Virtual agent body operation processing method and device and electronic equipment

Abstract

The invention provides a body operation processing method and device for a virtual agent and electronic equipment, and the method comprises the steps: guiding a user to control the body of the virtual agent under the condition that the virtual agent cannot execute an operation task corresponding to a preset virtual environment; and under the condition that the user controls the tool body, based on an action sequence formed by the user according to the operation task, controlling the tool body to perform task operation according to the action sequence so as to enable the tool body to complete the operation task. The virtual agent can effectively complete the operation task, and the capability of processing the operation task of the virtual agent is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device and electronic equipment for processing embodied operations of a virtual intelligent body. Background Art

[0002] There are many types of current virtual reality training systems, the most common of which are systems that train real-life operating skills, such as VR assembly technology training, VR medical technology training, etc. In order for a virtual agent (also known as a virtual person) to have a certain skill, it needs to be trained on data to reach a certain skill level, which is usually driven by an AI model.

[0003] For embodied operation tasks of virtual intelligent bodies, data sets are often required for training. However, embodied operation tasks are complex and diverse, which will lead to the fact that there are not enough data sets in reality to meet the training needs of embodied operation tasks, resulting in the inability of the body to effectively complete the operation tasks in certain scenarios.

[0004] Therefore, finding a method that can guide the embodied operation of virtual intelligent bodies to effectively complete operational tasks has become a research hotspot. Summary of the invention

[0005] The present invention provides a method, device and electronic device for processing embodied operation of a virtual intelligent body, which enables the embodiment of the virtual intelligent body to effectively complete operation tasks and improves the ability of the virtual intelligent body to process operation tasks.

[0006] The present invention provides a method for processing embodied operations of a virtual intelligent body, the method comprising: when the virtual intelligent body is unable to perform an operation task corresponding to a preset virtual environment, guiding a user to control the embodiment of the virtual intelligent body; when the user controls the embodiment, based on an action sequence formed by the user according to the operation task, controlling the embodiment to perform task operations according to the action sequence, so that the embodiment completes the operation task.

[0007] According to a method for processing embodied operation of a virtual intelligent body provided by the present invention, guiding a user to control the embodiment of the virtual intelligent body is achieved in the following manner: guiding the user to wear a wearable device interconnected with the preset virtual environment; when the user wears the wearable device, the embodiment of the virtual intelligent body is controlled by the user based on a selector.

[0008] According to a method for processing embodied operations of a virtual intelligent body provided by the present invention, after controlling the body to perform task operations according to the action sequence so that the body completes the operation task, the method also includes: instructing the user to no longer control the body of the virtual intelligent body, and storing the operation task and the action sequence; based on the operation task and the action sequence, re-updating and training the network model corresponding to the virtual intelligent body to obtain an updated network model; using the updated network model as the network model corresponding to the virtual intelligent body, so that when the virtual intelligent body faces the operation task again, it can complete the operation task based on the action sequence executed by the body.

[0009] According to a method for processing embodied operation of a virtual intelligent body provided by the present invention, guiding the user to no longer control the embodiment of the virtual intelligent body is achieved in the following manner: when the user is wearing a wearable device, guiding the user to adjust the selector so that the embodiment of the virtual intelligent body controlled based on the adjusted selector is no longer controlled by the user.

[0010] According to a method for processing embodied operations of a virtual intelligent body provided by the present invention, before the virtual intelligent body is unable to execute the operation task corresponding to the preset virtual environment, the method also includes: regularly checking the execution status of the virtual intelligent body executing the operation task at preset time intervals.

[0011] According to a method for processing embodied operations of a virtual agent provided by the present invention, the number of the users is one or more, and the number of the virtual agents is one or more.

[0012] The present invention also provides a device for processing embodied operations of a virtual intelligent body, the device comprising: a guidance module for guiding a user to control the embodiment of the virtual intelligent body when the virtual intelligent body is unable to perform an operation task corresponding to a preset virtual environment; a control module for controlling the embodiment to perform task operations according to an action sequence formed by the user according to the operation task when the user controls the embodiment, so that the embodiment completes the operation task.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the processor implements the embodied operation processing method of a virtual intelligent body as described in any one of the above.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the embodied operation processing method of the virtual intelligent body as described in any one of the above.

[0015] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the embodied operation processing method of a virtual intelligent body as described in any one of the above.

[0016] The embodiment operation processing method, device and electronic device of the virtual intelligent body provided by the present invention guide the user to control the embodiment of the virtual intelligent body when the virtual intelligent body cannot perform the operation task corresponding to the preset virtual environment; when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task. Thus, the embodiment of the virtual intelligent body can effectively complete the operation task, and the ability of the virtual intelligent body to process the operation task is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the embodiment operation processing method of the virtual intelligent body provided by the present invention;

[0019] Figure 2 It is a schematic diagram of a flow chart for guiding a user to control a virtual intelligent body provided by the present invention;

[0020] Figure 3 This is the second flow chart of the embodiment operation processing method of the virtual intelligent body provided by the present invention;

[0021] Figure 4 It is a structural schematic diagram of the embodiment operation processing device of the virtual intelligent body provided by the present invention;

[0022] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The embodied operation processing method of the virtual intelligent body provided by the present invention is based on the fact that the wearable device can obtain the detailed operations of the human user in real time. After the user obtains the control of the virtual person, the user directly operates the limb movement of the virtual person. The formed limb information is used as the guidance trajectory to train the original model, and the control of the virtual person is returned to the virtual person, thus forming a circular interaction, thereby realizing a learning mode of real-time human guidance and viewing of the guidance effect.

[0025] During the application process, users can observe and analyze the real-time state of the environment, propose the best operation method suitable for the virtual human to complete a given task, and give a demonstration.

[0026] Figure 1 It is one of the flow charts of the embodied operation processing method of the virtual intelligent body provided by the present invention.

[0027] The following will be combined Figure 1 The process of the embodied operation processing method of the virtual intelligent body provided by the present invention is explained.

[0028] In an exemplary embodiment of the present invention, Figure 1 It can be seen that the embodied operation processing method of the virtual intelligent body can include step 110 and step 120, and each step will be introduced below.

[0029] In step 110, when the virtual agent is unable to perform the operation task corresponding to the preset virtual environment, the user is guided to control the embodiment of the virtual agent.

[0030] In step 120, when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

[0031] It should be noted that the virtual agent can be implemented based on a network model. In other words, the essence of the virtual agent is a network model. In the application process, the virtual agent can drive the execution behavior based on the network model. In one example, the network model corresponding to the virtual agent can be a neural network trained offline or a rule-based behavior decision tree.

[0032] In one embodiment, when the virtual agent is unable to perform an operation task corresponding to a preset virtual environment, that is, in the virtual world, there is an operation task corresponding to the preset virtual environment that needs to be completed by the virtual agent, and when the virtual agent is unable to perform the operation task, the user can be guided to control the embodiment of the virtual agent. During the application process, the user can observe the embodiment operation of the virtual agent as a supervisor. Therefore, when the virtual agent is unable to perform the operation task, the user can discover it in the first place and control the embodiment of the virtual agent.

[0033] In another embodiment, after the user controls the embodiment of the virtual intelligent body, the embodiment can be controlled to perform task operations according to the action sequence formed by the user according to the operation task, so that the embodiment completes the operation task.

[0034] It should be noted that the action sequence formed according to the operation task is an action sequence that can complete the operation task.

[0035] In another embodiment, when the virtual agent encounters poor performance or a problem that cannot be solved when performing a task, the user takes over the embodiment of the virtual agent and generates guidance information (corresponding to an action sequence) based on the information of the current environment (corresponding to a preset virtual environment), such as directly controlling the virtual human body to perform demonstration actions. This enables the embodiment of the virtual agent to effectively complete the operation task, and improves the ability of the virtual agent to handle the operation task.

[0036] It should be noted that, in this embodiment, the action sequence is an instant guidance plan obtained by the user in combination with the preset virtual environment information, which can improve the effectiveness of the action sequence in solving operational tasks, lay the foundation for realizing the embodiment of the virtual intelligent body to effectively complete operational tasks, and improve the virtual intelligent body's ability to handle operational tasks.

[0037] The embodiment operation processing method of the virtual intelligent body provided by the present invention guides the user to control the embodiment of the virtual intelligent body when the virtual intelligent body cannot perform the operation task corresponding to the preset virtual environment; when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task. Thus, the embodiment of the virtual intelligent body can effectively complete the operation task, and the ability of the virtual intelligent body to process the operation task is improved.

[0038] In order to further introduce the embodiment operation processing method of the virtual intelligent body provided by the present invention, the following will be combined with Figure 2 Provide explanation.

[0039] Figure 2 This is a schematic diagram of the embodiment of the process of guiding the user to control the virtual intelligent body provided by the present invention.

[0040] In an exemplary embodiment of the present invention, Figure 2 It can be seen that guiding the user to control the embodiment of the virtual intelligent body may include step 210 and step 220, and each step will be introduced below.

[0041] In step 210, the user is instructed to wear a wearable device interconnected with a preset virtual environment;

[0042] In step 220, when the user wears the wearable device, the embodiment of the virtual agent is controlled by the user based on the gate control.

[0043] In one embodiment, since the wearable device is interconnected with the preset virtual environment, the user wearing the wearable device, such as a full-body motion capture system based on optical markers, a data glove system, etc., can enter a VR environment (corresponding to the preset virtual environment).

[0044] Furthermore, when the user wears a wearable device, the embodiment of the virtual intelligent body can be controlled by the user based on the gate control. Through this embodiment, the user can conveniently and frequently guide the behavior of the virtual intelligent body, and solve the problem of the embodiment operation of the virtual intelligent body in an immersive way in the form of a first-person perspective, thereby laying a foundation for realizing that the embodiment of the virtual intelligent body can effectively complete the operation task and improving the ability of the virtual intelligent body to handle the operation task.

[0045] In order to further introduce the embodiment operation processing method of the virtual intelligent body provided by the present invention, the following will be combined with Figure 3 Provide explanation.

[0046] Figure 3 This is the second flow chart of the embodied operation processing method of the virtual intelligent body provided by the present invention.

[0047] In an exemplary embodiment of the present invention, Figure 3 It can be seen that the embodied operation processing method of the virtual intelligent body may include steps 310 to 350, wherein steps 310 to 320 are respectively the same or similar to steps 110 to 120. For its specific implementation methods and beneficial effects, please refer to the previous description, which will not be repeated in this embodiment. Steps 330 to 350 will be introduced respectively below.

[0048] In step 330, the user is instructed to no longer control the embodiment of the virtual agent, and the operation task and action sequence are stored.

[0049] In step 340, based on the operation task and the action sequence, the network model corresponding to the virtual agent is retrained to obtain an updated network model.

[0050] In step 350, the updated network model is used as the network model corresponding to the virtual agent, so that when the virtual agent is faced with the operation task again, it can complete the operation task based on the action sequence performed in the embodiment.

[0051] In one embodiment, after controlling the body to perform a task according to an action sequence so that the body completes the operation task, the user can return the body control of the virtual intelligent body, and the virtual intelligent body uses the data about the action sequence generated by the user to update the network model and put it into a new round of use.

[0052] In another embodiment, the user can be instructed not to control the embodiment of the virtual agent, and the operation tasks and action sequences can be stored. Furthermore, based on the operation tasks and action sequences, the network model corresponding to the virtual agent is retrained to obtain an updated network model.

[0053] In another embodiment, the updated network model can be used as a network model corresponding to the virtual agent. In other words, in this scenario, the updated network model is actually the virtual agent. Since the virtual agent in the current scenario stores data about the operation task and the corresponding action sequence, the aforementioned data becomes the training data about the updated network model. Since the training data comes from the user's personal teaching data, this data is initiated by the user in real time, so it can take into account the latest information status of the environment in a timely manner and generate the most effective operation strategy, thereby ensuring that when the virtual agent faces the operation task again, it can complete the operation task based on the action sequence performed in person.

[0054] It is understandable that for the training data of the virtual intelligent body's operating tasks, due to the complexity of the types of tasks, it is obviously not feasible to construct a data set for each task. Through this embodiment, human users can generate corresponding operating data (which can correspond to an action sequence) according to the scene (which can correspond to a preset virtual environment) in real time, and use it for virtual intelligent body skill training, which will greatly alleviate the difficulties caused by the lack of training data.

[0055] In this embodiment, VR technology is used to construct various operation task environments. Users enter the virtual space through wearable devices, demonstrate the process of completing tasks for the virtual agent, and record corresponding data to form targeted task training. In addition, in this embodiment, the control right takeover method is adopted to allow users to teach the current task of the virtual agent from a first-person perspective, which can improve the accuracy of the teaching effect.

[0056] In another exemplary embodiment of the present invention, instructing the user to no longer control the embodiment of the virtual agent can be implemented in the following manner:

[0057] When the user wears the wearable device, the user is guided to adjust the selector so that the embodiment of the virtual intelligent body controlled based on the adjusted selector is no longer controlled by the user.

[0058] In one embodiment, a human wearing a wearable device, such as a full-body motion capture system based on optical markers, a data glove system, etc., can enter a VR environment. Among them, whether to control the embodiment of the virtual intelligent body is determined by a gate, wherein the state of the gate is controlled by the user. During the application process, when the user wears a wearable device, the user can be guided to adjust the gate so that the embodiment of the virtual intelligent body controlled by the gate after adjustment is no longer controlled by the user. Through this embodiment, it is possible to effectively return the control of the embodiment of the virtual intelligent body to the virtual intelligent body itself.

[0059] In order to further introduce the embodied operation processing method of the virtual intelligent body provided by the present invention, it will be described in conjunction with the following embodiments.

[0060] In another exemplary embodiment of the present invention, continuing with the above Figure 1 The embodiment is described as an example. Before the virtual agent is unable to perform the operation task corresponding to the preset virtual environment (corresponding to step 110), the method further includes:

[0061] At preset intervals, regularly check the execution status of the virtual agent's operational tasks.

[0062] In one embodiment, in order to ensure the effectiveness of the virtual agent in performing the operation task, the user can be guided as a supervisor to observe the behavior of the virtual agent in performing the operation task, and the user can regularly check the execution status of the virtual agent in performing the operation task, so as to timely obtain the situation where the agent cannot perform the operation task corresponding to the preset virtual environment. This lays the foundation for the subsequent timely guidance of the user to control the embodiment of the virtual agent, and when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so as to enable the embodiment to complete the operation task.

[0063] In another exemplary embodiment of the present invention, the number of the users mentioned above may be one or more, and the number of the virtual agents mentioned above may be one or more.

[0064] In one embodiment, the execution of operational tasks of the same virtual agent can be supervised based on different users, and when it is found that the virtual agent is unable to perform the operational tasks corresponding to the preset virtual environment, any one or more users can be guided to control the embodiment of the virtual agent, and when the user controls the embodiment, based on the action sequence formed by the user according to the operational task, the embodiment is controlled to perform the task according to the action sequence, so that the embodiment completes the operational task.

[0065] In another embodiment, the execution of the operation tasks of different virtual agents can be supervised accordingly based on different users. In other words, one user supervises the execution of the operation tasks of one virtual agent. If it is found that the virtual agent cannot perform the operation task corresponding to the preset virtual environment, the corresponding user can be guided to control the embodiment of the corresponding virtual agent, and if the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

[0066] In another embodiment, multiple virtual agents may exist in the same virtual environment, wherein multiple virtual agents may collaborate or compete on tasks. In the process of collaborating or competing on tasks, multiple virtual agents may learn action sequences for performing operation tasks, thereby laying a foundation for enriching the training data of the network model corresponding to the virtual agents. In other words, the ability of each virtual agent to complete the operation task may be improved by collaborating or competing on tasks between multiple virtual agents.

[0067] According to the above description, the embodiment operation processing method of the virtual intelligent body provided by the present invention guides the user to control the embodiment of the virtual intelligent body when the virtual intelligent body cannot perform the operation task corresponding to the preset virtual environment; when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task. Thereby, the embodiment of the virtual intelligent body can effectively complete the operation task, and the ability of the virtual intelligent body to process the operation task is improved.

[0068] Based on the same concept, the present invention also provides an embodied operation processing device for a virtual intelligent body.

[0069] The embodied operation processing device of the virtual intelligent body provided by the present invention is described below. The embodied operation processing device of the virtual intelligent body described below and the embodied operation processing method of the virtual intelligent body described above can be referenced to each other.

[0070] Figure 4 It is a structural schematic diagram of the embodied operation processing device of the virtual intelligent body provided by the present invention.

[0071] In an exemplary embodiment of the present invention, Figure 4 It can be seen that the embodied operation processing device of the virtual intelligent body can include a guidance module 410 and a control module 420, and each module will be introduced below.

[0072] The guidance module 410 may be configured to guide the user to control the embodiment of the virtual agent when the virtual agent is unable to perform the operation task corresponding to the preset virtual environment;

[0073] The control module 420 may be configured to control the embodiment to perform the task operation according to the action sequence formed by the user according to the operation task when the embodiment is controlled by the user, so that the embodiment completes the operation task.

[0074] In an exemplary embodiment of the present invention, the guidance module 410 can guide the user to control the embodiment of the virtual agent in the following manner:

[0075] Instruct users to wear wearable devices that are connected to a preset virtual environment;

[0076] When the user wears the wearable device, the embodiment of the virtual agent is controlled by the user based on the gate control.

[0077] In an exemplary embodiment of the present invention, the control module 420 may also be configured to:

[0078] Instruct the user to no longer control the embodiment of the virtual agent and store the operation tasks and action sequences;

[0079] Based on the operation tasks and action sequences, the network model corresponding to the virtual agent is retrained to obtain an updated network model;

[0080] The updated network model is used as the network model corresponding to the virtual agent, so that when the virtual agent faces the operation task again, it can complete the operation task based on the action sequence performed by the embodiment.

[0081] In an exemplary embodiment of the present invention, the control module 420 may guide the user to stop controlling the embodiment of the virtual agent in the following manner:

[0082] When the user wears the wearable device, the user is guided to adjust the selector so that the embodiment of the virtual intelligent body controlled based on the adjusted selector is no longer controlled by the user.

[0083] In an exemplary embodiment of the present invention, the guidance module 410 may also be configured to:

[0084] At preset intervals, regularly check the execution status of the virtual agent's operational tasks.

[0085] In an exemplary embodiment of the present invention, the number of users may be one or more, and the number of virtual agents may be one or more.

[0086] Figure 5An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the embodiment operation processing method of the virtual intelligent body, the method comprising: in the case where the virtual intelligent body cannot perform the operation task corresponding to the preset virtual environment, guiding the user to control the embodiment of the virtual intelligent body; in the case where the user controls the embodiment, based on the action sequence formed by the user according to the operation task, controlling the embodiment to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

[0087] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0088] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the embodied operation processing method of the virtual intelligent body provided by the above-mentioned methods. The method includes: when the virtual intelligent body is unable to perform the operation task corresponding to the preset virtual environment, guiding the user to control the embodiment of the virtual intelligent body; when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, controlling the embodiment to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

[0089] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the embodied operation processing method of the virtual intelligent body provided by the above-mentioned methods. The method includes: when the virtual intelligent body is unable to perform the operation task corresponding to the preset virtual environment, guiding the user to control the embodiment of the virtual intelligent body; when the user controls the embodiment, based on the action sequence formed by the user according to the operation task, controlling the embodiment to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

[0090] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0092] It is further understood that, although the operations are described in a specific order in the accompanying drawings in the embodiments of the present invention, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing embodied operations of a virtual agent, characterized in that: The method comprises: In the case where the virtual agent is unable to perform an operation task corresponding to a preset virtual environment, guiding the user to control the embodiment of the virtual agent; When the user controls the embodiment, based on the action sequence formed by the user according to the operation task, the embodiment is controlled to perform the task operation according to the action sequence, so that the embodiment completes the operation task.

2. The method for processing embodied operation of a virtual agent according to claim 1, characterized in that: Guiding the user to control the embodiment of the virtual agent is achieved in the following manner: Instructing the user to wear a wearable device interconnected with the preset virtual environment; When the user wears the wearable device, the embodiment of the virtual agent is controlled by the user based on the gate control.

3. The method for processing embodied operation of a virtual agent according to claim 1 or 2, characterized in that: After controlling the embodiment to perform the task operation according to the action sequence so that the embodiment completes the operation task, the method further includes: Instructing the user to stop controlling the embodiment of the virtual agent, and storing the operation task and the action sequence; Based on the operation task and the action sequence, re-update and train the network model corresponding to the virtual agent to obtain an updated network model; The updated network model is used as the network model corresponding to the virtual agent, so that when the virtual agent faces the operation task again, it can complete the operation task based on the action sequence performed by the embodiment.

4. The method for processing embodied operation of a virtual agent according to claim 3, characterized in that: Instructing the user to no longer control the embodiment of the virtual agent is achieved by: When the user wears the wearable device, the user is guided to adjust the selector so that the embodiment of the virtual agent controlled based on the adjusted selector is no longer controlled by the user.

5. The method for processing embodied operation of a virtual agent according to claim 1, characterized in that: Before the virtual agent is unable to perform the operation task corresponding to the preset virtual environment, the method further includes: At preset intervals, regularly check the execution status of the virtual agent in performing the operation task.

6. The method for processing embodied operation of a virtual agent according to claim 1, characterized in that: The number of the users is one or more, and the number of the virtual agents is one or more.

7. A virtual intelligent body embodied operation processing device, characterized in that: The device comprises: A guidance module, used to guide the user to control the embodiment of the virtual intelligent body when the virtual intelligent body cannot perform the operation task corresponding to the preset virtual environment; The control module is used to control the embodiment to perform the task operation according to the action sequence formed by the user according to the operation task when the user controls the embodiment, so that the embodiment completes the operation task.

8. The embodied operation processing device of a virtual intelligent body according to claim 7, characterized in that: The guidance module guides the user to control the embodiment of the virtual agent in the following manner: Instructing the user to wear a wearable device interconnected with the preset virtual environment; When the user wears the wearable device, the embodiment of the virtual agent is controlled by the user based on the gate control.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the embodied operation processing method of the virtual intelligent body as described in any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the embodied operation processing method of the virtual intelligent body as described in any one of claims 1 to 6.

Images