranged on the system, calculates by a corresponding formula and calculates the risk assessment degree of a client, wherein the risk assessment degree is divided into three grades, namely low grade, medium grade and high grade.
1. The invention applies a convolutional neural network model algorithm to enhance the capability of the system for image recognition.
2. The invention calculates and calculates the probability of risk assessment of the client by using a model algorithm, thereby effectively reducing the risk to be borne by the system.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An anti-fraud method based on image scene recognition is characterized by comprising the following steps:
when a client is connected with the system through WIFI and/or other wireless connection modes for the first time, the system prompts the client to authorize himself in a pop-up window mode so as to upload personal face image information into the system, and the system collects the image information;
after the system records the image, the system analyzes components in the picture based on image model information, separates character elements and background elements in the image, emphatically identifies the background elements in the image, and transmits the background elements and the image information to a server;
after detecting the image model information and the background elements, the system inputs the corresponding data of the image information and scans the classification of the image in a system database, and compares the uploaded photo information with the previous information one by one so as to combine the relevant information related to the client in the system;
the system utilizes a model algorithm arranged on the system, and the risk assessment probability of the client is judged through calculation of a corresponding formula, wherein the risk assessment probability is divided into three grades, namely low grade, medium grade and high grade.
2. The method of claim 1, wherein the system scans the database image information including any one or more of the address of the image, the time of the image, the name of the image, the style of the image and the uploading person in the step of combining the related information about the client in the system by inputting the corresponding data of the image information and scanning the classification of the image in the system database after detecting the image model information and the background element, and comparing the uploaded image information with the past information one by one.
3. An anti-fraud method based on image scene recognition according to claim 1, characterized in that the system is provided with a convolutional neural model algorithm for training the image recognition system.
4. An anti-fraud method based on image scene recognition according to claim 1, characterized in that said step of providing the client risk assessment by the system through model algorithm comprises:
the system scans the image and combines the related information of the previous customer image;
the system uses a model identification comparison algorithm to calculate the risk assessment of the client;
and the system judges according to the calculated result, if the obtained risk assessment of the client is of a medium-high degree, the client is regarded as a fraud group, and if the obtained risk assessment of the client is of a low degree, the client is regarded as a non-fraud group.
5. The method of claim 4, wherein the model recognition comparison algorithm applied by the system is as follows:
wherein
Is the vector value of the entire image information,
is a vector value of the individual image information.
6. An anti-fraud method based on image scene recognition according to claim 1, characterized by comprising:
an input section for the input section configured to input authorized image information and user identification information and/or image information for which unauthorized input is rejected, which are provided by the customer;
the acquisition part is used for carrying out corresponding detection scanning on the image information input into the system so as to acquire more specific information of a client from the image information;
the notification part is used for feeding back the scanned client image information and calculating the degree of the risk assessment probability and the like.
7. An image scene recognition based anti-fraud system according to claim 6, characterized in that said input section comprises:
a viewing module: screening and eliminating image information uploaded by a client;
a logging module: and inputting the information of the image which can be input after the screening is eliminated into the system.
8. The system of claim 6, wherein the acquiring unit comprises:
a scanning module: scanning and analyzing the image information which can be recorded into the client after screening and removing;
an integration module: the corresponding previous image information records of the client are searched and compared with the image information analyzed by synchronous scanning so as to combine the past image information with the current image information of the client for summary.
9. An anti-fraud system based on image scene recognition according to claim 6, characterized in that said notification section comprises:
an operation module: substituting the summarized information about the client into a model algorithm to obtain the risk assessment degree of the client;
an evaluation module: the risk assessment degree of the client is divided into three grades, namely low grade, medium grade and high grade.
10. An image scene recognition-based anti-fraud device according to claim 1, characterized in that said image scene recognition-based anti-fraud device comprises:
an input unit for the input part configured to input authorized image information and user identification information provided by the client and/or reject unauthorized image information
An acquisition unit, wherein the acquisition part is configured to perform corresponding detection scanning on the image information input into the system so as to acquire more specific information of the client from the image information;
and a notification unit for the notification section configured to feed back the scanned client image information and calculate a degree of the risk evaluation degree thereof.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110888410.4A CN113538015A (en) | 2021-08-03 | 2021-08-03 | Anti-fraud method, system and device based on image scene recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110888410.4A CN113538015A (en) | 2021-08-03 | 2021-08-03 | Anti-fraud method, system and device based on image scene recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113538015A true CN113538015A (en) | 2021-10-22 |
Family
ID=78121907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110888410.4A Withdrawn CN113538015A (en) | 2021-08-03 | 2021-08-03 | Anti-fraud method, system and device based on image scene recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538015A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116127337A (en) * | 2022-09-08 | 2023-05-16 | 北京中关村科金技术有限公司 | Risk mining method, device, storage medium and equipment based on position and image |
-
2021
- 2021-08-03 CN CN202110888410.4A patent/CN113538015A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116127337A (en) * | 2022-09-08 | 2023-05-16 | 北京中关村科金技术有限公司 | Risk mining method, device, storage medium and equipment based on position and image |
| CN116127337B (en) * | 2022-09-08 | 2023-12-08 | 北京中关村科金技术有限公司 | Risk mining method, device, storage medium and equipment based on position and image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10990811B2 (en) | Image classification and information retrieval over wireless digital networks and the internet | |
| WO2020155939A1 (en) | Image recognition method and device, storage medium and processor | |
| CN102201061B (en) | Intelligent safety monitoring system and method based on multilevel filtering face recognition | |
| US7587070B2 (en) | Image classification and information retrieval over wireless digital networks and the internet | |
| CN109447597A (en) | More people carry out the method, apparatus and face identification system of attendance jointly | |
| CN106790054A (en) | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition | |
| CN110390229B (en) | Face picture screening method and device, electronic equipment and storage medium | |
| CN111861240A (en) | Suspicious user identification method, device, equipment and readable storage medium | |
| US9378406B2 (en) | System for estimating gender from fingerprints | |
| CN115512259A (en) | Multimode-based short video auditing method | |
| CN108446687A (en) | A kind of adaptive face vision authentication method based on mobile terminal and backstage interconnection | |
| CN105740752B (en) | Sensitive picture filtering method and system | |
| CN113538015A (en) | Anti-fraud method, system and device based on image scene recognition | |
| US20140025624A1 (en) | System and method for demographic analytics based on multimodal information | |
| KR102275741B1 (en) | System and method for providing user customized contents service using image information | |
| CN110378587A (en) | Intelligent quality detecting method, system, medium and equipment | |
| CN111914649A (en) | Face recognition method and device, electronic equipment and storage medium | |
| JP5751889B2 (en) | Face image authentication device | |
| CN113591619A (en) | Face recognition verification device based on video and verification method thereof | |
| Alharbi et al. | Face-voice based multimodal biometric authentication system via FaceNet and GMM | |
| CN111143176A (en) | Automatic identification method for internet surfing service business place | |
| CN113052100A (en) | Traffic identification method and related device | |
| CN111145413A (en) | Intelligent access control system and face recognition method thereof | |
| CN110891049A (en) | Video-based account login method, device, medium and electronic equipment | |
| CN117395079B (en) | Identity authentication system based on big data information management |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211022 |
|
| WW01 | Invention patent application withdrawn after publication |