Target labeling processing method and device, electronic equipment and readable storage medium

Abstract

This application provides a target annotation processing method, apparatus, electronic device, and readable storage medium, relating to the field of smart home technology. The method includes: displaying a scene annotation interface, wherein the scene annotation interface includes a spatial layout map of a detection area; responding to an annotation operation on a selected target object, obtaining the annotation position of the target object in the spatial layout map based on the target object's actual position in the detection area; and displaying the labeled identifier of the target object at the annotation position in the spatial layout map. Thus, by responding to an annotation operation on a selected target object and automatically annotating the target object on the scene annotation interface based on its actual position in the detection area, the annotation of target objects can be completed quickly and accurately.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a target annotation processing method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] Currently, home environment images are typically obtained through manual annotation. However, since the objects in the image are manually annotated—essentially hand-drawn—it's possible that the object's position in the image may not correspond to its actual location, resulting in poor image quality and low annotation efficiency. Therefore, how to complete annotation quickly and accurately has become a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0003] This application provides a target annotation processing method, apparatus, electronic device, and readable storage medium. By responding to an annotation operation on a selected target object, the method automatically annotates the target object on the scene annotation interface based on the target object's actual position in the detection area, thus enabling the target object to be annotated quickly and accurately.

[0004] The embodiments of this application can be implemented as follows:

[0005] In a first aspect, embodiments of this application provide a target annotation processing method, the method comprising:

[0006] A scene annotation interface is displayed, which includes a spatial layout diagram of the detection area;

[0007] In response to the annotation operation for the selected target object, the annotation position of the target object in the spatial layout diagram is obtained based on the actual position of the target object in the detection area;

[0008] The labeled location in the spatial layout diagram displays the identifier of the target object.

[0009] Secondly, embodiments of this application provide a target annotation processing apparatus, the apparatus comprising:

[0010] The display module is used to display the scene annotation interface, wherein the scene annotation interface includes a spatial layout map of the detection area;

[0011] The processing module is used to respond to the annotation operation for the selected target object and obtain the annotation position of the target object in the spatial layout diagram based on the actual position of the target object in the detection area.

[0012] The display module is also used to display the identifier of the marked target object at the marked position in the spatial layout diagram.

[0013] In an optional implementation, the processing module is specifically used for:

[0014] In response to the annotation operation for the selected target object, it is determined that the reference object is located at the target object, the real position information of the detected reference object in the detection area is obtained, and the annotation position of the target object is determined based on the real position information.

[0015] In an optional implementation, the processing module is specifically used for:

[0016] In response to a selection operation on the target object, a prompt message is displayed to instruct the reference object to move to the target object;

[0017] In response to the annotation operation for the target object, it is determined that the reference object is located at the target object, and the annotation position of the target object is determined based on the actual position information of the reference object.

[0018] In an optional implementation, the true location information is obtained using millimeter-wave radar.

[0019] In an optional implementation, the target object includes a first target object, which is a controllable device with communication capabilities;

[0020] The processing module is specifically used for:

[0021] For the first target object, in response to the device selection operation for the first target object, the device identifier of the selected first target object is determined;

[0022] In response to the annotation operation for the selected first target object, the annotation position of the first target object in the spatial layout diagram is obtained based on the device identifier and the actual position of the first target object in the detection area.

[0023] In an optional implementation, the target object includes a first target object, which is a controllable device with communication capabilities;

[0024] The processing module is specifically used for:

[0025] Receive the device identifier reported by the selected first target object;

[0026] In response to the annotation operation for the selected first target object, the annotation position of the first target object in the spatial layout diagram is obtained based on the device identifier and the actual position of the first target object in the detection area.

[0027] In an optional implementation, the target object includes a second target object, which includes uncontrollable items and empty objects;

[0028] The processing module is specifically used for:

[0029] For the second target object, in response to the identifier selection operation for the second target object, the identifier of the selected second target object is determined;

[0030] In response to the annotation operation for the selected second target object, the annotation position of the second target object in the spatial layout diagram is obtained based on the identifier of the second target object and the actual position of the second target object in the detection area.

[0031] In an optional implementation, the detection region includes at least one subspace.

[0032] The processing module is further configured to: for the subspace, in response to the annotation operation for the selected subspace, obtain the annotation position of the subspace in the scene annotation interface based on the size of the subspace in the detection area;

[0033] The display module is also used to display the identifier of the marked subspace at the marked position corresponding to the subspace.

[0034] In an optional implementation, the dimensions of the subspace are obtained using millimeter-wave radar.

[0035] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the target annotation processing method described in any of the foregoing embodiments.

[0036] Fourthly, embodiments of this application provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the target annotation processing method as described in any of the foregoing embodiments.

[0037] The target annotation processing method, apparatus, electronic device, and readable storage medium provided in this application embodiment demonstrate a scene annotation interface including a spatial layout map of a detection area. Upon receiving an annotation operation for a selected target object, in response to the annotation operation, the method obtains the annotation position of the target object in the spatial layout map based on the target object's actual position in the detection area, and then displays the annotated target object's identifier at that annotation position. In this way, the target object's identifier can be automatically displayed at the annotation position in the spatial layout map of the detection area corresponding to its actual position, thereby avoiding situations where the object's position in the image does not correspond to its actual position, improving annotation quality and efficiency. Attached Figure Description

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A schematic diagram of an application environment provided for an embodiment of this application;

[0040] Figure 2 This is a schematic diagram of another application environment provided for an embodiment of this application;

[0041] Figure 3 One of the flowcharts of the target annotation processing method provided in the embodiments of this application;

[0042] Figure 4 A spatial layout diagram provided for an embodiment of this application;

[0043] Figure 5 This is one of the illustrated diagrams provided for embodiments of this application;

[0044] Figure 6 This is the second illustrated diagram provided for an embodiment of this application;

[0045] Figure 7 This is a flowchart illustrating the annotation of different types of objects provided in an embodiment of this application;

[0046] Figure 8 A second schematic flowchart illustrating the target annotation processing method provided in this application embodiment;

[0047] Figure 9 A schematic diagram illustrating the target labeling process of the smart home system provided in this application embodiment;

[0048] Figure 10One of the block diagrams of the target annotation processing device provided in the embodiments of this application;

[0049] Figure 11 A block diagram of the electronic device provided in this application.

[0050] Icons: 10-Smart home system; 100-Electronic device; 110-Processor; 120-Memory; 200-Location detection device; 300-Home device; 400-Gateway; 500-Router; 600-Server; 700-Target annotation processing device; 710-Display module; 720-Processing module. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0052] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0053] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0054] The following will describe one application environment involved in this application.

[0055] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment applicable to embodiments of this application. Wherein, Figure 1A smart home system 10 is provided, which includes an electronic device 100, a location detection device 200 communicatively connected to the electronic device 100, and home appliances 300. The number of location detection devices 200 and the number of home appliances 300 can be at least one.

[0056] The position detection device 200 can be a millimeter-wave radar, an image acquisition device, or other devices. The position detection device 200 is used to obtain the true position information of a target object through detection and then transmit this true position information to the electronic device 100. The target object is any object selected by the user that needs to be labeled.

[0057] Electronic device 100 may include smart mirrors, smartphones, large screens, televisions, wall-mounted small screens, personal computers (PCs), tablets, personal digital assistants (PDAs), and other intelligent interactive terminals, without limitation. Electronic device 100 can mark target objects in space through certain interactions for corresponding management. That is, electronic device 100 can determine the marked position of the target object in the spatial layout map of the detection area based on the actual position information of the target object sent by the position detection device 200, and then mark and display the target object at that marked position. This allows for rapid marking of target objects and avoids situations where the position of the object in the image does not correspond to its actual position.

[0058] Optionally, the target object may include devices involved in smart home control, such as curtain motors. In this way, the electronic device 100 can provide an intuitive and visual home interface, allowing users to view indoor objects and associate the icons on the interface with the actual objects, thus facilitating user management and control. For example, a user can quickly and accurately select a specific home device 300 to control on the interface. Based on the user's selection and specific control operation, the electronic device 100 controls the home device 300 through a communication connection.

[0059] In this embodiment, the smart home system 10 may further include a gateway 400 that is communicatively connected to the electronic device 100, home appliances 300, and location detection device 200. The number of gateways 400 may be at least one. The gateway 400 can be a smart gateway for smart home control, capable of functions such as system information collection, information input, information output, centralized control, remote control, and linkage control. The gateway 400 can be responsible for specific security alarms, appliance control, and electricity consumption information collection. The gateway 400 can also wirelessly interact with products such as smart interactive terminals. The gateway 400 also possesses wireless routing capabilities, excellent wireless performance, network security, and coverage.

[0060] In this embodiment, the home appliance 300 may include various smart home appliances, sensing devices, and detection devices installed in the indoor space, such as smart TVs, smart refrigerators, smart air conditioners, temperature and humidity sensors, pressure sensors, smoke sensors, sockets, lights, infrared transmitters, etc. The home appliance 300 and the location detection device 200 connected to the gateway 400 can interact with the gateway 400 through information and command exchange. The gateway 400 can connect to the home appliance 300 and the location detection device 200 via communication methods such as Bluetooth, WiFi (Wireless-Fidelity), or ZigBee. However, the specific connection method between the gateway 400 and the home appliance 300 and the location detection device 200 is not limited in this embodiment.

[0061] Optionally, in this embodiment, the smart home system 10 may further include a server 600 communicatively connected to the gateway 400. The server 600 may be a local server, a cloud server, or other similar server; the specific server type is not limited in this embodiment. The server 600 connected to the gateway 400 can wirelessly exchange information with the gateway 400. Gateways 400 located in different indoor spaces can all communicate with the same server 600 via a network to exchange information between the server 600 and the gateway 400.

[0062] Electronic device 100 can interact with server 600 via wireless methods such as 2G / 3G / 4G / 5G / WiFi. Of course, the connection method between electronic device 100 and server 600 is not limited in this embodiment. In some implementations, electronic device 100 can also be used to interact with users, facilitating wireless communication between users and router 500 and gateway 400 via electronic device 100. Furthermore, users can add account information to both gateway 400 and electronic device 100 simultaneously, enabling information synchronization between the two devices.

[0063] In some embodiments, users can set different trigger scenarios or automated linkages through the application (APP) of the electronic device 100. As one approach, the electronic device 100 can upload scenario configuration information or automation schemes to the server 600. When the triggering conditions of the scenario or automation are met, the server 600 can find the device corresponding to the execution action in the stored scenario configuration information or automation scheme, and notify the device to perform the action to satisfy the execution result of the trigger scenario or automation. Alternatively, the server 600 can also send the scenario configuration information or automation scheme to the gateway 400, which can then find the device corresponding to the execution action in the stored scenario configuration information or automation scheme. Simultaneously, the gateway 400 can feed back the device's execution status to the server 600.

[0064] Please refer to Figure 2 , Figure 2 This is a schematic diagram illustrating another application environment provided for an embodiment of this application. In this embodiment, millimeter-wave radar can be used as... Figure 1 The location detection device 200 is used in the system. Target objects can be divided into controllable and uncontrollable labeled objects. Controllable labeled objects can communicate with gateways or routers to achieve corresponding data communication.

[0065] exist Figure 2 In the environment shown, the electronic device may have an app installed for target annotation processing or a webpage for target annotation processing open. The user can operate the electronic device, and in response, the electronic device obtains the annotation position on the spatial layout map corresponding to the real position information of the uncontrollable or controllable annotated objects detected by millimeter-wave radar through a cloud server, gateway, or router. Then, based on the annotation position, the selected target object is marked and displayed.

[0066] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0067] Please refer to Figure 3 , Figure 3 This is one of the flowcharts illustrating the target annotation processing method provided in this application embodiment. This target annotation processing method can be applied to the aforementioned electronic device 100. The specific flow of the target annotation processing method is described in detail below. This method may include steps S130 to S150.

[0068] Step S130: Display the scene annotation interface.

[0069] In this embodiment, the electronic device 100 can display a scene annotation interface. The user can input annotation operations for selected target objects on this scene annotation interface, so that the electronic device 100 can annotate the selected target objects according to the received annotation operations. The annotation operation for the selected target object represents the user's input requesting the electronic device 100 to annotate a certain object (i.e., the target object). This annotation operation for the selected target object can be an operation where the user selects the target object in the scene annotation interface, an operation where the user confirms the annotation of the target object selected by the electronic device 100, or an operation where the user selects the target object and confirms the annotation, etc., which can be determined according to actual needs.

[0070] The scene annotation interface includes a spatial distribution map of the detection area. The detection area is the real-world spatial region where the target object to be annotated is located. For example, when using this scene annotation interface to obtain a home environment image from the control interface of a smart home, the detection area is the home space, and the annotated scene annotation interface is the home environment image.

[0071] A spatial distribution map is used to represent the distribution of real-world spaces, which can include various rooms, corridors, outdoor areas, commercial spaces, public areas, etc. This spatial distribution map can be created on, for example... Figure 4 Based on the floor plan shown, you can also... Figure 5 Based on the regular or irregular two-dimensional plane shown, it can also be built on a three-dimensional space. The specifics can be determined according to actual needs. As long as the size and distribution of the space in the spatial distribution map correspond to the size and distribution of the real space, and the user can determine the corresponding real object based on the markers in the spatial layout map and their positions in the spatial layout map.

[0072] Step S140: In response to the annotation operation for the selected target object, obtain the annotation position of the target object in the spatial layout map based on the actual position of the target object in the detection area.

[0073] In this embodiment, the selected target object is the object that needs to be labeled in the detection area, which can be determined by actual needs. The user can input a labeling operation on the scene labeling interface to indicate that the electronic device 100 needs to label the selected target object in the spatial layout diagram. Upon receiving the labeling operation, the electronic device 100 can obtain the actual position of the target object in the detection area in any way, and then determine the labeling position of the target object in the spatial layout diagram.

[0074] The label location indicates the position of the identifier when it is labeled in the spatial layout diagram, that is, a certain position in the spatial layout diagram. Correspondingly, the label location of the target object in the spatial layout diagram indicates the position of the target object in the spatial layout diagram after it has been labeled.

[0075] Step S150: Display the identifier of the target object at the marked location on the spatial layout diagram.

[0076] Once the selected target object is located in the spatial layout diagram, its identifier can be marked at the marked location in the spatial layout diagram. After marking, the identifier of the target object will be displayed in the scene annotation interface, thus completing the annotation of the selected target object.

[0077] The identifier of the target object can be any identifier used to represent the target object. The identifier can be an icon (e.g., an icon or other icon) and / or text. If the identifier includes text, the text can be a text field entered by the user in the scene annotation interface, or a text field selected by the user in the scene annotation interface. If the identifier includes an icon, the icon of the target object can be the target object icon selected by the user in the icon selection area, or it can be automatically determined by the electronic device 100 based on relevant information about the target object.

[0078] For example, such as Figure 3 As shown in 3b, a circular icon and the text field "Sleep Zone" are used as the identifier for the sleep zone and are marked at the designated location on the spatial layout diagram.

[0079] It can be understood that after completing the annotation of a target object through steps S130 to S150, the scene annotation interface with the current target object obtained in step S150 can be used as the scene annotation interface for the next annotation. For example, as Figure 3 As shown, assuming the target object for the first annotation is the smart panel, the scene annotation interface can include the smart panel's identifier after the first annotation is completed. When the target object for the second annotation is the sleep belt, the scene annotation interface will include the smart panel's identifier, and the sleep belt's identifier needs to be annotated in the spatial distribution map of the scene annotation interface.

[0080] In this way, by responding to the annotation operation for the selected target object, the identifier of the target object can be automatically displayed at the annotation position corresponding to the real position in the spatial layout map of the detection area, based on the real position of the target object in the detection area. This completes the automatic annotation of the target object, improves annotation efficiency and quality, and avoids the situation where the position of the object in the image does not correspond to the real position.

[0081] When a home environment image is obtained using the methods described above, an intuitive and visual home interface can be provided. Displaying this home environment image to the user is equivalent to providing a space-based interactive method. In this home environment image, the user can quickly find the corresponding icon for the object they want to control. That is, the user can quickly match the icons in the home environment image with objects in the real home space, thus facilitating user management.

[0082] Alternatively, as a possible implementation, if the electronic device 100 has a position detection function, the electronic device 100 can obtain the real position information of the selected target object within the detection area through position detection, and then determine the marked position of the target object based on the real position information of the target object.

[0083] For example, electronic device 100 acquires environmental images by taking pictures, and then combines its own position with the environmental images to obtain the real position information of the target object within the detection area by recognition, and then determines the labeled position based on the real position information of the target object.

[0084] Alternatively, as another possible implementation, if the electronic device 100 does not have a position detection function, the position detection device 200 can directly obtain the real position information of the target object within the detection area by detection, and send the real position information to the electronic device 100 so that the electronic device 100 can obtain the real position information of the target object and then determine the marking position based on the real position information.

[0085] Among them, such as Figure 1 As shown, the location detection device 200 can communicate with the electronic device 100 via gateway 400 and router 500, or via gateway 400, router 500, and server 600, respectively, thereby sending the real location information to the electronic device 100. Optionally, when the electronic device 100 needs to obtain the real location information of the target object, it can send a location request to the location detection device 200, and the location detection device 200 can send the detected real location information to the electronic device 100 based on the location request.

[0086] Alternatively, as another possible implementation, a reference object can be used as a carrier. If it is determined that the reference object is located at the target object, the real position information of the reference object obtained through detection within the detection area can be obtained, and then the labeled position of the target object can be determined based on the real position information.

[0087] The reference object is the object used as a carrier for position detection; specifically, it is an object that can move within the environment (i.e., the detection area) corresponding to the spatial layout diagram. Optionally, the reference object can include living reference objects and non-living reference objects. For example, living objects can be people, pets, etc., while non-living reference objects can be mobile robots, robotic vacuum cleaners, etc.

[0088] In this method, detecting a reference object is equivalent to detecting a target object. The actual location information of the reference object can be used as the actual location information of the target object, thereby determining the annotation position of the target object. This allows users to freely select the target object to be annotated and accurately determine its actual location information.

[0089] When using a reference object, it can be moved to the target object within a preset time period after the initial position detection. When the preset time period ends, it can be directly determined that the reference object is now at the target object. Thus, without manual operation, it can automatically determine whether the reference object has moved to the target object.

[0090] Users can also input a annotation operation into the electronic device 100 after determining that the reference object is located at the target object. Upon receiving the annotation operation, in response to the annotation operation for the selected target object, it can be determined that the reference object is currently located at the target object, and then the annotation position of the target object can be determined based on the actual position information of the reference object at this time. This provides greater flexibility, and obtains the actual position information when the reference object has actually moved to the target object.

[0091] Optionally, to increase the flexibility of target annotation processing, the user can input a selection operation for the target object into the electronic device 100. Optionally, upon receiving the selection operation, the electronic device 100 can respond by displaying a prompt message instructing the reference object to move to the target object. When the electronic device 100 displays the prompt message, the reference object can move towards the target object. When the reference object moves to the target object, the user can input an annotation operation for that target object into the electronic device 100. Upon receiving the annotation operation for that target object, the electronic device 100 can determine the reference object's position relative to the target object, thereby obtaining the reference object's true position information at that moment, and determining the annotation position of the target object based on the reference object's true position information.

[0092] The true location information of the reference object can be obtained through at least one of the following methods: obtaining true location information through millimeter-wave radar monitoring; obtaining true location information through ultra-wideband (UWB) positioning technology; or obtaining true location information through image analysis of environmental images including the reference object. The millimeter-wave radar is a positioning device that obtains the relative positional relationship between the millimeter-wave radar and the target by emitting millimeter-wave signals and analyzing the returned signals.

[0093] In one implementation, the true location information of a reference object is obtained through millimeter-wave radar monitoring. This true location information can be used as the true location information of the target object at that reference object, thus determining the labeled location of the target object. Therefore, the labeled location can be determined based on the true location information without compromising user privacy.

[0094] In this implementation, the reference object is unrelated to the target object itself. However, to mark the target object, the reference object is detected by millimeter-wave radar. When the reference object moves to the target object, it sends a feedback signal to the millimeter-wave radar, which then obtains the true location information of the reference object based on this signal. The reference object serves merely as a bridge between the target object and the millimeter-wave radar.

[0095] A single millimeter-wave radar can only detect the location information of reference objects within its coverage area. During detection, the user can manually select the space to be detected (e.g., a living room or a bedroom) and use that space as the detection area corresponding to the spatial layout map. The manually selected space cannot be larger than the coverage area of ​​a single millimeter-wave radar; otherwise, the true location information of the reference object may not be obtained. When the space to be detected is larger than the coverage area of ​​a single millimeter-wave radar, multiple millimeter-wave radars can be used for detection.

[0096] Millimeter-wave radar can be placed in a default space, and its detectable area can be determined based on its installation height, elevation angle, and other information within that space. In one possible example, the detection range of a millimeter-wave radar is 4 meters (width) x 7 meters (length), with an installation height of 1.4 meters, which can be adjusted as needed; the 1.4-meter height refers to the horizontal installation height of the millimeter-wave radar. The millimeter-wave radar can be installed horizontally or tilted downwards; its detection range is maximized when horizontally installed.

[0097] When real-time location information is obtained through millimeter-wave radar, this information can be mapped to a spatial coordinate system to obtain the coordinates of a reference object in that system. This allows the coordinates of the reference object to be displayed in the space in the user's desired manner. The specific mapping method can be implemented using a coordinate transformation algorithm.

[0098] The target object can include a first target object and a second target object. The first target object is a controllable device with communication capabilities, i.e., a controllable labeled object. The second target object includes any object that is not a controllable device, i.e., an uncontrollable labeled object, such as uncontrollable items (e.g., uncontrollable devices and uncontrollable household items) and empty objects. The distinction between controllable and uncontrollable can be based on protocols. For example, products and smart home devices that can connect to Tmall devices, Mijia devices, Homkit devices, or gateways 400 in the smart home system are considered controllable devices, such as smart lamps and electric curtains. Controllable objects are products that can interact with the cloud and can be queried and controlled by interactive pages; most are IoT (Internet of Things) products.

[0099] The second target object can be a traditional furniture item such as a sofa, TV cabinet, or curtains; or an appliance that is not compatible with the protocol, such as a Haier appliance; or a regular non-IoT appliance, such as a refrigerator, washing machine, router, or vacuum cleaner; it can also be an empty object, without a product, just a specific coordinate location that does not point to any item. Therefore, the second target object represents an uncontrollable object, one that cannot interact with the cloud.

[0100] Optionally, when labeling, different methods can be used to determine the labeling position and label the target object depending on whether the target object is controllable.

[0101] The electronic device 100 can display a scene annotation interface. When the target object is a first target object, the user can input a device selection operation for the first target object in the scene annotation interface. This device selection operation can be an operation used to select a unique device identifier (e.g., device number) for the first target object. For example, the user can first select the device type of the first target object in the scene annotation interface, such as selecting "refrigerator" from several device types like refrigerator, color TV, sensor, and curtain motor; then, within the selected device type, select a unique device identifier for the first target object. The electronic device 100 can determine the device identifier of the first target object selected by the user in response to the device selection operation for the first target object. Subsequently, the identifier of the first target object can be determined based on this device identifier.

[0102] It can also save the correspondence between the identifier of the first target object and the device identifier, so that when controlling the home environment image obtained based on the target annotation processing method in the future, the actual device to be controlled can be determined. For example, if the user selects an identifier in the home environment image, the specific device that the user wants to control can be determined based on the correspondence between the identifier and the device identifier, and then the specific device can be controlled.

[0103] After the user inputs a device selection operation for the first target object, the actual position of the first target object in the detection area can be obtained. Based on this actual position and the device identifier of the first target object, the marked position of the first target object in the spatial layout diagram can be obtained. The actual position is used to determine the marked position, and the device identifier is used to determine the identifier of the first target object in the spatial layout diagram.

[0104] Optionally, after the user inputs a device selection operation for the first target object, the electronic device 100 can display a prompt message indicating that the reference object should move to the actual location of the first target object. When the reference object moves to the actual location of the first target object, the user can input a annotation operation for that first target object into the electronic device 100, for example, by clicking the "Appliance Annotation" button on the scene annotation interface. Upon receiving the annotation operation for the first target object, the electronic device 100 can obtain the actual location information of the reference object and thus determine the annotation position of the first target object.

[0105] When the identifiers of controllable devices are stored in advance, the electronic device 100 can store the correspondence between device identifiers and identifiers in advance. After determining the device identifier of the first target object, the identifier of the first target object can be determined based on the above correspondence, and then the identifier can be marked at the marking position corresponding to the first target object in the spatial layout diagram.

[0106] In this embodiment, the user manually selects the first target object to be labeled, and the labeling is performed only after the user manually confirms the labeling. This provides good flexibility and makes it easy to meet the user's labeling needs.

[0107] When the target object is a first target object, the electronic device 100 can receive the device identifier reported by the selected first target object. The first target object may report its own device information under user control, and this device information may include the device identifier. The electronic device 100 can also receive a user-input annotation operation for the selected first target object, and then, in response to this annotation operation, obtain the annotation position of the first target object in the spatial layout diagram based on the received device identifier and the actual position of the first target object in the detection area. The device identifier can be used to determine the identifier of the first target object. Thus, the user does not need to manually select the device identifier.

[0108] In the above-described method for reporting device identification by the first target object, the user can input a device type selection operation for the first target object in the scene annotation interface. This device type selection operation indicates the selection of the device type to which the first target object belongs. After receiving the device type selection operation, the electronic device 100 can respond by displaying a prompt message indicating that the reference object should move to the location of the first target object. When the reference object moves to the actual location of the first target object, the user can control the first target object to report electrical information through the electronic device 100; alternatively, the user can trigger the first target object to report electrical information by operating a button on the first target object, such as pressing the reset button. This facilitates the rapid determination of the identification of the first target object based on the device type and device identification.

[0109] After receiving appliance information, electronic device 100 can determine the device identifier of the first target object based on the appliance information. Subsequently, the identifier of the first target object can be determined based on the device identifier. The correspondence between the identifier of the first target object and the device identifier can also be saved so that when controlling the home environment based on the image obtained using this method, the actual device to be controlled can be identified.

[0110] When the reference object moves to the actual location of the first target object, the user can also input annotation operations for the first target object into the electronic device 100. For example, the user can click the "Appliance Annotation" button on the scene annotation interface. Upon receiving the appliance information and annotation operation, the electronic device 100 can determine that the reference object is located at the device corresponding to the appliance information, and determine the annotation position of the device corresponding to the appliance information based on the actual location information of the reference object at this time.

[0111] Therefore, the device identifier of the first target object to be labeled can be automatically determined without the user having to manually select the device identifier.

[0112] The following is combined with Figure 5 An example is given to illustrate the labeling process based on automatically determined device identifiers.

[0113] like Figure 5 As shown in Figure 5a, the user has moved to a certain location within the detection area. The user can control the sleep belt device by selecting it on the interactive interface of the electronic device 100, causing the sleep belt device to actively report its own electrical information; alternatively, the user can press the button on the actual sleep belt device, causing it to actively report its own electrical information. Based on the received electrical information, the electronic device 100 can determine the device identifier of the sleep belt device, and thus determine the location of the sleep belt device.

[0114] Users can also input annotations on the scene annotation interface of the electronic device 100 when they move to the location of the sleep belt device. Upon receiving the annotation, the electronic device 100 can determine where the sleep belt device is annotated based on the user's current coordinates. Figure 5 The spatial layout diagram shown is used as a reference point for marking the location of the sleep aid device. The device's identifier is then placed at the determined location to obtain the desired result. Figure 5 The image shown in 5b.

[0115] When the target object is a second target object (i.e., an uncontrollable object), the user can input a selection operation for the identifier of the second target object in the scene annotation interface. The electronic device 100 can respond to this identifier selection operation and determine the identifier of the selected second target object. Then, upon receiving the annotation operation for the selected second target object, it can obtain the annotation position of the second target object in the spatial layout diagram based on the identifier of the second target object and the actual position of the second target object in the detection area. In this way, it is convenient for users to customize the objects to be annotated, that is, users can annotate any object in the spatial layout diagram according to actual needs and determine the identifier of that object in the spatial layout diagram.

[0116] Optionally, the user can select the item type of the second target object in the scene labeling interface, such as a refrigerator, sofa, key, fire extinguisher, etc. Then, from the labels included in the selected item type, the user selects the label of the second target object. In this way, the electronic device 100 can determine the label of the second target object based on the label selection operation received from the user.

[0117] Optionally, after the user inputs an identification selection operation for the second target object, the electronic device 100 can respond to the identification selection operation by displaying a prompt message indicating that the reference object should move to the second target object. When the reference object moves to the actual location of the second target object, the user can also input a labeling operation for the second target object into the electronic device 100, for example, the user clicks the "Item Labeling" button on the scene labeling interface. Upon receiving the labeling operation, the electronic device 100 can determine that the reference object is located at the second target object, and determine the labeling position of the second target object based on the actual location information of the reference object at this time, and then label the second target object with its identification at the labeled position.

[0118] Understandably, when the second target object is an empty object, the user can directly select the identifier corresponding to the empty object. Then, after determining the actual location of the empty object, the electronic device 100 will mark the identifier corresponding to the empty object at the marked location corresponding to the actual location. The actual location corresponding to the empty object can be a location used for marking items or problems, or a trigger point for special scenarios.

[0119] The following is combined with Figure 6 Examples are given to illustrate how to label uncontrollable objects.

[0120] like Figure 6 As shown in Figure 6a, when a user moves to the location of a second target object to be labeled within the detection area, the user can input a labeling operation on the scene labeling interface. After receiving the labeling operation, the electronic device 100 can obtain the user's current real position information. If the user inputs an operation to select the icon corresponding to the sofa on the scene labeling interface, the electronic device 100 can determine that the icon corresponding to the sofa is labeled according to the user's current real position information. Figure 6 The spatial layout diagram shows the marked positions, and then the corresponding labels for the sofas are marked at the determined positions to obtain... Figure 6 The image shown in 6b.

[0121] As described above, when the reference object is a person and a millimeter-wave device is used to detect the reference object, the target annotation processing method provided in this application embodiment can be as follows: Figure 7 As shown.

[0122] S1. Has the millimeter-wave device detected human information? If detected, proceed to S2; if not detected, continue with S1.

[0123] S2. Human body information was detected, that is, the location information of the target object was detected.

[0124] S3. When the target object is a controllable annotation object (i.e., the first target object), the controllable annotation object can be annotated through quick annotation.

[0125] The quick annotation method is the annotation process based on automatically determining the device identifier as described above, and will not be repeated here.

[0126] S4. When the target object is a controllable annotation object, it can be annotated using ordinary annotation.

[0127] The method of annotating the controllable object through ordinary annotation is the same as the method described above, which is based on the user manually selecting the device identifier and then performing the annotation process, and will not be repeated here.

[0128] S5. When the target object is an uncontrollable annotation object (i.e., the second target object), the uncontrollable annotation object can be annotated through ordinary annotation.

[0129] The method of annotating the uncontrollable object using ordinary annotation is the same as the annotation process for the second target object described above, and will not be repeated here.

[0130] The detection area corresponding to the spatial layout map in the scene annotation interface can include at least one subspace, within which a target object exists. The spatial layout map can include the identifier of this at least one subspace. Thus, when the identifier of the target object is annotated in the subspace of the spatial layout map in the above manner, it is convenient to intuitively present the specific objects included in each real subspace.

[0131] For example, the above method can be used to mark the target object in the corresponding subspace to obtain a home environment image. Based on this home environment image, users can manage and schedule objects in a specific space in a unified manner, so that the managed objects can generate various linkage relationships.

[0132] Please refer to Figure 8 , Figure 8 This is a second schematic flowchart illustrating the target annotation processing method provided in this application embodiment. In this embodiment, the target annotation processing method may further include steps S110 and S120.

[0133] Step S110: For the subspace, in response to the annotation operation for the selected subspace, obtain the annotation position of the subspace in the scene annotation interface based on the size of the subspace in the detection area.

[0134] Step S120: Display the identifier of the labeled subspace at the labeled position corresponding to the subspace.

[0135] Optionally, subspaces can be divided according to the spatial distribution of the detection area. For example, when the detection area is a family space, it can be divided into subspaces such as study, living room, kitchen, hallway, bedroom 1, and bedroom 2. When the electronic device 100 receives a user's annotation operation for subspaces input through the scene annotation interface, it can obtain the spatial information of each subspace selected by the user in any way. This spatial information may include the actual size of the subspace, i.e., the dimensions of the subspace, or it may include the size of the subspace when it is annotated in the spatial layout diagram (i.e., its size in the image, which is determined by the actual size of the subspace).

[0136] Optionally, the size of the user-selected subspace within the detection area can be obtained through detection. For example, an image of the selected subspace can be obtained, and its size can be determined by analyzing the image; alternatively, a reference object can be moved to the edge of the subspace, and the size of the subspace can be determined by detecting the reference object. For instance, the user submits coordinates at a location within the space, thereby automatically generating the size of the subspace within the detection area.

[0137] Alternatively, the received space size can be directly used as the size of the selected subspace. For example, if the user directly inputs the space size for a specific subspace, that space size can be directly used as the size of the targeted subspace. The received space size here can be the size of the empty space or the size shown in the space layout diagram.

[0138] Alternatively, the size of a subspace (which can be represented in the spatial layout diagram) can be determined based on the user's dragging action. For example, if a user drags a rectangle to change its size, the size of the rectangle when the user stops dragging is the size of the subspace corresponding to that rectangle in the spatial layout diagram. As another example, a user can drag the edge lines, intersections, etc., of a subspace displayed on the screen of the electronic device 100 to change the size of that subspace, thus allowing the electronic device 100 to obtain the size of that subspace.

[0139] As an alternative implementation, the above methods can be combined to obtain the size of the subspace. For example, the size of the selected subspace within the detection area can be obtained by detection, and then the user can manually modify the size of the space. Afterward, the electronic device 100 will use the modified size as the size of the space in the space information of the subspace, and this size is the actual size of the space.

[0140] Once the dimensions of the selected subspace are obtained, its annotation position in the scene annotation interface can be determined based on these dimensions. Then, the subspace's identifier can be placed at the corresponding annotation position on the spatial layout diagram. The subspace identifier can be, for example, as follows: Figure 5 and Figure 6 The rectangle shown can also be in other forms, depending on the specific needs.

[0141] Optionally, spatial information may also include space type. For example, when the detection area is a family space, the space type of the subspace can be: study area, activity area, kitchen area, etc. This space type can be manually selected or entered by the user in the scene annotation interface. Optionally, the user can customize the space type in the scene annotation interface of server 600 or electronic device 100. During use, the user can select the space type of a specific subspace to complete the setting. When annotating subspaces, one can also... Figure 4 As shown, the space type is labeled at the corresponding subspace in the space layout diagram so that users can clearly understand the attributes of the subspace.

[0142] Optionally, spatial information may also include location information. When there are multiple subspaces, the location information of each subspace can be combined to label multiple subspaces in the home environment image. The location information can be input by the user based on the actual distribution of the subspaces. This ensures that the distribution of subspaces in the home environment image matches the actual distribution of subspaces, making it easier for users to match the labeled objects in the home environment image with real objects.

[0143] Optionally, users can also set the background, texture, etc. of the subspace, and the electronic device 100 can also annotate the above information in the scene annotation interface.

[0144] This application also provides an application scenario, in which the above-described target annotation processing method is applied as follows: Figure 9 As shown in the figure. In this application scenario, the above-described target annotation processing method is used to obtain a home environment image.

[0145] First, the electronic device 100 displays a home scene annotation interface.

[0146] 1. Perform spatial annotation.

[0147] Users can select the type of subspace in the home scene annotation interface, such as sofa area, study area, activity area, TV area, kitchen area, etc. Subspaces can be room-level, such as bedroom; or small areas, such as sofa area, TV area, etc. Then, the size of the selected subspace can be defined.

[0148] Optionally, the size of the subspace can be set by the user through dragging and dropping in the home scene annotation interface, or it can be the size that the user manually enters. These two sizes represent the size of the subspace when it is annotated in the home scene annotation interface.

[0149] The size of the subspace can also be obtained as follows: The user moves to the edge of the selected subspace within the detection area and then clicks the "Space Annotation" button in the home scene annotation interface to input a space annotation operation. After receiving the space annotation operation, the electronic device 100 sends a location request to the millimeter-wave device sequentially through the cloud server, gateway, or router; the millimeter-wave device then returns the detected location of the person to the gateway or router. The location returned by the millimeter-wave device can be the location of the person represented by the millimeter-wave device as a reference point. The gateway or router can perform coordinate system transformation on the location returned by the millimeter-wave device to determine the size of the selected subspace (i.e., the space information as shown in 9) and the location of the subspace (i.e., the location coordinates at the edge of the subspace) in a preset coordinate system, and then returns the location and size of the subspace to the electronic device 100 via the cloud server. The electronic device 100 can display the received location and size of the subspace, and then, based on the location and size of the subspace, annotate the subspace in the home scene annotation interface and display it on the home scene annotation interface after the subspace annotation is completed.

[0150] Optionally, users can also enter other attributes of the selected subspace in the home scene interface, and mark the entered attributes in the subspace in the home scene annotation interface.

[0151] Understandably, when there are multiple subspaces, the above process can be repeated for the remaining unlabeled subspaces to complete the labeling of each subspace. In this way, a home space layout diagram can be created.

[0152] Second, it allows for general labeling of controllable equipment.

[0153] Users can first select the appliance type in the home scene annotation interface, such as choosing the type of controllable device to be annotated from appliance types like refrigerator, color TV, sensor, and curtain motor. After selecting the appliance type, the electronic device 100 can display the unique device number of each selected appliance type in the home scene annotation interface; users can then select the unique device number of the controllable device to be annotated from the displayed unique device numbers.

[0154] After the user selects a unique device number, the electronic device 100 can display a prompt message on the home scene annotation interface to instruct the user to move to the actual location of the selected controllable device. After the user moves to the location, they can click the "Appliance Annotation" button on the home scene annotation interface to input annotation operations for the selected controllable device.

[0155] Upon receiving the annotation operation, electronic device 100 can sequentially send a location request to the millimeter-wave device via a cloud server, gateway, or router. The millimeter-wave device then returns the detected location of the person to the gateway or router. The location returned by the millimeter-wave device can be a location represented by the millimeter-wave device as a reference point. The gateway or router can perform coordinate system transformation on the location returned by the millimeter-wave device to obtain the person's location in a preset coordinate system, store the location as the appliance location, and then return this appliance location to electronic device 100 via the cloud server. Electronic device 100 can display the appliance location, determine its annotation position on the home space layout map based on the appliance location, and then mark the location with the unique device number selected by the user. It can also display a home scene annotation interface with the marked controllable device.

[0156] Third, it can also quickly label controllable equipment.

[0157] Users can first select the type of appliance in the home scene labeling interface. For example, they can select the type of controllable device to be labeled from appliance types such as refrigerator, color TV, sensor, and curtain motor.

[0158] After the user selects the appliance type, the electronic device 100 can display prompts on the home scene annotation interface to guide the user to the actual location of the selected controllable device. Before, during, or after the user moves the device, the user can use the electronic device 100 to control the selected controllable device via a cloud server, gateway, or router to trigger appliance reporting. After receiving the appliance information reported by the controllable device, the gateway or router can report the appliance information to the cloud server. The appliance information includes a unique device number, eliminating the need for the user to manually search for the unique device number.

[0159] After the user moves to the designated location, the user can also click the "Appliance Labeling" button on the home scene labeling interface to input labeling operations for the selected controllable device.

[0160] Upon receiving the annotation operation, electronic device 100 can sequentially send a location request to the millimeter-wave device via a cloud server, gateway, or router. The millimeter-wave device then returns the detected location of the person to the gateway or router. The location returned by the millimeter-wave device can be a location represented by the millimeter-wave device as a reference point. The gateway or router can perform coordinate system transformation on the location returned by the millimeter-wave device to obtain the person's location in a preset coordinate system, and store the location as an appliance location by combining it with the appliance information reported by the gateway or router. Then, it returns the appliance information and appliance location to electronic device 100 via the cloud server, or returns the description information of the corresponding identifier and appliance location to electronic device 100. Electronic device 100 can display the information returned by the cloud server, determine the annotation location in the home space layout diagram based on the appliance location, and then mark the corresponding identifier at the marked location. It can also display a home scene annotation interface with the identifier of the controllable device.

[0161] Fourth, label uncontrollable objects.

[0162] Uncontrollable objects include uncontrollable electrical appliances, uncontrollable household items, and empty objects.

[0163] For example, users can first select the type of uncontrollable item in the home scene annotation interface. For example, refrigerator, sofa, etc. After selecting the type of uncontrollable item, the electronic device 100 can display the various icons under the selected uncontrollable item type in the home scene annotation interface; users can select the icon of the uncontrollable object to be annotated from the displayed icons.

[0164] After the user selects an icon, the electronic device 100 can display prompts on the home scene annotation interface to instruct the user to move to the actual location corresponding to the selected icon. Once the user has moved to the correct location, they can click the "Item Annotation" button on the home scene annotation interface to input annotation operations for the selected uncontrollable object.

[0165] Upon receiving the annotation operation, electronic device 100 can sequentially send a location request to the millimeter-wave device via a cloud server, gateway, or router. The millimeter-wave device then returns the detected location of the person to the gateway or router. The location returned by the millimeter-wave device can be a location represented by the millimeter-wave device as a reference point. The gateway or router can perform coordinate system transformation on the location returned by the millimeter-wave device to obtain the person's location in a preset coordinate system, store the location as an object location, and then return this object location to electronic device 100 via the cloud server. Electronic device 100 can display the received object location and determine the annotation location on the home space layout map based on the object location. It can then mark the user-selected icon at that marked location and can also display a home scene annotation interface with icons for uncontrollable objects.

[0166] In this way, any object in the home space can be labeled to obtain an image of the home environment.

[0167] To perform the corresponding steps in the above embodiments and various possible methods, an implementation of the target annotation processing apparatus 700 is given below. Please refer to... Figure 10 , Figure 10 This is a block diagram of the target annotation processing device 700 provided in this application embodiment. It should be noted that the target annotation processing device 700 provided in this embodiment has the same basic principle and technical effects as the above embodiments. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. This target annotation processing device 700 can be applied to the electronic device 100 described above. The target annotation processing device 700 may include: a display module 710 and a processing module 720.

[0168] The display module 710 is used to display the scene annotation interface. The scene annotation interface includes a spatial layout diagram of the detection area.

[0169] The processing module 720 is used to respond to the annotation operation on the selected target object and obtain the annotation position of the target object in the spatial layout map based on the actual position of the target object in the detection area.

[0170] The display module 710 is also used to display the identifier of the marked target object at the marked location in the spatial layout diagram.

[0171] Optionally, in this embodiment, the processing module 720 is specifically used to: in response to the annotation operation for the selected target object, determine that the reference object is located at the target object, obtain the real position information of the detected reference object in the detection area, and determine the annotation position of the target object based on the real position information.

[0172] Optionally, in this embodiment, the processing module 720 is specifically used to: in response to a selection operation for a target object, display prompt information indicating that a reference object should be moved to the target object; in response to a labeling operation for a target object, determine that the reference object is located at the target object, and determine the labeling position of the target object based on the actual position information of the reference object.

[0173] Optionally, in this embodiment, the real location information is obtained through millimeter-wave radar.

[0174] Optionally, in this embodiment, the target object includes a first target object, which is a controllable device with communication capabilities; the processing module 720 is specifically used to: for the first target object, in response to a device selection operation for the first target object, determine the device identifier of the selected first target object; in response to a labeling operation for the selected first target object, obtain the labeling position of the first target object in the spatial layout diagram based on the device identifier and the actual position of the first target object in the detection area.

[0175] Optionally, in this embodiment, the target object includes a first target object, which is a controllable device with communication capabilities; the processing module 720 is specifically used to: receive the device identifier reported by the selected first target object; and in response to the annotation operation for the selected first target object, obtain the annotation position of the first target object in the spatial layout diagram based on the device identifier and the real position of the first target object in the detection area.

[0176] Optionally, in this embodiment, the target object includes a second target object, which includes uncontrollable items and empty objects; the processing module 720 is specifically used to: for the second target object, in response to the identification selection operation for the second target object, determine the identification of the selected second target object; in response to the annotation operation for the selected second target object, obtain the annotation position of the second target object in the spatial layout diagram based on the identification of the second target object and the real position of the second target object in the detection area.

[0177] Optionally, in this embodiment, the detection area includes at least one subspace, and the processing module 720 is further configured to: for the subspace, in response to the annotation operation for the selected subspace, obtain the annotation position of the subspace in the scene annotation interface based on the size of the subspace in the detection area; the display module 710 is further configured to: display the identifier of the annotated subspace at the annotation position corresponding to the subspace.

[0178] Optionally, in this embodiment, the size of the subspace is obtained through millimeter-wave radar.

[0179] Please refer to Figure 11 , Figure 11This is a block diagram of an electronic device 100 provided in an embodiment of this application. Figure 11 As shown, the electronic device 100 may include one or more of the following components: processor 110, memory 120, and one or more application programs, wherein the one or more application programs may be stored in memory 120 and configured to be executed by one or more processors 110, and the one or more programs are configured to perform the target annotation processing method as described in the foregoing method embodiments.

[0180] Processor 110 may include one or more processing cores. Processor 110 connects to various parts within the electronic device 100 using various interfaces and lines, and performs various functions and processes data of the electronic device 100 by running or executing instructions, programs, code sets, or instruction sets stored in memory 120, and by calling data stored in memory 120. Optionally, processor 110 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 110 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 110 and may be implemented separately using a communication chip.

[0181] The memory 120 may include random access memory (RAM) or read-only memory (ROM). The memory 120 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created by the electronic device 100 during use. Those skilled in the art will understand that... Figure 11 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device 100 described above. For example, the electronic device 100 may also include components that are more... Figure 11The more or fewer components shown, or having the same Figure 11 The different configurations shown.

[0182] This application also provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the target annotation processing method described above.

[0183] In summary, the embodiments of this application provide a target annotation processing method, apparatus, electronic device, and readable storage medium, displaying a scene annotation interface including a spatial layout map of a detection area. Upon receiving an annotation operation for a selected target object, in response to the annotation operation, based on the target object's actual position in the detection area, the annotation position of the target object in the spatial layout map is obtained, and then the labeled target object's identifier is displayed at that annotation position. In this way, the identifier of the target object can be automatically displayed at the annotation position in the spatial layout map of the detection area corresponding to its actual position, thereby avoiding situations where the object's position in the image does not correspond to its actual position, improving annotation quality and efficiency.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0185] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0186] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in 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.

[0187] The above description is merely an optional embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A target annotation processing method, characterized in that, The method includes: A scene annotation interface is displayed, which includes a spatial layout diagram of the detection area; In response to the annotation operation for the selected target object, the annotation position of the target object in the spatial layout diagram is obtained based on the actual position of the target object in the detection area; At the marked locations in the spatial layout diagram, the identifier of the marked target object is displayed; The step of responding to the annotation operation for the selected target object, and obtaining the annotation position of the target object in the spatial layout map based on the actual position of the target object in the detection area, includes: In response to a selection operation for the target object, a prompt message is displayed to instruct a reference object to move to the target object, the reference object being an object used as a location detection carrier; In response to the annotation operation for the target object, it is determined that the reference object is located at the target object, and the real position information of the reference object in the detection area is obtained by the position detection device. The real position information of the reference object is used as the real position information of the target object, and the annotation position of the target object is determined according to the real position information of the target object.

2. The method according to claim 1, characterized in that, The actual location information is obtained through millimeter-wave radar.

3. The method according to claim 1, characterized in that, The target object includes a first target object, which is a controllable device with communication capabilities; The step of responding to the annotation operation for the selected target object, and obtaining the annotation position of the target object in the spatial layout diagram based on the actual position of the target object in the detection area, includes: For the first target object, in response to the device selection operation for the first target object, the device identifier of the selected first target object is determined; In response to the annotation operation for the selected first target object, the annotation position of the first target object in the spatial layout diagram is obtained based on the device identifier and the actual position of the first target object in the detection area.

4. The method according to claim 1, characterized in that, The target object includes a first target object, which is a controllable device with communication capabilities; The step of responding to the annotation operation for the selected target object, and obtaining the annotation position of the target object in the spatial layout diagram based on the actual position of the target object in the detection area, includes: Receive the device identifier reported by the selected first target object; In response to the annotation operation for the selected first target object, the annotation position of the first target object in the spatial layout diagram is obtained based on the device identifier and the actual position of the first target object in the detection area.

5. The method according to claim 1, characterized in that, The target object includes a second target object, which includes uncontrollable items and empty objects; The step of responding to the annotation operation for the selected target object, and obtaining the annotation position of the target object in the spatial layout diagram based on the actual position of the target object in the detection area, includes: For the second target object, in response to the identifier selection operation for the second target object, the identifier of the selected second target object is determined; In response to the annotation operation for the selected second target object, the annotation position of the second target object in the spatial layout diagram is obtained based on the identifier of the second target object and the actual position of the second target object in the detection area.

6. The method according to claim 1, characterized in that, The detection region includes at least one subspace, and the method further includes: For the subspace, in response to the annotation operation for the selected subspace, the annotation position of the subspace in the scene annotation interface is obtained based on the size of the subspace in the detection area; The identifier of the subspace is displayed at the labeled position corresponding to the subspace.

7. The method according to claim 6, characterized in that, The dimensions of the subspace are obtained using millimeter-wave radar.

8. A target annotation processing device, characterized in that, The device includes: The display module is used to display the scene annotation interface, wherein the scene annotation interface includes a spatial layout map of the detection area; The processing module is used to respond to the annotation operation for the selected target object and obtain the annotation position of the target object in the spatial layout diagram based on the actual position of the target object in the detection area. The display module is also used to display the identifier of the marked target object at the marked position in the spatial layout diagram; Specifically, the processing module is used to: in response to a selection operation on the target object, display prompt information indicating that a reference object is moved to the target object, wherein the reference object is an object used as a location detection carrier; in response to a labeling operation on the target object, determine that the reference object is located at the target object, obtain the real location information of the reference object within the detection area detected by the location detection device, use the real location information of the reference object as the real location information of the target object, and determine the labeling position of the target object based on the real location information of the target object.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the target annotation processing method according to any one of claims 1-7.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the target annotation processing method as described in any one of claims 1-7.

Images