Conference playback method, device, equipment and medium

Abstract

The invention relates to the technical field of computers, in particular to a conference playback method and device, equipment and a medium. The method comprises the following steps: acquiring playback parameters carried in a received playback request by the electronic equipment; acquiring a model identifier of a character model selected by the participant and stored for the identifier of the participant, each operation record and occurrence time, generating a corresponding state change of the character model of the model identifier in the playback video at the corresponding occurrence time, and if the speaking content is stored for the identifier of the participant, executing the corresponding state change of the character model of the model identifier in the playback video. And if so, adding the audio of the speaking content in the playback video at the corresponding time. Therefore, when the demands of some participants are known, the playback videos corresponding to the participants are directly generated, and the audios of the speaking contents of the participants are added in the playback videos, so that the speaking of the participants, the state change of the character model selected by the participants and the like can be more focused, and the experience of the participants is improved. Conference content can be deeply understood and analyzed, and time cost is greatly saved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a conference playback method, device, equipment and medium. Background Art

[0002] With the rapid development of information technology, especially the popularization of the Internet and mobile communication technology, the traditional meeting model has begun to show its limitations. First, from the perspective of time and space, traditional meetings require all participants to gather at the same time and place, which undoubtedly increases the cost of organization and participation and limits the accessibility and flexibility of meetings. For multinational and cross-regional teams, this limitation is particularly prominent, which may not only lead to the absence of key people, but also consume a lot of resources and time due to travel arrangements. Secondly, in terms of recording and playback of meeting content, traditional technology has significant shortcomings. In the past, meeting records mainly relied on manual notes or recording equipment, which was not only inefficient, but also easy to miss important information.

[0003] Even with the introduction of playback audio and video recording technology, the entire conference process is often simply recorded in its entirety. This playback method is an inefficient and cumbersome experience for participants or conference subscribers who need to review the information of specific participants in the meeting. Participants or conference subscribers often need to spend a lot of time browsing the information related to the entire meeting to find the content they really care about, which not only wastes time, but also may reduce the efficiency of understanding and absorbing the content of the meeting. Summary of the invention

[0004] The embodiments of the present application provide a conference playback method, apparatus, device and medium to resolve the problem in the prior art that when there is a need to understand the information of a specific participant in the meeting, the entire conference information needs to be browsed, resulting in a waste of resources and reduced understanding of the meeting.

[0005] The present application provides a conference playback method, the method comprising:

[0006] Obtaining playback parameters carried in the received playback request; wherein the playback parameters include an identifier of at least one participant;

[0007] For at least one identified participant, obtain the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, add the video content of the character model with the model identification undergoing the corresponding state change at the occurrence time in the playback video based on the state change information and the occurrence time contained in the operation record; if the speech content is saved for the participant's identification, add the audio of the speech content at the corresponding time in the playback video based on the speech content and the speech time.

[0008] Furthermore, the method further comprises:

[0009] If the playback parameters include a connection identifier and a corresponding connection time, obtaining connection content saved for the connection identifier;

[0010] Generating a video corresponding to the connection content;

[0011] The video is added at the connection time of the playback video.

[0012] Further, the generating of the video corresponding to the connection content includes:

[0013] If the connection content is text, a preset number of frames of video containing the text are generated.

[0014] Further, the adding the audio of the speech content at the corresponding time in the playback video according to the speech content and the speech time includes:

[0015] If the playback parameters include a waveform of a timbre and / or a frequency of a tone selected respectively for the identification of at least one participant, the timbre and / or tone of the audio containing the speech content is adjusted to the timbre of the waveform and / or the tone of the frequency, and the adjusted audio is added to the time corresponding to the speech time in the playback video.

[0016] Furthermore, the method further comprises:

[0017] If the playback parameters include key information, obtaining the key information;

[0018] A preset marking operation is performed on a preset area of ​​the video frame containing the key information in the playback video.

[0019] Furthermore, the method further comprises:

[0020] If a summary generation request is received, the playback audio in the playback video is converted into text to obtain a target text, and the target text and preset prompt words for prompting summary generation are input into the large model to obtain the target summary output by the large model.

[0021] Furthermore, the step of inputting the target text into the large model and obtaining the target summary output by the large model includes:

[0022] If the target text exceeds a preset length, the target text is divided into a preset number of sub-texts, each sub-text is input into the large model respectively, a sub-summary output by the large model is obtained, and the sub-summaries are spliced ​​according to the order of each sub-text in the target text to obtain a target summary.

[0023] Furthermore, the method further comprises:

[0024] If a conference construction instruction carrying a model identifier and a spatial scene identifier is received, a metaverse spatial scene corresponding to the spatial scene identifier and a character model corresponding to the model identifier are constructed in the UI page, and the position corresponding to the model identifier in the conference construction instruction is obtained, the character model is added to the position in the metaverse spatial scene, and the modeling data of the metaverse spatial scene with the character model added is synchronized to the device of each participant, so that the device of each participant renders based on the modeling data and displays the metaverse spatial scene containing the character model.

[0025] Furthermore, the method further comprises:

[0026] If state change information is received from a device of any participant, the state change information including behavior change information, position change information, form change information and mood change information, then the state of the character model corresponding to the device of the participant is adjusted based on the state change information.

[0027] Furthermore, the method further comprises:

[0028] If audio and video data is received from a device of any participant, the audio and video data is preprocessed and the preprocessed audio and video data is synchronized to the device of each participant.

[0029] The present application also provides a conference playback device, the device comprising:

[0030] An acquisition module, configured to acquire playback parameters carried in the received playback request; wherein the playback parameters include an identifier of at least one participant;

[0031] A processing module is used to obtain, for at least one identified participant, the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, according to the state change information and the occurrence time contained in the operation record, add, at the said occurrence time in the playback video, the video content of the character model with the model identification undergoing the corresponding state change; if the speech content is saved for the participant's identification, then according to the speech content and the speech time, add the audio of the speech content at the corresponding time in the playback video.

[0032] Furthermore, the processing module is also used to obtain the connection content saved for the connection identifier if the playback parameters include the connection identifier and the corresponding connection time; generate a video corresponding to the connection content; and add the video at the connection time of the playback video.

[0033] Furthermore, the processing module is specifically configured to generate a preset number of frames of video containing the text if the connection content is text.

[0034] Furthermore, the processing module is specifically used to adjust the timbre and / or tone of the audio containing the speech content to the timbre of the waveform and / or the tone of the frequency if the playback parameters include the waveform of the timbre and / or the frequency of the tone selected respectively for the identification of at least one participant, and add the adjusted audio at the time corresponding to the speech time in the playback video.

[0035] Furthermore, the processing module is further configured to obtain key information if the playback parameters include key information; and perform a preset marking operation on a preset area of ​​the video frame containing the key information in the playback video.

[0036] Furthermore, the processing module is also used to, if a summary generation request is received, convert the playback audio in the playback video into text to obtain a target text, input the target text and preset prompt words for prompting summary generation into the large model, and obtain the target summary output by the large model.

[0037] Furthermore, the processing module is specifically used to divide the target text into a preset number of sub-texts if the target text exceeds a preset length, input each sub-text into the large model respectively, obtain the sub-summaries output by the large model, and splice the sub-summaries according to the order of each sub-text in the target text to obtain the target summary.

[0038] Furthermore, the processing module is also used to, if a conference construction instruction carrying a model identifier and a space scene identifier is received, construct a metaverse space scene corresponding to the space scene identifier and a character model corresponding to the model identifier in the UI page, obtain the position corresponding to the model identifier in the conference construction instruction, add the character model to the position in the metaverse space scene, and synchronize the modeling data of the metaverse space scene with the character model added to the device of each participant; so that the device of each participant renders based on the modeling data and displays the metaverse space scene containing the character model.

[0039] Furthermore, the processing module is also used to adjust the state of the character model corresponding to the device of any participant based on the state change information received from the device of any participant, the state change information including behavior change information, position change information, form change information and mood change information.

[0040] Furthermore, the processing module is also used to pre-process the audio and video data if the audio and video data is received from the device of any participant, and synchronize the pre-processed audio and video data to the device of each participant.

[0041] An embodiment of the present application further provides an electronic device, the electronic device comprising a processor, the processor being configured to implement the steps of any of the above-described conference playback methods when executing a computer program stored in a memory.

[0042] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the conference playback methods described above.

[0043] An embodiment of the present application further provides a computer program product, which includes: a computer program code, and when the computer program code is executed on a computer, the computer executes the steps of any of the above-mentioned conference playback methods.

[0044] Because in the embodiment of the present application, the electronic device obtains the playback parameters carried in the received playback request; wherein the playback parameters include the identifier of at least one participant; for each participant, the model identifier, each operation record and the occurrence time of the character model selected by the participant saved for the identifier of the participant are obtained, and the character model of the model identifier is generated in the playback video to perform a corresponding state change at the corresponding occurrence time, and, if the speech content is saved for the identifier of the participant, the audio of the speech content is added to the playback video at the corresponding time according to the speech content and the speech time. Therefore, when there is a need to understand the information of certain participants during the meeting, there is no need to spend time browsing the lengthy records of the entire meeting, but directly generate the playback video of the corresponding participant, and the audio of the speech content of the participant is added to the playback video, which can focus more on the speech of the participant, the state change of the character model selected by the participant, etc., which is helpful for in-depth understanding and analysis of the content of the meeting, and greatly saves time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A process diagram of a conference playback method provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the conference playback process provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a conference implementation process provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of the structure of a conference playback device provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application clearer, this application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the embodiments described in this application are only part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0052] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

[0053] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0054] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0055] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0057] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope disclosed in the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0058] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.

[0059] Before introducing the conference playback method provided by the embodiment of the present application, in order to facilitate understanding, the background technology of the embodiment of the present application is first introduced.

[0060] With the rapid development of information technology, especially the popularization of the Internet and mobile communication technology, the traditional meeting model has begun to show its limitations. First, from the perspective of time and space, traditional meetings require all participants to gather at the same time and place, which undoubtedly increases the cost of organization and participation and limits the accessibility and flexibility of meetings. For multinational and cross-regional teams, this limitation is particularly prominent, which may not only lead to the absence of key people, but also consume a lot of resources and time due to travel arrangements. Secondly, in terms of recording and playback of meeting content, traditional technology has significant shortcomings. In the past, meeting records mainly relied on manual notes or recording equipment, which was not only inefficient, but also easy to miss important information.

[0061] Even with the introduction of playback audio and video recording technology, the entire conference process is often simply recorded in its entirety. This playback method is an inefficient and cumbersome experience for participants or conference subscribers who need to review the information of specific participants in the meeting. Participants or conference subscribers often need to spend a lot of time browsing the information related to the entire meeting to find the content they really care about, which not only wastes time, but also may reduce the efficiency of understanding and absorbing the content of the meeting.

[0062] In view of this, the embodiments of the present application provide a conference playback method, device, equipment and medium. The conference playback method includes: an electronic device obtains playback parameters carried in a received playback request; wherein the playback parameters include the identifier of at least one participant; for each participant, the model identifier of the character model selected by the participant and saved for the identifier of the participant, each operation record and the occurrence time are obtained; for each operation record, according to the state change information and occurrence time corresponding to the operation record, the character model with the model identifier is generated in the playback video to perform a corresponding state change at the occurrence time, and if the speech content is saved for the identifier of the participant, then according to the speech content and the speech time, the audio of the speech content is added to the playback video at the corresponding time.

[0063] The following is a detailed description of the technical terms involved in this application:

[0064] 3D graphics engine: A software and hardware system used to create and render 3D graphics. It can handle various 3D graphics-related tasks such as 3D models, textures, lighting, shadows, physical simulations, and ultimately generate a visual 3D scene.

[0065] Real-time communication (RTC) technology allows any communication service between the sender and the receiver to occur almost simultaneously. Compared with general communication, RTC focuses more on real-time, and can transmit audio, video, data and other information in a very short time, thereby achieving real-time communication and interaction. It is suitable for large-scale, low-latency, point-to-point usage scenarios.

[0066] Automatic Speech Recognition (ASR): ASR converts text information in speech into computer-readable input information, such as keystrokes, binary codes, or character sequences, through signal processing combined with pattern recognition technology, thereby achieving human-computer interaction.

[0067] Natural Language Processing (NLP): NLP is a machine learning technology that enables computers to interpret, process and understand human language. It includes two core tasks: natural language understanding and natural language generation. The pre-trained language model is a natural language processing model.

[0068] Pre-trained language model: A pre-trained language model is a machine learning technology that learns the laws and semantic information of language by training on a large amount of data, and encodes this knowledge into a model that can be used in a variety of natural language processing tasks.

[0069] Embodiment 1:

[0070] Figure 1 A process diagram of a conference playback method provided in an embodiment of the present application, the process includes the following steps:

[0071] S101: Acquire playback parameters carried in a received playback request; wherein the playback parameters include an identifier of at least one participant.

[0072] The conference playback method provided in the embodiment of the present application is applied to an electronic device, which may be a smart device such as a PC or a server.

[0073] When a participant or conference subscriber wishes to review the conference content, he or she can select playback parameters on a designated interface on the device he or she is using or a pre-set device, and initiate a playback request by clicking a preset button such as "playback". After receiving the playback request, the electronic device can obtain the playback parameters carried in the received playback request. Among them, "conference subscriber" refers to a user who has subscribed to the conference content in advance so that he or she can listen to and access the conference and conference playback. It should be noted that a user with management authority decides whether to allow a user to subscribe to a conference and become a conference subscriber of the conference.

[0074] The playback parameters include at least one participant's ID, that is, when a participant or conference subscriber needs to review the information of a certain participant or several participants during the conference, he or she can select the ID of the participant to be reviewed through a designated interface on the device used by himself or a pre-set device. The ID of each participant is different, and the ID of the participant can be a user name, an email address, etc., to ensure that the electronic device can accurately determine the corresponding participant.

[0075] S102: For at least one identified participant, obtain the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, add the video content of the character model with the model identification undergoing the corresponding state change at the occurrence time in the playback video according to the state change information and the occurrence time contained in the operation record; if the speech content is saved for the participant's identification, add the audio of the speech content at the corresponding time in the playback video according to the speech content and the speech time.

[0076] In order to replay the meeting, the electronic device locally saves the model identification of the character model selected by the participant, each operation record of the participant and the corresponding occurrence time of each operation record for each participant in advance, wherein the model identification of the character model selected by the participant is saved for each participant's identification, each operation record of the participant and the corresponding occurrence time of each operation record can be recorded in the behavior operation record file, and the electronic device can determine the playback video of the corresponding state change of the character model selected by the participant based on the information recorded in the operation record file.

[0077] Specifically, the electronic device can obtain, for each participant, in the operation record file, the model identification of the character model selected by the participant with the identification, each operation record and the occurrence time, wherein each operation record includes the state change information of the character model; the state change information includes the information of behavior change, position change, form change, mood change, etc. Among them, the information of behavior change includes changes to actions such as handshake and applause; the information of position change is the position change of the participant in the corresponding metaverse space scene; the information of form change includes form change to sitting, standing, etc.; the information of mood change includes concentration, relaxation, etc. For each operation record, the electronic device can determine the state change information and the occurrence time contained in the operation record, wherein the occurrence time refers to the time when the corresponding state change occurs, and the electronic device can replay the video at the occurrence time, create the target character model of the character model with the model identification after the state change corresponding to the state change information, and keep the target character model after the state change in the replayed video before the next state change of the character model with the model identification.

[0078] Since in actual scenarios, participants will also make speeches during the meeting, in order to accurately and effectively playback, the electronic device also saves the speech content for different participant identifiers, wherein the correspondence between the participant identifier and the speech content can be recorded in the conference speech file. The speech content is the text data of the participant's speech during the meeting. If the electronic device saves the speech content for the participant's identifier, the speech time corresponding to the speech content is obtained, and the audio of the speech content is added at the time corresponding to the speech time in the playback video. In a possible implementation, the electronic device can play the speech content with a preset tone and timbre to obtain the audio of the speech content, and the speech time can be one or more of the start time of the speech, the end time of the speech, or the length of the speech.

[0079] During this process, the electronic device will ensure that the status changes and speech content corresponding to each operation record are added in the order of their actual occurrence time in the meeting. Whether it is a speech or presentation by a single participant, or an interactive discussion between multiple participants, it will be accurately integrated into the playback video according to the timeline.

[0080] The sorting method provided in the embodiment of the present application not only improves the logic and coherence of the playback, but also enables participants or conference subscribers to more easily track the progress of the meeting and review the discussion content of specific participants during the meeting. In addition, the generated playback video may also include additional features, such as timeline marking, to further improve the viewing experience and review efficiency of participants or conference subscribers.

[0081] Because in the embodiment of the present application, the electronic device obtains the playback parameters carried in the received playback request; wherein the playback parameters include the identifier of at least one participant; for each participant, the model identifier, each operation record and the occurrence time of the character model selected by the participant saved for the identifier of the participant are obtained, and the character model of the model identifier is generated in the playback video to perform a corresponding state change at the corresponding occurrence time, and, if the speech content is saved for the identifier of the participant, the audio of the speech content is added to the playback video at the corresponding time according to the speech content and the speech time. Therefore, when there is a need to understand the information of certain participants during the meeting, there is no need to spend time browsing the lengthy records of the entire meeting, but directly generate the playback video of the corresponding participant, and the audio of the speech content of the participant is added to the playback video, which can focus more on the speech of the participant, the state change of the character model selected by the participant, etc., which is helpful for in-depth understanding and analysis of the content of the meeting, and greatly saves time costs.

[0082] Embodiment 2:

[0083] In order to improve the conference playback quality, based on the above embodiment, in the embodiment of the present application, the method further includes:

[0084] If the playback parameters include a connection identifier and a corresponding connection time, obtaining connection content saved for the connection identifier;

[0085] Generating a video corresponding to the connection content;

[0086] The video is added at the connection time of the playback video.

[0087] In order to improve the quality of conference playback, the playback video generated by the electronic device may also include a video corresponding to the transition content, wherein the transition content may be an introduction to participants, an introduction to the conference, and the like.

[0088] Specifically, when initiating a playback request, a participant or conference subscriber may select a connection identifier containing specific connection content as part of the playback parameters. The connection identifier for each connection content is different. When the electronic device receives the playback parameters containing the connection identifier, the electronic device may obtain the connection identifier and the corresponding connection time contained in the playback parameters. The electronic device obtains the connection content saved for the connection identifier based on the correspondence between the identifier and the content saved in advance, and obtains the video corresponding to the connection content. In a possible implementation, the connection content may be in the form of a video, and the video corresponding to the connection content is directly obtained.

[0089] In order to effectively integrate the connection content into the playback video, the electronic device will add the video to the playback video at the connection time according to the connection time included in the playback parameters.

[0090] In order to improve the conference playback quality, based on the above embodiments, in the embodiment of the present application, the step of obtaining the video corresponding to the connection content includes:

[0091] If the connection content is text, a preset number of frames of video containing the text are generated.

[0092] In actual scenarios, the transition content may be text. In order to add the transition content in the form of text to the playback video, the electronic device may generate a video frame containing the text. In addition, considering that a single-frame transition text video frame may be difficult to view clearly during fast playback, the electronic device may also generate a preset number of repeated frames of the video frame according to actual needs to ensure that the transition content can be fully noticed and effectively read by participants or subscribers.

[0093] Embodiment 3:

[0094] In order to improve the quality of conference playback, based on the above embodiments, in the embodiment of the present application, the audio of the speech content is added to the playback video at the corresponding time according to the speech content and speech time, including:

[0095] If the playback parameters include a waveform of a timbre and / or a frequency of a tone selected respectively for the identification of at least one participant, the timbre and / or tone of the audio containing the speech content is adjusted to the timbre of the waveform and / or the tone of the frequency, and the adjusted audio is added to the time corresponding to the speech time in the playback video.

[0096] In order to improve the conference playback quality, the playback video generated by the electronic device can also generate audio that meets the needs of the participant or conference subscriber who initiates the playback request based on the needs of the participant or conference subscriber who initiates the playback request.

[0097] Specifically, when a participant or conference subscriber initiates a playback request, they can select a waveform and / or a frequency of a tone with a corresponding timbre for at least one participant's identifier, wherein timbre refers to the characteristics of the sound, which determines the quality and style of the sound. Tone refers to the height and frequency of the sound. A higher frequency produces a higher pitch, and a lower frequency produces a lower pitch. When a participant or conference subscriber initiates a playback request, they can select a waveform representing the timbre and a frequency representing the tone. Different waveforms will produce different timbres, and different tones have different frequencies. Different sounds can be generated by adjusting the waveform of the timbre and / or adjusting the frequency of the tone. If the playback request explicitly includes the waveform of the timbre and / or the frequency of the tone selected for the identifiers of these participants, the electronic device can obtain the target waveform of the timbre and / or the target frequency of the tone contained in the playback parameters.

[0098] The electronic device can obtain audio containing the speech content, and adjust the timbre and / or pitch in the audio to the timbre corresponding to the target waveform and / or the pitch corresponding to the target frequency included in the playback parameters, wherein, when the timbre is not adjusted, the timbre in the audio can be the timbre of the participant himself or a preset timbre, and when the pitch is not adjusted, the pitch in the audio can be the pitch of the participant himself or a preset pitch.

[0099] After acquiring the adjusted audio, the electronic device can add the audio at the time corresponding to the speaking time in the playback video.

[0100] The method provided in the embodiment of the present application ensures that the audio portion of the playback can be presented in a specified timbre and / or tone according to the preferences of the participants or conference subscribers, thereby providing a more personalized and immersive playback experience.

[0101] In the embodiment of the present application, the playback controller can obtain playback parameters and send control instructions to the spatial renderer, and the spatial renderer executes the playback of the spatial conference. Among them, the playback parameters may include: the identification of the participants described in the embodiment of the present application, the connection content of the conference transition, the playback speed, the adjustment settings based on the granularity of the participants (such as pitch, timbre), storage method and format, etc. The content generated by the spatial renderer can be displayed through the playback client, and a file of the corresponding format can be generated for persistent storage in a specified manner. Among them, carrying the identification of the corresponding participant in different playback requests can realize the conversion of the playback perspective of the corresponding participant.

[0102] Figure 2 A schematic diagram of the conference playback process provided in an embodiment of the present application.

[0103] Depend on Figure 2 It can be seen that the electronic device locally stores behavioral operation record files, conference speech audio clip data, participant identification and other data. The playback controller obtains the playback parameters and sends control instructions to the spatial renderer. The spatial renderer executes the playback of the spatial meeting and sends the playback video to the participant's device, and the playback video is persistently saved.

[0104] In the embodiment of the present application, the electronic device integrates the operation records and speech content of the participants during the meeting. At the same time, the playback video includes the information of at least one participant selected by the participant or the conference subscriber during the meeting, which is equivalent to replaying the meeting process from the perspective of the participant, that is, displaying it with the individual participant as the center. In addition, it also supports the output and storage of the entire meeting in the form of audio and video, which greatly enriches the content of the meeting record and provides strong support for subsequent meeting review, analysis and research.

[0105] Embodiment 4:

[0106] In order to improve the conference playback quality, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0107] If the playback parameters include key information, obtaining the key information;

[0108] A preset marking operation is performed on a preset area of ​​the video frame containing the key information in the playback video.

[0109] During the conference playback process, participants or conference subscribers who have playback requirements may need to view certain key information. In an embodiment of the present application, the electronic device can mark the video frames containing the key information in the playback video.

[0110] Specifically, when a participant or conference subscriber initiates a playback request, he or she can select the corresponding key information. If the playback request clearly includes the key information, the electronic device can obtain the key information included in the playback request. Then, the electronic device will convert the audio in the playback video into text, determine the key text containing the key information, and perform a preset marking operation on the video frame containing the key text in the playback video. Among them, the video frame containing the key text refers to the video frame that narrates the key text during playback. The preset marking operation can be to highlight the subtitle part or to highlight the video frame.

[0111] Embodiment 5:

[0112] In order to improve the efficiency of information acquisition and facilitate meeting review, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0113] If a summary generation request is received, the playback audio data in the playback video is converted into text to obtain a target text, and the target text and preset prompt words for prompting summary generation are input into the large model to obtain the target summary output by the large model.

[0114] When the electronic device receives a summary generation request, it can first use ASR technology to convert the text in the playback video to obtain the accurate target text. The obtained target text is then input into the large model, which, with its powerful natural language processing capabilities, can efficiently analyze and extract the core information, and finally output the target summary corresponding to the target text.

[0115] It should be noted that in order to achieve the generation of the target summary, the electronic device can also store preset prompt words locally, which are used to prompt the large model to generate the corresponding summary. The electronic device inputs the prompt words together with the target text into the large model, which can be updated through the capabilities of the large model to support the generation of flexible and controllable target summaries. The electronic device can generate minutes of meeting content containing the target summary. Among them, the electronic device can also provide a function of optional and configurable prompt words, which can obtain the prompt words carried in the playback request and input the prompt words into the large model together, so as to facilitate the adjustment and optimization of the content generated by the large model.

[0116] Metaverse applications in the auxiliary processing of conference content currently lack a complete and systematic processing model. This limits the processing efficiency of conference content and affects the final processing effect of conference content. The embodiment of this application uses large model technology to generate summaries of conference content. It can greatly improve the efficiency of subsequent processing, reduce the workload of manual processing, and enable participants to obtain the essence and key information of conference content more quickly.

[0117] Embodiment 6:

[0118] In order to improve the accuracy of summary generation, based on the above embodiments, in the embodiment of the present application, the step of inputting the target text into a large model and obtaining the target summary output by the large model includes:

[0119] If the target text exceeds a preset length, the target text is divided into a preset number of sub-texts, each sub-text is input into the large model respectively, a sub-summary output by the large model is obtained, and the sub-summaries are spliced ​​according to the order of each sub-text in the target text to obtain a target summary.

[0120] If the length of the target text exceeds the preset length, the accuracy of the summary determined by the large model may be low. In order to improve the accuracy of summary generation, the electronic device can divide the target text into a preset number of sub-texts. In one possible implementation, the electronic device can divide the total number of words in the target text by the preset number of segments, that is, the preset number described in the embodiment of the present application, to obtain the number of words that each sub-text should contain. According to the calculated number of words, the target text is evenly divided into a preset number of sub-texts. In another possible implementation, the electronic device can use punctuation marks (such as periods, question marks, exclamation marks, etc.) as segmentation points. Traverse the target text and find all punctuation positions. According to the position of the punctuation marks and the preset number of segments, that is, the preset number described in the embodiment of the present application, the target text is divided into corresponding sub-texts.

[0121] After obtaining each sub-text, the electronic device can input each sub-text into the large model to obtain the sub-summary corresponding to each sub-text output by the large model. In order to ensure the coherence and accuracy of the summary, the electronic device will sequentially stitch together the sub-summaries generated by these sub-texts according to their order in the original target text, and finally form a complete and accurate target summary.

[0122] The method provided in the embodiment of the present application supports situations where the context is processed beyond the single processing of a large model through automatic segmentation integration iteration, which not only improves the efficiency of summary generation, but also further enhances the accuracy and readability of the summary content.

[0123] Embodiment 7:

[0124] In order to accurately and effectively implement the conference, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0125] If a conference construction instruction carrying a model identifier and a spatial scene identifier is received, a metaverse spatial scene corresponding to the spatial scene identifier and a character model corresponding to the model identifier are constructed in the UI page, and the position corresponding to the model identifier in the conference construction instruction is obtained, the character model is added to the position in the metaverse spatial scene, and the modeling data of the metaverse spatial scene with the character model added is synchronized to the device of each participant, so that the device of each participant renders based on the modeling data and displays the metaverse spatial scene containing the character model.

[0126] In order to increase the participation in meetings, electronic devices can implement meetings based on the metaverse.

[0127] Specifically, if the electronic device receives a conference construction instruction carrying a model identifier and a space scene identifier, the model identifier and the space scene identifier carried in the received instruction can be obtained. In one possible implementation, only participants with management authority have the right to carry the space scene identifier in the instruction. The electronic device can obtain the corresponding metaverse space scene resources and the corresponding character model resources from the predefined resource library based on the received space scene identifier and model identifier. These resources may include 3D model files, texture maps, animation data, etc.

[0128] The electronic device can use the resources of the loaded metaverse space scene to build a virtual metaverse space scene on the UI page. This scene may be a conference room, an outdoor environment, or any other virtual space that meets the needs of the meeting. In addition, the electronic device can use the resources of the loaded character model to build a virtual character model, obtain the position corresponding to the character model in the meeting construction instruction, and add the constructed character model to the position in the metaverse space scene. Among them, the character model constructed by the electronic device may include features such as the appearance, movement, and expression of the character. Among them, the metaverse space scene constructed by the electronic device can also construct a metaverse space scene of a conference table with lighting corresponding to the lighting mode and corresponding physical materials according to whether the conference construction instruction carries the lighting mode and the corresponding physical material.

[0129] Among them, the electronic device can generate glb, fbx, usdz and other formats for different types of content and display terminals.

[0130] The electronic device packages the rendered modeling data of the metaverse space scene containing the character model and synchronizes it in real time to the devices of all participants and conference subscribers. After receiving the modeling data, the devices of the participants and conference subscribers will use their own graphics rendering engines to parse and render the data, and display the rendered metaverse space scene containing the corresponding character model.

[0131] The conference described in the embodiments of the present application can be implemented based on professional 3D graphics engines, including but not limited to Unity, Unreal Engine, and Web Graphics Library (WebGL) engine for Web browsers. Participants can participate in the conference through a variety of different types of participant devices, including but not limited to mobile phones, computers, and virtual reality (VR) devices.

[0132] Through the method provided in the embodiment of the present application, the electronic device can provide participants with a richer, interactive and immersive metaverse conference experience.

[0133] It should be noted that with the rapid advancement of communication technology and computer technology, global conference activities have generally shifted to remote online modes in recent years, effectively transcending the limitations of location and time. Metaverse, the crystallization of the interweaving of science and technology and social progress, is leading a new trend of integrating the virtual and real worlds. Its development process has leaped from the initial concept germination to a new stage with solid technology and rich scenes. However, although the current mainstream online conference system is convenient and efficient, it is difficult to completely restore the on-site atmosphere and deep sense of participation of traditional offline meetings, and the interactive experience is relatively rigid and limited. In contrast, although the Metaverse digital space application can give participants or conference subscribers a strong immersive experience and a realistic sense of the scene, it still needs to be strengthened in the comprehensive management of conference content, especially the completeness of conference auxiliary functions. Traditional conference systems mainly rely on voice and video communication, and have obvious shortcomings in providing immersive experience and rich interactivity. However, the Metaverse application lacks a systematic and complete process at the auxiliary processing level of conference content, and the efficiency of subsequent processing of the conference is insufficient, which in turn affects the final quality of the conference results. The method proposed in the embodiment of the present application not only deeply integrates the immersive experience and high sense of presence of the metaverse, but also carefully constructs a complete set of conference processing procedures and a powerful functional system, aiming to create a comprehensive conference solution for participants that integrates the metaverse space conference experience and all-round and efficient auxiliary processing functions.

[0134] Embodiment 8:

[0135] In order to accurately and effectively implement the conference, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0136] If state change information is received from a device of any participant, the state change information including behavior change information, position change information, form change information and mood change information, then the state of the character model corresponding to the device of the participant is adjusted based on the state change information.

[0137] In actual scenarios, participants may have the need to express changes in their status. When participants have the need to express changes in their status, they can select status change information on the preset page of the device they are using and click a preset button, such as the "Change" button. The electronic device can then receive status change information sent by the participant's device. Status change information includes information on behavior changes, position changes, form changes, mood changes, etc. Among them, information on behavior changes includes changes to actions such as handshakes and applause; information on position changes is the change in the position of the participant in the corresponding metaverse space scene; information on form changes includes changes to sitting still, standing, etc.; information on mood changes includes concentration, relaxation, etc.

[0138] When the electronic device receives status change information sent from the device of any participant, the electronic device can adjust the status of the character model corresponding to the model identifier selected by the participant based on the status change information. Specifically, the electronic device can save the resource of the model with the adjusted status for the character model, and build the character model with the adjusted status based on the resource to ensure that the character model can reflect the real situation of the participant in real time and accurately. This dynamic adjustment not only enhances the immersion and interactivity of the meeting, but also enables remote participants to feel the on-site atmosphere and the status changes of other participants more intuitively and realistically, thereby promoting more effective communication and collaboration.

[0139] The space synchronization and recording module of the electronic device can realize synchronization in conference-related activities when the character model of the participant enters the metaverse space scene. The synchronization in the conference-related activities described here includes: data synchronization, scene synchronization, interaction synchronization, etc., wherein data synchronization refers to real-time synchronization of the state change information of different character models in the metaverse space scene to ensure that all participants have the same experience in the metaverse space scene. Among them, the state change information can be included in the operation record, and the electronic device records the operation record containing the state change information for the corresponding participant's identification, and records the corresponding occurrence time of the operation record. Scene synchronization refers to real-time synchronization of scenes, props, characters and other elements in the metaverse to ensure that all participants and conference subscribers have a consistent visual experience in the metaverse; interaction synchronization refers to real-time synchronization of the interactive behaviors between the character models of different participants, such as greetings, handshakes, applause, etc., to ensure that all participants and conference subscribers have a consistent social experience in the metaverse.

[0140] At the same time, the electronic device combines the meeting data of each participant with the time of occurrence, generates corresponding data records, associates them with the participant's ID, and stores them as derived content of the spatial meeting. The storage method can use time series database + object storage, or use document database for storage, and supports data compression to build efficient indexes.

[0141] In view of the lack of complete conference content processing in the Metaverse application, the embodiment of the present application sets up a conference content auxiliary processing function to improve the capabilities of the Metaverse space application in the conference scenario and improve the efficiency of conference result output.

[0142] Common conference systems mainly rely on voice and video communication methods, but they are insufficient in terms of the sense of presence and interactivity experienced by participants. The embodiment of the present application uses metaverse space technology to create a highly realistic virtual conference scene. Participants can see each other in the virtual environment, as if they were there, enhancing the sense of presence. Combined with virtual reality technology, participants can explore the virtual conference space more freely and interact more naturally and intuitively, allowing participants to participate in the meeting more deeply.

[0143] Embodiment 9:

[0144] In order to accurately and effectively implement the conference, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0145] If audio and video data is received from a device of any participant, the audio and video data is preprocessed and the preprocessed audio and video data is synchronized to the devices of each participant and conference subscriber.

[0146] During the meeting, participants can express their opinions through audio and video data. At this time, the device of the participant will send the audio and video data to the electronic device, wherein the device of the participant can perform multimedia encoding compression on the audio content, and send the audio and video data to the electronic device through streaming and file bypass transmission. If the electronic device receives the audio and video data sent by the device of any participant, the electronic device can pre-process the audio and video data, wherein the pre-processing includes: encoding and noise reduction processing, wherein the audio acquisition and transmission module of the electronic device can collect the audio and video data of each participant in the metaverse space scene, and perform corresponding encoding and noise reduction processing. In addition, the electronic device synchronizes the pre-processed audio and video data to the device of each participant and conference subscriber in the form of RTC real-time streaming. Among them, the real-time communication and media processing of the electronic device can synchronize the pre-processed audio and video data to the device of each participant and conference subscriber.

[0147] After receiving the audio and video data, the devices of the participants and the conference subscribers perform corresponding decoding processing, and play the audio and display the video at the receiving end. Due to the jitter in data transmission, the audio and video receiving and display module also has the functions of jitter buffering and packet loss compensation to provide reliable audio and video playback quality.

[0148] The audio and video recording module of the electronic device records the occurrence time of each audio and video data, and saves it together with the audio and video data as supporting information. Usually, the audio stream data is saved as multiple single stream files according to the participants, or a single mixed stream file containing all the speakers' audio can be saved.

[0149] In actual meetings, participants often speak alternately. To reduce the size of the generated audio files and facilitate flexible processing of each speaker's content, the conference recording will only generate the corresponding audio clip file when a participant speaks, which is discontinuous data in time. At the same time, the audio clip file is embedded with related metadata, including the identifier of the participant corresponding to the data, for the use of subsequent conference assistance and other functions.

[0150] In the embodiment of the present application, after the meeting, the electronic device can use advanced post-routing processing technology to conduct in-depth analysis and multi-dimensional, multimedia processing of the meeting content. This processing method allows the meeting content to be converted into various forms of information (such as text records, audio summaries, video clips, etc.), thereby meeting different information presentation needs. More importantly, these processed meeting contents can be intelligently driven according to different business processing logics. This means that according to specific business needs, the system can automatically select the most appropriate processing method or output format. For example, when you need to quickly understand the main points of the meeting, the system may generate a concise text summary; when you need to review the details of the meeting, you can provide a complete video record. In addition, the relationship between meeting content and business routing can be flexible and changeable. One mode is "1 to 1", that is, specific meeting content directly corresponds to specific business processing logic to achieve accurate matching; the other mode is "1 to many", that is, the same meeting content can be processed into multiple forms or output to multiple business systems according to different business needs. This flexibility ensures that the meeting content can be fully utilized and provides strong support for various business activities of the enterprise.

[0151] Figure 3 A schematic diagram of a conference implementation process provided in an embodiment of the present application.

[0152] Electronic devices can construct metaverse space, which specifically includes space environment construction and space content presentation, wherein space environment construction refers to creating a metaverse space scene and adding character models to the metaverse space scene, and space content presentation refers to synchronizing the modeling data of the metaverse space scene with character models added to the devices of each participant. Real-time communication and media processing are also performed during the conference implementation process, which specifically includes an audio and video acquisition and transmission module and an audio and video reception and display module, wherein the audio and video acquisition and transmission module refers to the equipment of each participant collecting audio and video data and sending the audio and video data to the electronic device, and the audio and video reception and display module refers to the electronic device synchronizing the received audio and video data to the devices of other participants. The electronic device also performs auxiliary processing of the content of the meeting, which specifically includes the generation of meeting minutes and the routing of the meeting to the devices of other participants.

[0153] Embodiment 10:

[0154] Based on the same inventive concept, the embodiment of the present application provides a conference playback device. Figure 4 For a schematic diagram of the structure of a conference playback device provided in an embodiment of the present application, please refer to Figure 4 , the device comprises:

[0155] The acquisition module 401 is used to acquire the playback parameters carried in the received playback request; wherein the playback parameters include the identifier of at least one participant;

[0156] Processing module 402 is used to obtain, for at least one identified participant, the model identification of the character model selected by the identified participant, each operation record and the occurrence time saved for the participant's identification; for each operation record, according to the state change information and occurrence time contained in the operation record, add the video content of the character model with the model identification undergoing the corresponding state change at the occurrence time in the playback video; if the speech content is saved for the participant's identification, then according to the speech content and the speech time, add the audio of the speech content at the corresponding time in the playback video.

[0157] In a possible implementation, the processing module 402 is further used to obtain the connection content saved for the connection identifier if the playback parameters include a connection identifier and a corresponding connection time; generate a video corresponding to the connection content; and add the video at the connection time of the playback video.

[0158] In a possible implementation, the processing module 402 is specifically configured to generate a preset number of frames of video containing the text if the connection content is text.

[0159] In one possible implementation, the processing module 402 is specifically used to adjust the timbre and / or tone of the audio containing the speech content to the timbre of the waveform and / or the tone of the frequency if the playback parameters include a waveform of the timbre and / or a frequency of the tone selected for the identification of at least one participant, and add the adjusted audio to the time corresponding to the speech time in the playback video.

[0160] In a possible implementation, the processing module 402 is further configured to obtain key information if the playback parameters include key information; and perform a preset marking operation on a preset area of ​​the video frame containing the key information in the playback video.

[0161] In a possible implementation, the processing module 402 is further used to, if a summary generation request is received, convert the playback audio in the playback video into text to obtain a target text, input the target text and preset prompt words for prompting summary generation into the big model, and obtain the target summary output by the big model.

[0162] In a possible implementation, the processing module 402 is specifically used to divide the target text into a preset number of sub-texts if the target text exceeds a preset length, input each sub-text into the large model respectively, obtain the sub-summaries output by the large model, and splice the sub-summaries according to the order of each sub-text in the target text to obtain the target summary.

[0163] In one possible implementation, the processing module 402 is also used to, if a conference construction instruction carrying a model identifier and a spatial scene identifier is received, construct a metaverse spatial scene corresponding to the spatial scene identifier and a character model corresponding to the model identifier in the UI page, obtain the position corresponding to the model identifier in the conference construction instruction, add the character model to the position in the metaverse spatial scene, and synchronize the modeling data of the metaverse spatial scene with the character model added to the device of each participant, so that the device of each participant renders based on the modeling data and displays the metaverse spatial scene containing the character model.

[0164] In a possible implementation, the processing module 402 is also used to adjust the state of the character model corresponding to the device of any participant based on the state change information received from the device of the participant, where the state change information includes behavior change information, position change information, form change information and mood change information.

[0165] In a possible implementation, the processing module 402 is further configured to pre-process the audio and video data if audio and video data sent by a device of any participant is received, and synchronize the pre-processed audio and video data to the device of each participant.

[0166] Embodiment 11:

[0167] Based on the same inventive concept, an embodiment of the present application provides an electronic device, which can implement the steps of the conference playback method discussed above. Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, it includes: a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504;

[0168] The memory 503 stores a computer program. When the program is executed by the processor 501, the processor 501 performs the following steps:

[0169] Obtaining playback parameters carried in the received playback request; wherein the playback parameters include an identifier of at least one participant;

[0170] For at least one identified participant, obtain the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, add the video content of the character model with the model identification undergoing the corresponding state change at the occurrence time in the playback video based on the state change information and the occurrence time contained in the operation record; if the speech content is saved for the participant's identification, add the audio of the speech content at the corresponding time in the playback video based on the speech content and the speech time.

[0171] In a possible implementation, the method further includes:

[0172] If the playback parameters include a connection identifier and a corresponding connection time, obtaining connection content saved for the connection identifier;

[0173] Generating a video corresponding to the connection content;

[0174] The video is added at the connection time of the playback video.

[0175] In a possible implementation manner, generating a video corresponding to the connection content includes:

[0176] If the connection content is text, a preset number of frames of video containing the text are generated.

[0177] In a possible implementation, adding the audio of the speech content at a corresponding time in the playback video according to the speech content and the speech time includes:

[0178] If the playback parameters include a waveform of a timbre and / or a frequency of a tone selected respectively for the identification of at least one participant, the timbre and / or tone of the audio containing the speech content is adjusted to the timbre of the waveform and / or the tone of the frequency, and the adjusted audio is added to the time corresponding to the speech time in the playback video.

[0179] In a possible implementation, the method further includes:

[0180] If the playback parameters include key information, obtaining the key information;

[0181] A preset marking operation is performed on a preset area of ​​the video frame containing the key information in the playback video.

[0182] In a possible implementation, the method further includes:

[0183] If a summary generation request is received, the playback audio in the playback video is converted into text to obtain a target text, and the target text and preset prompt words for prompting summary generation are input into the large model to obtain the target summary output by the large model.

[0184] In a possible implementation, inputting the target text into a large model to obtain a target summary output by the large model includes:

[0185] If the target text exceeds a preset length, the target text is divided into a preset number of sub-texts, each sub-text is input into the large model respectively, a sub-summary output by the large model is obtained, and the sub-summaries are spliced ​​according to the order of each sub-text in the target text to obtain a target summary.

[0186] In a possible implementation, the method further includes:

[0187] If a conference construction instruction carrying a model identifier and a spatial scene identifier is received, a metaverse spatial scene corresponding to the spatial scene identifier and a character model corresponding to the model identifier are constructed in the UI page, and the position corresponding to the model identifier in the conference construction instruction is obtained, the character model is added to the position in the metaverse spatial scene, and the modeling data of the metaverse spatial scene with the character model added is synchronized to the device of each participant, so that the device of each participant renders based on the modeling data and displays the metaverse spatial scene containing the character model.

[0188] In a possible implementation, the method further includes:

[0189] If state change information is received from a device of any participant, the state change information including behavior change information, position change information, form change information and mood change information, then the state of the character model corresponding to the device of the participant is adjusted based on the state change information.

[0190] In a possible implementation, the method further includes:

[0191] If audio and video data is received from a device of any participant, the audio and video data is preprocessed and the preprocessed audio and video data is synchronized to the device of each participant.

[0192] Since the principle of solving the problem by the above electronic device is similar to that of the conference playback method, the implementation of the above electronic device can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0193] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface 502 is used for communication between the above electronic device and other devices. The memory may include a random access memory (RAM) and may also include a non-volatile memory (NVM), such as at least one disk storage. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0194] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0195] Embodiment 12:

[0196] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, in which a computer program executable by a processor is stored. When the program runs on the processor, the processor executes any conference playback method discussed above. Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the conference playback method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0197] Based on the same inventive concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any conference playback method discussed above. Since the principle of solving the problem by the above computer program product is similar to any conference playback method discussed above, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.

[0198] Because in the embodiment of the present application, the electronic device obtains the playback parameters carried in the received playback request; wherein the playback parameters include the identifier of at least one participant; for each participant, the model identifier, each operation record and the occurrence time of the character model selected by the participant saved for the identifier of the participant are obtained, and the character model of the model identifier is generated in the playback video to perform a corresponding state change at the corresponding occurrence time, and, if the speech content is saved for the identifier of the participant, the audio of the speech content is added to the playback video at the corresponding time according to the speech content and the speech time. Therefore, when there is a need to understand the information of certain participants during the meeting, there is no need to spend time browsing the lengthy records of the entire meeting, but directly generate the playback video of the corresponding participant, and the audio of the speech content of the participant is added to the playback video, which can focus more on the speech of the participant, the state change of the character model selected by the participant, etc., which is helpful for in-depth understanding and analysis of the content of the meeting, and greatly saves time costs.

[0199] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0200] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0201] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0202] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0203] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A conference playback method, characterized in that: The method comprises: Obtaining playback parameters carried in the received playback request; wherein the playback parameters include an identifier of at least one participant; For at least one identified participant, obtain the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, add the video content of the character model with the model identification undergoing the corresponding state change at the occurrence time in the playback video based on the state change information and the occurrence time contained in the operation record; if the speech content is saved for the participant's identification, add the audio of the speech content at the corresponding time in the playback video based on the speech content and the speech time.

2. The method according to claim 1, characterized in that The method further comprises: If the playback parameters include a connection identifier and a corresponding connection time, obtaining connection content saved for the connection identifier; Generating a video corresponding to the connection content; The video is added at the connection time of the playback video.

3. The method according to claim 2, characterized in that The generating a video corresponding to the connection content includes: If the connection content is text, a preset number of frames of video containing the text are generated.

4. The method according to claim 1, characterized in that: The adding the audio of the speech content at the corresponding time in the playback video according to the speech content and the speech time includes: If the playback parameters include a waveform of a timbre and / or a frequency of a tone selected respectively for the identification of at least one participant, the timbre and / or tone of the audio containing the speech content is adjusted to the timbre of the waveform and / or the tone of the frequency, and the adjusted audio is added to the time corresponding to the speech time in the playback video.

5. The method according to claim 1, characterized in that The method further comprises: If the playback parameters include key information, obtaining the key information; A preset marking operation is performed on a preset area of ​​the video frame containing the key information in the playback video.

6. The method according to claim 1, characterized in that The method further comprises: If a summary generation request is received, the playback audio in the playback video is converted into text to obtain a target text, and the target text and preset prompt words for prompting summary generation are input into the large model to obtain the target summary output by the large model.

7. The method according to claim 6, characterized in that The step of inputting the target text into the large model and obtaining the target summary output by the large model includes: If the target text exceeds a preset length, the target text is divided into a preset number of sub-texts, each sub-text is input into the large model respectively, a sub-summary output by the large model is obtained, and the sub-summaries are spliced ​​according to the order of each sub-text in the target text to obtain a target summary.

8. The method according to claim 1, characterized in that The method further comprises: If a conference construction instruction carrying a model identifier and a spatial scene identifier is received, a metaverse spatial scene corresponding to the spatial scene identifier and a character model corresponding to the model identifier are constructed in the UI page, and the position corresponding to the model identifier in the conference construction instruction is obtained, the character model is added to the position in the metaverse spatial scene, and the modeling data of the metaverse spatial scene with the character model added is synchronized to the device of each participant, so that the device of each participant renders based on the modeling data and displays the metaverse spatial scene containing the character model.

9. The method according to claim 8, characterized in that The method further comprises: If state change information is received from a device of any participant, the state change information including behavior change information, position change information, form change information and mood change information, then the state of the character model corresponding to the device of the participant is adjusted based on the state change information.

10. The method according to claim 8, characterized in that The method further comprises: If audio and video data is received from a device of any participant, the audio and video data is preprocessed and the preprocessed audio and video data is synchronized to the device of each participant.

11. A conference playback device, characterized in that: The device comprises: An acquisition module, configured to acquire playback parameters carried in the received playback request; wherein the playback parameters include an identifier of at least one participant; A processing module is used to obtain, for at least one identified participant, the model identification of the character model selected by the identified participant and saved for the participant's identification, each operation record and the occurrence time; for each operation record, according to the state change information and the occurrence time contained in the operation record, add, at the said occurrence time in the playback video, the video content of the character model with the model identification undergoing the corresponding state change; if the speech content is saved for the participant's identification, then according to the speech content and the speech time, add the audio of the speech content at the corresponding time in the playback video.

12. The device according to claim 11, characterized in that The processing module is further used to obtain the connection content saved for the connection identifier if the playback parameters include the connection identifier and the corresponding connection time; generate a video corresponding to the connection content; and add the video at the connection time of the playback video.

13. The device according to claim 12, characterized in that The processing module is specifically used to generate a preset number of frames of video containing the text if the connection content is text.

14. The device according to claim 11, characterized in that The processing module is specifically used to adjust the timbre and / or tone of the audio containing the speech content to the timbre of the waveform and / or the tone of the frequency if the playback parameters include the waveform of the timbre and / or the frequency of the tone selected respectively for the identification of at least one participant, and add the adjusted audio to the time corresponding to the speech time in the playback video.

15. The device according to claim 11, characterized in that The processing module is further configured to obtain the key information if the playback parameters include the key information; and perform a preset marking operation on a preset area of ​​the video frame containing the key information in the playback video.

16. The device according to claim 11, characterized in that The processing module is further used to, if a summary generation request is received, convert the playback audio in the playback video into text to obtain a target text, input the target text and preset prompt words for prompting summary generation into the large model, and obtain the target summary output by the large model.

17. The device according to claim 16, characterized in that The processing module is specifically used to divide the target text into a preset number of sub-texts if the target text exceeds a preset length, input each sub-text into the large model respectively, obtain the sub-summaries output by the large model, and splice the sub-summaries according to the order of each sub-text in the target text to obtain the target summary.

18. The device according to claim 11, characterized in that The processing module is also used to, if receiving a conference construction instruction carrying a model identifier and a space scene identifier, construct a metaverse space scene corresponding to the space scene identifier and a character model corresponding to the model identifier in a UI page, obtain the position corresponding to the model identifier in the conference construction instruction, add the character model to the position in the metaverse space scene, and synchronize the modeling data of the metaverse space scene with the character model added to the device of each participant, so that the device of each participant can render based on the modeling data and display the metaverse space scene containing the character model.

19. The device according to claim 18, characterized in that The processing module is also used to adjust the state of the character model corresponding to the device of any participant based on the state change information if it receives state change information sent by the device of any participant, the state change information including behavior change information, position change information, form change information and mood change information.

20. The device according to claim 18, characterized in that The processing module is further configured to pre-process the audio and video data if the audio and video data is received from a device of any participant, and synchronize the pre-processed audio and video data to the device of each participant.

21. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is used to implement the steps of the conference playback method according to any one of claims 1 to 10 when executing a computer program stored in a memory.

22. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the conference playback method as described in any one of claims 1 to 10.

23. A computer program product, characterized in that The computer program product includes: a computer program code, and when the computer program code is executed on a computer, the computer executes the steps of the conference playback method according to any one of claims 1 to 10.

Images