Method and system for automatically updating child face data in intelligent door lock
By automatically updating children's face data in smart door locks, the recognition problems caused by changes in children's facial features are solved, the recognition accuracy and security are improved, and the management burden is reduced.
Patent Information
- Application Number
- CN202411185840.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
AI Technical Summary
The existing smart door lock system cannot automatically update face data when the facial features of children's users change greatly, resulting in frequent manual updates of users, which increases management burden and security risks.
By automatically updating children's face data in smart door locks, using facial recognition cameras to capture the face images of children's users and perform similarity calculations. When the similarity calculation results show a downward trend, the registered face images are updated to ensure that The system always uses the latest face data.
It improves the accuracy of the identification of smart door locks for children, enhances the security and convenience of the system, and reduces the management burden of parents and administrators.
Smart Images

Figure CN119068582A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart door locks, and in particular to a method and system for automatically updating children's facial data in a smart door lock, a smart door lock, and a computer-readable storage medium. Background Art
[0002] With the development of smart home technology, smart door locks have gradually become an important part of home security. However, existing smart door lock systems are insufficient in terms of the user experience of child users. Since children's facial features change greatly over time, existing smart door lock systems face challenges in identifying child users. Existing solutions usually require manual updating of children's facial data, which is not only troublesome but may also affect the convenience and security of smart door locks.
[0003] In other words, the existing smart door lock system has the following problems in terms of the user experience of child users: facial data needs to be updated frequently and manually, which increases the user's management burden; children may face situations where they cannot be recognized during their growth, affecting the security of the system; system security may be reduced due to untimely data updates, increasing security risks.
[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention
[0005] The main purpose of the present invention is to provide a method, system, smart door lock and computer-readable storage medium for automatically updating children's facial data in a smart door lock, aiming to solve the problem in the prior art that smart door locks cannot automatically update children's facial data when children's facial features change significantly.
[0006] To achieve the above object, the present invention provides a method for automatically updating child face data in a smart door lock, and the method for automatically updating child face data in a smart door lock comprises the following steps:
[0007] When a child user is detected triggering the smart door lock to perform face recognition, a face image of the child user is captured;
[0008] Acquire a registered child face image of the child user in the smart door lock, and perform similarity calculation between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result;
[0009] Record multiple similarity calculation results of the child user within a preset time period, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, update the registered child face image to the face image of the child user when the face recognition was performed most recently.
[0010] Optionally, the method for automatically updating child facial data in the smart door lock, wherein when a child user is detected to trigger the smart door lock to perform facial recognition, capturing the facial image of the child user specifically includes:
[0011] When a child user is detected triggering the smart door lock to perform face recognition, the smart door lock activates the facial recognition camera;
[0012] The facial recognition camera captures a clear and complete facial image of the child user in real time within the camera's field of view.
[0013] Optionally, the method for automatically updating child facial data in the smart door lock, wherein when a child user is detected to trigger the smart door lock to perform facial recognition, a facial image of the child user is captured, and then the method further includes:
[0014] The face image of the child user is preprocessed, and the preprocessing includes size normalization and grayscale conversion.
[0015] Optionally, the method for automatically updating child facial data in the smart door lock, wherein the step of obtaining a registered child facial image of the child user in the smart door lock, and performing similarity calculation between the currently captured facial image of the child user and the registered child facial image to obtain a similarity calculation result, specifically includes:
[0016] Obtaining a registered child face image of the child user in the smart door lock, and obtaining a feature vector of the registered child face image stored in a database of the smart door lock;
[0017] Extracting feature points of the currently captured facial image of the child user using image processing technology, and converting the feature points into feature vectors that can be used for identification;
[0018] A cosine similarity calculation is performed between the feature vector of the face image of the child user and the feature vector of the registered child face image to obtain a cosine similarity calculation result.
[0019] Optionally, in the method for automatically updating child facial data in the smart door lock, the feature points include the positions of eyes, nose and mouth.
[0020] Optionally, the method for automatically updating child face data in the smart door lock, wherein the recording of multiple similarity calculation results of the child user within a preset time period, when the number of similarity calculation results showing a downward trend exceeds a preset threshold, updating the registered child face image to the face image of the child user when the face recognition is performed the most recently, specifically includes:
[0021] Recording multiple cosine similarity calculation results of the child user within a preset time period, determining whether the cosine similarity calculation results show a downward trend, and counting the number of the cosine similarity calculation results showing a downward trend;
[0022] When the number of cosine similarity calculation results showing a downward trend exceeds a preset threshold, an update mechanism is triggered to update the registered child face image to the face image of the child user when the face recognition was performed most recently, and the updated registered child face image is stored in the database.
[0023] Optionally, the method for automatically updating child facial data in a smart door lock, wherein the method for automatically updating child facial data in a smart door lock further comprises:
[0024] When the registered child face image of the child user needs to be updated, a user interface is provided on the smart door lock or the application of the associated mobile terminal, and an update status is displayed on the user interface, wherein the update status includes a similarity calculation result and a data update progress;
[0025] A manual intervention option is provided on the user interface, so that the user can manually start the data update process, or manually enter a password or use other unlocking methods.
[0026] In addition, to achieve the above-mentioned purpose, the present invention also provides a system for automatically updating child face data in a smart door lock, wherein the system for automatically updating child face data in a smart door lock comprises:
[0027] A data acquisition module, used to capture a facial image of a child user when it is detected that a child user triggers the smart door lock to perform facial recognition;
[0028] a similarity calculation module, used for obtaining a registered child face image of the child user in the smart door lock, performing a similarity calculation between the currently captured face image of the child user and the registered child face image, and obtaining a similarity calculation result;
[0029] The data update module is used to record multiple similarity calculation results of the child user within a preset time period. When the number of similarity calculation results showing a downward trend exceeds a preset threshold, the registered child face image is updated to the face image of the child user when the face recognition is performed for the most recent time.
[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a smart door lock, wherein the smart door lock includes: a memory, a processor, and an automatic update program for children's facial data in the smart door lock stored in the memory and run on the processor, and when the automatic update program for children's facial data in the smart door lock is executed by the processor, the steps of the automatic update method for children's facial data in the smart door lock as described above are implemented.
[0031] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an automatic update program for children's facial data in a smart door lock, and when the automatic update program for children's facial data in a smart door lock is executed by a processor, the steps of the automatic update method for children's facial data in a smart door lock as described above are implemented.
[0032] In the present invention, when a child user is detected to trigger the smart door lock to perform face recognition, the face image of the child user is captured; the registered child face image of the child user in the smart door lock is obtained, and the similarity calculation is performed between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result; multiple similarity calculation results of the child user within a preset time period are recorded, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, the registered child face image is updated to the face image of the child user when the face recognition is performed the most recently. The present invention automatically and timely updates the face image of the child user for unlocking, improves the recognition accuracy of the smart door lock for child users, enhances the security and convenience of the system, and reduces the management burden of parents and administrators. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 It is a flow chart of a preferred embodiment of the method for automatically updating children's face data in the smart door lock of the present invention;
[0034] Figure 2 It is a structural diagram of a preferred embodiment of the automatic updating system of children's face data in the smart door lock of the present invention;
[0035] Figure 3 This is a structural diagram of a preferred embodiment of the smart door lock of the present invention. DETAILED DESCRIPTION
[0036] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0037] The method for automatically updating the face data of children in the smart door lock according to the preferred embodiment of the present invention is as follows: Figure 1As shown, the method for automatically updating the child face data in the smart door lock includes the following steps:
[0038] Step S10: When a child user is detected triggering the smart door lock to perform face recognition, a face image of the child user is captured.
[0039] Specifically, when a child user is detected triggering the smart door lock to perform face recognition, the smart door lock activates the face recognition camera; the face recognition camera captures a clear and complete face image of the child user in real time within the camera's field of view (preprocessing the face image of the child user, including size normalization and grayscale conversion). The face recognition camera captures the face image of the child user in real time, ensuring that the image is clear and complete, and keeping the facial features within the camera's field of view.
[0040] Step S20: obtaining a registered child face image of the child user in the smart door lock, performing a similarity calculation between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result.
[0041] Specifically, a registered child facial image of the child user in the smart door lock is obtained, and a feature vector of the registered child facial image stored in a database of the smart door lock is obtained; feature points of the currently captured facial image of the child user are extracted using image processing technology, and the feature points are converted into a feature vector that can be used for identification; cosine similarity calculation is performed between the feature vector of the facial image of the child user and the feature vector of the registered child facial image to obtain a cosine similarity calculation result.
[0042] First, the registered child face images of child users need to be stored in the database of the smart door lock. User registered face image acquisition: The user stands in front of the smart door lock and uses the built-in camera to collect multiple face images. These images need to be collected under different light and angles to ensure accuracy. Image processing: Process the collected face images and extract feature points, such as the location of the eyes, nose, and mouth. Feature modeling: Convert the extracted feature points into feature vectors that can be used for identification and store them in the database of the smart door lock. The acquisition and storage process of registered child face images is also the above steps.
[0043] Then, image processing technology is used to calculate the similarity between the current face image (i.e., the face image of the child user currently captured) and the registered child face image. Advanced image recognition technology, such as deep learning algorithms, is used to extract features and compare the face image of the child user. The similarity calculation result can be expressed as a percentage or score to intuitively reflect the degree of similarity between the two.
[0044] In face recognition systems, similarity calculations are usually based on the distance or match between feature vectors. The most commonly used distance metric is cosine similarity (cosine similarity measures the degree of similarity between two vectors in direction).
[0045] Step S30, recording multiple similarity calculation results of the child user within a preset time period, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, updating the registered child face image to the face image of the child user when the face recognition was performed most recently.
[0046] Specifically, multiple cosine similarity calculation results of the child user within a preset time period are recorded, it is determined whether the cosine similarity calculation results show a downward trend, and the number of cosine similarity calculation results showing a downward trend is counted; when the number of cosine similarity calculation results showing a downward trend exceeds a preset threshold, an update mechanism is triggered to update the registered child facial image to the facial image of the child user when the most recent facial recognition was performed, and the updated registered child facial image is stored in a database.
[0047] The similarity between the child user and the registered child face image each time the child user opens the door within a period of time is recorded. If the similarity exceeds a certain threshold number of times in the recent period and shows a downward trend, the registered child face image is updated.
[0048] Furthermore, when it is necessary to update the registered child facial image of a child user, a user interface is provided on the smart door lock or the application of the associated mobile terminal, and the update status is displayed on the user interface, and the update status includes the similarity calculation result and the data update progress; a manual intervention option is provided on the user interface so that the user can manually start the data update process, or manually enter the password or use other unlocking methods when necessary. After the child facial image update operation is started or completed, the parent user is notified through the application to inform the update status. Because the facial image of an adult usually does not change significantly, and the facial features of a child may change with age, timely notification can avoid user confusion about system operation and enhance the user's sense of security.
[0049] For example, in a family scenario, if there is a 10-year-old child in the family, the smart door lock system automatically updates the face recognition database by regularly monitoring the changes in the child's facial features. When the child grows up and his facial features change, the system can accurately identify the child and ensure the child's safe entry and exit.
[0050] For example, a school use scenario: The school has installed a smart door lock system that can automatically update students' facial data. As students grow up and their facial features change, the system can accurately identify the students and ensure their safe entry and exit on campus.
[0051] Beneficial effects of the present invention:
[0052] (1) Timely update of child user's facial image improves the recognition accuracy of child users by smart door locks.
[0053] (2) Monitor changes in children's facial features in real time and update the child user's facial image in a timely manner, reducing the possibility of unrecognition due to facial changes.
[0054] (3) Enhanced the security and convenience of the system.
[0055] (4) Reduce the management burden on parents and administrators.
[0056] Furthermore, if Figure 2 As shown, based on the above-mentioned method for automatically updating the facial data of children in a smart door lock, the present invention also provides a system for automatically updating the facial data of children in a smart door lock, wherein the system for automatically updating the facial data of children in a smart door lock comprises:
[0057] The data acquisition module 51 is used to capture the facial image of the child user when it is detected that the child user triggers the smart door lock to perform facial recognition;
[0058] A similarity calculation module 52 is used to obtain a registered child face image of the child user in the smart door lock, and perform similarity calculation between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result;
[0059] The data update module 53 is used to record multiple similarity calculation results of the child user within a preset time period. When the number of similarity calculation results showing a downward trend exceeds a preset threshold, the registered child face image is updated to the face image of the child user when the face recognition is performed for the most recent time.
[0060] Furthermore, if Figure 3 As shown, based on the above-mentioned method and system for automatically updating child facial data in the smart door lock, the present invention also provides a smart door lock accordingly, and the smart door lock includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the smart door lock are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.
[0061] In some embodiments, the memory 20 may be an internal storage unit of the smart door lock, such as a hard disk or memory of the smart door lock. In other embodiments, the memory 20 may also be an external storage device of the smart door lock, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the smart door lock. Further, the memory 20 may also include both an internal storage unit of the smart door lock and an external storage device. The memory 20 is used to store application software and various types of data installed in the smart door lock, such as the program code for installing the smart door lock. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores an automatic update program 40 for children's face data in a smart door lock, and the automatic update program 40 for children's face data in the smart door lock can be executed by the processor 10, thereby realizing the automatic update method for children's face data in a smart door lock in the present application.
[0062] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing a method for automatically updating child facial data in the smart door lock.
[0063] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the smart door lock and to display a visual user interface. The components 10-30 of the smart door lock communicate with each other via a system bus.
[0064] In one embodiment, when the processor 10 executes the automatic update program 40 of the child face data in the smart door lock in the memory 20, the following steps are implemented:
[0065] When a child user is detected triggering the smart door lock to perform face recognition, a face image of the child user is captured;
[0066] Obtaining a registered child face image of the child user in the smart door lock, performing similarity calculation between the currently captured face image of the child user and the registered child face image, and obtaining a similarity calculation result;
[0067] Record multiple similarity calculation results of the child user within a preset time period, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, update the registered child face image to the face image of the child user when the face recognition was performed most recently.
[0068] When a child user is detected to trigger the smart door lock to perform face recognition, capturing a face image of the child user specifically includes:
[0069] When a child user is detected triggering the smart door lock to perform face recognition, the smart door lock activates the facial recognition camera;
[0070] The facial recognition camera captures a clear and complete facial image of the child user in real time within the camera's field of view.
[0071] When a child user is detected to trigger the smart door lock to perform face recognition, a face image of the child user is captured, and then the method further includes:
[0072] The face image of the child user is preprocessed, and the preprocessing includes size normalization and grayscale conversion.
[0073] The step of obtaining the registered child face image of the child user in the smart door lock, and performing similarity calculation between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result specifically includes:
[0074] Obtaining a registered child face image of the child user in the smart door lock, and obtaining a feature vector of the registered child face image stored in a database of the smart door lock;
[0075] Extracting feature points of the currently captured facial image of the child user using image processing technology, and converting the feature points into feature vectors that can be used for identification;
[0076] A cosine similarity calculation is performed between the feature vector of the face image of the child user and the feature vector of the registered child face image to obtain a cosine similarity calculation result.
[0077] The feature points include the positions of eyes, nose and mouth.
[0078] The recording of multiple similarity calculation results of the child user within a preset time period, when the number of similarity calculation results showing a downward trend exceeds a preset threshold, updating the registered child face image to the face image of the child user when the face recognition was performed the most recently, specifically includes:
[0079] Recording multiple cosine similarity calculation results of the child user within a preset time period, determining whether the cosine similarity calculation results show a downward trend, and counting the number of the cosine similarity calculation results showing a downward trend;
[0080] When the number of cosine similarity calculation results showing a downward trend exceeds a preset threshold, an update mechanism is triggered to update the registered child face image to the face image of the child user when the face recognition was performed most recently, and the updated registered child face image is stored in the database.
[0081] Among them, the method for automatically updating the child face data in the smart door lock also includes:
[0082] When the registered child face image of the child user needs to be updated, a user interface is provided on the smart door lock or the application of the associated mobile terminal, and an update status is displayed on the user interface, wherein the update status includes a similarity calculation result and a data update progress;
[0083] A manual intervention option is provided on the user interface, so that the user can manually start the data update process, or manually enter a password or use other unlocking methods.
[0084] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an automatic update program for children's facial data in a smart door lock, and when the automatic update program for children's facial data in a smart door lock is executed by a processor, the steps of the automatic update method for children's facial data in a smart door lock as described above are implemented.
[0085] In summary, the present invention provides a method, system, smart door lock and computer-readable storage medium for automatically updating children's facial data in a smart door lock, the method comprising: when a child user is detected to trigger the smart door lock for facial recognition, capturing the facial image of the child user; obtaining the registered child facial image of the child user in the smart door lock, performing similarity calculation between the currently captured facial image of the child user and the registered child facial image to obtain a similarity calculation result; recording multiple similarity calculation results of the child user within a preset time period, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, updating the registered child facial image to the facial image of the child user when the face recognition was performed the most recently. The present invention automatically and timely updates the facial image of the child user used for unlocking, improves the recognition accuracy of the smart door lock for the child user, enhances the security and convenience of the system, and reduces the management burden of parents and administrators.
[0086] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or smart door lock including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or smart door lock. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or smart door lock including the element.
[0087] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.
[0088] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.
Claims
1. A method for automatically updating children's face data in a smart door lock, characterized in that: The method for automatically updating the child face data in the smart door lock includes: When a child user is detected triggering the smart door lock to perform face recognition, a face image of the child user is captured; Obtaining a registered child face image of the child user in the smart door lock, performing similarity calculation between the currently captured face image of the child user and the registered child face image, and obtaining a similarity calculation result; Record multiple similarity calculation results of the child user within a preset time period, and when the number of similarity calculation results showing a downward trend exceeds a preset threshold, update the registered child face image to the face image of the child user when the face recognition was performed most recently.
2. The method for automatically updating the face data of children in the smart door lock according to claim 1, characterized in that: When a child user is detected to trigger the smart door lock to perform face recognition, capturing a face image of the child user specifically includes: When a child user is detected triggering the smart door lock to perform face recognition, the smart door lock activates the facial recognition camera; The facial recognition camera captures a clear and complete facial image of the child user in real time within the camera's field of view.
3. The method for automatically updating the face data of children in the smart door lock according to claim 1, characterized in that: When a child user is detected to trigger the smart door lock to perform face recognition, a face image of the child user is captured, and then the following further includes: The face image of the child user is preprocessed, and the preprocessing includes size normalization and grayscale conversion.
4. The method for automatically updating the face data of children in a smart door lock according to claim 1, characterized in that: The step of obtaining a registered child face image of the child user in the smart door lock, and performing similarity calculation between the currently captured face image of the child user and the registered child face image to obtain a similarity calculation result specifically includes: Obtaining a registered child face image of the child user in the smart door lock, and obtaining a feature vector of the registered child face image stored in a database of the smart door lock; Extracting feature points of the currently captured facial image of the child user using image processing technology, and converting the feature points into feature vectors that can be used for identification; A cosine similarity calculation is performed between the feature vector of the face image of the child user and the feature vector of the registered child face image to obtain a cosine similarity calculation result.
5. The method for automatically updating the face data of children in the smart door lock according to claim 4, characterized in that: The feature points include the positions of eyes, nose and mouth.
6. The method for automatically updating the face data of children in a smart door lock according to claim 4, characterized in that: The recording of multiple similarity calculation results of the child user within a preset time period, when the number of similarity calculation results showing a downward trend exceeds a preset threshold, updating the registered child face image to the face image of the child user when the face recognition is performed the most recently, specifically includes: Recording multiple cosine similarity calculation results of the child user within a preset time period, determining whether the cosine similarity calculation results show a downward trend, and counting the number of the cosine similarity calculation results showing a downward trend; When the number of cosine similarity calculation results showing a downward trend exceeds a preset threshold, an update mechanism is triggered to update the registered child face image to the face image of the child user when the face recognition was performed most recently, and the updated registered child face image is stored in the database.
7. The method for automatically updating children's face data in a smart door lock according to claim 1, characterized in that: The method for automatically updating the child's face data in the smart door lock also includes: When the registered child face image of the child user needs to be updated, a user interface is provided on the smart door lock or the application of the associated mobile terminal, and an update status is displayed on the user interface, wherein the update status includes a similarity calculation result and a data update progress; A manual intervention option is provided on the user interface, so that the user can manually start the data update process, or manually enter a password or use other unlocking methods.
8. An automatic updating system for children's face data in a smart door lock, characterized in that: The automatic updating system of children's face data in the smart door lock includes: A data acquisition module, used to capture a facial image of a child user when it is detected that a child user triggers the smart door lock to perform facial recognition; a similarity calculation module, used for obtaining a registered child face image of the child user in the smart door lock, performing a similarity calculation between the currently captured face image of the child user and the registered child face image, and obtaining a similarity calculation result; The data update module is used to record multiple similarity calculation results of the child user within a preset time period. When the number of similarity calculation results showing a downward trend exceeds a preset threshold, the registered child face image is updated to the face image of the child user when the face recognition is performed for the most recent time.
9. A smart door lock, characterized in that: The smart door lock includes: a memory, a processor, and an automatic update program for children's facial data in the smart door lock stored in the memory and run on the processor. When the automatic update program for children's facial data in the smart door lock is executed by the processor, the steps of the automatic update method for children's facial data in the smart door lock as described in any one of claims 1-7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an automatic update program for children's facial data in a smart door lock. When the automatic update program for children's facial data in a smart door lock is executed by a processor, the steps of the automatic update method for children's facial data in a smart door lock are implemented as described in any one of claims 1-7.
Citation Information
Cited By
Quick door opening method and system based on pan-tilt door lock
CN120299120A
