Cooperative processing method and system for visitor unlocking

Abstract

The invention discloses a cooperative processing method and system for visitor unlocking, and the method comprises the steps: detecting that an abnormal visitor inputs wrong passwords for multiple times according to a door lock A, generating an abnormal visitor broadcast message, and obtaining a broadcast notification of the abnormal visitor; according to the abnormal visitor broadcast message received by the door lock B, accumulating the error input times of the lock and the error input times in the broadcast message; according to the fact that a door lock C detects that a normal visitor inputs wrong passwords for multiple times, an abnormal visitor broadcast message is generated, and a misoperation notification of the normal visitor is obtained; according to the abnormal visitor broadcast message received by the door lock A, generating an abnormal visitor exclusion broadcast message, and obtaining an identity confirmation result of a normal visitor; and according to the abnormal visitor exclusion broadcast message received by the door lock C, obtaining a visitor guiding result. By utilizing the embodiment of the invention, the response speed of the intelligent door lock on abnormal condition processing can be improved, and the safety protection capability of a family is further enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent locks, and particularly relates to a collaborative processing method and system for visitor unlocking. Background Art

[0002] With the continuous progress of smart home technology, smart door locks have gradually become an important part of modern residential security systems. Traditional door locks usually rely on physical keys or simple password input, with low security and are easily stolen or cracked. Smart door locks, on the other hand, enhance home security and convenience through biometric technologies (such as fingerprint, face recognition) and remote control. However, in actual use, smart door locks still face many challenges in processing visitor unlocking, especially in the identification of abnormal visitors and the guidance of normal visitors.

[0003] Nowadays, more and more households have installed smart door locks on their entrance doors, which can verify identity and unlock the door through face recognition, passwords, etc. The host can also give temporary unlocking passwords to visitors so that they can freely unlock and enter. However, sometimes visitors may forget and go to the wrong resident's room, or misremember the temporary unlocking password, disturbing other residents and causing trouble to community management. Summary of the Invention

[0004] The purpose of the present invention is to provide a collaborative processing method and system for visitor unlocking to solve the deficiencies in the prior art, improve the response speed of smart door locks in handling abnormal situations, and further enhance the home security prevention ability.

[0005] An embodiment of the present application provides a collaborative processing method for visitor unlocking, the method comprising: Abnormal visitor detection and broadcast notification: According to door lock A detecting that an abnormal visitor has entered the wrong password multiple times and the face feature vector of the visitor has not been matched in the resident registration information list, generating an abnormal visitor broadcast message; wherein, the broadcast message includes the face feature vector of the abnormal visitor and the number of times the wrong password has been entered, and sending it to other door locks through the local area network to obtain a broadcast notification of the abnormal visitor; Abnormal visitor cumulative counting and alarm: According to door lock B receiving the abnormal visitor broadcast message and detecting that the same visitor has entered the wrong password multiple times, adding the number of times the wrong password has been entered on this lock to the number of times the wrong password has been entered in the broadcast message; wherein, if the cumulative number of times reaches the total threshold number of times, sending a suspicious person alarm message to the platform to obtain the cumulative alarm result of the abnormal visitor; Detection and broadcast notification of normal visitor's misoperation: When the door lock C detects that a normal visitor enters the wrong password multiple times and the face feature vector of the visitor cannot be matched in the household registration information list, an abnormal visitor broadcast message is generated. The broadcast message includes the face feature vector of the normal visitor and the number of times the wrong password is entered, and is sent to other door locks through the local area network to obtain the misoperation notification of the normal visitor. Confirmation and exclusion of normal visitor's identity: When the door lock A receives the abnormal visitor broadcast message and matches that the visitor is a registered person of its own, an abnormal visitor exclusion broadcast message is generated. The exclusion message includes the face feature vector of the visitor and the correct door lock address, and is sent to other door locks through the local area network to obtain the identity confirmation result of the normal visitor. Visitor guidance and unlocking: When the door lock C receives the abnormal visitor exclusion broadcast message and detects that the visitor is still in front of the door, a prompt message of "Please visit the correct room" is generated. The prompt message is informed to the visitor by voice or on the screen display to guide them to unlock at the correct door lock, and the visitor guidance result is obtained.

[0006] Optionally, the abnormal visitor detection and broadcast notification includes: Detection of wrong password input: When the door lock A detects that an abnormal visitor enters the wrong password multiple times, the number of times the wrong password is entered is recorded. The detection is implemented through a password comparison algorithm to obtain the record of the number of times the wrong password is entered. Face feature extraction and comparison: Based on the face image of the abnormal visitor collected by the door lock A, the face feature vector is extracted. The extraction uses a deep learning model and is compared with the household registration information list to obtain an unmatched result. Generation and sending of broadcast message: Based on the unmatched result and the record of the number of times the wrong password is entered, an abnormal visitor broadcast message is generated. The broadcast message is sent to other door locks through the local area network to obtain the broadcast notification of the abnormal visitor.

[0007] Optionally, the abnormal visitor cumulative counting and alarm include: Receiving and comparing of broadcast message: When the door lock B receives the abnormal visitor broadcast message, the face feature vector of the abnormal visitor is extracted. The extraction is implemented through a deep learning model and is compared with the face image collected by this lock to obtain a comparison result. Accumulation and judgment of the number of times the wrong password is entered: Based on the comparison result, if it is the same visitor, the number of times the wrong password is entered by this lock is added to the number of times the wrong password is entered in the broadcast message. The accumulation is implemented through a counter to judge whether the total threshold of 6 times is reached to obtain an accumulated result. Generation and sending of alarm message: Based on the accumulated result, if the total threshold is reached, a suspicious person alarm message is generated. The alarm message is sent to the platform through the local area network to obtain the alarm result of the abnormal visitor.

[0008] Optionally, the normal visitor misoperation detection and broadcast notification include: Incorrect password input detection: Detect that a normal visitor inputs an incorrect password multiple times according to door lock C, and record the number of incorrect inputs; wherein, the detection is implemented through a password comparison algorithm to obtain a record of the number of incorrect inputs. Face feature extraction and comparison: Extract a face feature vector according to the face image of a normal visitor collected by door lock C; wherein, the extraction uses a deep learning model and is compared with the list of household registration information to obtain an unmatched result. Broadcast message generation and sending: Generate an abnormal visitor broadcast message according to the unmatched result and the record of the number of incorrect inputs; wherein, the broadcast message is sent to other door locks through a local area network to obtain a misoperation notification for the normal visitor.

[0009] Optionally, the normal visitor identity confirmation and exclusion include: Broadcast message reception and comparison: Extract the face feature vector of the visitor according to the abnormal visitor broadcast message received by door lock A; wherein, the extraction is implemented through a deep learning model and is compared with the list of household registration information of this lock to obtain a matching result. Exclusion message generation and sending: Generate an abnormal visitor exclusion broadcast message according to the matching result. If it is a registered household member, the exclusion message includes the face feature vector of the visitor and the correct door lock address and is sent to other door locks through a local area network to obtain an identity confirmation result for the normal visitor.

[0010] Optionally, the visitor guidance and unlocking include: Exclusion message reception and comparison: Extract the face feature vector of the visitor according to the abnormal visitor exclusion broadcast message received by door lock C; wherein, the extraction is implemented through a deep learning model and is compared with the face image collected by this lock to obtain a comparison result. Prompt message generation and display: Generate a prompt message to please visit the correct room according to the comparison result. If it is the same visitor, the prompt message is displayed by voice or on the screen to obtain a visitor guidance result. Correct door lock unlocking: According to the visitor going to the correct door lock A, input the correct password and pass the face recognition verification; wherein, the verification is implemented through password comparison and face feature comparison to obtain an unlocking result.

[0011] Another embodiment of the present application provides a collaborative processing system for visitor unlocking, and the system includes: Detection module for detecting abnormal visitors and broadcasting notifications: Based on Door Lock A detecting that an abnormal visitor has entered the wrong password multiple times and the face feature vector of the visitor not being matched in the list of registered household information, generate a broadcast message for the abnormal visitor; wherein, the broadcast message includes the face feature vector of the abnormal visitor and the number of times the wrong password has been entered, and is sent to other door locks via the local area network to obtain a broadcast notification of the abnormal visitor; Counting module for accumulating the count of abnormal visitors and giving an alarm: Based on Door Lock B receiving a broadcast message of an abnormal visitor and detecting that the same visitor has entered the wrong password multiple times, add the number of times the wrong password has been entered on this lock to the number of times in the broadcast message; wherein, if the accumulated number of times reaches the total threshold number of times, send a suspicious person alarm message to the platform to obtain the accumulated alarm result of the abnormal visitor; Notification module for detecting misoperations of normal visitors and broadcasting notifications: Based on Door Lock C detecting that a normal visitor has entered the wrong password multiple times and the face feature vector of the visitor not being matched in the list of registered household information, generate a broadcast message for the abnormal visitor; wherein, the broadcast message includes the face feature vector of the normal visitor and the number of times the wrong password has been entered, and is sent to other door locks via the local area network to obtain a misoperation notification of the normal visitor; Confirmation module for confirming the identity of normal visitors and excluding them: Based on Door Lock A receiving a broadcast message of an abnormal visitor and matching the visitor as a registered person of its own, generate a broadcast message for excluding the abnormal visitor; wherein, the exclusion message includes the face feature vector of the visitor and the correct door lock address, and is sent to other door locks via the local area network to obtain the identity confirmation result of the normal visitor; Guiding module for guiding visitors and unlocking: Based on Door Lock C receiving a broadcast message for excluding an abnormal visitor and detecting that the visitor is still in front of the door, generate a prompt message to invite the visitor to visit the correct room; wherein, the prompt message is informed to the visitor by voice or on the screen display to guide the visitor to the correct door lock for unlocking to obtain the visitor guiding result.

[0012] Another embodiment of the present application provides a storage medium, in which a computer program is stored, and wherein the computer program is set to execute the method described in any one of the above when running.

[0013] Another embodiment of the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of the above.

[0014] Compared with the prior art, a collaborative processing method for visitor unlocking provided by the present invention generates an abnormal visitor broadcast message according to the door lock A detecting that an abnormal visitor has entered the wrong password multiple times, and obtains a broadcast notification of the abnormal visitor; according to the door lock B receiving the abnormal visitor broadcast message, accumulates the number of wrong entries of this lock and the number of wrong entries in the broadcast message; according to the door lock C detecting that a normal visitor has entered the wrong password multiple times, generates an abnormal visitor broadcast message, and obtains a misoperation notification of the normal visitor; according to the door lock A receiving the abnormal visitor broadcast message, generates an abnormal visitor exclusion broadcast message, and obtains an identity confirmation result of the normal visitor; according to the door lock C receiving the abnormal visitor exclusion broadcast message, obtains a visitor guidance result, so as to improve the response speed of the intelligent door lock in dealing with abnormal situations and further enhance the home security prevention ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The hardware structure block diagram of a computer terminal for a collaborative processing method for visitor unlocking provided by an embodiment of the present invention; Figure 2 The flow schematic diagram of a collaborative processing method for visitor unlocking provided by an embodiment of the present invention; Figure 3 The structure schematic diagram of a collaborative processing system for visitor unlocking provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be construed as a limitation to the present invention.

[0017] An embodiment of the present invention first provides a collaborative processing method for visitor unlocking, which can be applied to an electronic device, such as a computer terminal, specifically a general computer, etc.

[0018] The following takes running on a computer terminal as an example to describe it in detail. Figure 1 The hardware structure block diagram of a computer terminal for a collaborative processing method for visitor unlocking provided by an embodiment of the present invention. As Figure 1 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory.

[0019] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any collaborative processing method for visitor unlocking.

[0020] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0021] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by a processor, the processor can be made to execute any one of the collaborative processing methods for visitor unlocking.

[0022] This network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 1 The structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0023] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0024] See Figure 2 , an embodiment of the present invention provides a collaborative processing method for visitor unlocking, which may include the following steps: S201, Abnormal visitor detection and broadcast notification: According to door lock A, it is detected that an abnormal visitor has entered the wrong password multiple times and the face feature vector of the visitor is not matched in the list of household registration information, and an abnormal visitor broadcast message is generated; wherein, the broadcast message includes the face feature vector of the abnormal visitor and the number of times the wrong password is entered, and is sent to other door locks through the local area network to obtain a broadcast notification of the abnormal visitor; Specifically, the abnormal visitor detection and broadcast notification includes: Wrong password input detection: According to door lock A, it is detected that an abnormal visitor has entered the wrong password multiple times, and the number of wrong entries is recorded; wherein, the detection is implemented through a password comparison algorithm to obtain a record of the number of wrong entries; Face feature extraction and comparison: According to the face image of the abnormal visitor collected by door lock A, the face feature vector is extracted; wherein, the extraction uses a deep learning model and is compared with the list of household registration information to obtain an unmatched result; Broadcast message generation and sending: Generate an abnormal visitor broadcast message based on the unmatched results and the record of the number of incorrect input attempts; among them, the broadcast message is sent to other door locks through the local area network to obtain a broadcast notification of the abnormal visitor.

[0025] S202, Abnormal visitor cumulative counting and alarm: According to door lock B receiving the abnormal visitor broadcast message and detecting that the same visitor has entered the wrong password multiple times, add the number of incorrect input attempts of this lock to the number of incorrect input attempts in the broadcast message; among them, if the cumulative number reaches the total threshold number of times, send a suspicious person alarm message to the platform to obtain the cumulative alarm result of the abnormal visitor; Specifically, the abnormal visitor cumulative counting and alarm include: Broadcast message reception and comparison: According to door lock B receiving the abnormal visitor broadcast message, extract the face feature vector of the abnormal visitor; among them, the extraction is implemented through a deep learning model and compared with the face image collected by this lock to obtain a comparison result; Accumulation and judgment of the number of incorrect input attempts: According to the comparison result, if it is the same visitor, add the number of incorrect input attempts of this lock to the number of incorrect input attempts in the broadcast message; among them, the accumulation is implemented through a counter, and judge whether it reaches the total threshold of 6 times to obtain the cumulative result; Alarm message generation and sending: According to the cumulative result, if the total threshold is reached, generate a suspicious person alarm message; among them, the alarm message is sent to the platform through the local area network to obtain the alarm result of the abnormal visitor.

[0026] S203, Detection of misoperations by normal visitors and broadcast notification: According to door lock C detecting that a normal visitor has entered the wrong password multiple times and the face feature vector of the visitor is not matched in the list of registered household information, generate an abnormal visitor broadcast message; among them, the broadcast message contains the face feature vector of the normal visitor and the number of incorrect password inputs, and is sent to other door locks through the local area network to obtain a misoperation notification of the normal visitor; Specifically, the detection of misoperations by normal visitors and broadcast notification include: Detection of incorrect password input: According to door lock C detecting that a normal visitor has entered the wrong password multiple times, record the number of incorrect input attempts; among them, the detection is implemented through a password comparison algorithm to obtain the record of the number of incorrect input attempts; Face feature extraction and comparison: According to the face image of the normal visitor collected by door lock C, extract the face feature vector; among them, the extraction uses a deep learning model and is compared with the list of registered household information to obtain an unmatched result; Broadcast message generation and sending: Generate an abnormal visitor broadcast message based on the unmatched result and the record of the number of incorrect input attempts; among them, the broadcast message is sent to other door locks through the local area network to obtain a misoperation notification of the normal visitor.

[0027] S204, normal visitor identity confirmation and exclusion: according to the abnormal visitor broadcast message received by door lock A, the visitor is matched as a registered person of the home, and an abnormal visitor exclusion broadcast message is generated; wherein, the exclusion message includes the visitor's face feature vector and the correct door lock address, and is sent to other door locks through the local area network to obtain the identity confirmation result of the normal visitor; Specifically, the normal visitor identity confirmation and exclusion includes: Broadcast message reception and comparison: Based on the abnormal visitor broadcast message received by door lock A, the visitor's face feature vector is extracted; wherein, the extraction is realized by a deep learning model, and the face feature vector is compared with the registration information list of the residents of this lock to obtain a matching result; Exclusion message generation and sending: Based on the matching results, if the visitor is a registered person, an abnormal visitor exclusion broadcast message is generated; wherein, the exclusion message contains the visitor's facial feature vector and the correct door lock address, and is sent to other door locks via the local area network to obtain the identity confirmation result of the normal visitor.

[0028] S205, visitor guidance and unlocking: based on the abnormal visitor exclusion broadcast message received by door lock C, it is detected that the visitor is still in front of the door, and a prompt message is generated to visit the correct room; wherein, the prompt message is notified to the visitor through voice or screen display, guiding him to unlock the correct door lock, and obtaining the visitor guidance result.

[0029] Specifically, the visitor guidance and unlocking includes: Receiving and comparing exclusion messages: extracting the visitor's facial feature vector based on the abnormal visitor exclusion broadcast message received by the door lock C; wherein the extraction is realized by a deep learning model, and the facial feature vector is compared with the facial image collected by the lock to obtain the comparison result; Prompt information generation and display: Based on the comparison results, if it is the same visitor, a prompt message is generated to visit the correct room; wherein the prompt message is displayed by voice or screen display to obtain the visitor guidance result; Correct door lock unlocking: the visitor goes to the correct door lock A, enters the correct password and passes the face recognition verification; wherein, the verification is achieved by password comparison and face feature comparison to obtain the unlocking result.

[0030] In practical applications, the present invention proposes a multi-lock collaboration method to handle the alarm events of entering the wrong door or entering the wrong password. By informing other door locks of the person who entered the wrong password and counting the cumulative number of wrong passwords to issue an alarm, it is necessary to alert suspicious people who blindly guess the password and avoid false alarms for normal visitors.

[0031] 1. Core idea: All door locks are connected to the network. It is necessary to alarm suspicious personnel who blindly guess passwords and avoid false alarms for normal visitors. When the abnormal visitor A enters the password of door lock A incorrectly multiple times (reaching the threshold of 3 times for this lock), and door lock A does not store the face feature vector of visitor A, then broadcast an abnormality notice to other door locks, including the face feature vector of abnormal visitor A. If the abnormal visitor A then blindly guesses the password of door lock B, and door lock B also does not have the face feature vector of visitor A, then when the failure count reaches the total threshold of 6 times, an alarm is triggered to drive away the abnormal visitor. When the normal visitor B mistakenly arrives at door lock A and enters the password incorrectly, reaching the threshold of 3 times for this lock, and door lock A does not store the face feature vector of visitor B, then broadcast an abnormality notice to other door locks, including the face feature vector of visitor B. If door lock B discovers that visitor B is a member of its own household, then broadcast a repair message to other door locks, including the face feature vector of visitor B. After other door locks receive it, they no longer store the above-mentioned abnormality notice. When visitor B mistakenly goes to door lock C to enter again, door lock C prompts on the lock: Please go to visit room XXX.

[0032] 2. The complete technical implementation process is as follows: (1)Preconditions: Intelligent door locks are installed on the household entrance doors (each door lock has an independent door lock ID, door lock IP address, door lock geographical location, etc.), and are connected to the cloud platform, registered with the platform, and updated periodically. The platform records the door lock list, including the door lock ID, door lock IP address, door lock geographical location, etc. The intelligent door lock records the list of household registration information, including the door lock ID, door lock address (XXX room), personnel category (visitor / owner), name, face image / feature vector, opening password, authorization validity period, authorization start time, etc. The intelligent lock verifies through the visitor's self-set password, face recognition, authorization validity period, etc.

[0033] (2)The owner sets unlocking authorization for the visitor: The owner uses the management authority to operate the intelligent door lock to collect the visitor's face image, enter the visitor's name, the visitor's self-set password (as the exclusive opening password for the visitor), and the authorization validity period (1 day, 1 week, or 1 month, etc.). The door lock binds the visitor's identity by writing to the list of household registration information. The content recorded in the list of household registration information includes the door lock ID, door lock address (XXX room), visitor's name, face image / feature vector, opening password, authorization validity period, authorization start time, etc. The intelligent lock unlocks and opens the door for the visitor after successfully verifying through the visitor's self-set password, face recognition, and authorization validity period.

[0034] Example: Suppose that after the door lock A binds the identity information of visitor a, if a wants to open the door lock A, they need to enter a self-set password in front of the door lock A, and the door lock A will collect a's face and the door lock clock, and then perform three comparison validations: comparing the similarity of the face image / feature vector with the face image / feature vector in the household registration information list, comparing the opening password, and calculating whether the validity period has expired based on the current clock and the authorized start time. If the verification is successful, the door lock will be unlocked and the door will open.

[0035] (3)Processing method for an abnormal visitor blindly guessing the door lock password: If an abnormal visitor enters the wrong opening password multiple times (possibly blindly guessing the door lock password) (reaching the threshold set by the door lock 3 times), the face image feature vector of the abnormal visitor will be broadcast to other door locks. When other door locks recognize that the wrong opening password is entered again multiple times, the number of times the wrong password is entered on this lock will be added to the number of times in the broadcast message. If the threshold is reached, an alarm will be issued immediately.

[0036] 1) Abnormal visitor b (possibly a suspicious person) comes to door lock A and enters the wrong opening password continuously multiple times (reaching the threshold set by the door lock 3 times), and b's face image / feature vector cannot be successfully compared with the household registration information list of A. Then door lock A collects b's face image / feature vector and immediately sends an alarm message of "suspicious person" (the content includes door lock ID (A), face image of abnormal person b, timestamp, etc.) to the host APP and the platform, and sends a message of "abnormal visitor" in a broadcast form to other door locks, the content includes door lock ID (A), door lock address (A), b's face image / feature vector, number of times the wrong password is entered / 3 times, etc. Each door lock receives and stores the broadcast message of "abnormal visitor" from door lock A, and then compares it with the household registration information list of this lock to check whether it is a person of this lock. If it is a person of this lock, it will be processed according to the method in step (4). If it is not a person of this lock, the message will be stored and no reply is required. If b continues to enter the wrong opening password at door lock A (after exceeding the threshold 3 times, such as n times), A will prompt in the form of voice or screen display that "the number of times the password is incorrect is too much, and it has been locked" and will no longer compare the password entered by b. After b leaves door lock A, door lock A stores b's "record of wrong password entries", the content includes b's face image / feature vector and the total number of times the wrong opening password is entered, and sends b's face image / feature vector and the number of times the wrong password is entered in a broadcast form as a message of "abnormal visitor" to other door locks, the content includes door lock ID (A), door lock address (A), b's face image / feature vector, number of times the wrong password is entered / n times, etc. After receiving the alarm message of "suspicious person", the host APP and the platform will handle it according to the pre-plan, which is not the focus of this invention and will not be elaborated.

[0037] For example: If the abnormal visitor b leaves after entering the wrong password 1 or 2 times, the door lock A will not give an alarm or send a message of "abnormal visitor" to other door locks, but the door lock A will record b's face image / feature vector and the total number of times the opening password was entered incorrectly; If the abnormal visitor b leaves after entering the wrong password 3 times, an alarm will be given and a broadcast message of "abnormal visitor" will be sent; If the opening password is entered incorrectly more than 3 times, a prompt of "too many password errors, locked" will be given in the form of voice or screen display from the 4th time onwards, and the password entered by b will no longer be compared until b leaves the door lock A, and then b's face image / feature vector and the total number of times the password was entered incorrectly will be sent to other door locks in the form of a broadcast message of "abnormal visitor".

[0038] 2) When the abnormal visitor b comes to the door lock B again, the door lock B performs face recognition comparison of family members (calculates the similarity with the face image / feature vector in the household registration information list of B). If the comparison shows that it is a family member of B, the door will be unlocked for them. If the face comparison shows that it is not a family member of B and the opening password is entered incorrectly continuously for multiple times (reaching the threshold of 3 times set by the door lock), the door lock B compares the face image / feature vector of b collected by this lock with the face image / feature vector in the broadcast message of "abnormal visitor" sent by the received and cached door lock A to check if the similarity exceeds the threshold (generally, the face similarity threshold is set to 80%). If the comparison fails (it may not be b but someone else), a broadcast message of "abnormal visitor" will be sent according to the method of the door lock A. If the comparison is successful (indicating it is b), the number of password errors (x times) of this lock will be added to the number of password errors (n times) sent by the door lock A (x + n) to check if it exceeds the threshold (generally set to 6 times). If it exceeds the threshold, an alarm message of "suspicious person" will be sent to the platform, including the door lock ID (B), the number of password errors of this lock (x times), the cumulative number of password errors (x + n times), and b's face image, etc.

[0039] If b continues to enter the wrong opening password multiple times at the door lock B (more than the threshold of 3 times set by the door lock, such as k times), according to the method of the door lock A in step 1), from the 4th time onwards, the door lock B will give a prompt of "too many password errors, locked" in the form of voice or screen display and will no longer compare the password entered by b. When b leaves the door lock B, the door lock B stores b's "password error record", which includes b's face image / feature vector and the number of times the opening password was entered incorrectly at this lock. (Note: After exceeding 3 times, no more alarms will be sent to the platform and the owner's APP because an alarm has already been sent at 3 times).

[0040] 3) If b enters the wrong opening password y times (such as 1 or 2 times) at door lock B and then leaves without reaching the threshold of 3 times set by the door lock, door lock B stores the "wrong password record" of b, which includes b's face image / feature vector and the number of times the wrong opening password is entered / y times. At the same time, door lock B sends a broadcast message of "query" to each door lock, including the door lock ID (B), b's face image, etc. After receiving the broadcast message of "query" from B, other door locks (such as door lock A) extract b's face image and calculate the similarity with the face image / feature vector in the "wrong password record" stored in A to see if it meets the threshold (generally, the face similarity threshold is set to 80%). If there is a match, the number of times b entered the wrong opening password in door lock A is extracted and replied to door lock B (the content includes: door lock ID (A), the number of times the wrong password is entered / n times). If there is no match, "no match" is replied. Door lock B accumulates the number of times b entered the wrong opening password according to the replies received from each door lock in the "query" reply message (for example, door lock A replies n times and this lock is y times, assuming the total number of times is m = n + y; if there are multiple replies, continue to accumulate). It judges whether the total number of times m exceeds 6 times. If it exceeds 6 times, an alarm message of "suspicious person" is immediately sent to the APP of the owner of this lock and the platform (including door lock ID (B), the number of times the password of this lock is wrong (y times), the cumulative number of times the password is wrong (m times), b's face image, etc.).

[0041] Note: Since the number of times the wrong opening password is entered in front of a single door lock does not exceed 3 times, only this "wrong password record" is stored. At this time, B does not know whether other door locks have the "wrong password record" of b, so a query needs to be initiated; if the cumulative number of times the password of door lock B is wrong is less than 6 times, since the password is entered wrong multiple times at the second door lock and it is not a person registered by the household, an alarm should also be given; if door lock B receives broadcast messages of "abnormal visitor" from multiple door locks, it will compare them one by one and accumulate the number of times the password is entered wrong to judge whether to give an alarm. For example, A has 2 times, C has 2 times, and B itself has 2 times, then a total of 6 times will trigger an alarm.

[0042] (4) Handling method for normal visitors who go to the wrong room or enter the wrong password: If a normal visitor forgets the room number and goes to the wrong door lock and cannot unlock after entering the password multiple times, this door lock sends the face image feature vector of this normal visitor as a broadcast message of "abnormal visitor" to other door locks. After receiving the broadcast message, the door lock that has registered this visitor finds that it is a person of its own door lock and sends a broadcast message of "abnormal visitor excluded", notifying other door locks that this person is a person of this lock and attaching the address of this lock. After receiving it, other door locks modify the stored "abnormal visitor" to "abnormal visitor excluded". If this visitor appears again at any door lock, the visitor can be informed according to the door lock address in the "abnormal visitor excluded" message, and then the visitor can return to the correct room number to unlock and enter the house.

[0043] Normal visitor a (for the sake of description distinction, a normal visitor is a visitor who has already bound to door lock A) comes to door lock C and enters the wrong door-opening password multiple times (the entered password is not the door-opening password of C, and the number of wrong entries reaches the threshold of 3 times set by the door lock). Moreover, a's face image / feature vector cannot be found in the list of resident registration information of C (at this time, it may be that visitor a has gone to the wrong room). Then, door lock C captures a's face image / feature vector and sends a message of "abnormal visitor" to other door locks in the form of a broadcast. The content includes the door lock ID (C), the door lock address (C), a's face image / feature vector, the number of wrong password entries / 3 times, etc. Each door lock receives and caches the broadcast message of "abnormal visitor" from door lock C.

[0044] After receiving the broadcast message of "abnormal visitor", door lock A conducts a similarity comparison with the face images / feature vectors registered in the list of resident registration information of A (the similarity meets the threshold, and the threshold is generally set at 80%). If there is a match (indicating that a is a person bound to door lock A), then door lock A sends a broadcast message of "abnormal visitor excluded" to all door locks. The content includes a's face image / feature vector, the bound door lock ID (A), the bound door lock address (A), etc.

[0045] Door lock C receives and caches the "abnormal visitor excluded" sent by A. If at this time door lock C recognizes through face comparison that a is still at the door of C, then it broadcasts a prompt message of "Please visit room (door lock address (A))" in the form of voice or screen display. After seeing / hearing "Please visit room (door lock address (A))", a goes to door lock A to unlock and open the door.

[0046] After other door locks (such as door lock D, etc.) receive and store the broadcast message of "abnormal visitor excluded" from door lock A, they delete the broadcast message of "abnormal visitor" from door lock C (because at this time the abnormal visitor a in this message has been excluded as a person of A by door lock A). If a arrives at door lock D at this time and is identified by door lock D as the person a in the "abnormal visitor excluded" message through face comparison, then according to the door lock address (A) of door lock A corresponding to a in the "abnormal visitor excluded", a prompt message of "Please visit room (door lock address (A))" is broadcast in the form of voice or screen display. After seeing / hearing "Please visit room (door lock address (A))", a goes to door lock A to unlock and open the door.

[0047] (5) Method for a normal visitor a to unlock and open the door lock A: If a registered normal visitor forgets the room number and goes to the wrong door lock, according to step (4), a reminder of "Please visit the room at (door lock address (A))" will be obtained and the visitor can then return to the correct door lock. Suppose the normal visitor a returns to the door lock A. At this time, if a enters the correct door opening password, then A will perform three comparison validations: comparing the password and face image collected by the door lock with the face image / feature vector in the household registration information list, comparing the door opening password, and calculating whether the validity period has expired based on the current clock and the authorized start time. If the verification is successful, the door will be unlocked and opened. If any one of the comparison validations fails, the door cannot be unlocked and opened, and the call button on the door lock needs to be used to call the owner to unlock the door. If the authorized validity period has expired, the owner will be reminded to reset according to the method in step (2). If a finds that the door lock A cannot be unlocked and leaves directly, the process ends.

[0048] Through the message notification between smart locks, it can be identified whether the visitor is a normal visitor or an abnormal visitor / suspicious person. If it is a suspicious person, an alarm will be initiated. If a normal visitor forgets the room number and goes to the wrong door lock, the visitor can be prompted to return to the correct room number to unlock the door and enter the house.

[0049] It can be seen that according to the door lock A detecting that an abnormal visitor has entered the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the broadcast notification of the abnormal visitor; according to the door lock B receiving the abnormal visitor broadcast message, the number of wrong entries of this lock is accumulated with the number of wrong entries in the broadcast message; according to the door lock C detecting that a normal visitor has entered the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the misoperation notification of the normal visitor; according to the door lock A receiving the abnormal visitor broadcast message, an abnormal visitor exclusion broadcast message is generated to obtain the identity confirmation result of the normal visitor; according to the door lock C receiving the abnormal visitor exclusion broadcast message, the visitor guidance result is obtained, so that the response speed of the smart door lock in handling abnormal situations can be improved, and the home security prevention ability can be further enhanced.

[0050] Another embodiment of the present invention provides a collaborative processing system for visitor unlocking. Refer to Figure 3 and the system may include: A detection module 301, used for abnormal visitor detection and broadcast notification: According to the door lock A detecting that an abnormal visitor has entered the wrong password multiple times and the face feature vector of the visitor cannot be matched in the household registration information list, an abnormal visitor broadcast message is generated; wherein, the broadcast message includes the face feature vector of the abnormal visitor and the number of wrong passwords entered, and is sent to other door locks through the local area network to obtain the broadcast notification of the abnormal visitor; The counting module 302 is used for abnormal visitor cumulative counting and alarm: According to the abnormal visitor broadcast message received by door lock B, when it detects that the same visitor enters the wrong password multiple times, it accumulates the number of wrong attempts of this lock and the number of wrong attempts in the broadcast message; among them, if the cumulative number reaches the total threshold number, it sends a suspicious person alarm message to the platform to obtain the cumulative alarm result of the abnormal visitor. The notification module 303 is used for normal visitor misoperation detection and broadcast notification: According to door lock C detecting that a normal visitor enters the wrong password multiple times and the face feature vector of this visitor cannot be matched in the list of household registration information, it generates an abnormal visitor broadcast message; among them, the broadcast message includes the face feature vector of the normal visitor and the number of wrong passwords, and is sent to other door locks through the local area network to obtain the misoperation notification of the normal visitor. The confirmation module 304 is used for normal visitor identity confirmation and exclusion: According to door lock A receiving the abnormal visitor broadcast message and matching that this visitor is a registered person of its own, it generates an abnormal visitor exclusion broadcast message; among them, the exclusion message includes the face feature vector of the visitor and the correct door lock address, and is sent to other door locks through the local area network to obtain the identity confirmation result of the normal visitor. The guiding module 305 is used for visitor guidance and unlocking: According to door lock C receiving the abnormal visitor exclusion broadcast message and detecting that this visitor is still in front of the door, it generates a prompt message to invite the visitor to visit the correct room; among them, the prompt message is informed to the visitor by voice or screen display to guide him to the correct door lock for unlocking to obtain the visitor guidance result.

[0051] It can be seen that according to door lock A detecting that an abnormal visitor enters the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the broadcast notification of the abnormal visitor; according to door lock B receiving the abnormal visitor broadcast message, the number of wrong attempts of this lock and the number of wrong attempts in the broadcast message are accumulated; according to door lock C detecting that a normal visitor enters the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the misoperation notification of the normal visitor; according to door lock A receiving the abnormal visitor broadcast message, an abnormal visitor exclusion broadcast message is generated to obtain the identity confirmation result of the normal visitor; according to door lock C receiving the abnormal visitor exclusion broadcast message, the visitor guidance result is obtained, so as to improve the response speed of the intelligent door lock in dealing with abnormal situations and further enhance the home security prevention ability.

[0052] The embodiment of the present invention also provides a storage medium, in which a computer program is stored, and wherein the computer program is set to execute the steps in any one of the above method embodiments when running.

[0053] Specifically, in this embodiment, the above storage medium can be set to store a computer program for executing the following steps: S201, Abnormal Visitor Detection and Broadcast Notification: Based on Door Lock A detecting that an abnormal visitor has entered the wrong password multiple times and the facial feature vector of the visitor not being matched in the list of registered household information, an abnormal visitor broadcast message is generated; wherein, the broadcast message includes the facial feature vector of the abnormal visitor and the number of times the wrong password has been entered, and is sent to other door locks via the local area network to obtain a broadcast notification of the abnormal visitor; S202, Abnormal Visitor Cumulative Counting and Alarm: Based on Door Lock B receiving the abnormal visitor broadcast message and detecting that the same visitor has entered the wrong password multiple times, the number of times the wrong password has been entered on this lock is added to the number of times in the broadcast message; wherein, if the cumulative number of times reaches the total threshold number of times, a suspicious person alarm message is sent to the platform to obtain the cumulative alarm result of the abnormal visitor; S203, Normal Visitor Misoperation Detection and Broadcast Notification: Based on Door Lock C detecting that a normal visitor has entered the wrong password multiple times and the facial feature vector of the visitor not being matched in the list of registered household information, an abnormal visitor broadcast message is generated; wherein, the broadcast message includes the facial feature vector of the normal visitor and the number of times the wrong password has been entered, and is sent to other door locks via the local area network to obtain a misoperation notification of the normal visitor; S204, Normal Visitor Identity Confirmation and Exclusion: Based on Door Lock A receiving the abnormal visitor broadcast message and matching that the visitor is a registered household member, an abnormal visitor exclusion broadcast message is generated; wherein, the exclusion message includes the facial feature vector of the visitor and the correct door lock address, and is sent to other door locks via the local area network to obtain the identity confirmation result of the normal visitor; S205, Visitor Guidance and Unlocking: Based on Door Lock C receiving the abnormal visitor exclusion broadcast message and detecting that the visitor is still in front of the door, a prompt message to visit the correct room is generated; wherein, the prompt message is informed to the visitor by voice or on the screen display to guide them to the correct door lock for unlocking to obtain the visitor guidance result.

[0054] It can be seen that based on Door Lock A detecting that an abnormal visitor has entered the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain a broadcast notification of the abnormal visitor; based on Door Lock B receiving the abnormal visitor broadcast message, the number of times the wrong password has been entered on this lock is added to the number of times in the broadcast message; based on Door Lock C detecting that a normal visitor has entered the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain a misoperation notification of the normal visitor; based on Door Lock A receiving the abnormal visitor broadcast message, an abnormal visitor exclusion broadcast message is generated to obtain the identity confirmation result of the normal visitor; based on Door Lock C receiving the abnormal visitor exclusion broadcast message, the visitor guidance result is obtained, thereby being able to improve the response speed of the intelligent door lock in handling abnormal situations and further enhancing the home security prevention ability.

[0055] An embodiment of the present invention further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0056] Specifically, the above electronic device may further include a transmission device and an input / output device. The transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0057] Specifically, in this embodiment, the above processor may be configured to execute the following steps through a computer program: S201, Abnormal visitor detection and broadcast notification: According to Door Lock A detecting that an abnormal visitor has entered the wrong password multiple times and the face feature vector of the visitor cannot be matched in the household registration information list, generate an abnormal visitor broadcast message; wherein, the broadcast message includes the face feature vector of the abnormal visitor and the number of times the wrong password has been entered, and send it to other door locks through the local area network to obtain a broadcast notification of the abnormal visitor. S202, Abnormal visitor cumulative counting and alarm: According to Door Lock B receiving the abnormal visitor broadcast message and detecting that the same visitor has entered the wrong password multiple times, add the number of times the wrong password has been entered on this lock to the number of times the wrong password has been entered in the broadcast message; wherein, if the cumulative number of times reaches the total threshold number of times, send a suspicious person alarm message to the platform to obtain a cumulative alarm result of the abnormal visitor. S203, Normal visitor misoperation detection and broadcast notification: According to Door Lock C detecting that a normal visitor has entered the wrong password multiple times and the face feature vector of the visitor cannot be matched in the household registration information list, generate an abnormal visitor broadcast message; wherein, the broadcast message includes the face feature vector of the normal visitor and the number of times the wrong password has been entered, and send it to other door locks through the local area network to obtain a misoperation notification of the normal visitor. S204, Normal visitor identity confirmation and exclusion: According to Door Lock A receiving the abnormal visitor broadcast message and matching that the visitor is a registered person of his own family, generate an abnormal visitor exclusion broadcast message; wherein, the exclusion message includes the face feature vector of the visitor and the correct door lock address, and send it to other door locks through the local area network to obtain an identity confirmation result of the normal visitor. S205, Visitor guidance and unlocking: According to Door Lock C receiving the abnormal visitor exclusion broadcast message and detecting that the visitor is still in front of the door, generate a prompt message to invite the visitor to visit the correct room; wherein, the prompt message is informed to the visitor by voice or on the screen display to guide him to the correct door lock to unlock and obtain a visitor guidance result.

[0058] It can be seen that according to the abnormal visitor detected by door lock A who enters the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the broadcast notification of the abnormal visitor; according to door lock B receiving the abnormal visitor broadcast message, the number of wrong entries of this lock is accumulated with the number of wrong entries in the broadcast message; according to the normal visitor detected by door lock C who enters the wrong password multiple times, an abnormal visitor broadcast message is generated to obtain the misoperation notification of the normal visitor; according to door lock A receiving the abnormal visitor broadcast message, an abnormal visitor exclusion broadcast message is generated to obtain the identity confirmation result of the normal visitor; according to door lock C receiving the abnormal visitor exclusion broadcast message, a visitor guidance result is obtained, so as to improve the response speed of the intelligent door lock in dealing with abnormal situations and further enhance the home security prevention ability.

[0059] The structure, features and effects of the present invention have been described in detail based on the embodiments shown in the drawings. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope defined by the drawings. Any changes made according to the concept of the present invention, or modified into equivalent embodiments with equivalent changes, should still be within the protection scope of the present invention when they do not exceed the spirit covered by the description and the drawings.

Claims

1. A collaborative processing method for unlocking by visitors, characterized in that The method includes: Abnormal visitor detection and broadcast notification: Door lock A detects that an abnormal visitor enters the wrong password and fails to match the face feature vector of the visitor, generates an abnormal visitor broadcast message and sends it to other door locks; Abnormal visitor cumulative counting and alarm: Door lock B receives the abnormal visitor broadcast message, detects that the same visitor enters the wrong password, accumulates the number of wrong entries of this lock and the number of wrong entries in the broadcast message. If the accumulated number reaches the total threshold number of times, it sends a suspicious person alarm message to the platform; Normal visitor misoperation detection and broadcast notification: Door lock C detects that a normal visitor enters the wrong password and fails to match the face feature vector of the visitor, generates an abnormal visitor broadcast message and sends it to other door locks; Normal visitor identity confirmation and exclusion: Door lock A receives the abnormal visitor broadcast message, matches that the visitor is a registered person of its own home, generates an abnormal visitor exclusion broadcast message and sends it to other door locks; Visitor guidance and unlocking: When door lock C receives the abnormal visitor exclusion broadcast message and detects the visitor, it generates a prompt message to invite the visitor to visit the correct room.

2. The method according to claim 1, wherein The abnormal visitor detection and broadcast notification includes: Wrong password input detection: According to door lock A detecting that an abnormal visitor enters the wrong password multiple times, record the number of wrong entries; among them, the detection is realized by password comparison to obtain the record of the number of wrong entries; Face feature extraction and comparison: According to the face image of the abnormal visitor collected by door lock A, extract the face feature vector; among them, the extraction uses a deep learning model and is compared with the list of household registration information to obtain an unmatched result; Broadcast message generation and sending: According to the unmatched result and the record of the number of wrong entries, generate an abnormal visitor broadcast message; among them, the broadcast message is sent to other door locks through the local area network to obtain the broadcast notification of the abnormal visitor.

3. The method according to claim 2, characterized in that, The abnormal visitor cumulative counting and alarm includes: Broadcast message reception and comparison: According to door lock B receiving the abnormal visitor broadcast message, extract the face feature vector of the abnormal visitor; among them, the extraction is realized by a deep learning model and is compared with the face image collected by this lock to obtain a comparison result; Accumulation and judgment of the number of wrong entries: According to the comparison result, if it is the same visitor, accumulate the number of wrong entries of this lock and the number of wrong entries in the broadcast message; among them, the accumulation is realized by a counter to judge whether it reaches the total threshold of 6 times to obtain an accumulated result; Alarm message generation and sending: According to the accumulated result, if the total threshold is reached, generate a suspicious person alarm message; among them, the alarm message is sent to the platform through the local area network to obtain the alarm result of the abnormal visitor.

4. The method according to claim 3, wherein The normal visitor misoperation detection and broadcast notification includes: Wrong password input detection: According to door lock C detecting that a normal visitor enters the wrong password multiple times, record the number of wrong entries; among them, the detection is realized by password comparison to obtain the record of the number of wrong entries; Face feature extraction and comparison: According to the face image of the normal visitor collected by door lock C, extract the face feature vector; among them, the extraction uses a deep learning model and is compared with the list of household registration information to obtain an unmatched result; Broadcast message generation and sending: Generate an abnormal visitor broadcast message based on the unmatched result and the wrong input count record; wherein, the broadcast message is sent to other door locks through the local area network to obtain a misoperation notice for normal visitors.

5. The method according to claim 4, characterized in that The confirmation and exclusion of the normal visitor identity include: Broadcast message reception and comparison: According to the abnormal visitor broadcast message received by Door Lock A, extract the face feature vector of the visitor; wherein, the extraction is implemented through a deep learning model and compared with the household registration information list of this lock to obtain a matching result; Exclusion message generation and sending: According to the matching result, if it is a registered person of one's own family, generate an abnormal visitor exclusion broadcast message; wherein, the exclusion message includes the face feature vector of the visitor and the correct door lock address, and is sent to other door locks through the local area network to obtain the identity confirmation result of the normal visitor.

6. The method according to claim 5, wherein The visitor guidance and unlocking include: Exclusion message reception and comparison: According to the abnormal visitor exclusion broadcast message received by Door Lock C, extract the face feature vector of the visitor; wherein, the extraction is implemented through a deep learning model and compared with the face image collected by this lock to obtain a comparison result; Prompt message generation and display: According to the comparison result, if it is the same visitor, generate a prompt message of "Please visit the correct room"; wherein, the prompt message is displayed by voice or screen display to obtain the visitor guidance result; Correct door lock unlocking: According to the visitor going to the correct Door Lock A, enter the correct password and pass the face recognition verification; wherein, the verification is implemented through password comparison and face feature comparison to obtain an unlocking result.

7. A collaborative processing system for visitors to unlock a lock, characterized in that, The system includes: A detection module for abnormal visitor detection and broadcast notification: Door Lock A detects that an abnormal visitor enters the wrong password and does not match the face feature vector of the visitor, generates an abnormal visitor broadcast message and sends it to other door locks; A counting module for abnormal visitor cumulative counting and alarm: Door Lock B receives the abnormal visitor broadcast message, detects that the same visitor enters the wrong password, adds the wrong input count of this lock to the wrong input count in the broadcast message, and if the cumulative count reaches the total threshold count, sends a suspicious person alarm message to the platform; A notification module for normal visitor misoperation detection and broadcast notification: Door Lock C detects that a normal visitor enters the wrong password and does not match the face feature vector of the visitor, generates an abnormal visitor broadcast message and sends it to other door locks; A confirmation module for normal visitor identity confirmation and exclusion: Door Lock A receives the abnormal visitor broadcast message, matches that the visitor is a registered person of one's own family, generates an abnormal visitor exclusion broadcast message and sends it to other door locks; A guidance module for visitor guidance and unlocking: Door Lock C receives the abnormal visitor exclusion broadcast message and detects the visitor, generates a prompt message of "Please visit the correct room".

8. The system according to claim 7, wherein The detection module is specifically used for: Wrong password input detection: According to Door Lock A detecting that an abnormal visitor enters the wrong password multiple times, record the wrong input count; wherein, the detection is implemented through password comparison to obtain the wrong input count record; Face feature extraction and comparison: Extract the face feature vector based on the abnormal visitor face image collected by door lock A; among them, the extraction uses a deep learning model and compares it with the list of household registration information to obtain an unmatched result; Broadcast message generation and sending: Generate an abnormal visitor broadcast message based on the unmatched result and the wrong input times record; among them, the broadcast message is sent to other door locks through the local area network to obtain a broadcast notification of the abnormal visitor.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is set to execute the method described in any one of claims 1-6 when running.

10. An electronic device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is set to run the computer program to execute the method described in any one of claims 1-6.

Images