Equipment management method and device, electronic equipment and chip

Abstract

The invention provides an equipment management method and device, electronic equipment and a chip, and relates to the field of equipment management. The method comprises the steps that a target image recognition model is used for recognizing a target image according to position information between electronic equipment and target equipment in the target image so as to determine whether the target equipment is first equipment or not, and the target image recognition model is used for recognizing the first equipment. According to the scheme, the target image is recognized by using the target image recognition model based on the target image and the position information between the electronic equipment and the target equipment, so that not only are model training and model reasoning of the end side realized, but also the accuracy of the image recognition result is improved, and the convenience and accuracy of equipment management are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of device management, and in particular, to a device management method, apparatus, electronic device, and chip. Background Art

[0002] With the popularization of intelligent terminal devices and the development of the device management field, users increasingly pursue accurate, convenient, and personalized control experiences. As an important direction in the device management field, when the image recognition model is inaccurate, it is necessary to make decisions by combining the relative position relationship and distance between the electronic device and the first device in the image frame. Therefore, a device management method that can effectively solve the above problems is needed. Summary of the Invention

[0003] The present disclosure provides a device management method, apparatus, electronic device, and chip.

[0004] In a first aspect embodiment of the present disclosure, a device management method is proposed. The method includes: using a target image recognition model to recognize a target image according to the position information between the electronic device and the target device in the target image, so as to determine whether the target device is a first device, and the target image recognition model is used to recognize the first device.

[0005] In some embodiments, the method further includes: determining a training data set, where the training data set includes multiple frames of training images and training parameters corresponding to each frame of training image. Each frame of training image includes the first device, and the training parameters include the position information between the electronic device and the first device; using the training data set to train the image recognition model to obtain the target image recognition model.

[0006] In some embodiments, the method further includes: obtaining multiple frames of original images collected by an image acquisition component, where the multiple frames of original images include multiple frames of training images; obtaining the morphological features of the electronic device when each frame of original image is collected through a sensor component, where the morphological features are used to determine the relative position relationship, and the morphological features include the rotation angle of the electronic device in at least one direction; obtaining the distance between the electronic device and the first device when each frame of original image is collected through a short-range communication component.

[0007] In some embodiments, using the target image recognition model to recognize the target image according to the position information between the electronic device and the target device in the target image includes: recognizing the image features of the target device through the target image recognition model; determining the device identifier of the target device according to the image features and the position information between the electronic device and the target device in the target image, where the position information includes the relative position relationship and the distance; in the case where the device identifier of the target device matches the device identifier of the first device, determining that the target device is the first device, and notifying the electronic device to display the control interface corresponding to the first device.

[0008] In some embodiments, using a target image recognition model to recognize a target image based on the position information between an electronic device and a target device in the target image includes: recognizing the image features of the target device through the target image recognition model; determining the device identifier of the target device according to the image features, and verifying the device identifier through the position information; in the case where the device identifier of the target device does not match the device identifier of the first device, determining that the target device is not the first device, and notifying the electronic device to display a prompt message.

[0009] In some embodiments, the method further includes: determining a test data set from multiple frames of original images, the test data set including multiple frames of test images; using the test data set to test the target image recognition model.

[0010] In some embodiments, the method further includes: in the case where the test accuracy of the target image recognition model is greater than or equal to the accuracy threshold, notifying the electronic device to display an addition confirmation window, and the addition confirmation window is used to prompt the user whether to add the binding relationship between the target image recognition model and the first device.

[0011] In some embodiments, the method further includes: in the case where the test accuracy of the target image recognition model is less than the accuracy threshold, notifying the electronic device to display a training failure message, and notifying the electronic device to delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image from the first storage space.

[0012] In some embodiments, the method further includes: in the case where the target device in the target image is determined to be the first device, if a correction instruction from the user is received, updating the target image recognition model, where the correction instruction is used to correct the target device being the first device to the target device being the second device.

[0013] An embodiment of the second aspect of the present disclosure proposes a device management method, the method including: the method according to any one of the methods in the embodiment of the first aspect of the present disclosure; controlling a target device.

[0014] In some embodiments, controlling the target device includes: in the case where the target device is the first device, automatically displaying the control interface corresponding to the first device; controlling the target device through the control interface.

[0015] In some embodiments, controlling the target device includes: in the case where the target device is the first device and a first gesture control instruction is obtained, displaying the control interface corresponding to the first device, and the first gesture control instruction is used to indicate displaying the control interface corresponding to the first device; controlling the target device through the control interface.

[0016] In some embodiments, the method further includes: displaying an addition confirmation window; receiving an addition instruction from the user to add a binding relationship between the target image recognition model and the first device.

[0017] In some embodiments, the method further includes: displaying an addition confirmation window; deleting multiple frames of training images and the morphological features and distances corresponding to each frame of training image in the case where an addition instruction from the user is not received.

[0018] In some embodiments, the method further includes: storing multiple frames of original images in a first storage space of the electronic device, and storing the morphological features and distances corresponding to the multiple frames of original images.

[0019] An embodiment of the third aspect of the present disclosure provides a device management apparatus, the apparatus includes: an identification unit, configured to use a target image recognition model to identify a target image according to the position information between the electronic device and the target device in the target image, so as to determine whether the target device is the first device, and the target image recognition model is used to identify the first device.

[0020] An embodiment of the fourth aspect of the present disclosure provides a device management apparatus, the apparatus includes: the apparatus provided in the embodiment of the third aspect of the present disclosure; and a control unit, configured to control the target device.

[0021] An embodiment of the fifth aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the embodiment of the second aspect of the present disclosure.

[0022] An embodiment of the sixth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described in the embodiment of the first aspect of the present disclosure, or execute the method described in the embodiment of the second aspect of the present disclosure.

[0023] An embodiment of the seventh aspect of the present disclosure provides a chip, the chip includes one or more interfaces and one or more processors; the interfaces are configured to receive signals from a memory of the electronic device and send the signals to the processors, the signals include computer instructions stored in the memory, and when the processors execute the computer instructions, the electronic device is caused to execute the method described in the embodiment of the first aspect of the present disclosure.

[0024] In summary, according to the device management method proposed in the present disclosure, the method includes: the SOC chip uses a target image recognition model to recognize a target image based on the position information between the electronic device and the target device in the target image, so as to determine whether the target device is a first device, and the target image recognition model is used to recognize the first device. Control the target device through the electronic device. The solution of the present disclosure is based on the target image and the position information between the electronic device and the target device. The SOC chip uses the target image recognition model to recognize the target image, combines the position information between the electronic device and the target device, determines whether the target device in the target image is a first device, and controls the target device through the electronic device. It not only realizes model training and model inference on the edge side, but also improves the accuracy of image recognition results, thereby enhancing the convenience and accuracy of device management.

[0025] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure and do not constitute an undue limitation to the present disclosure.

[0027] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0028] Figure 2 It is a flowchart of a device management method provided by an embodiment of the present disclosure;

[0029] Figure 3 It is a flowchart of another device management method provided by an embodiment of the present disclosure;

[0030] Figure 4 It is a flowchart of yet another device management method provided by an embodiment of the present disclosure;

[0031] Figure 5 It is a flowchart of still another device management method provided by an embodiment of the present disclosure;

[0032] Figure 6 It is a flowchart of another device management method provided by an embodiment of the present disclosure;

[0033] Figure 7 It is a flowchart of still another device management method provided by an embodiment of the present disclosure;

[0034] Figure 8 It is a flowchart of another device management method provided by an embodiment of the present disclosure;

[0035] Figure 9Flowchart of yet another device management method provided by an embodiment of the present disclosure;

[0036] Figure 10 Flowchart of another device management method provided by an embodiment of the present disclosure;

[0037] Figure 11 Schematic flowchart of a device management method provided by an application example of the present disclosure;

[0038] Figure 12 Schematic structural diagram of a device management apparatus provided by an embodiment of the present disclosure;

[0039] Figure 13 Schematic structural diagram of yet another device management apparatus provided by an embodiment of the present disclosure;

[0040] Figure 14 Schematic structural diagram of an electronic device provided by an embodiment of the present disclosure;

[0041] Figure 15 Schematic structural diagram of a chip provided by an embodiment of the present disclosure. Detailed implementation manners

[0042] The embodiments of the present disclosure will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0043] With the popularization of intelligent terminal devices and the development of the device management field, users are increasingly pursuing accurate, convenient, and personalized control experiences. As an important direction in the device management field, when the image recognition model is inaccurate, it is necessary to make decisions by combining the relative position relationship and distance between the electronic device and the first device in the image frame. Therefore, a device management method that can effectively solve the above problems is needed.

[0044] Therefore, to solve the problems existing in the related art, the present disclosure proposes a device management solution. By using the target image recognition model to recognize the target image based on the target image and the position information between the electronic device and the target device, the accuracy of the image recognition result is improved, thereby enhancing the convenience and accuracy of device management.

[0045] Before introducing the detailed solution of the present disclosure, the application scenario to which the present disclosure solution is applied will be described. Figure 1 It is a diagram of the application scenario of the device management method in an embodiment. As Figure 1As shown, in this application scenario, there is an electronic device 104. A camera module can be installed in the electronic device 104, and several application programs can also be installed. The application program can initiate an image acquisition instruction to acquire an image, and the camera module acquires the image 102. Among them, the camera module can include a front camera module and / or a rear camera module. Finally, the target image is sent to the target application program. The electronic device 104 can be a smart phone, a tablet computer, a personal digital assistant, a wearable device, etc.

[0046] In some embodiments, this application scenario can be places such as a home, a nursing home, etc. For example, in a home, a user can control the smart device switch through gestures, and can also remotely control the switch of the light, adjust the temperature, open the curtain, etc. through the control panel interface of the corresponding APP. In a nursing home or a hospital, the elderly or the physically disabled can perform remote operations through gestures and a camera. For example, knocking on the mobile phone can be used to turn on the TV, etc.

[0047] In some alternative embodiments, the above-mentioned electronic device can also be a vehicle-mounted device or a vehicle networking device, such as a smart car, etc. In this disclosure, only a smart phone is taken as an example, but it does not represent a limitation on the scope of this disclosure.

[0048] A camera can be installed on the electronic device, and an image is acquired through the installed camera. The camera can be classified into types such as a laser camera and a visible light camera according to the different acquired images. The laser camera can acquire an image formed by laser irradiating an object, and the visible light image can acquire an image formed by visible light irradiating an object. Several cameras can be installed on the electronic device, and the installation positions are not limited. For example, a camera can be installed on the front panel of the electronic device, and two cameras can be installed on the back panel. The camera can also be installed inside the electronic device in an embedded manner, and then the camera is opened by rotating or sliding. Specifically, a front camera and a rear camera can be installed on the electronic device. The front camera and the rear camera can acquire images from different perspectives. Generally, the front camera can acquire an image from the front perspective of the electronic device, and the rear camera can acquire an image from the back perspective of the electronic device.

[0049] It should be understood that in this disclosure, the front camera or the rear camera is only used as an example to distinguish the shooting angles of different cameras, rather than a limitation on the functions of multiple cameras. Multiple cameras in this disclosure can all be rear cameras or all be front cameras at the same time, which is not limited in this disclosure.

[0050] An electronic device can have several application programs. An application program refers to the software written for a certain application purpose in the electronic device. The electronic device can provide services to meet user needs through the application program. When an application program needs to capture an image, it will initiate an image capture instruction, and the electronic device will call the camera module according to the image capture instruction to capture the image. The image capture instruction is an instruction used to trigger the image capture operation.

[0051] A processor is also provided in the electronic device. The device management module in the processor can perform device management on the images captured by the camera module. For example, it can execute the device management method provided in the present disclosure.

[0052] Figure 2 The flowchart of a device management method provided in an embodiment of the present disclosure is shown. This method can be applicable to Figure 1 the application scenarios shown. For example, it can be executed by an electronic device, which can be a terminal integrated with device management functions. This method can also be executed by the device management system in the terminal, or by other systems suitable for device management. The present disclosure does not limit this. Optionally, the electronic device can be a mobile terminal (such as a mobile phone, a wearable device, etc.), an intelligent manufacturing device (such as an automated robotic arm, a 3D printer, etc.), a medical device (such as), an IoT device, a smart home device (such as a sweeping robot, a smart doorbell, etc.).

[0053] As Figure 2 shown, the device management method includes:

[0054] Step 201: Use a target image recognition model to identify the target image according to the position information between the electronic device and the target device in the target image, so as to determine whether the target device is a first device.

[0055] In some embodiments, the target image recognition model is used to identify the first device.

[0056] In some embodiments, the target image is input into the target image recognition model to identify the target device in the target image, and then compare whether the target device matches the first device, so as to determine whether the target device is a first device.

[0057] Figure 3 The flowchart of a device management method proposed by the present disclosure is further shown. Based on the above embodiments, the method may further include the following steps.

[0058] Step 301: Determine the training data set.

[0059] In some embodiments, the training data set includes multiple frames of training images and the training parameters corresponding to each frame of training image.

[0060] In some embodiments, each training image frame includes a first device, and the training parameters include the position information between the electronic device and the first device.

[0061] In some embodiments, the first device in each training image frame can be one or more.

[0062] In some embodiments, the first device is a device that the user wants to control, which can be a smart home device, a medical device, a smart manufacturing device, etc. Optionally, the first device can be a device that the user expects to be recognized by the electronic device.

[0063] In some embodiments, the multi-frame training images can be consecutive multi-frame images, i.e., a video, or can be independent multi-frame images, i.e., multiple static images. The multi-frame training images can be images of the first device taken from different angles and distances.

[0064] In some embodiments, the multi-frame training images should include various angles, lighting conditions, and background environments of the first device.

[0065] Step 302: Use the training data set to train the image recognition model to obtain a target image recognition model.

[0066] In some embodiments, the image recognition model can automatically extract features from the input training images and classify them into different categories.

[0067] In some embodiments, the image recognition model is an image recognition model pre-trained with a large amount of data.

[0068] In some embodiments, the above-mentioned pre-trained image recognition models include, but are not limited to, VGG16 and ResNet models.

[0069] In some embodiments, the pre-trained image recognition model is trained on a specified data set to make the model better adapt to a specific task. For example, using multi-frame training images of the first device taken from different angles and distances as training data to train the image recognition model, the target image recognition model can recognize the first device from different angles or distances, improving the recognition accuracy of the first device.

[0070] In some embodiments, the image recognition model is a neural network model.

[0071] In some embodiments, the neural network model provides a pre-trained backbone network.

[0072] In some embodiments, the ResNet structure can be used as the backbone network of the neural network model.

[0073] In some embodiments, meta-learning and few-shot learning strategies can be used on the edge side to quickly fine-tune a neural network model to provide a personalized experience.

[0074] In some embodiments, the meta-learning strategy can use the meta-update strategy of Model-Agnostic Meta-Learning (abbreviated as MAML) or Reptile.

[0075] In some embodiments, the neural network model provides a pre-trained backbone network. Using few-shot learning during formal training can accelerate the training speed and save computing resources.

[0076] In some embodiments, the neural network model can be a Convolutional Neural Network (CNN) or a Recurrent Neural Network (RNN).

[0077] In summary, according to the device management method of the present disclosure, the method includes: determining a training data set, where the training data set includes multiple frames of training images and training parameters corresponding to each frame of training image. Each frame of training image includes a first device, and the training parameters include the position information between the electronic device and the target device; using the training data set to train an image recognition model to obtain a target image recognition model; using the target image recognition model to recognize a target image according to the position information between the electronic device and the target device in the target image to determine whether the target device is the first device. The target image recognition model is used to recognize the first device. The solution of the present disclosure determines the training data set based on multiple frames of training images and the position information between the electronic device and the first device; then uses the training data set to train the image recognition model, and finally uses the target image recognition model to recognize the target image, which not only realizes the integration of model training and model inference on the edge side, but also improves the accuracy of the image recognition result, thereby enhancing the convenience and accuracy of device management.

[0078] Figure 4 Further shows a flowchart of a device management method proposed by the present disclosure. Based on Figure 3 the embodiments shown, the method further includes the following steps. Specifically, before performing step 301, the method further includes the following steps.

[0079] Step 401, obtain multiple frames of original images collected by an image acquisition component.

[0080] In some embodiments, a series of original images continuously captured by the image acquisition component are obtained. These original images can be multiple consecutive frames of original images or multiple independent frames of original images.

[0081] In some embodiments, the image acquisition component includes an image acquisition card, an image acquisition device, image acquisition software, and a storage device. Specifically, the image acquisition card is used to receive image data and convert it into a form that can be understood by a computer. The image acquisition device refers to a device that can capture images, such as a digital camera, a scanner, a webcam, etc. The image acquisition software is used to control the image acquisition device and acquire image data. The storage device is used to save the image data acquired from the image acquisition device. Common storage devices include hard disks, flash drives, memory cards, etc.

[0082] In some embodiments, the multi-frame original images include multi-frame training images. In other words, the multi-frame training images can be part or all of the multi-frame original images. The multi-frame training images can be selected from the multi-frame original images according to specific screening rules. For example, there may be some images in the multi-frame original images that do not include the first device. Then, these images that do not include the first device can be excluded, and the remaining images that can clearly show the first device can be used as training images.

[0083] Step 402: Obtain the morphological features of the electronic device when each frame of the original image is acquired through the sensor component.

[0084] In some embodiments, while acquiring each frame of the original image, the morphological features of the electronic device are obtained from multiple sensors.

[0085] In some embodiments, the morphological features are used to determine the relative position relationship, and the morphological features include the rotation angles of the electronic device in at least one direction.

[0086] In some embodiments, the rotation angle of the electronic device in at least one direction refers to the rotation angle of the electronic device relative to a certain reference system (such as the ground coordinate system).

[0087] In some embodiments, assume that we have a smartphone equipped with a gyroscope and an accelerometer. The gyroscope and the accelerometer will continuously monitor the posture changes of the phone (i.e., the rotation angle and the moving distance), which can help the system determine the angle and direction of the user's phone.

[0088] Exemplarily, there may be a corresponding relationship between each frame of the original image and the morphological features of the electronic device. For example, when the first frame of the original image is acquired, the form of the electronic device is in the vertical direction and has an angle of 45° with the front of the first device; when the nth frame of the image is acquired, the form of the electronic device is at an angle of 30° with the horizontal plane and is facing the front of the first device.

[0089] Step 403: Obtain the distance between the electronic device and the first device when each frame of the original image is acquired through the short-range communication component.

[0090] In some embodiments, while acquiring each frame of the original image, the distance between the electronic device and the first device is acquired through the short-range communication component.

[0091] In some embodiments, the short-range communication component is a technology that allows short-range wireless communication between electronic devices. Common short-range communication components include Bluetooth, WIFI, and UWB, etc.

[0092] In summary, according to the device management method of the present disclosure, the method includes: acquiring multiple frames of original images collected by the image acquisition component, where the multiple frames of original images include multiple frames of training images; acquiring the morphological features of the electronic device when each frame of the original image is collected through the sensor component, where the morphological features are used to determine the relative position relationship, and the morphological features include the rotation angles of the electronic device in at least one direction; acquiring the distance between the electronic device and the first device when each frame of the original image is collected through the short-range communication component. This solution acquires the morphological features of the electronic device and the distance between the electronic device and the first device while acquiring each frame of the original image, and then determines the distance and relative angular position of the target device to be controlled, effectively solving the problem of low accuracy in multi-device selection in a complex environment.

[0093] Figure 5 Further shows a flowchart of a device management method proposed by the present disclosure. Based on Figure 2 、 Figure 3 or Figure 4 The embodiments shown, step 201 is further described, including the following steps.

[0094] Step 501, identify the image features of the target device through the target image recognition model.

[0095] In some embodiments, the image features refer to the signs in the image that can represent its content and attributes, and are usually used to identify and compare different images. Such as the content of the image, the shooting angle, and the distance between the electronic device and the target device.

[0096] In some embodiments, the device identifier refers to the unique features in a device image that can be used to distinguish different device types or brands.

[0097] In some embodiments, the image of the target device is input into the target image recognition model to obtain the image features of the target device, and then the type or brand of the target device is determined according to the image features of the target device.

[0098] Step 502, determine the device identifier of the target device according to the image features, and verify the device identifier through the location information.

[0099] In some embodiments, by comparing the device identifier of the target device with that of the first device, if the two device identifiers match, it can be determined that the target device is the first device.

[0100] Step 503, in the case where the device identifier of the target device does not match that of the first device, determine that the target device is not the first device, and notify the electronic device to display a prompt message.

[0101] In some embodiments, by comparing the device identifier of the target device with that of the first device, if the two device identifiers do not match, it is considered that the target device is not the first device. At this time, display information to prompt other devices.

[0102] In summary, according to the device management method proposed by the present disclosure, the method includes: identifying the image features of the target device through a target image recognition model; determining the device identifier of the target device according to the image features, and verifying the device identifier through the location information; in the case where the device identifier of the target device does not match that of the first device, determine that the target device is not the first device, and notify the electronic device to display a prompt message. The solution of the present disclosure identifies the image features of the target device through the target image recognition model, and then determines the device identifier of the target device; and matches the device identifier of the target device with the image identifier of the first device, and then determines whether the target device is the first device. It improves the recognition efficiency of the target device image and lays a foundation for subsequent device management.

[0103] Figure 6 Further shows a flowchart of a device management method proposed by the present disclosure. Based on Figure 4 the embodiments shown, further explain this method, Figure 4 the embodiments shown may further include the following steps.

[0104] Step 601, determine a test data set from multiple frames of original images.

[0105] In some embodiments, the test data set and the training data set may be derived from different original data sets. For example, the user can shoot two videos as the training data set and the test data set respectively.

[0106] Optionally, in some embodiments, the test data set and the training data set may be derived from the same original data set. For example, the user can shoot a video to train and test the model at the same time.

[0107] In some embodiments, the test data set includes multiple frames of test images and test parameters corresponding to the multiple frames of test images.

[0108] In some embodiments, each frame of test image includes the first device, and the test parameters include the relative position relationship and distance between the electronic device and the first device.

[0109] In some embodiments, there may be one or more first devices in each frame of test images.

[0110] In some embodiments, the multi-frame test images may be consecutive multi-frame images, i.e., a video, or mutually independent multi-frame images, i.e., multiple static images.

[0111] In some embodiments, the multi-frame test images should include various angles, lighting conditions, and background environments of the first device.

[0112] Step 602: Use the test data set to test the target image recognition model.

[0113] In some embodiments, the target image recognition model refers to an image recognition model trained with a training data set.

[0114] In some embodiments, use the target image recognition model to test the test data set to obtain the image features of the devices in the multi-frame test images in the test data set, and then determine the device identifiers of the devices in the multi-frame test images.

[0115] In summary, according to the device management method proposed by the present disclosure, the method includes: determining a test data set from multi-frame original images, where the test data set includes multi-frame test images; using the test data set to test the target image recognition model. The solution of the present disclosure reduces the number of user operations by determining the test data set from the same original image data set and testing the target image recognition model, thereby further improving the convenience of device management.

[0116] Figure 7 Further shows a flowchart of a device management method proposed by the present disclosure. Based on Figure 6 the embodiments shown, further explain the method, Figure 6 the embodiments shown may further include the following steps.

[0117] Step 701: When the test accuracy of the target image recognition model is greater than or equal to the accuracy threshold, notify the electronic device to display an addition confirmation window.

[0118] In some embodiments, the addition confirmation window is used to prompt the user whether to add the binding relationship between the target image recognition model and the first device.

[0119] In some embodiments, the test accuracy of the target image recognition model is the ratio of the number of test images correctly recognized to the total number of images in the test data set.

[0120] In some embodiments, the accuracy threshold can be set according to the actual needs of the user or summarized from relevant literature.

[0121] Step 702, when the test accuracy of the target image recognition model is less than the accuracy threshold, notify the electronic device to display a training failure message and notify the electronic device to delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image from the first storage space.

[0122] In summary, according to the device management method proposed by the present disclosure, the method includes: when the test accuracy of the target image recognition model is greater than or equal to the accuracy threshold, notify the electronic device to display an addition confirmation window, and the addition confirmation window is used to prompt the user whether to add the binding relationship between the target image recognition model and the first device. When the test accuracy of the target image recognition model is less than the accuracy threshold, notify the electronic device to display a training failure message, and notify the electronic device to delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image from the first storage space. The method of the present disclosure controls the test accuracy, retains the image recognition model with high test accuracy, and further improves the accuracy of device management.

[0123] In some embodiments, the method may further include: when it is determined that the target device in the target image is the first device, if a correction instruction from the user is received, update the target image recognition model.

[0124] In some embodiments, the target image recognition model determines that the target device in the target image is the first device, but the user finds that the recognition result is inaccurate. At this time, the user can directly feedback through the electronic device that the model recognition is inaccurate, and then the image recognition model can be updated.

[0125] In some embodiments, the image recognition model can be updated by re-obtaining the original multiple frames of images and the morphological features and distances corresponding to the multiple frames of training images; or the image recognition model can be updated by re-dividing the ratio of the training data set and the test data set.

[0126] In some embodiments, the correction instruction is used to correct the target device from the first device to the second device.

[0127] In summary, according to the device management method proposed by the present disclosure, the method includes: when it is determined that the target device in the target image is the first device, if a correction instruction from the user is received, update the image recognition model, where the correction instruction is used to correct the target device from the first device to the second device. The method of the present disclosure updates the image recognition model by receiving the correction instruction from the user to improve the accuracy of the image recognition model, thereby further improving the quality of device management.

[0128] This embodiment includes the above Figures 2 - 7 In addition to the method steps, it further includes:

[0129] Step 801: Control the target device.

[0130] Figure 9 Further shows a flowchart of a device management method proposed by the present disclosure. Based on the above embodiments, the method may further include the following steps.

[0131] Step 901, when the target device is the first device, automatically display the control interface corresponding to the first device; or, when the target device is the first device and a first gesture control instruction is obtained, display the control interface corresponding to the first device;

[0132] In some embodiments, the control interface is a graphical interface that allows the user to control a certain function.

[0133] In some embodiments, the control interface corresponding to the first device refers to an interface through which the user can control the first device.

[0134] In some embodiments, the first gesture control instruction is used to indicate the display of the control interface corresponding to the first device.

[0135] In some embodiments, the first gesture control instruction refers to an operation method of controlling a device by using a person's hand movement.

[0136] In some embodiments, when the target device is the first device, automatically displaying the control interface corresponding to the first device can reduce the number of interactions between the user and the electronic device.

[0137] In some embodiments, when the target device is the first device and a first gesture control instruction is obtained, displaying the control interface corresponding to the first device can effectively prevent the situation of mis-scanning, that is, prevent the user from accidentally scanning a device and automatically opening the control interface corresponding to the device.

[0138] In some embodiments, when the target device is the first device, automatically displaying the control interface corresponding to the first device saves multiple steps in traditional operations and effectively improves the operation efficiency.

[0139] Step 902, control the target device through the control interface.

[0140] In some embodiments, the user can control the target device through the control interface to achieve a specific function.

[0141] In summary, according to the device management method proposed by the present disclosure, the method includes: when the target device is the first device, automatically displaying the control interface corresponding to the first device; or, when the target device is the first device and a first gesture control instruction is obtained, displaying the control interface corresponding to the first device, where the first gesture control instruction is used to indicate the display of the control interface corresponding to the first device; and controlling the target device through the control interface. The method of the present disclosure realizes the automatic display of the control interface corresponding to the first device through two triggering methods, so as to improve the convenience and accuracy of device management.

[0142] Figure 10 Further shows the flowchart of a device management method proposed by the present disclosure. Based on Figure 8 the embodiments shown, further explain this method, Figure 8 the embodiments shown may further include the following steps.

[0143] Step 1001, display an addition confirmation window.

[0144] Step 1002, receive the user's addition instruction to add the binding relationship between the target image recognition model and the first device.

[0145] Step 1003, in the case where the user's addition instruction is not received, delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image.

[0146] In summary, according to the device management method proposed by the present disclosure, the method includes: displaying an addition confirmation window; receiving the user's addition instruction to add the binding relationship between the target image recognition model and the first device; in the case where the user's addition instruction is not received, deleting multiple frames of training images and the morphological features and distances corresponding to multiple frames of training images. The method of the present disclosure obtains the user's instruction through the confirmation addition window, and deletes multiple frames of training images and the morphological features and distances corresponding to multiple frames of training images from the first storage space in the case where the addition instruction is not received, reducing the system space occupancy and further improving the device management quality.

[0147] In some embodiments, the method further includes: storing multiple frames of original images in the first storage space of the electronic device, and storing the morphological features and distances corresponding to the multiple frames of original images.

[0148] The solution of the present disclosure is based on the target image and the position information between the electronic device and the target device. The SOC chip uses the training data set to train the image recognition model. Finally, the target image recognition model is used to recognize the target image, and in combination with the position information between the electronic device and the target device, it is determined whether the target device in the target image is the first device, and the target device is controlled through the electronic device. The accuracy of the image recognition result is improved, thereby enhancing the convenience and accuracy of device management.

[0149] Therefore, the present solution has the following beneficial effects:

[0150] 1. Based on multiple frames of training images and the position information between the electronic device and the target device, a training data set is determined; then the training data set is used to train an image recognition model, and finally the target image recognition model is used to recognize the target image, improving the accuracy of the image recognition result, thereby enhancing the convenience and accuracy of device management.

[0151] 2. By obtaining the morphological features of the electronic device and the distance between the electronic device and the first device while acquiring each frame of the original image, the distance and relative angular position of the target device to be controlled are further determined, effectively solving the problem of low accuracy in multi-device selection in a complex environment.

[0152] 3. The image features of the target device are recognized through the target image recognition model, and then the device identifier of the target device is determined; and the device identifier of the target device is matched with the image identifier of the first device, and then it is determined whether the target device is the first device. The recognition efficiency of the target device image is improved, and a foundation is laid for subsequent device management.

[0153] 4. Through two triggering methods, the control interface corresponding to the first device is automatically displayed, the test data set is determined from the same original image data set, the target image recognition model is tested, and the target image recognition model with high test accuracy is retained, reducing the number of user operations, thereby further improving the convenience and accuracy of device management.

[0154] 5. Through the confirmation addition window, user instructions are obtained, and in the case where no addition instruction is received, multiple frames of training images and the morphological features and distances corresponding to each frame of training image are deleted from the first storage space, reducing the system space occupancy and further improving the device management quality.

[0155] 6. The method in the present disclosure is based on image recognition and does not rely on voice input, so the risk of noise interference can be effectively avoided.

[0156] 7. The method in the present disclosure allows the user to create and set exclusive gesture controls on the control interface corresponding to the first device according to their own needs and habits, making the device operation more intuitive and personalized, and further enhancing the user's operation experience.

[0157] 8. In the present disclosure, the relative position and distance data between target devices obtained by sensors are combined with the environmental features of the image recognition model to further enhance the accuracy of image recognition.

[0158] 9. The meta - learning method in this disclosure that uses a limited amount of data on the edge side, such as the meta - update strategy of MAML or Reptile, can quickly adapt and optimize the image model, thus achieving a highly personalized user experience.

[0159] 10. Once the first device in this disclosure is recognized, the system will be able to seamlessly link to the control interface of the corresponding manufacturer, thus providing a seamless and integrated experience for users.

[0160] The device management method of this disclosure will be further described below with specific application examples.

[0161] As Figure 11 shown, Figure 11 is a schematic flowchart of the device management method provided by the application example of this disclosure. The device management method includes the following steps:

[0162] Step 1101: Obtain multiple frames of original images collected by the image acquisition component, obtain the morphological characteristics of the electronic device when each frame of the original image is collected through the sensor component, and obtain the distance between the electronic device and the first device when each frame of the original image is collected through the short - range communication component.

[0163] Step 1102: Determine the training data set and the test data set.

[0164] Step 1103: Use the training data set to train the image recognition model; use the test data set to test the target image recognition model.

[0165] Step 1104: Store the multiple frames of original images and the corresponding morphological characteristics and distances of each frame of the original image in the first storage space of the electronic device.

[0166] Step 1105: Determine whether the test accuracy is greater than or equal to the accuracy threshold.

[0167] If the judgment result is yes, then go to step 1106;

[0168] If the judgment result is no, then go to step 1116;

[0169] Step 1106: Display an addition confirmation window.

[0170] Step 1107: Determine whether an addition instruction is received.

[0171] If the judgment result is yes, then go to step 1108;

[0172] If the judgment result is no, then go to step 1117;

[0173] Step 1108: Add the binding relationship between the image recognition model and the first device.

[0174] Step 1109: Identify the image features of the target device through the target image recognition model to determine the device identifier of the target device.

[0175] Step 1110: Check whether the device identifier of the target device matches the device identifier of the first device.

[0176] If the judgment result is yes, proceed to Step 1111;

[0177] If the judgment result is no, proceed to Step 1118;

[0178] Step 1111: Determine that the target device is the first device.

[0179] Step 1112: Check whether a correction instruction from the user is received.

[0180] If the judgment result is yes, proceed to Step 1113;

[0181] If the judgment result is no, proceed to Step 1119;

[0182] Step 1113: Obtain the first gesture control instruction (optional).

[0183] Step 1114: Display the control interface corresponding to the first device; control the target device through the control interface.

[0184] Step 1115: If a correction instruction from the user is received, update the target image recognition model.

[0185] Step 1116: Display a training failure message.

[0186] Step 1117: Delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image.

[0187] Step 1118: Determine that the target device is not the first device and display a prompt message.

[0188] Step 1119: Update the image recognition model.

[0189] Figure 12 FIG. 46 is a schematic structural diagram of a device management apparatus 1200 provided by an embodiment of the present disclosure. The device management apparatus 1200 includes:

[0190] An identification unit 1210, configured to use a target image recognition model to identify a target image according to the position information between an electronic device and a target device in the target image, so as to determine whether the target device is a first device, and the target image recognition model is used to identify the first device.

[0191] The device management apparatus proposed according to the present disclosure uses a target image recognition model through an SOC chip, and recognizes a target image according to the position information between an electronic device and a target device in the target image to determine whether the target device is a first device, where the target image recognition model is used to recognize the first device. The electronic device is used to control the target device. The solution of the present disclosure determines a training data set based on multiple frames of training images and the relative position relationship and distance between the electronic device and the first device; then uses the training data set to train an image recognition model, and finally uses the target image recognition model to recognize the target image, improving the accuracy of the image recognition result, thereby enhancing the convenience and accuracy of device management.

[0192] In some embodiments, the device management apparatus 1200 further includes a training unit, and the training unit is configured to: determine a training data set, where the training data set includes multiple frames of training images and training parameters corresponding to each frame of training image, each frame of training image includes the first device, and the training parameters include the position information between the electronic device and the first device; use the training data set to train an image recognition model to obtain a target image recognition model.

[0193] In some embodiments, the device management apparatus 1200 further includes an acquisition unit, and the acquisition unit is configured to: acquire multiple frames of original images acquired by an image acquisition component, where the multiple frames of original images include multiple frames of training images; acquire the morphological features of the electronic device when each frame of original image is acquired through a sensor component, where the morphological features are used to determine the relative position relationship, and the morphological features include the rotation angles of the electronic device in at least one direction; acquire the distance between the electronic device and the first device when each frame of original image is acquired through a short-range communication component.

[0194] In some embodiments, the recognition unit 1210 is further configured to: recognize the image features of the target device through the target image recognition model; determine the device identifier of the target device according to the image features and the position information between the electronic device and the target device in the target image, where the position information includes the relative position relationship and the distance; in the case where the device identifier of the target device matches the device identifier of the first device, determine that the target device is the first device, and notify the electronic device to display the control interface corresponding to the first device.

[0195] In some embodiments, the recognition unit 1210 is further configured to: recognize the image features of the target device through the target image recognition model; determine the device identifier of the target device according to the image features, and verify the device identifier through the position information; in the case where the device identifier of the target device does not match the device identifier of the first device, determine that the target device is not the first device, and notify the electronic device to display a prompt message.

[0196] In some embodiments, the device management apparatus 1200 further includes a testing unit configured to: determine a test data set from multiple frames of original images, the test data set including multiple frames of test images; and use the test data set to test the target image recognition model.

[0197] In some embodiments, the device management apparatus 1200 further includes a display unit configured to: when the test accuracy of the target image recognition model is greater than or equal to the accuracy threshold, notify the electronic device to display an addition confirmation window for prompting the user whether to add the binding relationship between the target image recognition model and the first device.

[0198] In some embodiments, the device management apparatus 1200 further includes a first deletion unit configured to: when the test accuracy of the target image recognition model is less than the accuracy threshold, notify the electronic device to display a training failure message, and notify the electronic device to delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image from the first storage space.

[0199] In some embodiments, the device management apparatus 1200 further includes a correction unit configured to: when it is determined that the target device in the target image is the first device, if a correction instruction from the user is received, update the target image recognition model, where the correction instruction is used to correct the target device from the first device to the second device.

[0200] Figure 13 FIG. 13 is a schematic structural diagram of another device management apparatus 1300 provided by an embodiment of the present disclosure. The device management apparatus 1300 includes:

[0201] A control unit 1310 for controlling the target device.

[0202] In some embodiments, the control unit 1310 is further configured to: when the target device is the first device, automatically display a control interface corresponding to the first device; and control the first device through the control interface.

[0203] In some embodiments, the control unit 1310 is further configured to: when the target device is the first device and a first gesture control instruction is obtained, display a control interface corresponding to the first device, where the first gesture control instruction is used to indicate the display of the control interface corresponding to the first device; and control the first device through the control interface.

[0204] In some embodiments, the device management apparatus 1300 further includes an addition unit configured to: display an addition confirmation window; and receive an addition instruction from the user to add the binding relationship between the target image recognition model and the first device.

[0205] In some embodiments, the device management apparatus 1300 further includes a second deletion unit, and the second deletion unit is configured to: display an addition confirmation window; and delete multiple frames of training images and the morphological features and distances corresponding to each frame of training image when no addition instruction from the user is received.

[0206] In some embodiments, the device management apparatus 1300 further includes a storage unit, and the storage unit is configured to: store multiple frames of original images in the first storage space of the electronic device, and store the morphological features and distances corresponding to the multiple frames of original images.

[0207] Since the apparatus provided in the embodiments of the present disclosure corresponds to the methods provided in the above several embodiments, the implementation manners of the methods are also applicable to the apparatus provided in this embodiment and will not be described in detail in this embodiment.

[0208] In the above embodiments provided in the present application, the methods and apparatuses provided in the embodiments of the present application are introduced. To implement each function in the methods provided in the above embodiments of the present application, the electronic device may include a hardware structure and software modules, and implement the above functions in the form of a hardware structure, software modules, or a combination of a hardware structure and software modules. A certain function among the above functions may be executed in the form of a hardware structure, software module, or a combination of a hardware structure and software module.

[0209] Figure 14 FIG. is a block diagram of an electronic device 1400 for implementing the above device management method according to an exemplary embodiment. For example, the electronic device 1400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0210] Referring to Figure 14 , the electronic device 1400 may include one or more of the following components: a processing component 1402, a memory 1404, a power component 1406, a multimedia component 1408, an audio component 1410, an input / output (I / O) interface 1412, a sensor component 1414, and a communication component 1416.

[0211] The processing component 1402 generally controls the overall operation of the electronic device 1400, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 1402 may include one or more processors 1420 to execute instructions to complete all or part of the steps of the above methods. In addition, the processing component 1402 may include one or more modules to facilitate the interaction between the processing component 1402 and other components. For example, the processing component 1402 may include a multimedia module to facilitate the interaction between the multimedia component 1408 and the processing component 1402.

[0212] The memory 1404 is configured to store various types of data to support the operation of the electronic device 1400. Examples of such data include instructions for any application or method operating on the electronic device 1400, contact data, phone book data, messages, pictures, videos, and the like. The memory 1404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0213] The power supply component 1406 provides power to various components of the electronic device 1400. The power supply component 1406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 1400.

[0214] The multimedia component 1408 includes a screen that provides an output interface between the electronic device 1400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of the touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operations. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 1400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0215] The audio component 1410 is configured to output and / or input audio signals. For example, the audio component 1410 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 1400 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 1404 or transmitted via the communication component 1416. In some embodiments, the audio component 1410 further includes a speaker for outputting audio signals.

[0216] The I / O interface 1412 provides an interface between the processing component 1402 and the peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0217] The sensor assembly 1414 includes one or more sensors for providing a status assessment of various aspects for the electronic device 1400. For example, the sensor assembly 1414 can detect the on / off state of the electronic device 1400, the relative positioning of components, such as components for the display and keypad of the electronic device 1400. The sensor assembly 1414 can also detect a change in the position of the electronic device 1400 or a component of the electronic device 1400, the presence or absence of user contact with the electronic device 1400, the orientation or acceleration / deceleration of the electronic device 1400, and the temperature change of the electronic device 1400. The sensor assembly 1414 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 1414 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1414 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0218] The communication component 1416 is configured to facilitate communication between the electronic device 1400 and other devices in a wired or wireless manner. The electronic device 1400 can access a wireless network based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or a combination thereof. In an exemplary embodiment, the communication component 1416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1416 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0219] In an exemplary embodiment, the electronic device 1400 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.

[0220] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1404 including instructions, and the above instructions can be executed by a processor 1420 of the electronic device 1400 to complete the above method for device management. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0221] Embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause a computer to execute the methods described in the above embodiments of the present disclosure.

[0222] Embodiments of the present disclosure also propose a chip, see Figure 15 the structural schematic diagram of the chip shown. Figure 15 The chip shown includes a processor 1501 and an interface 1502. Among them, the number of processors 1501 can be one or more, and the number of interfaces 1502 can be multiple.

[0223] Optionally, the chip further includes a memory 1503, and the memory 1503 is used to store necessary computer programs and data.

[0224] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0225] Any process or method description in a flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of the present invention belong.

[0226] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (control methods), portable computer disk cartridges (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing as necessary, and then stored in a computer memory.

[0227] It should be understood that various parts of the embodiments of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0228] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0229] In addition, each functional unit in various embodiments of the present invention may be integrated into one processing module, may exist separately as individual units physically, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, or the like.

[0230] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A device management method, characterized in that, the method includes: using a target image recognition model to recognize the target image according to the position information between the electronic device and the target device in the target image, so as to determine whether the target device is a first device, and the target image recognition model is used to recognize the first device.

2. The method according to claim 1, characterized in that, the method further includes: determining a training data set, where the training data set includes multiple frames of training images and training parameters corresponding to each frame of training image, the first device is included in each frame of training image, and the training parameters include the position information between the electronic device and the first device; using the training data set to train the image recognition model to obtain the target image recognition model.

3. The method according to claim 2, characterized in that, the method further includes: acquiring multiple frames of original images collected by an image acquisition component, and the multiple frames of original images include the multiple frames of training images; acquiring the morphological features of the electronic device when each frame of original image is collected through a sensor component, where the morphological features are used to determine the relative position relationship, and the morphological features include the rotation angle of the electronic device in at least one direction; acquiring the distance between the electronic device and the first device when each frame of original image is collected through a short-range communication component.

4. The method according to any one of claims 1 to 3, characterized in that, the step of using a target image recognition model to recognize the target image according to the position information between the electronic device and the target device in the target image includes: recognizing the image features of the target device through the target image recognition model; determining the device identifier of the target device according to the image features and the position information between the electronic device and the target device in the target image, where the position information includes the relative position relationship and the distance; when the device identifier of the target device matches the device identifier of the first device, determining that the target device is the first device, and notifying the electronic device to display the control interface corresponding to the first device.

5. The method according to any one of claims 1 to 3, characterized in that, the step of using a target image recognition model to recognize the target image according to the position information between the electronic device and the target device in the target image includes: recognizing the image features of the target device through the target image recognition model; determining the device identifier of the target device according to the image features, and verifying the device identifier through the position information; when the device identifier of the target device does not match the device identifier of the first device, determining that the target device is not the first device, and notifying the electronic device to display a prompt message.

6. The method according to claim 3, characterized in that, the method further includes: determining a test data set from the multiple frames of original images, and the test data set includes multiple frames of test images; using the test data set to test the target image recognition model.

7. The method according to claim 6, It is characterized in that The method further includes: When the test accuracy of the target image recognition model is greater than or equal to the accuracy threshold, notifying the electronic device to display an addition confirmation window, where the addition confirmation window is used to prompt the user whether to add the binding relationship between the target image recognition model and the first device.

8. The method according to claim 6, It is characterized in that The method further includes: When the test accuracy of the target image recognition model is less than the accuracy threshold, notifying the electronic device to display a training failure message, and notifying the electronic device to delete the multiple frames of training images and the morphological features and distances corresponding to each frame of training image from the first storage space.

9. The method according to any one of claims 1 to 3, It is characterized in that The method further includes: When it is determined that the target device in the target image is the first device, if a correction instruction from the user is received, updating the target image recognition model. Wherein, the correction instruction is used to correct the target device being the first device to the target device being the second device.

10. A device management method, It is characterized in that The method includes: The method according to any one of claims 1 to 9; Controlling the target device.

11. The method according to claim 10, It is characterized in that The controlling the target device includes: When the target device is the first device, automatically displaying the control interface corresponding to the first device; Controlling the target device through the control interface.

12. The method according to claim 10, It is characterized in that The controlling the target device includes: When the target device is the first device and a first gesture control instruction is obtained, displaying the control interface corresponding to the first device, where the first gesture control instruction is used to indicate the display of the control interface corresponding to the first device; Controlling the target device through the control interface.

13. The method according to any one of claims 10 to 12, It is characterized in that The method further includes: Displaying an addition confirmation window; Receiving an addition instruction from the user to add the binding relationship between the target image recognition model and the first device.

14. The method according to any one of claims 10 to 12, It is characterized in that The method further includes: Displaying an addition confirmation window; When the addition instruction from the user is not received, deleting the multiple frames of training images and the morphological features and distances corresponding to each frame of training image.

15. The method according to any one of claims 10 to 12, It is characterized in that The method further includes: Storing the multiple frames of original images in the first storage space of the electronic device, and storing the morphological features and distances corresponding to the multiple frames of original images.

16. A device management apparatus, It is characterized in that Includes: An identification unit, configured to use a target image recognition model to identify the target image according to the position information between the electronic device and the target device in the target image, so as to determine whether the target device is a first device, where the target image recognition model is used to identify the first device.

17. A device management apparatus, characterized in that it includes: the apparatus according to claim 16; and a control unit, configured to control the target device.

18. An electronic device, characterized in that it includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 10 to 15.

19. A computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the method according to any one of claims 1 to 9, or implements the method according to any one of claims 10 to 15.

20. A chip, characterized in that it includes one or more interfaces and one or more processors; the interfaces are configured to receive a signal from a memory of an electronic device and send the signal to the processors, where the signal includes computer instructions stored in the memory; when the processors execute the computer instructions, the electronic device is caused to execute the method according to any one of claims 1 to 9.

Images