Digital human interaction method, apparatus and device, and storage medium

Abstract

The invention provides a digital human interaction method and device, equipment and a storage medium, and relates to the technical field of meta universe. In some embodiments of the disclosure, user feature points of a plurality of digital humans are obtained; wherein the user feature points represent position information of skeleton nodes of the digital human; performing security risk identification based on the user feature points to obtain an identification result whether a security risk event exists; under the condition that the identification result is that the security risk event occurs, executing a security protection action to realize dynamic monitoring and active protection of digital human behaviors in the virtual environment; based on the user feature points of the digital human, the security risk identification accuracy is improved, the security risk in the digital human interaction process is further reduced, and the user experience is improved.

Description

Technical Field

[0001] This disclosure relates to the field of metaverse technology, and in particular to a digital human interaction method, apparatus, device, and storage medium. Background Technology

[0002] Because the metaverse environment can simulate highly realistic experiences, some content may negatively impact users' mental health. Inappropriate content such as violence in virtual reality can have a negative effect on users, especially in multi-person interactive environments, where such content may exacerbate the problem. Currently, based on publicly available news reports, several safety incidents involving digital human interaction have occurred in VRChat, causing psychological harm to users. With the technological advancement of digital humans, they will possess more realistic appearances and movements, and more intelligent interactive capabilities. Furthermore, with the development of 5G-A and 6G, the realization of sensory interconnection will provide users with a fully immersive holographic interactive experience.

[0003] With the development of these technologies, security remains a significant and unresolved issue. Currently, digital human interaction faces substantial security risks and results in a poor user experience. Summary of the Invention

[0004] This disclosure provides a digital human interaction method, apparatus, device, and storage medium to at least address the problems of significant security risks and low user experience in existing digital human interactions.

[0005] The technical solution disclosed herein is as follows: This disclosure provides a digital human interaction method, including: Multiple user feature points of a digital human are acquired; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human; Security risks are identified based on the user feature points, and the identification results are obtained. If the identification result indicates that a security risk event has occurred, security protection actions will be performed.

[0006] Optionally, the step of identifying security risks based on the user feature points to obtain the identification result includes: The user feature points are input into the security risk identification model to identify security risks, and the identification results are obtained.

[0007] Optionally, the security risk identification model includes: an input layer, a hidden layer, and an output layer; the step of inputting the user feature points into the security risk identification model for security risk identification and obtaining the identification result includes: Within the security risk identification model, the user feature points are input into the input layer, and the user feature points are normalized to obtain normalized feature points. The normalized feature points are output to the hidden layer, potential risk features are extracted from the normalized feature points, and the target risk type and the probability corresponding to the target risk type are determined based on the potential risk features. The target risk type and the probability corresponding to the target risk type are output to the output layer, and the identification result is output according to the target risk type and the probability corresponding to the target risk type.

[0008] Optionally, before using the security risk identification model, the method further includes: Collect feature sample data; The feature sample data is labeled to obtain a training sample set; The initial neural network model is trained based on the training sample set to obtain the trained security risk identification model.

[0009] Optionally, the collected feature sample data includes: Using VR devices to control 3D digital humans to artificially simulate security risk events, and collecting characteristic sample data; or... Using cameras and AR motion capture technology, feature sample data is collected by artificially simulating safety risk events.

[0010] Optionally, the step of performing security protection actions when the identification result indicates that a security risk event has occurred includes: If the identification result indicates a security risk event, stop sending interactive commands; or, In the event that the identification result indicates a security risk event has occurred, the digital human controlling the risk-proactive party stops moving; or, If the identification result indicates a security risk event has occurred, the digital human of the party at risk will be moved to a safe area; or, If the identification result indicates that a security risk event has occurred, a security warning is sent to the terminal device corresponding to the digital human of the party at risk.

[0011] This disclosure also provides a digital human interaction device, including: The acquisition module is used to acquire multiple user feature points of the digital human; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human; The identification module is used to identify security risks based on the user's feature points and obtain the identification results; The execution module is used to perform security protection actions when the identification result indicates that a security risk event has occurred.

[0012] This disclosure also provides an electronic device, including: processor; Memory used to store processor-executable instructions; The processor is configured to execute instructions to implement the steps in the above method.

[0013] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0014] This disclosure also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described above.

[0015] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In some embodiments of this disclosure, multiple user feature points of the digital human are acquired; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human; security risk identification is performed based on the user feature points to obtain the identification result of whether a security risk event exists; if the identification result indicates that a security risk event has occurred, security protection actions are executed to realize dynamic monitoring and proactive protection of the digital human's behavior in the virtual environment; this disclosure improves the accuracy of security risk identification based on the user feature points of the digital human, thereby reducing the security risks in the digital human interaction process and improving the user experience.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 A flowchart illustrating a digital human interaction method provided for an exemplary embodiment of this disclosure; Figure 2 A schematic diagram of a security risk identification model provided for an exemplary embodiment of this disclosure; Figure 3 A schematic diagram of a security risk identification model provided for an exemplary embodiment of this disclosure; Figure 4 A schematic diagram of the structure of a digital human interaction device provided for an exemplary embodiment of this disclosure; Figure 5 A schematic diagram of the structure of an electronic device provided for an exemplary embodiment of this disclosure. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0020] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0021] It should be noted that the user information involved in this disclosure includes, but is not limited to, user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0022] To address the aforementioned technical issues, some embodiments of this disclosure acquire multiple user feature points of the digital human; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human; security risk identification is performed based on the user feature points to obtain an identification result indicating whether a security risk event exists; if the identification result indicates that a security risk event has occurred, security protection actions are executed to achieve dynamic monitoring and proactive protection of digital human behavior in the virtual environment; this disclosure improves the accuracy of security risk identification based on the user feature points of the digital human, thereby reducing security risks in the digital human interaction process and improving user experience.

[0023] The technical solutions provided by the embodiments of this disclosure are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 This is a flowchart illustrating a digital human interaction method provided as an exemplary embodiment of this disclosure. Figure 1 As shown, the method includes: S101: Acquire multiple user feature points of the digital human; whereby the user feature points represent the positional information of the skeletal nodes of the digital human; S102: Identify security risks based on user feature points and obtain the identification results; S103: If the identification result indicates that a security risk event has occurred, execute security protection actions.

[0025] In this embodiment, the entity executing the above method can be a terminal device or a server.

[0026] The terminal device includes, but is not limited to, mobile stations (MS), mobile terminals, mobile phones, handsets, and portable equipment. This terminal device can communicate with one or more core networks via a radio access network (RAN). For example, the terminal device can be a mobile phone (or "cellular" phone), a computer with wireless communication capabilities, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an AR terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. The operating systems installed on the terminal device include, but are not limited to, iOS, Android, Windows, Linux, and Mac OS. In different networks, terminals may be called by different names, such as: user equipment, mobile station, user unit, station, cellular phone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop, cordless phone, wireless local loop station, television, etc. For ease of description, this embodiment will simply refer to it as terminal device.

[0027] In this embodiment, the implementation form of the server is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, or other server devices. The server's components mainly include a processor, hard disk, memory, system bus, and other common computer architecture types. Specifically, the server can be an RTC server.

[0028] In this embodiment, multiple user feature points of the digital human are acquired; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human; security risk identification is performed based on the user feature points to obtain the identification result of whether a security risk event exists; if the identification result indicates that a security risk event has occurred, security protection actions are executed to realize dynamic monitoring and proactive protection of digital human behavior in the virtual environment; this disclosure improves the accuracy of security risk identification based on the user feature points of the digital human, thereby reducing the security risks in the digital human interaction process and improving the user experience.

[0029] In some embodiments of this disclosure, multiple user feature points of the digital human are acquired; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human. By analyzing these feature points, this disclosure can achieve more advanced human-computer interaction methods, such as allowing characters in a virtual environment to react in real time according to the user's actual actions, greatly enhancing immersion and interactive experience. The acquisition system is responsible for collecting feature point data of the digital human, including but not limited to: world coordinates (x, y, z) and rotation angle (θ) of the left eye, right eye, mouth, left shoulder, left upper arm, left lower arm, left hand, left upper leg, left lower leg, left foot, right shoulder, right upper shoulder, right lower shoulder, right hand, right upper leg, right lower leg, and right foot. The data format of a single feature point is represented as P:{x,y,z,θ}; the list of feature values ​​P array is represented as [left eye feature point P1, right eye feature point P2, mouth feature point P3, left shoulder feature point P4, left upper arm feature point P5, left lower arm feature point P6, left hand feature point P7,...]; the data format of the user feature point set is represented as U:{user id, user information, timestamp, [P1, P2, P3, P4, P5, P6, P7,...]}; the acquisition system collects the user feature point set data U(a,t) in real time and sends it to the security protection system on the RTC server side. U(a,t) represents the feature point set data U of user a at time t; the feature point data set [U(a,t1), U(a,t2), U(a,t3),..., U(a,t4)] received by the security protection system can be represented as the behavioral feature values ​​of user a controlling the digital human from time t1 to t4.

[0030] In some embodiments of this disclosure, security risks are identified based on user feature points to obtain identification results. One possible approach is to input user feature points into a security risk identification model for security risk identification to obtain identification results. This disclosure analyzes user feature points input into a security risk identification model to achieve intelligent identification of security risks related to user behavior or posture.

[0031] It should be noted that a security risk identification model needs to be trained before it can be used. One possible approach is to collect feature sample data; label the feature sample data to obtain a training sample set; and train the initial neural network model based on the training sample set to obtain the trained security risk identification model.

[0032] In the above embodiments, feature sample data is collected and stored on a server. One possible approach is to use a VR device to control a 3D digital human to artificially simulate a security risk event and collect feature sample data; or, to use a camera to collect feature sample data using AR motion capture technology to artificially simulate a security risk event.

[0033] Among them, the generated security risk event A feature sample Sample(A): Sample(A) = {[U(a,t1), U(a,t2), U(a,t3), ..., U(a,t4)], [U(b,t1), U(b,t2), U(b,t3), ..., U(b,t4)]}; can be represented as the feature set of security risk events A for users a and b at times t1 to t2.

[0034] To improve the accuracy of feature samples A of security risk events, a feature sample data model Model is generated through machine learning and manual labeling.

[0035] The feature sample data model Model(Sample(A), Sample(B), Sample(C)) represents the security risk event sample model A, security risk event sample model B, and security risk event sample model C.

[0036] Taking real-world examples of eye contact harassment as an example: Eye harassment is defined as: when a man stares at a woman's private parts for a certain period of time, for example 10 seconds, causing the woman to feel uncomfortable and harassed.

[0037] The specific characteristics of eye harassment incidents are as follows: the relative positional relationship between male feature point P (left eye) and feature point P (right eye) and female feature point P (chest) conforms to the gaze relationship and lasts for about t=10 seconds.

[0038] Converted into data representation as: Sample(eye contact harassment) = {[U(male,t1),..., U(male,t2)], [U(female,t1),..., U(female,t2)]}; U(male, t1) = {male user ID, male user information, t1, [P(left eye), P(right eye), ...]}; U(male, t2) = {male user ID, male user information, t2, [P(left eye), P(right eye), ...]}; U(female, t1) = {female user ID, female user information, t1, [...], P(breasts), [...]; U(female, t2) = {female user ID, female user information, t2, [...], P(breasts), ...]}; F(Male P(left eye), Male P(right eye), Female P(chest), t) = gaze; F is the processing unit, with input variables: male P (left eye), male P (right eye), female P (chest), t, and output result: fixation; The duration t is: t2 - t1 = 10s; Using Sample (eye harassment) as training data and various parameters as input units, a model of eye harassment is generated after training with neural network technology.

[0039] In some embodiments of this disclosure, the security risk identification model includes an input layer, a hidden layer, and an output layer. User feature points are input into the security risk identification model for security risk identification to obtain identification results. One possible approach is to input user feature points into the input layer within the security risk identification model, normalize the user feature points to obtain normalized feature points, output the normalized feature points to the hidden layer, extract potential risk features from the normalized feature points, and determine the target risk type and its corresponding probability based on the potential risk features. The target risk type and its corresponding probability are then output to the output layer, and the identification result is output based on the target risk type and its corresponding probability. This disclosure uses a deep learning model architecture to process user feature point data, achieving intelligent identification of security risks, improving the efficiency and reliability of security monitoring systems, and is suitable for security assurance needs in various application scenarios.

[0040] Figure 2 This is a schematic diagram of a security risk identification model provided for an exemplary embodiment of this disclosure. Figure 2 As shown, taking the identification of eye harassment incidents as an example, the user's information, all feature values ​​P, time t, etc. are input as input variables in the input layer. In the hidden layer, the data is processed by a multi-layer neural network. When the probability of an eye harassment incident is higher than 90%, it is determined to be an eye harassment incident and output from the output layer.

[0041] In some embodiments of this disclosure, when the identification result indicates that a security risk event has occurred, security protection actions are performed, including but not limited to at least one of the following security protection methods: Security Protection Method 1: If the identification result indicates that a security risk event has occurred, stop sending interactive commands; Security Protection Method Two: In the event that a security risk event has been identified, the digital human of the party in charge of controlling the risk will stop moving; Security Protection Method 3: If the identification result indicates that a security risk event has occurred, move the digital human of the party at risk to a safe scene area; Security Protection Method 4: If the identification result indicates that a security risk event has occurred, a security warning notification will be sent to the terminal device corresponding to the digital human of the party at risk.

[0042] In one feasible approach, during the multi-user interaction phase of the digital human, the security protection system analyzes the received user feature point data sets U(a,ti) and U(b,ti) in real time on the RTC server side. When the analysis finds that the feature point data set at time t1 to t2 matches the sample of the infringing feature point dataset, the aforementioned security protection action is executed.

[0043] Figure 3 This is an interactive schematic diagram of a digital human interaction method provided as an exemplary embodiment of the present disclosure. For example... Figure 3 As shown, a set of several feature points of the digital human is collected. During the data signaling RTC transmission and reception stage, the security protection system of the protection server analyzes the feature point data in real time. When the event meets the criteria for an infringement, the security protection mechanism is triggered to prevent the infringement interaction signaling from being sent to the victim (user B), and to send security protection signaling to the interacting parties (user A and user B), and to store the evidence-collecting infringement signaling data, thus realizing the prevention mechanism and evidence-collecting capability of security protection.

[0044] Figure 4 This is a schematic diagram of the structure of a digital human interaction device 40 provided for an exemplary embodiment of this disclosure. (See diagram below.) Figure 4 As shown, the digital human interaction device 40 includes: an acquisition module 41, an identification module 42, and an execution module 43.

[0045] The acquisition module 41 is used to acquire multiple user feature points of the digital human; wherein, the user feature points represent the positional information of the skeletal nodes of the digital human. The identification module 42 is used to identify security risks based on user feature points and obtain identification results; Execution module 43 is used to perform security protection actions when the identification result indicates that a security risk event has occurred.

[0046] Optionally, when the identification module 42 performs security risk identification based on user feature points and obtains the identification result, it is used for: User feature points are input into the security risk identification model to identify security risks and obtain the identification results.

[0047] Optionally, the security risk identification model includes: an input layer, a hidden layer, and an output layer; the identification module 42, when inputting user feature points into the security risk identification model to perform security risk identification and obtaining the identification result, is used for: Within the security risk identification model, user feature points are input into the input layer, and the user feature points are normalized to obtain normalized feature points. The normalized feature points are output to the hidden layer. Potential risk features are extracted from the normalized feature points, and the target risk type and the probability corresponding to the target risk type are determined based on the potential risk features. The target risk type and its corresponding probability are output to the output layer, and the identification result is output based on the target risk type and its corresponding probability.

[0048] Optionally, before using the security risk identification model, the identification module 42 can also be used for: Collect feature sample data; The feature sample data is labeled to obtain the training sample set; Based on the training sample set, the initial neural network model is trained to obtain the trained security risk identification model.

[0049] Optionally, when collecting feature sample data, the recognition module 42 is used for: Using VR devices to control 3D digital humans to artificially simulate security risk events, and collecting characteristic sample data; or... Using cameras and AR motion capture technology, feature sample data is collected by artificially simulating safety risk events.

[0050] Optionally, when the execution module 43 performs security protection actions in the event that a security risk event has occurred, it is used to: If the identification result indicates a security risk event, stop sending interactive commands; or, If the identification result indicates a security risk event, the digital human controlling the risk stops moving; or... If the identification result indicates a security risk event, the digital human of the party at risk will be moved to a safe area; or, If the identification result indicates that a security risk event has occurred, a security warning will be sent to the terminal device corresponding to the digital human of the party at risk.

[0051] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0052] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this disclosure. For example... Figure 5 As shown, the electronic device includes a memory 51 and a processor 52. Additionally, the electronic device also includes a power supply component 53 and a communication component 54.

[0053] Memory 51 is used to store computer programs and can be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device.

[0054] The memory 51 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0055] Communication component 54 is used for data transmission with other devices.

[0056] The processor 52 can execute computer instructions stored in the memory 51 for: acquiring multiple user feature points of the digital human; wherein the user feature points represent the positional information of the skeletal nodes of the digital human; identifying security risks based on the user feature points and obtaining identification results; and performing security protection actions if the identification results indicate that a security risk event has occurred.

[0057] Accordingly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores a computer program, and the computer program is executed by one or more processors, it causes one or more processors to perform... Figure 1 Each step in the method embodiment.

[0058] Accordingly, this disclosure also provides a computer program product, which includes a computer program / instructions that are executed by a processor. Figure 1 Each step in the method embodiment.

[0059] The above Figure 5The communication component is configured to facilitate wired or wireless communication between the device containing the communication component and other devices. The device containing the communication component can access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G / LTE, 5G, or combinations thereof. In one exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA) technology, Ultra-Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0060] The above Figure 5 The power supply component provides power to the various components of the device in which it resides. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which it resides.

[0061] The aforementioned electronic devices also include a display screen and audio components.

[0062] The display includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions, but also the duration and pressure associated with the touch or swipe operation.

[0063] An audio component may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals may be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0064] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied 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.

[0065] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0069] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0070] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0071] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0072] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A digital human interaction method, characterized by, The method comprises: obtaining user feature points of a plurality of digital humans; wherein the user feature points represent position information of bone nodes of the digital humans; performing security risk identification according to the user feature points to obtain an identification result; in the case where the identification result indicates that a security risk event occurs, performing a security protection action.

2. The method of claim 1, wherein, The security risk identification according to the user feature points to obtain an identification result comprises: inputting the user feature points into a security risk identification model to perform security risk identification and obtain the identification result.

3. The method of claim 2, wherein, The security risk identification model comprises an input layer, a hidden layer and an output layer; the inputting of the user feature points into the security risk identification model to perform security risk identification and obtain the identification result comprises: inputting the user feature points into the input layer inside the security risk identification model to perform normalization processing on the user feature points to obtain normalized feature points; outputting the normalized feature points to the hidden layer to extract potential risk features from the normalized feature points and determine a target risk type and a probability corresponding to the target risk type according to the potential risk features; outputting the target risk type and the probability corresponding to the target risk type to the output layer to output the identification result according to the target risk type and the probability corresponding to the target risk type.

4. The method of claim 2, wherein, Before using the security risk identification model, the method further comprises: collecting feature sample data; labeling the feature sample data to obtain a training sample set; training an initial neural network model according to the training sample set to obtain the security risk identification model after training.

5. The method of claim 4, wherein, The collection of feature sample data comprises: collecting feature sample data by manually simulating a security risk event by controlling a 3D digital human using a VR device; or collecting feature sample data by manually simulating a security risk event by AR motion capture technology using a camera.

6. The method of claim 1, wherein, The execution of a security protection action in the case where the identification result indicates that a security risk event occurs comprises: stopping sending an interaction instruction in the case where the identification result indicates that a security risk event occurs; or controlling a digital human of a risk active party to stop moving in the case where the identification result indicates that a security risk event occurs; or moving a digital human of a risk passive party to a safe scene area in the case where the identification result indicates that a security risk event occurs; or sending a safety warning prompt to a terminal device corresponding to the digital human of the risk passive party in the case where the identification result indicates that a security risk event occurs.

7. A digital human interaction device, characterized by The method comprises: an acquisition module configured to obtain user feature points of a plurality of digital humans; wherein the user feature points represent position information of bone nodes of the digital humans; an identification module configured to perform security risk identification according to the user feature points to obtain an identification result; an execution module configured to perform a security protection action in the case where the identification result indicates that a security risk event occurs.

8. An electronic device, comprising: The method comprises: a processor; a memory configured to store processor-executable instructions; wherein the processor is configured to execute instructions to implement the steps of the method of any of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, which when executed by the processor, carries out the steps of the method of any of claims 1-6.

10. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions, which when executed by the processor, carry out the steps of the method of any of claims 1-6.

Images