Virtual robot remote interaction method and system based on digital avatar

Abstract

The invention relates to a remote interaction method and system for a virtual robot based on a digital avatar, and the method comprises the steps: constructing a partial virtualization data set, and enabling the partial virtualization data set to meet a construction condition; and constructing virtualization data by using each part of virtualization data in the part of virtualization data group meeting the construction condition, acting the constructed virtualization data on a virtual robot model, and performing interaction and / or display by using the virtualization data by a virtual robot. According to the method, support is provided for quick response of the virtual robot based on the digital avatar through behavior data splitting and three-level storage resource management, and the method is suitable for quick response during collaborative or parallel operation of multiple virtual robots in a large-scale virtual scene.

Description

[Technical field]

[0001] The present invention belongs to the technical field of digital avatars, and in particular to a virtual robot remote interaction method and system based on digital avatars. [Background technology]

[0002] Digital doppelgangers, also known as AI virtual digital robots or digital humans, are digital images that are highly similar to real people or completely fictional, created using advanced technologies such as artificial intelligence, machine learning, and computer graphics. This technology has developed rapidly in recent years and has become a hot topic in the field of science and technology. Digital human doppelgangers have various application scenarios, including real-time human-computer dialogue, short video production, digital human office, unmanned live broadcast, etc. With the continuous maturity of technology and the reduction of costs, it has become easier and more popular to create personal digital doppelgangers. Digital human doppelganger technology is developing at an unprecedented speed. It not only represents technological progress, but also opens up a new way for humans to interact with the digital world, bringing innovative possibilities to all walks of life.

[0003] Current computing systems often include a central processing unit (CPU) and a graphics processor unit (GPU), which may also be called a video processing unit (VPU). A GPU is a processor with a highly parallel structure and is generally used for graphics operations such as texture mapping and rendering polygons. Graphics commands are sent from the CPU to the GPU (via a GPU driver) and executed on the GPU. Computer virtualization is a technology that involves encapsulating a physical computing machine platform into a virtual machine that executes under the control of virtualization software on a hardware computing platform or "host". The virtual machine has both virtual system hardware and client operating system software.

[0004] With the rapid development of industrial automation and the widespread application of artificial intelligence technology, virtual robots based on digital avatars are developing in the direction of increasing quantity and parallelism, which is also one of the main development directions at present. This has brought huge pressure to various types of computing power, communication bandwidth, storage capacity, etc. of computing systems. How to make these limited resources support the increase in quantity and parallelism is a technical problem to be solved. Based on the above problems, the present invention provides support for the rapid response of virtual robots based on digital avatars through behavior data splitting and three-level storage resource management, which is suitable for rapid response when multiple virtual robots are running collaboratively or in parallel in large-scale virtualization scenarios. [Summary of the invention]

[0005] In order to solve the above problems in the prior art, the present invention proposes a virtual robot remote interaction method and system based on a digital avatar, the method comprising:

[0006] Step S1: constructing a virtual robot model for a virtual robot including one or more virtual robot parts, wherein the virtual robot model includes one or more sub-models, each sub-model corresponding to a virtual robot part; behavior data for each virtual robot can be split into partial behavior data corresponding to each virtual robot part, and correspondingly, partial virtualization data about each partial behavior data corresponds to one or more sub-models;

[0007] Step S2: Each virtual robot asynchronously receives the behavior data sent by the real object, and determines whether there is virtualized data corresponding to the behavior data in the storage device. If yes, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, the virtualization device is waited to return the virtualized data for the behavior data, and the returned virtualized data is used for interaction and / or display;

[0008] The storage device includes a private storage space associated with each virtual robot, a shared storage space shared by one or more virtual robot robots, and an external storage space for storing historical behavior data and historical virtualized data; wherein: the private storage space is used to store each behavior data of each virtual robot and its corresponding virtualized data; and the shared storage space stores part of the behavior data and its corresponding part of the virtualized data;

[0009] The step S2 specifically includes the following steps:

[0010] Step S21: the virtual robot asynchronously receives the behavior data collected from the real object; determines whether the virtualized data vd corresponding to the behavior data exists in the private storage space corresponding to the virtual robot; if so, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, proceeds to the next step;

[0011] The virtualized data vd as a whole can be split into partial virtualized data corresponding to each virtual robot part; it is represented as vd = {vdp p}; where: vdp i is the pth part of virtualized data corresponding to the pth virtual robot part in the virtualized data; the behavior data is projected to each virtual robot part p to obtain partial behavior data dp; the association relationship between the partial virtualized data is determined based on the association relationship or constraint relationship between the partial behavior data, and the virtual relationship matrix Ra is set accordingly = [vdp p，q ], where vdp p，q is an association relationship or constraint relationship between any two virtualized data of the pth and qth parts;

[0012] Step S22: determine the virtual robot part p involved in the current behavior data; project the behavior data to each virtual robot part p to obtain the corresponding partial behavior data; determine the partial virtualization data vdp corresponding to the partial behavior data dp p Whether it exists in the shared storage space, if all the partial behavior data corresponds to the partial virtualization data vdp p All of them are located in the shared storage space, and a partial virtualization data is selected from the partial virtualization data corresponding to each partial behavior data to construct the partial virtualization data group, so that the partial virtualization data group meets the construction condition; the virtualization data is constructed using each partial virtualization data in the partial virtualization data group that meets the construction condition, and the constructed virtualization data is applied to the virtual robot model, and the virtual robot uses the virtualization data for interaction and / or display; wherein: the construction condition is the virtual relationship matrix cRa of the virtualization data group = [cvdp ic，jc ] and the distance between the virtual relationship matrix corresponding to each part of the behavior data in the action data is the shortest; otherwise, proceed to the next step;

[0013] Step S23: sending the current behavior data to the virtualization device to virtualize the behavior data; waiting for the virtualization data returned by the virtualization device;

[0014] Step S3: The virtual robot manages the private storage space, and the storage device manages the shared storage space; the storage device is also used to manage the external storage space.

[0015] Furthermore, the virtualization device is a GPU device.

[0016] Furthermore, the one or more virtual robots are the same or similar.

[0017] Furthermore, the storage device is divided into multiple parts, and the shared storage space and the private storage space are located in different parts of the storage device.

[0018] Furthermore, the access efficiency of the private storage space and the shared storage space is higher than that of the external storage space.

[0019] Furthermore, virtual robots based on digital avatars act on assembly line devices, cluster operation devices, real-time monitoring devices, game systems or conference systems.

[0020] Furthermore, when the virtualized data returned by the virtualization device is loaded into the private storage space, the corresponding part of the virtualized data is also loaded into the shared storage space.

[0021] A virtual robot remote interaction system based on digital avatars, comprising: the system includes one or more virtual robots based on digital avatars, a virtualization device, a storage device and real objects corresponding to the one or more virtual robots; the virtual robot, as the digital avatar of the real object, interacts and displays based on virtualization data; and is used to implement the virtual robot remote interaction method based on digital avatars.

[0022] A virtual robot remote interaction platform based on a digital avatar comprises a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the virtual robot remote interaction method based on the digital avatar is implemented.

[0023] A computer-readable storage medium includes a program, which, when running on a computer, enables the computer to execute the virtual robot remote interaction method based on a digital avatar.

[0024] The beneficial effects of the present invention include:

[0025] (1) Setting up the splitting of virtual robot parts and the projection of behavior data, and setting up private storage space and shared storage space accordingly, fully discovering and utilizing the common behaviors of the behavior data of virtual robots and their corresponding partial virtualized data. When the virtualized data for the entire behavior data cannot be obtained quickly, the interaction and display of virtual robots can be quickly completed by sharing partial virtualized data. This is suitable for rapid response when multiple virtual robots are running in collaboration or parallel in large-scale virtualized scenarios.

[0026] (2) Constructing a correlation matrix to constrain some virtualized data, thereby improving the availability of virtualized data constructed by some virtualized data and reducing the fusion difference between virtualized data constructed by some virtualized data and virtualized data returned by the virtualization device;

[0027] (3) Setting up a three-level storage space ensures the privacy of each virtual robot’s data while improving the degree of data sharing. It discovers the common behaviors of all virtual robots and predicts and pre-fetches some behavior data and some virtualized data, which makes up for the moment when the computing power of the virtualization device is insufficient and improves the parallel support for virtual robots.

Brief Description of the Drawings

[0028] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0029] Figure 1 Schematic diagram of the virtual robot remote interaction method based on digital avatar provided by the present invention. [Specific implementation method]

[0030] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0031] The present invention proposes a virtual robot remote interaction method and system based on digital avatar, wherein: the system comprises: one or more virtual robots based on digital avatar, a virtualization device, a storage device and real objects corresponding to the one or more virtual robots; the virtual robot, as a digital avatar of the real object, interacts and displays based on virtualization data;

[0032] Preferably: the virtual robot acts in an assembly line device, a cluster operation device, a real-time monitoring device, a game system or a conference system, etc.;

[0033] The storage device includes a private storage space associated with each virtual robot, a shared storage space shared by one or more virtual robot robots, and an external storage space for storing historical behavior data and historical virtualized data; wherein: the private storage space is used to store each behavior data of each virtual robot and its corresponding virtualized data; and the shared storage space stores part of the behavior data and its corresponding part of the virtualized data;

[0034] Preferably: the shared storage space and the private storage space are located in different storage devices, and when the virtualized data is loaded into the private storage space, its corresponding part of the virtualized data is also loaded into the shared storage space;

[0035] Alternatively: the shared storage space and the private storage space are located in different parts of the storage device, the private storage space is used to store virtualized data, and the shared storage space is used to store indexes (addresses) of partial virtualized data, and when the virtualized data is loaded from the virtualization device into the private storage space, the indexes (addresses) of the various partial virtualized data in the private storage space are stored in the shared storage space;

[0036] Preferably: the access efficiency of the private storage space and the shared storage space is higher than that of the external storage space;

[0037] The virtual robot is virtualized based on the behavior data of the real object to obtain virtualized data, and the virtualized data is applied to the virtual robot model for interaction and display;

[0038] The one or more virtual robots share a virtualization device; after receiving the behavior data sent by the real object, the virtualization device completes virtualization based on the behavior data and sends the virtualization data corresponding to the behavior data to the virtual robot, and the virtual robot uses the virtualization data to complete remote interaction and display;

[0039] Preferred: Using ultra-high-definition 3D scanning and motion sensor technology to capture the appearance, movements and facial expressions of real objects, create the basic appearance of the digital avatar, and achieve voice matching through voice cloning technology;

[0040] Preferably: the virtualization operation is a rendering operation; the rendering operation is a rendering operation based on a virtual robot model;

[0041] Preferably: the virtual robot is arranged in a remote terminal or a remote server;

[0042] Preferably: when there are multiple virtual robots, the multiple virtual robots are arranged in one or more remote terminals or remote servers;

[0043] The present invention proposes a virtual robot remote interaction method and system based on digital avatar, as shown in the attached Figure 1 As shown, the method comprises the following steps:

[0044] Step S1: constructing a virtual robot model for a virtual robot including one or more virtual robot parts, wherein the virtual robot model includes one or more sub-models, each sub-model corresponding to a virtual robot part; behavior data for each virtual robot can be split into partial behavior data corresponding to each virtual robot part, and correspondingly, partial virtualization data about each partial behavior data corresponds to one or more sub-models;

[0045] Preferably: the virtualization device is a GPU device;

[0046] Preferably: the one or more virtual robots are the same or similar;

[0047] Preferably: the one or more virtual robots are of the same type and have similar functions; therefore, partial virtualized data of different virtual robots can be shared seamlessly or seamlessly. When sharing seamlessly, the combination of partial virtualized data brought about by applying partial virtualized data to each sub-model may bring about interaction or display defects; however, it will bring about a smoother interaction and display experience;

[0048] Preferably, the one or more sub-models are sub-models of components of the virtual robot, and the components include: body part models, different types of data modal models, different action models in an action sequence, etc.;

[0049] Step S2: Each virtual robot asynchronously receives the behavior data sent by the real object, and determines whether there is virtualized data corresponding to the behavior data in the storage device. If yes, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, the virtualization device is waited to return the virtualized data for the behavior data, and the returned virtualized data is used for interaction and / or display;

[0050] The step S2 specifically includes the following steps:

[0051] Step S21: the virtual robot asynchronously receives the behavior data collected from the real object; determines whether the virtualized data vd corresponding to the behavior data exists in the private storage space corresponding to the virtual robot; if so, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, proceeds to the next step;

[0052] The virtualized data vd as a whole can be split into partial virtualized data corresponding to each virtual robot part; it is represented as vd = {vdp p}; where: vdp i is the pth part of virtualized data corresponding to the pth virtual robot part in the virtualized data; the behavior data is projected to each virtual robot part p to obtain partial behavior data dp; the association relationship between the partial virtualized data is determined based on the association relationship or constraint relationship between the partial behavior data, and the virtual relationship matrix Ra is set accordingly = [vdp p，q ], where vdp p，q is an association relationship or constraint relationship between any two virtualized data of the pth and qth parts;

[0053] Preferably: a virtual relationship matrix between corresponding virtualized data is set based on the association relationship or constraint relationship between each part of the behavior data in the action data;

[0054] Preferably: there are one or more virtual relationship matrices corresponding to the association relationship or constraint relationship between each behavior data and each part of the behavior data, which correspond to different association relationships or constraint relationships respectively;

[0055] Preferably: the association relationship refers to the higher the probability of simultaneous occurrence, the higher the probability of simultaneous occurrence of the two, the stronger the association relationship between them; the constraint relationship refers to the constraint relationship between data values, which is related to the inherent attributes of the behavior itself; for example: position, angle, speed, time sequence constraint relationship, etc.;

[0056] Step S22: determine the virtual robot part p involved in the current behavior data; project the behavior data to each virtual robot part p to obtain the corresponding partial behavior data; determine the partial virtualization data vdp corresponding to the partial behavior data dp p Whether the partial virtualized data vd corresponding to the partial behavior data dp exists in the shared storage space, if all the partial virtualized data vd are located in the shared storage space, then the partial virtualized data vd is used to construct virtualized data, and the constructed virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, proceed to the next step;

[0057] Alternatively: if all of the partial behavior data corresponds to the partial virtualization data vdp p All of them are located in the shared storage space, and a partial virtualization data is selected from the partial virtualization data corresponding to each partial behavior data to construct the partial virtualization data group, so that the partial virtualization data group meets the construction condition; the virtualization data is constructed using each partial virtualization data in the partial virtualization data group that meets the construction condition, and the constructed virtualization data is applied to the virtual robot model, and the virtual robot uses the virtualization data for interaction and / or display; wherein: the construction condition is the virtual relationship matrix cRa of the virtualization data group = [cvdp ic，jc ] and the distance between the virtual relationship matrix corresponding to each part of the action data is the shortest;

[0058] Alternatively: the construction condition is that the association relationship between the various partial behavior data corresponding to the virtualized data group is the strongest or most consistent with the requirements of the constraint relationship;

[0059] Alternatively: using each partial virtualization data in the partial virtualization data group that meets the construction condition to act on each sub-model respectively, so that the virtual robot uses the virtualization data for interaction and / or display;

[0060] Step S23: Send the current behavior data to the virtualization device to virtualize the behavior data; at the same time, predict the completion time of sending the current behavior data to the virtualization device; if the completion time is less than or equal to the historical query time threshold, wait for the virtualization data returned by the virtualization device; otherwise, search for the virtualization data corresponding to the behavior data in the historical virtualization data in the external storage space; if the corresponding virtualization data is found, load it, so that the virtualization data acts on the virtual robot model, and the virtual robot uses the virtualization data for interaction and / or display; if it is not found in the historical virtualization data, wait for the virtualization data returned by the virtualization device;

[0061] Preferably: predicting the completion time based on the queue length of the behavior data to be completed in the virtualization device;

[0062] Preferably: before searching for virtualized data corresponding to the behavior data in the historical virtualized data stored in the external storage space, determine the access queue length of the external communication interface to estimate the access time; when the estimated access time is close to or greater than the completion time, proceed to the next step; this indicates that both the completion time and the access time of the virtualized device are relatively long;

[0063] Step S24: if there are partial virtualization data corresponding to the partial behavior data in the shared storage space, one partial virtualization data is selected from the partial virtualization data corresponding to the partial behavior data, and the partial behavior data without partial virtualization data is filled with default values ​​to construct a missing partial virtualization data group; for each missing partial virtualization data group, its associated total amount is calculated, and the one with the highest associated total amount is selected as the constructed missing partial virtualization data group; prediction is performed based on the missing partial virtualization data group to obtain a predicted partial virtualization data group; each partial virtualization data in the predicted partial virtualization data group is used to act on each sub-model respectively, so that the virtual robot can interact and / or display;

[0064] The calculating of the total amount of association is specifically: adding the association relationship value between each two non-default value partial virtualization data in the missing partial virtualization data group as the total amount of association of the missing partial virtualization data group;

[0065] The step of performing prediction based on the missing partial virtualized data set to obtain the predicted partial virtualized data set specifically includes the following steps:

[0066] Step S24A1: obtaining an unprocessed defective partial virtualized data in the defective partial virtualized data group;

[0067] Step S24A2: finding U partial virtualized data with the largest correlation with the unprocessed defective partial virtualized data in the virtual relationship matrix corresponding to the behavior data as input of the virtualized data prediction model, outputting the U partial virtualized data as the predicted partial virtualized data of the unprocessed defective partial virtualized data, and filling the partial virtualized data group with the predicted partial virtualized data;

[0068] Preferably: the U is a preset value, for example: U=2;

[0069] Preferably: the virtualized data prediction model is obtained by training based on historical data, its input width is U, and its output width is 1;

[0070] Preferably: the virtualized data prediction model is a neural network model;

[0071] Step S24A3: Determine whether all missing virtualized data have been predicted. If not, return to step S24A1; repeat the above steps until all missing virtualized data have been filled in.

[0072] Preferably: after the virtualization device returns the virtualized data for the behavior data, and before the next behavior data arrives, the virtualized data is saved in the private storage space of the virtual robot, and the corresponding part of the virtualized data is stored in the shared storage space, and the returned virtualized data is used to act on the virtual robot model again, and the virtual robot uses the returned virtualized data for interaction and / or display;

[0073] Step S3: the virtual robot manages its private storage space, and the storage device manages the shared storage space; the storage device is also used to manage the external storage space;

[0074] The virtual robot manages its private storage space, specifically: the virtual robot manages its private storage space, and saves the virtualized data returned by the virtualization device into the private storage space; predicts the behavior data based on the frequency of occurrence of the behavior data, and pre-virtualizes the predicted behavior data, and then pre-fetches the obtained virtualized data into the private storage space, and deletes the least recently used virtualized data from the private storage space, and saves the deleted virtualized data into the external storage space;

[0075] The storage device manages the shared storage space, specifically: while each virtual robot stores the virtualized data in the private storage space of the virtual robot, the corresponding partial virtualized data is stored in the shared storage space; based on the usage (access) frequency of the partial virtualized data, the storage management is performed, and the least used partial virtualized data is deleted; based on the occurrence frequency of the partial behavior data, the partial behavior data is predicted, and the predicted partial behavior data is pre-virtualized for each virtual robot, and the obtained partial virtualized data is pre-fetched into the shared storage space;

[0076] The prediction of partial behavior data based on the occurrence frequency of partial behavior data is specifically as follows: obtaining a weight value of each partial behavior data, so that the weight value of the partial behavior data most frequently used recently is high, and the weight value of the partial behavior data least used recently is low; clustering is performed based on the weight value and the degree of similarity between the partial behavior data to obtain one or more clusters of partial behavior data; the constraint condition of clustering is the degree of similarity between the partial behavior data or the number of elements in the cluster; calculating the sum of the weight values ​​of each cluster of partial behavior data; taking the cluster of partial behavior data with the highest sum of weight values ​​as the prediction object for prediction to obtain predicted partial behavior data;

[0077] The prediction is performed by taking the partial behavior data cluster with the highest total weight value as the prediction object, specifically: performing partial behavior data interpolation on the partial behavior data cluster to obtain interpolated partial behavior data, and sending the interpolated partial behavior data to the virtualization device to obtain predicted partial behavior data;

[0078] The storage device is also used to manage the external storage space, specifically: the storage device saves the virtualized data deleted by the virtual robot and performs storage management; the storage management includes backup, hierarchical storage, etc.;

[0079] Based on the same inventive concept, the present invention also provides a virtual robot remote interaction platform based on a digital avatar, and the platform is used to implement the above-mentioned virtual robot remote interaction method based on a digital avatar;

[0080] Based on the same inventive concept, the present invention also provides a virtual robot remote interaction system based on a digital avatar, and the system is used to implement the above-mentioned virtual robot remote interaction method based on a digital avatar;

[0081] Based on the same inventive concept, the present invention also provides a virtual robot remote interaction device based on a digital avatar, and the device is used to implement the above-mentioned virtual robot remote interaction method based on a digital avatar;

[0082] Based on the same inventive concept, the present invention also provides a virtual robot remote interaction server based on a digital avatar, and the server is used to implement the above-mentioned virtual robot remote interaction method based on a digital avatar;

[0083] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of a programming language, including an assembled or interpreted language, a declarative or procedural language, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A virtual robot remote interaction method based on digital avatar, characterized in that: The method comprises: Step S1: constructing a virtual robot model for a virtual robot including one or more virtual robot parts, wherein the virtual robot model includes one or more sub-models, each sub-model corresponding to a virtual robot part; behavior data for each virtual robot can be split into partial behavior data corresponding to each virtual robot part, and correspondingly, partial virtualization data about each partial behavior data corresponds to one or more sub-models; Step S2: Each virtual robot asynchronously receives the behavior data sent by the real object, and determines whether there is virtualized data corresponding to the behavior data in the storage device. If yes, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, the virtualization device is waited to return the virtualized data for the behavior data, and the returned virtualized data is used for interaction and / or display; The storage device includes a private storage space associated with each virtual robot, a shared storage space shared by one or more virtual robot robots, and an external storage space for storing historical behavior data and historical virtualized data; wherein: the private storage space is used to store each behavior data of each virtual robot and its corresponding virtualized data; and the shared storage space stores part of the behavior data and its corresponding part of the virtualized data; The step S2 specifically includes the following steps: Step S21: the virtual robot asynchronously receives the behavior data collected from the real object; determines whether the virtualized data vd corresponding to the behavior data exists in the private storage space corresponding to the virtual robot; if so, the virtualized data is applied to the virtual robot model, and the virtual robot uses the virtualized data for interaction and / or display; otherwise, proceeds to the next step; The virtualized data vd as a whole can be split into partial virtualized data corresponding to each virtual robot part; it is represented as vd = {vdp p }; where: vdp i is the pth part of virtualized data corresponding to the pth virtual robot part in the virtualized data; the behavior data is projected to each virtual robot part p to obtain partial behavior data dp; the association relationship between the partial virtualized data is determined based on the association relationship or constraint relationship between the partial behavior data, and the virtual relationship matrix Ra is set accordingly = [vdp p，q ], where vdp p，q is an association relationship or constraint relationship between any two virtualized data of the pth and qth parts; Step S22: determine the virtual robot part p involved in the current behavior data; project the behavior data to each virtual robot part p to obtain the corresponding partial behavior data; determine the partial virtualization data vdp corresponding to the partial behavior data dp p Whether it exists in the shared storage space, if all the partial behavior data corresponds to the partial virtualization data vdp p All of them are located in the shared storage space, and a partial virtualization data is selected from the partial virtualization data corresponding to each partial behavior data to construct the partial virtualization data group, so that the partial virtualization data group meets the construction condition; the virtualization data is constructed using each partial virtualization data in the partial virtualization data group that meets the construction condition, and the constructed virtualization data is applied to the virtual robot model, and the virtual robot uses the virtualization data for interaction and / or display; wherein: the construction condition is the virtual relationship matrix cRa of the virtualization data group = [cvdp ic,jc ] and the distance between the virtual relationship matrix corresponding to each part of the behavior data in the action data is the shortest; otherwise, proceed to the next step; Step S23: sending the current behavior data to the virtualization device to virtualize the behavior data; waiting for the virtualization data returned by the virtualization device; Step S3: The virtual robot manages the private storage space, and the storage device manages the shared storage space; the storage device is also used to manage the external storage space.

2. The virtual robot remote interaction method based on digital avatar according to claim 1, characterized in that: The virtualization device is a GPU device.

3. The method for remote interaction of a virtual robot based on a digital avatar according to claim 2, characterized in that: The one or more virtual robots are the same or similar.

4. The method for remote interaction of a virtual robot based on a digital avatar according to claim 3, characterized in that: The storage device is divided into multiple parts, and the shared storage space and the private storage space are located in different parts of the storage device.

5. The method for remote interaction of a virtual robot based on a digital avatar according to claim 4, characterized in that: The access efficiency of the private storage space and the shared storage space is higher than that of the external storage space.

6. The virtual robot remote interaction method based on digital avatar according to claim 5, characterized in that: Virtual robots based on digital avatars can be used in assembly line devices, cluster operation devices, real-time monitoring devices, game systems or conference systems.

7. The virtual robot remote interaction system based on digital avatar according to claim 6, characterized in that: When the virtualized data returned by the virtualization device is loaded into the private storage space, the corresponding part of the virtualized data is also loaded into the shared storage space.

8. A virtual robot remote interaction system based on digital avatar, characterized in that: include: The system includes one or more virtual robots based on digital avatars, a virtualization device, a storage device and real objects corresponding to the one or more virtual robots; the virtual robots, as digital avatars of real objects, interact and display based on virtualization data; and is used to implement the virtual robot remote interaction method based on digital avatars as described in any one of claims 1 to 7.

9. A virtual robot remote interaction platform based on digital avatar, characterized in that: It includes a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the virtual robot remote interaction method based on a digital avatar described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: It includes a program which, when running on a computer, enables the computer to execute the virtual robot remote interaction method based on a digital avatar as described in any one of claims 1 to 7.

Images