Virtual conference method and device and computer readable storage medium

Abstract

The invention discloses a virtual conference method and device and a computer readable storage medium. Relates to the technical field of digital employees, and the method comprises the steps: receiving a virtual conference request which comprises a conference demand and a conference process; creating a virtual digital person and a virtual conference scene based on the virtual conference request, and placing the virtual digital person in the virtual conference scene; controlling the virtual digital person to carry out an online conference in the virtual conference scene according to the conference process; and in the online conference process, controlling the virtual digital person to receive information input based on the target account to reply. Through application of the method and the device, the problem of low user experience caused by low participation degree of participants in the current virtual digital human conference and insufficiently tight connection in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of digital employee technology, and in particular to a virtual meeting method, device, and computer-readable storage medium. Background Art

[0002] Virtual human conferencing utilizes artificial intelligence and virtual reality technologies to allow users to confer and communicate with digital characters in a virtual space. Users can enter the virtual space through devices such as head-mounted displays (HMDs) or smartphones and engage in face-to-face communication with digital characters. Virtual human conferencing saves time and costs while also enabling remote meetings worldwide. Currently, virtual human conferencing technology is continuously developing and improving. With the continuous advancement of artificial intelligence and virtual reality technologies, the experience and effectiveness of virtual human conferencing are becoming increasingly realistic and efficient. Related technologies allow for the seating of digital characters participating in virtual human conferencing.

[0003] However, the online and offline connections in related technologies are not close enough, the online virtual digital people's meeting behaviors are not rich, and they do not simulate the various actions of offline participants, which will lead to a weak experience for participants and fail to provide users with a more realistic virtual meeting experience.

[0004] Currently, no effective solution has been proposed to the problem that participants in virtual digital human conferences have low participation and insufficient connection, resulting in a poor user experience. Summary of the Invention

[0005] The main purpose of this application is to provide a virtual conference method, device and computer-readable storage medium to solve the problem in the related art that the participation of participants in virtual digital human conferences is low, the connection is not tight enough, and the user experience is not good.

[0006] To achieve the above objectives, according to one aspect of the present application, a virtual meeting method is provided. The method includes: receiving a virtual meeting request, wherein the virtual meeting request includes meeting requirements and a meeting process; based on the virtual meeting request, creating a virtual digital human and a virtual meeting scene and placing the virtual digital human in the virtual meeting scene; controlling the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process; and during the online meeting, controlling the virtual digital human to respond to information input based on a target account.

[0007] Optionally, creating a virtual digital human based on a virtual meeting request includes: obtaining a virtual digital human template; and adjusting the appearance, voice, and motion mode of the virtual digital human template based on meeting requirements to obtain the virtual digital human.

[0008] Optionally, based on the virtual meeting request, a virtual meeting scene is created, including: determining the type of virtual meeting scene based on the meeting requirements; determining the virtual meeting scene template based on the virtual meeting scene type; determining the size of the virtual digital human; based on the meeting requirements and the size of the virtual digital human, adjusting the size of the virtual meeting scene template and the materials and lighting in the virtual meeting scene template to obtain the virtual meeting scene.

[0009] Optionally, placing the virtual digital human in the virtual meeting scene further includes: identifying objects in the virtual meeting scene and determining a target position, wherein the target position is a position where the virtual digital human is placed; placing the virtual digital human at the target position; and adjusting the movement and direction of the virtual digital human at the target position.

[0010] Optionally, controlling the virtual digital human to receive and reply to information input based on the target account includes: when the information input into the target account is voice information, controlling the virtual digital human to convert the voice information into text information; controlling the virtual digital human to query target data related to the text information from a preset corpus; and controlling the virtual digital human to reply based on the target data.

[0011] Optionally, feedback information based on the target account input is received, wherein the feedback information represents feedback information of a reply to the virtual digital person; and the corpus is adjusted based on the feedback information.

[0012] Optionally, controlling the virtual digital human to conduct an online meeting in a virtual meeting scene according to the meeting process includes: setting actions for the virtual digital human corresponding to N links in the meeting process, where N is a positive integer; and controlling the virtual digital human to perform corresponding actions in the virtual meeting scene according to the meeting process.

[0013] To achieve the above objectives, according to another aspect of the present application, a virtual conference device is provided. The device includes: a receiving module for receiving a virtual conference request, wherein the virtual conference request includes the conference requirements and the conference process; a creation module for creating a virtual digital human and a virtual conference scene based on the virtual conference request and placing the virtual digital human in the virtual conference scene; a first control module for controlling the virtual digital human to conduct an online meeting in the virtual conference scene according to the conference process; and a second control module for controlling the virtual digital human to respond to information received based on input from a target account during the online meeting.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is also provided, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned virtual conference methods.

[0015] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is run, any one of the virtual conference methods in the claims above is executed.

[0016] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, comprising computer instructions, which implement the steps of any one of the above-mentioned virtual conference methods when executed by a processor.

[0017] In an embodiment of the present application, a virtual meeting method is adopted, by receiving a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures; based on the virtual meeting request, a virtual digital person and a virtual meeting scene are created and the virtual digital person is placed in the virtual meeting scene; the virtual digital person is controlled to conduct an online meeting in the virtual meeting scene according to the meeting procedure; during the online meeting, the virtual digital person is controlled to receive information input based on the target account and respond, thereby achieving the purpose of closely connecting the virtual digital person with the participants, thereby realizing the technical effect of improving the user experience, and further solving the technical problem that the participation of participants in the current virtual digital person meeting is low, the connection is not tight enough, and the user experience is not high. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0019] Figure 1 A hardware structure block diagram of a computer terminal for implementing a virtual conference method is shown;

[0020] Figure 2 is a flowchart of a virtual conference method provided according to an embodiment of the present application;

[0021] Figure 3 is a structural block diagram of a virtual conference device provided according to an embodiment of the present application;

[0022] Figure 4 This is a structural block diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation portals for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0026] Example 1

[0027] According to an embodiment of the present application, a method embodiment of a virtual meeting is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal for implementing a virtual conference method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the virtual conference method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned virtual conference method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0033] Under the above operating environment, this application provides Figure 2 Virtual meeting method shown. Figure 2 This is a flowchart of a virtual conference method provided according to an embodiment of the present application.

[0034] Step S201: receiving a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures.

[0035] Virtual meetings in the Metaverse are highly immersive online collaborative experiences that combine cutting-edge technologies such as virtual reality (VR), augmented reality (AR), 3D modeling, artificial intelligence (AI), and blockchain to provide participants with a meeting space that mimics the real world. Virtual meetings in the Metaverse break down geographical boundaries, allowing people from around the world to gather in the same virtual space. Whether it's internal corporate training, international seminars, or remote work meetings, these virtual meetings are all possible.

[0036] Virtual meetings can be held in a customized virtual space, which can be modeled after a real-world conference room, office building, outdoor landscape, or a completely innovative futuristic design. Leveraging 3D modeling and rendering technology, the virtual environment can display rich detail and realism. Participants can choose their own avatar, customize its appearance to suit their preferences, and use motion capture technology to display realistic movements. Furthermore, through AI technology, virtual humans can not only serve as hosts or speakers for pre-set presentations but can also interact with attendees in real time, answering questions and participating in discussions. Using VR helmets or AR glasses, participants can enjoy an immersive meeting experience, enhancing their sense of participation and focus, and making communication more intuitive and vivid.

[0037] In this step, a user sends a request to the Metaverse system to initiate a virtual meeting, which is received by the system. The request must include at least the meeting requirements and process. The requirements primarily include participant information, meeting objectives and topics, participation methods, expected outcomes, and interaction requirements. The process primarily includes time scheduling, agenda, technical demonstrations or presentations, breaks, and follow-up. A complete meeting request facilitates subsequent operations, providing users with a complete and authentic meeting experience and enhancing user experience.

[0038] Specifically, meeting requirements can include a list of attendees, avatar preferences, and any special needs (such as assistive hearing or vision). The main objectives and content of the meeting should be clearly defined to design the virtual environment and digital human characters accordingly. Meeting organizers should also specify the outcomes or key decision points they expect to achieve, as well as whether interactive sessions such as voting, Q&A sessions, and group discussions are necessary. This information can be used to inform the interaction design of the virtual human and the configuration of platform features. The meeting process should include the start and end times, as well as the time allocation for each session, to ensure the virtual meeting starts on time and proceeds in an orderly manner. Each session, such as the opening introduction, keynote speech, group discussions, and concluding remarks, should be outlined in detail to facilitate the virtual human's guidance according to the agenda. If the meeting includes a technical demonstration or product presentation, the relevant technology can be planned and tested in advance to ensure a smooth presentation. Similar to a real-life meeting, virtual meetings can also include breaks or online social sessions to allow participants to relax and freely communicate. A post-meeting action plan can include the distribution of materials, the preparation of meeting minutes, and the scheduling of follow-up meetings to ensure effective follow-up on the meeting's outcomes.

[0039] Every meeting has a specific purpose, agenda, participants, and desired outcomes. Meeting requests help you understand the specific meeting requirements and process, allowing you to customize the design of the virtual human and its behavior to ensure the precise achievement of meeting objectives. Virtual meetings require the allocation of various resources, including the design of the virtual environment, the image and movement design of the digital human, and technical platform support. Clearly defining meeting requests helps rationally plan resources, avoid unnecessary waste, and ensure the smooth progress of the meeting. Different meeting processes may require different types of technical support, such as real-time speech-to-text, multilingual translation, and immersive virtual reality experiences. Meeting requests provide ample time for technical debugging and preparation, ensuring technical stability and user experience during the meeting. Understanding the specific meeting process allows you to pre-set interactive nodes for the virtual human, such as question-and-answer sessions, demonstrations, or guided discussions. This not only makes the meeting more interesting and interactive, but also improves participant engagement and meeting efficiency.

[0040] Step S202: Based on the virtual meeting request, a virtual digital human and a virtual meeting scene are created and the virtual digital human is placed in the virtual meeting scene.

[0041] In this step, the Metaverse system receives the virtual request sent by the user and creates a meeting based on the meeting requirements and meeting process. It can design virtual digital people and virtual meeting scenes based on the participants and meeting topics in the meeting requirements, making the virtual meeting more in line with the real meeting and improving the user experience.

[0042] Specifically, each meeting has a specific purpose, theme, and attendees. By refining the information in the meeting request, we can create virtual digital people and environments that align with the meeting theme. For example, a company's annual meeting might require a festive setting, while a professional seminar might require a more formal conference room layout. This customization not only enhances the professionalism and engagement of the meeting, but also ensures that the virtual experience is as relevant to the theme as the physical meeting.

[0043] First, the meeting request can clarify whether the meeting is for finance, education, business, entertainment, or other fields, as well as the specific meeting theme. This allows the design style and atmosphere of the virtual human to be determined. Based on the meeting theme and participant preferences, the virtual human's appearance, including clothing, facial features, and avatar behavior, can be designed. Real human movements can be recorded and applied to the virtual human, or the virtual human can be programmed to have natural and fluent body language to ensure its expressiveness in the meeting. Speech synthesis technology can be used to enable the virtual human to speak, and natural language processing technology can ensure that it can understand and respond to participant questions, achieving smooth communication.

[0044] Secondly, professional 3D modeling software can be used to create a virtual space, whether it's a conference room, auditorium, outdoor landscape, or a creative themed space. Add decorative details like furniture placement, lighting effects, background music, and even dynamic weather changes to enhance the scene's realism and appeal. Integrate virtual reality, augmented reality, and AI technologies into the scene, including but not limited to interactive whiteboards, real-time translation services, and 360-degree panoramic views, to enhance attendees' interactive experience and information acquisition.

[0045] Finally, integrate the virtual human into the constructed meeting scene. Determine the optimal placement of the virtual human within the scene and the optimal viewing angle for participants to observe it, ensuring that every participant can clearly see and hear the virtual human. Based on the meeting flow, assign the virtual human corresponding actions, such as standing to speak, sitting to listen, or interacting with participants, to make the scene more vivid. Before the meeting officially begins, conduct multiple rehearsals and tests to ensure the virtual human's coordination with the scene and that all technical facilities are functioning properly.

[0046] Step S203: Control the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process.

[0047] In this step, the virtual digital human is controlled based on the meeting process information in the meeting request to ensure that the virtual meeting can proceed smoothly according to the plan of the meeting process, thereby improving the user's meeting experience.

[0048] Specifically, controlling the virtual human based on the meeting flow ensures that its movements are closely synchronized with the script set in the meeting process (including speeches, Q&A sessions, and presentations), resulting in a natural and smooth performance. Natural language processing and machine learning technologies can also be used to enable the virtual human to understand participants' questions or instructions in real time and respond appropriately, enhancing the interactivity and participation of participants. Furthermore, based on the meeting flow, the lighting design and sound effects settings within the scene can be optimized to tailor them to different meeting segments, such as using focused lighting during presentations and adding background music during discussion sessions to enhance the overall audio-visual experience. During the meeting, technical personnel need to monitor the technical status of the scene in real time, such as the virtual human's performance and the quality of participants' network connections, and be ready to make necessary adjustments. Furthermore, to ensure that each segment starts and ends on time, a virtual clock or countdown function can be used to help the virtual human and participants maintain a sense of time. Virtual humans can serve as meeting facilitators, not only presiding over meetings but also explaining processes, providing guidance, and reminding attendees of important matters. They can present multimedia content such as PowerPoint presentations, videos, and 3D models, achieving high-quality content presentation through screen sharing or virtual presentation platforms. Interactive sessions such as real-time Q&A sessions and group discussions can also be designed. Virtual humans can coordinate and facilitate these interactions, ensuring that all participants have the opportunity to participate, effectively enhancing the overall effectiveness and impact of the meeting.

[0049] Step S204: During the online meeting, the virtual digital human is controlled to receive and respond to information input based on the target account.

[0050] In this step, the target account can refer to the participants of the meeting. Participants can send text messages or voice commands to the virtual digital human through the interface or equipment of the conference platform (such as microphones and cameras) to interact. The virtual digital human can respond after receiving the information, realizing real-time interaction between reality and virtuality and enhancing the immersive experience of the participants.

[0051] Specifically, the virtual human can integrate an efficient information reception module that monitors input from the target account in real time, including text chats and voice messages. Natural language processing (NLP) technology is applied to parse incoming messages, identifying question intent, key words, and sentiment, ensuring the virtual human can understand complex and ambiguous expressions. A comprehensive knowledge base and corpus can be established, encompassing meeting-related topics, terminology, common problems, and solutions, enabling the virtual human to provide accurate responses. AI algorithms can be used to generate appropriate and natural responses based on the parsed input and the knowledge base, including subtasks such as question classification, answer retrieval, context matching, and text generation. Machine learning models are used to continuously optimize response strategies. By collecting and analyzing interactive data during the meeting, the virtual human's responses become more personalized, professional, and targeted. Response strategies can be customized for different stages of the meeting, for example, restricting off-topic questions during presentations while encouraging open questions during interactive sessions. The virtual human can also provide more personalized responses based on attendee profiles or past question records, such as using attendee names and referencing past conversations to enhance the authenticity of the interaction.

[0052] After receiving text or voice messages from attendees, the AI ​​system within the virtual human parses the message to understand the instructions, questions, or intent. This is achieved through natural language processing (NLP), speech recognition, and other forms of AI technology. The virtual human then generates a response based on its built-in knowledge base, pre-set rules, or real-time learning capabilities. This response can be a text answer, voice speech, facial expression, or an action performed directly within the meeting environment (such as presenting a slideshow or playing a video). The virtual human then communicates this response to the target account or all attendees. Throughout the process, the meeting organizer or designated on-site control personnel can monitor and control the virtual human's behavior to ensure that its responses are consistent with the meeting process and objectives. Any inappropriate or erroneous responses can be immediately intervened and corrected. In this way, the virtual human effectively facilitates the two-way flow of information, assists in the smooth progress of meetings, and enhances overall interactivity and participation.

[0053] Through the above steps, the goal of closely connecting the virtual digital human and the participants can be achieved, thereby achieving the technical effect of improving the user experience, and thus solving the current technical problem of low participation of participants in virtual digital human meetings, insufficient connection, and poor user experience.

[0054] As an optional embodiment, creating a virtual digital human based on a virtual meeting request includes: obtaining a virtual digital human template; and adjusting the appearance, voice, and motion mode of the virtual digital human template based on meeting requirements to obtain the virtual digital human.

[0055] Optionally, a custom-designed virtual human can be created based on the meeting requirements in the meeting request. Appearance, voice, and movement can be adjusted based on a pre-set template, or a new template can be created to personalize the virtual human. Based on the specific meeting requirements, a virtual human can be created that suits the style and needs of the meeting, thereby enhancing the participant experience.

[0056] For example, first, you can select a basic template for a virtual human based on the meeting type (e.g., business, education, entertainment) and theme. Different templates come with preset appearances, voices, and basic movements, facilitating subsequent customization and adjustment. You can also adjust the virtual human's facial features, hairstyle, makeup, and clothing to suit the meeting's brand image or specific theme. For example, a corporate meeting might prefer a formally dressed virtual host, while a creative workshop might opt ​​for a more casual or creative look. If the preset template doesn't fit the meeting theme, you can use 3D modeling software to modify and optimize the basic template to achieve the desired appearance, such as adding additional embellishments, changing material textures, or adjusting body proportions. This ensures that the virtual human's appearance remains consistent across various devices and platforms, taking into account differences in resolution, screen size, and viewing angle. Secondly, you can select a suitable speech synthesis engine and adjust the voice's timbre, speed, and intonation based on the meeting's language requirements and the preferences of the target audience. By customizing a voice library or using specific voice actor recordings, virtual digital humans can be given unique voice characteristics to make them sound more friendly and professional. A voice recognition system can also be developed to ensure that virtual digital humans can understand and correctly respond to participants' voice commands or questions.

[0057] If a meeting requires a virtual human to display complex movements or express emotions, motion capture technology can be used to record the movements of a real actor and then project them onto the virtual human, making the movements more natural and fluid. Alternatively, existing motion libraries can be selected and edited to suit different meeting scenarios and needs. For example, a business meeting might require more nods, smiles, and handshakes, while an educational training session might focus more on teaching demonstrations and gestures. By following these steps, a virtual human can be created that is tailored to the meeting, with a vivid appearance, voice, and movements, enhancing the professionalism, fun, and engagement of attendees.

[0058] As an optional embodiment, creating a virtual meeting scene based on a virtual meeting request includes: determining the type of virtual meeting scene based on meeting requirements; determining a virtual meeting scene template based on the virtual meeting scene type; determining the size of the virtual digital human; and adjusting the size of the virtual meeting scene template and the materials and lighting in the virtual meeting scene template based on the meeting requirements and the size of the virtual digital human to obtain the virtual meeting scene.

[0059] Optionally, within the Metaverse system, a virtual meeting scene can be created based on the meeting requirements in the meeting request. This scene can be created using a template based on the scenario type. This template can include multiple pre-set scenario templates or be created through on-site scanning. Once the meeting scene is determined, the size of the virtual human must be considered and further adjustments made to avoid any awkward placement or mismatching of the virtual human within the meeting scene.

[0060] For example, by understanding the nature of the meeting (e.g., finance, business, education, entertainment, training), the theme and objectives (e.g., product launch, academic seminar, online training course), and the characteristics of the attendees (e.g., geographic distribution, technology familiarity, cultural background), and analyzing the meeting flow, it is possible to identify potential special features or settings, such as presentation areas, discussion rooms, breakout areas, and exhibition spaces. Based on this needs analysis, the most appropriate virtual meeting scenario type can be selected. For example, a corporate business meeting may be more suited to a formal conference room or lecture hall, while a creative workshop may require an open workspace or creative lab. Based on the scenario type, templates matching the scenario type can be searched for in professional 3D asset libraries, virtual meeting platform resource libraries, or design software. The templates can be evaluated for customizability, visual appeal, technical compatibility, and cost-effectiveness, and the template that best meets the meeting needs can be selected for subsequent customization. Alternatively, 3D scanning technologies such as laser scanning, structured light scanning, and infrared scanning can be used to scan the actual scene. Modeling can then be performed based on the acquired scan data, using professional 3D modeling software to transform the scattered data into a structured 3D model. It can also simulate the lighting conditions on site, including natural light, artificial light and shadow effects, to ensure that the lighting atmosphere of the virtual scene matches the actual situation.

[0061] Determine the optimal size of the virtual human within the scene based on the role it plays and the needs of the meeting. For example, if the virtual human is the meeting host or speaker, its size should be comparable to a real person so that participants can interact naturally with it. Considering the differences in devices that different participants may use (such as VR headsets, PC screens, and mobile devices), you can ensure that the virtual human appears appropriately sized and proportional across all devices. Based on the virtual human's size, the number of participants, and the meeting layout requirements, adjust the size of the virtual meeting scene template to ensure appropriate spacing between the virtual human, participant avatars, and other elements in the scene for easy movement and interaction. Select and adjust the materials in the scene, including walls, floors, and furniture, to reflect the theme of the meeting or create a specific atmosphere. For example, using wood textures can create a warm and inviting meeting space, while metal or glass materials are more suitable for a high-tech or futuristic meeting setting. Set the scene's lighting effects, using point lights, spotlights, or ambient lights to highlight the virtual human and key presentation areas. Lighting can also be used to simulate different times of day or specific weather effects to enhance the scene's realism and immersion. Through the above content, a customized virtual meeting scene that meets the meeting needs can be created, providing participants with an immersive online meeting environment.

[0062] As an optional embodiment, placing the virtual digital human in a virtual meeting scene further includes: identifying objects in the virtual meeting scene and determining a target position, wherein the target position is the position where the virtual digital human is placed; placing the virtual digital human at the target position; and adjusting the movement and direction of the virtual digital human at the target position.

[0063] Optionally, the customized virtual digital human is integrated with the virtual conference scene. It is necessary to ensure the coordination of the virtual digital human in the scene. At the same time, there are multiple virtual objects in the scene, and it is necessary to avoid overlap or penetration of the digital human and the objects. Therefore, it is necessary to determine a target position in the scene to place the virtual digital human. At the same time, the movement and direction of the virtual digital human can be adaptively adjusted to improve the adaptability of the virtual digital human and the virtual conference scene, thereby improving the experience of the participants.

[0064] For example, advanced computer vision algorithms can be used to identify and classify all objects in a virtual meeting scene, including but not limited to desks, chairs, doors and windows, decorations, and presentation equipment. Object identification helps understand the spatial layout of the scene and provides a basis for subsequent virtual human placement. Secondly, the ideal position of the virtual human within the scene can be determined based on the nature and purpose of the meeting. For example, if the virtual human is the presenter, it should be placed at the podium or center stage; if it is the receptionist, it should be near the entrance or reception area. Finally, the potential movement routes and gathering points of participants in the virtual meeting can be analyzed. The target position should make the virtual human easy to spot and facilitate interaction, without obstructing key visual fields or interfering with main activity areas. It is also necessary to consider the perspective of most participants, ensuring that the virtual human is in a focal point or easily noticed area, while avoiding angles and positions that may cause visual fatigue or discomfort.

[0065] Furthermore, scene editing tools can be used to precisely place the virtual human at a predetermined target location, adjusting its height, depth, and width coordinates to ensure proper alignment with objects in the scene. Consider the virtual human's potential for interaction with surrounding objects, such as adjusting its distance from the table to ensure it can sit naturally or stand in front of the podium without obstructing the content behind it. Determine the virtual human's primary facing direction, typically toward the majority of attendees, to enhance its visibility and interactivity. Fine-tune the virtual human's posture, such as standing, sitting, or specific presentation poses, to ensure its appearance is natural and appropriate for the meeting context. Preset a series of appropriate action sequences based on the virtual human's role in the meeting. For example, a moderator might include a welcoming gesture or pointing in different directions, while a speaker should include gestures and head movements during a presentation. By doing so, a metaverse meeting environment can be created for participants that is both realistic, functional, and interactive.

[0066] As an optional embodiment, controlling the virtual digital human to receive and reply to information input based on the target account includes: when the information input into the target account is voice information, controlling the virtual digital human to convert the voice information into text information; controlling the virtual digital human to query target data related to the text information from a preset corpus; and controlling the virtual digital human to reply based on the target data.

[0067] Optionally, in the Metaverse system, participants can send voice or text messages to virtual digital humans through the conference platform to ask questions or provide commands. Upon receiving a text message, the virtual human can directly query and respond to a pre-set corpus. However, upon receiving a voice message, the virtual human must first use a speech recognition engine to convert the voice message into text before querying the corpus based on the text message. The virtual human's ability to receive and respond to participant messages enables interaction between the virtual and the real world, enhancing the interactivity and participation of the meeting and improving the user experience.

[0068] For example, the Metaverse system can integrate a high-performance speech recognition engine to ensure that the virtual digital human can accurately recognize the voice information input by the target account. Taking into account the possible noise interference in the meeting environment, the noise resistance and multi-language support of speech recognition can be optimized to ensure that voice commands or questions can be smoothly recognized in various situations. The speech recognition engine can convert the received voice information into text information in real time, facilitating subsequent natural language processing and data analysis. The converted text information is recorded to provide data support for the subsequent analysis, summary and playback of the meeting. Furthermore, a comprehensive corpus can be established, which contains meeting-related subject knowledge, frequently asked questions by participants, historical information about the company or organization, industry terminology, and meeting procedures and rules. The corpus should be updated regularly to reflect the latest meeting information and industry trends to ensure that the virtual digital human can provide the latest and most accurate responses.

[0069] The Metaverse system can also integrate natural language understanding technology to analyze the intent, entities, and context within text messages, thereby determining the specific requirements of the query corpus. Based on the analyzed requirements, the corpus can be quickly searched for target data matching the text messages, such as answers, examples, data, or guidance. Leveraging text generation technology, the query target data can be converted into natural, fluent responses that fit the meeting context, enhancing the participant's interactive experience and information acquisition efficiency. Virtual digital humans can also be controlled to respond via voice, text, or combined with video presentations, selecting the optimal expression method based on participant preferences and scenario requirements. Voice responses can be converted using text-to-speech (TTS) to ensure clarity and naturalness, while video presentations can provide intuitive visual aids to explain complex information. Emotional intelligence can also be incorporated, enabling the virtual digital human to adjust the tone and content of its responses based on the participant's mood and tone. For example, it can provide more detailed explanations for questionable questions and more enthusiastic responses to positive interactions. Leveraging participant interaction data, responses can be personalized, providing more attentive and customized service based on their preferences and needs.

[0070] If a participant's question falls outside the scope of the corpus, the virtual human should be able to intelligently guide the participant, such as prompting them to describe their question more specifically. By integrating machine learning models, such as deep learning technology, the Metaverse system enables the virtual human to learn from each interaction, improving the accuracy and intelligence of its understanding and responses. Through this, the virtual human can provide rich and accurate information services, enhancing meeting interactivity, information delivery efficiency, and the overall participant experience.

[0071] As an optional embodiment, feedback information based on the target account input is received, wherein the feedback information represents feedback information of the reply to the virtual digital person; and the corpus is adjusted based on the feedback information.

[0072] Optionally, based on the virtual digital person's response content, participants can provide feedback and evaluation on the response content, including scoring or feedback. Based on this feedback content, the metaverse system can adjust the corpus to make the virtual digital person's response more accurate.

[0073] For example, a feedback collection mechanism can be integrated into the conference platform, allowing participants to provide feedback through various channels, including but not limited to feedback buttons within the conference interface, "unsatisfied" options in voice commands, email feedback, or social media comments. Natural language processing techniques, such as sentiment analysis, topic modeling, and entity recognition, can be used to structure the collected feedback and transform it into analyzable data. Comments on the quality of the virtual human's responses, content accuracy, and communication experience can be screened as the primary basis for adjusting the corpus. This screened feedback can then be categorized into categories such as technical issues, information needs, and user experience to enable targeted corpus adjustments. Feedback processing can also be prioritized based on the urgency of the issue, its scope of impact, and the frequency of participant feedback. Information in the corpus can be promptly updated and supplemented to address any errors or missing information identified in feedback, ensuring that the virtual human can provide accurate and comprehensive responses. Real-time updates are necessary to ensure timely and professional responses to industry trends, the latest knowledge related to the conference theme, and specific requests from participants. Alternatively, feedback can be analyzed for communication breakdowns, identifying bottlenecks or misunderstandings in the conversation process. This can be used to optimize conversational scenarios and question-solving algorithms, improving the efficiency of communication between the virtual human and attendees. Consider adding conversational guides or example questions to help attendees more accurately express their needs or questions, leading to more effective responses. Based on attendee emotional feedback, the tone and emotional expression of responses in the corpus can be adjusted to make the virtual human's interactions more humane. Emotional intelligence can be enhanced by adding positive emotional vocabulary, providing more thoughtful response suggestions, or optimizing the process for handling negative feedback.

[0074] Furthermore, the collected feedback information is converted into training data to improve the virtual digital human's natural language processing model and conversational strategies. Positive feedback can be used as a reward signal for model optimization, while negative feedback can be used as a penalty signal to guide the iteration direction of the machine learning algorithm. By establishing an effective feedback collection mechanism, analyzing participants' true feelings about the virtual digital human's responses, and making targeted adjustments and optimizations to the corpus based on this, the quality of information exchange and user experience in virtual meetings can be significantly improved.

[0075] As an optional embodiment, controlling a virtual digital human to conduct an online meeting in a virtual meeting scene according to the meeting process includes: setting actions for the virtual digital human corresponding to N links in the meeting process, where N is a positive integer; and controlling the virtual digital human to perform corresponding actions in the virtual meeting scene according to the meeting process.

[0076] Optionally, in a virtual meeting, each session has its own specific purpose and atmosphere. Setting specific actions for the virtual digital human, such as the welcome gesture at the opening, body language during the speech, and facial expressions when listening and answering in the question-and-answer session, can make participants feel more real and involved, thereby enhancing the immersion and appeal of the entire meeting.

[0077] For example, a meeting process can be broken down into N specific segments, each corresponding to a key event in the meeting, such as opening remarks, keynote speeches, panel discussions, question-and-answer sessions, and closing remarks. For each segment, the virtual human can be assigned specific actions. For example, during the opening remarks, the virtual human might be required to make a welcoming gesture, smile, and wave to the audience. During the keynote speech, the virtual human might be required to demonstrate specific gestures, change facial expressions to match the speech content, and interact with virtual presentation equipment. Furthermore, a detailed animation script can be designed for each segment, including parameters such as the sequence, duration, intensity, direction, and target location of the action. The animation script should also consider the coherence and naturalness of the action, avoiding abrupt transitions and ensuring that each movement of the virtual human is smooth and natural. Based on virtual reality technology, a virtual human action library can be constructed containing a variety of predefined actions, covering gestures, expressions, body language, and interactive actions for specific scenarios. This action library can be continuously updated and enriched to adapt to different types of meeting processes and the needs of participants.

[0078] Furthermore, motion capture technology and machine learning algorithms can be used to map the action instructions in the designed animation script to the virtual digital human, enabling it to automatically switch and execute corresponding actions according to the different meeting processes, and to adjust the timing and method of action execution in real time according to dynamic changes in the virtual meeting scene (such as the location of participants and the speaker's emotional changes). Advanced animation control algorithms can also be developed or integrated to ensure the accuracy and naturalness of the virtual digital human's actions. The control algorithm can also have a fault-tolerant mechanism, which can automatically adjust or compensate when network delays or other technical problems affect the execution of actions, thereby maintaining the smoothness of the meeting.

[0079] The virtual human can also be given environmental awareness, dynamically adjusting its movements and tone based on real-time changes in the virtual meeting scene, such as participants' facial expressions and the tone of voice when asking questions. This allows for a more advanced interactive experience, ensuring that the virtual human's movements are coordinated with other elements in the virtual meeting scene (such as background music, lighting changes, and the movement of virtual objects), enhancing the overall immersiveness of the scene. The virtual human's movement settings can also be dynamically adjusted based on its role changes in the meeting, such as transitioning from host to speaker, ensuring that each role has a corresponding natural behavior pattern. Through the above steps, the virtual human can naturally and accurately execute the corresponding actions of N links in the virtual meeting scene according to the meeting process, providing participants with an immersive and highly interactive meeting experience.

[0080] The virtual conference method provided in the embodiment of the present application receives a virtual conference request, wherein the virtual conference request includes conference requirements and conference procedures; based on the virtual conference request, creates a virtual digital human and a virtual conference scene and places the virtual digital human in the virtual conference scene; controls the virtual digital human to conduct an online conference in accordance with the conference procedures in the virtual conference scene; and during the online conference, controls the virtual digital human to respond to information input based on the target account. This solves the problem in the related art that participants in virtual digital human conferences have low participation, insufficient connection, and poor user experience. This achieves the purpose of closely connecting the virtual digital human and the participants, thereby achieving the technical effect of improving user experience.

[0081] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0082] Example 2

[0083] The embodiment of the present application further provides a virtual conference device. It should be noted that the virtual conference device of the embodiment of the present application can be used to execute the virtual conference method provided in the embodiment of the present application. The virtual conference device provided in the embodiment of the present application is introduced below.

[0084] According to an embodiment of the present application, a device for implementing the above-mentioned virtual conference method is also provided. Figure 3 As shown, the device includes: a receiving module 301, a creating module 302, a first control module 303 and a second control module 304. The virtual conference device is described below.

[0085] The receiving module 301 is configured to receive a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures;

[0086] The creation module 302 is connected to the receiving module 301 and is used to create a virtual digital human and a virtual meeting scene based on the virtual meeting request and place the virtual digital human in the virtual meeting scene;

[0087] The first control module 303 is connected to the creation module 302 and is used to control the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process;

[0088] The second control module 304 is connected to the first control module 303 and is used to control the virtual digital human to respond to information input based on the target account during the online meeting.

[0089] Optionally, in the virtual conference device provided in the embodiment of the present application, the creation module is used to create a virtual digital human based on a virtual conference request, including: a first acquisition unit, used to obtain a virtual digital human template; a first adjustment unit, used to adjust the appearance, sound and action mode of the virtual digital human template based on the conference requirements to obtain a virtual digital human.

[0090] Optionally, in the virtual conference device provided in the embodiment of the present application, the creation module is used to create a virtual conference scene based on a virtual conference request, including: a first determination unit, used to determine the virtual conference scene type based on the conference requirements; a second determination unit, used to determine the virtual conference scene template based on the virtual conference scene type; a third determination unit, used to determine the size of the virtual digital human; and a second adjustment unit, used to adjust the size of the virtual conference scene template and the material and lighting in the virtual conference scene template based on the conference requirements and the size of the virtual digital human to obtain the virtual conference scene.

[0091] Optionally, in the virtual conference device provided in the embodiment of the present application, the creation module is used to place the virtual digital human in the virtual conference scene, and also includes: a fourth determination unit, used to identify objects in the virtual conference scene and determine the target position, wherein the target position is the position where the virtual digital human is placed; a placement unit, used to place the virtual digital human at the target position; and a third adjustment unit, used to adjust the movement and direction of the virtual digital human at the target position.

[0092] Optionally, in the virtual conference device provided in the embodiment of the present application, the second control module is used to control the virtual digital human to respond to information received based on the target account input, including: a first control unit, used to control the virtual digital human to convert the voice information into text information when the information input into the target account is voice information; a second control unit, used to control the virtual digital human to query target data related to the text information from a preset corpus; and a third control unit, used to control the virtual digital human to respond based on the target data.

[0093] Optionally, the virtual conference device provided in the embodiment of the present application is further used to receive feedback information based on the input of the target account, wherein the feedback information represents feedback information of the reply to the virtual digital person; and adjust the corpus based on the feedback information.

[0094] Optionally, in the virtual conference device provided in the embodiment of the present application, the first control module is used to control the virtual digital person to conduct an online meeting in the virtual conference scene according to the conference process, including: a setting unit, used to set actions for the virtual digital person corresponding to N links in the conference process, where N is a positive integer; a fourth control unit, used to control the virtual digital person to perform corresponding actions in the virtual conference scene according to the conference process.

[0095] The virtual conference device provided in the embodiment of the present application receives a virtual conference request, wherein the virtual conference request includes conference requirements and conference procedures; based on the virtual conference request, creates a virtual digital human and a virtual conference scene and places the virtual digital human in the virtual conference scene; controls the virtual digital human to conduct an online meeting in the virtual conference scene according to the conference procedures; and during the online meeting, controls the virtual digital human to respond to information input based on the target account. This solves the problem in the related art that participants in virtual digital human conferences have low participation, insufficient connection, and poor user experience. This achieves the purpose of closely connecting the virtual digital human and the participants, thereby achieving the technical effect of improving user experience.

[0096] It should be noted that the receiving module 301, the creating module 302, the first control module 303, and the second control module 304 correspond to steps S201 to S204 in Example 1. The examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above-mentioned modules can also be run as part of the device in the computer terminal 10 provided in Example 1.

[0097] Example 3

[0098] An embodiment of the present application may provide an electronic device, Figure 4 This is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 Only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0099] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0100] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receive a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures; based on the virtual meeting request, create a virtual digital person and a virtual meeting scene and place the virtual digital person in the virtual meeting scene; control the virtual digital person to conduct an online meeting in the virtual meeting scene according to the meeting procedure; during the online meeting, control the virtual digital person to receive information input based on the target account and respond.

[0101] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: creating a virtual digital human based on the virtual meeting request, including: obtaining a virtual digital human template; adjusting the appearance, sound and movement mode of the virtual digital human template based on the meeting requirements to obtain a virtual digital human.

[0102] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: creating a virtual meeting scene based on the virtual meeting request, including: determining the type of virtual meeting scene based on the meeting requirements; determining the virtual meeting scene template based on the virtual meeting scene type; determining the size of the virtual digital human; adjusting the size of the virtual meeting scene template and the materials and lighting in the virtual meeting scene template based on the meeting requirements and the size of the virtual digital human to obtain the virtual meeting scene.

[0103] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: placing the virtual digital human in the virtual meeting scene, and also including: identifying objects in the virtual meeting scene and determining the target position, where the target position is the position where the virtual digital human is placed; placing the virtual digital human at the target position; and adjusting the movement and direction of the virtual digital human at the target position.

[0104] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: control the virtual digital human to receive and reply to information based on the input of the target account, including: when the information input of the target account is voice information, control the virtual digital human to convert the voice information into text information; control the virtual digital human to query target data related to the text information from a preset corpus; and control the virtual digital human to reply based on the target data.

[0105] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: receiving feedback information based on the input of the target account, wherein the feedback information represents feedback information of the reply to the virtual digital person; and adjusting the corpus based on the feedback information.

[0106] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: controlling the virtual digital person to conduct an online meeting in a virtual meeting scene according to the meeting process, including: setting actions for the virtual digital person corresponding to N links in the meeting process, where N is a positive integer; controlling the virtual digital person to perform corresponding actions in the virtual meeting scene according to the meeting process.

[0107] The embodiment of the present application provides a virtual conference method. The method comprises receiving a virtual conference request, wherein the virtual conference request includes conference requirements and conference procedures; creating a virtual digital person and a virtual conference scene based on the virtual conference request and placing the virtual digital person in the virtual conference scene; controlling the virtual digital person to conduct an online conference in accordance with the conference procedures in the virtual conference scene; and controlling the virtual digital person to respond to information input based on a target account during the online conference. This achieves a close connection between the virtual digital person and the participants, thereby achieving the technical effect of improving the user experience and further resolving the current technical problem of low participant participation and insufficient connection in virtual digital person meetings, resulting in a poor user experience.

[0108] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 4 Different configurations shown.

[0109] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0110] Example 4

[0111] The embodiment of the present application further provides a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by any one of the virtual conference methods provided in the above embodiment 1.

[0112] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0113] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: receiving a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures; based on the virtual meeting request, creating a virtual digital person and a virtual meeting scene and placing the virtual digital person in the virtual meeting scene; controlling the virtual digital person to conduct an online meeting in the virtual meeting scene according to the meeting procedure; during the online meeting, controlling the virtual digital person to receive information input based on the target account and respond.

[0114] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: creating a virtual digital human based on a virtual meeting request, including: obtaining a virtual digital human template; adjusting the appearance, sound, and motion mode of the virtual digital human template based on meeting requirements to obtain a virtual digital human.

[0115] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: creating a virtual meeting scene based on a virtual meeting request, including: determining the type of virtual meeting scene based on meeting requirements; determining a virtual meeting scene template based on the virtual meeting scene type; determining the size of the virtual digital human; adjusting the size of the virtual meeting scene template and the materials and lighting in the virtual meeting scene template based on the meeting requirements and the size of the virtual digital human to obtain the virtual meeting scene.

[0116] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: placing a virtual digital human in a virtual meeting scene, further comprising: identifying objects in the virtual meeting scene and determining a target position, wherein the target position is the position where the virtual digital human is placed; placing the virtual digital human at the target position; and adjusting the movement and direction of the virtual digital human at the target position.

[0117] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: controlling the virtual digital human to receive information based on the target account input and respond, including: when the information input into the target account is voice information, controlling the virtual digital human to convert the voice information into text information; controlling the virtual digital human to query target data related to the text information from a preset corpus; and controlling the virtual digital human to respond based on the target data.

[0118] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: receiving feedback information based on the target account input, wherein the feedback information represents feedback information of a reply to the virtual digital person; and adjusting the corpus based on the feedback information.

[0119] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: controlling the virtual digital human to conduct an online meeting in a virtual meeting scene according to the meeting process, including: setting actions for the virtual digital human corresponding to N links in the meeting process, where N is a positive integer; controlling the virtual digital human to perform corresponding actions in the virtual meeting scene according to the meeting process.

[0120] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing any one of the steps of the above-mentioned virtual conference method.

[0121] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0122] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0124] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or 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 enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0127] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A virtual conference method, characterized in that: include: receiving a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures; Based on the virtual meeting request, creating a virtual digital person and a virtual meeting scene and placing the virtual digital person in the virtual meeting scene; Controlling the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process; During the online meeting, the virtual digital person is controlled to respond to information received based on the target account input.

2. The method according to claim 1, characterized in that Creating a virtual digital person based on the virtual meeting request, including: Obtain a virtual digital human template; Based on the meeting requirements, the appearance, voice and action mode of the virtual digital human template are adjusted to obtain the virtual digital human.

3. The method according to claim 1, characterized in that Creating a virtual meeting scenario based on the virtual meeting request, including: Determine the type of virtual meeting scenario based on the meeting requirements; Determining a virtual conference scene template based on the virtual conference scene type; Determining the size of the virtual digital human; Based on the meeting requirements and the size of the virtual digital human, the size of the virtual meeting scene template and the materials and lighting in the virtual meeting scene template are adjusted to obtain the virtual meeting scene.

4. The method according to claim 1, wherein Placing the virtual digital human in the virtual conference scene further includes: Identify objects in the virtual conference scene and determine a target location, wherein the target location is the location where the virtual digital human is placed; placing the virtual digital human at the target location; At the target position, the movement and direction of the virtual digital human are adjusted.

5. The method according to claim 1, characterized in that The controlling the virtual digital human to receive a reply based on information input from the target account includes: In the case where the information input by the target account is voice information, controlling the virtual digital human to convert the voice information into text information; Controlling the virtual digital human to query target data related to the text information from a preset corpus; Based on the target data, the virtual digital human is controlled to respond.

6. The method according to claim 5, characterized in that Also includes: receiving feedback information input based on the target account, wherein the feedback information represents feedback information of a reply to the virtual digital person; Based on the feedback information, the corpus is adjusted.

7. The method according to claim 1, characterized in that Controlling the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process includes: Setting actions corresponding to N steps in the conference process for the virtual digital human, where N is a positive integer; The virtual digital human is controlled to perform corresponding actions in the virtual conference scene according to the conference process.

8. A virtual conference device, characterized in that: include: A receiving module, configured to receive a virtual meeting request, wherein the virtual meeting request includes meeting requirements and meeting procedures; A creation module, configured to create a virtual digital human and a virtual meeting scene based on the virtual meeting request and place the virtual digital human in the virtual meeting scene; A first control module is used to control the virtual digital human to conduct an online meeting in the virtual meeting scene according to the meeting process; The second control module is used to control the virtual digital human to respond to information received based on the target account input during the online meeting.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the virtual conference method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor is used to run the program, wherein the program executes the virtual conference method described in any one of claims 1 to 7 when running.

11. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the virtual conference method according to any one of claims 1 to 7 are implemented.

Images