Conference recording device, method, system and medium

Abstract

The embodiments of this specification provide a conference recording device, method, system and medium. The device includes an image processing unit, a storage unit and a control unit. The image processing unit is used to generate conference data and initial conference recording data. The storage unit is connected to the image processing unit and is used to store the initial conference recording data. The control unit is used to obtain the demand information for conference recording; based on the demand information, control the image processing unit to generate the initial conference recording data and obtain the storage information of the initial conference recording data; based on the storage information, obtain the initial conference recording data stored in the storage unit; based on the initial conference recording data, generate the target conference recording data and send it to the target terminal.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a conference recording device, method, system and medium. Background Art

[0002] With the continuous development of Internet technology, online office forms are also becoming more and more popular. Traditional online meetings are usually in the form of videos, which cannot meet the growing work needs. With the development of virtual reality related technologies, it is possible for multiple people to hold meetings in three-dimensional virtual scenes through virtual reality devices with virtual images. However, due to the different participation forms of virtual meetings and traditional online meetings, recording virtual meetings is different from directly saving related audio, video and other data in traditional online meetings.

[0003] Therefore, it is necessary to provide a conference recording device, method, system and medium to record a virtual conference, which can quickly and conveniently record the virtual conference according to the needs of the participants for later viewing. Summary of the invention

[0004] One of the embodiments of the present specification provides a conference recording device, which includes: an image processing unit, used to generate conference data and initial conference recording data; a storage unit, connected to the image processing unit, used to store the initial conference recording data; a control unit, communicatively connected to the image processing unit and the storage unit, used to: obtain demand information for conference recording; based on the demand information, control the image processing unit to generate the initial conference recording data and obtain storage information of the initial conference recording data; based on the storage information, obtain the initial conference recording data stored in the storage unit; based on the initial conference recording data, generate the target conference recording data and send it to the target terminal.

[0005] One of the embodiments of the present specification provides a conference recording method, including: obtaining demand information for conference recording; based on the demand information, controlling an image processing unit to generate initial conference recording data and obtaining storage information of the initial conference recording data; based on the storage information, obtaining the initial conference recording data stored in a storage unit; based on the initial conference recording data, generating the target conference recording data and sending it to a target terminal.

[0006] One of the embodiments of the present specification provides a conference recording system, including: a first acquisition module, used to obtain demand information for conference recording; a control module, used to control an image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data based on the demand information; a second acquisition module, used to obtain the initial conference recording data stored in a storage unit based on the storage information; and a generation module, used to generate the target conference recording data based on the initial conference recording data and send it to a target terminal.

[0007] One of the embodiments of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the conference recording method described in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of a conference recording device according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a conference recording method according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of determining a target rendering strategy according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of determining a target rendering strategy according to some embodiments of this specification;

[0013] Figure 5 It is a schematic diagram of a virtual meeting according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 It is a schematic diagram of a conference recording device according to some embodiments of this specification.

[0019] like Figure 1 As shown, the conference recording device 100 can be used to record target conference data of a virtual conference. The conference recording device 100 can include an image processing unit 110 , a storage unit 120 , and a control unit 130 .

[0020] The image processing unit 110 refers to a unit that generates conference data and initial conference recording data. The image processing unit may include a graphics processing unit (GPU). In some embodiments, for each participant, the image processing unit may generate conference data corresponding to the participant in real time based on the virtual conference space, the participant's virtual image, and display materials, and transmit the data to the participant's terminal so that the participant can conduct a real-time virtual conference with other participants in the virtual conference space. For more information about virtual conference spaces, participants' virtual images, and display materials, please refer to Figure 2 In some embodiments, the image processing unit may also generate initial conference recording data of the virtual conference. For more information on generating initial conference recording data, see Figure 2 and its related description.

[0021] The storage unit 120 can be used to store relevant data and / or instructions from the conference recording device 100 or other devices. For example, the storage unit 120 can be connected to the image processing unit 110 to store the initial conference recording data generated by the image processing unit. For another example, the storage unit 120 can also store relevant data of the virtual conference space, the virtual images corresponding to each participant, etc. The storage unit 120 may include one or more storage components, each of which may be an independent device or a part of other devices. In some embodiments, the storage device 120 may include a random access memory (RAM), a read-only memory (ROM), a large capacity storage, a removable memory, a volatile read-write memory, etc. or any combination thereof. Exemplarily, the large capacity storage may include a magnetic disk, an optical disk, a solid-state disk, etc. In some embodiments, the storage unit 120 may also store data and / or instructions used by the control unit 130 to execute or use to complete the exemplary method described in this specification.

[0022] The control unit 130 can process data and / or information obtained from other devices or other components of the conference recording device 100. For example, the control unit can obtain the demand information of the conference recording; based on the demand information, control the image processing unit to generate initial conference recording data and obtain the storage information of the initial conference recording data; based on the storage information, obtain the initial conference recording data stored in the storage unit; based on the initial conference recording data, generate the target conference recording data and send it to the target terminal. In some embodiments, the control unit 130 can be connected to the image processing unit 110 and the storage unit 120 in the conference recording device 100 to obtain relevant data or control other components. The control unit 130 can be connected to the image processing unit 110 and the storage unit 120. For example, the control unit 130 can control the image processing unit 110 to generate initial conference recording data. For another example, the control unit 130 can also obtain the initial conference recording data from the storage unit 120.

[0023] Figure 2 is an exemplary flow chart of a conference recording method according to some embodiments of this specification. In some embodiments, process 200 may be executed by a control unit. Figure 2 As shown, process 200 may include the following steps:

[0024] Step 210: Obtain the conference recording requirement information.

[0025] The demand information may refer to information indicating whether the meeting needs to be recorded. The meeting may include a virtual meeting. A virtual meeting may refer to a meeting in which participants participate in a three-dimensional virtual meeting space in the form of a real image or a virtual image through various devices (e.g., a VR (Virtual Reality) device, an MR (Mixed Reality) device, an XR (Extended Reality) device, etc.). Figure 5 As shown, the virtual meeting may be a meeting attended by virtual image 510, virtual image 520, and virtual image 530 in virtual meeting space 500. Each virtual image may represent a participant, and the virtual image and the virtual meeting space may both be in a three-dimensional space. At the same time, the appearance of the virtual image and the virtual meeting space may be determined by presetting.

[0026] The demand information may include the demand of the participants to record the meeting, and may also include the personnel information of the participants who need to record the meeting. The control unit may obtain the demand for recording the meeting initiated by the participants and the personnel information of the aforementioned participants. For example, the participants may initiate the demand for recording the virtual meeting by clicking on "meeting recording" on the virtual screen in the virtual meeting space through the virtual image in the virtual conference system. The control unit may obtain the demand for recording the virtual meeting and the personnel information of the participants who initiated the aforementioned demand.

[0027] In some embodiments, the demand information may also include the first position information of the virtual camera in the virtual conference space. The first position information may include coordinate information and angle information in the virtual conference space. For example, the first position information may include (10, 10, 15) and (30°, 20°, 60°), where (10, 10, 15) is the coordinate information of the virtual camera in the virtual conference space, and (30°, 20°, 60°) is the angle information of the virtual camera represented as the Euler angle in the ZXY sequence in the virtual conference space.

[0028] After the target object initiates a request to record the virtual meeting, a virtual camera may appear in the virtual meeting space. The target object may refer to the participant who initiates the request to record the meeting. The control unit may determine the position and angle of the virtual camera according to the position of the virtual image corresponding to the target object and a preset correspondence. In some embodiments, the target object may not adjust the virtual camera, and correspondingly, the control unit may directly determine the first position information based on the position and angle of the virtual camera. In some embodiments, the target object may also adjust the position of the virtual camera to determine the first position information. Figure 5As shown, the target object can drag the virtual camera 540 that appears through the corresponding virtual image to adjust its coordinates and the shooting angle of the lens for the virtual camera 550. The target object can click "Start Recording" on the virtual screen 560 (not shown) through the corresponding virtual image. The control unit can obtain the coordinate information and angle information of the virtual camera 550 in the virtual conference space 500 as the first position information of the virtual camera 550 in the virtual conference space 500.

[0029] It should be understood that the virtual camera is only an element in the virtual meeting space for the target object to directly adjust the shooting angle and position. The virtual camera is different from the image acquisition device in the real world and does not have a real shooting function. The control unit needs to process the relevant data of the meeting through the image processing unit to obtain the target meeting recording data.

[0030] In some embodiments of the present specification, the target object can drag the virtual camera through the virtual image to adjust the coordinates and angle of the virtual camera, so that the acquired conference recording screen can meet the relevant needs of the target object for conference recording.

[0031] In some embodiments, when recording a meeting, the control unit may monitor the third position information of the virtual image corresponding to the participant in the virtual meeting space. The third position information may include the angle information of the virtual image in the virtual meeting space and the coordinate information of multiple preset skeletal key points in the virtual image in the virtual meeting space. The aforementioned third position information can be obtained by the control unit by monitoring the virtual meeting in real time.

[0032] In some embodiments, when the coordinate information of the virtual image corresponding to the participant changes in the virtual conference space, the control unit can adjust the first position information of the virtual camera. The control unit can obtain new first position information through the first position determination model based on the third position information corresponding to each participant and the first position information. The input of the first position determination model may include the first position information and the third position information corresponding to each participant, and the output may include the new first position information. The first position determination model may include one or more of a deep neural network model and a support vector machine model.

[0033] The first position determination model can be obtained by training based on the first training set. The first training set may include multiple labeled training samples, wherein the training samples may include the sample first position information and multiple sample third position information in the sample virtual meeting space, and the labels of the training samples may include the new first position information of the samples. The training labels can be obtained through relevant data of historical virtual meetings, and the labels can be obtained by manually adjusting the sample first position information based on multiple sample third position information. The training samples are input into the initial first position determination model, and a loss function is constructed based on the output and labels of the initial first position determination model. The parameters of the aforementioned initial first position determination model are iteratively updated based on the loss function until the preset conditions are met, and a trained first position determination model is obtained. Among them, the preset conditions may include but are not limited to the convergence of the loss function, the training cycle reaching a threshold, etc.

[0034] In some embodiments of the present specification, the control unit can adjust the first position information of the virtual camera in real time to avoid blocking the front view of the virtual camera when the virtual image corresponding to the participant moves in the virtual space, thereby reducing the quality of the conference recording. It should be understood that when the movement of the virtual image does not cause the virtual camera to be blocked, the new first position information output by the first position determination model can be consistent with the first position information input into the first position determination model.

[0035] like Figure 5 As shown, when participating in a virtual meeting, participants can also present information on a virtual screen 560 in a virtual conference space 500. In some embodiments, when information needs to be presented on a virtual screen in a virtual conference space, the control unit can also determine new first position information based on the third position information corresponding to each participant, the first position information, the fourth position information of the virtual screen in the virtual conference space, and the virtual screen image. The fourth position information may include coordinate information of each vertex of the virtual screen in the virtual conference space and angle information of the virtual screen, and the fourth position information may be obtained by presetting. The virtual screen image can be obtained through conference data generated by the image processing unit. For more information about the image processing unit generating conference data, see Figure 1 and its related description.

[0036] In some embodiments, the control unit may process the third position information, the first position information, the fourth position information, and the virtual screen image corresponding to each participant based on the second position determination model to determine the new first position information. The input of the second position determination model may include the third position information, the first position information, the fourth position information, and the virtual screen image corresponding to each participant, and the output may include the new first position information. The second position determination model may include one or more of a deep neural network model and a support vector machine model.

[0037] The second position determination model can be obtained by training based on the second training set. The second training set may include multiple labeled training samples, wherein the training samples may include the sample first position information, the sample fourth position information, the sample screen image, and multiple sample third position information in the sample virtual meeting space, and the labels of the training samples may include the new first position information of the samples. The training labels can be obtained through the relevant data of the historical virtual meeting, and the labels can be obtained by manually adjusting the sample first position information based on the sample fourth position information, the sample screen image, and multiple sample third position information. The training samples are input into the initial second position determination model, and a loss function is constructed based on the output and labels of the aforementioned initial second position determination model. The parameters of the aforementioned initial second position determination model are iteratively updated based on the loss function until the preset conditions are met to obtain a trained second position determination model. Among them, the preset conditions may include but are not limited to the convergence of the loss function, the training cycle reaching a threshold, etc.

[0038] In some embodiments of this specification, the control unit can also adjust the first position information of the virtual camera in real time based on the fourth position information of the virtual screen and the virtual screen image, so as to avoid the virtual screen blocking the front view of the virtual camera and reducing the quality of the conference recording. At the same time, the second position determination model can also analyze and process the virtual screen image to determine the clarity of the virtual screen image, so as to adjust the first position information, so as to avoid the unclear content in the virtual screen caused by the virtual screen being too far away, and ensure the quality of the conference recording.

[0039] Step 220: Based on the demand information, control the image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data.

[0040] The initial conference recording data may refer to the data of the conference recording generated by the image processing unit. The initial conference recording data may be an image of the conference recording. The image processing unit may generate the initial conference recording data based on a preset setting. For example, the image processing unit generates an image of 60FPS (Frame Per Second) as the initial conference recording data.

[0041] In some embodiments, the control unit may perform modeling or use various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to analyze and process the demand information to control the image processing unit to generate initial conference recording data.

[0042] In some embodiments, the control unit may determine the second position information of the target rendering point in the image processing unit based on the first position information. The target rendering point may refer to the point where the image processing unit generates the initial conference recording data, and the second position information may be the position information of the target rendering point in the rendering space of the image processing unit. The second position information of the target rendering point is related to the first position information of the virtual camera. In some embodiments, the control unit may determine the second position information based on the first position information by a preset correspondence. For example, the virtual conference space may completely correspond to the rendering space, and correspondingly, the first position information of the virtual camera may be directly determined as the second position information of the target rendering point.

[0043] In some embodiments, the control unit may control the image processing unit to add a target rendering point and generate rendering data corresponding to the target rendering point based on the second position information.

[0044] It should be understood that the rendering space of the image processing unit may include other rendering points in addition to the target rendering point, and the position information of the other rendering points may correspond one to one with the third position information of the participants. The image processing unit may generate rendering data corresponding to each other rendering point as conference data corresponding to each participant, and send it to the corresponding terminal of the corresponding participant so that the corresponding participant can conduct a virtual meeting. The rendering data may include a rendered image. For example, when the rendering frame rate of the image processing unit is 60FPS, the image processing unit needs to generate 60 rendering images once per second at each rendering point. For each rendering point (e.g., target rendering point, other rendering points, etc.), the image processing unit may generate multiple images of different angles at the rendering point, and perform image registration and image fusion on the aforementioned multiple images of different angles, thereby generating a 360° image as a rendering image at the rendering point.

[0045] In some embodiments, the control unit may determine the rendering data corresponding to the target rendering point as the initial conference recording data. The image processing unit may store the initial conference recording data in the storage unit in chronological order.

[0046] In some embodiments, the control unit can also obtain storage information of the initial conference recording data. The storage information can be determined by pre-setting. For example, a folder can be generated in the storage unit corresponding to each minute of the meeting time, and the rendering order can be used to store the rendered images within the time period in the folder in sequence. The control unit can obtain the corresponding folder information as storage information. In some real-time examples, the control unit can also obtain storage information of other conference-related content. For example, the control unit can also obtain storage information of conference audio, presentation materials and other content, and the aforementioned storage information can be obtained by pre-setting.

[0047] Step 230: Based on the storage information, obtain the initial conference recording data stored in the storage unit.

[0048] In some embodiments, the control unit may obtain the initial conference recording data stored in the storage unit based on the storage information. The control unit may also obtain conference audio, presentation materials, etc. based on the storage information.

[0049] Step 240: Generate target conference recording data based on the initial conference recording data and send it to the target terminal.

[0050] The target conference recording data may refer to the finally generated conference recording data. The target conference recording data may be 360° video data.

[0051] In some embodiments, the control unit may synthesize the initial conference recording data, conference audio, presentation materials, etc. in chronological order to obtain the target conference recording data. The control unit may send the target conference recording video to the target terminal, where the target terminal may be the terminal used by the target object or a terminal designated by other target objects.

[0052] Some embodiments of this specification can generate target conference recording data corresponding to the first position information of the virtual camera, so as to facilitate the later viewing of the participants. At the same time, some embodiments of this specification can directly generate initial conference recording data in the image processing unit and store it in the storage unit, so as to generate target conference recording data, ensure the smoothness of the process operation, and avoid repeated operations in the central processing unit.

[0053] Figure 3 FIG. 300 is an exemplary flow chart of determining a target rendering strategy according to some embodiments of this specification. In some embodiments, process 300 may be executed by a control unit. Figure 3 As shown, process 300 may include the following steps:

[0054] Step 310, obtaining the meeting information of the virtual meeting and the personnel information of the participants.

[0055] Meeting information may refer to information related to a virtual meeting. Meeting information may include fourth location information of the display material in the virtual meeting space. Meeting information may also include specific information of the display material. For example, the type of display material, file size, etc. Meeting information may be determined in a variety of ways. For example, the control unit may determine the meeting information by presetting. For another example, the control unit may obtain specific information of the display material uploaded by the participant.

[0056] Personnel information refers to relevant information about participants in a virtual meeting. For example, personnel information may include one or more of a participant's virtual image, third-position information in the virtual meeting space, and a corresponding terminal. Personnel information may also be obtained in a variety of ways. For example, a participant's virtual image may be obtained by the participant pinching his or her face or selecting a preset option.

[0057] Step 320: Determine a target rendering strategy for controlling the image processing unit to generate initial conference recording data based on the conference information, the personnel information, and the first location information.

[0058] The target rendering strategy may refer to a strategy for the image processing unit to render the conference data and the initial conference recording data. The target rendering strategy may include the type of data that the image processing unit needs to generate. For example, the target rendering strategy may include the image processing unit rendering all rendering points at the same time to generate corresponding conference data and initial conference recording data.

[0059] The target rendering strategy may also include settings for the generated conference data and the initial conference recording data. For example, the target rendering strategy may include adjusting the rendering data corresponding to the initial conference recording data from 60 FPS to 40 FPS.

[0060] In some embodiments, the control unit can perform modeling or adopt various data analysis algorithms, such as regression analysis, discriminant analysis, etc., to analyze and process the target meeting information, personnel information and first location information, and obtain a target rendering strategy for controlling the image processing unit to generate initial meeting recording data.

[0061] In some embodiments, the control unit may also determine the first data volume of conference data generated by the image processing unit within the target time period and the second data volume of initial conference recording data generated by the image processing unit through a data volume determination model based on the first location information, personnel information, and conference information, wherein the data volume determination model is a machine learning model; based on the first data volume and the second data volume, a target rendering strategy is determined. For more information about the above embodiments, please refer to Figure 4 and its related description.

[0062] Step 330: Control the image processing unit to generate initial conference recording data based on the target rendering strategy.

[0063] In some embodiments of the present specification, the control unit determines a target rendering strategy through meeting information, personnel information, and first location information to avoid overloading of the image processing unit and to increase the service life of the image processing unit.

[0064] Figure 4 It is a schematic diagram of determining a target rendering strategy according to some embodiments of this specification.

[0065] In some embodiments, the control unit may determine the first data volume of conference data generated by the image processing unit within the target time period and the second data volume of initial conference recording data generated by the image processing unit through a data volume determination model based on the first location information, personnel information, and conference information. The data volume determination model may be a machine learning model. The target time period may be a preset time period. For example, the control unit may execute the aforementioned embodiment once every 1 minute, and correspondingly, the target time period may be within the next minute of the current time point.

[0066] like Figure 4 As shown, the control unit may construct graph structure data 440 based on the first location information 410 , the personnel information 420 , and the meeting information 430 .

[0067] Graph structured data can be composed of nodes and edges, edges connect nodes, and nodes and edges can have attributes.

[0068] In some embodiments, the nodes of the graph may correspond to the virtual camera and each participant. The node attributes may reflect the relevant characteristics of the corresponding node. For example, the node attributes corresponding to the virtual camera may include the first position information, and the node attributes corresponding to each participant may include the corresponding virtual image and the third position information. The virtual information and the third position information may be determined based on the personnel information.

[0069] In some embodiments, the control unit may connect nodes whose distance is less than a preset threshold to obtain an edge. The edge attribute may reflect relevant characteristics of the area between the two nodes. For example, the edge attribute may include the distance and direction between the two nodes. In some embodiments, the edge attribute may also include fourth position information of a virtual screen located between the two nodes. The fourth position information may be determined based on the conference information.

[0070] like Figure 4As shown, the data volume determination module 450 can process the graph structure data 440 to determine the first data volume 460 of the generated conference data and the second data volume 470 of the generated initial conference recording data within the target time period. The data volume determination module can be a graph neural network model (GNN). The data volume determination module can also be other graph models, such as a graph convolutional neural network model (GCNN), or add other processing layers to the graph neural network model, modify its processing method, etc.

[0071] The first data volume may refer to the data volume required by the image processing unit to generate conference data of the conference participants corresponding to the node within the target time period. The second data volume may refer to the data volume required by the image processing unit to generate initial conference recording data corresponding to the virtual camera within the target time period.

[0072] The data volume determination module can be trained and acquired through the third training set. The third training set may include multiple labeled training samples. The training sample may include sample graph structure data at the sample time point, and the training label may include the data volume of each sample node in the sample graph structure data within the sample time period. Among them, the sample time point is the starting time point of the sample time period. Both the training samples and the training labels can be obtained through historical meeting data. The training sample can be input into the initial data volume determination module, and the loss function can be constructed based on the output and label of the initial data volume determination module. The parameters of the initial data volume determination module are iteratively updated based on the loss function until the preset conditions are met, and a trained data volume determination module is obtained. Among them, the preset conditions may include but are not limited to the convergence of the loss function and the training cycle reaching a threshold.

[0073] like Figure 4 As shown, the control unit can determine the target rendering strategy 480 within the target time period based on the first data volume 460 and the second data volume 470. The control unit can determine the target rendering strategy according to a preset rule. For example, the preset rule can be that when the sum of the first data volume and the second data volume is greater than the preset first data volume threshold, the conference data related to the initial conference recording data within the target time period is stored, until the sum of the first data volume and the second data volume within a certain time period of the image processing unit is less than the preset second data volume threshold, the image processing unit generates the initial conference recording data corresponding to the aforementioned target time period based on the conference data related to the initial conference recording data, and stores it in the storage unit or adjusts the FPS of the initial conference recording data generated by the image processing unit; when the sum of the first data volume and the second data volume is not greater than the preset first data volume threshold, the image processing unit generates the conference data corresponding to the participants and the initial conference recording data corresponding to the virtual camera in real time. Wherein, the aforementioned first data volume threshold and the second data volume threshold can be related to the frequency of the image processing unit.

[0074] In some embodiments of the present specification, the control unit can determine the first data volume and the second data volume that the image processing unit needs to process within the target time period through a data volume determination module for evaluation, and further determine the target rendering strategy, thereby ensuring that the image processing unit can generate initial conference recording data as quickly as possible based on the conference data output without any lag.

[0075] Some embodiments of the present specification also provide a conference recording system, which may include a first acquisition module, a control module, a second acquisition module, and a generation module.

[0076] The first acquisition module can be used to obtain the demand information of the conference recording. For more information about obtaining demand information, please refer to Figure 2 In some embodiments, the demand information may include the first position information of the virtual camera in the virtual conference space. For more information about the demand information, see Figure 2 and its related description.

[0077] The control module can be used to control the image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data based on the demand information. For more information about generating and controlling the image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data, please refer to Figure 2 In some embodiments, the control module can also be used to determine the second position information of the target rendering point in the image processing unit based on the first position information; based on the second position information, control the image processing unit to add a target rendering point and generate rendering data corresponding to the target rendering point; and determine the rendering data as the initial meeting recording data. For more information about controlling the image processing unit to generate rendering data corresponding to the target rendering point and determining the rendering data as the initial meeting recording data, please refer to Figure 2 In some embodiments, the control module can also be used to obtain the meeting information of the virtual meeting and the personnel information of the participants; based on the meeting information, the personnel information and the first location information, determine the target rendering strategy for controlling the image processing unit to generate the initial meeting recording data; and control the image processing unit to generate the initial meeting recording data based on the target rendering strategy. For more information about generating the target rendering strategy and controlling the image processing unit to generate the initial meeting recording data based on the target rendering strategy, please refer to Figure 2 and its related description.

[0078] The second acquisition module can be used to obtain the initial conference recording data stored in the storage unit based on the storage information. For more information about obtaining the initial conference recording data, please refer to Figure 2 and its related description.

[0079] The generation module can be used to generate target conference recording data based on the initial conference recording data and send it to the target terminal. For more information about generating target conference recording data and sending it to the target terminal, please refer to Figure 2 and its related description.

[0080] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the conference recording method described in any embodiment of the present specification is implemented.

[0081] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0082] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0083] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0084] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0085] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0086] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0087] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A conference recording device, characterized in that: The device comprises: An image processing unit, used to generate conference data and initial conference recording data; A storage unit, connected to the image processing unit, and used to store the initial conference recording data; A control unit, which is in communication with the image processing unit and the storage unit, is used to: Acquiring conference recording requirement information, wherein the requirement information includes first position information of a virtual camera in a virtual conference space; Based on the demand information, controlling the image processing unit to generate the initial conference recording data and obtaining storage information of the initial conference recording data; Based on the storage information, obtaining the initial conference recording data stored in the storage unit; Based on the initial conference recording data, generating target conference recording data and sending the data to the target terminal; The control unit is also used for: Monitoring third position information of a virtual image corresponding to a conference participant in the virtual conference space, wherein the third position information includes angle information of the virtual image in the virtual conference space and coordinate information of a plurality of preset skeleton key points of the virtual image in the virtual conference space; When the third location information corresponding to each of the conference participants changes, new first location information is obtained through a first location determination model based on the third location information and the first location information, wherein the first location determination model is a machine learning model; The virtual camera is adjusted based on the new first position information, and the front field of view of the adjusted virtual camera is not blocked by the virtual image.

2. The device according to claim 1, characterized in that The control unit is further configured to: Based on the first position information, determining second position information of a target rendering point in the image processing unit; Based on the second position information, controlling the image processing unit to add the target rendering point and generate rendering data corresponding to the target rendering point; The rendering data is determined as the initial conference recording data.

3. The device according to claim 1, characterized in that The control unit is further configured to: Obtain meeting information of virtual meetings and personnel information of participants; Determine, based on the meeting information, the personnel information, and the first location information, a target rendering strategy for controlling the image processing unit to generate the initial meeting recording data; The image processing unit is controlled to generate the initial conference recording data based on the target rendering strategy.

4. A conference recording method, characterized in that: include: Acquiring conference recording requirement information, wherein the requirement information includes first position information of a virtual camera in a virtual conference space; Based on the demand information, control the image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data; Based on the storage information, obtaining the initial conference recording data stored in the storage unit; Based on the initial conference recording data, generating target conference recording data and sending the data to the target terminal; The method further comprises: Monitoring third position information of a virtual image corresponding to a conference participant in the virtual conference space, wherein the third position information includes angle information of the virtual image in the virtual conference space and coordinate information of a plurality of preset skeleton key points of the virtual image in the virtual conference space; When the third location information corresponding to each of the conference participants changes, new first location information is obtained through a first location determination model based on the third location information and the first location information, wherein the first location determination model is a machine learning model; The virtual camera is adjusted based on the new first position information, and the front field of view of the adjusted virtual camera is not blocked by the virtual image.

5. The method according to claim 4, characterized in that Based on the demand information, controlling the image processing unit to generate initial conference recording data includes: Based on the first position information, determining second position information of a target rendering point in the image processing unit; Based on the second position information, controlling the image processing unit to add the target rendering point and generate rendering data corresponding to the target rendering point; The rendering data is determined as the initial conference recording data.

6. The method according to claim 5, characterized in that Based on the demand information, controlling the image processing unit to generate initial conference recording data includes: Obtain meeting information of virtual meetings and personnel information of participants; Determine, based on the meeting information, the personnel information, and the first location information, a target rendering strategy for controlling the image processing unit to generate the initial meeting recording data; The image processing unit is controlled to generate the initial conference recording data based on the target rendering strategy.

7. A conference recording system, characterized in that: include: A first acquisition module, configured to acquire demand information for conference recording, wherein the demand information includes first position information of a virtual camera in a virtual conference space; A control module, configured to control the image processing unit to generate initial conference recording data and obtain storage information of the initial conference recording data based on the demand information; A second acquisition module, configured to obtain the initial conference recording data stored in the storage unit based on the storage information; A generating module is used to generate target conference recording data based on the initial conference recording data and send the target conference recording data to the target terminal: So the first acquisition module is also used for: Monitoring third position information of a virtual image corresponding to a conference participant in the virtual conference space, wherein the third position information includes angle information of the virtual image in the virtual conference space and coordinate information of a plurality of preset skeleton key points of the virtual image in the virtual conference space; When the third location information corresponding to each of the conference participants changes, new first location information is obtained through a first location determination model based on the third location information and the first location information, wherein the first location determination model is a machine learning model; The virtual camera is adjusted based on the new first position information, and the front field of view of the adjusted virtual camera is not blocked by the virtual image.

8. A computer-readable storage medium storing computer instructions, which, when executed by a processor, implements the conference recording method as described in any one of claims 4 to 6.

Images