Object processing method and apparatus, computer device, and storage medium

Abstract

The application discloses an object processing method and device, computer equipment and a storage medium, which can be applied to the field of maps. The method comprises the following steps: determining a target physical object region from physical objects in a physical space; determining a digital space obtained by digital processing of the physical space; determining a target digital object region corresponding to the target physical object region in digital objects in the digital space, and performing path planning in the digital space according to the spatial position of the target digital object region and the spatial position of a digital robot; after the path information is planned, scheduling a physical robot to move to the target physical object region according to the path information, and processing the target physical object region according to a work task. The application can save the energy consumption cost of the physical robot and improve the object processing efficiency.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to the field of maps, and more particularly to an object processing method, apparatus, computer device, and storage medium. Background Technology

[0002] With the continuous development of computer technology, more and more users and enterprises are choosing to use physical robots (i.e., real robots) to process corresponding physical objects, such as using cleaning robots to clean glass curtain walls or floors. Currently, when it is necessary to use physical robots to process physical objects, the user usually sends a cleaning command about the physical object to the physical robot through application software. The physical robot then responds to the cleaning command and moves to the location of the physical object using obstacle avoidance based on internal sensors, thereby processing the physical object in its entirety.

[0003] This approach prevents the physical robot from selectively processing specific areas of the physical object, resulting in significant energy waste due to unnecessary work and reduced object processing efficiency. Furthermore, the physical robot's reliance on internal sensors for obstacle avoidance to reach the physical object not only consumes a large amount of energy but also leads to a low movement speed due to real-time route planning, further impacting object processing efficiency. Summary of the Invention

[0004] This application provides an object processing method, apparatus, computer device, and storage medium, which can save energy costs of physical robots and improve object processing efficiency.

[0005] On one hand, embodiments of this application provide an object processing method, the method comprising:

[0006] Determine the target physical object region from the physical objects in the physical space. The target physical object region refers to the physical object region that needs to be processed by the physical robot in the physical space according to the work task.

[0007] A digital space is determined by digitizing the physical space; the digital space includes at least: the digital object corresponding to the physical object and the digital robot corresponding to the physical robot;

[0008] In the digital object, a target digital object region corresponding to the target physical object region is determined, and in the digital space, path planning is performed based on the spatial location of the target digital object region and the spatial location of the digital robot;

[0009] After the path information is planned, the physical robot is dispatched to move to the target physical object region according to the path information, and the target physical object region is processed according to the work task.

[0010] In another aspect, an object processing apparatus is provided, and the apparatus includes:

[0011] A processing unit is configured to determine a target physical object region from physical objects in a physical space, the target physical object region being a region of physical objects that needs to be processed by a physical robot in the physical space according to a work task.

[0012] The processing unit is further configured to determine a digital space obtained by digitizing the physical space, the digital space including at least digital objects corresponding to the physical objects and a digital robot corresponding to the physical robot.

[0013] The processing unit is further configured to determine a target digital object region corresponding to the target physical object region in the digital objects, and to perform path planning in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot.

[0014] A dispatching unit is configured to dispatch the physical robot to move to the target physical object region according to the path information after the path information is planned, and to process the target physical object region according to the work task.

[0015] In another aspect, a computer device is provided, and the computer device includes an input interface and an output interface, and further includes:

[0016] A processor is adapted to implement one or more instructions; and

[0017] A computer storage medium stores one or more instructions, and the one or more instructions are adapted to be loaded and executed by the processor to perform the following steps:

[0018] A target physical object region is determined from physical objects in a physical space, the target physical object region being a region of physical objects that needs to be processed by a physical robot in the physical space according to a work task.

[0019] A digital space obtained by digitizing the physical space is determined, the digital space including at least digital objects corresponding to the physical objects and a digital robot corresponding to the physical robot.

[0020] determine a target digital object region corresponding to the target physical object region in the digital object, and perform path planning in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot;

[0021] After the path information is planned, the physical robot is scheduled to move to the target physical object region according to the path information, and the target physical object region is processed according to the work task.

[0022] In another aspect, the embodiment of the present application provides a computer storage medium, which stores one or more instructions, and the one or more instructions are adapted to be loaded by a processor and execute the object processing method mentioned above.

[0023] In another aspect, the embodiment of the present application provides a computer program product, which comprises a computer program; and the computer program is executed by a processor to implement the object processing method mentioned above.

[0024] The embodiment of the present application can determine a target physical object region from a physical object in a physical space, and then schedule a physical robot to process the target physical object region. Compared with full processing, the object processing efficiency can be improved, and the waste of energy cost caused by the physical robot doing more useless work can be avoided, thereby saving the energy cost. In addition, the embodiment of the present application obtains a digital space by digitizing the physical space, so that the environment of the digital space is consistent with that of the physical space. Therefore, the path information obtained by path planning in the digital space according to the spatial position of the target digital object region corresponding to the target physical object region and the spatial position of the digital robot corresponding to the physical robot can accurately avoid obstacles in the physical space, ensuring the accuracy and reliability of the path information, and avoiding collision when the physical robot moves according to the path information, thereby improving the safety of the physical robot. Since the physical robot does not need to use internal sensors to avoid obstacles and plan routes in real time during the entire processing process, the energy cost of the physical robot can be further saved, the moving speed of the physical robot can be improved, and the object processing efficiency can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1is a schematic diagram of a physical space and a digital space provided by an embodiment of the present application;

[0027] Figure 2 is a flowchart of an object processing method provided by an embodiment of the present application;

[0028] Figure 3a is a flowchart of scheduling a physical robot provided by an embodiment of the present application;

[0029] Figure 3b is a flowchart of another scheduling a physical robot provided by an embodiment of the present application;

[0030] Figure 4 is a flowchart of an object processing method provided by another embodiment of the present application;

[0031] Figure 5a is a schematic diagram of constructing a digital space provided by an embodiment of the present application;

[0032] Figure 5b is a schematic diagram of transmitting data through a data transmission channel provided by an embodiment of the present application;

[0033] Figure 5c is a schematic diagram of processing logic about an object image provided by an embodiment of the present application;

[0034] Figure 6a is a schematic diagram of an application scenario of an object processing method provided by an embodiment of the present application;

[0035] Figure 6b is a schematic diagram of application logic of an object processing method provided by an embodiment of the present application;

[0036] Figure 7 is a structural schematic diagram of an object processing apparatus provided by an embodiment of the present application;

[0037] Figure 8 is a structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0039] In the embodiments of the present application, an object processing scheme is proposed to achieve convenient, efficient and intelligent control of a physical robot to process part or all of the physical object regions in a physical object, thereby improving the object processing efficiency and saving the energy consumption cost of the physical robot. The physical robot mentioned herein refers to a robot in an actual space (i.e., a physical space), and the specific type of the physical robot is not limited in the embodiments of the present application. For example, the physical robot mentioned in the embodiments of the present application can be a physical cleaning robot (such as a window cleaning robot or a sweeping robot) with a cleaning function. In this case, the physical object can be any object that may have a cleaning requirement, such as a floor, a road, or an external wall of a building (such as a glass curtain wall or a ceramic tile external wall). For another example, the physical robot mentioned in the embodiments of the present application can be a physical irrigation robot with an irrigation (i.e., watering) function. In this case, the physical object can be any object that may have an irrigation requirement, such as land or plants.

[0040] The general principle of the object processing scheme proposed in the embodiments of the present application will be described below taking a physical robot as a physical cleaning robot as an example.

[0041] First, a physical camera device can be deployed in a physical space where the physical object and the physical robot are located. The number of the physical robot and the physical camera device can be one or more, and the physical camera device can be used to take pictures of the physical object to obtain corresponding object images. After the physical camera device is deployed in the physical space, a computer device can build a corresponding digital space based on the physical space, and bind (i.e., record) the spatial positions of the physical object, the physical camera device, and the physical robot in the computer device. The digital space mentioned herein refers to a virtual space model constructed by digital processing of the physical space. The environment of the digital space is the same as that of the physical space, i.e., the digital space can include a digital object corresponding to the physical object, a digital robot corresponding to the physical robot, and digital camera devices corresponding to the physical camera devices, as shown in FIG. 1. Figure 1 It should be noted that the figures in the embodiments of the present application only representatively show the styles of the physical robot and the digital robot, and do not limit the styles of the physical robot and the digital robot.

[0042] wherein (1) the digital object refers to a virtual object model obtained by digitizing a physical object and deployed in a digital space, a position of the digital object in the digital space corresponds to a position of the physical object in a physical space; (2) the digital robot refers to a virtual robot model obtained by digitizing a physical robot and deployed in the digital space, a position of the digital robot in the digital space corresponds to a position of the physical robot in the physical space; (3) the digital camera device refers to a virtual camera device model obtained by digitizing a physical camera device and deployed in the digital space, a position of the digital camera device in the digital space corresponds to a position of the physical camera device in the physical space.

[0043] The computer device can acquire an object image collected by the physical camera device, and intelligently calculate cleanliness levels of each physical object region in the physical object based on AI analysis capability according to the acquired object image, so as to determine a target physical object region in the physical object that needs to be cleaned by the physical robot based on the calculated cleanliness levels, and determine a target digital object region corresponding to the target physical object region in the digital object in the digital space. Then, path planning can be intelligently performed for the digital robot according to the spatial position of the target digital object region in the digital space and the spatial position of the digital robot in the digital space. Since the environment in the digital space and the environment in the physical space are the same, the path information planned for the digital robot can be applicable to the physical robot; based on this, the physical robot can be dispatched to move to the target physical object region according to the planned path information, and clean the target physical object region.

[0044] It should be noted that the above is only illustratively described the general principle of the object processing scheme, and does not limit the same. For example, in other embodiments, if the physical object is an object with a light-transmitting material (such as a glass curtain wall), a physical light transmission tester can also be used to test the light transmission of each physical object region in the physical object, so as to intelligently calculate the cleanliness level of each physical object region in the physical object based on AI analysis capability according to the tested light transmission, and then perform a series of subsequent processing based on the calculated cleanliness levels; wherein the light transmission refers to the efficiency of transmitting light, that is, the percentage of light flux transmitted through a transparent or translucent body to its incident light flux. For example, in other embodiments, if the physical robot is a physical watering robot, when the above object processing scheme is executed, the dryness of each physical object region in the physical object is calculated, and then the target physical object region is determined based on the calculated dryness, and a series of subsequent processing is performed based on the target physical object region, and the like.

[0045] It should be noted that the computer device mentioned above can be a terminal or a server. The terminal mentioned herein can include, but is not limited to, a smartphone, a computer (such as a tablet computer, a notebook computer, a desktop computer, etc.), a smart wearable device (such as a smart watch, smart glasses), a smart voice interaction device, a smart home appliance (such as a smart television), a vehicle-mounted terminal, an aircraft, etc. The server mentioned herein can be a standalone physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms, etc. Further, the computer device can be located inside or outside the blockchain network, and no limitation is made in this regard. Furthermore, the computer device can upload any data stored therein to the blockchain network for storage, so as to prevent the data stored therein from being tampered with and improve data security.

[0046] It is shown by practice that the object processing scheme proposed in the embodiments of the present application can have at least the following beneficial effects: ①The scheme can automatically determine whether each physical object region in a physical object needs to be processed by a physical robot, thereby saving labor costs. ②The scheme can realize scheduling the physical robot to process only a physical object region that needs to be processed, without full processing, thereby improving object processing efficiency and avoiding waste of energy costs due to the physical robot doing more useless work, so as to save energy costs. ③By constructing a digital space corresponding to a physical space, the path information planned in the digital space can be applied to the physical robot, and the path information can accurately avoid obstacles in the physical space, thereby ensuring the accuracy and reliability of the path information, and further avoiding collision of the physical robot when moving according to the path information, thereby improving the moving safety of the physical robot. ④Since the physical robot does not need to use internal sensors to avoid obstacles and plan routes in real time during the entire processing process, the energy costs of the physical robot can be further saved, and the moving speed of the physical robot can be improved, thereby improving the object processing efficiency.

[0047] Based on the description of the above object processing scheme, an embodiment of the present application proposes an object processing method. The object processing method can be executed by the computer device (such as a terminal or a server) mentioned above, or can be executed by a terminal or a server together. For the sake of description, the object processing method executed by the computer device is mainly taken as an example for description. Please refer to Figure 2 The object processing method can include the following steps S201-S205:

[0048] S201, determine a target physical object region from the physical objects in the physical space.

[0049] In the embodiments of the present application, the physical space can include physical robots in addition to the physical objects, and the number of the physical robots can be one or more, which is not limited. Moreover, the working tasks of the physical objects and the physical robots can be different with different application scenarios of the embodiments of the present application. For example, when the embodiments of the present application are applied to a cleaning scenario, the physical objects can refer to any object that can have a cleaning demand, such as a floor, an architectural outer wall (such as a glass curtain wall, a ceramic tile outer wall), etc.; correspondingly, the working task of the physical robots is a cleaning task. For another example, when the embodiments of the present application are applied to an irrigation scenario, the physical objects can refer to any object that can have an irrigation demand, such as land, a field, etc.; correspondingly, the working task of the physical robots is an irrigation task.

[0050] Further, the physical objects can include I physical object regions, I being a positive integer; the target physical object region mentioned in step S201 refers to a physical object region that needs to be processed according to a working task by a physical robot in the physical space. For example, when the working task is a cleaning task, the target physical object region refers to a physical object region that needs to be processed according to the cleaning task by the physical robot in the physical space, i.e., a physical object region that needs to be cleaned in the physical objects; for another example, when the working task is an irrigation task, the target physical object region refers to a physical object region that needs to be processed according to the irrigation task by the physical robot in the physical space, i.e., a physical object region that needs to be irrigated in the physical objects.

[0051] In a specific implementation, the specific implementation of step S201 can be different as the working task of the physical robot changes. For example, when the working task of the physical robot is a cleaning task, the physical space can further include a physical cleanliness detection device; accordingly, the specific implementation of step S201 can be: performing cleanliness detection on the i-th physical object region in the physical objects in the physical space by the physical cleanliness detection device to obtain a cleanliness level of the i-th physical object region; if the cleanliness level of the i-th physical object region is less than a threshold level, the i-th physical object region is determined as the target physical object region. Wherein, i ∈ [1, I]. For another example, when the working task of the physical robot is a watering task, the physical space can further include a physical camera device; accordingly, the specific implementation of step S201 can be: obtaining a target image obtained by the physical camera device for photographing the i-th physical object region in the physical objects in the physical space, determining the dryness degree of the i-th physical object region by image recognition on the target image; if the dryness degree of the i-th physical object region is greater than a dryness degree threshold, the i-th physical object region is determined as the target physical object region.

[0052] S202, determining a digital space obtained by digitally processing the physical space.

[0053] The digital space at least includes: a digital object corresponding to the physical object and a digital robot corresponding to the physical robot. Optionally, if the physical space further includes a physical cleanliness detection device (such as a physical camera device or a physical light transmittance test device), the digital space also correspondingly includes: a digital cleanliness detection device (such as a digital camera device or a digital light transmittance test device) corresponding to the physical cleanliness detection device; if the physical space further includes a physical obstacle, the digital space also correspondingly includes: a digital obstacle corresponding to the physical obstacle, and the like. It is worth mentioning that when the physical object is an external wall of a building, the physical space can also be referred to as a building space; in this case, the digital space can be understood as a virtual building 3D (three-dimensional) space model that is intelligent and digital.

[0054] S203, determining a target digital object region corresponding to the target physical object region in the digital object.

[0055] S204, in the digital space, performing path planning according to the spatial position of the target digital object region and the spatial position of the digital robot.

[0056] In one specific implementation, if the number of digital robots is one, the computer device can further obtain the device state of the digital robot, and the device state can include a working state or an idle state; if the obtained device state is an idle state, the computer device can perform path planning in the digital space according to the spatial position of the target digital object region and the spatial position of the digital robot.

[0057] In another specific implementation, if the number of digital robots is multiple, the computer device can further acquire state information of each digital robot, and select Q schedulable digital robots from the P digital robots according to the state information of each digital robot, Q ∈ [1, P]. Then, in the digital space, path planning is performed according to the spatial position of the target digital object region and the spatial position of each schedulable digital robot to obtain path information of each schedulable digital robot. Alternatively, after the Q schedulable digital robots are selected, the computer device can further select a digital robot closest to the target digital object region from the Q schedulable digital robots as the target digital robot to be scheduled; and then, in the digital space, path planning is performed according to the spatial position of the target digital object region and the spatial position of the target digital robot.

[0058] It should be noted that the specific manner of path planning is not limited in the embodiments of the present application. For example, the computer device can perform path planning in the digital space according to the spatial position of the target digital object region in the digital space and the spatial position of the digital robot in the digital space according to the principle of avoiding obstacles, by using a path planning algorithm to obtain corresponding path information. The path planning algorithm can include but is not limited to the following: search-based path planning algorithm (such as the best path priority search algorithm), sampling-based path planning algorithm (such as the rapid random search tree (RRT) algorithm, the target preference RRT algorithm, the bidirectional rapid expansion random tree (RRT CONNECT) algorithm, etc.), potential field-based path planning algorithm, etc.

[0059] S205, after obtaining the path information, the physical robot is scheduled to move to the target physical object region according to the path information, and the target physical object region is processed according to the work task.

[0060] Since the environment of the digital space and the environment of the physical space are the same, the path information obtained by performing path planning in the digital space in step S204 can be applicable to the physical robot in the physical space; based on this, after obtaining the path information, the computer device can schedule the physical robot to move to the target physical object region according to the path information, and process the target physical object region according to the work task.

[0061] It should be understood that if the number of the aforementioned digital robots is one, it indicates that the number of the physical robots is also one; in this case, the path information obtained by the computer device through the aforementioned step S204 is one, and thus the computer device can directly dispatch the physical robot to move to the target physical object region according to the path information and process the target physical object region according to the work task when performing step S205. If the number of the aforementioned digital robots is multiple, it indicates that the number of the physical robots is also multiple; in this case, if the path information of each dispatchable digital robot is obtained by the computer device through the aforementioned step S204, then the computer device can dispatch the physical robot corresponding to each dispatchable digital robot to move to the target physical object region according to the corresponding path information and instruct the dispatched Q physical robots to jointly process the target physical object region according to the work task when performing step S205, as shown in FIG. 8. Figure 3a If the path information of the target digital robot to be dispatched is obtained by the computer device through the aforementioned step S204, then the computer device can dispatch the physical robot corresponding to the target digital robot to move to the target physical object region according to the planned path information and process the target physical object region according to the work task when performing step S205, as shown in FIG. 9. Figure 3b

[0062] The embodiment of the present application can determine the target physical object region from the physical objects in the physical space, so as to dispatch the physical robot to process the target physical object region in a targeted manner; compared with full processing, the object processing efficiency can be improved, and the waste of energy cost of the physical robot due to doing more useless work can be avoided, so as to save the energy cost. Moreover, the embodiment of the present application obtains the digital space by digitally processing the physical space, so that the environment of the digital space and the environment of the physical space remain consistent; in this way, the path information obtained by path planning in the digital space according to the spatial position of the target digital object region corresponding to the target physical object region and the spatial position of the digital robot corresponding to the physical robot can accurately avoid the obstacles in the physical space, so as to ensure the accuracy and reliability of the path information, and further avoid the collision of the physical robot when moving according to the path information, so as to improve the moving safety of the physical robot. Since the physical robot does not need to use the internal sensor to avoid obstacles and plan the route in real time in the whole processing process, the energy cost of the physical robot can be further saved, the moving speed of the physical robot can be improved, and thus the object processing efficiency can be improved.

[0063] Based on the above Figure 2 ​In the related description of the method embodiment shown, the embodiment of the present application further proposes a flowchart of another object processing method. In the embodiment of the present application, the computer device is still taken as an example to execute the object processing method. Please refer to Figure 4 The object processing method can include the following steps S401-S409:

[0064] S401, determining a target physical object region from physical objects in a physical space.

[0065] In the embodiment of the present application, the working task of the physical robot is taken as an example of a cleaning task to elaborate the specific implementation of step S401. In this case, the physical space further includes a physical cleanliness detection device, and the physical objects include I physical object regions. Then, when executing step S401, the computer device can detect the cleanliness of the i-th physical object region in the physical objects in the physical space by using the physical cleanliness detection device to obtain the cleanliness level of the i-th physical object region. Then, the computer device compares the size relationship between the cleanliness level of the i-th physical object region and the threshold level. If the cleanliness level of the i-th physical object region is less than the threshold level, the i-th physical object region is determined as the target physical object region. Optionally, if the cleanliness level of the i-th physical object region is less than the threshold level, it can be further detected whether there is a physical robot working in the i-th object region. If there is, the existing physical robot is notified to stop working, and the existing physical robot is notified to wait for the next scheduling.

[0066] In a specific implementation, when the physical object is an object of any material, the above-mentioned physical cleanliness detection device can be a physical camera device. In this case, the specific implementation of detecting the cleanliness of the i-th physical object region in the physical objects in the physical space by using the physical cleanliness detection device to obtain the cleanliness level of the i-th physical object region can be: obtaining a target object image obtained by the physical camera device by shooting the physical object, and the target object image at least includes the region image of the i-th physical object region in the physical objects. Secondly, the computer device can segment the region image of the i-th physical object region from the target object image. Then, the computer device can detect the cleanliness of the i-th physical object region according to the region image of the i-th physical object region to obtain the cleanliness level of the i-th physical object region. Specifically, this step can include any one of the following ways:

[0067] The computer device can obtain N reference images, different reference images have different cleanliness levels, N is a positive integer; then, the computer device can calculate the feature similarity between the region image of the i th physical object region and each reference image in the N reference images; and according to the feature similarity calculation result, select the reference image corresponding to the maximum feature similarity from the N reference images as the similar reference image of the i th physical object region; thereby determining the cleanliness level of the similar reference image as the cleanliness level of the i th physical object region.

[0068] The computer device can obtain a plurality of preset cleanliness ranges, one cleanliness range corresponds to one cleanliness level; and the computer device can call a cleanliness detection model to detect the cleanliness of the region image of the i th physical object region to obtain the cleanliness of the i th physical object region. Then, the cleanliness of the i th physical object region is used to hit process the plurality of cleanliness ranges to determine the cleanliness range to which the cleanliness of the i th physical object region belongs; thereby determining the cleanliness level corresponding to the determined cleanliness range as the cleanliness level of the i th physical object region.

[0069] In another specific implementation, when the physical object is an object with a light-transmitting material (such as a glass curtain wall), the physical cleanliness detection device mentioned above can be a physical light transmittance tester; in this case, the specific implementation of detecting the cleanliness of the i th physical object region in the physical object in the physical space by the physical cleanliness detection device to obtain the cleanliness level of the i th physical object region can be: obtaining the light transmittance of the i th physical object region in the physical object in the physical space, the light transmittance of the i th physical object region is obtained by the physical light transmittance tester testing the light transmittance of the i th physical object region; then, the cleanliness level of the i th physical object region can be determined according to the light transmittance of the i th physical object region and the light transmittance range corresponding to the plurality of preset cleanliness levels. For example, three cleanliness levels are preset, which are cleanliness level A, cleanliness level B and cleanliness level C; if the light transmittance of the i th physical object region falls within the light transmittance range corresponding to the cleanliness level A, the cleanliness level A can be determined as the cleanliness level of the i th physical object region.

[0070] S402, determining a digital space obtained by digitally processing the physical space, the digital space at least including: a digital object corresponding to the physical object and a digital robot corresponding to the physical robot.

[0071] In one specific implementation, the computer device can digitally process the physical space based on digital twinning technology to obtain a corresponding digital space. The so-called digital twinning can be understood as the digitization of the real world (system). Specifically, digital twinning is to fully utilize physical models, sensor updates, operation history, etc. Data, integrate multi-disciplinary, multi-physical, multi-scale, and multi-probability processes, and complete mapping in a virtual space to reflect the entire life cycle process of the corresponding entity object, which can be a physical object, a physical robot, etc. It can be seen that digital twinning technology refers to a technology that can establish a digital mapping of the real world (system) in an information platform, simulate physical entities, processes, or systems.

[0072] In another specific implementation, when the physical object is a building outer wall (i.e., the physical space is a building space), the computer device can also construct a building space model with three-dimensional spatial coordinates based on BIM (Building Information Modeling), global geographic position information of each entity object in the physical space, and a building surface positioning space system; then, the constructed building space model can be used as a digital space, as shown in Figure 5a

[0073] After constructing the digital space by any of the above methods, the computer device can also bind the geographic coordinates of each entity object (such as a physical object, a physical robot, a physical camera device, etc.) in the physical space and the corresponding object in the digital space to realize that each object in the digital space is assigned a globally unique spatial coordinate (i.e., spatial position) to facilitate subsequent AI analysis and calculation services on the business logic of scheduling robots based on the digital space and in combination with the spatial coordinates of the objects. The specific way of binding can be that for any entity object (such as a physical object or a physical robot, etc.) in the physical space, the spatial coordinate of the any entity object in the physical space can be recorded as the spatial coordinate of the corresponding object (such as a digital object corresponding to a physical object, or a digital robot corresponding to a physical robot, etc.) in the digital space.

[0074] S403, determining a target digital object region corresponding to a target physical object region in the digital object.

[0075] S404, selecting Q schedulable digital robots from P digital robots according to the state information of each digital robot, Q ∈ [1, P].

[0076] ​The state information of any digital robot is consistent with the state information reported by the corresponding physical robot. The state information of any digital robot includes at least one of the following: the device state of any digital robot and the remaining working material amount of any digital robot. The device state includes a working state or an idle state. The remaining working material amount refers to the remaining working material amount loaded by the robot. The working material can be understood as a material resource required by the robot when performing a working task, such as water, cleaning agent, and the like.

[0077] In a specific implementation, if the state information of any digital robot includes the device state of any digital robot, the specific implementation of step S404 can be: selecting Q digital robots in a working state from the P digital robots as schedulable digital robots.

[0078] In another specific implementation, if the state information of any digital robot includes the remaining working material amount of any digital robot, the specific implementation of step S404 can be: determining a target material demand required for performing a working task on the target physical object region, and selecting Q digital robots with a remaining working material amount greater than or equal to the target material demand from the P digital robots as schedulable digital robots.

[0079] In another specific implementation, the state information of any digital robot includes the device state of any digital robot and the remaining working material amount of any digital robot. In this case, the specific implementation of step S404 can be: determining a target material demand required for performing a working task on the target physical object region, and determining digital robots with a remaining working material amount greater than or equal to the target material demand from the P digital robots; and then selecting Q digital robots in a working state from the determined digital robots as schedulable digital robots.

[0080] S405, in the digital space, according to the spatial position of each schedulable digital robot and the spatial position of the target digital object region, calculating the distance between each schedulable digital robot and the target digital object region.

[0081] S406, according to the distance between each digital robot and the target digital object region, selecting a digital robot corresponding to the minimum distance from the Q schedulable digital robots as a target digital robot to be scheduled.

[0082] S407, path planning is performed according to the spatial position of the target digital object region and the spatial position of the target digital robot in the digital space. It should be noted that the specific implementation of step S407 can refer to the specific implementation of path planning mentioned in step S204, which will not be repeated here.

[0083] S408, the physical robot corresponding to the target digital robot in the P physical robots is taken as a target physical robot to be dispatched.

[0084] S409, the target physical robot is dispatched to move to the target physical object region according to the path information, and the target physical object region is processed according to the work task.

[0085] In a specific implementation, the computer device can generate a work instruction information according to the path information, and the work instruction information can carry at least the path information. Optionally, the work instruction information can also carry the position information of the target physical object region, the required amount of target materials required for performing the work task on the target physical object region, and the like. Further, if the work task is a cleaning task, the work instruction information can be referred to as a cleaning instruction information, and the work instruction information can further include the cleanliness level of the target physical object region and the like. After generating the work instruction information, the computer device can issue the work instruction information to the target physical robot, so that the target physical robot moves to the target physical object region according to the path information in the work instruction information, and processes the target physical object region according to the work task.

[0086] It should be noted that based on the above description of steps S401-S409, in the specific implementation process of steps S401-S409, data transmission operations such as uploading of object images of the physical camera device, uploading of current position information and state information of the physical robot, and issuing of work instruction information can be involved. Then, in order to ensure the security of the transmitted data, the embodiments of the present application establish a secure and trusted data transmission channel based on the national cryptographic algorithm, so as to perform data transmission through the data transmission channel. The national cryptographic algorithm can be understood as a cryptographic algorithm approved by the cryptographic bureau, which can include symmetric encryption algorithms (such as SM1, SMS4, etc.), elliptic curve asymmetric encryption algorithms, cryptographic hash algorithms (such as SM3), and the like. SM1 here is an algorithm with an encryption strength of 128 bits and implemented by hardware. SMS4 here is an algorithm with an encryption strength of 128 bits and implemented by software. SM3 here is an algorithm with a hash value length of 32 bytes.

[0087] For example, referring to Figure 5bAs shown: the object image collected by the physical camera can be stored in the cloud database through the data transmission channel based on the national secret algorithm, so that the computer equipment can read the object image from the database. Further, to improve the security of the object image, after receiving any object image, the cloud database can store the object image after encryption; and the cloud database can also perform strong identity verification on the computer equipment when the computer equipment wants to obtain a certain object image, so that after the computer equipment passes the strong identity verification, the computer equipment is allowed to obtain the corresponding object image, thereby performing subsequent AI computing service calling operations, such as Figure 5c As shown: the object image collected by the physical camera can be stored in the cloud database through the data transmission channel based on the national secret algorithm, so that the computer equipment can read the object image from the database. Further, to improve the security of the object image, after receiving any object image, the cloud database can store the object image after encryption; and the cloud database can also perform strong identity verification on the computer equipment when the computer equipment wants to obtain a certain object image, so that after the computer equipment passes the strong identity verification, the computer equipment is allowed to obtain the corresponding object image, thereby performing subsequent AI computing service calling operations, such as Figure 5b As shown: the state information of the physical robot can be transmitted to the computer equipment through the data transmission channel based on the national secret algorithm, so that the computer equipment can perform subsequent AI computing service calling operations based on the state information of the physical robot. Alternatively, the computer equipment can transmit the work instruction information to the corresponding physical robot through the data transmission channel based on the national secret algorithm, so that the physical robot can work.

[0088] Among them, the AI computing service mentioned above includes but is not limited to the following operations: (1) the aforementioned real-time calculation of the cleanliness level of any physical object area; (2) the aforementioned intelligent judgment of the device state and spatial position of the digital robot or the physical robot; (3) the aforementioned analysis of the nearest and idle digital robot to the target digital object area corresponding to the target physical object area to be processed, thereby automatically planning path information and processing time required for completion (such as cleaning time required for completion); (4) offline calculation and learning of the processing of the entire physical object, and more reasonable and energy-saving object processing suggestions for the manager of the physical object, such as the glass curtain wall of the building, the cleaning condition of the entire building glass curtain wall can be learned offline, thereby giving the manager more reasonable and energy-saving cleaning suggestions and the like.

[0089] Further, when the physical space includes a physical camera device, as the physical camera device takes long-term photos of the physical object, the physical camera device can collect a large number of object images of the physical object; based on this, the embodiments of the present application can also filter a part of valuable object images (i.e. effective object images) from the object images uploaded by the physical camera device for storage, thereby laying a foundation for the AI analysis service to perform offline deep learning calculation on image data, so as to subsequently enable the initial prediction model to continuously perform neural network deep learning based on these valuable object images, and obtain a target prediction model for predicting the cleanliness level of the physical object region in the physical object, thereby realizing that the target prediction model can be used to learn how the physical robot cleans and maintains the physical object (such as a glass curtain wall), and after a large amount of actual data is accumulated, the cleanliness level predicted by the target prediction model can be used to predict the physical object region prone to stains, so that cleaning materials and equipment can be prepared in advance to shorten the time in the subsequent actual processing process and improve the processing efficiency.

[0090] Specifically, the computer device can obtain a plurality of object images obtained by the physical camera device taking photos of the physical object. Then, effective object images are selected from the plurality of object images, and the effective object images refer to object images used to determine that the i th physical object region is a target physical object region. For example, the plurality of object images include object image a, object image b, object image c, object image d, object image e, and object image f; if the i th physical object region is determined to be the target physical object region when the historical step S401 is performed based on the object image a, the object image d, and the object image f respectively, then the object image a, the object image d, and the object image f can be regarded as effective object images. After the effective object images are determined, the computer device can use the effective object images to optimize the initial prediction model to obtain a target prediction model.

[0091] In the embodiment, the effective object images are arranged according to the time stamps of the effective object images in the order from early to late. For any one of the arranged effective object images, the cleanliness level of the next effective object image corresponding to the any one of the arranged effective object images is taken as the labeled cleanliness level of the any one of the arranged effective object images. The next effective object image refers to the effective object image located after the any one of the arranged effective object images and adjacent to the any one of the arranged effective object images, and the cleanliness level corresponding to the next effective object image refers to the cleanliness level of the ith physical object region determined by the specific embodiment of step S401 when step S401 is executed. Then, the initial prediction model is called to predict the cleanliness level of the ith physical object region according to the any one of the arranged effective object images, to obtain the predicted cleanliness level, and to optimize the model parameters of the initial prediction model according to the difference between the predicted cleanliness level and the corresponding labeled cleanliness level. The above steps are iterated to obtain the target prediction model.

[0092] After obtaining the target prediction model by the above method, the computer device further obtains a reference object image of the physical object and the target prediction model used to predict the cleanliness level of the ith physical object region. Then, the target prediction model is called to predict the cleanliness level of the ith physical object region according to the reference object image. If the predicted cleanliness level is greater than the threshold level, the material requirement amount required for cleaning the ith physical object region is predicted according to the predicted cleanliness level, and the physical robot is loaded with materials according to the predicted material requirement amount.

[0093] Compared with full processing, the object processing efficiency can be improved, and the waste of energy consumption cost caused by the physical robot doing more useless work can be avoided, so that the energy consumption cost is saved. Moreover, the application embodiment obtains a digital space by digitizing the physical space, so that the environment of the digital space and the environment of the physical space are consistent. In this way, in the digital space, the path information obtained by path planning according to the spatial position of the target digital object region corresponding to the target physical object region and the spatial position of the digital robot corresponding to the physical robot can accurately avoid obstacles in the physical space, ensuring the accuracy and reliability of the path information, and avoiding collision when the physical robot moves according to the path information, thereby improving the moving safety of the physical robot. Since the physical robot does not need to use the internal sensor to avoid obstacles and plan the route in real time in the whole processing process, the energy consumption cost of the physical robot can be further saved, the moving speed of the physical robot can be improved, and the object processing efficiency can be improved.

[0094] Based on the above Figure 2 and Figure 4 It can be seen from the related description of the object processing method embodiment that the object processing method proposed in the application embodiment can be applied to various scenes, such as cleaning scenes, irrigation scenes, etc. In the following, the application of the object processing method in the cleaning scene is taken as an example, and the physical object is the glass curtain wall of the building, the physical robot is the physical cleaning robot, and the computer device is the cloud server. In combination with Figure 6a and Figure 6b The application process of the object processing method is described:

[0095] Firstly, the manager of the building can manage all devices (including glass curtain walls, physical camera devices, physical robots, etc.) of the whole building in a unified management platform, and configure rules (such as configuring the threshold level of cleanliness, intelligent cleaning mode, etc.). In addition, the cloud server can construct a corresponding digital space based on the physical space corresponding to the whole building.

[0096] Secondly, the physical camera device can capture images of the glass curtain wall to obtain surface data of the glass curtain wall, the surface data including the captured object image; and the physical camera device can upload the captured object image in real time. Correspondingly, the cloud server can obtain the surface data of the glass curtain wall based on the object image uploaded by the physical camera device, that is, obtain the object image of the glass curtain wall. Then, the AI computing server of the cloud can be called to analyze the object image in real time; specifically, the region image of the i-th physical object region can be segmented from the object image, and the region image of the i-th physical object region and the reference image of the preset different cleanliness levels are compared to determine the cleanliness level of the i-th physical object region.

[0097] If the cleanliness level of the i-th physical object region is greater than or equal to the threshold level, it is detected whether there is a physical robot working in the i-th object region; if there is, a stop working instruction is issued to the existing physical robot, and the existing robot is instructed to return to the starting position or stop at the current position, and the existing robot is notified to wait for the next scheduled instruction. If the cleanliness level of the i-th physical object region is less than the threshold level, it can also be detected whether there is a physical robot working in the i-th object region; if there is, jump to the object image uploading step, if there is not, it can be detected whether the automatic cleaning mode is turned on. If the automatic cleaning mode is not turned on, a prompt information is issued to the administrator for processing; if the automatic cleaning mode is turned on, it can be further detected whether there is a schedulable digital robot, if there is no schedulable digital robot, a prompt information can also be issued to the administrator for processing, if there is a schedulable digital robot, the corresponding digital object region of the i-th physical object region can be found in the digital space, and based on the spatial position of the found digital object region in the digital space and the spatial position of the schedulable digital robot in the digital space, the nearest schedulable target digital robot is found from the schedulable digital robot based on the digital space, and the required amount of working materials and the corresponding path information are intelligently calculated. Then, the physical robot corresponding to the schedulable target digital robot goes to the i-th physical object region for cleaning according to the path information.

[0098] Optionally, the scheduled physical robot can upload the data of the location and the equipment state in real time to the cloud server during the working process. When the cleanliness level of the i-th physical object area monitored by the physical camera device meets the requirement (i.e., greater than or equal to the threshold level), the cloud server can issue a stop working instruction to the physical robot and notify the physical robot to return according to the planned path information, or schedule the physical robot to another physical object area for continuous work. Moreover, with long-term monitoring, the cloud server can also learn a glass curtain wall cleaning and maintenance system model (i.e., the aforementioned target prediction model) of a building as the use time elapses and the external environment changes, to predict in advance the physical object area that needs to be cleaned, so as to make reasonable and constructive suggestions (such as preparing cleaning supplies and providing available cleaning robot equipment) to the administrator in a timely manner.

[0099] Based on the above description, the embodiments of the present application can realize efficient and intelligent glass cleaning management by combining the capabilities of hardware devices with the AI analysis capabilities of the cloud. Especially for high-rise buildings, the object processing method based on digital space proposed by the embodiments of the present application can realize intelligent control of physical robots to work, which can save management labor cost and energy cost in real time and effectively: personnel do not need to spend time to judge the cleanliness of the glass curtain wall and manually control the robot equipment to clean; when a certain area needs to be cleaned, only the current area needs to be cleaned, without the need to clean the whole area again.

[0100] Based on the description of the above object processing method embodiments, the embodiments of the present application also disclose an object processing apparatus, which can be a computer program (including program code) running in a computer device. The object processing apparatus can execute the object processing method shown in Figure 2 or Figure 4 . Please refer to Figure 7 , the object processing apparatus can run the following units:

[0101] The processing unit 701 is configured to determine a target physical object area from the physical objects in the physical space, wherein the target physical object area refers to a physical object area that needs to be processed by the physical robot in the physical space according to a working task;

[0102] The processing unit 701 is further configured to determine a digital space obtained by digitally processing the physical space, wherein the digital space at least includes a digital object corresponding to the physical object and a digital robot corresponding to the physical robot;

[0103] The processing unit 701 is further configured to determine a target digital object region corresponding to the target physical object region in the digital object, and to perform path planning in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot.

[0104] The scheduling unit 702 is configured to schedule the physical robot to move to the target physical object region according to the path information, and to perform processing on the target physical object region according to the work task after the path information is planned.

[0105] In an embodiment, the number of the physical robots is P, and one physical robot corresponds to one digital robot, P is an integer greater than 1; accordingly, when the processing unit 701 is configured to perform path planning in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot, the processing unit 701 can be specifically configured to:

[0106] select Q schedulable digital robots from the P digital robots according to the state information of each digital robot, Q ∈ [1, P];

[0107] calculate a distance between each schedulable digital robot and the target digital object region in the digital space according to a spatial position of each schedulable digital robot and the spatial position of the target digital object region;

[0108] select a digital robot corresponding to a minimum distance from the Q schedulable digital robots as a target digital robot to be scheduled according to the distance between each digital robot and the target digital object region;

[0109] perform path planning in the digital space according to the spatial position of the target digital object region and the spatial position of the target digital robot.

[0110] In another embodiment, the state information of any digital robot includes a device state of the any digital robot and a remaining work material amount of the any digital robot; the device state includes a working state or an idle state; accordingly, when the processing unit 701 is configured to select Q schedulable digital robots from the P digital robots according to the state information of each digital robot, the processing unit 701 can be specifically configured to:

[0111] determine a target material demand amount required for performing the work task on the target physical object region, and determine a digital robot with a remaining work material amount greater than or equal to the target material demand amount from the P digital robots;

[0112] From the determined digital robots, Q digital robots in a working state are selected as schedulable digital robots.

[0113] In another implementation, the scheduling unit 702 can be specifically configured to:

[0114] select a physical robot corresponding to the target digital robot from P physical robots as a target physical robot to be scheduled;

[0115] schedule the target physical robot to move to the target physical object region according to the path information and to process the target physical object region according to the work task.

[0116] In another implementation, the work task of the physical robot is a cleaning task, and the physical space further includes a physical cleanliness detection device; the physical object includes I physical object regions, I being a positive integer; accordingly, the processing unit 701 can be specifically configured to, when determining a target physical object region from the physical objects in the physical space:

[0117] perform cleanliness detection on an i-th physical object region in the physical objects in the physical space by using the physical cleanliness detection device to obtain a cleanliness level of the i-th physical object region; wherein i∈[1, I];

[0118] if the cleanliness level of the i-th physical object region is less than a threshold level, the i-th physical object region is determined as the target physical object region.

[0119] In another implementation, the physical cleanliness detection device is a physical camera device; accordingly, the processing unit 701 can be specifically configured to, when performing cleanliness detection on an i-th physical object region in the physical objects in the physical space by using the physical cleanliness detection device to obtain a cleanliness level of the i-th physical object region:

[0120] obtain a target object image obtained by the physical camera device by shooting the physical object, the target object image at least including a region image of the i-th physical object region in the physical object;

[0121] segment the region image of the i-th physical object region from the target object image, and perform cleanliness detection on the i-th physical object region according to the region image of the i-th physical object region to obtain the cleanliness level of the i-th physical object region.

[0122] In another implementation, the processing unit 701 can be specifically configured to:

[0123] obtain N reference images, different reference images having different cleanliness levels, N being a positive integer;

[0124] calculate feature similarity between the region image of the ith physical object region and each of the N reference images;

[0125] select, according to the calculation result of the feature similarity, a reference image corresponding to the maximum feature similarity from the N reference images as a similar reference image of the ith physical object region;

[0126] determine the cleanliness level of the similar reference image as the cleanliness level of the ith physical object region.

[0127] In another implementation, the processing unit 701 can be further configured to:

[0128] obtain a reference object image of the physical object and a target prediction model for predicting the cleanliness level of the ith physical object region;

[0129] invoke the target prediction model to predict the cleanliness level of the ith physical object region according to the reference object image;

[0130] if the predicted cleanliness level is greater than a threshold level, predict the material requirement amount required for cleaning the ith physical object region according to the predicted cleanliness level;

[0131] perform material loading processing on the physical robot according to the predicted material requirement amount.

[0132] In another implementation, the processing unit 701 can be further configured to:

[0133] obtain a plurality of object images obtained by the physical camera device capturing the physical object;

[0134] select an effective object image from the plurality of object images, the effective object image being an object image used to determine that the ith physical object region is the target physical object region;

[0135] perform model optimization on an initial prediction model using the effective object image to obtain a target prediction model.

[0136] In another implementation, the physical object is an object with a light-transmitting material, and the physical cleanliness detection device is a physical light-transmission tester. Accordingly, when the processing unit 701 is used to detect the cleanliness of the ith physical object region in the physical object in the physical space by using the physical cleanliness detection device, the processing unit 701 can be specifically used to:

[0137] obtain the light transmission of the ith physical object region in the physical object in the physical space, the light transmission of the ith physical object region being obtained by performing light transmission testing on the ith physical object region by using the physical light-transmission tester;

[0138] determine the cleanliness level of the ith physical object region according to the light transmission of the ith physical object region and the light transmission ranges corresponding to the plurality of cleanliness levels.

[0139] In another implementation, the processing unit 701 can be further used to:

[0140] if the cleanliness level of the ith physical object region is less than the threshold level, detect whether there is a physical robot working in the ith object region;

[0141] if there is, notify the existing physical robot to stop working, and notify the existing physical robot to wait for the next scheduling.

[0142] According to another embodiment of the present application, Figure 7 The units in the object processing apparatus shown can be combined into one or several other units respectively or all, or some of the units can be further split into a plurality of units with smaller functions to constitute, which can achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present application. The units are divided based on logical functions. In actual applications, the functions of a unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the object processing apparatus can also include other units. In actual applications, these functions can also be assisted by other units, and can be implemented by multiple units.

[0143] According to another embodiment of the present application, a computer program (including program code) capable of executing the steps involved in the corresponding method shown in Figure 2 or Figure 4 can be constructed by running on a general computing device such as a computer including a central processing unit (CPU), a random access storage medium (RAM), a read-only storage medium (ROM), and the like processing elements and storage elements. Figure 7The object processing apparatus device and the object processing method for implementing the embodiments of the present application are described above. The computer program can be recorded on a computer readable recording medium, for example, and loaded into the above-mentioned computing device through the computer readable recording medium and run therein.

[0144] The embodiments of the present application can determine a target physical object region from physical objects in a physical space, so as to schedule a physical robot to process the target physical object region in a targeted manner. Compared with full processing, the object processing efficiency can be improved, and the waste of energy consumption cost caused by the physical robot doing more useless work can be avoided, so as to save the energy consumption cost. Moreover, the embodiments of the present application obtain a digital space by digitizing the physical space, so that the environment of the digital space and the environment of the physical space remain consistent. In this way, in the digital space, the path information obtained by path planning according to the spatial position of the target digital object region corresponding to the target physical object region and the spatial position of the digital robot corresponding to the physical robot can accurately avoid obstacles in the physical space, ensuring the accuracy and reliability of the path information, and further avoiding collision when the physical robot moves according to the path information, thereby improving the moving safety of the physical robot. Since the physical robot does not need to use internal sensors to avoid obstacles and plan routes in real time during the entire processing process, the energy consumption cost of the physical robot can be further saved, the moving speed of the physical robot can be improved, and the object processing efficiency can be improved.

[0145] Based on the description of the method embodiments and the device embodiments, the embodiments of the present application further provide a computer device. Please refer to Figure 8 The computer device at least includes a processor 801, an input interface 802, an output interface 803, and a computer storage medium 804. The processor 801, the input interface 802, the output interface 803, and the computer storage medium 804 in the computer device can be connected through a bus or other means. The computer storage medium 804 can be stored in the memory of the computer device, and is used to store a computer program, which includes program instructions. The processor 801 is used to execute the program instructions stored in the computer storage medium 804. The processor 801 (or CPU (Central Processing Unit, Central Processing Unit)) is the computing core and control core of the computer device, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to realize corresponding method processes or corresponding functions.

[0146] In one embodiment, the processor 801 described in the embodiments of the present application can be used to perform a series of object processing, specifically including: determining a target physical object region from physical objects in a physical space, the target physical object region refers to a physical object region that needs to be processed by a physical robot in the physical space according to a work task; determining a digital space obtained by digitizing the physical space; the digital space at least includes a digital object corresponding to the physical object and a digital robot corresponding to the physical robot; determining a target digital object region corresponding to the target physical object region in the digital object, and performing path planning in the digital space according to the spatial position of the target digital object region and the spatial position of the digital robot; after the path information is planned, the physical robot is dispatched to move to the target physical object region according to the path information, and the target physical object region is processed according to the work task, and the like.

[0147] The embodiments of the present application also provide a computer storage medium (Memory), which is a memory device in a computer device, used for storing programs and data. It can be understood that the computer storage medium here can include an internal storage medium in the computer device, and of course can also include an extended storage medium supported by the computer device. The computer storage medium provides a storage space, which stores an operating system of the computer device. Moreover, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory; optionally, it can also be at least one computer storage medium located away from the aforementioned processor.

[0148] In one embodiment, one or more instructions stored in the computer storage medium can be loaded and executed by the processor to implement the corresponding steps of the method in the above-described object processing method embodiment; in a specific implementation, the one or more instructions in the computer storage medium are loaded and executed by the processor to perform the following steps: Figure 2 Or Figure 4 The steps of the method in the object processing method embodiment shown in the method; in a specific implementation, the one or more instructions in the computer storage medium are loaded and executed by the processor to perform the following steps:

[0149] Determining a target physical object region from physical objects in a physical space, the target physical object region refers to a physical object region that needs to be processed by a physical robot in the physical space according to a work task;

[0150] determine a digital space obtained by digitizing the physical space, the digital space comprising at least a digital object corresponding to the physical object and a digital robot corresponding to the physical robot;

[0151] determine a target digital object region corresponding to the target physical object region in the digital object, and perform path planning in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot;

[0152] after the path information is planned, dispatch the physical robot to move to the target physical object region according to the path information, and process the target physical object region according to the work task.

[0153] In an embodiment, the number of the physical robots is P, and one physical robot corresponds to one digital robot, P is an integer greater than 1; accordingly, when performing path planning in the digital space according to the spatial position of the target digital object region and the spatial position of the digital robot, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0154] select Q dispatchable digital robots from the P digital robots according to the state information of each digital robot, Q ∈ [1, P];

[0155] calculate a distance between each dispatchable digital robot and the target digital object region in the digital space according to the spatial position of each dispatchable digital robot and the spatial position of the target digital object region;

[0156] select a digital robot corresponding to a minimum distance from the Q dispatchable digital robots as a target digital robot to be dispatched according to the distance between each digital robot and the target digital object region;

[0157] perform path planning in the digital space according to the spatial position of the target digital object region and the spatial position of the target digital robot.

[0158] In another embodiment, the state information of any digital robot comprises a device state of the any digital robot and a remaining work material amount of the any digital robot; wherein the device state comprises a working state or an idle state; accordingly, when selecting Q dispatchable digital robots from the P digital robots according to the state information of each digital robot, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0159] determining a target resource demand required for performing the work task on the target physical object region, and determining, from the P digital robots, a digital robot whose remaining work resource amount is greater than or equal to the target resource demand;

[0160] selecting Q digital robots in the working state from the determined digital robots as schedulable digital robots.

[0161] In another implementation, when the physical robot is scheduled to move to the target physical object region according to the path information and to process the target physical object region according to the work task, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0162] taking the physical robot corresponding to the target digital robot in the P physical robots as a target physical robot to be scheduled;

[0163] scheduling the target physical robot to move to the target physical object region according to the path information and to process the target physical object region according to the work task.

[0164] In another implementation, the work task of the physical robot is a cleaning task, and the physical space further includes a physical cleanliness detection device; the physical objects include I physical object regions, I being a positive integer; correspondingly, when the target physical object region is determined from the physical objects in the physical space, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0165] performing cleanliness detection on an i-th physical object region in the physical objects in the physical space by the physical cleanliness detection device to obtain a cleanliness level of the i-th physical object region; wherein i ∈ [1, I];

[0166] if the cleanliness level of the i-th physical object region is less than a threshold level, determining the i-th physical object region as the target physical object region.

[0167] In another implementation, the physical cleanliness detection device is a physical camera device; correspondingly, when the cleanliness level of the i-th physical object region is obtained by performing cleanliness detection on the i-th physical object region in the physical objects in the physical space by the physical cleanliness detection device, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0168] obtaining a target object image obtained by the physical camera device by photographing the physical objects, the target object image at least including a region image of the i-th physical object region in the physical objects;

[0169] segmenting a region image of the i-th physical object region from the target object image, and performing cleanliness detection on the i-th physical object region according to the region image of the i-th physical object region to obtain a cleanliness level of the i-th physical object region.

[0170] In another implementation, when the cleanliness level of the i-th physical object region is obtained by performing cleanliness detection on the i-th physical object region according to the region image of the i-th physical object region, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0171] obtaining N reference images, different reference images having different cleanliness levels, N being a positive integer;

[0172] calculating a feature similarity between the region image of the i-th physical object region and each reference image in the N reference images;

[0173] selecting, according to a feature similarity calculation result, a reference image corresponding to a maximum feature similarity from the N reference images as a similar reference image of the i-th physical object region;

[0174] determining a cleanliness level of the similar reference image as the cleanliness level of the i-th physical object region.

[0175] In another implementation, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0176] obtaining a reference object image of the physical object and a target prediction model for predicting the cleanliness level of the i-th physical object region;

[0177] calling the target prediction model to predict the cleanliness level of the i-th physical object region according to the reference object image;

[0178] if the predicted cleanliness level is greater than a threshold level, predicting a material requirement amount required for cleaning the i-th physical object region according to the predicted cleanliness level;

[0179] performing material loading processing on the physical robot according to the predicted material requirement amount.

[0180] In another implementation, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0181] obtaining a plurality of object images obtained by the physical camera device capturing the physical object;

[0182] screening an effective object image from the plurality of object images, the effective object image being an object image used for determining that the ith physical object region is taken as the target physical object region;

[0183] adopting the effective object image to perform model optimization on an initial prediction model to obtain a target prediction model.

[0184] In another implementation, the physical object is an object with a light-transmitting material, and the physical cleanliness detection device is a physical light-transmitting rate tester. Correspondingly, when the cleanliness of the ith physical object region in the physical object in the physical space is detected by the physical cleanliness detection device to obtain the cleanliness level of the ith physical object region, the one or more instructions can be loaded by the processor and specifically executed as follows:

[0185] obtaining the light-transmitting rate of the ith physical object region in the physical object in the physical space, the light-transmitting rate of the ith physical object region being obtained by the physical light-transmitting rate tester performing light-transmitting rate testing on the ith physical object region;

[0186] determining the cleanliness level of the ith physical object region according to the light-transmitting rate of the ith physical object region and a preset light-transmitting rate range corresponding to a plurality of cleanliness levels.

[0187] In another implementation, the one or more instructions can also be loaded by the processor and specifically executed as follows:

[0188] if the cleanliness level of the ith physical object region is less than a threshold level, detecting whether there is a physical robot working in the ith object region;

[0189] if there is, notifying the existing physical robot to stop working, and notifying the existing physical robot to wait for next scheduling.

[0190] Compared with full processing, the object processing efficiency can be improved, and the waste of energy consumption cost of the physical robot caused by doing more useless work can be avoided, so that the energy consumption cost is saved. Moreover, the environment of the digital space is consistent with the environment of the physical space by digital processing of the physical space, so that the path information obtained by path planning in the digital space according to the spatial position of the target digital object region corresponding to the target physical object region and the spatial position of the digital robot corresponding to the physical robot can accurately avoid obstacles in the physical space, ensuring the accuracy and reliability of the path information, and avoiding collision when the physical robot moves according to the path information, thereby improving the moving safety of the physical robot. Since the physical robot does not need to use the internal sensor to avoid obstacles and plan the route in real time in the whole processing process, the energy consumption cost of the physical robot can be further saved, the moving speed of the physical robot is improved, and the object processing efficiency is improved.

[0191] It should be noted that, according to an aspect of the present application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned various optional manners of the object processing method embodiment aspect provided by the object processing method embodiment aspect shown in the present application. Figure 2 or Figure 4 The method provided by the various optional manners of the object processing method embodiment aspect shown in the present application.

[0192] Moreover, it should be understood that the above disclosure is only the preferred embodiment of the present application, and of course cannot limit the scope of the rights of the present application, so the equivalent changes made according to the claims of the present application still fall within the scope of the present application.

Claims

1. An object processing method characterized by comprising: The method comprises the following steps: determining a target physical object area from physical objects in a physical space, the target physical object area being an area of a physical object that needs to be processed by a physical robot in the physical space according to a work task; when the work task of the physical robot is a cleaning task, the physical object refers to any object that has a cleaning demand, and the physical object comprises a plurality of physical object areas, each physical object area being subjected to cleanliness level detection, and the target physical object area being a physical object area with a cleanliness level less than a threshold level; before the physical robot works, the cleanliness level of an i-th physical object area is predicted by a target prediction model to determine whether to load the physical robot with supplies, i being a positive integer; if the predicted cleanliness level of the i-th physical object area is greater than the threshold level, the predicted cleanliness level of the i-th physical object area is used to predict the amount of supplies required by the i-th physical object, and the physical robot is loaded with supplies according to the predicted amount of supplies; the target prediction model is generated in the following manner: arranging a plurality of effective object images in a time sequence, the effective object images being object images that have been historically used to determine the i-th physical object area as the target physical object area; taking the cleanliness level of the i-th physical object area determined by a physical cleanliness detection device based on a (k+1)th effective object image as the labeled cleanliness level of a kth effective object image, and calling an initial prediction model to predict the cleanliness level of the i-th physical object area according to the kth effective object image, and optimizing the model parameters of the initial prediction model according to the difference between the predicted cleanliness level and the labeled cleanliness level to obtain the target prediction model, k being a positive integer and being less than the total number of effective object images; determining a digital space obtained by digitizing the physical space; the digital space at least comprising a digital object corresponding to the physical object and a digital robot corresponding to the physical robot; determining a target digital object area corresponding to the target physical object area in the digital object, and performing path planning in the digital space according to the spatial position of the target digital object area and the spatial position of the digital robot; after the path information is planned, scheduling the physical robot to move to the target physical object area according to the path information, and processing the target physical object area according to the work task.

2. The method of claim 1, wherein, The number of physical robots is P, and one physical robot corresponds to one digital robot, P being an integer greater than 1; the path planning in the digital space according to the spatial position of the target digital object area and the spatial position of the digital robot comprises: selecting Q schedulable digital robots from the P digital robots according to the state information of each digital robot, Q ∈ [1, P]. In the digital space, a distance between each schedulable digital robot and the target digital object region is calculated according to a spatial position of each schedulable digital robot and a spatial position of the target digital object region; A digital robot corresponding to a minimum distance is selected as a target digital robot to be scheduled from the Q schedulable digital robots according to the distance between each digital robot and the target digital object region; In the digital space, path planning is performed according to the spatial position of the target digital object region and the spatial position of the target digital robot.

3. The method of claim 2, wherein, The state information of any digital robot includes a device state of the any digital robot and a remaining working resource amount of the any digital robot; wherein the device state includes a working state or an idle state; The selecting Q schedulable digital robots from the P digital robots according to the state information of each digital robot includes: Determining a target resource demand amount required for performing the working task on the target physical object region, and determining a digital robot with a remaining working resource amount greater than or equal to the target resource demand amount from the P digital robots; Selecting Q digital robots in a working state as schedulable digital robots from the determined digital robots.

4. The method of claim 2, wherein, The scheduling the physical robot to move to the target physical object region according to the path information and performing processing on the target physical object region according to the working task includes: Selecting a physical robot corresponding to the target digital robot from the P physical robots as a target physical robot to be scheduled; Scheduling the target physical robot to move to the target physical object region according to the path information and performing processing on the target physical object region according to the working task.

5. The method according to any one of claims 1 to 4, wherein The working task of the physical robot is a cleaning task, and the physical space further includes a physical cleanliness detection device; The determining the target physical object region from the physical objects in the physical space includes: Performing cleanliness detection on an i th physical object region in the physical objects in the physical space by the physical cleanliness detection device to obtain a cleanliness level of the i th physical object region; If the cleanliness level of the i th physical object region is less than a threshold level, the i th physical object region is determined as the target physical object region.

6. The method of claim 5, wherein, The physical cleanliness detection device is a physical camera device; and the performing cleanliness detection on the i th physical object region in the physical objects in the physical space by the physical cleanliness detection device to obtain the cleanliness level of the i th physical object region includes: Obtaining a target object image obtained by the physical camera device by shooting the physical objects, the target object image at least including a region image of the i th physical object region in the physical objects; and Segmenting a region image of the i-th physical object region from the target object image, and performing cleanliness detection on the i-th physical object region according to the region image of the i-th physical object region to obtain a cleanliness level of the i-th physical object region.

7. The method of claim 6, wherein, The cleanliness detection on the i-th physical object region according to the region image of the i-th physical object region to obtain a cleanliness level of the i-th physical object region comprises: Obtaining N reference images, different reference images having different cleanliness levels, N being a positive integer; Calculating feature similarity between the region image of the i-th physical object region and each reference image in the N reference images; According to the feature similarity calculation result, selecting a reference image corresponding to the maximum feature similarity from the N reference images as a similar reference image of the i-th physical object region; Determining the cleanliness level of the similar reference image as the cleanliness level of the i-th physical object region.

8. The method of claim 5, wherein, The physical object is an object with a light-transmitting material, and the physical cleanliness detection device is a physical light-transmission rate tester; the cleanliness detection on the i-th physical object region in the physical object in the physical space by the physical cleanliness detection device to obtain a cleanliness level of the i-th physical object region comprises: Obtaining a light-transmission rate of the i-th physical object region in the physical object in the physical space, the light-transmission rate of the i-th physical object region being obtained by the physical light-transmission rate tester performing light-transmission rate testing on the i-th physical object region; According to the light-transmission rate of the i-th physical object region and a light-transmission rate range corresponding to a plurality of cleanliness levels, determining the cleanliness level of the i-th physical object region.

9. The method of claim 5, wherein, The method further comprises: If the cleanliness level of the i-th physical object region is less than a threshold level, detecting whether there is a physical robot working in the i-th object region; If there is, notifying the existing physical robot to stop working, and notifying the existing physical robot to wait for next scheduling.

10. An object processing apparatus characterized by comprising: It comprises: A processing unit is configured to determine a target physical object region from physical objects in a physical space, the target physical object region being a physical object region that needs to be processed by a physical robot in the physical space according to a work task; when the work task of the physical robot is a cleaning task, the physical object is any object that needs to be cleaned, and the physical object includes a plurality of physical object regions, each of which is detected for a cleanliness level, and the target physical object region is a physical object region with a cleanliness level less than a threshold level; before the physical robot works, the cleanliness level of an i-th physical object region is predicted by a target prediction model to determine whether to load the physical robot with supplies, i being a positive integer; if the cleanliness level of the i-th physical object region is predicted to be greater than the threshold level, the predicted cleanliness level of the i-th physical object region is used to predict the amount of supplies required for the i-th physical object, and the physical robot is loaded with supplies according to the predicted amount of supplies; the target prediction model is generated in the following manner: arranging a plurality of effective object images of the physical object according to a time sequence of the effective object images, the effective object image being an object image that has historically been used to determine the i-th physical object region as the target physical object region; taking the cleanliness level of the i-th physical object region determined by a physical cleanliness detection device based on a (k+1)-th effective object image as a labeled cleanliness level of a k-th effective object image, and calling an initial prediction model to predict the cleanliness level of the i-th physical object region according to the k-th effective object image, and optimizing model parameters of the initial prediction model according to a difference between the predicted cleanliness level and the labeled cleanliness level to obtain the target prediction model, k being a positive integer and being less than a total number of effective object images; The processing unit is further configured to determine a digital space obtained by digitizing the physical space; the digital space at least includes a digital object corresponding to the physical object and a digital robot corresponding to the physical robot; The processing unit is further configured to determine a target digital object region corresponding to the target physical object region in the digital object, and to plan a path in the digital space according to a spatial position of the target digital object region and a spatial position of the digital robot; A scheduling unit is configured to schedule the physical robot to move to the target physical object region according to the path information and to process the target physical object region according to the work task after the path information is planned.

11. A computer device comprising an input interface and an output interface, characterized in that, Further comprising: a processor adapted to implement one or more instructions; and a computer storage medium storing one or more instructions adapted to be loaded and executed by the processor to implement the object processing method according to any one of claims 1-9. ​ 12. A computer storage medium, characterized in that The computer storage medium stores one or more instructions adapted to be loaded and executed by the processor to perform the object processing method according to any one of claims 1-9.

13. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the object processing method according to any one of claims 1-9.

Images