CN112182537A - Monitoring method, device, server, system and storage medium - Google Patents
Monitoring method, device, server, system and storage medium Download PDFInfo
- Publication number
- CN112182537A CN112182537A CN202011041264.3A CN202011041264A CN112182537A CN 112182537 A CN112182537 A CN 112182537A CN 202011041264 A CN202011041264 A CN 202011041264A CN 112182537 A CN112182537 A CN 112182537A
- Authority
- CN
- China
- Prior art keywords
- operation instruction
- information
- risk value
- processing
- biological characteristic
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000012806 monitoring device Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 102
- 238000000605 extraction Methods 0.000 claims description 28
- 230000008921 facial expression Effects 0.000 claims description 16
- 230000036760 body temperature Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 description 16
- 238000012549 training Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 15
- 239000013598 vector Substances 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 230000014509 gene expression Effects 0.000 description 8
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 208000031636 Body Temperature Changes Diseases 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 210000000554 iris Anatomy 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010063659 Aversion Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the application provides a monitoring method, a monitoring device, a server, a monitoring system and a storage medium, wherein first biological characteristic information and an operation instruction of an operation instruction input by a user on a terminal device are obtained, the operation instruction acts on a financial business system, a risk value of the operation instruction is obtained according to the first biological characteristic information, and when the risk value reaches a preset threshold value, response to the operation instruction is stopped. The risk value of the operation instruction is determined through the biological characteristic information when the user inputs the operation instruction, so that the damage of the financial business system caused by people intentionally can be effectively reduced.
Description
Technical Field
The present application relates to the field of financial technology, and in particular, to a monitoring method, apparatus, server, system, and storage medium.
Background
With the rapid development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually changing to financial technology (Fintech), but higher requirements are also put forward on the technologies due to the requirements of the financial industry on safety and real-time performance.
The financial business system supports financial enterprises to engage in various financial businesses. The operation maintenance personnel (hereinafter referred to as operation maintenance personnel) can perform operations such as code change, data change and the like on the financial business system. In order to ensure the operation safety of the financial business system, different monitoring modes are set for the operation instructions used by operation and maintenance personnel. For example: when the operated instruction is not modified to the content in the financial business system, and the timeliness is high, the operation and maintenance personnel only need to confirm again and then execute the operation and maintenance instruction when the operation instruction is executed. When the operation instruction modifies the important content in the financial business system, the operation instruction can be executed after being checked by superior management personnel. When the operated instruction modifies important contents in the financial business system, the operation instruction is directly prevented from being executed because the operation instruction is not checked by superior management personnel.
However, the operation and maintenance personnel still have higher authority to use the operation instruction, the operation and maintenance personnel still cannot be prevented from damaging the financial service system by setting different monitoring modes for the operation instruction, and the monitoring mode through the authority is too single, so that the problem still cannot be accurately and effectively avoided.
Disclosure of Invention
The embodiment of the application provides a monitoring method, a monitoring device, a server, a monitoring system and a storage medium, and aims to provide a safer monitoring method so as to reduce the risk of damage to a financial business system by operation and maintenance personnel.
In a first aspect, the present application provides a monitoring method, including:
acquiring first biological characteristic information of an operation instruction input by a user on terminal equipment and the operation instruction, wherein the operation instruction acts on a financial service system;
obtaining a risk value of the operation instruction according to the first biological characteristic information;
and stopping responding to the operation instruction when the risk value reaches a preset threshold value.
Optionally, obtaining the risk value of the operation instruction according to the first biological feature information specifically includes:
processing the first biological characteristic information according to the trained processing model to obtain a risk value of the operation instruction;
wherein the first biometric information comprises: one or more combinations of body temperature data, first image data representing facial expressions, and second image data representing limb movements.
Optionally, the processing the first biological feature information according to the trained processing model to obtain the risk value of the operation instruction specifically includes:
processing the body temperature data according to the trained first processing model to obtain a first intermediate risk value;
processing the first image data according to the trained second processing model to obtain a second intermediate risk value;
processing the second image data according to a trained third processing model to obtain a third intermediate risk value;
obtaining the risk value according to the first intermediate risk value, the second intermediate risk value and the third intermediate risk value.
Optionally, the processing the first image data according to the trained second processing model to obtain a second intermediate risk value specifically includes:
processing the first image data by using the trained first key point extraction submodel to obtain first face key point information;
processing the face key point information and the first image data by using a trained first feature extraction submodel to obtain first feature data;
classifying the first feature data by using the trained classification submodel to obtain a psychological feature type of the first image data;
and determining the second intermediate risk value according to the psychological characteristic type.
Optionally, the method further comprises:
when the operation instruction is used for updating the version of the financial business system, acquiring the updating information of the financial business system; the updating information comprises one or more combinations of updating time, updating content, an operation account corresponding to the operation instruction and a system identifier of the financial business system;
if the updated information of the financial business system is matched with preset information, processing the first biological characteristic information according to a trained processing model to obtain a risk value of the operation instruction;
and if the updated information of the financial business system is not matched with the preset information, stopping responding to the operation instruction.
Optionally, the method further comprises:
if the updated information of the financial service system is not matched with the preset information, continuously judging whether the system identification of the financial service system is matched with the first preset identification; and if so, limiting the function permission of the operation instruction initiated by the operation account.
Optionally, the method further comprises:
acquiring a machine identifier of the terminal equipment;
and when the machine identifier is matched with a second preset identifier, acquiring the first biological characteristic information and the operation instruction.
Optionally, the method further comprises:
acquiring second biological characteristic information of the user;
and when the second biological characteristic information is matched with preset biological characteristic information, acquiring the first biological characteristic information and the operation instruction.
Optionally, when the second biometric information matches preset biometric information, the first biometric information and the operation instruction are acquired, specifically including
Processing the face image data by using a trained second key point extraction sub-model to obtain second face key point information, wherein the second biological characteristic information comprises the face image data;
processing the second face key point information and the face image data by using a trained second feature extraction sub-model to obtain second feature data;
when the difference value between the second characteristic data and preset characteristic data is smaller than a preset threshold value, acquiring the first biological characteristic information and the operation instruction;
and the preset characteristic data is obtained according to the preset biological characteristic information.
In a second aspect, the present application provides a monitoring device comprising:
the acquisition module is used for acquiring first biological characteristic information and an operation instruction of an operation instruction input by a user on the terminal equipment, wherein the operation instruction acts on the financial business system;
the processing module is used for obtaining a risk value of the operation instruction according to the first biological characteristic information;
the processing module is further used for stopping responding to the operation instruction when the risk value reaches a preset threshold value.
In a third aspect, the present application provides a monitoring server, including:
a memory for storing a program;
a processor for executing the program stored in the memory, the processor being adapted to perform the monitoring method according to the first aspect and the alternative when the program is executed.
In a fourth aspect, the present application provides a computer-readable storage medium having computer-executable instructions stored thereon, which, when executed by a processor, are configured to implement the monitoring method according to the first aspect and the alternative.
The embodiment of the application provides a monitoring method, a monitoring device, a server, a monitoring system and a storage medium, wherein first biological characteristic information of an operation instruction input by a user on a terminal device is obtained, a risk value of the operation instruction is obtained according to the first biological characteristic information, and the operation instruction is stopped responding when the risk value reaches a preset threshold value. The risk value of the operation instruction is determined through the biological characteristic information when the user inputs the operation instruction, compared with a traditional single authority monitoring mode, the risk value is determined through the biological characteristic information, so that the operation instruction is controlled, and the damage to a financial business system caused by people intentionally can be accurately and effectively reduced. In addition, the preset updating information and the biological characteristic information are combined for identity verification, so that the damage of the financial business system caused by people intentionally can be further reduced.
Drawings
Fig. 1 is a schematic structural diagram of a monitoring system according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a monitoring method according to another embodiment of the present application;
fig. 3 is a schematic flow chart of a monitoring method according to another embodiment of the present application;
fig. 4 is a schematic flowchart of a monitoring method according to another embodiment of the present application;
FIG. 5 is a schematic diagram of a second process model according to another embodiment of the present application;
fig. 6 is a schematic flow chart of face recognition according to another embodiment of the present application;
fig. 7 is a schematic structural diagram of a monitoring device according to another embodiment of the present application
Fig. 8 is a schematic structural diagram of a monitoring server according to another embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.
With the rapid development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually changing to financial technology (Fintech), but higher requirements are also put forward on the technologies due to the requirements of the financial industry on safety and real-time performance.
The financial business system supports financial enterprises to engage in various financial businesses. The operation maintenance personnel (hereinafter referred to as operation maintenance personnel) can perform operations such as code change, data change and the like on the financial business system. In order to ensure the operation safety of the financial business system, different monitoring modes are set for the operation instructions used by operation and maintenance personnel. For example: when the risk of the operated instruction is low but the timeliness is high, the operation instruction is executed only after the operation instruction is confirmed again by the operation and maintenance personnel. When the operation instruction is in danger, the operation instruction can be executed after being audited by superior management personnel. When the operated instruction is high risk, the operation instruction is directly prevented from being executed. However, the operation and maintenance personnel still have higher authority to use the operation instruction, and the operation and maintenance personnel still cannot avoid damaging the financial service system by setting different monitoring modes for the operation instruction.
The embodiment of the application provides a monitoring method, a monitoring device, a server, a monitoring system and a storage medium, and aims to provide a safer monitoring mode. The inventive concept of the embodiment of the application is as follows: acquiring biometric information of a user when inputting an operation instruction, for example: the body temperature, the facial expression or the limb movement and the like determine the risk value of the input operation instruction according to the biological characteristic information, and then determine whether to respond to the operation instruction according to the risk value, the biological characteristic information can reflect the risk of the user when inputting the operation instruction, and further determine whether to respond to the operation instruction input by the user.
As shown in fig. 1, a monitoring system 100 provided in the embodiment of the present application includes a monitoring server 101, a bastion machine 102, a terminal device 103, and a collecting apparatus 104.
The monitoring system is arranged in the enterprise master control center and is the only place for the operation and maintenance personnel to operate the financial service system.
The monitoring server 101 is in communication connection with the bastion machine 102, the monitoring server 101 is also in communication connection with the financial service system, and the terminal device 103 is in communication connection with the bastion machine. The terminal device 103 is used for acquiring an operation instruction input by a user, forwarding the operation instruction to the bastion machine 102, and forwarding the operation instruction to the monitoring server 101 by the bastion machine 102.
The fortress machine is equipment for monitoring and recording operation behaviors of operation and maintenance personnel on equipment such as servers, network equipment, safety equipment, database equipment and the like in the financial business system by using various technical means, and can conveniently give an alarm in a centralized manner, process in time and audit and determine responsibility. The bastion machine 102 receives the operation instruction forwarded by the terminal device 102 and forwards the operation instruction to the monitoring server 101, so that the safety performance of the monitoring system can be improved.
The acquisition device 104 may be integrated in the terminal device 103, and the biometric information acquired by the acquisition device and the operation instruction input by the user are transmitted to the bastion machine 102 through the terminal device 103 and then transmitted to the monitoring server 101 via the bastion machine 102. The acquisition device 104 may also be separately provided and communicatively connected to the monitoring server 101, and the acquisition device 104 directly transmits the biometric information when the user inputs the operation instruction to the monitoring server 101. The monitoring server 101 is configured to execute the monitoring method provided in the embodiment shown below, and the detailed description refers to the following description.
As shown in fig. 2, an embodiment of the present application provides a monitoring method, where an execution subject of the monitoring method is a monitoring server, and the monitoring method includes the following steps:
s201, acquiring first biological characteristic information and an operation instruction when a user inputs the operation instruction on the terminal equipment.
The operation instruction acts on the financial service system, that is, the operation instruction is used to modify the financial service system, for example: modifying data in the financial transaction system, or modifying a version of the financial transaction system.
The terminal device 103 acquires an operation instruction input by a user, and forwards the operation instruction to the bastion machine 102, and then forwards the operation instruction to the monitoring server 101 by the bastion machine 102.
When the acquisition device 104 is integrated in the terminal device, the terminal device 103 also needs to forward the biometric information acquired by the acquisition device 104 to the bastion machine 102, and the bastion machine 102 forwards the biometric information to the monitoring server 101.
When the acquisition device 104 is separately provided, the acquisition device 104 acquires biometric information and transmits the acquired biometric information to the monitoring server.
The first biometric information includes one or more combinations of body temperature data, first image data representing facial expressions, and second image data representing limb movements. The acquisition device comprises an infrared temperature sensor and an image sensor. The infrared temperature sensor is used for collecting body temperature changes of a user when an operation instruction is input. The image sensor is used for acquiring image data representing facial expressions or limb movements when a user inputs an operation instruction, and preferably, the image sensor acquires image data of a plurality of frames of facial expressions or limb movements.
S202, obtaining a risk value of the operation instruction according to the first biological characteristic information.
The risk value of the operation instruction can be obtained according to the first biological characteristic information by searching the preset mapping table. The preset mapping table is a relationship representing the biometric information and the risk value of the operation instruction.
The first biological characteristic information can be processed according to the trained processing model, and a risk value of the operation instruction is obtained. The processing model can use a model structure such as a convolutional neural network and a deep learning model, and the processing model is trained through the sample, so that the processing model can output a risk value of the operation instruction according to the first biological characteristic information.
And when the first biological characteristic information comprises body temperature data, first image data representing facial expressions and second image data representing limb movements, processing the body temperature data according to the trained first processing model to obtain a first intermediate risk value. And processing the first image data representing the facial expression according to the trained second processing model to obtain a second intermediate risk value. Processing the second image data representing the limb movement according to the trained third processing model to obtain a third intermediate risk value. And obtaining a risk value according to the first intermediate risk value, the second intermediate risk value and the third intermediate risk value.
Preferably, the risk value is obtained by calculating a weighted average of the first intermediate risk value, the second intermediate risk value and the third intermediate risk value.
S203, judging whether the risk value reaches a preset threshold value, if so, entering S204, and otherwise, entering S205.
The preset threshold is determined according to actual requirements, when the risk value of the operation instruction obtained according to the processing model reaches the preset threshold, the operation instruction is indicated to have higher risk, and then the operation instruction is stopped responding. And when the risk value of the operation instruction obtained according to the processing model is smaller than the preset threshold value, indicating that the risk of the operation instruction is lower, and responding to the operation instruction.
And S204, stopping responding to the operation instruction.
The operation instruction acts on the financial business system, and when the operation instruction is determined to have higher risk, the modification of the financial business system is stopped.
And S205, responding to the operation instruction.
And when the risk of the operation instruction is determined to be low, modifying the financial business system according to the operation instruction. For example: and modifying the version of the financial business system or modifying the data of the financial business system.
According to the monitoring method provided by the embodiment of the application, the risk value of the operation instruction is determined according to the biological characteristic information when the user inputs the operation instruction, and the operation instruction is stopped responding when the risk value exceeds the preset value, so that the damage of the financial business system caused by people intentionally can be effectively reduced.
As shown in fig. 3, another embodiment of the present application provides a monitoring method, where an execution subject of the monitoring method is a monitoring server, and the monitoring method includes the following steps:
s301, acquiring first biological characteristic information and an operation instruction when the user inputs the operation instruction on the terminal device.
The method comprises the steps of obtaining an operation instruction input by a user through terminal equipment, and collecting first biological characteristic information of the user when the operation instruction is input through a collecting device. The first biological characteristic information comprises one or more of body temperature data, image data representing facial expressions or image data representing limb movements.
S302, determining whether the operation instruction is used for updating the version of the financial business system, if so, entering S303, and otherwise, entering S309.
The operating instruction is analyzed to determine whether the operating instruction is used for updating the version of the financial service system, that is, the version of the financial service system is updated.
S303, acquiring the updating information of the financial service system.
And when the operation instruction is determined to be used for updating the version of the financial business system, acquiring the updating information of the financial business system. The updating information comprises one or more combinations of updating time, updating content, an operation account corresponding to the operation instruction and a system identifier of the financial business system.
S304, determining whether the updating information of the financial business system is matched with the preset information, if so, entering S309, otherwise, entering S305.
Wherein the preset information is determined according to an update plan of the financial transaction system. If the updated information of the financial business system is determined to be matched with the preset information, the updated information is planned, and the risk of the operation instruction is low. If the updated information of the financial business system is determined not to be matched with the preset information, the updated information is out of plan, and the risk of the operation instruction is high.
S305, stopping responding to the operation command.
And if the updated information of the financial service system is determined not to match the preset information and the risk of the operation instruction is high, stopping modifying the financial service system.
S306, continuously judging whether the system identifier of the financial business system is matched with the first preset identifier; if yes, go to S307, otherwise go to S308.
The first preset identification is determined according to the importance level of the financial service system, and the system identification of the financial service system with high importance level is set as the first preset identification. When the system identification of the financial service system to be updated is determined to be matched with the first preset identification, namely, the financial service system with a high importance level is updated.
S307, limiting the function authority of the operation instruction initiated by the operation account.
When the updated information of the financial business system is determined not to be matched with the preset information and the system identifier of the financial business system is determined to be matched with the first preset identifier, the risk of the operation instruction is high, and the function permission of the operation instruction initiated by the operation account is limited. For example: the operating account can only view the financial transaction system.
S308, generating warning information.
When the update information of the financial business system is determined to be not matched with the preset information and the system identifier of the financial business system is determined to be not matched with the first preset identifier, the operation instruction is an intermediate risk instruction, and warning information is generated.
S309, processing the first biological characteristic information according to the trained processing model to obtain a risk value of the operation instruction.
And training the processing model to enable the processing model to obtain the risk value of the operation instruction according to the first biological characteristic information.
And S310, judging whether the risk value reaches a preset threshold value, if so, entering S311, and otherwise, entering S312.
The preset threshold is determined according to requirements, the operation instruction with the risk value reaching the preset threshold is a high-risk operation instruction, and the operation instruction with the risk value smaller than the preset threshold is a low-risk operation instruction.
And S311, stopping responding to the operation instruction.
And when the operation instruction is a high-risk operation instruction, stopping the modification of the financial business system by the user through the terminal equipment.
And S312, responding to the operation instruction.
When the operation instruction is a low-risk operation instruction, the operation instruction is forwarded to the financial business system, so that the financial business system correspondingly modifies the code or data of the financial business system.
In the monitoring method provided by the embodiment of the application, the operation instruction is pre-screened, that is, whether the code of the financial service system can be modified is determined, whether the modification information is in plan and the grade of the financial service system is determined, and whether the risk value of the operation instruction is obtained is determined according to the pre-screening result, so that the efficiency of the monitoring method can be improved, and the monitoring of code updating can be realized.
As shown in fig. 4, another embodiment of the present application provides a monitoring method, where an execution subject of the monitoring method is a monitoring server, and the monitoring method includes the following steps:
s401, obtaining a machine identification of the terminal equipment.
The machine identifier of the terminal device may be a network address of the terminal device or a device code of the terminal device. The user sends a login request to the bastion machine through the terminal equipment, the bastion machine forwards the login request to the monitoring server, and the login request comprises the machine identification, the login account and the login password of the terminal equipment.
S402, judging whether the machine identifier is matched with the second preset identifier, if so, entering S403, and otherwise, entering S410.
The second preset identification is determined according to the machine identification of the terminal equipment arranged in the enterprise general control center, and is used for determining whether a user inputs an operation instruction by using the terminal equipment arranged in the enterprise general control center.
And S403, acquiring second biological characteristic information of the user.
The second biological characteristic information comprises any one of fingerprints, irises and faces and is used for uniquely identifying the user. The image of the fingerprint, the iris or the face can be collected through the image sensor, and the collected image is processed to obtain second biological characteristic information.
S404, determining whether the second biological characteristic information is matched with the preset biological characteristic information, if so, entering S405, and otherwise, entering S410.
Wherein the preset biometric information is determined based on biometric information of the registered user. When a user registers an operation account of the monitoring server, biometric information of the user needs to be entered.
S405, acquiring first biological characteristic information and an operation instruction when the user inputs the operation instruction on the terminal equipment.
S406, obtaining a risk value of the operation instruction according to the first biological characteristic information.
And S407, judging whether the risk value reaches a preset threshold value, if so, entering S408, and otherwise, entering S409.
And S408, stopping responding to the operation instruction.
And S409, responding to the operation instruction.
And S410, generating prompt information.
And when the machine identifier is determined not to be matched with the second preset identifier, generating prompt information to prompt a user not to log in by using the terminal equipment in the enterprise general control center. And generating prompt information when the second biological characteristic information is determined not to be matched with the preset biological characteristic information so as to prompt the user not to log in the operation account by oneself.
In the monitoring method provided by the embodiment of the application, the financial service system can be modified by limiting that the user can only use the terminal equipment in the enterprise master control center, so that the security of the modification of the financial service system is ensured.
Another embodiment of the present application provides a monitoring method, where an execution subject of the monitoring method is a monitoring server, and the monitoring method includes the following steps:
s501, acquiring first biological characteristic information and an operation instruction when the user inputs the operation instruction on the terminal device.
The first biological characteristic information comprises body temperature data, first image data representing facial expressions and second image data representing limb movements. And recording the body temperature change corresponding to the time through an infrared temperature sensor. The method comprises the steps of collecting face images and limb images of multiple frames of users through an image sensor, obtaining first image data representing facial expressions according to the face images, and obtaining second image data representing limb actions according to the limb images.
And S502, obtaining a risk value of the operation instruction according to the first biological characteristic information.
And training the first treatment model to enable the first treatment model to obtain a first intermediate risk value according to the body temperature data. And training the second processing model to enable the second processing model to obtain a second intermediate risk value according to the first image data representing the facial expression. And training the third processing model to enable the third processing model to obtain a third intermediate risk value according to the second image data representing the limb movement.
Obtaining the second intermediate risk value is described in detail below. And processing the first image data by using the trained first key point extraction submodel to obtain first face key point information. And processing the key point information of the face and the first image data by using the trained first feature extraction submodel to obtain first feature data. And classifying the first feature data by using the trained classification submodel to obtain a psychological feature type of the first image data. A second intermediate risk value is determined based on the psychographic feature type.
More specifically, when the second processing model processes the multiple frames of the first image data, the second processing model may take the areas such as the forehead, the eyebrows, the eyes, the nose, the mouth, the cheek and the like as key points of the face, extract key point information of the key points, obtain feature maps of the key points according to the first image data and the key point information, represent the feature maps of the areas to reflect the degree of confusion of the user when inputting an operation instruction, obtain facial expression types of the first image data according to the feature maps of the areas, and obtain a second intermediate risk value according to the obtained facial expression types. The corresponding relation between the expression type and the risk value can be set in advance, and when the expression type of the user is obtained according to the second processing model, a second intermediate risk value is obtained according to the corresponding relation.
The training process of the second process model is described below in conjunction with FIG. 5: training sample data for training the second processing model is obtained. Sample data was obtained from an existing facial expression dataset containing a total of 26190 48 x 48 gray scale images, which included image data for expression 6. Reference numeral 0 indicates anger, reference numeral 1 indicates aversion, reference numeral 2 indicates fear, reference numeral 3 indicates distraction, reference numeral 4 indicates distraction, reference numeral 5 indicates surprise, and reference numeral 6 indicates neutrality.
In order to prevent the network from being overfitting too fast, image transformation processing such as turning, rotating, cutting and the like can be carried out on the image data in the data set, namely data enhancement is carried out, the data volume of the database can be enlarged, and the robustness of the trained network is stronger.
The second processing model comprises a preprocessing submodel, a first key point extracting submodel, a first characteristic extracting submodel and a classification submodel. When the submodel is trained, the submodel is trained simultaneously by using the training sample data.
The preprocessing submodel is used for normalizing the size and the gray level of an image, and then target detection is carried out based on a Histogram of Oriented Gradients (HOG) of a sliding window, so that a target object area is obtained, and the size of data to be processed by a subsequent submodel is reduced.
The first key point extraction submodel is used for extracting key points of a target object region output by the preprocessing submodel to obtain key point information.
The feature extraction submodel is used for extracting features of the target object region and the key point information, wherein the feature extraction submodel is composed of a ResNet18 network structure and a Dropout network structure. The ResNet18 network structure is composed of two convolution layers and two BatchNorm layers, and a shortcut link is arranged at the input end and the output end of each module. The BatchNorm layer is used to achieve normalization.
Dropout network architecture is a general type of regularization method that randomly discards a portion of the input during the training process. The occurrence of overfitting can be effectively relieved, the regularization effect is achieved to a certain extent, and the robustness is enhanced.
And the classification submodel is used for determining the probability that the feature vector of the image data belongs to various expression categories, taking the expression category with the maximum probability as an output result, and then obtaining a second intermediate risk value according to the expression type and the corresponding relation. The classification submodel adopts the input of the softmax layer, removes a plurality of full connection layers in ResNet18, and directly identifies by softmax classification after one full connection layer.
The ResNet18 network structure, Dropout network structure, and softmax layer are explained separately below.
The ResNet18 network structure is largely divided into three sections, an input section, an output section, and an intermediate convolution section. The input section consists of a convolution kernel of size 7x7, step size 2, and a maximum pooling of size 3x3, step size 2, by which 224 x 224 images can be converted to 56 x 56 feature maps, greatly reducing the amount of data storage.
The middle convolution part corresponds to four convolution layers, wherein each convolution layer corresponds to a defective block which is divided into two paths. One path is subjected to two 3 multiplied by 3 convolutions, the other path is directly short-circuited, and the two paths are added and then output through a relu function. A 7 × 7 signature is finally output by these four convolutional layers.
The output part converts all feature maps into 1x1 through global adaptive smooth pooling, and then connects the output of the whole connection layer.
In the Dropout layer, rate is set to 20%, that is, 20% of neurons are randomly discarded. Different input masks are equivalent to learning all sub-network structures, joint adaptability among neuron nodes is eliminated and generalization capability is enhanced.
In softmax regression, the multi-classification problem is solved by the magnitude of the normalized probability. That is, the feature vector output by the previous layer is processed by a softmax classifier to obtain the probability of each type of expression, and the cross entropy loss function is used for calculation.
In the logical regression, the training sample pair is represented as { (x)1,y1),…,(xm,ym)}，xi∈Rn+1，xiAnd representing the feature vector of the image, i is more than or equal to 1 and less than or equal to m, and m is the total number of the training set. Feature vector xiIs n +1, is the number of,
corresponding to the intercept term. The class label y can take k different values, and the label y isjE.g., {1, 2.. eta.,. k }. The assumed function is as follows:
where θ represents the model parameter and T represents the transpose.
By training the model parameters θ, it is possible to minimize the cost function (2):
through the above process, the training process of the second process model is completed.
It should be noted that the first processing model may be a common neural network model, and the neural network model is trained to obtain the first intermediate risk value according to the body temperature data.
The model structure of the third process model is the same as that of the second process model, except that the training samples are different when the two models are trained. That is, the training sample pair of the third processing model is a training sample pair composed of images and expression types of different body movements.
More specifically, the second image data is processed by using the trained third key point extraction sub-model to obtain the limb key point information. And processing the limb key point information and the second image data by using the trained third feature extraction submodel to obtain third feature data. And classifying the third feature data by using the classification submodel to obtain the psychological feature type of the second image data. A third intermediate risk value is determined based on the psychographic feature type.
And S503, judging whether the risk value reaches a preset threshold value, if so, entering S504, and otherwise, entering S505.
After the first intermediate risk value to the third intermediate risk value are obtained respectively, the risk value of the operation instruction is obtained through weighted averaging, and the operation instruction is determined to be a high risk instruction or a low risk instruction according to the risk value.
And S504, stopping responding to the operation instruction.
And S505, responding to the operation instruction.
According to the monitoring method provided by the embodiment of the application, the risk value of the operation instruction is determined according to the biological characteristic information when the user inputs the operation instruction, and the operation instruction is stopped responding when the risk value exceeds the preset value, so that the damage of the financial business system caused by people intentionally can be effectively reduced.
Another embodiment of the present application provides a monitoring method, where an execution subject of the monitoring method is a monitoring server, and the monitoring method includes the following steps:
s601, acquiring a machine identifier of the terminal equipment.
The user sends a login request to the bastion machine through the terminal device, the bastion machine forwards the login request to the monitoring server, and the login request comprises a machine identifier, a login account and a login password of the terminal device. The monitoring server judges whether the account number has the face data recorded or not, and if not, the monitoring server prompts that the operation account number can be logged in only after the face data needs to be pre-recorded. And if the face data is input into the account, determining whether the user inputs an operation instruction by using the terminal equipment arranged in the enterprise master control center.
And S602, judging whether the machine identifier is matched with the second preset identifier, if so, entering S603, and otherwise, entering S609.
Here, this step has already been described in detail in S402, and is not described here again.
And S603, acquiring second biological characteristic information of the user.
And calling the image sensor to acquire second biological characteristic information of the user after determining whether the user inputs an operation instruction by using the terminal equipment arranged in the enterprise general control center.
S604, determining whether the second biological characteristic information is matched with the preset biological characteristic information, if so, entering S605, otherwise, entering S609.
Wherein the second biometric information comprises face image data; whether the second biometric information matches the preset biometric information is determined as follows. And processing the face image data by using the trained second key point extraction sub-model to obtain second face key point information. And processing the second face key point information and the face image data by using the trained second feature extraction submodel to obtain second feature data. And when the difference value between the second characteristic data and the preset characteristic data is smaller than a preset threshold value, acquiring first biological characteristic information and an operation instruction. Wherein, when the characteristic data is preset, the characteristic data is obtained according to preset biological characteristic information.
As shown in fig. 6, the following describes a process of determining whether the second biometric information matches the preset biometric information, taking the second biometric information as a face image as an example. The process comprises three processing processes of preprocessing the face image data, extracting key points and extracting features.
In the processing process, no matter the face image data is pre-recorded or the face image data is acquired from the camera in real time, the key point extraction is carried out after the size of the face image data is judged, namely, if the size of the face image data reaches the preset image size, the face image data needs to be compressed.
When the size of the face image data is smaller than the preset image size, the image is grayed, and each pixel is subjected to gamma correction, so that the influence of color and illumination is reduced.
After the above processing, the target detection is performed on the face image data. That is, the windows with different sizes and positions are used for sliding in the image to judge whether the window has the human face or not. And carrying out target detection by using HOG based on the sliding window to obtain a target image area.
The following describes the keypoint extraction process. And extracting the key points of the human face by using the pre-trained 68 key point extraction submodel in the dlib. The key point extraction comprises the following key steps:
(1) and calculating gradient values of pixel points in the target image region to obtain a gradient map.
For example, the gray-scale values of the upper, lower, left, and right pixels of the pixel point a are 32, 64, 20, and 30, respectively. Respectively calculating the horizontal gradient g of the pixel point AxAnd a vertical gradient gy。
gx＝30-20＝10 (3)
gy＝64-32＝32 (4)
The total gradient strength value g and gradient direction θ will be calculated according to the following equations:
(2) a gradient histogram is calculated. When calculating in an 8 × 8 pixel region, we can find 128 values, including gradient strength and gradient direction, 8 × 8 × 2. The division of 0-180 degrees into 9 intervals, which are (0, 20), (20, 40), … …, (160, 180) respectively. And then counting the interval of each pixel point. By statistically forming the gradient histogram, 128 values will become 9 values, which greatly reduces the amount of calculation. After counting the weighted votes of 64 points, each interval will get a value, and a histogram can be obtained. Inside the computer is an array of size 9.
(3) Normalization treatment: a pixel area is 8 × 8, a pixel block is composed of 4 pixel areas, a vector with the size of 9 in one pixel area is obtained in the previous step, each pixel block with the size of 16 × 16 will obtain a vector with the size of 36, for an image with the size of 64 × 128, normalization is performed by sliding according to the window of 16 × 16 and the step size of 8, 7 horizontal positions and 15 vertical positions can be obtained, 7 × 15-105 pixel blocks can be obtained in total, the vectors of all the pixel blocks are integrated, the size of a large one-dimensional vector is 36 × 105-3780, that is, the image is subjected to the above processing, and the total feature number is 3780.
(4) And (4) carrying out face key point detection on the features of the face gray level image obtained in the step by using a key point extraction sub-model, and finally outputting 68 face feature points.
The feature extraction process is described below, and the feature extraction is to obtain a 128-dimensional face feature vector according to a depth residual error network, and a pre-trained ResNet model in dlib is used. And inputting the face gray level picture obtained in the step and 68 personal face key points into the model to obtain 128-dimensional face feature vector output.
The implementation principle of the depth residual error network is as follows:
the deep residual error network adds residual error blocks in the convolution network, the residual error blocks generally have two layers, an activation function is represented by sigma, W1The first layer of the residual block is represented by the following specific calculation formula:
F(x)＝σ(W1x) (7)
σ(W1x) represents the output of the input data x through the first layer processing of the residual block.
And introducing the input data x of the previous two layers into the output of the current layer through a shortcut link, and taking the input data x as the output of the next layer through a relu linear rectification function, wherein the specific calculation formula is as follows:
y＝σ(σ(W2σ(W1x))+x) (8)
wherein, W1，W2Respectively representing a first layer of residual blocks and a second layer of residual blocks, sigma (W)2σ(W1x) output result of the first layer of the table residual block after the second layer of the residual block, sigma representing activation functionAnd (4) counting.
After second feature data of the face image data are obtained through the depth residual error network, the second feature data are compared with preset feature data to obtain a difference value of the two data, and whether the second biological feature information is matched with the preset biological feature information or not is determined according to the difference value of the two data. Preferentially, calculating the Euclidean distance between the second characteristic data of the face image data obtained by processing and the characteristic data of the face image data recorded in advance; and if the Euclidean distance is less than or equal to 0.4, the user operates the Euclidean distance, and the first biological characteristic information and the operation instruction are continuously acquired. Otherwise, judging that the operation is not self-operation, and terminating the authority and informing the account self.
S605, acquiring first biological characteristic information and an operation instruction when the user inputs the operation instruction on the terminal equipment.
And S606, obtaining a risk value of the operation instruction according to the first biological characteristic information.
And S607, judging whether the risk value reaches a preset threshold value, if so, entering S608, and if not, entering S609.
And S608, stopping responding to the operation instruction.
And S609, responding to the operation instruction.
S610, generating prompt information.
In the monitoring method provided by the embodiment of the application, the financial service system can be modified by limiting that the user can only use the terminal equipment in the enterprise master control center, so that the security of the modification of the financial service system is ensured.
As shown in fig. 7, another embodiment of the present application provides a monitoring apparatus 700, where the monitoring apparatus 700 includes:
an obtaining module 701, configured to obtain first biometric information of an operation instruction input by a user on a terminal device and the operation instruction, where the operation instruction acts on a financial service system;
a processing module 702, configured to obtain a risk value of the operation instruction according to the first biological characteristic information;
the processing module 702 is further configured to stop responding to the operation instruction when the risk value reaches a preset threshold.
Optionally, the processing module 702 is specifically configured to:
processing the first biological characteristic information according to the trained processing model to obtain a risk value of the operation instruction;
wherein the first biometric information comprises: one or more combinations of body temperature data, first image data representing facial expressions, and second image data representing limb movements.
Optionally, the processing module 702 is specifically configured to:
processing the body temperature data according to the trained first processing model to obtain a first intermediate risk value;
processing the first image data according to the trained second processing model to obtain a second intermediate risk value;
processing the second image data according to a trained third processing model to obtain a third intermediate risk value;
obtaining the risk value according to the first intermediate risk value, the second intermediate risk value and the third intermediate risk value.
Optionally, the processing module 702 is specifically configured to:
processing the first image data by using the trained first key point extraction submodel to obtain first face key point information;
processing the face key point information and the first image data by using a trained first feature extraction submodel to obtain first feature data;
classifying the first feature data by using the trained classification submodel to obtain a psychological feature type of the first image data;
and determining the second intermediate risk value according to the psychological characteristic type.
Optionally, the processing module 702 is specifically configured to:
when the operation instruction is used for updating the version of the financial business system, acquiring the updating information of the financial business system; the updating information comprises one or more combinations of updating time, updating content, an operation account corresponding to the operation instruction and a system identifier of the financial business system;
if the updated information of the financial business system is matched with preset information, processing the first biological characteristic information according to a trained processing model to obtain a risk value of the operation instruction;
and if the updated information of the financial business system is not matched with the preset information, stopping responding to the operation instruction.
Optionally, the processing module 702 is specifically configured to:
if the updated information of the financial service system is not matched with the preset information, continuously judging whether the system identification of the financial service system is matched with the first preset identification; and if so, limiting the function permission of the operation instruction initiated by the operation account.
Optionally, the obtaining module 701 is specifically configured to:
acquiring a machine identifier of the terminal equipment;
and when the machine identifier is matched with a second preset identifier, acquiring the first biological characteristic information and the operation instruction.
Optionally, the obtaining module 701 is specifically configured to:
acquiring second biological characteristic information of the user;
and when the second biological characteristic information is matched with preset biological characteristic information, acquiring the first biological characteristic information and the operation instruction.
Optionally, when the second biometric information matches preset biometric information, the first biometric information and the operation instruction are acquired, specifically including
Processing the face image data by using a trained second key point extraction sub-model to obtain second face key point information, wherein the second biological characteristic information comprises the face image data;
processing the second face key point information and the face image data by using a trained second feature extraction sub-model to obtain second feature data;
when the difference value between the second characteristic data and preset characteristic data is smaller than a preset threshold value, acquiring the first biological characteristic information and the operation instruction;
and the preset characteristic data is obtained according to the preset biological characteristic information.
As shown in fig. 8, a monitoring server 800 according to another embodiment of the present application includes: a transmitter 801, a receiver 802, a memory 803, and a processor 804.
A transmitter 801 for transmitting instructions and data;
a receiver 802 for receiving instructions and data;
a memory 803 for storing computer-executable instructions;
the processor 804 is configured to execute the computer-executable instructions stored in the memory to implement the steps performed by the monitoring method in the above embodiments. Reference may be made specifically to the description relating to the foregoing monitoring method embodiment.
Alternatively, the memory 803 may be separate or integrated with the processor 804. When the memory 803 is separately provided, the monitoring server further includes a bus for connecting the memory 803 and the processor 804.
An embodiment of the present application further provides a computer-readable storage medium, where a computer executing instruction is stored in the computer-readable storage medium, and when the processor executes the computer executing instruction, the monitoring method executed by the monitoring server is implemented.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (13)
1. A method of monitoring, comprising:
acquiring first biological characteristic information of an operation instruction input by a user on terminal equipment and the operation instruction, wherein the operation instruction acts on a financial service system;
obtaining a risk value of the operation instruction according to the first biological characteristic information;
and stopping responding to the operation instruction when the risk value reaches a preset threshold value.
2. The method according to claim 1, wherein obtaining the risk value of the operation instruction according to the first biometric information specifically includes:
processing the first biological characteristic information according to the trained processing model to obtain a risk value of the operation instruction;
wherein the first biometric information comprises: one or more combinations of body temperature data, first image data representing facial expressions, and second image data representing limb movements.
3. The method according to claim 2, wherein the processing the first biometric information according to the trained processing model to obtain the risk value of the operation instruction specifically comprises:
processing the body temperature data according to the trained first processing model to obtain a first intermediate risk value;
processing the first image data according to the trained second processing model to obtain a second intermediate risk value;
processing the second image data according to a trained third processing model to obtain a third intermediate risk value;
obtaining the risk value according to the first intermediate risk value, the second intermediate risk value and the third intermediate risk value.
4. The method according to claim 3, wherein the processing the first image data according to the trained second processing model to obtain a second intermediate risk value specifically comprises:
processing the first image data by using the trained first key point extraction submodel to obtain first face key point information;
processing the first face key point information and the first image data by using a trained first feature extraction submodel to obtain first feature data;
classifying the first feature data by using the trained classification submodel to obtain a psychological feature type of the first image data;
and determining the second intermediate risk value according to the psychological characteristic type.
5. The method of claim 1, further comprising:
when the operation instruction is used for updating the version of the financial business system, acquiring the updating information of the financial business system; the updating information comprises one or more combinations of updating time, updating content, an operation account corresponding to the operation instruction and a system identifier of the financial business system;
if the updated information of the financial business system is matched with preset information, processing the first biological characteristic information according to a trained processing model to obtain a risk value of the operation instruction;
and if the updated information of the financial business system is not matched with the preset information, stopping responding to the operation instruction.
6. The method of claim 5, further comprising:
if the updated information of the financial service system is not matched with the preset information, continuously judging whether the system identification of the financial service system is matched with the first preset identification; and if so, limiting the function permission of the operation instruction initiated by the operation account.
7. The method according to any one of claims 1-6, further comprising:
acquiring a machine identifier of the terminal equipment;
and when the machine identifier is matched with a second preset identifier, acquiring the first biological characteristic information and the operation instruction.
8. The method according to any one of claims 1-6, further comprising:
acquiring second biological characteristic information of the user;
and when the second biological characteristic information is matched with preset biological characteristic information, acquiring the first biological characteristic information and the operation instruction.
9. The method according to claim 8, wherein when the second biometric information matches preset biometric information, acquiring the first biometric information and the operation instruction comprises
Processing the face image data by using a trained second key point extraction sub-model to obtain second face key point information, wherein the second biological characteristic information comprises the face image data;
processing the second face key point information and the face image data by using a trained second feature extraction sub-model to obtain second feature data;
when the difference value between the second characteristic data and preset characteristic data is smaller than a preset threshold value, acquiring the first biological characteristic information and the operation instruction;
and the preset characteristic data is obtained according to the preset biological characteristic information.
10. A monitoring device, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first biological characteristic information of an operation instruction input by a user on terminal equipment and the operation instruction, and the operation instruction acts on a financial service system;
the processing module is used for obtaining a risk value of the operation instruction according to the first biological characteristic information;
the processing module is further used for stopping responding to the operation instruction when the risk value reaches a preset threshold value.
11. A monitoring server, comprising:
a memory for storing a program;
a processor for executing the program stored by the memory, the processor being configured to perform the monitoring method of any of claims 1 to 9 when the program is executed.
12. A monitoring system, comprising: terminal device, bastion machine, acquisition means and monitoring server according to claim 11.
13. A computer-readable storage medium having computer-executable instructions stored therein, which when executed by a processor, are configured to implement the monitoring method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041264.3A CN112182537A (en) | 2020-09-28 | 2020-09-28 | Monitoring method, device, server, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041264.3A CN112182537A (en) | 2020-09-28 | 2020-09-28 | Monitoring method, device, server, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112182537A true CN112182537A (en) | 2021-01-05 |
Family
ID=73943827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011041264.3A Pending CN112182537A (en) | 2020-09-28 | 2020-09-28 | Monitoring method, device, server, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112182537A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536269A (en) * | 2021-07-23 | 2021-10-22 | 中信银行股份有限公司 | Face recognition-based automatic token authorization method, device, equipment and storage medium for bastion machine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304308A (en) * | 2018-02-07 | 2018-07-20 | 平安普惠企业管理有限公司 | User behavior monitoring method, device, computer equipment and storage medium |
| CN109816893A (en) * | 2019-01-23 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Method for sending information, device, server and storage medium |
| CN109933503A (en) * | 2019-02-13 | 2019-06-25 | 平安科技（深圳）有限公司 | User's operation risk factor determines method, apparatus and storage medium, server |
| WO2019134246A1 (en) * | 2018-01-03 | 2019-07-11 | 平安科技（深圳）有限公司 | Facial recognition-based security monitoring method, device, and storage medium |
| CN110489951A (en) * | 2019-07-08 | 2019-11-22 | 招联消费金融有限公司 | Method, apparatus, computer equipment and the storage medium of risk identification |
| CN111429267A (en) * | 2020-03-26 | 2020-07-17 | 深圳壹账通智能科技有限公司 | Face examination risk control method and device, computer equipment and storage medium |
| CN111581661A (en) * | 2020-03-26 | 2020-08-25 | 平安普惠企业管理有限公司 | Terminal management method and device based on biological feature recognition and computer equipment |
| CN111612879A (en) * | 2020-05-22 | 2020-09-01 | 浙江讯飞智能科技有限公司 | Device detection method, device and readable storage medium |
| CN111641610A (en) * | 2020-05-19 | 2020-09-08 | 深信服科技股份有限公司 | Remote response and remote control method, device, equipment and storage medium |
-
2020
- 2020-09-28 CN CN202011041264.3A patent/CN112182537A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019134246A1 (en) * | 2018-01-03 | 2019-07-11 | 平安科技（深圳）有限公司 | Facial recognition-based security monitoring method, device, and storage medium |
| CN108304308A (en) * | 2018-02-07 | 2018-07-20 | 平安普惠企业管理有限公司 | User behavior monitoring method, device, computer equipment and storage medium |
| CN109816893A (en) * | 2019-01-23 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Method for sending information, device, server and storage medium |
| CN109933503A (en) * | 2019-02-13 | 2019-06-25 | 平安科技（深圳）有限公司 | User's operation risk factor determines method, apparatus and storage medium, server |
| CN110489951A (en) * | 2019-07-08 | 2019-11-22 | 招联消费金融有限公司 | Method, apparatus, computer equipment and the storage medium of risk identification |
| CN111429267A (en) * | 2020-03-26 | 2020-07-17 | 深圳壹账通智能科技有限公司 | Face examination risk control method and device, computer equipment and storage medium |
| CN111581661A (en) * | 2020-03-26 | 2020-08-25 | 平安普惠企业管理有限公司 | Terminal management method and device based on biological feature recognition and computer equipment |
| CN111641610A (en) * | 2020-05-19 | 2020-09-08 | 深信服科技股份有限公司 | Remote response and remote control method, device, equipment and storage medium |
| CN111612879A (en) * | 2020-05-22 | 2020-09-01 | 浙江讯飞智能科技有限公司 | Device detection method, device and readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536269A (en) * | 2021-07-23 | 2021-10-22 | 中信银行股份有限公司 | Face recognition-based automatic token authorization method, device, equipment and storage medium for bastion machine |
| CN113536269B (en) * | 2021-07-23 | 2024-05-03 | 中信银行股份有限公司 | Automatic fort token authorization method, device, equipment and storage medium based on face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10565433B2 (en) | Age invariant face recognition using convolutional neural networks and set distances | |
| CN107423690B (en) | Face recognition method and device | |
| CN111709409B (en) | Face living body detection method, device, equipment and medium | |
| CN111191616A (en) | Face shielding detection method, device, equipment and storage medium | |
| CN111274916B (en) | Face recognition method and face recognition device | |
| CN109886222B (en) | Face recognition method, neural network training method, device and electronic equipment | |
| CN110163236A (en) | The training method and device of model, storage medium, electronic device | |
| US11804071B2 (en) | Method for selecting images in video of faces in the wild | |
| US20190236738A1 (en) | System and method for detection of identity fraud | |
| CN113449704B (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| CN113205002B (en) | Low-definition face recognition method, device, equipment and medium for unlimited video monitoring | |
| US20150178544A1 (en) | System for estimating gender from fingerprints | |
| CN112949468A (en) | Face recognition method and device, computer equipment and storage medium | |
| CN112989334A (en) | Data detection method for machine learning and related equipment | |
| CN114333011A (en) | Network training method, face recognition method, electronic device and storage medium | |
| CN112182537A (en) | Monitoring method, device, server, system and storage medium | |
| CN112818899A (en) | Face image processing method and device, computer equipment and storage medium | |
| Silva et al. | POEM-based facial expression recognition, a new approach | |
| Sallam et al. | Iris recognition system using convolutional neural network | |
| Sai et al. | Student Attendance Monitoring System Using Face Recognition | |
| CN116229528A (en) | Living body palm vein detection method, device, equipment and storage medium | |
| CN109886320A (en) | A kind of human femur under loading X-ray intelligence reading method and system | |
| CN115601807A (en) | Face recognition method suitable for online examination system and working method thereof | |
| CN114038045A (en) | Cross-modal face recognition model construction method and device and electronic equipment | |
| CN114764948A (en) | Living body detection method, living body detection device, living body detection equipment and storage medium |
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 |