Object display method and device, object recognition method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to an object display method and device, an object recognition method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of Internet of Things. According to the method, the type of the target object can be accurately displayed. The method comprises the steps that a monitoring page of a target device is displayed, the monitoring page comprises a monitoring area, the monitoring area displays a target object identifier, the target object identifier represents a target object monitored by the target device, the target object identifier corresponds to a target object type, and the target object type represents an identified object type of the target object; in response to an operation triggered for the target object identifier, determining an object type changed by the target object; and changing the display of the target object identifier according to the changed object type, and identifying the new target object by applying the changed object type.

Description

Technical Field

[0001] This application relates to the technical field of the Internet of Things, and particularly to an object display method, an object recognition method, a device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the development of the Internet of Things (IOT) technology, various intelligent devices are being rapidly popularized. For example, various smart home devices, etc. Some devices can monitor and identify target objects and display information such as their locations and types.

[0003] In the current technology, a large amount of relevant data of objects can be pre-collected for training so that the device can monitor and identify target objects. However, due to factors such as the complexity of the monitoring environment, target objects with incorrect type identifications may be displayed, resulting in the technical problem of inaccurate display of the type of target objects. Summary of the Invention

[0004] Based on this, in order to solve the above technical problems, it is necessary to provide an object display method, an object recognition method, a device, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] In a first aspect, this application provides an object display method, including:

[0006] Display a monitoring page of a target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents the target object monitored by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type of the target object identified.

[0007] In response to an operation triggered on the target object identifier, determine the object type changed by the target object.

[0008] According to the changed object type, change the display of the target object identifier, and apply the changed object type to identify a new target object.

[0009] In a second aspect, this application provides an object recognition method, including:

[0010] Obtain the feature information of the monitored target object.

[0011] According to the feature information, identify the target object type matched by the target object in the object type set; the object type set includes the changed object type fed back by the terminal.

[0012] Send the target object type of the target object and the location information of the target object to the terminal, so that the terminal can display the monitoring page of the target device according to the target object type and the location information.

[0013] In a third aspect, the present application further provides an object display device, including:

[0014] A page display module, configured to display a monitoring page of a target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents a target object detected by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type of the target object being recognized;

[0015] A type change module, configured to determine the object type of the target object change in response to an operation triggered on the target object identifier;

[0016] A change processing module, configured to change the display of the target object identifier according to the changed object type, and identify a new target object by applying the changed object type.

[0017] In a fourth aspect, the present application further provides an object recognition device, including:

[0018] A feature acquisition module, configured to acquire feature information of a monitored target object;

[0019] A type recognition module, configured to identify the target object type matched by the target object in the object type set according to the feature information; the object type set includes the changed object type fed back by the terminal;

[0020] An information sending module, configured to send the target object type of the target object and the location information of the target object to the terminal, so that the terminal can display the monitoring page of the target device according to the target object type and the location information.

[0021] In a fifth aspect, the present application further provides an electronic device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0022] Display a monitoring page of the target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents the target object detected by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type by which the target object is recognized; in response to an operation triggered on the target object identifier, determine the object type changed by the target object; change the display of the target object identifier according to the changed object type, and recognize a new target object by applying the changed object type.

[0023] In a sixth aspect, the present application further provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0024] Obtain feature information of a detected target object; according to the feature information, identify the target object type matched by the target object in an object type set; the object type set includes the changed object type fed back by the terminal; send the target object type of the target object and the location information of the target object to the terminal for the terminal to display a monitoring page of the target device according to the target object type and the location information.

[0025] In a seventh aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0026] Display a monitoring page of the target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents the target object detected by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type by which the target object is recognized; in response to an operation triggered on the target object identifier, determine the object type changed by the target object; change the display of the target object identifier according to the changed object type, and recognize a new target object by applying the changed object type.

[0027] In an eighth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0028] Obtain the feature information of the monitored target object; according to the feature information, identify the target object type matched by the target object in the object type set; the object type set includes the changed object types fed back by the terminal; send the target object type of the target object and the location information of the target object to the terminal for the terminal to display the monitoring page of the target device according to the target object type and the location information.

[0029] In a ninth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0030] Display the monitoring page of the target device; the monitoring page includes a monitoring area; the monitoring area shows a target object identifier; the target object identifier represents the target object monitored by the target device; the target object identifier corresponds to the target object type; the target object type represents the object type of the target object being recognized; in response to an operation triggered on the target object identifier, determine the object type changed by the target object; change the display of the target object identifier according to the changed object type, and identify the new target object by applying the changed object type.

[0031] In a tenth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0032] Obtain the feature information of the monitored target object; according to the feature information, identify the target object type matched by the target object in the object type set; the object type set includes the changed object types fed back by the terminal; send the target object type of the target object and the location information of the target object to the terminal for the terminal to display the monitoring page of the target device according to the target object type and the location information.

[0033] The above object display method, object recognition method, device, electronic device, storage medium and program product display a monitoring page of a target device. The monitoring page includes a monitoring area, and a target object identifier is displayed in the monitoring area. The target object identifier represents a target object detected by the target device, and the target object identifier corresponds to a target object type, where the target object type represents the type of object that the target object is recognized as; in response to an operation triggered on the target object identifier, determine the object type change of the target object; change the display of the target object identifier according to the changed object type, and recognize a new target object using the changed object type. This solution can display the target object identifier corresponding to the target object type in the monitoring area of the monitoring page of the target device. The user can change the corresponding target object type by triggering an operation on the target object identifier. Thus, the display of the target object identifier can be changed according to the changed type, enabling the monitoring area of the monitoring page to accurately display the type of the target object. Moreover, the changed type can also be used to recognize a new target object, improving the accuracy of recognizing the type of the target object, and further enabling the monitoring area to accurately display the new target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] To more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or the related art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0035] Figure 1 It is an application environment diagram of the related method in an embodiment;

[0036] Figure 2 It is a flowchart of the object display method in an embodiment;

[0037] Figure 3 It is a schematic diagram of a monitoring page in an embodiment;

[0038] Figure 4 It is a schematic diagram of showing optional object types in an embodiment;

[0039] Figure 5 It is a schematic diagram of showing change prompt information in an embodiment;

[0040] Figure 6 It is a flowchart of the object recognition method in an embodiment;

[0041] Figure 7 It is a flowchart of the steps of recognizing the target object type in an embodiment;

[0042] Figure 8 Flow diagram of steps for obtaining feature information in an embodiment;

[0043] Figure 9 Structural block diagram of an object display device in an embodiment;

[0044] Figure 10 Structural block diagram of an object recognition device in an embodiment;

[0045] Figure 11 Internal structure diagram of an electronic device in an embodiment. Detailed implementation manners

[0046] To make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The object display method and object recognition method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 The application environment can be a smart home system, which may include: cloud / cloud server, router, gateway, user terminal (such as mobile phone, tablet), multiple devices (such as smart lamp, smart curtain, smart speaker, smart TV, smart socket, smart air conditioner, sensor, switch, smart door lock, millimeter wave radar), etc. In the smart home system, each device can be connected to the gateway through the ZIGBEE / Bluetooth / matter network, and the gateway and the user terminal can be connected to the router through WiFi respectively. In addition, the user terminal can also establish a network connection with the cloud / cloud server through 2G / 3G / 4G / 5G, WiFi, etc., so as to obtain the data sent by the cloud / cloud server.

[0048] For the smart home system, its system configuration method can be: an application program is installed on the user terminal. First, at least one gateway device can be added on the application program. When adding other devices (such as smart lamps), the add device button on the interface of the application program can be clicked, and the gateway device to which the device needs to be connected can be selected on the add interface, so that the device can be added to the network corresponding to the gateway, and then together with other added devices and the gateway, a local area network can be formed, such as specifically a ZigBee network, a Matter network, a Bluetooth network, a WIFI network, etc. When the application program, the router and the gateway are in the same local area network, the application program can interact with the gateway and the devices connected to the gateway through the local area network path; when the application program, the router and the gateway are not in the same local area network, the application program can interact with the gateway and the devices connected to the gateway through the wide area network path.

[0049] As Figure 1 The smart home system shown may include target devices such as radars that have a monitoring function for target objects such as the human body. In the current technology, a large amount of relevant data of objects can be pre-collected for training so that the target device can monitor and identify the target objects. For example, based on the target recognition function of a millimeter-wave radar, target objects such as people indoors can be identified. After the identification is completed, the target objects monitored by the target device can be intuitively displayed on the user terminal. However, due to factors such as the sensitivity of the target device and the complexity of the monitoring environment, even if a large amount of relevant data of the target objects is collected for training, there will still be cases where the target objects are misidentified. As a result, the target objects with incorrect type recognition may be displayed on the user terminal, and there is a technical problem of inaccurate display of the type of the target object.

[0050] In response to this, the method provided in this application can display the target object identifier corresponding to the target object type in the monitoring area of the monitoring page of the target device. The user can change the corresponding target object type through an operation triggered by the target object identifier. Thus, the display of the target object identifier can be changed according to the changed type, enabling the monitoring area of the monitoring page to accurately display the type of the target object. Moreover, the changed type can also be used to identify new target objects, improving the accuracy of identifying the type of the target object, and further enabling the monitoring area to accurately display the new target object.

[0051] The method of this application will be described in detail below in conjunction with various embodiments and the corresponding drawings.

[0052] In an exemplary embodiment, as Figure 2 shown, an object display method is provided. This method can be applied to the user terminal as Figure 1 and can also be applied to other electronic devices with a screen. Taking the application of this method to the user terminal as Figure 1 an example for illustration, this method may include the following steps:

[0053] Step S201, display the monitoring page of the target device. Among them, the monitoring page includes a monitoring area, and the monitoring area displays a target object identifier. The target object identifier represents the target object monitored by the target device, and the target object identifier corresponds to the target object type, and the target object type represents the object type of the target object identified.

[0054] In this step, the target device can be a target device such as a radar that has a monitoring function for a target object such as a human body. The monitoring page of the target device can be a page for displaying relevant information about the target object monitored by the target device. The relevant information can include the target object identifier, the position of the target object, the target object type, etc. Among them, the monitoring page of the target device can include the monitoring area of the target device. The monitoring area can be used to represent the range that the target device can monitor. The monitoring page of the target device can be used to display the relevant information of the above-mentioned target object, such as the target object identifier, the position of the target object, the target object type, etc. Among them, the target object identifier represents the target object monitored by the target device. The target object identifier can be an icon, and the target object identifier corresponds to the target object type. Different target object types can correspond to different target object identifiers. Among them, the target object type represents the object type of the target object being recognized, and the target device can identify the target object type of the target object. Among them, the position of the target object can be the position of the target object in the monitoring area of the target device. The position of the target object can be obtained according to the distance between the target object and the target device. The distance between the target object and the target device can be monitored by the target device for the target object. The user terminal can, according to this distance, display the corresponding target object identifier at the corresponding position in the monitoring area of the monitoring page in combination with the target object type. Thus, the user can intuitively and clearly view the target object monitored by the target device and its object type in the monitoring area of the monitoring page of the target device displayed on the user terminal.

[0055] As an example, as Figure 3 shown, the user terminal can display the monitoring page 300 of the target device. The monitoring page 300 can include the monitoring area 310 of the target device. The target device identifier T0 can be displayed in the monitoring area 310. The target device identifier T0 represents the target device. The monitoring area 310 can be displayed according to the installation position of the target device in space, and the target device identifier T0 can be marked in the monitoring area 310. In addition, based on the monitoring and identification of various target objects in the monitoring area 310 by the target device, the user terminal can display the target object identifiers (T1 to T4) of various target objects in the monitoring area 310, and the target object identifier corresponds to the target object type. For example, the target object identifier T1 of an adult, the target object identifier T2 of a pet, the target object identifier T3 of a child, the target object identifier T4 of a sweeping robot, etc. can be displayed. Thus, the user can intuitively and clearly view the target object monitored by the target device and its object type in the monitoring area 310.

[0056] Step S202, in response to an operation triggered by the target object identifier, determine the changed object type of the target object.

[0057] In this step, the user can trigger an operation on the target object identifier displayed in the monitoring area 310, and this operation can be used to determine the object type of the target object change. Among them, the object type of the target object change can be the object type that the user indicates the target object needs to change. In this step, the user terminal can determine the object type of the target object change in response to operations triggered by the user on the target object identifier, such as long pressing, clicking, double clicking, etc.

[0058] Step S203: Change the display of the target object identifier according to the changed object type, and identify the new target object by applying the changed object type.

[0059] In this step, after determining the object type of the target object change, the user terminal can change the display of the target object identifier according to the changed object type. Thus, the target object identifier with an incorrect original object type display can be corrected according to the object type determined by the user to be changed, so that the user terminal accurately displays the object type of the target object, and can identify the new target object by applying the changed object type. For example, the object type determined by the user to be changed can be fed back to the target device, and the target device can identify the new target object according to the changed object type and the corresponding characteristic information of the target object, so as to improve the accuracy of the type identification of the target object, and then enable the monitoring area to accurately display the new target object. Among them, the new target object can include the target object monitored by the target device after receiving the changed object type fed back by the user terminal.

[0060] The object display method of this embodiment displays the monitoring page of the target device. The monitoring page includes a monitoring area, and the monitoring area displays a target object identifier, which represents the target object monitored by the target device. The target object identifier corresponds to the target object type, and the target object type represents the object type by which the target object is identified; in response to an operation triggered on the target object identifier, determine the object type of the target object change; change the display of the target object identifier according to the changed object type, and identify the new target object by applying the changed object type. This solution can display the target object identifier corresponding to the target object type in the monitoring area of the monitoring page of the target device. The user can change the corresponding target object type by triggering an operation on the target object identifier. Thus, the display of the target object identifier can be changed according to the changed type, so that the monitoring area of the monitoring page accurately displays the type of the target object, and the changed type can also be used to identify the new target object, improving the accuracy of the type identification of the target object, and then enabling the monitoring area to accurately display the new target object.

[0061] In an exemplary embodiment, determining the object type of the target object change in response to an operation triggered by the target object identifier in step S202 may include:

[0062] In response to an operation triggered by the target object identifier, display at least one first object type option; the first object type option is used to represent an optional object type; obtain the object type of the target object change according to the selected first object type option; or, in response to an addition operation for the optional object type, display a second object type option; the second object type option is used to represent the added object type; obtain the changed object type according to the selected first object type option or the second object type option.

[0063] In this embodiment, after the user triggers an operation on the target object identifier, some object type options can be displayed for the user to make changes, and on the basis of these displayed object type options, the user can also add object types. Thus, the user can either select the object types provided by the terminal for changes or select the added object types for changes, improving the flexibility of object type changes and making the display of the object type of the target object in the monitoring area more accurate.

[0064] Combined with Figure 4, the user can trigger operations such as long - press, click, double - click, etc. on the target object identifier T4 in the monitoring area 310, such as a floor - cleaning robot. The user terminal can respond to this operation and display at least one first object type option, which is used to represent optional object types, such as object types like adult, child, pet, interference source, etc. Thus, the user can select one of the at least one first object type options. If the selected first object type option corresponds to an adult, the user terminal can obtain that the object type of the target object change is, for example, an adult according to the selected first object type option. In addition to directly selecting the first object type option, the user can also trigger an addition operation for the optional object type, such as triggering operations like long - press, click, double - click, etc. on the new component “…”. This addition operation can be used for the user to add to the optional object type. The user terminal can respond to this addition operation and display a second object type option, which can be used to represent the added object type. Among them, the added object type can be an object type different from the optional object types represented by the above - mentioned first object type options. For example, the added object type can include cats, dogs, plants, etc. The added object type can be obtained by the user inputting in ways such as text, voice, etc. The user terminal can display the corresponding second object type option according to the added object type input by the user. Thus, the user terminal can display the first object type option and the second object type option. The user can select the first object type option or the second object type option, and the user terminal can obtain the changed object type according to the selected first object type option or second object type option.

[0065] In an exemplary embodiment, before changing the display of the target object identifier according to the changed object type and identifying the new target object by applying the changed object type in step S203, the following steps may also be included:

[0066] Display the corresponding change prompt information according to the changed object type; the change prompt information is used to predict the effect after the change of the target object type; in response to the confirmation operation on the change prompt information, execute the steps of changing the display of the target object identifier according to the changed object type and identifying the new target object by applying the changed object type.

[0067] The solution of this embodiment can display the change prompt information to predict the effect after changing the target object type before determining to change the target object type of the target object, so as to reduce the user's misoperation and improve the accuracy and efficiency of changing the target object type.

[0068] Combined with Figure 4 Figure 5, the user can change the object type for the target object identifier T4 of the floor sweeping robot on the monitoring page 300. For example, the user can select an adult or a disturbance source represented in the first object type option for the change and then click Next. Based on this, taking the selection of an adult as the changed object type as an example, as shown in the monitoring page 300 indicated by (a) in Figure 5 , the monitoring page 300 can display corresponding change prompt information 320 according to the changed object type, i.e., an adult. The change prompt information 320 can be used to predict the effect after the change of the target object type, that is, the effect after changing to an adult. Taking the selection of a disturbance source as the changed object type as an example, as shown in the monitoring page 300 indicated by (b) in Figure 5 , the monitoring page 300 can display corresponding change prompt information 320 according to the changed object type, i.e., a disturbance source. The change prompt information 320 can be used to predict the effect after the change of the target object type, that is, the effect after changing to a disturbance source. Thus, the user can clearly know the effect after the change of the target object type, and then the user can trigger a confirmation operation on the change prompt information, such as clicking "OK" in the change prompt information 320. The user terminal can respond to this confirmation operation and execute the above step S203 "Change the display of the target object identifier according to the changed object type and identify the new target object by applying the changed object type".

[0069] In an exemplary embodiment, changing the display of the target object identifier according to the changed object type in step S203 may include:

[0070] If the changed object type does not belong to the preset object type, display the changed target object identifier; if the changed object type belongs to the preset object type, remove the display of the target object identifier.

[0071] In this embodiment, different change processes can be performed on the target object identifier for different changed object types, improving the flexibility and adaptability of the display of the target object identifier. Among them, if the changed object type does not belong to the preset object type, the user terminal can continue to display the changed target object identifier in the monitoring area 310; if the changed object type belongs to the preset object type, the user terminal can remove the display of the corresponding target object identifier in the monitoring area 310. In practical applications, the preset object type may include a disturbance source. Combining Figure 5, if the object type to be changed belongs to an interference source, the user terminal can remove the display of the target object identifier of the target object in the monitoring area 310, and in some embodiments, the user terminal can also set the regional position of the target object identifier in the monitoring area 310 as an interference position, so that the target device can not subsequently identify the target object based on this interference position. If the object type to be changed is an adult and does not belong to an interference source, the user terminal can replace the target object identifier T4 with a target object identifier representing an adult in the monitoring area 310.

[0072] In an exemplary embodiment, the application of the changed object type to identify a new target object in step S203 may include:

[0073] Feedback the changed object type to the target device for the target device to apply the changed object type to the identification of the new target object.

[0074] In this embodiment, after determining the object type of the target object change, the user terminal can send the changed object type to the target device. The target device can identify the new target object according to the changed object type and the feature information of the target object corresponding to the changed object type, thereby improving the accuracy of the target device in identifying the new target object, and further enabling the user terminal to accurately display the new target object identified by the target device.

[0075] In an exemplary embodiment, before displaying the monitoring page of the target device in step S201, it may further include: receiving the target object information sent by the target device; the target object information includes the position information of the target object and the target object type of the target object; obtaining the target object identifier corresponding to the target object type; the display of the monitoring page in step S201 may include: displaying the monitoring page according to the position information and the target object identifier.

[0076] In this embodiment, the user terminal can receive the position information of the target object and the target object type of the target object reported by the target device, display the monitoring page according to the target object identifier corresponding to the target object type and the position information of the target object, and display the target object identifier in the monitoring area of the monitoring page. Among them, the user terminal can store the target object identifiers corresponding to various target object types. The target device can monitor and identify the position information of the target object and its target object type, and then send the target object information including the position information of the target object and its target object type to the user terminal. The user terminal can obtain the corresponding target object identifier according to the target object type, so as to display the monitoring page and display the target object identifier corresponding to the target object in the monitoring area of the monitoring page according to the position information of the target object.

[0077] In an exemplary embodiment, as Figure 6 shown, an object recognition method is provided. This method can be applied to a target device such as a radar that has a monitoring function for a target object such as a human body. The method may include the following steps:

[0078] Step S601, obtain the feature information of the monitored target object.

[0079] In this step, the target device can monitor the target object and obtain the feature information of the monitored target object. Among them, the feature information may include information for identifying the target object, and may include static feature information of the target object, such as shape, size, coordinates, etc., or may also include dynamic feature information of the target object, such as speed, acceleration, etc.

[0080] Step S602, according to the feature information, identify the target object type that matches in the object type set. The object type set contains the changed object types fed back by the terminal.

[0081] In this step, the target device can, according to the feature information, identify the target object type that matches in the object type set by means of, for example, a classification model for classifying the target object. Among them, the object type set may include multiple object types, and this object type set can be stored on the target device. The object type set includes the changed object types fed back by the terminal (user terminal), and each object type is bound with corresponding feature information. Among them, regarding the changed object types, reference can be made to the content disclosed in the relevant embodiments of the foregoing object display method, which will not be elaborated here. The target device can identify the target object type that matches the target object according to the feature information of the target object and the feature information associated with each object type.

[0082] Step S603, send the target object type of the target object and the location information of the target object to the terminal for the terminal to display the monitoring page of the target device according to the target object type and the location information.

[0083] In this step, after the target device identifies the target object type of the target object and monitors the location information of the target object, it can send the target object type of the target object and the location information of the target object to the terminal. Among them, the location information of the target object can be obtained according to the distance between the target device and the target object. Thus, the terminal can display the monitoring page of the target device according to the target object type and the location information. Among them, regarding the monitoring page of the terminal, reference can be made to the content disclosed in the relevant embodiments of the foregoing object display method, which will not be elaborated here.

[0084] In the solution of this embodiment, the target device can identify the target object in combination with the changed object type fed back by the terminal, improve the accuracy of identifying the type of the target object, and further enable the monitoring area to accurately display the target object.

[0085] In an exemplary embodiment, the object type set may include a first object type subset and a second object type subset; the first object type subset is obtained according to the object types recognizable by the classification model; the second object type subset is obtained according to the changed object type fed back by the terminal. As Figure 7 shown, the step of identifying the target object type matched by the target object in the object type set according to the feature information in step S602 may include:

[0086] Step S701, input the feature information into the classification model, and the classification model identifies the first matching degree between the target object and each object type in the first object type subset.

[0087] In this step, the target device inputs the feature information of the target object into the classification model. Among them, the classification model can be used to identify the object type of the target object. The classification model can identify the object type of the target object in the first object type subset and obtain the matching degree (denoted as the first matching degree) between the target object and each object type in the first object type subset. The first matching degree can be represented by a value from 0 to 1. Among them, the first object type subset may include various object types recognizable by the classification model. Among them, the classification model can be trained based on the feature information samples of target objects of various object types, and can be trained for a multi-classification task based on the feature information samples of target objects of various object types to obtain a trained classification model. The trained classification model can identify the target object and can identify the first matching degree of the target object belonging to object types such as adults, children, pets, or floor-sweeping robots. In practical applications, machine learning or deep learning networks can be selected for multi-classification task training.

[0088] Step S702, according to the correlation between the feature information and each reference feature information, obtain the second matching degree between the target object and each object type in the second object type subset. Among them, the reference feature information is the feature information bound to the object type in the second object type subset.

[0089] In this step, the target device can calculate the correlation between the feature information of the target object and each piece of reference feature information to obtain the matching degree (denoted as the second matching degree) between the target object and each object type in the second object type subset. Among them, the reference feature information refers to the feature information bound to the object types in the second object type subset. Among them, the second object type subset can be obtained according to the changed object types fed back by the terminal. The target device can form the second object type subset from various changed object types fed back by the terminal. When the target device receives the changed object types fed back by the terminal, it can bind the changed object types to the feature information of the corresponding target object to obtain the above-mentioned reference feature information. In practical applications, both the feature information and the reference feature information can be represented by feature vectors. The second matching degree between the target object and each object type in the second object type subset can be obtained by calculating the correlation between the feature vector of the feature information and the feature vector of the reference feature information. The second matching degree can be represented by a value from 0 to 1.

[0090] Step S703: Identify the target object type that the target object matches in the object type set according to the first matching degree and the second matching degree.

[0091] In this step, the target device can comprehensively consider the first matching degree and the second matching degree to identify the target object type that the target object matches in the object type set. For example, the first matching degree and the second matching degree can be summed up, and the target object type that the target object matches in the object type set can be identified according to the magnitude of the summed matching degree.

[0092] The solution of this embodiment can identify the target object type of the target object by combining the object type identified by the classification model and the object types whose changes are confirmed by the user and fed back by the terminal, improving the accuracy and reliability of the identification. When combining the object types whose changes are confirmed by the user and fed back by the terminal, there is no need to collect a large amount of data, saving computing resources. Moreover, the object type set can be stored in the target device, making it safer and more reliable without consuming platform and system resources.

[0093] In an exemplary embodiment, before obtaining the second matching degree between the target object and each object type in the second object type subset according to the correlation between the feature information and each piece of reference feature information in step S702, the above method may further include the following steps:

[0094] If the changed object types for the already identified target object are received from the terminal feedback, then use the feature information when creating the already identified target object as the reference feature information to bind to the changed object types, and add the changed object types to the second object type subset.

[0095] In this embodiment, the target device may bind the object type of the change in the identified target object fed back by the terminal and the feature information when creating the identified target object as reference feature information to the changed object type, and add it to the second object type subset for identifying a new target object. Among them, the same target object may have different feature information in different positions and postures. In order to obtain reference feature information that can be used to identify a new target object, it is necessary to ensure that the target object has the same posture or behavior at this position. Since the posture and behavior of the target object are relatively fixed when it is first created, this embodiment retains the feature information of the identified target object of the target device when it is first created as reference feature information. Among them, the identified target object may be a target object that has been identified by the target device and the corresponding target object identifier is displayed by the user terminal. The user can change the object type of the target object on the user terminal. As a result, the target device will receive the changed object type of the identified target object fed back by the terminal. When the target device detects the target object, it will create the target object and save the feature information of the target object. Therefore, when the target device receives the changed object type of the target object, it can bind the feature information as reference feature information to the changed object type.

[0096] In an exemplary embodiment, according to the first matching degree and the second matching degree, identifying the target object type matched by the target object in the object type set in step S703 may include:

[0097] For each object type in the object type set, weight the first matching degree and the second matching degree of the object type to obtain the comprehensive matching degree of each object type; determine the target object type according to the comprehensive matching degree of each object type.

[0098] In this embodiment, weights can be set for the first object type subset and the second object type subset in the object type set. The weights can be dynamically changed or fixed. Thus, for each object type in the object type set, the first matching degree and the second matching degree of the object type can be weighted according to the corresponding weights, and the weighted result is used as the comprehensive matching degree of the object type. In this way, the comprehensive matching degree of each object type can be obtained. Then, according to the ranking of the comprehensive matching degree of each object type, the object type with the largest comprehensive matching degree can be determined as the target object type. The solution of this embodiment can set weights for the first object type subset and the second object type subset in the object type set, and accordingly improve the accuracy of identifying the target object type by combining the classification model and user feedback.

[0099] In an exemplary embodiment, such as Figure 8As shown, the obtaining of the feature information of the monitored target object in step S601 may include:

[0100] Step S801, obtain the point cloud of the target object.

[0101] In this step, the target device can obtain the point cloud of the target object. Thus, the target device can extract the feature information based on the point cloud of the target object. Among them, the target device can monitor various objects within its monitoring range and record the monitored various objects in the form of point clouds. The point cloud recorded in one monitoring can correspond to one frame. The point cloud in this frame can be recorded as the original point cloud. The target device can cluster the original point cloud of this frame. For example, it can use DBSCAN (Density-Based Spatial Clustering of Applications with Noise) for clustering. Thus, the point clouds of various target objects can be clustered, and the point cloud of each frame can be associated with the target object.

[0102] Step S802, obtain the spatial feature information and / or motion feature information of the target object according to the point cloud.

[0103] In this step, the target device can obtain the spatial feature information and / or motion feature information of the target object according to the point cloud of the target object. Among them, the spatial feature information may include information such as the position, shape, attitude, and spatial distribution of the target object, which can be used as information to describe the static features of the target object in the target space. This target space can be the space where the target device monitors the target object. In the smart home scenario, the target space can be the living room, room, etc. Among them, the motion feature information may include motion parameters of the target object (such as speed, acceleration, angular velocity, etc.), motion trajectory, and changes in motion state (such as start / stop, turning, acceleration / deceleration, etc.), which can be used as information to describe the dynamic features of the target object in the target space.

[0104] Step S803, obtain the feature information of the target object according to the spatial feature information and / or motion feature information.

[0105] In this step, the target device can use the spatial feature information and / or motion feature information as the feature information of the target object.

[0106] The solution of this embodiment is based on the point cloud of the target object, can accurately and completely record the data of the target object in space, and then accurately and completely describe the spatial feature information and / or motion feature information of the target object. Thus, the accurate feature information of the target object can be obtained.

[0107] In an exemplary embodiment, obtaining the spatial feature information and / or motion feature information of the target object according to the point cloud in step S802 above may include:

[0108] Obtaining spatial feature information according to the spatial distribution information of the point cloud in the target space range; the target space range is determined according to the space range occupied by the reference object in the target space; and / or, obtaining motion feature information according to the speed distribution information of the point cloud in the target speed range; the target speed range is determined according to the speed range of the reference object in the target space. Wherein, the target space is the space monitored by the target device.

[0109] In this embodiment, on the one hand, the target device can obtain spatial feature information according to the spatial distribution information of the point cloud in the target space range. Wherein, the target space range is determined according to the space range occupied by the reference object in the target space. Wherein, the reference object can be determined according to the space ranges occupied by various objects that can be monitored in the target space. For example, the object that can occupy the largest space range can be selected as the reference object. For example, an adult can be selected as the reference object. Wherein, the target space can be the space where the target device monitors the target object. In the smart home scenario, the target space can be the living room, a room, etc. Thus, by determining the target space range according to the space range occupied by the reference object in the target space, the space range occupied by the reference object in the target space can be determined as the target space range. If the object that can occupy the largest space range is selected as the reference object as described above, the target space range can be used to analyze the feature information covering various objects that can be monitored in the spatial dimension. Wherein, the spatial distribution information of the point cloud in the target space range may include the distribution of the point cloud of the target object within the target space range, which can be the distribution of the point cloud in one or more spatial dimensions. For example, it can be the distribution of the point cloud in the three spatial dimensions represented by the x, y, and z axes, etc. Thus, the target device can obtain spatial feature information according to the distribution of the point cloud of the target object in one or more spatial dimensions within the target space range.

[0110] In this embodiment, on the other hand, the target device may obtain motion feature information according to the velocity distribution information of the point cloud within the target velocity range. Wherein, the target velocity range is determined according to the velocity range of the reference object in the target space. The reference object may be determined according to the velocity ranges of the various objects that can be monitored in the target space. For example, the object with the largest velocity range may be selected as the reference object. For example, an adult may be selected as the reference object. Thus, the target velocity range is determined according to the velocity range of the reference object in the target space, and the velocity range of the reference object in the target space may be determined as the target velocity range. Thus, the target velocity range can cover various objects that can be monitored in the velocity dimension for feature information analysis.

[0111] In an exemplary embodiment, obtaining spatial feature information according to the spatial distribution information of the point cloud within the target space range may include: if there is a first point cloud of the target object outside the target space range, selecting a second point cloud that satisfies the target space range based on the center point cloud of the target object, and obtaining spatial feature information according to the spatial distribution information of the second point cloud within the target space range; and / or, obtaining motion feature information according to the velocity distribution information of the point cloud within the target velocity range may include: if there is a third point cloud of the target object outside the target velocity range, obtaining motion feature information according to the velocity distribution information of the fourth point cloud of the target object within the target velocity range.

[0112] In this embodiment, for the spatial feature information, the target device can determine whether there is point cloud (denoted as the first point cloud) of the target object located outside the target space range. If there is the first point cloud of the target object, the target device can select the point cloud that meets the target space range (denoted as the second point cloud) based on the central point cloud of the target object, so as to obtain the spatial feature information according to the spatial distribution information of the second point cloud in the target space range. Among them, the target space range can include the target space ranges of multiple spatial dimensions, and the target space range is represented by the position coordinate interval of the corresponding spatial dimension. Taking the spatial dimension represented by the x-axis as an example, in this spatial dimension, the target space range can be expressed as [0, 1], where 1 can represent 1 meter. In this embodiment, the minimum value xmin and the maximum value xmax of the position coordinates of the point cloud of the target object in this spatial dimension can be determined. If the difference between the maximum value xmax and the minimum value xmin of the target object is greater than 1, it means that there is the first point cloud of the target object. At this time, the target device can calculate the position coordinate of the central point cloud of the target object in this spatial dimension as "(xmax + xmin) / 2" according to the maximum value xmax and the minimum value xmin. Based on this, the second point cloud that meets the target space range can be selected, and the second point cloud within the target space range can be selected according to the position coordinate of the central point cloud of the target object in this spatial dimension. The position coordinates of the second point cloud in this spatial dimension are within [(xmax + xmin) / 2 - 0.5, (xmax + xmin) / 2 + 0.5]. In addition to the spatial dimension represented by the x-axis, the second point cloud of the target object in each spatial dimension can also be determined in a similar manner. Among them, for different spatial dimensions, the target space range can be the same or different. Thus, obtaining the spatial feature information according to the spatial distribution information of the second point cloud in the target space range can make the spatial feature information include the main spatial features of the target object.

[0113] In this embodiment, for the motion feature information, the target device can determine whether there is point cloud (denoted as the third point cloud) of the target object outside the target speed range. If there is the third point cloud of the target object, the target device can obtain the motion feature information according to the speed distribution information of the point cloud (denoted as the fourth point cloud) of the target object within the target speed range. Among them, the target speed range can be represented by a speed interval, and the target speed range can be expressed as [0, 2], where 2 can represent 2 m / s. In this embodiment, the maximum value of the speed value of the point cloud of the target object can be determined. If the maximum value of the speed value is greater than 2 m / s, it indicates that there is the third point cloud of the target object. At this time, the target device can select the fourth point cloud with the speed value within the target speed range [0, 2], and obtain the motion feature information of the target object according to the speed distribution information of the fourth point cloud within the target speed range [0, 2]. Thus, obtaining the motion feature information according to the speed distribution information of the fourth point cloud of the target object within the target speed range can make the motion feature information contain the main motion features of the target object.

[0114] In one embodiment, taking the radar as the target device, the method of the present application will be described.

[0115] In this embodiment, the radar can monitor the target object in the target space, and send the target object type of the target object and the position information of the target object to the user terminal. As Figure 3 shown, the user terminal can display various target object identifiers (such as T1 to T4) in the monitoring area 310 of the radar monitoring page 300 according to the target object type and position information reported by the radar, and each target object identifier corresponds to the target object type.

[0116] As Figure 4 and Figure 5 shown, the user can click on the target object identifier displayed in the monitoring area 310 to change its corresponding target object type (for example, change the target object type from a cat to a dog, etc.). After the user changes the target object type corresponding to the target object identifier, the user terminal can change the display of the target object identifier according to the changed object type, and feedback the changed object type to the radar. The radar can bind and record the changed object type with the corresponding feature information of the target object. Based on this, when a new target object enters the monitoring range of the radar subsequently, the radar can match the feature information of the newly recognized target object with the above-recorded feature information. If there is a matching object type, the target object type of the new target object can be determined according to the matching object type and reported to the user terminal for display.

[0117] In the above change of the target object type, the changed object type can be an interference source or other object types. In this regard, if the changed object type is not an interference source, the user terminal can display the changed target object identifier. If the changed object type is an interference source, then the user terminal can remove the target object identifier from the monitoring area 310. In subsequent identification of the target object, the target object identified as an interference source can no longer be displayed in the monitoring area 310, and the user terminal can also set the area position of the interference source in the monitoring area 310 as the interference position, so that the radar can subsequently not identify the target object based on this interference position. Additionally, as Figure 5 shown, when the user changes the target object type, the user terminal can display a change prompt message 320 on the monitoring page 300 to indicate the effect after the change of the target object type.

[0118] For the radar, as described above, the radar can identify the target object type matched by the target object in the object type set according to the feature information of the target object. The object type set contains the changed object type fed back by the user terminal, and thus sends the target object type of the target object and the position information of the target object to the user terminal. The user terminal displays the monitoring page of the target device according to the target object type and the position information.

[0119] Among them, in the identification of the target object type, the radar inputs the feature information into the classification model, and the classification model identifies the first matching degree between the target object and each object type in the first object type subset. The radar also obtains the second matching degree between the target object and each object type in the second object type subset according to the correlation between the feature information and each reference feature information respectively. Finally, according to the first matching degree and the second matching degree, the radar identifies the target object type matched by the target object in the object type set.

[0120] In this regard, regarding the feature information of the target object, the radar can obtain the spatial feature information and the motion feature information of the target object according to the point cloud of the target object, and use the spatial feature information and the motion feature information of the target object as the feature information of the target object. Among them, the spatial feature information can include the spatial distribution information of the point cloud of the target object in the target space range, and the motion feature information can include the speed distribution information of the point cloud of the target object in the target speed range.

[0121] The following explains the extraction of the feature information of the point cloud:

[0122] The above spatial feature information may include the point cloud distribution density in the spatial dimensions corresponding to the x, y, and z axes, i.e., the point cloud distribution density of the x axis, the point cloud distribution density of the y axis, and the point cloud distribution density of the z axis, where the z axis may be defined as the height axis of the target space. The above motion feature information may include the velocity distribution density of the point cloud.

[0123] The radar may have a transmitting antenna and a receiving antenna. The transmitting antenna of the radar may send electromagnetic waves at a certain frame rate, and the receiving antenna may receive the electromagnetic waves reflected by the target object. The radar may implement the monitoring of the target object through signal processing algorithms such as moving target indication (MTI), fast Fourier transform (FFT), and constant false alarm rate (CFAR), and all the point clouds in this frame can be obtained through monitoring. Each point cloud may have multi-dimensional information, which may include three-dimensional spatial information (x coordinate, y coordinate, z coordinate), velocity, signal-to-noise ratio SNR, and other information. For the point clouds obtained by the radar monitoring in this frame, clustering may be performed first to associate each frame of point clouds with the target object. In practical applications, if the antenna performance of the radar is good and the single-frame point cloud is rich enough, the feature vector can be obtained according to the information of the single-frame point cloud under each target object. If the number of single-frame point clouds is small, the extended Kalman filter can be used for trajectory tracking. After obtaining the information of multiple frames of point clouds under a certain target, the information of these multiple frames of point clouds is superimposed to obtain the feature vector.

[0124] For the extraction of spatial feature information:

[0125] 1) Point cloud distribution density of the x axis: A distribution density can be predefined. Taking the space range occupied by an adult in the target space, such as 1 m, as the target space range, and setting the resolution to 10 cm, the distribution density of a total of 10 grids can be obtained. According to the x coordinates of all the point clouds of a certain target object, they are mapped into these 10 grids to form the point cloud distribution density of the x axis of the target object. Among them, let the maximum value of the x coordinates of all the point clouds of the target object be xmax, and the minimum value be xmin. When xmax - xmin <= 1 m, when the x coordinate of the point cloud is in the range of [xmin, xmin + 0.1 * i], the point cloud is mapped into the i-th grid. When xmax - xmin > 1 m, the point clouds with x coordinates in the range of [(xmax + xmin) / 2 - 0.5, (xmax + xmin) / 2 + 0.5] are selected for mapping. When the x coordinate of a certain point cloud is in the range of [(xmax + xmin) / 2 - 0.5 + 0.1 * i], the point cloud is mapped into the i-th grid. In this way, all the point clouds of the target object can be mapped into 10 grids, and the number of point clouds mapped into each grid is counted, which can form the point cloud distribution density of the x axis.

[0126] 2) Point cloud distribution density of the y-axis: A distribution density can be predefined. Taking the space range occupied by an adult in the target space, such as 1m, as the target space range, setting the resolution to 10cm, and there is a distribution density for a total of 10 grids. Map the y-coordinates of all the point clouds of a certain target object into these 10 grids to form the point cloud distribution density of the y-axis of the target object. Among them, let the maximum value of the y-coordinates of all the point clouds of the target object be ymax, and the minimum value be ymin. When ymax - ymin <= 1m, when the y-coordinate of the target object is in the range of [ymin, ymin + 0.1 * i], this point cloud is mapped into the i-th grid. When ymax - ymin > 1m, select the point clouds with y-coordinates in the range of [(ymax + ymin) / 2 - 0.5, (ymax + ymin) / 2 + 0.5] for mapping. When the y-coordinate of a certain point cloud is in the range of [(ymax + ymin) / 2 - 0.5 + 0.1 * i], this point cloud is mapped into the i-th grid. In this way, all the point clouds of the target object can be mapped into 10 grids, and by counting the number of point clouds mapped into each grid, the point cloud distribution density of the y-axis can be formed.

[0127] 3) Point cloud distribution density of the z-axis: The z-axis is the height axis. A distribution density can be predefined. Taking the space range occupied by an adult in the target space, such as 2m, as the target space range, setting the resolution to 10cm, and there is a distribution density for a total of 20 grids. Map the z-coordinates of all the point clouds of a certain target object into these 20 grids to form the point cloud distribution density of the z-axis of the target object. Among them, let the maximum value of the z-coordinates of all the point clouds of the target object be zmax, and the minimum value be zmin. When zmax - zmin <= 2m, when the z-coordinate of the target object is in the range of [zmin, zmin + 0.1 * i], this point cloud is mapped into the i-th grid. When zmax - zmin > 2m, select the point clouds with z-coordinates in the range of [(zmax + zmin) / 2 - 1, (zmax + zmin) / 2 + 1] for mapping. When the z-coordinate of a certain point cloud is in the range of [(zmax + zmin) / 2 - 1 + 0.1 * i], this point cloud is mapped into the i-th grid. In this way, all the point clouds of the target object can be mapped into 20 grids, and by counting the number of point clouds mapped into each grid, the point cloud distribution density of the z-axis can be formed.

[0128] For the extraction of motion feature information:

[0129] A distribution density can be predefined. According to the movement speed of adults, the target speed range can be defined as 0 to 2 m / s. Assuming the resolution is 0.2 m / s, there is a distribution density of a total of 10 grids. The movement speeds of all the point clouds of a certain target object are mapped into these 10 grids to form the speed distribution density of the target object. Among them, let the maximum value of the movement speeds of all the point clouds of the target object be vmax. When vmax <= 2 m / s, when the movement speed of a certain point cloud is in the range of [(i - 1) * 0.1, 0.1 * i], this point cloud is mapped into the i-th grid. When vmax > 2 m / s, the point clouds with movement speeds in the range of [0 m / s, 2 m / s] are selected for mapping. When the movement speed of a certain point cloud is in the range of [(i - 1) * 0.1, 0.1 * i], this point cloud is mapped into the i-th grid. Through this method, all the point clouds of the target object can be mapped into 10 grids, and the number of point clouds mapped into each grid is counted to obtain the speed distribution density of the target object.

[0130] Through the above method, the characteristic information samples of the target objects of various object types can also be obtained. Based on the characteristic information samples of the target objects of various object types, multi-classification task training is carried out to obtain a trained classification model. Through the trained classification model, the target object can be recognized, and the first matching degree of the target object belonging to object types such as adults, children, pets, or sweeping robots can be recognized. In practical applications, machine learning or deep learning networks can be selected for multi-classification task training.

[0131] As described above, in the recognition of the target object type, the radar also obtains the second matching degree of the target object with each object type in the second object type subset according to the correlation between the characteristic information and each reference characteristic information. In this regard, when the user determines the changed object type on the user terminal, the user terminal sends the changed object type to the radar. The radar stores the characteristic information of the target object corresponding to the changed object type, and the extraction method of the characteristic information of the target object can be seen in the previous description. Considering that the same target object may have different characteristic information in different positions and different postures, in order to save the characteristic information that can be used for target object recognition, it is necessary to ensure that the target object has the same posture or behavior at this position. Therefore, the radar can retain the characteristic information when the target object is initially created, because when the target object is initially created, the posture and behavior of the target object will be relatively fixed. Then, algorithms such as trajectory tracking, such as the extended Kalman filter, can be used to continue the association between the target object and the characteristic information. When the user changes the target object type of the target object, the radar can bind the characteristic information when the target object was initially created to the changed object type.

[0132] After obtaining the object type determined by the user feedback from the user terminal, when a new target object enters the monitoring range of the radar subsequently, the radar can perform a correlation solution on the feature information of the new target object and the feature information bound with the object type saved, so as to obtain a second matching degree of the new target object belonging to a certain object type.

[0133] Regarding the calculation of the second matching degree:

[0134] The feature information of the target object is represented by a feature vector. Suppose the feature vector has 50 dimensions. Then the correlation calculation between the feature vector v

[50] of the target object and the feature vector v1

[50] bound with the object type is as follows:

[0135]

[0136] Among them, n represents the dimension of the feature vector. Here, i represents the serial number of the dimension of the feature vector, and p(v, v1) represents the correlation. After calculating the correlation between the feature vector of the target object and all the feature vectors bound with the object type, the correlation can be normalized to obtain the second matching degree:

[0137]

[0138] Among them, m represents the number of object types in the second object type subset, that is, the number of object types already bound with the feature vector, s(i) represents the second matching degree, and here i represents the serial number of the object type in the second object type subset.

[0139] Finally, the radar can identify the target object type matched by the target object in the object type set according to the first matching degree and the second matching degree.

[0140] In this regard, the radar can obtain the first matching degree (denoted as S1) and the second matching degree (denoted as S2) of the new target object under various object types. From this, the radar can fuse the first matching degree S1 and the second matching degree S2 to obtain the comprehensive matching degree S of the new target object under various object types:

[0141] S = K1 * S1 + (1 - K1)S2

[0142] Among them, K1 represents the weight coefficient and can take 0.5. In this way, the radar believes both the classification model and the user feedback. As more feedback is received, the recognition result will be more and more accurate.

[0143] The radar can sort the comprehensive matching degree S of the new target object under various object types, and determine the target object type of the new target object as the object type with the maximum comprehensive matching degree S.

[0144] The solution of this embodiment can visually display the target object identifier corresponding to the target object type on the user terminal. In scenarios with relatively simple environments such as smart homes that are not prone to significant changes, there is no need to collect a large amount of data. Only the object type changed by the user and the characteristic information of the target object need to be recorded. Based on the characteristic information of the target object bound to the object type changed by the user, the accuracy of target object recognition can be improved. The solution of this embodiment can also replace a large amount of data collection costs. It can use simple data collection for target object recognition. In case of misrecognition, the user can also change the target object type, enabling the radar to perform target object recognition based on the accurately changed object type by the user in the subsequent process. Moreover, the characteristic information of the target object and the target object type can be stored in the radar, making data processing more secure and reliable without consuming platform and system resources.

[0145] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0146] Based on the same inventive concept, the embodiments of the present application also provide an object display device for implementing the above-mentioned object display method and an object recognition device for implementing the object recognition method. The implementation solutions for solving problems provided by this device are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more of the following device embodiments can refer to the limitations on the method in the above text and will not be elaborated here.

[0147] In an exemplary embodiment, as Figure 9 shown, an object display device is provided. The device 900 may include:

[0148] A page display module 901, configured to display a monitoring page of a target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents the target object detected by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type of the target object being recognized.

[0149] The type change module 902 is configured to determine the object type of the target object change in response to an operation triggered on the target object identifier.

[0150] The change processing module 903 is configured to change the display of the target object identifier according to the changed object type, and identify a new target object by applying the changed object type.

[0151] In an exemplary embodiment, the type change module 902 is configured to, in response to an operation triggered on the target object identifier, display at least one first object type option; the first object type option is used to represent an optional object type; according to the selected first object type option, obtain the object type of the target object change; or, in response to an addition operation for an optional object type, display a second object type option; the second object type option is used to represent an added object type; according to the selected first object type option or the second object type option, obtain the changed object type.

[0152] In an exemplary embodiment, the change processing module 903 is further configured to display corresponding change prompt information according to the changed object type; the change prompt information is used to indicate the effect after the change of the target object type; in response to a confirmation operation on the change prompt information, perform the steps of changing the display of the target object identifier according to the changed object type, and identifying a new target object by applying the changed object type.

[0153] In an exemplary embodiment, the change processing module 903 is configured to, if the changed object type does not belong to a preset object type, display the changed target object identifier; if the changed object type belongs to the preset object type, remove the display of the target object identifier.

[0154] In an exemplary embodiment, the change processing module 903 is configured to feedback the changed object type to the target device for the target device to apply the changed object type to the identification of a new target object.

[0155] In an exemplary embodiment, the page display module 901 is configured to receive target object information sent by the target device; the target object information includes the location information of the target object and the target object type of the target object; obtain the target object identifier corresponding to the target object type; and display the monitoring page according to the location information and the target object identifier.

[0156] In an exemplary embodiment, such as Figure 10As shown, an object recognition device is provided. The device 1000 may include:

[0157] A feature acquisition module 1001 for acquiring the feature information of the monitored target object;

[0158] A type recognition module 1002 for identifying the target object type matched by the target object in the object type set according to the feature information; the object type set includes the changed object types fed back by the terminal;

[0159] An information sending module 1003 for sending the target object type of the target object and the location information of the target object to the terminal for the terminal to display the monitoring page of the target device according to the target object type and the location information.

[0160] In an exemplary embodiment, the object type set includes a first object type subset and a second object type subset; the first object type subset is obtained according to the object types recognizable by the classification model; the second object type subset is obtained according to the changed object types fed back by the terminal; the type recognition module 1002 is configured to input the feature information into the classification model, and the classification model recognizes the first matching degree between the target object and each object type in the first object type subset; according to the correlation between the feature information and each reference feature information, the second matching degree between the target object and each object type in the second object type subset is obtained; wherein, the reference feature information is the feature information bound to the object type in the second object type subset; according to the first matching degree and the second matching degree, the target object type matched by the target object in the object type set is recognized.

[0161] In an exemplary embodiment, the type recognition module 1002 is further configured to, if receiving the changed object type of the identified target object fed back by the terminal, bind the feature information at the time of creating the identified target object as the reference feature information to the changed object type, and add the changed object type to the second object type subset.

[0162] In an exemplary embodiment, the type recognition module 1002 is further configured to weight the first matching degree and the second matching degree of each object type in the object type set to obtain the comprehensive matching degree of each object type; and determine the target object type according to the comprehensive matching degrees of each object type.

[0163] In an exemplary embodiment, the feature acquisition module 1001 is configured to acquire the point cloud of the target object; obtain the spatial feature information and / or motion feature information of the target object according to the point cloud; and obtain the feature information of the target object according to the spatial feature information and / or the motion feature information.

[0164] In an exemplary embodiment, the feature acquisition module 1001 is configured to obtain the spatial feature information according to the spatial distribution information of the point cloud within a target space range; the target space range is determined according to the space range occupied by the reference object in the target space; and / or, obtain the motion feature information according to the velocity distribution information of the point cloud within a target velocity range; the target velocity range is determined according to the velocity range of the reference object in the target space; wherein, the target space is the space monitored by the target device.

[0165] In an exemplary embodiment, the feature acquisition module 1001 is configured to, if there is a first point cloud of the target object outside the target space range, select a second point cloud that satisfies the target space range based on the center point cloud of the target object, and obtain the spatial feature information according to the spatial distribution information of the second point cloud within the target space range; and / or, the obtaining the motion feature information according to the velocity distribution information of the point cloud within a target velocity range includes: if there is a third point cloud of the target object outside the target velocity range, obtain the motion feature information according to the velocity distribution information of the fourth point cloud of the target object within the target velocity range.

[0166] Each module in the above device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0167] In an exemplary embodiment, an electronic device is provided. The electronic device can be a terminal or a smart home device, etc. Its internal structure diagram can be as Figure 11As shown in the figure. The electronic device includes a processor, a memory, an input / output interface, and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and external devices. The communication interface of the electronic device is used to communicate with external devices in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it realizes an object display method and an object recognition method.

[0168] Those skilled in the art can understand that Figure 11 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0169] In one embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0170] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are realized.

[0171] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are realized.

[0172] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0173] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0174] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0175] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An object display method, characterized in that, The method includes: Displaying a monitoring page of a target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents a target object detected by the target device; the target object identifier corresponds to a target object type; the target object type represents the type of object that the target object is recognized as; Responding to an operation triggered on the target object identifier to determine the object type changed by the target object; Changing the display of the target object identifier according to the changed object type, and applying the changed object type to identify a new target object.

2. The method according to claim 1, characterized in that, The responding to an operation triggered on the target object identifier to determine the object type changed by the target object includes: Responding to an operation triggered on the target object identifier to display at least one first object type option; the first object type option is used to represent an optional object type; Obtaining the object type changed by the target object according to the selected first object type option; or, responding to an addition operation for an optional object type to display a second object type option; the second object type option is used to represent an added object type; obtaining the changed object type according to the selected first object type option or the second object type option.

3. The method according to claim 1, wherein Before changing the display of the target object identifier according to the changed object type and applying the changed object type to identify a new target object, it further includes: Displaying corresponding change prompt information according to the changed object type; the change prompt information is used to indicate the effect after the change of the target object type; Responding to a confirmation operation on the change prompt information to execute the steps of changing the display of the target object identifier according to the changed object type and applying the changed object type to identify a new target object.

4. The method according to claim 1, characterized in that, The changing the display of the target object identifier according to the changed object type includes: If the changed object type does not belong to a preset object type, displaying the changed target object identifier; If the changed object type belongs to the preset object type, removing the display of the target object identifier.

5. The method according to any one of claims 1 to 4, characterized in that, The applying the changed object type to identify a new target object includes: Feeding back the changed object type to the target device for the target device to apply the changed object type to the identification of a new target object.

6. The method according to any one of claims 1 to 4, characterized in that Before displaying the monitoring page of the target device, it further includes: Receiving target object information sent by the target device; the target object information includes the location information of the target object and the target object type of the target object; Obtaining the target object identifier corresponding to the target object type; The displaying the monitoring page of the target device includes; Displaying the monitoring page according to the location information and the target object identifier.

7. An object recognition method, characterized in that, The method includes: Obtaining the characteristic information of the monitored target object; Identify the target object type that the target object matches in the object type set according to the feature information; the object type set includes the changed object types fed back by the terminal. Send the target object type of the target object and the location information of the target object to the terminal for the terminal to display the monitoring page of the target device according to the target object type and the location information.

8. The method according to claim 7, wherein The object type set includes a first object type subset and a second object type subset; the first object type subset is obtained according to the object types recognizable by the classification model; the second object type subset is obtained according to the changed object types fed back by the terminal. The step of identifying the target object type that the target object matches in the object type set according to the feature information includes: Input the feature information into the classification model, and the classification model identifies the first matching degree between the target object and each object type in the first object type subset. According to the correlation between the feature information and each reference feature information, obtain the second matching degree between the target object and each object type in the second object type subset; wherein, the reference feature information is the feature information bound to the object type in the second object type subset. According to the first matching degree and the second matching degree, identify the target object type that the target object matches in the object type set.

9. The method according to claim 8, wherein Before obtaining the second matching degree between the target object and each object type in the second object type subset according to the correlation between the feature information and each reference feature information, the method further includes: If receiving the changed object type fed back by the terminal for the already identified target object, bind the feature information at the time of creating the already identified target object as the reference feature information to the changed object type, and add the changed object type to the second object type subset.

10. The method according to claim 8, wherein The step of identifying the target object type that the target object matches in the object type set according to the first matching degree and the second matching degree includes: For each object type in the object type set, weight the first matching degree and the second matching degree of the object type to obtain the comprehensive matching degree of the object type. Determine the target object type according to the comprehensive matching degrees of the object types.

11. The method according to claim 7, wherein The step of obtaining the feature information of the monitored target object includes: Obtain the point cloud of the target object. According to the point cloud, obtain the spatial feature information and / or the motion feature information of the target object. According to the spatial feature information and / or the motion feature information, obtain the feature information of the target object.

12. The method according to claim 11, wherein The step of obtaining the spatial feature information and / or the motion feature information of the target object according to the point cloud includes: Obtain the spatial feature information according to the spatial distribution information of the point cloud in the target space range; the target space range is determined according to the space range occupied by the reference object in the target space. And / or Obtain the motion feature information according to the velocity distribution information of the point cloud within the target velocity range; the target velocity range is determined according to the velocity range of the reference object in the target space; wherein, the target space is the space monitored by the target device.

13. The method according to claim 12, wherein, the obtaining the spatial feature information according to the spatial distribution information of the point cloud within the target spatial range includes: if there is a first point cloud of the target object outside the target spatial range, then select a second point cloud that meets the target spatial range based on the central point cloud of the target object, and obtain the spatial feature information according to the spatial distribution information of the second point cloud within the target spatial range; and / or, the obtaining the motion feature information according to the velocity distribution information of the point cloud within the target velocity range includes: if there is a third point cloud of the target object outside the target velocity range, then obtain the motion feature information according to the velocity distribution information of the fourth point cloud of the target object within the target velocity range within the target velocity range.

14. An object display device, characterized in that, The device includes: a page display module, configured to display a monitoring page of the target device; the monitoring page includes a monitoring area; a target object identifier is displayed in the monitoring area; the target object identifier represents the target object monitored by the target device; the target object identifier corresponds to a target object type; the target object type represents the object type of the target object identified; a type change module, configured to determine the changed object type of the target object in response to an operation triggered on the target object identifier; a change processing module, configured to change the display of the target object identifier according to the changed object type, and identify a new target object by applying the changed object type.

15. An object recognition device, characterized in that, The device includes: a feature acquisition module, configured to acquire the feature information of the monitored target object; a type identification module, configured to identify the target object type that matches the target object in the object type set according to the feature information; the object type set includes the changed object type fed back by the terminal; an information sending module, configured to send the target object type and the location information of the target object to the terminal, so that the terminal can display the monitoring page of the target device according to the target object type and the location information.

16. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 or any one of claims 7 to 13 are implemented.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 or any one of claims 7 to 13 are implemented.

18. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 or any one of claims 7 to 13 are implemented.

Images