A method, device, equipment and storage medium for recording conference content

Abstract

The present application discloses a method, device, equipment and storage medium for recording conference content. The method comprises: receiving a conference video; determining an action area of ​​a target action in the conference video; determining an identification of the target action based on facial image information of a facial area closest to the action area; and generating conference content based on the identification of the target action and target expression information of the target action. The method realizes automatic recording of conference content for deaf-mute people, reduces the workload of conference recorders, and improves the efficiency of recording conference content.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a method, apparatus, device and storage medium for recording conference content. Background Art

[0002] Currently, conference minutes are usually recorded by using microphones or other equipment to record the speeches of each participant during the meeting. After the meeting, the participants and their speeches are sorted and recorded by playing the recordings.

[0003] However, in the above solution, if the participant is a deaf-mute who is unable to speak, he or she communicates with other deaf-mute people through gestures. In this process, the deaf-mute person conveys information to other deaf-mute people through gestures, and thus the microphone will not be able to collect sound signals.

[0004] Based on this, the industry urgently needs a method to record the meeting content of the deaf and mute people. Summary of the Invention

[0005] To address the above technical issues, this application provides a method, device, equipment, and storage medium for recording meeting content. This method automatically generates information about the deaf-mute person and the content they express by recognizing their target movements and facial information, effectively solving the problem of recording meeting content for deaf-mute individuals.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] In a first aspect, the present application provides a method for recording meeting content, comprising:

[0008] Receive conference videos;

[0009] Determining an action area of ​​a target action in the conference video;

[0010] determining an identifier of the target action based on facial image information of a facial area closest to the action area;

[0011] Conference content is generated according to the identifier of the target action and the target expression information of the target action.

[0012] Optionally, determining the identifier of the target action based on facial image information of a facial area closest to the action area includes:

[0013] Determine the center point of the action area and the center points of N face areas; where N ≥ 1 and N is an integer;

[0014] If N=1, obtaining first facial image information of a facial region; determining the identifier of the target action based on the first facial image information;

[0015] If N>1, obtain the distance between the center point of the action area and the center point of each face area, determine the center point of the face area closest to the center point of the action area, and obtain the second face image information corresponding to the center point of the face area closest to the center point of the action area; determine the identifier of the target action based on the second face image information.

[0016] Optionally, generating conference content according to the identifier of the target action and the expression information of the target action includes:

[0017] Get the mapping relationship between actions and expression information;

[0018] Determining target expression information corresponding to the target action according to the mapping relationship;

[0019] The target expression information is bound to the identifier of the target action to generate conference content.

[0020] Optionally, the identifier of the target action includes the name of the target object or the work number of the target object.

[0021] Optionally, the target action includes arm action and / or lip action.

[0022] Optionally, the method further includes:

[0023] The conference content is presented.

[0024] Optionally, the method further includes:

[0025] Receive user configuration information;

[0026] The conference content is exported according to the file format indicated by the configuration information.

[0027] In a second aspect, the present application provides a device for recording conference content, comprising: a receiving module, a processing module, and a generating module;

[0028] The receiving module is used to receive the conference video;

[0029] The processing module is configured to determine an action area of ​​a target action in the conference video; and determine an identifier of the target action based on facial image information of a facial area closest to the action area.

[0030] The generating module is used to generate conference content according to the identifier of the target action and the target expression information of the target action.

[0031] Optionally, the processing module is specifically configured to determine the center point of the action area and the center points of N face areas; wherein N≥1, and N is an integer;

[0032] If N=1, obtaining first facial image information of a facial region; determining the identifier of the target action based on the first facial image information;

[0033] If N>1, obtain the distance between the center point of the action area and the center point of each face area, determine the center point of the face area closest to the center point of the action area, and obtain the second face image information corresponding to the center point of the face area closest to the center point of the action area; determine the identifier of the target action based on the second face image information.

[0034] Optionally, the generation module is specifically used to obtain a mapping relationship between action and expression information; determine the target expression information corresponding to the target action based on the mapping relationship; bind the target expression information with the identifier of the target action to generate meeting content.

[0035] Optionally, the identifier of the target action includes the name of the target object or the work number of the target object.

[0036] Optionally, the target action includes arm action and / or lip action.

[0037] Optionally, the device further includes: a display module;

[0038] The display module is used to present the conference content.

[0039] Optionally, the device further includes: an export module;

[0040] The receiving module is specifically used to receive the user's configuration information;

[0041] The export module is configured to export the conference content according to the file format indicated by the configuration information.

[0042] In a third aspect, the present application provides a device for recording conference content, the device comprising: a memory and a processor;

[0043] The memory is used to store a computer program and transmit the computer program to the processor;

[0044] The processor executes the method according to any one of the instructions in the computer program.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium for storing computer software instructions. When the computer-readable storage medium is run on a computer, the computer can execute any of the methods described in the first aspect above.

[0046] It can be seen from the above technical solution that this application has the following beneficial effects:

[0047] The present application provides a method, apparatus, device and storage medium for recording conference content. The method includes: receiving a conference video; determining the action area of ​​a target action in the conference video; determining the identifier of the target action based on the facial image information of the facial area closest to the action area; and generating conference content based on the identifier of the target action and the target expression information of the target action. In this method, the action area of ​​the target action in the video image is determined by image recognition technology, and then the facial area closest to the action area is determined, the facial image information of the facial area is obtained, and the identifier corresponding to the facial image information is determined, that is, the identifier of the target action, which is used to describe the performer of the target action. By identifying the target action, determining the expression information of the target action, and then matching the expression information of the target action with the performer of the target action, the conference content is recorded. In this way, the method realizes the automatic recording of the conference content of the deaf and mute, reduces the workload of the meeting recorder, and improves the efficiency of recording the conference content. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0049] Figure 1 A system architecture diagram of a recording system provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of an interface of an interactive subsystem provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a conference video interface provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a conference video interface provided in an embodiment of the present application;

[0053] Figure 5A flowchart of a method for recording conference content provided in an embodiment of the present application;

[0054] Figure 6 A flowchart of another method for recording conference content provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of a device for recording conference content provided in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0058] To facilitate understanding, the technical terms involved in this application are first introduced below.

[0059] The content of a meeting refers to the speech information of the participants during the meeting. For example, the content of the meeting includes the speaker and the content of the speaker's speech. In the related art, the speaker's voice signal can be processed by sound processing technology. The name of the speaker is determined by the sound signal, and the sound signal is converted into text information for recording. However, for participants who are not convenient to speak (for example, deaf-mute people), it will not be possible to record the speech information of the participant through sound signals. Based on this, the industry is in urgent need of a method for recording the content of meetings for the deaf-mute.

[0060] In view of this, the present application provides a method for recording conference content. This method can be implemented by a recording system. Specifically, the recording system receives a conference video and determines the action area of ​​a target action in the conference video. The target action can be an arm movement (e.g., sign language, gesture) or lip movement (e.g., lip reading) of a participant. Then, the recording system determines the facial area closest to the action area, and determines the identifier of the target action based on the facial image information of the facial area. Finally, the recording system generates the conference content based on the identifier of the target action and the target expression information of the target action. This achieves the recording of the conference content.

[0061] This method uses image recognition technology to identify the action area of ​​a target action in a conference video to determine the facial area corresponding to the target action. Using the facial image information in this facial area, the method determines the identifier of the target action, which is used to identify the person performing the target action. This method also uses image recognition technology to determine the target expression information of the target action, thereby automatically identifying the text information corresponding to the target action. This method automatically associates the performer with the expression information, and can then generate the meeting content corresponding to the conference video. Therefore, this method can record the meeting content of deaf-mute individuals.

[0062] The recording system can be a software system. Specifically, the recording system can be deployed in the form of computer software on a computing device to implement the function of recording meeting content. In some embodiments, the recording system can also be a hardware system. The hardware system includes a physical device that has the function of recording meeting content.

[0063] The recording system is implemented by subsystems with different functions and units with different functions. The embodiment of the present application does not limit the division of subsystems and units within the recording system. Figure 1 An exemplary division method is shown in FIG.

[0064] like Figure 1 As shown, recording system 100 includes an interaction subsystem 120 and a recording subsystem 140. Interaction subsystem 120 is used to provide a graphical user interface (GUI) to the user and receive conference videos. Recording subsystem 140 is used to determine the action area of ​​a target action in the conference video; determine the identifier of the target action based on facial image information of the facial area closest to the action area; and generate conference content based on the identifier of the target action and the target expression information of the target action.

[0065] The interaction subsystem 120 includes a communication unit 122 and a display unit 124. The recording subsystem 140 includes a communication unit 142, a processing unit 144, and a generating unit 146. Each of these will be described below.

[0066] The communication unit 122 is used to receive the conference video. The display unit 124 is used to provide a GUI, see Figure 2 , which is a schematic diagram of the main interface of an interactive subsystem provided in an embodiment of the present application, such as Figure 2As shown, the main interface 200 includes an upload control 220. Users can use upload control 220 to input a conference video. The communication unit 122 can retrieve the conference video and then send it to the recording subsystem 140. In some implementations, the main interface 200 also includes a capture control 260, which allows users to capture the conference video in real time. The communication unit 122 then sends the conference video to the recording subsystem.

[0067] The communication unit 142 is used to receive the conference video sent by the interaction subsystem 120. The processing unit 144 is used to determine the action area of ​​the target action in the conference video. For example, the processing unit 144 can use image recognition technology to determine the action area where the target action appears in the conference video, where the target action can be an arm movement (e.g., sign language) or a lip movement (e.g., lip reading). When the processing unit 144 recognizes that the target action exists in the conference video, it then determines the action area of ​​the target action in the conference video. Figure 3 , which is a schematic diagram of an action area provided in an embodiment of the present application. Taking the target action as sign language as an example, Figure 3 As shown, the interface 300 of the conference video includes multiple participants 310. After the processing unit 144 identifies the target action 320, it can determine the area 330 of the target action.

[0068] To further determine the performer of the target action, the processing unit 144 determines the identifier of the target action based on the facial image information of the face area closest to the action area. The identifier is used to describe the performer of the target action, for example, the identifier can be a name, work number, etc.

[0069] In some implementations, the processing unit 144 determines the center point of the action area and the center points of N face areas, where N≥1 and N is an integer. For ease of understanding, take N greater than 1 as an example, see Figure 4 , which is a schematic diagram of determining the facial region closest to the action region provided by an embodiment of the present application. The conference video interface 300 includes N facial regions 3401-340N, where the center point of the action region is M, and the center points of the N facial regions are F1-FN. The processing unit 144 then determines the distance from the center point M of the action region to the center points F1-FN of each facial region, and then determines the center point Fx of the facial region with the smallest distance from the center point M of the action region. For example, Fx can be F1.

[0070] After determining the center point F1 of the facial region, processing unit 144 obtains facial image information of the facial region and determines the identifier of the target action based on the facial image information. Specifically, processing unit 144 may obtain a pre-stored mapping relationship between the facial image information of conference participants and their identifiers from a database. Then, based on the mapping relationship, processing unit 144 determines the identifier of the conference participant corresponding to the facial image information of the facial region. The identifier of the conference participant is used as the identifier of the target action, indicating that the target action is to be performed by the conference participant.

[0071] In another implementation, N=1, and the processing unit 144 obtains facial image information of a face area, and determines the identifier of the target action based on the facial image information.

[0072] The generation unit 146 is used to generate the meeting content based on the identifier of the target action and the expression information of the target action. Specifically, the processing unit 144 is also used to obtain the mapping relationship between the action and the expression information from the database, and determine the target expression information corresponding to the target action based on the mapping relationship. Then, the generation unit 146 binds the identifier of the target action with the target expression information corresponding to the target action, and then generates the meeting content. Among them, the expression information can be the meaning to be expressed by the target action. Taking the above-mentioned target action 320 as an example, the expression information of the target action 320 is "we".

[0073] In some implementations, after the generation unit 146 generates the conference content, the communication unit 142 sends the conference content to the interaction subsystem 120. The display unit 124 is also used to present the conference content through a GUI, so that the meeting recorder can browse the conference content or correct any errors in the recording.

[0074] In some implementations, the communication unit 122 is further configured to receive user configuration information, which is used to describe the file format. Specifically, the user enters the configuration information through the GUI provided by the display unit 124, and the communication unit 122 then sends the configuration information to the recording subsystem 140.

[0075] After the communication unit 142 receives the configuration information sent by the interactive subsystem, the processing unit 144 exports the conference content according to the file format indicated by the configuration information. Thus, users can export conference content according to their own personalized needs and the required file format.

[0076] Next, in order to make the technical solution of the present application clearer and easier to understand, a method for recording conference content provided by an embodiment of the present application is described in detail from the perspective of the recording system 100.

[0077] See also Figure 5The flowchart of the method for recording the meeting content shown in FIG. 1 includes:

[0078] S501: The recording system 100 receives a conference video.

[0079] The recording system 100 can receive conference videos via the GUI. The conference videos can be pre-recorded or recorded. The conference videos record the participants and their target actions. Participants express their speeches through specific target actions.

[0080] S502: The recording system 100 determines an action area of ​​a target action in the conference video.

[0081] The recording system 100 determines the action area of ​​the target action in the conference video. For example, the recording system 100 can use image recognition technology to determine the action area where the target action appears in the conference video, where the target action can be an arm movement (e.g., sign language) or a lip movement (e.g., lip reading). When the recording system 100 identifies the presence of the target action in the conference video, it then determines the action area of ​​the target action in the conference video. For the specific process, please refer to Figure 3 As shown, no further details are given here.

[0082] S503: The recording system 100 determines the identifier of the target action based on the facial image information of the face area closest to the action area.

[0083] The recording system 100 determines the center point of the action region and the center points of N face regions, where N ≥ 1 and N is an integer. The recording system processes differently depending on the value of N. Two scenarios are described below.

[0084] The first type: N=1.

[0085] Recording system 100 obtains first facial image information of a facial region and then determines the identity of the target action based on the first facial image information. Since the target video only contains a facial region, it can be determined that the target action was performed by the participant corresponding to the facial information in that facial region. In this way, recording system 100 can determine the performer of the target action, that is, which participant performed the target action.

[0086] The second type: N=2.

[0087] The recording system 100 obtains the distance between the center point of the action area and the center point of each face area, determines the center point of the face area closest to the center point of the action area, obtains the second face image information corresponding to the center point of the face area closest to the center point of the action area; and determines the identifier of the target action based on the second face image information. The specific process can be found in Figure 4 The introduction of , will not be repeated here.

[0088] The identifier of the target action includes the name of the target object or the work number of the target object.

[0089] S504: The recording system 100 generates conference content according to the identifier of the target action and the target expression information of the target action.

[0090] Specifically, the recording system 100 obtains a mapping relationship between actions and expression information, and then determines the target expression information corresponding to the target action based on the mapping relationship, binds the target expression information with the identifier of the target action, and then generates the meeting content.

[0091] The present application provides a method for recording conference content, which includes: receiving a conference video; determining the action area of ​​a target action in the conference video; determining the identifier of the target action based on the facial image information of the facial area closest to the action area; and generating conference content based on the identifier of the target action and the target expression information of the target action. In this method, the action area of ​​the target action in the video image is determined by image recognition technology, and then the facial area close to the action area is determined, the facial image information of the facial area is obtained, and the identifier corresponding to the facial image information is determined, that is, the identifier of the target action, which is used to describe the executor of the target action. By identifying the target action, determining the expression information of the target action, and then matching the expression information of the target action with the executor of the target action, the conference content is recorded. In this way, the method realizes the automatic recording of the conference content of the deaf and mute, reduces the workload of the meeting recorder, and improves the efficiency of recording the conference content.

[0092] The present application also provides a method for recording conference content. Figure 6 , based on S501-S504, the method further includes:

[0093] S601: The recording system 100 presents the conference content.

[0094] The recording system 100 can present the meeting content through the GUI. Specifically, the meeting content can be as shown in Table 1 below.

[0095] Table 1: Example of meeting content

[0096] Participant A How did we complete the tasks in the previous stage? Participant B Basically completed. Participant C Not completed. …… ……

[0097] S602: The recording system 100 exports the conference content.

[0098] In some implementations, the recording system 100 may also receive user configuration information, where the configuration information is used to specify a file format for exporting conference content, thereby supporting the user to customize the export format of conference content.

[0099] In other implementations, if the user does not enter configuration information, the recording system 100 uses default configuration information to export the meeting content. For example, the default configuration information indicates that the exported file format is a table. When the user does not enter configuration information, the recording system 100 exports the meeting content in table form.

[0100] It should be noted that there is no order in which S601 and S602 are executed. S601 may be executed first, or S602 may be executed first, or both S601 and S602 may be executed simultaneously. This embodiment does not limit the order in which S601 and S602 are executed.

[0101] Combination of the above Figures 1 to 6 The method for recording the meeting content provided in an embodiment of the present application is introduced. Next, the device for recording the meeting content provided in an embodiment of the present application and the computing device for implementing the function of the device for recording the meeting content are introduced in conjunction with the accompanying drawings.

[0102] like Figure 7 As shown, the embodiment of the present application further provides a conference content recording device 700, which is used to execute the aforementioned conference content recording method. The embodiment of the present application does not limit the division of the functional modules in the device 700. The following is an exemplary division of the functional modules:

[0103] The conference content recording device 700 includes a receiving module 702 , a processing module 704 and a generating module 706 .

[0104] The receiving module 702 is used to receive the conference video;

[0105] The processing module 704 is configured to determine an action region of a target action in the conference video; and determine an identifier of the target action based on facial image information of a facial region closest to the action region.

[0106] The generating module 706 is configured to generate conference content according to the identifier of the target action and the target expression information of the target action.

[0107] The above-mentioned conference content recording device 700 can be implemented by a computing device. Figure 8 A computing device is provided, such as Figure 8 As shown, the computing device 800 can be used to implement the above Figure 7 The function of the recording device 700 for conference content in the illustrated embodiment.

[0108] The computing device 800 includes a bus 801 , a processor 802 , a display 803 , and a memory 804 . The processor 802 , the memory 804 , and the display 803 communicate with each other via the bus 801 .

[0109] The processor 802 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0110] Display 803 is an input / output (I / O) device. It can display electronic files, such as images and text, on a screen for the user to view. Depending on the material used, display 803 can be a liquid crystal display (LCD), an organic light emitting diode (OLED), or other similar display. Specifically, display 803 can receive conference video via a user interface (GUI).

[0111] The memory 804 may include volatile memory, such as random access memory (RAM). The memory 804 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard drive (HDD), or solid state drive (SSD).

[0112] Memory 804 stores executable program code, and processor 802 executes the executable program code to perform the aforementioned method for recording conference content. Specifically, processor 802 executes the aforementioned program code to control display 803 to receive conference video via a GUI. Processor 802 then determines the action area of ​​a target action in the conference video; determines the identifier of the target action based on facial image information of the facial area closest to the action area; and generates conference content based on the identifier of the target action and the target expression information of the target action.

[0113] The present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for recording meeting content.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system embodiment described above is merely illustrative, wherein the units and modules described as separate components may or may not be physically separated. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0115] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0116] The above are only preferred embodiments of the present application and are not intended to limit the present application in any form. Although the present application has been disclosed as above with preferred embodiments, it is not intended to limit the present application. Any technician familiar with the art can use the above-disclosed methods and technical contents to make many possible changes and modifications to the technical solution of the present application without departing from the scope of the technical solution of the present application, or modify it into an equivalent embodiment with equivalent changes. Therefore, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of protection of the technical solution of the present application.

Claims

1. A method for recording conference content, characterized in that: include: Receive conference video; Determine an action area of ​​a target action in the conference video; The target movement includes an arm movement or a lip movement; Determining the identification of the target action according to the facial image information of the facial area closest to the action area; Wherein, determining the identification of the target action according to the facial image information of the facial region closest to the action region includes: determining the center point of the action region and the center points of N facial regions; wherein N≥1, and N is an integer; if N=1, obtaining the first facial image information of a facial region; determining the identification of the target action according to the first facial image information; if N>1, obtaining the distance between the center point of the action region and the center point of each facial region, determining the center point of the facial region closest to the center point of the action region, obtaining the second facial image information corresponding to the center point of the facial region closest to the center point of the action region; determining the identification of the target action according to the second facial image information; Conference content is generated according to the identifier of the target action and the target expression information of the target action.

2. The method according to claim 1, characterized in that: The generating of conference content according to the identifier of the target action and the target expression information of the target action includes: Get the mapping relationship between actions and expression information; Determining target expression information corresponding to the target action according to the mapping relationship; The target expression information is bound to the identifier of the target action to generate conference content.

3. The method according to any one of claims 1 to 2, characterized in that: The identifier of the target action includes the name of the target object or the work number of the target object.

4. The method according to any one of claims 1 to 2, characterized in that: The target motion includes an arm motion and / or a lip motion.

5. The method according to any one of claims 1 to 2, characterized in that: The method further comprises: The conference content is presented.

6. The method according to any one of claims 1 to 2, characterized in that: The method further comprises: Receive user configuration information; The conference content is exported according to the file format indicated by the configuration information.

7. A device for recording conference content, characterized in that: include: Receiving module, processing module and generating module; The receiving module is used to receive the conference video; The processing module is used to determine the action area of ​​the target action in the conference video, wherein the target action includes an arm action or a lip action; and determine the identification of the target action according to the facial image information of the facial area closest to the action area; wherein the processing module is specifically used to: determine the center point of the action area and the center points of N facial areas; wherein N≥1, and N is an integer; if N=1, obtain the first facial image information of a facial area; and determine the identification of the target action according to the first facial image information; if N>1, obtain the distance between the center point of the action area and the center point of each facial area, determine the center point of the facial area closest to the center point of the action area, and obtain the second facial image information corresponding to the center point of the facial area closest to the center point of the action area; and determine the identification of the target action according to the second facial image information; The generating module is used to generate conference content according to the identifier of the target action and the target expression information of the target action.

8. A device for recording conference content, characterized in that: The device comprises: a memory and a processor; The memory is used to store a computer program and transmit the computer program to the processor; The processor executes the method according to any one of claims 1 to 6 according to the instructions in the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store computer software instructions. When the computer-readable storage medium is run on a computer, the computer can execute the method according to any one of claims 1 to 6.

Images