Embodied Task Configuration Method Based on User Demonstration Data and Related Devices

Abstract

The present application discloses an embodied task configuration method and related device based on user demonstration data. The method includes: sending a busy / idle query request to the server in response to a first operation of the user; receiving a busy / idle query reply message from the server and displaying a task configuration interface, where the task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls; sending a task configuration message to the server in response to a second operation of the user, where the task configuration message carries a target humanoid robot and a target task; receiving a training result message from the server and displaying a training result interface, where the training result interface is used to display the training score of the target humanoid robot executing the target control scheme, and the target control scheme is the content generated by the server according to the user demonstration data, and the user demonstration data is used to characterize the actions performed by the user for the target task. The present application can achieve remote training of the robot and improve the diversity and flexibility of the tasks performed by the humanoid robot.

Description

Technical Field

[0001] This application relates to the field of robot technology, and particularly relates to an embodied task configuration method and related device based on user demonstration data. Background Art

[0002] A humanoid robot, also known as an anthropomorphic robot, is a robot with a human form. Before being put into application, a humanoid robot needs to continuously perform imitation training and learning based on human actions. Currently, in order to improve efficiency and save costs, manufacturers usually provide the same set of training data to multiple humanoid robots for training to improve the functions of the humanoid robots before leaving the factory. Such training cannot achieve differential training for different humanoid robots, and the training effect is limited. Summary of the Invention

[0003] Embodiments of this application provide an embodied task configuration method and related device based on user demonstration data, aiming to implement the application function of remotely training a humanoid robot, thereby improving the diversity and flexibility of the training and learning of the humanoid robot.

[0004] In a first aspect, embodiments of this application provide an embodied task configuration method applied to a user device of an embodied task configuration system. The embodied task configuration system includes a server, a humanoid robot, the user device, and a virtual reality device. The server is communicatively connected to the humanoid robot, the user device, and the virtual reality device respectively. The method includes:

[0005] Sending a busy / idle query request to the server in response to a first operation by the user on the user device;

[0006] Receiving a busy / idle query reply message from the server and displaying a task configuration interface. The task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls. The task selection controls are used to display corresponding task contents, and the humanoid robot selection controls are used to display the busy / idle status of the corresponding humanoid robots;

[0007] Sending a task configuration message to the server in response to a second operation by the user on the user device. The task configuration message carries a target humanoid robot and a target task. The target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls;

[0008] Receive a training result message from the server and display a training result interface for displaying the training score of the target humanoid robot executing the target control scheme. The target control scheme is generated by the server based on user demonstration data uploaded by the virtual reality device to the server. The user demonstration data is used to represent the actions performed by the user for the target task.

[0009] In a possible example of the first aspect, the task selection control includes a first task control and a second task control. The task content corresponding to the first task control is a task performed on the upper body of the humanoid robot, and the task content corresponding to the second task control is a task performed on the whole body of the humanoid robot.

[0010] When the target task is the task content corresponding to the first task control, the user demonstration data includes user pose data, which is operation data collected by the virtual reality device.

[0011] When the target task is the task content corresponding to the second task control, the user demonstration data includes the user pose data and task video data, which is video content collected by the virtual reality device for the user's whole body activities.

[0012] In a possible example of the first aspect, the target control scheme is generated by the server according to the following steps:

[0013] Determine the task type of the target task. The task type includes a first task type and a second task type. The first task type is the task type corresponding to the first task control, and the second task type is the task type corresponding to the second task control.

[0014] If the task type of the target task is the first task type, determine the execution object according to the target task, and generate the target control scheme according to the execution object and the user pose data. The execution object includes the left hand, the right hand, or both hands.

[0015] If the task type of the target task is the second task type, analyze the task video data to determine the user action pose data, and generate the target control scheme according to the user action pose data and the user pose data.

[0016] In a possible example of the first aspect, before determining the task type of the target task, the generation steps of the target control scheme further include:

[0017] Determine the fluctuation value of the user posture data, where the fluctuation value is used to characterize the stability degree of the user posture data;

[0018] Compare the fluctuation value with a preset threshold;

[0019] If the fluctuation value is greater than the preset threshold, perform smoothing processing on the user posture data to obtain target posture data, where the target posture data is used to generate the target control scheme.

[0020] In a possible example of the first aspect, the training score is generated by the server according to the following steps:

[0021] Obtain the training data uploaded by the target humanoid robot, where the training data includes training time, preset training times, and training success rate;

[0022] Determine the training score according to the training data.

[0023] In a possible example of the first aspect, the training result interface is further used to display the score result of the integral, where the integral is used to exchange items according to a preset integral rule; the score result of the integral is determined by the server according to the following steps:

[0024] Obtain the preset basic score for a single training;

[0025] Determine the training score according to the training score and the preset score rule;

[0026] Sum the basic score and the training score to obtain the score result.

[0027] In a possible example of the first aspect, after receiving the training result message from the server and displaying the training result interface, the method further includes:

[0028] Send a machine query request to the server in response to a third operation by the user on the user device, where the machine query request is used to query a recommended humanoid robot suitable for the user;

[0029] Receive a query reply message from the server and display a product recommendation interface, where the product recommendation interface is used to display the device information of the recommended humanoid robot, and the recommended humanoid robot is determined by the server according to the following steps: Obtain the historical data of the user for the target task, where the historical data includes all the training data of the user selecting different humanoid robots to execute the target task; Determine the adaptation value corresponding to each humanoid robot for executing the target task according to the historical data; Compare all the adaptation values and determine the humanoid robot corresponding to the maximum adaptation value as the recommended humanoid robot.

[0030] In a second aspect, an embodiment of the present application provides an embodied task configuration device based on user demonstration data, which is applied to a user device of an embodied task configuration system. The embodied task configuration system includes a server, a humanoid robot, the user device, and a virtual reality device. The server is communicatively connected to the humanoid robot, the user device, and the virtual reality device respectively. The embodied task configuration device based on user demonstration data includes:

[0031] A first response unit, configured to send a busy / idle query request to the server in response to a first operation by the user on the user device;

[0032] A first receiving unit, configured to receive a busy / idle query reply message from the server and display a task configuration interface, where the task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls. The task selection controls are used to display corresponding task contents, and the humanoid robot selection controls are used to display the busy / idle status of the corresponding humanoid robots;

[0033] A second response unit, configured to send a task configuration message to the server in response to a second operation by the user on the user device. The task configuration message carries a target humanoid robot and a target task, where the target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls;

[0034] A second receiving unit, configured to receive a training result message from the server and display a training result interface, where the training result interface is used to display the training score of the target humanoid robot executing a target control scheme. The target control scheme is content generated by the server according to user demonstration data, and the user demonstration data is content uploaded by the virtual reality device to the server. The user demonstration data is used to characterize the actions performed by the user for the target task.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. The programs include instructions for performing the steps in the first aspect of the embodiments of the present application.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, storing a computer program for electronic data exchange, where the computer program causes a computer to execute some or all of the steps described in the first aspect of this embodiment.

[0037] It can be seen that in this embodiment, the user equipment sends a busy / idle query request to the server by responding to a first operation of the user on the user equipment; and receives a busy / idle query reply message from the server, and can display a task configuration interface, which includes a plurality of task selection controls and a plurality of humanoid robot selection controls. The task selection controls are used to display the corresponding task content, and the humanoid robot selection controls are used to display the busy / idle status of the corresponding humanoid robots. It can also send a task configuration message to the server by responding to a second operation of the user on the user equipment. The task configuration message carries a target humanoid robot and a target task. The target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls; receive a training result message from the server, and display a training result interface, which is used to display the training score of the target humanoid robot executing the target control scheme. The target control scheme is the content generated by the server according to the user demonstration data, and the user demonstration data is the content uploaded by the virtual reality device to the server, and the user demonstration data is used to represent the actions performed by the user for the target task. It can be seen that in this application, the user can select the required humanoid robot selection control and task selection control on the task configuration interface displayed on the user equipment to determine the target humanoid robot to be trained and the target task for its corresponding training, and display the training result interface on the user equipment after the training is completed for the user to understand the training situation. In this way, the application function of remotely training the humanoid robot can be realized, which is beneficial to the differential training of the humanoid robot and improves the diversity and flexibility of the training and learning of the humanoid robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a schematic architecture diagram of an embodied task configuration system provided by an embodiment of the present application;

[0040] Figure 2 is a schematic flowchart of an embodied task configuration method based on user demonstration data provided by an embodiment of the present application;

[0041] Figure 3 is a schematic interface diagram of a task initiation interface provided by an embodiment of the present application;

[0042] Figure 4 is a schematic interface diagram of a task configuration interface provided by an embodiment of the present application;

[0043] Figure 5 is a schematic diagram of an interface of a wearable prompt interface provided by an embodiment of the present application;

[0044] Figure 6 is a schematic diagram of an interface of a training result interface provided by an embodiment of the present application;

[0045] Figure 7 is a schematic diagram of an interface of a product recommendation interface provided by an embodiment of the present application;

[0046] Figure 8 is a composition example diagram of an electronic device provided by an embodiment of the present application;

[0047] Figure 9 is a functional unit composition block diagram of a first embodied task configuration device based on user demonstration data provided by an embodiment of the present application;

[0048] Figure 10 is a functional unit composition block diagram of a second embodied task configuration device based on user demonstration data provided by an embodiment of the present application. Detailed implementation manners

[0049] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0050] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0051] Referring to "embodiment" in this article means that a specific feature, structure or characteristic described in combination with the embodiment may be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0052] The embodiments of the present application will be described below with reference to the accompanying drawings.

[0053] The technical solution of the present application can be applied to, for example, Figure 1 the embodied task configuration system 10 as shown. The embodied task configuration system 10 includes a server 110, a user device 120, a humanoid robot 130, and a virtual reality device 140. The server 110 is communicatively connected to the user device 120, the humanoid robot 130, and the virtual reality device 140 respectively.

[0054] Among them, the server 110 can be an outsourced server, a cloud server, an edge server, an intelligent robot, etc., which is not limited here.

[0055] Among them, the user device 120 can be a terminal device configured with the software application provided by the server 110 for humanoid robot training. The user device 120 can implement the related functions of the software application by communicating with the server 110. For example, the user device 120 can be a smart phone (such as an Android phone, an iOS phone, a Windows Phone), a smart computer (such as a tablet computer, a handheld computer, a notebook computer, a desktop computer), a driving recorder, a mobile Internet device (MID, Mobile Internet Devices), or a wearable device (such as a smart watch, a Bluetooth headset), etc. The above are only examples, not an exhaustive list, including but not limited to the above devices.

[0056] Among them, the virtual reality device 140 includes a head-mounted display device (i.e., a head-mounted stereoscopic display, etc.) and an interaction device, etc. Among them, the head-mounted display device is used to dynamically display the visual information of the target humanoid robot so that the user can operate from the perspective of the target humanoid robot. The interaction device is used to collect user demonstration data for the server to analyze and process to obtain a target control scheme to control the training of the target humanoid robot. The interaction device includes wearable devices such as data gloves for collecting interaction data and action capture devices (such as RGB cameras, etc., pose estimators).

[0057] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of an embodied task configuration method based on user demonstration data provided by an embodiment of the present application. This method can be applied to the user device 120 in the embodied task configuration system as shown in Figure 1 As shown in Figure 2 , the embodied task configuration method based on user demonstration data includes:

[0058] Step S210, sending a busy / idle query request to the server in response to a first operation by the user on the user device.

[0059] Among them, the first operation refers to the selection operation performed by the user on the control for initiating a busy / idle query request in the interface displayed on the user device. The selection operation can be operations such as single-click, double-click, long-press, etc. Exemplarily, refer to Figure 3 , the user performs a selection operation on the task initiation control 310 in the task initiation interface 30 shown in Figure 3 , and the user device can send a busy / idle query request to the server. Specifically, the task initiation interface 30 may further include controls such as a mall and training history, etc., so that functions such as commodity purchase and training history query can be realized by triggering these controls.

[0060] Among them, the busy / idle query request is used to query the busy / idle state of the robot. The busy / idle state includes a busy state and an idle state. Exemplarily, refer to Figure 4 . The busy state is used to represent that the corresponding humanoid robot is performing training tasks for other users. The idle state is used to represent that the corresponding humanoid robot is not currently selected by other users, and the user can select this humanoid robot to perform training tasks.

[0061] Step S220: Receive the busy / idle query reply message from the server and display a task configuration interface. The task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls.

[0062] Among them, the busy / idle query reply message is used to instruct the user device to display the task configuration interface. The task selection controls in the task configuration interface are used to display the corresponding task content. One task selection control corresponds to one task content, and the task content is specifically the task content available for the user to select for training the humanoid robot. The humanoid robot selection controls in the task configuration interface are used to display the busy / idle state of the corresponding humanoid robot. One humanoid robot selection control corresponds to one humanoid robot.

[0063] In a specific implementation, after receiving the busy / idle query request, the server will query the busy / idle states of all humanoid robots to generate a query reply message. Alternatively, the server can pre-query the busy / idle states of all robots before receiving the busy / idle query request, so as to directly send a query reply message to the user device when receiving the busy / idle query request, thereby improving the response efficiency and enhancing the user experience on the user device side.

[0064] Specifically, the task content corresponding to any task selection control can be executed by any humanoid robot. At this time, in the task configuration interface, the task selection control and the humanoid robot selection control can be two parallel contents for the user to select. Or, in the task configuration interface, the directory corresponding to any task selection control includes the humanoid robot selection controls corresponding to all humanoid robots. Or, in the task configuration interface, the directory corresponding to the humanoid robot selection control corresponding to any humanoid robot includes all task selection controls.

[0065] Or, specifically, humanoid robots can be used differently to execute different task contents, so as to further implement the differential training of humanoid robots, making the functions of the trained humanoid robots more targeted. At this time, in the task configuration interface, the directory corresponding to a single task selection control only includes the humanoid robot selection controls corresponding to the humanoid robots that can be used to execute the task content corresponding to this task selection control. Or, in the task configuration interface, the directory corresponding to the humanoid robot selection control corresponding to a single humanoid robot includes the task selection controls corresponding to the task contents that this humanoid robot can execute.

[0066] Step S230, in response to a second operation by the user on the user device, send a task configuration message to the server, where the task configuration message carries a target humanoid robot and a target task.

[0067] Among them, the target humanoid robot is one of the humanoid robots corresponding to multiple humanoid robot selection controls, and the target task is one of the task contents corresponding to multiple task selection controls.

[0068] Among them, the second operation refers to the selection operation performed by the user on the control for initiating the task configuration message after performing the selection operations on a single task selection control and a single humanoid robot selection control in the task configuration interface displayed on the user device.

[0069] Exemplarily, referring to Figure 4 , after the user device displays the task configuration interface 40, the user can perform a selection operation on one of all the displayed task selection controls 420, and perform a selection operation on one of the idle humanoid robot selection controls 430 that are displayed, and then perform a selection operation on the task confirmation control 410 to generate a task configuration message and send the task configuration message to the server. Among them, the task content corresponding to the task selection control on which the user performs the selection operation is the target task, and the humanoid robot corresponding to the humanoid robot selection control on which the user performs the selection operation is the target humanoid robot.

[0070] Specifically, referring to Figure 4, the task contents corresponding to multiple task selection controls 420 include "desktop resource processing", "desktop garbage cleaning", "desktop item color classification", etc. When the user selects the task selection control 420 corresponding to "desktop item color classification", the humanoid robots available for performing this task content include "Robot A", "Robot B", and "Robot C". Among them, "Robot A" and "Robot B" are in an idle state, and their corresponding humanoid robot selection controls 430 can be used as the selected objects.

[0071] Step S240, receive a training result message from the server and display a training result interface, where the training result interface is used to display the training score of the target humanoid robot executing the target control scheme.

[0072] Among them, the training result message is used to instruct the user device to display the training result interface.

[0073] Among them, the target control scheme is the content generated by the server according to the user demonstration data, the user demonstration data is the content uploaded by the virtual reality device to the server, and the user demonstration data is used to represent the actions performed by the user for the target task.

[0074] In a specific implementation, after the server receives a task configuration message from the user device, it will obtain the user demonstration data uploaded by the virtual reality device, analyze and process the user demonstration data to generate a target control scheme, and then send a control instruction carrying the target control scheme to the target humanoid robot to instruct the target humanoid robot to perform training according to the target control scheme. The target humanoid robot will upload the training data for its training, and the server can analyze and process the training data to obtain the training score of the target humanoid robot executing the target control scheme, thereby generating a training result message and sending the training result message to the user device to instruct the user device to display the training result interface.

[0075] It can be seen that in this embodiment, the user equipment sends a busy / idle query request to the server by responding to a first operation of the user on the user equipment; and receives a busy / idle query reply message from the server, and can display a task configuration interface. The task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls. The task selection controls are used to display the corresponding task content, and the humanoid robot selection controls are used to display the busy / idle status of the corresponding humanoid robots. It can also send a task configuration message to the server by responding to a second operation of the user on the user equipment. The task configuration message carries a target humanoid robot and a target task. The target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls; receive a training result message from the server, and display a training result interface. The training result interface is used to display the training score of the target humanoid robot executing the target control scheme. The target control scheme is the content generated by the server according to the user demonstration data. The user demonstration data is the content uploaded by the virtual reality device to the server, and the user demonstration data is used to represent the actions performed by the user for the target task. It can be seen that in this application, the user can select the required humanoid robot selection control and task selection control on the task configuration interface displayed by the user equipment to determine the target humanoid robot to be trained and the target task for its corresponding training, and display the training result interface through the user equipment after the training is completed for the user to understand the training situation. In this way, the application function of remotely training the humanoid robot can be realized, which is beneficial to differentiating the training of the humanoid robot and improving the diversity and flexibility of the training and learning of the humanoid robot.

[0076] In a possible example, the task selection controls include a first task control and a second task control. The task content corresponding to the first task control is a task performed on the upper body of the humanoid robot, and the task content corresponding to the second task control is a task performed on the whole body of the humanoid robot; when the target task is the task content corresponding to the first task control, the user demonstration data includes user posture data, and the user posture data is the operation data collected by the virtual reality device; when the target task is the task content corresponding to the second task control, the user demonstration data includes the user posture data and task video data, and the task video data is the video content collected by the virtual reality device for the whole body activities of the user.

[0077] Specifically, when the embodied task configuration system is pre-configured, the task content can be further divided into a first task type, a second task type, etc. Exemplarily, see Figure 4, the task content refers to the content of the teleoperation task, which may include a first task type and a second task type. Among them, the task content corresponding to the first task control belongs to the first task type. The task content corresponding to the second task control belongs to the second task type. In this way, the user can select the first task control under the first task type or the second task control under the second task type according to the needs, so as to achieve differential training for different humanoid robots, making the functions of the humanoid robots more targeted. In specific implementation, the component devices and structures of the humanoid robot for executing the first task type and the humanoid robot for executing the second task type can be configured differently, so as to reduce the production and manufacturing costs while meeting the functional requirements, and meet the usage and purchase needs of different users.

[0078] In specific implementation, the user posture data refers to the data collected by wearable devices such as data gloves and head-mounted displays for collecting interaction data. The task video data refers to the video data collected by a full-body motion capture device (such as an RGB camera). When the target task is the task content corresponding to the first task control, it indicates that the target task to be executed by the target humanoid robot is a task for the upper body. At this time, the server can generate a target control scheme based on the user posture data, so the user demonstration data collected by the virtual reality device can only include the user posture data. When the target task is the task content corresponding to the second task control, it indicates that the target task to be executed by the target humanoid robot is a task for the whole body. At this time, the virtual reality device can further collect task video data on the basis of collecting the user posture data, so as to improve the accuracy and reliability of the result of the server's processing of the user demonstration data. Exemplarily, the tasks for the upper body may include desktop resource processing, desktop garbage cleaning, desktop item color classification, etc., and the tasks for the whole body may include squatting down to tie, take out, and place the garbage bag of the trash can at the door.

[0079] In specific implementation, after the server receives the task configuration message from the user device, the server can also send a wearing prompt message to the user device. The user device can display a wearing prompt interface according to the indication of the wearing prompt message to prompt the user to wear the virtual reality device. After the user device displays the wearing prompt interface for prompting, the virtual reality device can detect whether the user has completed wearing, and prompt the user to perform corresponding actions according to the target task after wearing, so that the virtual reality device can collect the user demonstration data.

[0080] Exemplarily, see Figure 5 , when the target task is the task content corresponding to the first task control, the wearing prompt interface can be as Figure 5As shown in (a) therein, the wearing prompt interface includes a first prompt area 510 for prompting the user to wear the head-mounted device, and a second prompt area 520 for prompting the user to wear wearable devices such as data gloves for collecting interaction data. When the target task is the task content corresponding to the second task control, the displayed wearing prompt interface may further include the content shown in Figure 5 as shown in (b) therein. The user can view the content shown in Figure 5 as shown in (a) and (b) therein by means of sliding or page turning. As Figure 5 shown in (b) therein, the wearing prompt interface may further include a third prompt area 530 for prompting the user to set up the motion capture device and be within its acquisition range.

[0081] It can be seen that in this example, by classifying the task selection controls into the first task control and the second task control, and obtaining the user gesture data corresponding to the first task control as the user demonstration data, and obtaining the user gesture data and the task video data corresponding to the second task control as the user demonstration data, the embodied task configuration system can achieve differential management of different types of tasks, so as to ensure the accuracy of the wearing prompt content displayed on the user device side, which is beneficial to improving the accuracy and reliability of the server's data processing.

[0082] In a possible example, the target control scheme is generated by the server according to the following steps: determining the task type of the target task, where the task type includes a first task type and a second task type, the first task type is the task type corresponding to the first task control, and the second task type is the task type corresponding to the second task control; if the task type of the target task is the first task type, determining the execution object according to the target task, and generating the target control scheme according to the execution object and the user gesture data, where the execution object includes the left hand, the right hand or both hands; if the task type of the target task is the second task type, analyzing the task video data to determine the user action posture data, and generating the target control scheme according to the user action posture data and the user gesture data.

[0083] Among them, the execution object is used to represent the limb structure used by the target humanoid robot when executing the training content corresponding to the target task.

[0084] In specific implementation, after receiving the task configuration message from the user device, the server can obtain the user demonstration data uploaded by the virtual reality device, and analyze and process the user demonstration data to generate the target control scheme. The specific analysis and processing process is as follows: the server first determines the task type corresponding to the currently executed target task, and the task type can be the data pre-stored by the server according to the task content, or the content carried in the task configuration message.

[0085] When the server determines that the task type of the target task is the first task type, it will determine the limb structure used by the user to perform the action of the target task based on the user posture data uploaded by the virtual reality device, and determine the execution object corresponding to the target humanoid robot according to the limb structure. If the user uses the left hand for the action, the execution object is the left hand of the target humanoid robot. Then, the server determines the motion data of the execution object according to the joint movement direction and joint movement angle (data collected by the data glove) when the limb structure moves, so as to generate a target control scheme for controlling the upper body of the target humanoid robot according to the motion data and the data captured by the head-mounted device in the user posture data, so as to realize the remote control training of the target humanoid robot. Among them, the data captured by the head-mounted device is used to represent the positions and movement trajectories of the user's head, upper body and arms.

[0086] When the server determines that the task type of the target task is the second task type, it will obtain the task video data and user posture data uploaded by the virtual reality device. On the basis of the above data processing for the first task type, it will perform posture analysis on the task video data to obtain user action posture data (such as upper body posture and lower body posture, arm and wrist posture, finger joint posture, etc. data), so as to generate a target control scheme for controlling the whole body of the target humanoid robot in combination with the user action posture data and motion data, and realize the remote control training of the target humanoid robot. Alternatively, the server can generate a target control scheme for controlling the whole body of the target humanoid robot in combination with the user action posture data, motion data and the data captured by the head-mounted device in the user posture data to improve the accuracy and reliability of the data.

[0087] It can be seen that in this example, the server adopts different data processing methods for target tasks of different task types, which can realize the differential processing of data and improve the intelligence of the server in data processing.

[0088] In a possible example, before determining the task type of the target task, the step of generating the target control scheme further includes: determining the fluctuation value of the user posture data, where the fluctuation value is used to characterize the stability degree of the user posture data; comparing the fluctuation value with a preset threshold; if the fluctuation value is greater than the preset threshold, perform smoothing processing on the user posture data to obtain target posture data, and the target posture data is used to generate the target control scheme.

[0089] Among them, the preset threshold can be set according to requirements.

[0090] In specific implementation, when generating a target control scheme, the server can first determine the variance or standard deviation of the user posture data, and determine this variance or standard deviation as the fluctuation value of the user posture data. Then, the server compares this fluctuation value with a preset threshold. If the fluctuation value is greater than the preset threshold, it indicates that the user's movement stability is poor during the action. At this time, the server can perform smoothing processing on the user posture data through smoothing algorithms such as moving average or Kalman filter to obtain the target posture data, thereby achieving noise reduction of the user posture data and improving the accuracy and stability of the data. The target control scheme generated by the server based on this target posture data can ensure the movement stability of the target humanoid robot during training. If the fluctuation value is less than or equal to the preset threshold, it indicates that the user's movement stability meets the standard during the action. At this time, the server can directly generate a target control scheme based on this user posture data.

[0091] It can be seen that in this example, before generating the target control scheme, the server first determines the fluctuation value of the user posture data, and determines the stability of the user posture data by comparing the fluctuation value with the preset threshold. When the stability of the user posture data is poor, smoothing processing is performed on it, which can improve the movement stability of the target humanoid robot controlled by the generated target control scheme and optimize the training effect.

[0092] In a possible example, the training score is generated by the server according to the following steps: obtaining the training data uploaded by the target humanoid robot, where the training data includes training time, preset training times, and training success rate; determining a training score based on the training data.

[0093] Among them, the training data is the data content generated during the training process of the target humanoid robot according to the target control scheme. The training data includes training time, preset training times, and training success rate. Among them, the training time is used to represent the total time for the target humanoid robot to complete the target task. The preset training times are used to represent the number of times the target humanoid robot is preset to execute the target task. The training success rate is used to represent the ratio of the total number of times the target humanoid robot completes the target task to the preset training times when executing the target task.

[0094] In specific implementation, a scoring rule can be pre-stored in the server, and this scoring rule is used to configure weights for the training time, preset training times, and training success rate. Specifically, after the training of the target humanoid robot is completed, the training data will be uploaded to the server. After the server obtains this training data, it can convert the training time into a first value according to the first preset conversion rule, convert the preset training times into a second value according to the second preset conversion rule, and convert the training success rate into a third value according to the third preset conversion rule. Then, according to the scoring rule, the weighted sum of the first value, the second value, and the third value is determined as the training score. Exemplarily, seeFigure 6 The first display control 610 in the training result interface 60 is used to display the training score.

[0095] Specifically, the first preset rule is as follows: for the target task, multiple consecutive time ranges are divided, and each time range corresponds to a value. The time range corresponding to the determined training time will be determined, and thus the value corresponding to the time range will be determined as the first value. The second preset conversion rule and the third preset conversion rule can be set in the same way, and will not be elaborated further here.

[0096] It can be seen that in this example, the server determines the training score by comprehensively considering the training time, the preset number of training times, and the training success rate of the target humanoid robot, which can ensure the intelligence and reliability of the determined training score.

[0097] In a possible example, the training result interface is also used to display the score result of the integral, and the integral is used to exchange items according to the preset integral rule; the score result of the integral is determined by the server according to the following steps: obtaining the preset basic score for a single training; determining the training score according to the training rating and the preset rating score rule; summing the basic score and the training score to obtain the score result.

[0098] Among them, the integral is a kind of reward representation in the application provided by the embodied task configuration system. It is used to exchange coupons or goods (such as humanoid robots and their accessories, etc.) and other items in this application.

[0099] In specific implementation, after the server determines the training rating, it can further calculate the training score corresponding to the training rating according to the preset rating score rule, and then sum the training score and the preset basic score to obtain the score result of the integral. Exemplarily, the preset rating score rule can be: 0 points for a training rating lower than 80, 1 point for a training rating between 80 and 90, 2 points for a training rating between 90 and 95, and 3 points for a training rating between 95 and 100. Exemplarily, refer to Figure 6 The second display control 620 in the training result interface 60 is used to display the score result of the integral corresponding to the current training, and the third display control 630 is used to display the total integral of the user. By performing a selection operation on the third display control 630, the user can jump to the integral details interface, which is used to display contents such as the historical integral situation and the historical usage situation of the integral.

[0100] In specific implementation, refer to Figure 6 The training result interface 60 may also include a historical training control to query the records and ratings of the user's historical training by triggering the historical training control.

[0101] It can be seen that in this example, by configuring the integral redemption function for the applications provided by the embodied task configuration system, the intelligence of the applications provided by the embodied task configuration system can be improved. Determining the score result according to the preset basic score and training score can improve the flexibility and intelligence of the server in data processing, which is beneficial to stimulating the user's enthusiasm for use and enhancing the seriousness of the user in training the humanoid robot.

[0102] In a possible example, after receiving the training result message from the server and displaying the training result interface, the method further includes: sending a machine query request to the server in response to a third operation by the user on the user device, where the machine query request is used to query a recommended humanoid robot suitable for the user; receiving a query reply message from the server and displaying a product recommendation interface, where the product recommendation interface is used to display the device information of the recommended humanoid robot, and the recommended humanoid robot is determined by the server according to the following steps: obtaining the historical data of the user for the target task, where the historical data includes all the training data of the user selecting different humanoid robots to perform the target task; determining the adaptation values corresponding to all the humanoid robots for performing the target task according to the historical data; comparing all the adaptation values and determining the humanoid robot corresponding to the largest adaptation value as the recommended humanoid robot.

[0103] Among them, the third operation refers to the selection operation performed by the user on the control for initiating the machine query request in the interface displayed on the user device. Exemplarily, see Figure 6 , when the user performs a selection operation on the fourth display control 640 in the training result interface 60, the user device sends a machine query request to the server. This machine query request is used to query a recommended humanoid robot suitable for the user. The recommended humanoid robot refers to the humanoid robot with the highest adaptability to the user among all the humanoid robots used by the user for training.

[0104] In a specific implementation, after receiving a machine query request, the server first determines the target task corresponding to the current training, and then fetches the historical data corresponding to the target task. Thus, based on the historical data, all the humanoid robots used by the user during the training for the target task and all the training data corresponding to each humanoid robot are determined. Then, the adaptation value corresponding to each humanoid robot is confirmed according to the historical data. The adaptation value can be the average of the training scores corresponding to all the training data of each humanoid robot. Then, the server can compare the adaptation values corresponding to all the humanoid robots and determine the humanoid robot with the largest adaptation value as the recommended humanoid robot. After determining the recommended humanoid robot, the server can generate a query reply message and send the query reply message to the user device. The user device can display a product recommendation interface according to the query reply message to show the device information of the recommended humanoid robot to the user.

[0105] Specifically, the product recommendation interface can be a device introduction interface, which is only used to display the device information of the recommended humanoid robot. Or, the product recommendation interface can be a Figure 7 product purchase interface as shown. The product displayed on the product purchase interface is the recommended humanoid robot, and the device information is the content shown in the detailed information on the product purchase interface.

[0106] It can be seen that in this example, the user device sends a machine query request to the server by responding to the third operation performed by the user on the user device, and receives a query reply message from the server to display a product recommendation interface, which is beneficial to enriching the functionality of the application provided by the embodied task configuration system and providing a fast purchase path for the user to recommend a humanoid robot. At the same time, by determining the humanoid robot with the largest adaptation value among multiple humanoid robots corresponding to the target task as the recommended humanoid robot, the server is beneficial to the intelligence and accuracy of data processing and ensures the reliability of the adaptation between the user and the recommended humanoid robot.

[0107] The composition structure of the electronic device 80 in this application can be as Figure 8 shown. The electronic device 80 is a computing device, and the computing device is a computer or a server, etc., which can be used to execute the above method. Specifically, the electronic device 80 may include a processor 810, a memory 820, a communication interface 830, and one or more programs 821. Among them, the one or more programs 821 are stored in the above memory 820 and are configured to be executed by the above processor 810. The one or more programs 821 include instructions for executing any step in the above method embodiment.

[0108] Among them, the communication interface 830 is used to support the communication between the electronic device 80 and other devices. The processor 810 can be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, units, and circuits described in connection with the disclosed content of the embodiments of the present application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on.

[0109] The memory 820 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synch link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).

[0110] In a specific implementation, the processor 810 is used to execute any step in the above method embodiments, and when performing data transmission such as sending, it can optionally call the communication interface 830 to complete the corresponding operation.

[0111] It should be noted that the schematic structural diagram of the above electronic device 80 is only an example, and the specific devices included may be more or less, and there is no unique limitation here.

[0112] The present application can divide the functional units of the electronic device according to the above method examples. For example, each functional unit can be divided corresponding to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0113] Figure 9 It is a block diagram of the functional units of a first embodied task configuration device based on user demonstration data provided by an embodiment of the present application. The first embodied task configuration device 90 based on user demonstration data includes:

[0114] A first response unit 910, configured to send a busy / idle query request to the server in response to a first operation by the user on the user device;

[0115] A first receiving unit 920, configured to receive a busy / idle query reply message from the server and display a task configuration interface, where the task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls, the task selection controls are used to display corresponding task contents, and the humanoid robot selection controls are used to display the busy / idle status of corresponding humanoid robots;

[0116] A second response unit 930, configured to send a task configuration message to the server in response to a second operation by the user on the user device, where the task configuration message carries a target humanoid robot and a target task, the target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls;

[0117] A second receiving unit 940, configured to receive a training result message from the server and display a training result interface, where the training result interface is used to display the training score of the target humanoid robot executing a target control scheme, the target control scheme is content generated by the server according to user demonstration data, the user demonstration data is content uploaded by the virtual reality device to the server, and the user demonstration data is used to represent the actions performed by the user for the target task.

[0118] In a possible example, the task selection control includes a first task control and a second task control. The task content corresponding to the first task control is a task performed on the upper body of the humanoid robot, and the task content corresponding to the second task control is a task performed on the whole body of the humanoid robot. When the target task is the task content corresponding to the first task control, the user demonstration data includes user posture data, which is operation data collected by the virtual reality device. When the target task is the task content corresponding to the second task control, the user demonstration data includes the user posture data and task video data, and the task video data is video content of the user's whole body activities collected by the virtual reality device.

[0119] In a possible example, the target control scheme is generated by the server according to the following steps: determining the task type of the target task, where the task type includes a first task type and a second task type. The first task type is the task type corresponding to the first task control, and the second task type is the task type corresponding to the second task control. If the task type of the target task is the first task type, determining the execution object according to the target task, and generating the target control scheme according to the execution object and the user posture data. The execution object includes the left hand, the right hand, or both hands. If the task type of the target task is the second task type, analyzing the task video data to determine the user action posture data, and generating the target control scheme according to the user action posture data and the user posture data.

[0120] In a possible example, before determining the task type of the target task, the generating step of the target control scheme further includes: determining the fluctuation value of the user posture data, where the fluctuation value is used to characterize the stability degree of the user posture data; comparing the fluctuation value with a preset threshold; if the fluctuation value is greater than the preset threshold, performing smoothing processing on the user posture data to obtain target posture data, and the target posture data is used to generate the target control scheme.

[0121] In a possible example, the training score is generated by the server according to the following steps: obtaining the training data uploaded by the target humanoid robot, where the training data includes training time, preset training times, and training success rate; determining the training score according to the training data.

[0122] In a possible example, the training result interface is further configured to display the scoring result of points, where the points are used to exchange items according to a preset point rule; the scoring result of the points is determined by the server according to the following steps: obtaining a preset basic score for a single training; determining a training score according to the training score and a preset scoring rule; and summing the basic score and the training score to obtain the scoring result.

[0123] In a possible example, the first embodiment task configuration device based on user demonstration data further includes a third response unit and a third receiving unit. After receiving a training result message from the server and displaying a training result interface, the third response unit is configured to send a machine query request to the server in response to a third operation by the user on the user device, where the machine query request is used to query a recommended humanoid robot suitable for the user; the third receiving unit is configured to receive a query reply message from the server and display a product recommendation interface, where the product recommendation interface is used to display device information of the recommended humanoid robot, and the recommended humanoid robot is determined by the server according to the following steps: obtaining historical data of the user for the target task, where the historical data includes all training data of the user selecting different humanoid robots to execute the target task; determining adaptation values corresponding to each humanoid robot for executing the target task according to the historical data; comparing all the adaptation values, and determining the humanoid robot corresponding to the maximum adaptation value as the recommended humanoid robot.

[0124] In the case of adopting integrated units, the functional unit composition block diagram of the second embodiment task configuration device based on user demonstration data provided in this application is as Figure 10 shown. In Figure 10 , the second embodiment task configuration device 100 based on user demonstration data includes: a processing module 1020 and a communication module 1010. The processing module 1020 is configured to control and manage the actions of the first embodiment task configuration device 90 based on user demonstration data. For example, the steps executed by the first response unit 910, the first receiving unit 920, the second response unit 930, and the second receiving unit 940, and / or is configured to execute other processes of the technologies described herein. The communication module 1010 is configured to support the interaction between the second embodiment task configuration device 100 based on user demonstration data and other devices. As Figure 10 shown, the second embodiment task configuration device 100 based on user demonstration data may further include a storage module 1030, and the storage module 1030 is configured to store program codes and data of the second embodiment task configuration device 100 based on user demonstration data.

[0125] Among them, the processing module 1020 can be a processor or a controller. For example, it can be a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosed content of the embodiments of the present application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The communication module 1010 can be a transceiver, an RF circuit, a communication interface, etc. The storage module 1030 can be a memory.

[0126] Among them, all relevant content of each scenario involved in the above method embodiments can be cited in the function descriptions of the corresponding functional modules, and will not be elaborated here. The above-mentioned first embodied task configuration device based on user demonstration data or the second embodied task configuration device based on user demonstration data can both execute the Figure 2 steps executed by the user equipment in the embodied task configuration method based on user demonstration data shown above.

[0127] The embodiments of the present application also provide a computer-readable storage medium. Among them, the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program enables the computer to execute some or all of the steps of any method described in the above method embodiments. The above computer includes a server.

[0128] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0129] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0130] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0131] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0133] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods in various embodiments of the present application. And the aforementioned memory includes: USB flash drive, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disc and other various media that can store program codes.

[0134] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory. The memory can include: flash drive, ROM, RAM, magnetic disk, or optical disc, etc.

[0135] The above has introduced the embodiments of the present application in detail. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. An embodied task configuration method based on user demonstration data, characterized in that A user device applied to an embodied task configuration system, the embodied task configuration system including a server, a humanoid robot, the user device, and a virtual reality device, the server being communicatively connected to the humanoid robot, the user device, and the virtual reality device respectively, the method comprising: Sending a busy / idle query request to the server in response to a first operation by the user on the user device; Receiving a busy / idle query reply message from the server and displaying a task configuration interface, the task configuration interface including a plurality of task selection controls and a plurality of humanoid robot selection controls, the task selection controls being used to display corresponding task contents, and the humanoid robot selection controls being used to display the busy / idle status of corresponding humanoid robots; Sending a task configuration message to the server in response to a second operation by the user on the user device, the task configuration message carrying a target humanoid robot and a target task, the target humanoid robot being one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task being one of the task contents corresponding to the plurality of task selection controls; Receiving a training result message from the server and displaying a training result interface, the training result interface being used to display the training score of the target humanoid robot executing a target control scheme, the target control scheme being content generated by the server according to user demonstration data, the user demonstration data being content uploaded by the virtual reality device to the server, and the user demonstration data being used to characterize the actions performed by the user for the target task.

2. The method according to claim 1, characterized in that, The task selection controls include a first task control and a second task control, the task content corresponding to the first task control being a task performed on the upper body of the humanoid robot, and the task content corresponding to the second task control being a task performed on the whole body of the humanoid robot; When the target task is the task content corresponding to the first task control, the user demonstration data includes user posture data, and the user posture data is operation data collected by the virtual reality device; When the target task is the task content corresponding to the second task control, the user demonstration data includes the user posture data and task video data, and the task video data is video content collected by the virtual reality device for the whole body activities of the user.

3. The method according to claim 2, wherein The target control scheme is generated by the server according to the following steps: Determining the task type of the target task, the task type including a first task type and a second task type, the first task type being the task type corresponding to the first task control, and the second task type being the task type corresponding to the second task control; If the task type of the target task is the first task type, determining an execution object according to the target task, and generating the target control scheme according to the execution object and the user posture data, the execution object including the left hand, the right hand, or both hands; If the task type of the target task is the second task type, analyze the task video data to determine the user action and pose data, and generate the target control solution according to the user action and pose data and the user posture data.

4. The method according to claim 3, wherein Before determining the task type of the target task, the generating step of the target control solution further includes: Determine the fluctuation value of the user posture data, where the fluctuation value is used to characterize the stability degree of the user posture data; Compare the fluctuation value with a preset threshold; If the fluctuation value is greater than the preset threshold, perform smoothing processing on the user posture data to obtain target posture data, where the target posture data is used to generate the target control solution.

5. The method according to claim 1, characterized in that, The training score is generated by the server according to the following steps: Obtain the training data uploaded by the target humanoid robot, where the training data includes training time, preset training times, and training success rate; Determine the training score according to the training data.

6. The method according to claim 5, characterized in that, The training result interface is further used to display the score result of the integral, where the integral is used to exchange items according to a preset integral rule; the score result of the integral is determined by the server according to the following steps: Obtain the preset basic score for a single training; Determine the training score according to the training score and the preset score rule; Sum the preset basic score and the training score to obtain the score result.

7. The method according to claim 5, characterized in that After receiving the training result message from the server and displaying the training result interface, the method further includes: Respond to a third operation by the user on the user device to send a machine query request to the server, where the machine query request is used to query the recommended humanoid robot suitable for the user; Receive a query reply message from the server and display a product recommendation interface, where the product recommendation interface is used to display the device information of the recommended humanoid robot, and the recommended humanoid robot is determined by the server according to the following steps: obtain the historical data of the user for the target task, where the historical data includes all the training data of the user selecting different humanoid robots to execute the target task; determine the adaptation value corresponding to each humanoid robot executing the target task according to the historical data; compare all the adaptation values, and determine the humanoid robot corresponding to the maximum adaptation value as the recommended humanoid robot.

8. An embodied task configuration device based on user demonstration data, characterized in that, Applied to a user device of an embodied task configuration system, the embodied task configuration system includes a server, a humanoid robot, the user device, and a virtual reality device, and the server is communicatively connected to the humanoid robot, the user device, and the virtual reality device respectively. The embodied task configuration device based on user demonstration data includes: A first response unit, configured to send a busy / idle query request to the server in response to a first operation by the user on the user device; A first receiving unit, configured to receive a busy / idle query reply message from the server and display a task configuration interface, where the task configuration interface includes a plurality of task selection controls and a plurality of humanoid robot selection controls, the task selection controls are configured to display corresponding task contents, and the humanoid robot selection controls are configured to display the busy / idle status of corresponding humanoid robots; A second response unit, configured to send a task configuration message to the server in response to a second operation performed by a user on the user device, where the task configuration message carries a target humanoid robot and a target task, the target humanoid robot is one of the humanoid robots corresponding to the plurality of humanoid robot selection controls, and the target task is one of the task contents corresponding to the plurality of task selection controls; A second receiving unit, configured to receive a training result message from the server and display a training result interface, where the training result interface is configured to display a training score of the target humanoid robot executing a target control scheme, the target control scheme is content generated by the server according to user demonstration data, the user demonstration data is content uploaded by the virtual reality device to the server, and the user demonstration data is used to characterize actions performed by the user for the target task.

9. An electronic device, characterized in that, It includes a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing the steps in the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program for electronic data exchange is stored, where the computer program causes a computer to execute the steps in the method according to any one of claims 1-7.

Images