Privacy protection method and related device

Abstract

Embodiments of the present application provide a privacy protection method and related equipment, the method comprises: detecting the ambient light brightness of the environment in which the electronic device is located; if the ambient light brightness is greater than or equal to a preset value, controlling a low-power camera to collect a first image; calling a first target detection model running on a low-power chip to detect whether the first image contains a target object; if it is detected that the first image contains a target object, calling a first target recognition model running on a low-power chip to detect whether the target object in the first image matches a preset target object; if the target object in the first image does not match the preset target object, responding to privacy data received by the electronic device, and prompting the privacy data using a preset notification method. In a bright light environment, the embodiments of the present application collect image data through a low-power camera, and perform target recognition through an algorithm running on a low-power chip, thereby reducing system power consumption while providing continuous identity recognition for the electronic device.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and in particular to a privacy protection method and related equipment. Background Technology

[0002] Currently, smartphones, tablets, and other smart devices all have a locking function. When locked, user access to the device is restricted, such as only being able to view notifications, access drop-down menus, and activate the camera. When unlocked, users can access various data on the device, such as applications, call logs, images, documents, and perform payment operations. If the owner fails to lock the device in time, or if the device is unlocked illegally, unauthorized users may access the device's data, leading to a breach of the owner's privacy. Therefore, it is necessary for devices to provide continuous user authentication, such as facial recognition; however, continuous user authentication results in higher system power consumption. Summary of the Invention

[0003] In view of the above, it is necessary to provide a privacy protection method and related equipment to solve the problem that continuous user identification leads to high system power consumption.

[0004] In a first aspect, this application provides a privacy protection method applied to an electronic device. The method includes: detecting the ambient light intensity of the environment in which the electronic device is located; if the ambient light intensity is greater than or equal to a preset value, controlling a low-power camera to capture a first image; calling a first target detection model running on a low-power chip to detect whether the first image contains a target object; if the first image contains a target object, calling a first target recognition model running on the low-power chip to detect whether the target object in the first image matches a preset target object; if the target object in the first image does not match the preset target object, responding to privacy data received by the electronic device, and prompting the privacy data using a preset notification method.

[0005] The above technical solution enables the acquisition of image data by a low-power camera in bright lighting conditions, and target recognition through algorithms running on a low-power chip. This reduces system power consumption while providing continuous identity verification for the electronic device. Furthermore, when the electronic device receives private data, it only prompts for the private data instead of directly displaying it, effectively protecting user privacy.

[0006] In one possible implementation, the step of using the preset notification method to prompt the privacy data includes: if the target object in the first image does not match the preset target object, the first target recognition service of the kernel layer of the electronic device reports the user identification failure result to the second target recognition service of the hardware abstraction layer of the electronic device; the second target recognition service reports the user identification failure result to the third target recognition service of the application layer of the electronic device; the third target recognition service sends the user identification failure result to the target application that receives the privacy data, and the target application prompts the privacy data using the preset notification method based on the user identification failure result.

[0007] Through the above technical solution, the reporting mechanism between different layers of the electronic device software architecture can accurately and efficiently transmit the result of user identification failure to the target application that receives the privacy data, thereby providing timely reminders about the privacy data.

[0008] In one possible implementation, the step of using the preset notification method to prompt the privacy data further includes: if the target object in the first image does not match the preset target object, the first target recognition service compares the user identity recognition failure result with the previous user identity recognition result; if the previous user identity recognition result is a recognition failure, the target application prompts the privacy data using the preset notification method based on the previous user identity recognition result.

[0009] With the above technical solution, when the current user identification result is the same as the previous user identification result, that is, when the user identification result remains unchanged, there is no need to report the current user identification result. The target application can directly process the privacy data based on the previous user identification result, thereby reducing system power consumption.

[0010] In one possible implementation, the step of using the preset notification method to prompt the privacy data further includes: if the previous user identification result was successful, the first target identification service reports the user identification failure result to the second target identification service.

[0011] Through the above technical solution, when the current user identification result is different from the previous user identification result, that is, when the user identification result changes, the current user identification result is reported in a timely manner, ensuring that the target application processes the privacy data accordingly.

[0012] In one possible implementation, the method further includes: if the target object in the first image matches the preset target object, in response to the privacy data received by the electronic device, displaying the privacy data using the preset notification method.

[0013] Using the above technical solution, when the user's identity verification result is successful, privacy data can be displayed directly to prevent the user from missing messages.

[0014] In one possible implementation, the method further includes: if a target object is detected in the first image, determining whether the frame rate of the target object in the first image is greater than or equal to a preset frame rate; if the frame rate of the target object in the first image is greater than or equal to the preset frame rate, displaying or prompting the privacy data using the preset notification method based on the previous user identification result.

[0015] With the above technical solution, the frame rate containing the target object in the first image is greater than or equal to the preset frame rate. That is, when the low-power camera continuously detects the target object, there is no need to extract and identify the target object. Instead, the privacy data is processed directly based on the previous user identity recognition result, reducing the number of times the first target recognition model runs and effectively reducing system power consumption.

[0016] In one possible implementation, the method further includes: if the frame rate of the first image containing the target object is greater than or equal to a preset frame rate, determining whether the number of the target object in the first image has not changed; if the number of the target object in the first image has not changed, displaying or prompting the privacy data using the preset notification method based on the previous user identification result.

[0017] With the above technical solution, when the frame rate of the target object in the first image is greater than or equal to the preset frame rate and the number of target objects does not change, that is, when the number of target objects continuously detected by the low-power camera remains unchanged, there is no need to extract and identify the target objects. Instead, the privacy data is processed directly based on the previous user identity recognition result, reducing the number of times the first target recognition model runs and effectively reducing system power consumption.

[0018] In one possible implementation, displaying the privacy data using a preset notification method includes: if a target object in the first image matches the preset target object, a first target recognition service in the kernel layer of the electronic device reports the successful user identification result to a second target recognition service in the hardware abstraction layer of the electronic device; the second target recognition service reports the successful user identification result to a third target recognition service in the application layer of the electronic device; the third target recognition service sends the successful user identification result to a target application, and the target application displays the privacy data using the preset notification method based on the successful user identification result.

[0019] Through the above technical solution, the reporting mechanism between different layers of the electronic device software architecture can accurately and efficiently transmit the result of successful user identification to the target application that receives the privacy data, thereby displaying the privacy data in a timely manner.

[0020] In one possible implementation, displaying the privacy data using a preset notification method includes: if the target object in the first image matches the preset target object, the first target recognition service compares the successful user identification result with the previous user identification result; if the previous user identification result was successful, the target application displays the privacy data using the preset notification method based on the previous user identification result.

[0021] With the above technical solution, when the current user identification result is the same as the previous user identification result, that is, when the user identification result remains unchanged, there is no need to report the current user identification result. The target application can directly display the privacy data based on the previous successful user identification result, thereby reducing system power consumption.

[0022] In one possible implementation, displaying the privacy data using a preset notification method includes: if the target object in the first image matches the preset target object, the first target recognition service compares the successful user identification result with the previous user identification result; if the previous user identification result is a failure, the first target recognition service reports the successful user identification result to the second target recognition service.

[0023] Through the above technical solution, when the current user identification result is different from the previous user identification result, that is, when the user identification result changes, the current successful user identification result is reported in a timely manner, ensuring that the target application displays private data.

[0024] In one possible implementation, the step of calling the first target detection model running on the low-power chip to detect whether the first image contains a target object includes: detecting target features in the first image through the first target detection model; if the target features are not detected in the first image, determining that the first image does not contain the target object; or if the target features are detected in the first image, determining that the first image contains the target object.

[0025] By using the above technical solution, the first target detection model running on a low-power chip can detect whether the first image contains a target object, which can reduce the system power consumption during the model operation while ensuring the detection accuracy of the target object.

[0026] In one possible implementation, the step of calling the first target recognition model running on the low-power chip to detect whether a target object in the first image matches a preset target object includes: extracting a first feature vector from the first image using the first target recognition model; calculating the similarity between the first feature vector of the first image and a second feature vector of the preset target object; if the similarity between the first feature vector of the first image and the second feature vector of the preset target object is greater than or equal to a preset similarity threshold, determining that the target object in the first image matches the preset target object; or if the similarity between the first feature vector of the first image and the second feature vector of the preset target object is less than the preset similarity threshold, determining that the target object in the first image does not match the preset target object.

[0027] By using the above technical solution, the first target recognition model, which operates on a low-power chip, identifies whether the target object in the first image matches a preset target object. This can reduce the system power consumption during model operation while ensuring the recognition accuracy of the target object.

[0028] In one possible implementation, the preset notification method includes pop-up display, notification information bar display, and lock screen interface display.

[0029] By using the above technical solution and the preset notification method to notify users of privacy data, it is possible to ensure that users are promptly informed that their electronic devices have received privacy data, thus avoiding missing important information.

[0030] In one possible implementation, the method further includes: if the target object in the first image does not match the preset target object, responding to an access request to the application and determining whether the application is a privacy application; if the application is a privacy application, not responding to the access request; or if the application is not a privacy application, determining whether the application contains privacy data; if the application contains privacy data, hiding the privacy data.

[0031] The above technical solution can effectively protect user privacy and prevent privacy leaks when the user identification result fails, i.e., when the current user of the electronic device is not the owner. It can also hide privacy data in non-privacy applications.

[0032] In one possible implementation, the method further includes: if the target object in the first image does not match the preset target object, prohibiting the operation of the privacy data.

[0033] The above technical solution can prevent the operation of privacy data when the user identification result fails, that is, when the current user of the electronic device is not the owner user, thus preventing the deletion or modification of the user's privacy data and effectively protecting the user's privacy.

[0034] In one possible implementation, the method further includes: if the ambient light intensity is less than the preset value, controlling the time-of-flight camera to acquire a second image; calling a second target detection model running on the processor to detect whether the second image contains the target object; if the second image contains the target object, calling a second target recognition model running on the processor to detect whether the target object in the second image matches the preset target object; if the target object in the second image does not match the preset target object, responding to the privacy data received by the electronic device, and prompting the privacy data using the preset notification method.

[0035] The above technical solution allows for image data acquisition via a time-of-flight camera in low-light environments, followed by target recognition through an algorithm run by the processor. This eliminates the need for external light sources, reducing system power consumption while providing continuous identity verification for electronic devices. Furthermore, when the electronic device receives private data, it only prompts for the data rather than directly displaying it, effectively protecting user privacy.

[0036] In one possible implementation, the method further includes: if the target object in the second image matches the preset target object, displaying the privacy data using the preset notification method.

[0037] The above technical solution can directly display private data, preventing users from missing messages.

[0038] In one possible implementation, both the first target detection model and the first target recognition model employ low-power model parameters, wherein the low-power model parameters include operator type, number of channels, quantization method, parameter storage bits, feature map bits, number of feature vectors, and data type.

[0039] Through the above technical solution, the first target detection model and the first target recognition model running on the low-power chip adopt low-power model parameters, which can reduce the amount of computation during the model operation and thus reduce the system power consumption.

[0040] Secondly, this application provides an electronic device, which includes a memory and a processor: wherein the memory is used to store program instructions; and the processor is used to read and execute the program instructions stored in the memory, such that when the program instructions are executed by the processor, the electronic device performs the aforementioned privacy protection method.

[0041] Thirdly, this application provides a chip coupled to a memory in an electronic device, the chip being used to control the processor of the electronic device to execute the aforementioned privacy protection method.

[0042] Fourthly, this application provides a computer storage medium storing program instructions that, when executed on an electronic device, cause the processor of the electronic device to perform the aforementioned privacy protection method.

[0043] Furthermore, the technical effects brought about by the second to fourth aspects can be found in the descriptions of the methods in the above-mentioned method section, and will not be repeated here. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the user interface of an electronic device provided in an embodiment of this application.

[0045] Figure 2 This is a software architecture diagram of an electronic device provided in an embodiment of this application.

[0046] Figure 3 This is a flowchart of a privacy protection method provided in an embodiment of this application.

[0047] Figure 4 This is another schematic diagram of the software architecture of an electronic device provided in an embodiment of this application.

[0048] Figure 5 This is a schematic diagram of another user interface of an electronic device provided in one embodiment of this application.

[0049] Figure 6 This is a schematic diagram of another user interface of an electronic device provided in one embodiment of this application.

[0050] Figure 7 This is a schematic diagram of another user interface of an electronic device provided in one embodiment of this application.

[0051] Figure 8 This is a flowchart of a privacy protection method provided in another embodiment of this application.

[0052] Figure 9 This is a flowchart of a privacy protection method provided in another embodiment of this application.

[0053] Figure 10 This is a flowchart of a privacy protection method provided in another embodiment of this application.

[0054] Figure 11 This is a partial timing diagram of the privacy protection method provided in one embodiment of this application.

[0055] Figure 12 This is another part of the processing timing diagram of the privacy protection method provided in one embodiment of this application.

[0056] Figure 13 This is a hardware architecture diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0057] In one embodiment of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in one embodiment of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to limit the application. It should be understood that, unless otherwise stated, " / " in this application means "or". For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. "At least one" refers to one or more. "More than one" refers to two or more. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, and a, b, and c. Where there is no conflict, the following embodiments and features described herein can be combined with each other.

[0059] Nowadays, smartphones, tablets, and other smart devices all have a locking function. When locked, user access to the device is restricted, such as only being able to view notifications, access drop-down menus, and activate the camera. When unlocked, users can access various data on the smart device, such as applications, call logs, images, documents, and perform payment operations. If the owner fails to lock the device in time, or if the device is unlocked illegally, non-owner users may access the device's data, leading to a breach of the owner's privacy. Therefore, it is necessary for devices to provide continuous user authentication, such as facial recognition. However, continuous user authentication leads to higher system power consumption, increases battery usage, and may also affect the processing of other processes, causing system lag.

[0060] Taking push notifications as an example, when an electronic device receives a push notification from an application, it typically displays the message's content as a pop-up at the top of the user interface. For example... Figure 1 As shown, when a user invites a non-user to view photos in the gallery application of an electronic device, if the electronic device directly displays a push message from an instant messaging application in the form of a pop-up window, the non-user can also see the specific content of the push message, resulting in the leakage of the user's privacy and causing inconvenience to the user.

[0061] To protect the privacy of the device owner, electronic devices can provide continuous user identification. For example, the device can capture the face of the current user through its camera and compare it with the owner's face. If the captured face matches the owner's face, the current user is identified as the owner, and the device can display a pop-up window showing the details of the push notification. If the captured face does not match the owner's face, the current user is identified as a non-owner, and the device will only display a pop-up window indicating that a push notification from a specific application has been received, without showing the details of the push notification.

[0062] However, when electronic devices provide continuous user identification, the camera needs to be kept on and provide real-time face recognition (including face detection and face comparison). This can easily lead to high system power consumption, accelerate the power consumption of electronic devices, and thus affect the user experience.

[0063] To address the aforementioned issues, this application provides a privacy protection method that, in bright light environments, acquires image data using a low-power camera and performs target recognition on the acquired image data using an algorithm running within a low-power chip. This effectively reduces system power consumption while providing continuous user identification for electronic devices.

[0064] See Figure 2 The diagram shown is a software architecture diagram of an electronic device provided in an embodiment of this application. The layered architecture divides the software into several layers, each with a clear role and function. Layers communicate with each other through software interfaces. For example, the Android system, from top to bottom, consists of the application layer 101, framework layer 102, Android runtime and system libraries 103, hardware abstraction layer 104, kernel layer 105, and hardware layer 106.

[0065] Application layer 101 may include a series of application packages. For example, application packages may include applications such as camera, gallery, calendar, calling, map, navigation, WLAN, Bluetooth, music, video, SMS, device control services, etc.

[0066] The framework layer 102 provides an Application Programming Interface (API) and programming framework for applications in the application layer. The application framework layer includes predefined functions. For example, it may include a window manager, content provider, view system, phone manager, resource manager, notification manager, etc.

[0067] The window manager manages window programs. It can obtain screen size, determine the presence of a status bar, lock the screen, and capture screenshots. The content provider stores and retrieves data, making it accessible to applications. This data can include videos, images, audio, made and received calls, browsing history and bookmarks, phone books, etc. The view system includes visual controls, such as controls for displaying text and controls for displaying images. The view system can be used to build applications. A display interface can consist of one or more views. For example, a display interface including a text notification icon can include views for displaying text and views for displaying images. The phone manager provides communication functionality for electronic devices, such as managing call status (including connection and disconnection). The resource manager provides applications with various resources, such as localized strings, icons, images, layout files, and video files. The notification manager allows applications to display notifications in the status bar, conveying informational messages that disappear automatically after a short pause without user interaction. For example, the notification manager is used to notify of download completion or message alerts. The notification manager can also display notifications as icons or scrolling text in the system's top status bar, such as notifications from background applications, or as dialog boxes on the screen. Examples include displaying text messages in the status bar, emitting alert sounds, causing electronic devices to vibrate, and flashing indicator lights.

[0068] The Android Runtime consists of the core libraries and the virtual machine. The Android runtime is responsible for the scheduling and management of the Android system. The core libraries consist of two parts: one part contains the functionalities that the Java language needs to call, and the other part contains the core Android libraries.

[0069] Application layer 101 and framework layer 102 run in a virtual machine. The virtual machine executes the Java files of the application layer and framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0070] System library 103 may include multiple functional modules. For example, a surface manager, media libraries, 3D graphics processing libraries (e.g., OpenGL ES), 2D graphics engines (e.g., SGL), etc.

[0071] The Surface Manager manages the display subsystem and provides fusion of 2D and 3D layers for multiple applications. The Media Library supports playback and recording of various common audio and video formats, as well as still image files. It supports multiple audio and video encoding formats, such as MPEG4, H.264, MP3, AAC, AMR, JPG, and PNG. The 3D Graphics Processing Library implements 3D graphics drawing, image rendering, compositing, and layer processing. The 2D Graphics Engine is the drawing engine for 2D graphics.

[0072] Hardware Abstraction Layer 104 runs in user space, encapsulates kernel-level drivers, and provides calling interfaces to the upper layers.

[0073] Kernel layer 105 is the layer between hardware and software. Kernel layer 105 contains at least the display driver, touch driver, audio driver, and sensor driver.

[0074] The kernel layer (105) is the core of the operating system for electronic devices. It is the first layer of software extension based on the hardware, providing the most basic functions of the operating system. It is the foundation for the operation of the operating system, responsible for managing system processes, memory, device drivers, files, and network systems, and determining the system's performance and stability. For example, the kernel layer can determine the timing of an application's operation on a certain part of the hardware.

[0075] Kernel layer 105 includes hardware-dependent programs such as interrupt handlers and device drivers, as well as basic, common, and frequently running modules such as clock management and process scheduling modules, and critical data structures. The kernel layer can be located within the processor or embedded in internal memory.

[0076] Hardware layer 106 includes the hardware of electronic devices, such as displays, buttons, cameras, etc.

[0077] For a detailed description of the privacy protection method, please refer to the descriptions in the various embodiments below.

[0078] See Figure 3 The diagram shown is a flowchart of a privacy protection method provided in an embodiment of this application. The method is applied in an electronic device, and the privacy protection method includes:

[0079] S101, detect the ambient light intensity of the environment in which the electronic device is located, and determine whether the ambient light intensity is greater than or equal to a preset value. If the ambient light intensity is greater than or equal to the preset value, execute S102; if the ambient light intensity is less than the preset value, execute S106.

[0080] See Figure 4The diagram shown is another schematic representation of the software architecture of an electronic device according to an embodiment of this application. In one embodiment of this application, the hardware layer of the electronic device includes an ambient light sensor 180L. After the electronic device is powered on, the electronic device controls the ambient light sensor 180L to detect the ambient light brightness of the environment in which the electronic device is located every first preset time interval, and determines whether the ambient light brightness is greater than or equal to a preset value. The first preset time interval is 3 seconds, 4 seconds, 5 seconds, or other times, and the preset value is 15 lux, 20 lux, 25 lux, or other brightness values.

[0081] In another embodiment of this application, it can also be determined whether the smoothed values ​​of multiple ambient light brightness detected within a preset time period are greater than or equal to a preset value. If the smoothed values ​​of multiple ambient light brightness detected within the preset time period are greater than or equal to the preset value, S102 is executed; if the smoothed values ​​of multiple ambient light brightness detected within the preset time period are less than the preset value, S106 is executed.

[0082] In another embodiment of this application, the preset time period is 1 minute, and the smoothing value of the multiple ambient light brightness can be the average value of the multiple ambient light brightness detected every first preset time within the preset time period or the average value of the multiple ambient light brightness remaining after removing outliers. Outliers can include the maximum and minimum values ​​of the multiple ambient light brightness detected within the preset time period.

[0083] S102 controls the low-power camera to capture the first image.

[0084] like Figure 4 As shown, the hardware layer of the electronic device also includes a low-power camera 1061. In one embodiment of this application, the low-power camera is an active optical (AO) camera. The low-power camera can be a front-facing camera of the electronic device or located near the front-facing camera. The electronic device controls the low-power camera to capture a first image of the scene in front of the electronic device's display screen every second preset time interval. The second preset time interval is 0.2 seconds, 0.3 seconds, 0.5 seconds, or other times. The active optical camera uses active optics technology for depth perception and tracking, employing an infrared light source and an infrared light receiver to calculate depth information by measuring the round-trip time of light between the object and the camera. Compared to time-of-flight cameras, low-power cameras consume less power during operation and are widely used in fields such as face recognition and gesture control.

[0085] In another embodiment of this application, the low-power camera is an Always On (AO) camera. The image sensor used in the Always On camera has low power consumption, can dynamically control power consumption, and can also collect image data suitable for deep learning models, thereby suppressing the information processing load caused by external processors and reducing system power consumption.

[0086] S103: The first target detection model running on the low-power chip is invoked to detect whether the first image contains a target object. If a target object is detected in the first image, S104 is executed; otherwise, S101 is returned to be executed.

[0087] In one embodiment of this application, the kernel layer of the electronic device includes a sensor hub 1050, and the hardware layer includes a low-power chip 1062. The sensor hub 1050 includes a first target recognition service 1051, and the first target recognition service 1051 includes a first target detection model 1052. The low-power chip 1062 is an eNPU (Embedded Neural-network Processing Unit) chip. The first target detection model detects target features in a first image. If no target features are detected in the first image, it is determined that the first image does not contain the target object; if target features are detected in the first image, it is determined that the first image contains the target object. The type of the first target detection model and the type of target features are determined according to the type of the target object. The target object includes a face and / or gestures. The first target detection model includes a first face detection model and / or a first gesture detection model, and the target features include face features and gesture features.

[0088] In one embodiment of this application, the first face detection model is a convolutional neural network model. The convolutional neural network model is trained and generated using face bounding boxes as feature data. A face bounding box is the smallest rectangle that includes multiple parts of the face, such as eyebrows, eyes, nose, and mouth. In other embodiments of this application, the multiple parts may also include the facial features.

[0089] In one embodiment of this application, a first face detection model detects face bounding boxes in a first image captured by a low-power camera. If no face bounding box is detected in the first image captured by the low-power camera, it is determined that the first image captured by the low-power camera does not contain a face. If a face bounding box is detected in the first image captured by the low-power camera, it is determined that the first image captured by the low-power camera includes a face, and face information is output. The face information includes, but is not limited to, the number of faces and the coordinates of at least one vertex on the face bounding box. The number of faces is the same as the number of bounding boxes. The coordinates of at least one vertex on the bounding box can include the coordinates of the top-left vertex and the bottom-right vertex of the bounding box, and the vertex coordinates are pixel coordinates. For example, the face information output by the first face detection model is "2, target1 rect(500*40, 600*80), target2 rect(700*200, 800*240)". In other embodiments of this application, the first face detection model can also be a cascaded classifier based on Haar features, the Dlib face detection algorithm, etc.

[0090] In one embodiment of this application, the first object detection model employs low-power model parameters. These parameters include, but are not limited to, operator type, number of channels, quantization method, parameter storage bit depth, and feature map bit depth. The operators in the first object detection model include, but are not limited to, convolution and activation functions. The convolution type is regular convolution (i.e., ordinary convolution), and the activation function is ReLU. Compared to depthwise convolution and parameterized PReLU activation functions, regular convolution and ReLU activation functions are more suitable for low-power eNPU chips, effectively reducing model computation and system power consumption during model operation. The number of channels in the first object detection model (e.g., the number of channels for input and output data) is a multiple of 32. The quantization method quantizes 32-bit floating-point numbers or converts floating-point numbers to fixed-point numbers, using low-precision floating-point numbers to reduce model storage requirements and computational overhead. The parameter storage bit depth is 8 bits, meaning the model parameters are stored using 8-bit data. The feature map bit depth is 8 bits, meaning the feature map is calculated using 8-bit data. The first target detection model uses low-power model parameters, which can reduce the amount of computation during model operation and reduce system power consumption.

[0091] In another embodiment of this application, if no target object is detected in the first image, S105 can also be executed.

[0092] S104: The first target recognition model running on the low-power chip is invoked to detect whether the target object in the first image matches a preset target object. If the target object in the first image does not match the preset target object, S105 is executed; if the target object in the first image matches the preset target object, the process returns to S101.

[0093] In one embodiment of this application, the first target recognition service 1051 further includes a first target recognition model 1053 running on a low-power chip 1062. The type of the first target recognition model and the preset target object are determined according to the type of the target object. The target object includes a face and / or a gesture. The first target recognition model includes a first face recognition model and / or a first gesture recognition model. The preset target object includes a preset face and / or a preset gesture. The preset face can be a face set by the owner user or a face set by the owner user. The preset gesture can be a gesture preset by the owner user. A first feature vector of the first image is extracted through the first target recognition model. The similarity between the first feature vector of the first image and the second feature vector of the preset target object is calculated. If the similarity between the first feature vector of the first image and the second feature vector of the preset target object is greater than or equal to a preset similarity threshold, it is determined that the target object in the first image matches the preset target object. If the similarity between the first feature vector of the first image and the second feature vector of the preset target object is less than the preset similarity threshold, it is determined that the target object in the first image does not match the preset target object.

[0094] In one embodiment of this application, the first face recognition model can also be a convolutional neural network model, which is trained and generated using the positions of facial feature points as feature data. The first face recognition model detects multiple feature points within the face bounding box extracted by the first face detection model using a keypoint detector. For example, the multiple feature points include the inner and outer corners of the eyes and the tip of the nose. The coordinates of these multiple feature points are extracted as the feature vector of the face in the first image captured by the low-power camera. The coordinates of the feature points are the pixel coordinates of the feature points in the image. For example, the feature vector is points[(94, 238), (98, 271), (105, 303), (113, 334), (125, 362)]. The feature vector of the face in the first image captured by the low-power camera is calculated. The similarity between the feature vector of the face in the first image captured by the low-power camera and the feature vector of the preset face is determined; it is determined whether the similarity between the feature vector of the face in the first image captured by the low-power camera and the feature vector of the preset face is greater than or equal to a preset similarity threshold; if the similarity between the feature vector of the face in the first image captured by the low-power camera and the feature vector of the preset face is greater than or equal to the preset similarity threshold, it is determined that the face in the first image captured by the low-power camera does not match the preset face.

[0095] In one embodiment of this application, the first target recognition model also employs low-power model parameters. In addition to the parameters mentioned above, the model parameters of the first target recognition model also include the number and data type of feature vectors. For example, the number of feature vectors is 512, and the data type is 8-bit fixed-point numbers. Compared to floating-point numbers, the 8-bit fixed-point representation is simpler and faster, improving the computational efficiency of similarity. The first target recognition model also uses the SIMD (Single Instruction Multiple Data) instruction set for reading and calculating feature vectors. The SIMD instruction set is provided by the Qualcomm Hexagon digital signal processor, which can improve computational efficiency, support efficient multi-threaded programming, and provide large-scale parallel computing capabilities.

[0096] In one embodiment of this application, the similarity can be cosine similarity, and the formula (1) for calculating cosine similarity is:

[0097]

[0098] In other embodiments of this application, the similarity can also be Euclidean distance.

[0099] S105, responding to the privacy data received by the electronic device, prompts the user with a preset notification method.

[0100] In one embodiment of this application, a privacy application or a non-privacy application containing privacy data may send a subscription request to a third target identification service at the application layer to subscribe to user identification results. The third target identification service may send a subscription request to a second target identification service at the hardware abstraction layer to subscribe to user identification results obtained by the second target identification service. The second target identification service may send a subscription request to a first target identification service at the kernel layer to subscribe to user identification results obtained by the first target identification service.

[0101] In one embodiment of this application, the second target recognition service of the hardware abstraction layer can also subscribe to different sensor services from the sensor center of the kernel layer, such as subscribing to the sensing service of the ambient light sensor. This allows the ambient light sensor of the sensor center to send the detected ambient light brightness to the second target recognition service. After receiving the ambient light brightness, the second target recognition service determines whether the ambient light brightness is greater than or equal to a preset value. If the ambient light brightness is greater than or equal to the preset value, the second target recognition service subscribes to the first target recognition service, and the first target recognition service starts running. It controls the low-power camera to capture a first image. When the first target detection model detects that the first image contains a target object, and the first target recognition model detects that the target object in the first image is not a preset target object, the first target recognition service reports the identity recognition failure result to the second target recognition service. The second target recognition service then reports the identity recognition failure result to the third target recognition service. The third target recognition service further reports the identity recognition failure result to the target application that received the privacy data. The target application uses a preset notification method to prompt the privacy data.

[0102] In one embodiment of this application, a user can preset push data received by a preset type of application or all applications in an electronic device as private data. The preset type of application includes, but is not limited to, email applications, communication applications, work applications, and health applications. For example, push data from an email application may include summaries of newly received emails; push data from a communication application may include messages sent by other users; push data from a work application may include work plans; and push data from a health application may include physiological data.

[0103] In one embodiment of this application, if the target object in the first image is detected to not match the preset target object, that is, when the user using the electronic device is not the owner user, when the electronic device receives push data from the application, it is determined whether the push data from the application is preset privacy data. If the push data from the application is preset privacy data, the privacy data is prompted using a preset notification method instead of directly displaying the specific content of the privacy data, so as to protect the privacy of the owner user.

[0104] In one embodiment of this application, the preset notification methods include, but are not limited to: pop-up display, notification information bar display, and lock screen display. For example, when the instant messaging application A of an electronic device receives a message sent by another user, such as... Figure 5 As shown, a pop-up window displays a notification at the top of the user interface, thus alerting the electronic device to the received private data. The notification could state, "Instant messaging application A has received a new message." Figure 6 As shown, a notification message is displayed in the drop-down notification bar of the electronic device, thus notifying the device of the received private data through a notification. The content of the notification message could be "Instant messaging application A has received a new message." Figure 7 As shown, a notification message is displayed on the lock screen of the electronic device to inform the device of the private data it has received. The content of the notification message may be "Instant messaging application A has received a new message".

[0105] In another embodiment of this application, if it is detected that the target object in the first image captured by the low-power camera does not match the preset target object, the privacy data may not be displayed or prompted until it is detected that the target object in the first image captured by the low-power camera matches the preset target object, at which point the privacy data will be displayed using a preset notification method.

[0106] In this embodiment, an algorithm based on a low-power camera and a low-power chip is used for continuous user identification to determine whether the user in front of the electronic device is an authorized user or an unauthorized user. When the user in front of the electronic device is an unauthorized user, the electronic device only displays a prompt message to indicate the received privacy data when it receives privacy data, without directly displaying the specific content of the privacy data, thereby effectively protecting user privacy.

[0107] S106 controls the Time of Flight (TOF) camera to acquire a second image.

[0108] like Figure 4As shown, in one embodiment of this application, the hardware layer of the electronic device further includes a time-of-flight camera 1063. If the ambient light intensity is less than a preset value, the time-of-flight camera is controlled to capture a second image of the scene in front of the electronic device's display screen every second preset time interval. The time-of-flight camera is a front-facing camera of the electronic device or is located near the front-facing camera of the electronic device, used to capture a second image of the scene in front of the electronic device's display screen. The time-of-flight camera determines the distance by emitting infrared light or laser pulses and measuring the time required for the light signal to travel from the camera to the target object and back. The time-of-flight camera can acquire depth information of the scene in real time and is widely used in augmented reality, virtual reality, robot navigation, and other fields.

[0109] S107: The second object detection model running on the processor is invoked to detect whether the second image contains a target object. If a target object is detected in the second image, proceed to S108; otherwise, return to S101.

[0110] like Figure 4 As shown, in one embodiment of this application, the hardware abstraction layer of the electronic device includes an Intelligent Sensor Fusion Service (ISF Service) 1040, which includes a second target recognition service 1041. The second target recognition service 1041 includes a first target detection model 1042 and a second target recognition model 1043 running on the processor. In one embodiment of this application, the method by which the second target detection model detects whether a target object is contained in the second image is the same as the method by which the first target detection model detects whether a target object is contained in the first image, and will not be described in detail here. In another embodiment of this application, if no target object is detected in the second image, step S105 can also be executed.

[0111] S108: The second target recognition model running on the processor is invoked to detect whether the target object in the second image matches a preset target object. If the target object in the second image does not match the preset target object, S105 is executed; if the target object in the second image matches the preset target object, the process returns to S101.

[0112] In one embodiment of this application, the method by which the second target recognition model detects whether a target object in the second image matches a preset target object is the same as the method by which the first target recognition model detects whether a target object in the first image matches a preset target object, and will not be described in detail here.

[0113] In one embodiment of this application, the second object detection model and the second object recognition model are pre-parsed and sequentially loaded, meaning they are loaded at runtime, requiring only a certain amount of memory and reducing power consumption during non-use periods. Pre-parsing refers to creating the trained model as a file in advance, while sequential loading refers to loading the model structure and parameters from the file to implement the model's functions, such as object detection and recognition.

[0114] See Figure 8 The diagram shown is a flowchart of a privacy protection method provided in another embodiment of this application. The method is applied in an electronic device, and the privacy protection method includes:

[0115] S201, detect the ambient light intensity of the environment in which the electronic device is located, and determine whether the ambient light intensity is greater than or equal to a preset value. If the ambient light intensity is greater than or equal to the preset value, execute S202; if the ambient light intensity is less than the preset value, execute S206.

[0116] S202 controls the low-power camera to capture the first image.

[0117] S203: The first target detection model running on the low-power chip is invoked to detect whether the first image contains a target object. If a target object is detected in the first image, S204 is executed; if no target object is detected in the first image, the process returns to S201.

[0118] S204: The first target recognition model running on the low-power chip is invoked to detect whether the target object in the first image matches a preset target object. If the target object in the first image does not match the preset target object, S205 is executed; if the target object in the first image matches the preset target object, the process returns to S201.

[0119] S205, responding to privacy data received by the electronic device, prompts the user with a preset notification method regarding the privacy data.

[0120] S206, In response to the privacy data received by the electronic device, the privacy data is displayed using a preset notification method.

[0121] In one embodiment of this application, if a target object in the first image is detected to match a preset target object, the first target service reports the successful user identification result to the second target identification service, the second target identification service then reports the successful identification result to the third target identification service, and the third target identification service further reports the successful identification result to the target application that received the privacy data. The target application directly displays the privacy data using a preset notification method. For example, when the instant messaging application A of an electronic device receives a message sent by another user, such as... Figure 1As shown, a pop-up window at the top of the user interface displays the specific content of the privacy data, thus displaying the privacy data in the form of a pop-up notification. The specific content of the privacy data can be "Xiao Zhang: There is an urgent meeting at 3 pm that requires your attendance."

[0122] S207, controls the time-of-flight camera to acquire a second image.

[0123] S208: The second object detection model running on the processor is invoked to detect whether the second image contains a target object. If a target object is detected in the second image, proceed to S209; otherwise, return to S201.

[0124] S209: The second target recognition model running on the processor is invoked to detect whether the target object in the second image matches a preset target object. If the target object in the second image does not match the preset target object, S205 is executed; if the target object in the second image matches the preset target object, S206 is executed.

[0125] In one embodiment of this application, the method further includes: if the target object in the first image does not match a preset target object, responding to an access request to the application and determining whether the application is a privacy application; if the application is a privacy application, not responding to the access request; or if the application is not a privacy application, determining whether the application contains privacy data; if the application contains privacy data, hiding the privacy data, and responding to an access request to the application after hiding the privacy data.

[0126] In one embodiment of this application, privacy data also includes all data corresponding to the privacy application and data involving user privacy in non-privacy applications. Users can set an application as a privacy application or a non-privacy application in system settings. If an application is set as a privacy application by the user, then all data in that privacy application is privacy data. Users can also set data involving user privacy as privacy data in non-privacy applications. For example, a user may set a gallery application as a non-privacy application in system settings, but set a specific album within the gallery application as privacy data.

[0127] For example, if work application B has been preset as a private application by the user, and the target object in the first or second image does not match the preset target object, when work application B receives an access request, the access request could be a request to open work application B, or a request to switch the current user interface to the interface of work application B while it is running in the background. If work application B is determined to be a private application, then the access request will not be responded to, that is, work application B will not be opened or its interface will not be displayed. This prevents the user's child from sending work-related messages, prevents the user's assistant from viewing the user's confidential work information, and prevents the user's partner from using work applications and causing confidential information to be leaked.

[0128] For example, the photo album application C has been preset by the user as a non-privacy application, but album a within photo album application C has been preset by the user as private data. If the target object in the first or second image does not match the preset target object, when photo album application C receives an access request, it can open photo album application C normally or switch the current interface to photo album application C. Then, upon determining that album a is private data, after opening photo album application C or switching the current interface to photo album application C, album a within photo album application C is hidden, thereby preventing the owner's assistant or partner from viewing the specified photos in the album.

[0129] In another embodiment of this application, the desktop of the electronic device can be the interface of a desktop application. If the target object in the first image or the second image does not match the preset target object, the icon of the privacy application can be hidden when the interface of the electronic device is switched to the desktop, thereby preventing non-owner users from opening the privacy application.

[0130] In one embodiment of this application, the method further includes: if the target object in the first image does not match a preset target object, prohibiting operations on privacy data. Operations on privacy data include, but are not limited to: viewing, modifying, deleting, and downloading.

[0131] For example, the system settings application D has been set as a non-privacy application by the user, but some settings items in the system settings application D (such as alarm clock settings, ringtone settings, volume settings, desktop icon layout settings, etc.) have been set as private data by the user. If the target object in the first image or the second image does not match the preset target object, when the system settings application D receives modifications to the alarm clock time, ringtone, volume, and desktop icon layout, it disables the operation on the alarm clock, ringtone, volume, and desktop icon layout, thereby preventing the system settings from being arbitrarily changed by the owner's child.

[0132] For example, if application E has been set as a private application by the user, and the target object in the first or second image does not match the preset target object, when application E receives a deletion operation, the operation on application E is disabled, thereby preventing application E from being accidentally deleted by the owner's child.

[0133] In another embodiment of this application, user authentication can be initiated when the electronic device receives privacy data, receives an access request for privacy data, or receives an operation on privacy data. This involves detecting ambient light intensity using an ambient light sensor, acquiring image data using a low-power camera or time-of-flight camera, performing target detection and recognition using a target detection model and a target recognition model, obtaining the authentication result, determining whether the authentication result has changed, and if so, reporting the result to the target application. The target application then displays or prompts about privacy data based on the authentication result, responds or does not respond to access requests for privacy data, and prohibits or does not prohibit operations on privacy data. In other words, continuous authentication is only initiated when privacy protection is required, thereby reducing system power consumption.

[0134] See Figure 9 The diagram shown is a flowchart of a privacy protection method provided in another embodiment of this application. The method is applied in an electronic device, and the privacy protection method includes:

[0135] S301, detect the ambient light intensity of the environment in which the electronic device is located, and determine whether the ambient light intensity is greater than or equal to a preset value. If the ambient light intensity is greater than or equal to the preset value, execute S302; if the ambient light intensity is less than the preset value, execute S308.

[0136] S302 controls the low-power camera to capture the first image.

[0137] S303: The first target detection model running on the low-power chip is invoked to detect whether the first image contains a target object. If a target object is detected in the first image, S304 is executed; otherwise, S305 is executed.

[0138] S304, determine whether the frame rate at which the target object is detected in the first image is greater than or equal to a preset frame rate. If the frame rate at which the target object is detected in the first image is greater than or equal to the preset frame rate, execute S306; if the frame rate at which the target object is detected in the first image is less than the preset frame rate, execute S308.

[0139] In one embodiment of this application, the frame rate is the frequency at which the target object is detected in the first image, and the preset frame rate is 5Hz, 6Hz, 7Hz or other frame rates.

[0140] S305, determine whether the previous authentication result was successful. If the previous authentication result was unsuccessful, proceed to S306; if the previous authentication result was successful, proceed to S307.

[0141] In one embodiment of this application, if the frame rate at which the first image contains a target object is greater than or equal to a preset frame rate, the first target recognition service does not need to perform identity authentication, nor does it need to report the identity authentication result to the second target recognition service, thereby reducing system power consumption. The target application that receives the privacy data directly prompts or displays the privacy data using a preset notification method based on the previous identity authentication result.

[0142] S306, in response to privacy data received by the electronic device, prompts the user with a preset notification method regarding the privacy data.

[0143] S307 responds to privacy data received by the electronic device and displays the privacy data using a preset notification method.

[0144] S308: The first target recognition model running on the low-power chip is invoked to detect whether the target object in the first image matches a preset target object. If the target object in the first image does not match the preset target object, S306 is executed; if the target object in the first image matches the preset target object, S307 is executed.

[0145] S309 controls the time-of-flight camera to acquire a second image.

[0146] S310: The second object detection model running on the processor is invoked to detect whether the second image contains a target object. If a target object is detected in the second image, S311 is executed; otherwise, S309 is returned to the previous step.

[0147] S311: The second target recognition model running on the processor is invoked to detect whether the target object in the second image matches a preset target object. If the target object in the second image does not match the preset target object, S306 is executed; if the target object in the second image matches the preset target object, S307 is executed.

[0148] In another embodiment of this application, step S304 can be replaced by: determining whether the frame rate at which the target object is detected in the first image is greater than or equal to a preset frame rate, and determining whether the number of target objects in the first image has not changed. If the frame rate at which the target object is detected in the first image is greater than or equal to the preset frame rate, and the number of target objects in the first image has not changed, proceed to step S306; if the frame rate at which the target object is detected in the first image is less than the preset frame rate, or the number of target objects in the first image has changed, proceed to step S308.

[0149] See Figure 10 The diagram shown is a flowchart of a privacy protection method provided in another embodiment of this application. The method is applied in an electronic device, and the privacy protection method includes:

[0150] S401, Detect the ambient light intensity of the environment in which the electronic device is located, and determine whether the ambient light intensity is greater than or equal to a preset value. If the ambient light intensity is greater than or equal to the preset value, execute S402; if the ambient light intensity is less than the preset value, execute S408.

[0151] S402 controls the low-power camera to capture the first image.

[0152] S403: The first target detection model running on the low-power chip is invoked to detect whether the first image contains a target object. If a target object is detected in the first image, S404 is executed; otherwise, S405 is executed.

[0153] S404, determine whether the frame rate at which the target object is detected in the first image is greater than or equal to a preset frame rate. If the frame rate at which the target object is detected in the first image is greater than or equal to the preset frame rate, execute S406; if the frame rate at which the target object is detected in the first image is less than the preset frame rate, execute S408.

[0154] S405, determine whether the previous authentication result was successful. If the previous authentication result was unsuccessful, proceed to S406; if the previous authentication result was successful, proceed to S407.

[0155] S406, in response to privacy data received by the electronic device, prompts the user with a preset notification method regarding the privacy data.

[0156] S407 responds to privacy data received by the electronic device and displays the privacy data using a preset notification method.

[0157] S408: The first target recognition model running on the low-power chip is invoked to detect whether the target object in the first image matches a preset target object. If the target object in the first image does not match the preset target object, S406 is executed; if the target object in the first image matches the preset target object, S407 is executed.

[0158] S409 controls the time-of-flight camera to acquire a second image.

[0159] S410: The second object detection model running on the processor is invoked to detect whether the second image contains a target object. If a target object is detected in the second image, S411 is executed; otherwise, S412 is executed.

[0160] S411: The second target recognition model running on the processor is invoked to detect whether the target object in the second image matches a preset target object. If the target object in the second image does not match the preset target object, S406 is executed; if the target object in the second image matches the preset target object, S407 is executed.

[0161] S412, determine whether the number of consecutive times the target object is not detected in the second image is greater than or equal to a preset number. If the number of consecutive times the target object is not detected in the second image is greater than or equal to the preset number, proceed to S413; if the number of consecutive times the target object is not detected in the second image is less than the preset number, return to S409. In one embodiment of this application, the preset number is 2, 3, 4 or other values.

[0162] S413, determine whether the previous authentication result was successful. If the previous authentication result was unsuccessful, proceed to S406; if the previous authentication result was successful, proceed to S407.

[0163] In another embodiment of this application, it can also be determined whether the frame rate at which the target object is detected in the second image is greater than or equal to a preset frame rate, and whether the number of target objects in the second image has not changed. If the frame rate at which the target object is detected in the second image is greater than or equal to the preset frame rate, and the number of target objects in the second image has not changed, it is determined that the user authentication result remains unchanged, and the target application displays or prompts privacy data based on the previous authentication result. If the frame rate at which the target object is detected in the second image is less than the preset frame rate, or the number of target objects in the second image has changed, execution returns to step S409.

[0164] See Figure 11-12 The diagram shown is a timing diagram of the privacy protection method provided in an embodiment of this application.

[0165] S501, the target application in the application layer subscribes to the authentication result from the third target identification service in the application layer.

[0166] S502, the third target recognition service subscribes to the identity authentication result from the second target recognition service of the hardware abstraction layer.

[0167] S503, the second target recognition service subscribes to the ambient light brightness detected by the ambient light sensor from the sensor center in the kernel layer.

[0168] S504, The second target recognition service obtains the ambient light intensity sent by the sensor service.

[0169] S505, the second target recognition service determines whether the ambient light intensity is greater than or equal to a preset value.

[0170] S506, if the ambient light intensity is greater than or equal to the preset value, the second target recognition service subscribes to the identity authentication result from the first target recognition service in the kernel layer and sends the identity authentication instruction to the first target detection service.

[0171] S507, the first object detection service responds to the authentication command and sends an image acquisition command to the low-power camera.

[0172] S508, a low-power camera, acquires a first image and sends the first image to a first target detection model.

[0173] S509, the first target detection model running in the low-power chip of the kernel layer detects whether the first image contains a target object.

[0174] S510, if the first image contains a target object, the first target recognition service determines whether the frame rate at which the first image contains the target object is greater than or equal to a preset frame rate, and whether the number of target objects in the first image has not changed. If the frame rate at which the first image contains the target object is greater than or equal to the preset frame rate, and the number of target objects in the first image has not changed, the service returns to execute S508. If the frame rate at which the first image contains the target object is less than the preset frame rate, or the number of target objects in the first image has changed, the service executes S511.

[0175] S511, the first target recognition service sends the first image to the first target recognition model, and the first target recognition model running on the low-power chip detects whether the target object in the first image matches the preset target object, determines the identity recognition result, and returns the determined identity recognition result to the first target recognition service.

[0176] S512, the first target recognition service determines whether the current identity recognition result is the same as the previous identity recognition result.

[0177] S513, if the current identity recognition result is different from the previous identity recognition result, the first target recognition service will report the current identity recognition result to the second target recognition service.

[0178] S514, the second target recognition service reports the current identity recognition result to the third target recognition service.

[0179] S515, the third target identification service sends the current identity recognition result to the target application.

[0180] S516 If the ambient light is less than the preset value, the second target recognition service sends an image acquisition command to the time-of-flight camera.

[0181] S517, the time-of-flight camera acquires a second image and sends the second image to the second target detection model.

[0182] S518 detects whether the second image contains a target object using a second object detection model run by the processor.

[0183] S519, if no target object is detected in the second image, the second target recognition service determines whether the number of consecutive times the target object is not detected in the second image is greater than or equal to a preset number. If the number of consecutive times the target object is not detected in the second image is greater than or equal to the preset number, proceed to S520; if the number of consecutive times the target object is not detected in the second image is less than the preset number, return to proceed to S517.

[0184] S520, the second target identification service determines that the identity authentication result has not changed.

[0185] S521, if the second image is detected to contain a target object, the second image is sent to the second target recognition model. The second target recognition model, which is run by the processor, detects whether the target object in the second image matches a preset target object and determines the identity recognition result.

[0186] S522, the second target recognition service determines whether the current identity recognition result is the same as the previous identity recognition result.

[0187] S523, if the current identity recognition result is different from the previous identity recognition result, the second target recognition service will report the current identity recognition result to the third target recognition service.

[0188] S524, the third target identification service sends the current identity recognition result to the target application.

[0189] In one embodiment of this application, if the current identity recognition result is successful (i.e., the target object in the first image matches a preset object), the target application displays the received privacy data; if the current identity recognition result is unsuccessful (i.e., the target object in the first image does not match the preset object), the target application provides a prompt regarding the received privacy data. If the current identity recognition result is the same as the previous identity recognition result (i.e., the identity recognition result remains unchanged), and if the previous identity recognition result was successful, the target application displays the received privacy data; if the previous identity recognition result was unsuccessful, the target application provides a prompt regarding the received privacy data.

[0190] Through the above embodiments of this application, the first target identification service and the second target identification service will only report the identity identification result when the identity identification result changes, thus avoiding the increase in system power consumption caused by reporting the identity identification result when the identity identification result remains unchanged.

[0191] This application also provides an electronic device 100, see reference. Figure 13 As shown, the electronic device 100 may be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR) device, virtual reality (VR) device, artificial intelligence (AI) device, wearable device, in-vehicle device, smart home device and / or smart city device. The specific type of electronic device 100 is not specifically limited in the embodiments of this application.

[0192] Electronic device 100 may include processor 110, external memory interface 120, internal memory 121, Universal Serial Bus (USB) interface 130, charging management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, and Subscriber Identification Module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0193] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0194] Processor 110 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0195] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0196] The processor 110 may also include a memory for storing instructions and data. In one embodiment of this application, the memory in the processor 110 is a cache memory. The memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instructions or data again, it can directly retrieve them from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0197] In one embodiment of this application, the processor 110 may include one or more interfaces. These interfaces may include an Inter-integrated Circuit (I2C) interface, an Inter-integrated Circuit Sound (I2S) interface, a Pulse Code Modulation (PCM) interface, a Universal Asynchronous Receiver / Transmitter (UART) interface, a Mobile Industry Processor Interface (MIPI) interface, a General-Purpose Input / Output (GPIO) interface, a Subscriber Identity Module (SIM) interface, and / or a Universal Serial Bus (USB) interface, etc.

[0198] The I2C interface is a bidirectional synchronous serial bus, including a serial data line (SDA) and a serial clock line (SCL). In one embodiment of this application, the processor 110 may include multiple I2C buses. The processor 110 can couple to the touch sensor 180K, charger, flash, camera 193, etc., through different I2C bus interfaces. For example, the processor 110 can couple to the touch sensor 180K through the I2C interface, enabling the processor 110 and the touch sensor 180K to communicate through the I2C bus interface, thereby realizing the touch function of the electronic device 100.

[0199] The I2S interface can be used for audio communication. In one embodiment of this application, the processor 110 may include multiple I2S buses. The processor 110 can be coupled to the audio module 170 via the I2S bus to realize communication between the processor 110 and the audio module 170. In one embodiment of this application, the audio module 170 can transmit audio signals to the wireless communication module 160 via the I2S interface to realize the function of answering phone calls through a Bluetooth headset.

[0200] The PCM interface can also be used for audio communication, sampling, quantizing, and encoding analog signals. In one embodiment of this application, the audio module 170 and the wireless communication module 160 can be coupled via the PCM bus interface. In another embodiment of this application, the audio module 170 can also transmit audio signals to the wireless communication module 160 via the PCM interface, enabling the function of answering phone calls through a Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.

[0201] The UART interface is a universal serial data bus used for asynchronous communication. The bus can be a bidirectional communication bus. It converts the data to be transmitted between serial and parallel communication. In one embodiment of this application, the UART interface is typically used to connect the processor 110 and the wireless communication module 160. For example, the processor 110 communicates with the Bluetooth module in the wireless communication module 160 via the UART interface to implement Bluetooth functionality. In one embodiment of this application, the audio module 170 can transmit audio signals to the wireless communication module 160 via the UART interface to enable music playback via Bluetooth headphones.

[0202] The MIPI interface can be used to connect the processor 110 to peripheral devices such as the display screen 194 and the camera 193. The MIPI interface includes a Camera Serial Interface (CSI) and a Display Serial Interface (DSI). In one embodiment of this application, the processor 110 and the camera 193 communicate via the CSI interface to realize the shooting function of the electronic device 100. The processor 110 and the display screen 194 communicate via the DSI interface to realize the display function of the electronic device 100.

[0203] The GPIO interface can be configured via software. It can be configured as a control signal or a data signal. In one embodiment of this application, the GPIO interface can be used to connect the processor 110 to a camera 193, a display screen 194, a wireless communication module 160, an audio module 170, a sensor module 180, etc. The GPIO interface can also be configured as an I2C interface, an I2S interface, a UART interface, a MIPI interface, etc.

[0204] USB port 130 is a USB standard compliant interface, specifically a Mini USB port, Micro USB port, USB Type-C port, etc. USB port 130 can be used to connect a charger to charge electronic device 100, and can also be used for data transfer between electronic device 100 and peripheral devices. It can also be used to connect headphones for audio playback. Furthermore, the interface can be used to connect other electronic devices 100, such as AR devices.

[0205] It is understood that the interface connection relationships between the modules illustrated in the embodiments of the present invention are merely illustrative and do not constitute a structural limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may also utilize different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0206] The charging management module 140 receives charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 receives charging input from the wired charger via a USB interface 130. In some wireless charging embodiments, the charging management module 140 receives wireless charging input via the wireless charging coil of the electronic device 100. While charging the battery 142, the charging management module 140 can also supply power to the electronic device 100 via the power management module 141.

[0207] The power management module 141 connects the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, providing power to the processor 110, internal memory 121, display screen 194, camera 193, and wireless communication module 160, etc. The power management module 141 can also monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance). In some other embodiments, the power management module 141 may also be located within the processor 110. In other embodiments, the power management module 141 and the charging management module 140 may be located in the same device.

[0208] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0209] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0210] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low-noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In one embodiment of this application, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In another embodiment of this application, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0211] The modem processor may include a modulator and a demodulator. The modulator modulates the low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After processing by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs sound signals through audio devices (not limited to speaker 170A, receiver 170B, etc.) or displays images or videos through the display screen 194. In one embodiment of this application, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor 110 and housed within the same device as the mobile communication module 150 or other functional modules.

[0212] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including Wireless Local Area Networks (WLANs) (such as Wireless Fidelity (Wi-Fi) networks), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), and Infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0213] In one embodiment of this application, antenna 1 of electronic device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, enabling electronic device 100 to communicate with networks and other devices via wireless communication technology. The wireless communication technology may include Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS may include the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the Beidou Navigation Satellite System (BDS), the Quasi-Zenith Satellite System (QZSS), and / or Satellite Based Augmentation Systems (SBAS).

[0214] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for face recognition, connecting the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0215] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel can utilize a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), an Active-Matrix Organic Light-Emitting Diode (AMOLED), a Flexible Light-Emitting Diode (FLED), Minied, Microled, Micro-OLED, Quantum Dot Light-Emitting Diodes (QLED), etc. In one embodiment of this application, electronic device 100 may include one or N display screens 194, where N is a positive integer greater than 1.

[0216] Electronic device 100 can perform shooting functions through ISP, camera 193, video codec, GPU, display 194 and application processor.

[0217] The ISP is used to process data fed back from the camera 193. For example, when taking a picture, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, and the camera's photosensitive element transmits the electrical signal to the ISP for processing, converting it into an image visible to the naked eye. The ISP can also perform algorithmic optimization on image noise, brightness, and skin tone. The ISP can also optimize parameters such as exposure and color temperature of the shooting scene. In one embodiment of this application, the ISP can be set in the camera 193.

[0218] Camera 193 is used to capture still images or videos. An object is projected onto a photosensitive element by generating an optical image through the lens. The photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to an ISP for conversion into a digital image signal. The ISP outputs the digital image signal to a DSP for processing. The DSP converts the digital image signal into image signals in standard RGB, YUV, or other formats. In one embodiment of this application, the electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0219] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when electronic device 100 selects a frequency, the DSP can perform Fourier transforms on the frequency energy.

[0220] Video codecs are used to compress or decompress digital video. Electronic device 100 may support one or more video codecs. Thus, electronic device 100 can play or record video in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0221] NPU stands for Neural Network (NN) computing processor. By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs enable intelligent cognitive applications in electronic devices, such as image recognition, facial recognition, speech recognition, and text understanding.

[0222] Internal memory 121 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM).

[0223] Random access memory can include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), and double data rate synchronous dynamic random-access memory (DDR SDRAM, such as fifth-generation DDR SDRAM, which is generally called DDR5 SDRAM).

[0224] Non-volatile memory can include disk storage devices and flash memory.

[0225] Flash memory can be classified according to its operating principle, including NOR FLASH, NAND FLASH, 3D NAND FLASH, etc.; according to the level of the storage cell, including single-level cell (SLC), multi-level cell (MLC), triple-level cell (TLC), quad-level cell (QLC), etc.; and according to the storage specification, including universal flash storage (UFS) and embedded multi-media card (eMMC), etc.

[0226] The random access memory can be directly read and written by the processor 110. It can be used to store executable programs (such as machine instructions) of the operating system or other running programs, as well as user and application data.

[0227] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 110.

[0228] The external memory interface 120 can be used to connect to external non-volatile memory, thereby expanding the storage capacity of the electronic device 100. The external non-volatile memory communicates with the processor 110 through the external memory interface 120 to perform data storage functions. For example, music, video, and other files can be stored in the external non-volatile memory.

[0229] Internal memory 121 or external memory interface 120 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 110. The one or more computer programs include multiple instructions, which, when executed by processor 110, can implement the screen display detection method executed on electronic device 100 in the above embodiments, so as to realize the screen display detection function of electronic device 100.

[0230] Electronic device 100 can implement audio functions, such as music playback and recording, through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0231] The audio module 170 is used to convert digital audio information into analog audio signals for output, and also to convert analog audio input into digital audio signals. The audio module 170 can also be used for encoding and decoding audio signals. In one embodiment of this application, the audio module 170 may be located in the processor 110, or some functional modules of the audio module 170 may be located in the processor 110.

[0232] The speaker 170A, also known as a "loudspeaker," is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music or make hands-free calls through the speaker 170A.

[0233] The receiver 170B, also known as the "earpiece," is used to convert audio electrical signals into sound signals. When the electronic device 100 answers a telephone call or voice message, the receiver 170B can be brought close to the ear to listen to the voice.

[0234] Microphone 170C, also known as a "microphone" or "voice transducer," is used to convert sound signals into electrical signals. When making a phone call or sending a voice message, the user can speak by bringing their mouth close to microphone 170C, inputting the sound signal into microphone 170C. Electronic device 100 may have at least one microphone 170C. In some embodiments, electronic device 100 may have two microphones 170C, which, in addition to collecting sound signals, can also perform noise reduction. In other embodiments, electronic device 100 may also have three, four, or more microphones 170C, which can collect sound signals, reduce noise, identify the sound source, and perform directional recording, etc.

[0235] The 170D headphone jack is used to connect wired headphones. The 170D headphone jack can be a USB 130 interface or a 3.5mm Open Mobile Terminal Platform (OMTP) standard interface, a CTIA (Cellular Telecommunications Industry Association of the USA) standard interface.

[0236] Buttons 190 include a power button, volume buttons, etc. Buttons 190 can be mechanical buttons or touch-sensitive buttons. Electronic device 100 can receive button input and generate key signal inputs related to user settings and function control of electronic device 100.

[0237] Motor 191 can generate vibration alerts. Motor 191 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can correspond to touch operations performed on different applications (such as taking photos, playing audio, etc.). Motor 191 can also correspond to different vibration feedback effects for touch operations performed on different areas of the display screen 194. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0238] Indicator 192 can be an indicator light, used to indicate charging status, power changes, or to indicate messages, missed calls, notifications, etc.

[0239] The SIM card interface 195 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 195 to make contact with and separate from the electronic device 100. The electronic device 100 can support one or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc. Multiple cards can be inserted into the same SIM card interface 195 simultaneously. The multiple cards can be of the same or different types. The SIM card interface 195 is also compatible with different types of SIM cards. The SIM card interface 195 is also compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to realize functions such as calls and data communication. In one embodiment of this application, the electronic device 100 utilizes an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100. This application also provides a computer storage medium storing computer instructions. When the computer instructions are executed on the electronic device 100, the electronic device 100 performs the aforementioned related method steps to implement the privacy protection method in the above embodiments.

[0240] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the privacy protection method described in the above embodiments.

[0241] In addition, embodiments of this application also provide an apparatus, which may specifically be a chip, component or module. The apparatus may include a connected processor and a memory; wherein the memory is used to store computer execution instructions, and when the apparatus is running, the processor may execute the computer execution instructions stored in the memory to cause the chip to execute the privacy protection methods in the above-described method embodiments.

[0242] In this embodiment, the electronic device, computer storage medium, computer program product or chip are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding method provided above, and will not be repeated here.

[0243] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0244] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0245] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0246] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0247] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0248] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A privacy protection method applied to electronic devices, characterized in that, The method includes: Detect the ambient light level of the environment in which the electronic device is located; If the ambient light brightness is greater than or equal to a preset value, control the low-power camera to capture the first image; The first target detection model, which runs on a low-power chip, is invoked to detect whether the first image contains a target object. If a target object is detected in the first image, the first target recognition model running on the low-power chip is invoked to detect whether the target object in the first image matches a preset target object. If the target object in the first image does not match the preset target object, the privacy data received by the electronic device is responded to by prompting the privacy data using a preset notification method; If a target object is detected in the first image, and the frame rate of the target object in the first image is greater than or equal to a preset frame rate, the privacy data is displayed or prompted using the preset notification method based on the previous user identification result.

2. The privacy preserving method of claim 1, wherein, The method of notifying the user of the privacy data using the preset notification method includes: If the target object in the first image does not match the preset target object, the first target recognition service of the kernel layer of the electronic device will report the user identity recognition failure result to the second target recognition service of the hardware abstraction layer of the electronic device. The second target identification service reports the result of the user identity recognition failure to the third target identification service in the application layer of the electronic device; The third target identification service sends the result of the user identification failure to the target application that received the privacy data. The target application then uses the preset notification method to notify the privacy data based on the result of the user identification failure.

3. The privacy preserving method of claim 2, wherein, The method of notifying the user of the privacy data using the preset notification method further includes: If the target object in the first image does not match the preset target object, the first target recognition service will compare the result of the failed user identity recognition with the result of the previous user identity recognition. If the previous user identification result was a failure, the target application will notify the user of the privacy data using the preset notification method based on the previous user identification result.

4. The privacy preserving method of claim 3, wherein, The method of notifying the user of the privacy data using the preset notification method further includes: If the previous user identification result was successful, the first target identification service will report the user identification failure result to the second target identification service.

5. The privacy preserving method of claim 1, wherein, The method further includes: If the target object in the first image matches the preset target object, the privacy data received by the electronic device is displayed using the preset notification method.

6. The privacy preserving method of claim 5, wherein, The method further includes: If the frame rate of the first image containing the target object is greater than or equal to the preset frame rate, determine whether the number of the target object in the first image has not changed. If the number of target objects in the first image remains unchanged, the privacy data is displayed or prompted using the preset notification method based on the previous user identification result.

7. The privacy preserving method of claim 5, wherein, The method of displaying the privacy data using a preset notification method includes: If the target object in the first image matches the preset target object, the first target recognition service of the kernel layer of the electronic device will report the successful user identification result to the second target recognition service of the hardware abstraction layer of the electronic device. The second target recognition service reports the successful user identification result to the third target recognition service in the application layer of the electronic device; The third target identification service sends the result of successful user identification to the target application, and the target application displays the privacy data according to the result of successful user identification using the preset notification method.

8. The privacy preserving method of claim 7, wherein, The method of displaying the privacy data using a preset notification method includes: If the target object in the first image matches the preset target object, the first target recognition service compares the successful user identification result with the previous user identification result. If the previous user identification result was successful, the target application displays the privacy data using the preset notification method based on the previous user identification result.

9. The privacy protection method as described in claim 7, characterized in that, The method of displaying the privacy data using a preset notification method includes: If the target object in the first image matches the preset target object, the first target recognition service compares the successful user identification result with the previous user identification result. If the previous user identification result was a failure, the first target identification service will report the successful user identification result to the second target identification service.

10. The privacy protection method as described in claim 1, characterized in that, The step of calling the first target detection model running on the low-power chip to detect whether the first image contains a target object includes: The target features in the first image are detected using the first target detection model; If the target feature is not detected in the first image, it is determined that the first image does not contain the target object; or If the target feature is detected in the first image, it is determined that the first image contains the target object.

11. The privacy protection method as described in claim 1, characterized in that, The step of calling the first target recognition model running on the low-power chip to detect whether the target object in the first image matches a preset target object includes: The first feature vector of the first image is extracted using the first target recognition model; Calculate the similarity between the first feature vector of the first image and the second feature vector of the preset target object; If the similarity between the first feature vector of the first image and the second feature vector of the preset target object is greater than or equal to a preset similarity threshold, it is determined that the target object in the first image matches the preset target object; or If the similarity between the first feature vector of the first image and the second feature vector of the preset target object is less than the preset similarity threshold, it is determined that the target object in the first image does not match the preset target object.

12. The privacy protection method as described in claim 1, characterized in that, The preset notification methods include pop-up display, notification information bar display, and lock screen display.

13. The privacy protection method as described in claim 1, characterized in that, The method further includes: If the target object in the first image does not match the preset target object, respond to the access request to the application and determine whether the application is a privacy application; If the application is a privacy application, do not respond to the access request; or If the application is not a privacy application, determine whether the application contains privacy data; If the application contains private data, hide the private data.

14. The privacy protection method as described in claim 1, characterized in that, The method further includes: If the target object in the first image does not match the preset target object, operations on the privacy data are prohibited.

15. The privacy protection method as described in claim 1, characterized in that, The method further includes: If the ambient light intensity is less than the preset value, control the time-of-flight camera to acquire a second image; The second object detection model, run by the processor, is invoked to detect whether the second image contains the target object; If the target object is detected in the second image, the second target recognition model run by the processor is invoked to detect whether the target object in the second image matches the preset target object; If the target object in the second image is detected to be inconsistent with the preset target object, the privacy data received by the electronic device is responded to by prompting the privacy data using the preset notification method.

16. The privacy protection method as described in claim 15, characterized in that, The method further includes: If the target object in the second image matches the preset target object, the privacy data is displayed using the preset notification method.

17. The privacy protection method as described in claim 1, characterized in that, Both the first target detection model and the first target recognition model use low-power model parameters, which include operator type, number of channels, quantization method, parameter storage bits, feature map bits, number of feature vectors, and data type.

18. An electronic device, characterized in that, The electronic device includes a memory and a processor: The memory is used to store program instructions; The processor is configured to read and execute the program instructions stored in the memory, and when the program instructions are executed by the processor, cause the electronic device to perform the privacy protection method as described in any one of claims 1 to 17.

19. A chip coupled to a memory in an electronic device, characterized in that, The chip is used to control the electronic device to perform the privacy protection method as described in any one of claims 1 to 17.

20. A computer storage medium, characterized in that, The computer storage medium stores program instructions that, when executed on an electronic device, cause the processor of the electronic device to perform the privacy protection method as described in any one of claims 1 to 17.

Images