CN116665352B - Access control method and system - Google Patents
Access control method and system Download PDFInfo
- Publication number
- CN116665352B CN116665352B CN202310626444.5A CN202310626444A CN116665352B CN 116665352 B CN116665352 B CN 116665352B CN 202310626444 A CN202310626444 A CN 202310626444A CN 116665352 B CN116665352 B CN 116665352B
- Authority
- CN
- China
- Prior art keywords
- user
- access control
- identity
- data
- intelligent
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000004044 response Effects 0.000 claims abstract description 24
- 238000012795 verification Methods 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 8
- 230000002618 waking effect Effects 0.000 claims abstract description 7
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 48
- 230000006399 behavior Effects 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 description 25
- 239000013598 vector Substances 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 241000282414 Homo sapiens Species 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000005764 inhibitory process Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
- Telephonic Communication Services (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
Abstract
The embodiment of the specification provides an access control method and system, the method is applied to an access control system, the access control system comprises an intelligent control end, a mobile identification end and an intelligent lock, the intelligent control end and the intelligent lock are in communication connection, the method is executed by the intelligent control end and comprises the following steps: responding to the permission of the mobile identification terminal, and acquiring identity identification information corresponding to an access control mode through the mobile identification terminal; based on the identity identification information, carrying out identity verification on the user; in response to successful authentication, waking up the intelligent lock and establishing connection; and sending an unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction. Through presetting different access control modes, the method can improve access passing efficiency while guaranteeing access safety.
Description
Technical Field
The specification relates to the field of artificial intelligence, and in particular relates to an access control method and system.
Background
Under the wave of artificial intelligence, the intellectualization of the door lock gradually becomes a development trend. Through various identification methods and remote control means, the intelligent door lock can enable door opening to be faster. The intelligent door lock is generally opened temporarily after passing through the authentication to enable the user to pass through, and the user without authentication may be mixed into the user after authentication to pass through the gate.
In order to solve the problem of illegal opening, CN112562139B provides an access control method based on image recognition, and the application jointly confirms a target portrait by extracting a plurality of portrait areas, so that a plurality of people can be prevented from passing through the access control simultaneously. However, the successful personnel can only pass through the entrance guard by one person, the passing efficiency is low, and the waiting time of the passing personnel is too long in the time of large flow of people.
Therefore, the access control method and the access control system are beneficial to improving the access passing efficiency while solving the illegal rushing to close problem.
Disclosure of Invention
One or more embodiments of the present disclosure provide an access control method, where the method is applied to an access control system, where the access control system includes an intelligent control end, a mobile identification end, and an intelligent lock, where the intelligent control end is in communication connection with the intelligent lock, and the method is performed by the intelligent control end, and the method includes: responding to the permission of the mobile identification terminal, and acquiring identity identification information corresponding to an access control mode through the mobile identification terminal; based on the identity information, carrying out identity verification on the user; in response to the authentication success, waking up the intelligent lock and establishing connection; and sending the unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction.
One or more embodiments of the present specification provide an access control system, the system comprising: the intelligent control terminal is in communication connection with the intelligent lock; the intelligent control terminal is used for: responding to the permission of the mobile identification terminal, and acquiring identity identification information corresponding to an access control mode through the mobile identification terminal; based on the identity information, carrying out identity verification on the user; in response to the authentication success, waking up the intelligent lock and establishing connection; and sending the unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction.
One or more embodiments of the present specification provide an access control device comprising at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the access control method as in any of the embodiments above.
One or more embodiments of the present disclosure provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs the access control method of any one of the above embodiments.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is an exemplary flow chart of a door access control method according to some embodiments of the present disclosure;
FIG. 2 is an exemplary schematic diagram illustrating a determination of an access control mode according to some embodiments of the present description;
FIG. 3 is an exemplary schematic diagram of an intrusion prediction model according to some embodiments of the present description.
Fig. 4 is an exemplary schematic diagram illustrating an adjustment of access control modes according to some embodiments of the present disclosure.
Detailed Description
A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.
The requirements of different time on the passing efficiency and safety of the access control are different. The CN112562139B confirms one target figure in common by a plurality of figure areas, but is suitable only for an area where the flow of people is small or entrance guard at night because the passing efficiency is not considered when the flow of people is large. Therefore, some embodiments of the present disclosure preset different access control modes based on different time data, and may comprehensively consider safety and passing efficiency. Meanwhile, some embodiments of the present disclosure remind the user to re-verify through the access control system when the non-verified face is recognized, so that the person without identity verification can be prevented from forcefully running the gateway.
Fig. 1 is an exemplary flow chart of a door access control method according to some embodiments of the present description.
In some embodiments, process 100 may be performed by an intelligent control terminal in an access control system. In some embodiments, the access control system may include an intelligent control terminal, a mobile identification terminal, and an intelligent lock, with a communication connection between the intelligent control terminal and the intelligent lock.
In some embodiments, the access control system may be used in various situations where personnel access rights are set, for example, the application field may be smart device management, hotel room management, rental room management, password security door setting, apartment door lock management, shared automobile door lock management, safe door lock management, attendance door lock management, dormitory door lock management, and the like.
In some embodiments, the intelligent control terminal process may obtain the identification information and perform authentication on the user to control the opening and closing of the intelligent lock. In some embodiments, the identification information may be obtained by the mobile identification terminal.
The mobile identity may be a device with information acquisition, storage and/or transmission capabilities. For example, the mobile identification terminal includes, but is not limited to, one or a combination of several of a mobile device, a computer, a camera device, etc.
In some embodiments, the mobile identification terminal can be used for collecting various information related to identity identification. For example, the information collected by the mobile recognition terminal may include identity-related information of the user (e.g., face recognition information, iris recognition information, fingerprint recognition information, etc. of the user).
The intelligent lock refers to an execution device for opening and closing a door in an access control system. Smart locks include, but are not limited to, fingerprint recognition locks, iris recognition locks, vein recognition locks, voice recognition locks, and the like.
As shown in fig. 1, the process 100 includes the steps of:
step 110, in response to the mobile identification terminal being enabled, the mobile identification terminal obtains the identification information corresponding to the access control mode.
The mobile identification terminal is a mobile terminal for acquiring the identity identification information of the user. For more on the mobile identity side, see the relevant description above in fig. 1.
The access control mode refers to a mode of operation associated with the access control system. For example, the access control mode may include the kind of identification information, the maximum allowable number of passing people, and the like. For more on the maximum number of allowed passes, see the relevant description of fig. 2.
In some embodiments, the access control mode may include whether a mobile identification end is enabled, access transit time, etc. For more on the gate inhibition transit time, see the relevant description of fig. 3.
In some embodiments, the mobile identification terminal is enabled to enable functions related to information acquisition identification, information interaction with the intelligent control terminal and the like by allowing a user to operate at the mobile identification terminal. For example, the mobile recognition terminal is allowed to enable a click operation of one button, one link, which may be an opening operation of the related application program, or a display interface thereof. And responding to clicking a button or a link of the related application program display interface by the user, and collecting the identification information of the user by the mobile identification terminal.
In some embodiments, the intelligent control terminal may determine the access control mode in a variety of ways. For example, the intelligent control terminal may determine a history contemporaneous access control mode as the current access control mode.
In some embodiments, the intelligent control terminal may determine the access control mode based on the execution security level, and the relevant embodiment content may be referred to as the corresponding description of fig. 2.
The identification information refers to various information reflecting the identity of the user, and for example, the identification information may include any one or more of face recognition information, living body identification information (iris identification information, fingerprint identification information, etc.) of the user. In some embodiments, fingerprint identification information may be extracted from a user fingerprint image, face recognition information may be extracted from a user face image, and so forth.
In some embodiments, the intelligent control terminal may obtain the identification information in a variety of ways. For example, in response to the mobile identification terminal being enabled, the intelligent control terminal may acquire and obtain identification information via the mobile identification terminal via the network.
In some embodiments, the intelligent control terminal may also obtain the identification information directly in response to the mobile identification terminal not being allowed to be enabled. The intelligent control end can be provided with any one or combination of a camera, a fingerprint collector and the like for acquiring the identity identification information.
Step 120, based on the identification information, performing authentication on the user.
In some embodiments, the intelligent control terminal can perform identity verification on the user in various ways based on the identity information. For example, the intelligent control terminal can process the identity identification information through a face identification model to obtain the verification result of the identity identification information of the user.
The verification result of the identity identification information of the user means that the identity of the user is verified to judge the identity of the user corresponding to the identity identification information. For example, the authentication result of the identification information of the user may include any one or combination of authentication result of a face, authentication result of an iris, authentication result of a fingerprint, and the like. In some embodiments, the verification result of the identification information of the user may further include aging information. The aging information may reflect the validity time of the verification result of the identification information. For example, the intelligent control terminal can determine whether the verification of the identity information is out of date through the aging information.
The user identity may be pre-entered or stored in a personal identity repository. The personnel identity library can be used for storing identity information of personnel passing through the access control system. Each user identity has unique corresponding identity information such as face identification information, living body identification information, user numbers, user categories and the like.
In some embodiments, the face recognition model may be a machine learning model. The input of the face recognition model may comprise a face image and the output of the face recognition model may comprise the user identity and its recognition confidence. The recognition confidence is the accuracy for judging the user authentication result.
In some embodiments, the face recognition model may be trained from a plurality of first training samples with first labels. In some embodiments, the first training sample may comprise a sample face image, and the first training sample may be obtained from historical data. In some embodiments, the first label is whether the user identity and the authentication result corresponding to the first training sample are accurate. The first tag may be obtained based on human or processor labeling.
In some embodiments, the intelligent control terminal determines that the authentication is successful when it is determined that the user identity belongs to the allowed user and the recognition confidence is greater than the recognition threshold. The recognition threshold may be adjusted according to the execution security level, e.g., the higher the execution security level, the greater the recognition threshold. The successful verification may be that the currently verified user identity is consistent with the user identity stored in the personal identity repository, allowing passage.
In some embodiments, when the authentication is not successful, the intelligent control terminal may set the user identity to "unidentified user+number" and store in the personnel identity library.
In some embodiments, the intelligent control terminal may be a stand-alone device or may be part of the mobile identification terminal. In some embodiments, the intelligent control terminal may authorize the mobile identification terminal to perform authentication of the user and generate the unlocking instruction. The waiting time of a user can be reduced by completing identity verification and generating an unlocking instruction at the mobile identification end.
And 130, waking up the intelligent lock and establishing connection in response to successful authentication.
In some embodiments, the intelligent control terminal may send a wake-up signal to wake up the intelligent lock in response to successful authentication. The wake-up signal may be a signal indicating that the device is entering or ready to enter an operational state from a standby state.
In some embodiments, the intelligent control terminal may establish a communication connection with the intelligent lock after waking the intelligent lock. The communication connection may refer to signal transmission by means of WIFI, bluetooth low energy, and the like.
In some embodiments, the smart lock may be in a standby state when not unlocked, which may be the lowest power consumption operating state. After the authentication is successful, the intelligent control terminal can send Bluetooth broadcasting to wake up the standby intelligent lock, and after the intelligent lock is waken up, bluetooth connection is established with the intelligent lock.
Step 140, an unlocking instruction is sent to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction.
The unlock command refers to information related to unlocking. For example, the unlock instructions may include unlock ciphertext.
The unlocking ciphertext is generated by encrypting the unlocking plaintext by using a preset secret key and a specific encryption algorithm.
The unlocking plaintext refers to a data packet formed by mixing unlocking information. The unlocking information may include random information, unlocking request, device information, etc. The random information refers to a random number which is randomly generated and used for determining a preset key, and the device information refers to device information of an intelligent control terminal, such as MAC address information and the like.
The preset key may be a default key. The specific algorithm may be the AES128 algorithm, but may be other encryption algorithms.
In some embodiments, the intelligent control terminal may send an unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction, for example, the intelligent control terminal may send an unlocking ciphertext to the intelligent lock through bluetooth, so that after the intelligent lock receives the unlocking ciphertext, the intelligent lock decrypts the unlocking ciphertext by using a key matched with a preset key, and unlocks the intelligent lock after confirming that the decrypted information is valid. The encryption algorithm may be asymmetric encryption, symmetric encryption, or the like.
In some embodiments, the intelligent lock may acquire unlocking information after decryption is completed, determine whether the unlocking request and the device information in the unlocking information are valid, and unlock the intelligent lock if the unlocking request and the device information are valid. In some embodiments, the intelligent lock stores the MAC address information corresponding to the intelligent control terminal in advance, and if the decrypted MAC address information and the stored mismatch indicate that the decrypted MAC address information is not the unlocking ciphertext sent by the corresponding intelligent control terminal, the unlocking is not performed.
In some embodiments of the specification, through the access control system, after the authentication is successful, the intelligent control end and the intelligent lock are enabled to establish low-power-consumption Bluetooth connection, the intelligent lock is kept to work with low power consumption, the use cost can be effectively reduced while timely opening of the door is achieved, and the safety of the access control system and the endurance of the intelligent lock are greatly improved.
FIG. 2 is an exemplary schematic diagram illustrating a determination of an access control mode according to some embodiments of the present description.
In some embodiments, the intelligent control terminal may determine the execution security level 240 of the access control system based on the time data 210; based on the execution security level 240, an access control mode 250 is determined.
Time data 210 may refer to data related to time. In some embodiments, the time data may include specific date and time data. Specific date data may include holidays (specifically to what holidays, such as spring festival, weekend, etc.), weekdays, etc. Specific time data may include time periods (commute, night, early morning). In some embodiments, the execution security level corresponding to different time periods may be different, e.g., the execution security level at night is higher than the commute time period.
The enforcement security level 240 may refer to different security levels that are enforced by the access control system. In some embodiments, the execution security level may be divided into four levels, the first level of access control system only performs face recognition, allowing multiple persons to pass (the maximum number of persons allowed to pass may be determined based on actual traffic data, see specifically the description below in fig. 2); the second-level access control system only carries out face recognition, but one person is one card, and controls a single person to pass through; the third-level access control system performs iris or fingerprint recognition on the basis of face recognition and controls a single person to pass through; and the fourth-level access control system performs identity recognition through three types of recognition information (face, iris and fingerprint) and controls a single person to pass through.
In some embodiments, the mobile identification terminal may be disabled when the execution security level is at the third level and the fourth level, and at this time, the acquisition of the identification information is performed by the intelligent control terminal, and the information acquisition is not performed by the mobile control terminal, so as to strictly identify the identification information.
In some embodiments, the intelligent control side may determine the execution security level directly based on the time data 210. For example, the intelligent control terminal can set 7:00-9:00 in the morning as the rush hour, and the execution security level is at the first level. For another example, the intelligent control terminal may set the night time period to a special time period in which the safety level needs to be improved, and the execution safety level is at the fourth level.
In some embodiments, the intelligent control terminal may obtain the people traffic data 220 and determine the execution security level 240 based on the people traffic data 220 and the time data 210.
The people flow data 220 may refer to the number of people passing within a preset period of time. For example, the people flow data may be the number of people passing each minute.
People traffic class 230 may refer to a standard for dividing people traffic size. In some embodiments, the traffic levels may be divided into seven levels, the greater the traffic level, the greater the traffic. In some embodiments, different temporal data may affect the determination of the people traffic class. For example, the flow rate of people is rated seven when 30 people pass each minute during the day, but the flow rate of people is rated seven when 10 people pass each minute during the night.
In some embodiments, the people flow feature vector to be matched can be constructed based on the access control data, the people flow data and the time data (including specific time and date data), and the people flow grade can be determined by searching in a people flow feature vector database. In some embodiments, the vector database includes a plurality of reference people flow feature vectors, and the intelligent control terminal may determine the people flow level based on the similarity between the people flow feature vector to be matched and the corresponding reference people flow feature vector. In some embodiments, the people traffic level with the greatest similarity may be used as the determined people traffic level.
In some embodiments, the traffic level may need to be readjusted based on traffic data at intervals of a preset time, which may be set by human personnel. For example, the preset time is set to be five minutes, and the people flow characteristic vector needs to be reconstructed based on the current people flow data, the access control data and the time data every five minutes to determine a new people flow level.
In some embodiments, the access control data may include a current level of performance security and a maximum number of allowed passes.
In some embodiments, the intelligent control side may adjust the execution security level 240 based on the traffic level 230.
In some embodiments, the execution security level may be reduced when the people flow level is greater than the people flow threshold. For example, the execution security level corresponding to the access control mode determined according to the time data is two, at this time, the traffic level is seven, and the intelligent control terminal can reduce the execution security level to one level. In some embodiments, the minimum criteria for adjusting the security level based on the traffic level is required to meet the current time period requirements, e.g., the execution security level at night must be maintained above two levels.
In some embodiments, the people stream threshold may be determined based on the current execution security level and historical data, the higher the execution security level, the greater the people stream threshold.
In some embodiments, the performance security level adjusted based on the traffic level may need to be updated at intervals. For example, after a certain adjustment is performed to a security level, the recalculated traffic level is less than the traffic threshold, and the performance security level needs to be restored to the level before adjustment.
In some embodiments, the intelligent control may adjust the maximum allowed number of passes 251 in the access control mode based on the traffic level 230.
The maximum allowable passing number 251 may refer to the maximum number that can pass when the entrance guard is opened.
In some embodiments, the maximum allowable number of passes may be adjusted based on a preset adjustment strategy. For example, the maximum allowable passing number defaulted by the corresponding entrance guard control mode when the security level is at the first level is 3, if the traffic level is not less than five at this time, the maximum allowable passing number is adjusted to be 4, and if the adjusted traffic level is not reduced, the maximum allowable passing number is continuously adjusted to be 5. In some embodiments, the adjustment policy may be obtained based on historical experience.
In some embodiments of the present disclosure, the maximum allowable passing number in the access control mode is adjusted based on the traffic level, so that the maximum allowable passing number can be flexibly changed for different traffic levels, and the passing efficiency is improved when the traffic level is higher.
In some embodiments, the intelligent control terminal may reduce the maximum number of passing people or increase the execution security level when determining that the user breaks the way.
In some embodiments, the intelligent control end may increase the execution security level corresponding to the user when determining that the break-over frequency corresponding to the user is greater than the preset frequency threshold.
In some embodiments, the intelligent control terminal can predict the break-over frequency in a future time period through a break-over prediction model based on the people flow data and the time data; the security level is determined based on the traffic data, the time data, and the frequency of the intrusion. For more details on the intrusion prediction model, see fig. 3 and its associated description.
In some embodiments of the present disclosure, the execution security level of the access control system is determined based on the traffic data and the time data, and the requirements of the traffic and the time on the passing efficiency and the security are comprehensively considered, so that the access control mode is more reasonable.
In some embodiments, the intelligent control terminal can determine the type and the number of the identity recognition information and the maximum allowed number of the passing people based on the execution security level, and comprehensively determine the access control mode by combining the access time and whether the mobile recognition terminal is started or not.
In some embodiments, the intelligent control terminal can adjust the access control mode in various ways. For example, based on a preset comparison relation between the execution security level and the access control mode, the intelligent control end can adjust the execution security level to realize the adjustment corresponding to the access control mode.
In some embodiments of the present disclosure, the execution security level of the access control system is determined through the time data, and then the access control mode is determined based on the execution security level, so that different access control modes can be matched for different time, and requirements on access security and passing efficiency are satisfied.
It should be noted that the above description of the flow is only for the purpose of illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the flow may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.
FIG. 3 is an exemplary schematic diagram of an intrusion prediction model according to some embodiments of the present description.
In some embodiments, the access control mode further includes access times, the different execution security levels having respective access time settings, the determining the execution security level further including: based on the people flow data and the time data, predicting the break-over frequency in a future time period through a break-over prediction model; the security level is determined based on the traffic data, the time data, and the frequency of the intrusion.
The access control passing time is the holding time of the intelligent lock in the opening state after verification is passed. For example, the gate access time may be the gate open time.
In some embodiments, the longer the access transit time, the more the maximum number of allowed passes; conversely, the fewer.
The future period refers to a certain period of time after a preset current time.
The break-through frequency refers to the number of times that a user who does not perform or passes authentication in a preset time period is forced to pass through the access control. For example, the frequency of the break-through may include the number of times the strong traffic passes through the gate during a predetermined period of time. The preset time period may be set by the system or by human beings.
The jayway prediction model may be a machine learning model such as a neural network.
In some embodiments, the inputs to the intrusion prediction model 320 may include people flow data, time data, execution security level, maximum allowed number of passes, and so forth. The output of the intrusion prediction model 320 may include the intrusion frequency 340 over a future time period.
In some embodiments, the jayware predictive model may be trained based on a plurality of second training samples with second labels. In some embodiments, the second training sample may include sample people flow data, sample time data, sample execution security level, sample maximum allowable number of passes. Wherein, the sample time data refers to historical time data.
In some embodiments, the second tag may be a frequency of a break-through of the second training sample at a future time of the at least one sample. Wherein each sample future time period corresponds to an actual break-through frequency as a tag. The sample future time point refers to a point in time after the sample time data, and the sample future time period is also a historical time period.
In some embodiments, the second training sample may be obtained by collecting data. For example, actual recording is performed in an area where an entrance guard is installed, and traffic data, time data, execution security level, maximum allowable number of passes, and actual intrusion data are recorded. The first tag may be obtained based on a manual tag.
In some embodiments, the intelligent control terminal may determine an initial execution security level based on the time data; the initial execution security level is adjusted based on the traffic data, the predicted intrusion frequency. For example, the intelligent control terminal may preset a comparison relation between the time data and the initial execution security level, and determine the initial execution security level based on a table look-up manner. The initial execution security level may refer to an unregulated execution security level.
In some embodiments, the intelligent control terminal may reduce the initial execution security level when the current traffic level is greater than the traffic threshold and the break-over frequency is less than the first break-over threshold.
In some embodiments, the intelligent control terminal may maintain the initial execution security level when the current traffic level is greater than the traffic threshold and the break-over frequency is greater than the first break-over threshold.
In some embodiments, the intelligent control terminal may increase the initial execution security level when the current traffic level is greater than the traffic threshold and the break-over frequency is greater than the second break-over threshold.
In some embodiments, the intelligent control terminal may increase the initial execution security level when the current traffic level is less than the traffic threshold and the break-over frequency is greater than the first break-over threshold.
Wherein the people flow threshold, the first break-out threshold, the second break-out threshold (the second break-out threshold being greater than the first break-out threshold) may be determined based on system defaults or human settings.
In some embodiments, the gate inhibition transit time is related to an execution security level, the higher the execution security level, the shorter the gate inhibition transit time, and the smaller the corresponding maximum number of allowed passes. And each time the safety level is adjusted, the maximum allowable passing number correspondingly changes the adjustment.
In some embodiments, the intelligent control terminal may adjust the execution security level based on a preset adjustment value. For example, the intelligent control terminal can lower or raise the current execution security level one level at a time. The preset adjustment value may be a system default or a manually set value.
In some embodiments, the intrusion prediction model 320 may include an embedding layer 321 for generating the access characteristic 330.
The door control feature refers to parameter information related to the door control itself. For example, the access characteristic may include an access structural characteristic, an access distribution characteristic, and the like. The access control structural features may include access control width, access control passing depth, etc., and the access control passing depth may refer to the length of the side of the gate. The door distribution feature may include the number of doors, for example, the number of gates in a predetermined area. The preset area may refer to an area where an access control system needs to be provided, for example, an office building, a railway station, a school, or the like.
In some embodiments, the embedded layer may be a machine learning model such as a convolutional neural network model. The input to the embedded layer may include an access control image and the output may include an access control feature.
In some embodiments, the intrusion prediction model 320 may include an embedding layer 321 and a prediction layer 322 for predicting the intrusion frequency 340 over a future time period. The input to embedded layer 321 may include access control image 310 and the output may include access control feature 330. The inputs to the predictive layer 322 may include time data 210, people flow data 220, execution security level 240, maximum allowed number of passes 251, entrance guard feature 330, and the like. The output of the predictive layer 322 may include the frequency of the jayway 340 over a future time period.
In some embodiments, the embedding layer of the intrusion prediction model may be trained by migrating the training of the judgment model to the initial intrusion model after training.
The judgment model comprises two embedded layers and one judgment layer. The two embedding layers of the judgment model may be convolutional Neural networks (Convolutional Neural Networks, CNN) including a first embedding sub-layer and a second embedding sub-layer, and the judgment layer may be Neural Networks (NN). The input of the first embedded sub-layer may include a first access control image and the output of the first embedded sub-layer may include a first access control feature. The input of the second embedded sub-layer may include a second portal image and the output of the second embedded sub-layer may include a second portal feature. The input of the judging layer can comprise a first access control feature and a second access control feature, and the output of the judging layer can comprise a judging result, wherein the judging result is used for indicating whether the first access control feature and the second access control feature come from the same access control.
In some embodiments, the first embedded sub-layer, the second embedded sub-layer, and the judgment layer may be obtained through joint training. The third training sample of the joint training may include multiple sets of sample access images (each set of sample access images including a pair of access images), and the third tag may include whether each set of sample access image pairs in the third sample are access images from the same place (cell). If so, the tag may be 1, otherwise the tag may be 0. A third training sample may be obtained based on the acquisition and a third label may be obtained by manual annotation.
An exemplary joint training process includes: inputting one of each pair of access images in a third training sample into an initial first embedding sub-layer to obtain a first access feature output by the first embedding sub-layer, inputting the other of each pair of access images in the third training sample into an initial second embedding sub-layer to obtain a second access feature output by the second embedding sub-layer, inputting the first access feature output by the first embedding sub-layer and the second access feature output by the second embedding sub-layer into an initial judging layer to obtain whether the first access feature and the second access feature come from the same place; and constructing a loss function according to the output of the initial judgment layer and the third label, and simultaneously updating parameters of the first embedded sub-layer, the second embedded sub-layer and the judgment layer until the preset condition is met, and finishing training. The preset condition may be that the loss function is smaller than a threshold, converges, or the training period reaches the threshold.
The first access control feature and the second access control feature can respectively correspond to different types of access control features, such as access control structural features, access control distribution features and the like.
In some embodiments, the intelligent control end can determine parameters of the embedded layer based on the above manner, and when the intrusion prediction model is trained, the parameters of any one embedded sub-layer are migrated to the embedded layer of the intrusion prediction model and fixed, and sample access control features are determined by processing sample access control images based on the embedded layer.
Then, the intelligent control end can input sample people flow data, sample time data, sample execution safety level, maximum allowed passing number of samples and sample entrance guard characteristics into an initial prediction layer, and determine the break-over frequency in an initial future time period; a loss function is constructed based on the frequency of the break-through and the second tag over an initial future time period. Updating the initial prediction layer based on the loss function, and determining the trained prediction layer through parameter updating. The sample people flow data, the sample time data, the sample execution security level and the maximum allowed passing number of the sample can be obtained based on historical data related to a sample access control image, and the sample access control characteristics can be obtained based on the trained embedded layer.
According to the embodiment of the specification, the parameters of the trained embedded layer are migrated to the interloper prediction model, so that the problem that labels are difficult to obtain when the embedded layer is independently trained is solved, the training efficiency of the evaluation model is improved, and the training difficulty is reduced.
In some embodiments of the present disclosure, by predicting the intrusion frequency in the future time period through the intrusion prediction model, a reliable intrusion frequency can be obtained, which is beneficial to improving the accuracy of the subsequent execution of the security level adjustment.
Fig. 4 is an exemplary schematic diagram illustrating an adjustment of access control modes according to some embodiments of the present disclosure.
In some embodiments, the intelligent control terminal may obtain the personal data 430 of the user from the pre-stored database 420 based on the verification result 410 of the identification information of the user; based on the personal data, determining whether the user has abnormal behavior 460; in response to the presence of abnormal behavior, an adjustment 470 to the access control mode is performed.
For more on the verification result of the identification information of the user, reference may be made to the relevant description of fig. 1.
A pre-stored database refers to a database for storing, indexing and querying reference vectors. For example, a plurality of reference vectors are included in a pre-stored database. The reference vector may be constructed based on personal data of the user.
The user's personal data 430 is data related to the user's access. For example, the user's personal data 430 may include identification data 430-1, user traffic records 430-2, historical behavioral exception rates 430-3, user operational data 430-4. The user pass record may be a record of the user entering and exiting the gate inhibition. The user operation data may be abnormal behavior (e.g., face blocked, camera blocked, forced rushing to close, etc.) made by the user in and out of the access control. The historical behavior anomaly rate may be a ratio of the number of times the user experiences an anomalous behavior over a period of time in the history to the total number of times the user passes through the access control. The identification data can refer to an identity verification result, and the identification data can comprise a current identity verification result and a history identity verification result passing through the entrance guard.
The abnormal behavior may be a user authentication behavior when the number of user authentication failures exceeds a number threshold.
In some embodiments, the intelligent control terminal may determine whether the user has abnormal behavior based on the identification data of the user. For example, the intelligent control terminal may count the total number of authentication failures, and determine the user authentication behavior corresponding to the total number of authentication failures exceeding the first preset threshold as the abnormal behavior when the total number of authentication failures exceeds the first preset threshold. The first preset threshold may be determined empirically or experimentally.
In some embodiments, the intelligent control terminal may determine whether the user has abnormal behavior based on the type of the identification information and the corresponding verification result thereof. For example, when the identification information includes face identification information, it is determined that the user has abnormal behavior based on the total number of failures of face identification exceeding a first preset threshold.
In some embodiments, when it is determined that the user has abnormal behavior, the intelligent control terminal may stop authentication of the user having abnormal behavior; sending out an alarm prompt and waiting for a result of on-site confirmation of a staff, and selecting whether to unlock or not based on the result; the record is saved to the user's personal data.
In some embodiments, when it is determined that the user has abnormal behavior, the intelligent control terminal may increase the execution security level, and enter the abnormal prevention state until it is continuously determined that a preset number of users have no abnormal behavior, and restore to the default security level. The abnormal prevention state may be that the entrance guard control mode is strictly executed without accepting the adjustment. The preset number may be a system default or a manually set value.
In some embodiments, if in the abnormal prevention state, the intelligent control end may increase the execution security level when detecting the abnormal behavior of the user.
In some embodiments, the intelligent control end may output the confidence 450 of the user behavior abnormality through the abnormal behavior recognition model 440 based on the personal data 430 of the user, so as to determine whether the user has abnormal behavior 460, and relevant embodiments of the determination may be referred to as corresponding descriptions below.
In some embodiments, the abnormal behavior recognition model may be a machine learning model such as a neural network model.
In some embodiments, the input of the abnormal behavior recognition model may include recognition data, user traffic records, historical behavior anomaly rates, user operation data, etc., and the output of the abnormal behavior recognition model may include confidence that the user behavior is abnormal. The confidence of a user behavior anomaly may refer to the probability that the user has an anomalous behavior.
In some embodiments, the abnormal behavior recognition model may be trained from a number of fourth training samples with fourth labels. In some embodiments, the fourth training sample may include a sample user pass record, a sample user behavioral anomaly rate, sample user operational data, and the fourth training sample may be obtained from historical data. In some embodiments, the fourth label is whether the user corresponding to the fourth training sample has abnormal behavior, for example, the label corresponding to the abnormal behavior is 1 if there is abnormal behavior, and the label corresponding to the abnormal behavior is 0 if there is no abnormal behavior.
In some embodiments, when the confidence level of the abnormal behavior of the user is greater than the abnormal confidence threshold, the intelligent control end may increase the execution security level, and enter the abnormal prevention state until continuously determining that the preset number of users have no abnormal behavior, and restore to the default security level. The description of the abnormality prevention state and the preset number can be referred to the corresponding description above. The anomaly confidence threshold may be a system default or a manually set value.
In some embodiments of the present disclosure, the confidence level of the user behavior abnormality is determined through the abnormal behavior recognition model, and the accuracy and efficiency of determining the user behavior abnormality can be improved by using the self-learning capability of the machine learning model.
In some embodiments, the intelligent control terminal may obtain personal data of a plurality of users from a pre-stored database in response to simultaneously obtaining face recognition information of the plurality of users; and judging that the user has abnormal behavior in response to the authentication failure of at least one user in the plurality of users.
The face recognition information may be face related information of the user. In some embodiments, the intelligent control terminal may obtain face images including face recognition information of a plurality of users through the camera.
In some embodiments, the intelligent control end may process the face image through a face recognition model to obtain a user identity of at least one user and a recognition confidence level thereof. For more on the acquisition of face recognition information by a face recognition model, see the relevant description of fig. 1.
In some embodiments, the intelligent control terminal may determine that the user has abnormal behavior in response to the identification confidence coefficient of the user identity being less than the identity confidence coefficient threshold, and prompt the user to need to perform independent identification.
In some embodiments, in response to obtaining an access control image with face identification information of a plurality of users, when authentication of at least one user is successful and authentication failure of at least one user is also present, the intelligent control terminal can send out an alarm prompt, so that the plurality of users are prompted to perform authentication again, the situation that the user with the authentication failure is followed by the access control is avoided, and further potential strangers are prevented from forcibly rushing to close when the access control is opened.
In some embodiments, the intelligent control terminal may add the user to the attention list in response to the number of the user's breaks being greater than a preset break threshold. The attention list may be a list of users who are prohibited from passing through or a list of people who need to be confirmed by a staff site.
The preset frequency threshold and the preset jaywalking threshold can be values set by a system or a person.
The identity confidence threshold may be the lowest confidence that the user authentication was successful.
In some embodiments, the identity confidence threshold for the user identity is related to historical companion data for the plurality of users.
The history company data is data of a plurality of users accompanying access. The historical companion data may include a record of the identity of the user on the companion line.
In some embodiments, for multiple users with frequent accompaniment, the intelligent control terminal may reduce the identity confidence threshold of some users in the multiple users with frequent accompaniment when judging that the identification confidence of more than half of the users is greater than the identity confidence threshold. For example, the identity confidence coefficient threshold value is 90%, if the historical companion times of the user 1, the user 2 and the user 3 are greater than the companion threshold value, when the user 1, the user 2 and the user 3 are simultaneously identified, and the identification confidence coefficient of two users is greater than 90%, the identity confidence coefficient of the third user only needs to reach 85%, and the verification can be passed.
The plurality of users who are frequently paired may be a plurality of users who have a historical number of paired times greater than a paired threshold for a certain period of time. The companion threshold may be a system or an artificially set value.
According to some embodiments of the specification, through historical companion data, the identity confidence threshold is adjusted, so that the access security is ensured, and meanwhile, the passing rate of multiple persons in the same time is improved.
According to the embodiment of the specification, through judging the abnormal behavior of the user, the safety of the access control system can be improved, different access control strategies are matched for different users, and the travel efficiency is further improved.
In one or more embodiments of the present disclosure, there is further provided an access control device, including a processor, where the processor is configured to perform the access control method according to any one of the embodiments above.
There is also provided in one or more embodiments of the present specification a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs the access control method as described in any one of the embodiments above.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (8)
1. An access control method, the method is applied to an access control system, the access control system comprises an intelligent control end, a mobile identification end and an intelligent lock, the intelligent control end is in communication connection with the intelligent lock, the method is executed by the intelligent control end, and the method comprises:
responding to the permission of the mobile identification terminal, and acquiring identity identification information corresponding to an access control mode through the mobile identification terminal;
based on the identity information, carrying out identity verification on the user; comprising the following steps:
based on the identity recognition result of the user, acquiring personal data of the user from a pre-stored database;
based on the personal data, identifying whether the user has abnormal behavior, and adjusting the access control mode in response to the identifying;
wherein said identifying, based on said personal data, whether said user has abnormal behavior comprises:
determining the confidence coefficient of the user behavior abnormality based on the personal data through an abnormal behavior recognition model, and judging whether the user has the abnormal behavior based on the confidence coefficient of the behavior abnormality; the abnormal behavior recognition model is input by recognition data, user traffic records, historical behavior abnormal rates and user operation data, and confidence degrees comprising the behavior abnormalities are output;
Acquiring the personal data of a plurality of users from the pre-stored database in response to the face recognition information of the plurality of users being acquired simultaneously; responding to the authentication failure of at least one user in the plurality of users, and judging that the user has the abnormal behavior; wherein the determining that the user has the abnormal behavior in response to the authentication failure of at least one user of the plurality of users comprises:
processing face images of the plurality of users through a face recognition model, and determining the user identity of at least one user and the recognition confidence coefficient of the identity of the user;
judging that the user has the abnormal behavior in response to the identification confidence coefficient of the identity of the user being smaller than an identity confidence coefficient threshold value;
wherein the identity confidence threshold is related to historical companion data of the plurality of users;
in response to the authentication success, waking up the intelligent lock and establishing connection;
and sending an unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction.
2. The method of claim 1, the method of determining the access control mode comprising:
Determining the execution security level of the access control system based on the time data;
and determining the access control mode based on the execution security level.
3. The method of claim 2, the determining an execution security level of the access control system based on the time data comprising:
acquiring people flow data;
and determining the execution security level based on the people flow data and the time data.
4. The access control system comprises an intelligent control end, a mobile identification end and an intelligent lock, wherein the intelligent control end is in communication connection with the intelligent lock;
the intelligent control terminal is used for:
responding to the permission of the mobile identification terminal, and acquiring identity identification information corresponding to an access control mode through the mobile identification terminal;
based on the identity information, carrying out identity verification on the user; comprising the following steps:
based on the identity recognition result of the user, acquiring personal data of the user from a pre-stored database;
based on the personal data, identifying whether the user has abnormal behavior, and adjusting the access control mode in response to the identifying;
wherein said identifying, based on said personal data, whether said user has abnormal behavior comprises:
Determining the confidence coefficient of the user behavior abnormality based on the personal data through an abnormal behavior recognition model, and judging whether the user has the abnormal behavior based on the confidence coefficient of the behavior abnormality; the abnormal behavior recognition model is input by recognition data, user traffic records, historical behavior abnormal rates and user operation data, and confidence degrees comprising the behavior abnormalities are output;
acquiring the personal data of a plurality of users from the pre-stored database in response to the face recognition information of the plurality of users being acquired simultaneously; responding to the authentication failure of at least one user in the plurality of users, and judging that the user has the abnormal behavior; wherein the determining that the user has the abnormal behavior in response to the authentication failure of at least one user of the plurality of users comprises:
processing face images of the plurality of users through a face recognition model, and determining the user identity of at least one user and the recognition confidence coefficient of the identity of the user;
judging that the user has the abnormal behavior in response to the identification confidence coefficient of the identity of the user being smaller than an identity confidence coefficient threshold value;
Wherein the identity confidence threshold is related to historical companion data of the plurality of users;
in response to the authentication success, waking up the intelligent lock and establishing connection;
and sending an unlocking instruction to the intelligent lock, so that the intelligent lock is unlocked according to the unlocking instruction.
5. The system of claim 4, the intelligent control terminal further configured to:
determining the execution security level of the access control system based on the time data;
and determining the access control mode based on the execution security level.
6. The system of claim 5, the intelligent control terminal further configured to:
acquiring people flow data;
and determining the execution security level based on the people flow data and the time data.
7. An access control device, the device comprising at least one processor and at least one memory;
the at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement the access control method of any one of claims 1 to 3.
8. A computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs the entrance guard control method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310626444.5A CN116665352B (en) | 2023-05-30 | 2023-05-30 | Access control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310626444.5A CN116665352B (en) | 2023-05-30 | 2023-05-30 | Access control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116665352A CN116665352A (en) | 2023-08-29 |
| CN116665352B true CN116665352B (en) | 2024-01-30 |
Family
ID=87713143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310626444.5A Active CN116665352B (en) | 2023-05-30 | 2023-05-30 | Access control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665352B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117118907B (en) * | 2023-10-25 | 2024-02-02 | 深圳市亲邻科技有限公司 | Entrance guard flow dynamic monitoring system and method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568063A (en) * | 2011-12-14 | 2012-07-11 | 深圳市中联创新自控系统有限公司 | Door opening method for door control system, and door control system |
| CN109801408A (en) * | 2018-12-06 | 2019-05-24 | 安徽凯川电力保护设备有限公司 | A kind of access control management method for computer room |
| CN110310406A (en) * | 2019-07-24 | 2019-10-08 | 珠海格力电器股份有限公司 | A kind of method for unlocking and intelligent door lock of intelligent door lock |
| CN110544334A (en) * | 2019-08-22 | 2019-12-06 | 上海晋泷科技有限公司 | data processing method and device for access control management, electronic equipment and storage medium |
| CN110930548A (en) * | 2019-11-14 | 2020-03-27 | 重庆特斯联智慧科技股份有限公司 | Face recognition intelligent security system |
| CN110930574A (en) * | 2019-11-26 | 2020-03-27 | 深圳神目信息技术有限公司 | Access control method and system and intelligent device |
| CN111612950A (en) * | 2020-05-25 | 2020-09-01 | 歌尔科技有限公司 | Intelligent lockset and unlocking authentication method and device thereof |
| CN213182886U (en) * | 2020-10-12 | 2021-05-11 | 佛山市瀚宇科技有限公司 | Alarm system based on entrance guard's equipment |
| CN115311703A (en) * | 2022-04-21 | 2022-11-08 | 亿慧云智能科技（深圳）股份有限公司 | Access control system control method and device based on face recognition and terminal equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7424618B2 (en) * | 2001-03-14 | 2008-09-09 | Paladin Electronic Services, Inc. | Biometric access control and time and attendance network including configurable system-on-chip (CSOC) processors with embedded programmable logic |
-
2023
- 2023-05-30 CN CN202310626444.5A patent/CN116665352B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568063A (en) * | 2011-12-14 | 2012-07-11 | 深圳市中联创新自控系统有限公司 | Door opening method for door control system, and door control system |
| CN109801408A (en) * | 2018-12-06 | 2019-05-24 | 安徽凯川电力保护设备有限公司 | A kind of access control management method for computer room |
| CN110310406A (en) * | 2019-07-24 | 2019-10-08 | 珠海格力电器股份有限公司 | A kind of method for unlocking and intelligent door lock of intelligent door lock |
| CN110544334A (en) * | 2019-08-22 | 2019-12-06 | 上海晋泷科技有限公司 | data processing method and device for access control management, electronic equipment and storage medium |
| CN110930548A (en) * | 2019-11-14 | 2020-03-27 | 重庆特斯联智慧科技股份有限公司 | Face recognition intelligent security system |
| CN110930574A (en) * | 2019-11-26 | 2020-03-27 | 深圳神目信息技术有限公司 | Access control method and system and intelligent device |
| CN111612950A (en) * | 2020-05-25 | 2020-09-01 | 歌尔科技有限公司 | Intelligent lockset and unlocking authentication method and device thereof |
| CN213182886U (en) * | 2020-10-12 | 2021-05-11 | 佛山市瀚宇科技有限公司 | Alarm system based on entrance guard's equipment |
| CN115311703A (en) * | 2022-04-21 | 2022-11-08 | 亿慧云智能科技（深圳）股份有限公司 | Access control system control method and device based on face recognition and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116665352A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104318654B (en) | Building conversational system and method | |
| CN109272613B (en) | Sensor and video linked Internet of things safety electronic access control system | |
| CN116665352B (en) | Access control method and system | |
| KR101814719B1 (en) | System and method for remote controlling digital door-lock using smartphone | |
| CN105405186B (en) | A kind of safeguard management method and device | |
| US20040263315A1 (en) | Information security system interworking with entrance control device and control method thereof | |
| US20120218075A1 (en) | Methods and apparatus to control access | |
| CN109243040B (en) | Access control passing management method, device, equipment and storage medium | |
| CN105427413A (en) | Intelligent unlocking method and intelligent lock | |
| WO2018231703A1 (en) | Securitization of temporal digital communications via authentication and validation for wireless user and access devices | |
| CN109064608A (en) | Intelligent door lock is wireless method for unlocking and device | |
| CN110211267A (en) | Indoor openings control method, the configuration method of permission, device and storage medium | |
| CN106920296A (en) | It is anti-to trail intelligent door system and intelligent door control method | |
| CN109147125A (en) | Intelligent door lock theft preventing method and anti-theft intelligent door lock | |
| CN108537917B (en) | Method for improving success rate of identity recognition, intelligent door lock, entrance machine and server | |
| WO2021164389A1 (en) | Intelligent lock access control system, control method and apparatus, device, and storage medium | |
| CN109291881B (en) | Management method for automobile fingerprint identification | |
| CN106296932A (en) | The control method of vehicle, control device and vehicle | |
| CN107481362A (en) | Access control system and access control method | |
| CN106846583A (en) | A kind of wireless intelligent access control system | |
| CN108242096A (en) | Access control system based on face recognition technology | |
| CN207123882U (en) | A kind of antitheft cloud service door-locking system of multiple intelligent | |
| CN109243014A (en) | Access control system and the double mirror unlocking methods of gate inhibition | |
| KR100894421B1 (en) | Fingerprint authentication terminal, access control system thereof, and user authentication method | |
| CN108389289A (en) | A kind of intelligent door lock, unlocking method and locking method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |