Intelligent door lock anti-theft management system

Abstract

The invention discloses an anti-theft management system for an intelligent door lock, and belongs to the technical field of intelligent door locks, the anti-theft management system acquires unlocking habits of users with long-term use records in time, performs a round of verification on unlocking personnel according to the unlocking habits, and performs secondary verification on the users with abnormal use time, so that the unlocking habits of the users with the long-term use records in time are obtained. Therefore, the situation that the intelligent door lock is broken through and is difficult to leave any record when the NFC card, the fingerprint, the password and the like are leaked is effectively reduced or even avoided, so that the loss caused by the leakage of the unlocking condition is reduced. In addition, for a password verification mode, the password input habit of the user is collected and analyzed, whether the user belongs to a user with a long-term use record or not is judged, whether secondary verification is needed or not is judged accordingly, and the mode can achieve the effect of hidden verification; the situation that an unlocking thief can open the intelligent door lock at will after obtaining the password, and consequently economic losses and even potential safety hazards are caused is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent door locks, and specifically relates to an intelligent door lock anti-theft management system. Background Art

[0002] With the continuous development of the smart home market and the increasing demand for home security from consumers, the smart door lock market is showing a rapid growth trend. More and more families are choosing to install smart door locks to improve home security. Smart door locks integrate advanced biometric technologies (such as fingerprint, face, finger vein recognition) and traditional unlocking methods (such as passwords, NFC cards, mechanical keys) to provide a variety of unlocking options to meet the needs of different users.

[0003] In the prior art, when an intruder obtains unlocking solutions such as passwords and NFC cards that can be reused by different people, the smart door lock loses its protection value. Therefore, how to reduce the impact of the above situation and further enhance the security and anti-theft capabilities of smart locks is also an urgent need in the industry. In order to solve the above problem, a solution is provided to reduce the losses caused by the loss of repeatable unlocking solutions. The present invention provides and technical solutions. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent door lock anti-theft management system to solve the problem in the prior art that reusable unlocking solutions such as NFC cards, fingerprints and passwords of intelligent door locks can easily cause large economic losses after being stolen.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An intelligent door lock anti-theft management system, comprising: An outdoor camera is used to collect facial image information of the person who performs the unlocking action; An execution unit, used to execute unlocking and locking actions; A verification account database is used to store the designated account corresponding to each facial information and the corresponding relationship between each designated account and the facial information; The administrator terminal is used to receive the facial image information collected and uploaded by the outdoor camera, and upload the administrator's unlocking and locking judgment signal to the door lock host; The door lock host is used to identify whether the verification account of the user who completes the verification action belongs to the designated account of the user with a long-term usage record. If it is a designated account, it is further determined whether it corresponds to the usual usage time. If not, a second verification is performed.

[0006] Furthermore, the method for the door lock host to determine whether to perform secondary verification includes the following steps: The first step is to collect the user's facial image information through the outdoor camera when the user completes the verification action; The second step is to take the unlocking records of the same facial information as a sample group; The unlock record includes the unlock time and the verification account; the verification account includes fingerprint, NFC card number, and password input characteristics; Obtain the verification account corresponding to each facial information and record it as the designated account; The designated account is saved in the verification account library and corresponds to each facial information one by one; The third step is to obtain the customary unlocking time corresponding to each designated account; Step 4: When using the app, after the user completes the verification action, identify the verification account that completed the verification action; When the verification account that completes the verification action in real time corresponds to a designated account in the verification account library, the time ts at which the verification action is currently completed is obtained, and the time difference tc between ts and the habitual unlocking time closest to ts of the corresponding designated account is obtained. When tc is greater than the preset value tcy, a secondary verification is performed. Otherwise, the door lock host sends an unlocking command to the execution unit, and the execution unit executes the unlocking action.

[0007] Furthermore, when a designated account does not have a corresponding customary unlocking time, secondary verification is performed directly after the verification action is completed.

[0008] Furthermore, the method for obtaining a specified account corresponding to a facial information is: For NFC card number and fingerprint: Get the verification account corresponding to the facial information in the sample group within the past T time range starting from the current time, where T is the preset time length; When the usage ratio of one of the verification accounts exceeds the preset ratio coefficient θ%, the verification account is considered to be the designated account corresponding to the facial information.

[0009] Furthermore, the method for obtaining the password input feature is: obtaining the password input record within the past T time range starting from the current time in the sample group; Label the passwords as a1, a2, ..., a n , n is the number of digits contained in the password; For a password input process, the time when a1 is input is taken as time 0, and (a2-a1), (a3-a2), ..., (a n -a n-1 ), and label them as b1, b2, …, b n-1 ; Calculate the mean value bip and standard deviation fi corresponding to each bi in turn, 1≤i≤n-1; For a password input process, the area pressed by the user each time when entering the password is marked as c1, c2, ..., c n ; Calculate the mean value cip and standard deviation qi corresponding to each ci value in turn; Use (bip, fi, cip, qi) as the designated account corresponding to the facial information.

[0010] Furthermore, in the third step, the method for obtaining the customary unlocking time corresponding to each designated account is: For a specified account, obtain the unlocking time of the specified account within the past T time range starting from the current time; A rectangular coordinate system is established with 24 hours of day and night as the horizontal coordinate and the date as the vertical coordinate, and each unlocking time is marked in the rectangular coordinate system; Define a rectangular range with y=0, x=x1, x=x1+x2 and y=d, where d is the number of days covered by the sample, x1 is any value between 0 and 24 hours, and x2 is the preset duration, which can be 40 minutes. When the ratio of the number of days with unlocking moments to d within the rectangular range reaches the maximum value within the range of 20 minutes of x1, and the ratio of the number of days with unlocking moments to d is greater than or equal to the preset proportional coefficient θ1, the coordinate points within the rectangular range are fitted to obtain a vertical line, and the moment corresponding to the vertical line is marked as the habitual unlocking time of the corresponding specified account.

[0011] Furthermore, the secondary verification method is: The user's facial image information is collected through the outdoor camera, and the facial information corresponding to the specified account in the verification account library is compared with the facial information collected by the outdoor camera. When it is determined that they are the same person, the door lock host sends an unlocking command to the execution unit, and the execution unit performs the unlocking action. When it is determined that they are not the same person, the user's facial image information is collected through the outdoor camera and transmitted to the administrator terminal.

[0012] Furthermore, in the fourth step, when the user uses the password to unlock, the method for determining whether there is a designated account corresponding to the currently completed verification action in the verification account library is as follows: when the password is entered to unlock, the password input record is obtained, and firstly, whether the password input is correct is determined, and if correct, the first verification parameter K1 is calculated according to the formula, and the second verification parameter K2 is calculated according to the formula; Where bis is the time interval between two consecutive key presses when entering the password in real time; cis is the key area corresponding to ai when the password is input in real time; Enter the information corresponding to each designated account in turn to calculate several sets of K1 and K2 values; The comprehensive verification parameter K is calculated according to the formula K=λ1*K1+λ2*K2; Where λ1 and λ2 are both preset coefficients, and λ1+λ2=1; The designated account in the verification account database that satisfies the corresponding K≤Ky is used as the designated account corresponding to this unlocking, and Ky is a preset value.

[0013] Beneficial effects of the present invention: 1. The present invention collects and obtains the unlocking habits of users with long-term usage records over time, and uses this to conduct a round of verification on the unlocking personnel, and conducts a second verification on users with abnormal usage time, thereby effectively reducing or even avoiding the situation where the smart door lock is breached and it is difficult to leave any records when the NFC card, fingerprint, password, etc. are leaked, thereby reducing the loss caused by the leakage of unlocking conditions.

[0014] 2. For the password verification method, the present invention collects and analyzes the user's password input habits, specifically, including the time interval between numbers when the user enters the password and the pressing area of ​​the capacitive screen when the user presses each number, and uses this to distinguish different users who enter the same password. In the subsequent judgment process, the user who enters the password in real time is analyzed to determine whether he or she is a user with a long-term usage record, and whether a secondary verification is needed. This method can achieve the effect of hidden verification, preventing thieves from opening the smart door lock at will after obtaining the password, resulting in economic losses or even safety hazards.

[0015] 3. Compared with the prior art method of directly establishing two or more verification schemes to improve the verification effect, the present invention, on the one hand, greatly shortens the verification process and improves the verification efficiency without affecting daily use; on the other hand, when verifying the password, the subsequent verification of the present invention is confidential, which makes it difficult for theft attackers to grasp the rules and the theft behavior is easier to be discovered. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a schematic diagram of the framework structure of an intelligent door lock anti-theft management system; Figure 2 A flowchart of a method for a door lock host to determine whether secondary verification is required. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1 An intelligent door lock anti-theft management system, such as Figure 1 As shown: An outdoor camera is used to collect facial image information of the person who performs the unlocking action; A power supply, used to supply power to other units; An execution unit, used to execute unlocking and locking actions; A verification account database is used to store the designated account corresponding to each facial information and the corresponding relationship between each designated account and the facial information; The administrator terminal has the highest unlocking authority and is used to receive facial image information collected and uploaded by the outdoor camera, and upload the administrator's unlocking and locking judgment signal to the door lock host; The door lock host is used to identify whether the verification account of the user who completes the verification action belongs to the designated account of the user with a long-term usage record. If it is a designated account, it is further determined whether it corresponds to the usual usage time. If not, a second verification is performed.

[0020] Embodiment 2 The method for the door lock host to determine whether secondary verification is required includes the following steps: The first step is to collect the user's facial image information through the outdoor camera when the user completes the verification action; The verification action includes fingerprint recognition, password recognition, NFC card recognition and other unlocking actions that can be reused by different people after leakage; The second step is to take the unlocking records of the same facial information as a sample group; The unlocking record includes the unlocking time and the verification account; The verification account includes fingerprint, NFC card number, password input characteristics, etc.; Analyze and process a sample group, obtain the verification account corresponding to the facial information corresponding to the sample group, and mark the verification account corresponding to the facial information as the designated account of the facial information; The designated account corresponding to each facial information is saved in the verification account library, and corresponds to each facial information one by one; Specifically, the method for obtaining a specified account corresponding to a facial information is: For unique verification accounts such as NFC card numbers and fingerprints: Get the verification account corresponding to the facial information in the sample group within the past T time range starting from the current time, where T is the preset time length; When the usage ratio of one of the verification accounts exceeds the preset ratio coefficient θ%, the verification account is considered to be the designated account corresponding to the facial information; The third step is to obtain the customary unlocking time corresponding to each designated account; For a specified account, obtain the unlocking time of the specified account within the past T time range starting from the current time; A rectangular coordinate system is established with 24 hours of day and night as the horizontal coordinate and the date as the vertical coordinate, and each unlocking time is marked in the rectangular coordinate system; Define a rectangular range with y=0, x=x1, x=x1+x2 and y=d, where d is the number of days covered by the sample, x1 is any value between 0 and 24 hours, and x2 is the preset duration, which can be 40 minutes. Furthermore, since the activity time is greatly affected by weekdays and holidays, when setting the sample group, weekdays and holidays can be processed separately. When the ratio of the number of days with unlocking moments to d in the rectangular range reaches the maximum value within the range of 20 minutes of x1, and the ratio of the number of days with unlocking moments to d is greater than or equal to the preset proportional coefficient θ1, the coordinate points in the rectangular range are fitted to obtain a vertical line, and the time corresponding to the vertical line is marked as the customary unlocking time of the corresponding specified account; On the contrary, when the ratio of the number of days with unlocking moments to d reaches the maximum value within the range of 20min of x1, and the ratio of the number of days with unlocking moments to d is less than the preset proportional coefficient θ1, no fitting is performed; Obtain the customary unlocking time corresponding to each designated account in turn. It should be noted that a designated account may correspond to two or more customary unlocking times; Step 4: When using the app, after the user completes the verification action, identify the verification account that completed the verification action; When the verification account that completes the verification action in real time does not correspond to any specified account in the verification account database, the user's facial image information is collected through the outdoor camera and transmitted to the administrator terminal for further judgment by the administrator; When the verification account that completes the verification action in real time corresponds to a specified account in the verification account library, the time ts at which the verification action is currently completed is obtained, and the time difference tc between ts and the customary unlocking time closest to ts of the corresponding specified account is obtained. When tc is greater than the preset value tcy, a secondary verification is performed. Otherwise, the door lock host sends an unlocking instruction to the execution unit, and the execution unit executes the unlocking action; The setting of tcy is related to x2, and tcy can be preferably 1.5*x2; For designated accounts that do not have a custom unlocking time, secondary verification is performed directly.

[0021] The secondary verification method is: The user's facial image information is collected through the outdoor camera, and the facial information corresponding to the specified account in the verification account library is compared with the facial information collected by the outdoor camera. When it is determined that they are the same person, the door lock host sends an unlocking command to the execution unit, and the execution unit executes the unlocking action. When it is determined that they are not the same person, the user's facial image information is collected through the outdoor camera and transmitted to the administrator terminal for further judgment by the administrator.

[0022] Embodiment 3 For authentication accounts that are not unique, such as passwords: The method to obtain its password input characteristics is: Obtain the password input records in the sample group within the past T time range starting from the current time; Label the passwords as a1, a2, ..., a n , where n is the number of digits contained in the password; For a password input process, the time when a1 is input is taken as time 0, and (a2-a1), (a3-a2), ..., (a n -a n-1 ), and label them as b1, b2, …, b n-1 ; Get the average value b1p and standard deviation f1 of the corresponding m b1 values, where m is the number of times the password has been entered within the past T time period; Then calculate the mean value bip and standard deviation fi corresponding to bi in turn, 1≤i≤n-1; Obtain the password input records in the sample group within the past T time range starting from the current time; For a password input process, the area pressed by the user each time when entering the password is marked as c1, c2, ..., c n ; Calculate and obtain the average value c1p and standard deviation q1 of the corresponding m c1 values; Then calculate the mean value cip and standard deviation qi corresponding to the ci value in turn; Use (bip, fi, cip, qi) as the designated account corresponding to the facial information.

[0023] In the fourth step, when the user uses the password to unlock, when entering the password to unlock, the password input record is obtained, and firstly, it is determined whether the password input is correct. If it is correct, the first verification parameter K1 is calculated according to the formula, and the second verification parameter K2 is calculated according to the formula; Where bis is the time interval between two consecutive key presses when entering the password in real time; cis is the key area corresponding to ai when the password is input in real time; Enter the information corresponding to each designated account in turn to calculate multiple sets of K1 and K2 values ​​(corresponding to the number of designated accounts in the verification account library that use passwords as verification); The comprehensive verification parameter K is calculated according to the formula K=λ1*K1+λ2*K2; Where λ1 and λ2 are both preset coefficients, and λ1+λ2=1; The designated account in the verification account library that satisfies the corresponding K≤Ky is used as the designated account corresponding to this unlocking, so as to determine whether there is a designated account corresponding to the currently completed verification action in the verification account library, where Ky is a preset value.

[0024] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

Claims

1. An intelligent door lock anti-theft management system, characterized in that: include: An outdoor camera is used to collect facial image information of the person who performs the unlocking action; An execution unit, used to execute unlocking and locking actions; A verification account database is used to store the designated account corresponding to each facial information and the corresponding relationship between each designated account and the facial information; The administrator terminal is used to receive the facial image information collected and uploaded by the outdoor camera, and upload the administrator's unlocking and locking judgment signal to the door lock host; The door lock host is used to identify whether the verification account of the user who completes the verification action belongs to the designated account of the user with a long-term usage record. If it is a designated account, it is further determined whether it corresponds to the usual usage time. If not, a second verification is performed.

2. The intelligent door lock anti-theft management system according to claim 1 is characterized in that: The method for the door lock host to determine whether to perform secondary verification includes the following steps: The first step is to collect the user's facial image information through the outdoor camera when the user completes the verification action; The second step is to take the unlocking records of the same facial information as a sample group; The unlock record includes the unlock time and the verification account; the verification account includes fingerprint, NFC card number, and password input characteristics; Obtain the verification account corresponding to each facial information and record it as the designated account; The designated account is saved in the verification account library and corresponds to each facial information one by one; The third step is to obtain the customary unlocking time corresponding to each designated account; Step 4: When using the app, after the user completes the verification action, identify the verification account that completed the verification action; When the verification account that completes the verification action in real time corresponds to a designated account in the verification account library, the time ts at which the verification action is currently completed is obtained, and the time difference tc between ts and the habitual unlocking time closest to ts of the corresponding designated account is obtained. When tc is greater than the preset value tcy, a secondary verification is performed. Otherwise, the door lock host sends an unlocking command to the execution unit, and the execution unit executes the unlocking action.

3. The intelligent door lock anti-theft management system according to claim 2 is characterized in that: When a designated account does not have a corresponding customary unlocking time, secondary verification is performed directly after completing the verification action.

4. The intelligent door lock anti-theft management system according to claim 2 is characterized in that: The method to obtain the specified account corresponding to a facial information is: For NFC card number and fingerprint: Get the verification account corresponding to the facial information in the sample group within the past T time range starting from the current time, where T is the preset time length; When the usage ratio of one of the verification accounts exceeds the preset ratio coefficient θ%, the verification account is considered to be the designated account corresponding to the facial information.

5. The intelligent door lock anti-theft management system according to claim 2 is characterized in that: The method for obtaining the password input feature is as follows: obtaining the password input record within the past T time range starting from the current time in the sample group; Label the passwords as a1, a2, ..., a n , n is the number of digits contained in the password; For a password input process, the time when a1 is input is taken as time 0, and (a2-a1), (a3-a2), ..., (a n -a n-1 ), and label them as b1, b2, …, b n-1 ; Calculate the mean value bip and standard deviation fi corresponding to each bi in turn, 1≤i≤n-1; For a password input process, the area pressed by the user each time when entering the password is marked as c1, c2, ..., c n ; Calculate the mean value cip and standard deviation qi corresponding to each ci value in turn; Use (bip, fi, cip, qi) as the designated account corresponding to the facial information.

6. The intelligent door lock anti-theft management system according to claim 5 is characterized in that: In the fourth step, when the user uses the password to unlock, the method for determining whether there is a designated account corresponding to the currently completed verification action in the verification account library is as follows: when the password is entered to unlock, the password input record is obtained, and firstly, whether the password input is correct is determined. If correct, the first verification parameter K1 is calculated according to the formula, and the second verification parameter K2 is calculated according to the formula; Where bis is the time interval between two consecutive key presses when entering the password in real time; cis is the key area corresponding to ai when the password is input in real time; Enter the information corresponding to each designated account in turn to calculate several sets of K1 and K2 values; The comprehensive verification parameter K is calculated according to the formula K=λ1*K1+λ2*K2; Where λ1 and λ2 are both preset coefficients, and λ1+λ2=1; The designated account in the verification account database that satisfies the corresponding K≤Ky is used as the designated account corresponding to this unlocking, and Ky is a preset value.

7. The intelligent door lock anti-theft management system according to claim 2 is characterized in that: The method for obtaining the customary unlocking time corresponding to each specified account in the third step is: For a specified account, obtain the unlocking time of the specified account within the past T time range starting from the current time; A rectangular coordinate system is established with 24 hours of day and night as the horizontal coordinate and the date as the vertical coordinate, and each unlocking time is marked in the rectangular coordinate system; Define a rectangular range with y=0, x=x1, x=x1+x2 and y=d, where d is the number of days covered by the sample, x1 is any value between 0 and 24 hours, and x2 is the preset duration, which can be 40 minutes. When the ratio of the number of days with unlocking moments to d within the rectangular range reaches the maximum value within the range of 20 minutes of x1, and the ratio of the number of days with unlocking moments to d is greater than or equal to the preset proportional coefficient θ1, the coordinate points within the rectangular range are fitted to obtain a vertical line, and the moment corresponding to the vertical line is marked as the habitual unlocking time of the corresponding specified account.

8. The intelligent door lock anti-theft management system according to claim 2 is characterized in that: The secondary verification method is: The user's facial image information is collected through the outdoor camera, and the facial information corresponding to the specified account in the verification account library is compared with the facial information collected by the outdoor camera. When it is determined that they are the same person, the door lock host sends an unlocking command to the execution unit, and the execution unit performs the unlocking action. When it is determined that they are not the same person, the user's facial image information is collected through the outdoor camera and transmitted to the administrator terminal.

Images