Electronic device and method for determining speaker

Abstract

The present application discloses an electronic device and a method for determining a speaker, and relates to the technical field of collaborative conferences. The electronic device of this embodiment includes a communication unit and a processor; the communication unit is used to transmit data with a connected user device; the processor is used to respond to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participants include the current speaker and ordinary participants, and the user characteristics include facial features and / or voiceprint features; the user characteristics of each participant are feature matched with the user characteristics of the uploading user; if the user characteristics of a participant successfully match the user characteristics of the uploading user, the successfully matched participant is determined as the new speaker. The above embodiment efficiently and intelligently completes the speaker switching without interrupting the meeting.

Description

Technical Field

[0001] The present application relates to the technical field of collaborative conferences, and in particular to an electronic device and a method for determining a speaker. Background Art

[0002] With the development of technology, video collaborative conferences are becoming more and more popular. Video collaborative conferences refer to the process in which participants jointly analyze and discuss the displayed images. The speaker among the participants can control the permissions of other ordinary participants and enable participants to browse the conference content in real time by operating files, such as sharing presentation documents, the speaker's desktop, controlling the whiteboard, switching interface layout, etc. During the video collaborative conference, the speaker can be switched, that is, the speaker can be changed.

[0003] In the related technology, the meeting needs to be interrupted and the speaker can be changed only after interaction between the current speaker and ordinary participants. For example, the current speaker transfers the speaker's rights to ordinary participants, and after the ordinary participants confirm, the speaker's rights are transferred; or, the ordinary participants actively apply for the speaker's rights, and after the current speaker confirms, the speaker's rights are transferred.

[0004] However, the process of switching the speaker in the above solution is relatively complicated. Summary of the invention

[0005] The present application provides an electronic device and a method for determining a speaker, which are used to efficiently and intelligently complete the switching of the speaker.

[0006] In a first aspect, an embodiment of the present application provides an electronic device, including: a communication unit and a processor;

[0007] The communication unit is used to perform data transmission with a connected user equipment;

[0008] The processor is used to respond to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participants include the current speaker and ordinary participants, and the user characteristics include facial characteristics and / or voiceprint characteristics;

[0009] Matching the user characteristics of each participant with the user characteristics of the uploading user;

[0010] If the user characteristics of a participant successfully match the user characteristics of the uploading user, the participant who successfully matches will be determined as the new speaker.

[0011] In the above scheme, since in an image collaborative conference, the user who uploaded the image is usually required to introduce the image first, therefore, when switching images, the user characteristics of the uploading user corresponding to the switched image and the user characteristics of the current participants of the meeting are determined, and feature matching is performed to determine whether the user characteristics of the participant successfully match the user characteristics of the uploading user. If so, it means that the participant is the person who uploaded the image, and the participant can be determined as the new speaker to introduce the image, thereby completing the speaker switching efficiently and intelligently without interrupting the meeting.

[0012] In some exemplary embodiments, the processor is specifically configured to:

[0013] Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user;

[0014] If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

[0015] The above scheme determines the similarity between the user characteristics of each participant and the user characteristics of the uploading user; if the similarity between the user characteristics of a participant and the user characteristics of the uploading user reaches a preset similarity threshold, it means that the user characteristics of the participant are highly similar to the user characteristics of the uploading user, and the user characteristics are matched successfully.

[0016] In some exemplary embodiments, the processor is further configured to:

[0017] In response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

[0018] In the above scheme, since in the image collaborative conference, even if the image is not switched, the speaker switching is also involved, when ordinary participants have the need to be the speaker, they can actively trigger the first switching instruction to achieve the speaker switching.

[0019] In some exemplary embodiments, the first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information.

[0020] In some exemplary implementations, before determining the ordinary participant as a new presenter, the processor is further configured to:

[0021] It is determined that the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered.

[0022] In the above scheme, since the above-mentioned first switching instruction is actively triggered by an ordinary participant, the current speaker may still be performing the speaking operation when the first switching instruction is triggered. By determining that the current speaker has not performed the speaking operation within a preset time after the first switching instruction is triggered before performing the speaking switch, the occurrence of interrupting the speaking operation is reduced.

[0023] In some exemplary embodiments, the processor is further configured to:

[0024] In response to a second switching instruction triggered by the current speaker, a target ordinary participant corresponding to the second switching instruction is determined as a new speaker.

[0025] In the above scheme, since in the video collaborative conference, even if the video is not switched, the speaker switching is also involved, when the current speaker needs the assistance of ordinary participants, the second switching instruction can be triggered to designate the target ordinary participant as the new speaker.

[0026] In some exemplary embodiments, the second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier.

[0027] In some exemplary implementations, before determining the target ordinary participant corresponding to the second switching instruction as the new presenter, the processor is further configured to:

[0028] Determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier;

[0029] If the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, the ordinary participant is determined as the target ordinary participant.

[0030] In the above scheme, since the second switching instruction is triggered by the current speaker, after the second switching instruction is triggered, it is necessary to determine the target ordinary participant from the current ordinary participants, and accurately determine the target ordinary participant from the current ordinary participants through the similarity of user characteristics.

[0031] In a second aspect, an embodiment of the present application provides a method for determining a speaker, the method comprising:

[0032] In response to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participant includes the current presenter and ordinary participants, and the user characteristics include facial characteristics and / or voiceprint characteristics;

[0033] Matching the user characteristics of each participant with the user characteristics of the uploading user;

[0034] If the user characteristics of a participant successfully match the user characteristics of the uploading user, the participant who successfully matches will be determined as the new speaker.

[0035] In some exemplary implementations, the user characteristics of each participant are matched with the user characteristics of the uploading user, including:

[0036] Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user;

[0037] If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

[0038] In some exemplary embodiments, the method further comprises:

[0039] In response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

[0040] In some exemplary embodiments, the first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information.

[0041] In some exemplary implementations, before determining the ordinary participant as a new speaker, the method further includes:

[0042] It is determined that the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered.

[0043] In some exemplary embodiments, the method further comprises:

[0044] In response to a second switching instruction triggered by the current speaker, a target ordinary participant corresponding to the second switching instruction is determined as a new speaker.

[0045] In some exemplary embodiments, the second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier.

[0046] In some exemplary implementations, before determining the target ordinary participant corresponding to the second switching instruction as the new presenter, the method further includes:

[0047] Determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier;

[0048] If the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, the ordinary participant is determined as the target ordinary participant.

[0049] In a third aspect, an embodiment of the present application provides a device for determining a speaker, the device comprising:

[0050] A feature processing module, for responding to an image switching instruction in a multi-person conference, determining a user feature of an uploading user corresponding to the switched image, and user features of each current participant of the conference; the participant includes the current presenter and ordinary participants, and the user features include facial features and / or voiceprint features;

[0051] The feature processing module is also used to perform feature matching between the user features of each participant and the user features of the uploading user;

[0052] The speaker switching module is used to determine the successfully matched participant as the new speaker if the user characteristics of the participant successfully match the user characteristics of the uploading user.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining a speaker as described in any one of the second aspects above.

[0054] In addition, the technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by different implementation methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0056] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a flow chart of a first method for determining a speaker provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of a user interface provided in an embodiment of the present application;

[0059] Figure 4 A flowchart of a second method for determining a speaker provided in an embodiment of the present application;

[0060] Figure 5 A schematic diagram of a flow chart of a third method for determining a speaker provided in an embodiment of the present application;

[0061] Figure 6 A schematic diagram of a speaker determination device provided in an embodiment of the present application;

[0062] Figure 7 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0064] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0065] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0066] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal connection of two devices. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0067] An image collaboration meeting is a process in which multiple participants communicate via audio and video to analyze and discuss the displayed images together. Before the image collaboration meeting begins, participants upload multiple images in advance. After the image collaboration meeting begins, participants analyze and discuss the images one by one.

[0068] The speaker among the participants can control the permissions of other ordinary participants and enable the participants to browse the meeting content in real time by operating files, such as sharing presentation documents, the speaker's desktop, controlling the whiteboard, switching the interface layout, etc. During the video collaborative conference, the speaker can be switched, that is, the speaker can be changed. For example, during the presentation of a certain video, a participant first expresses his or her views as the speaker, and then through the speaker switching, another person expresses his or her views as the new speaker.

[0069] In some embodiments, the meeting needs to be interrupted first, and then the current speaker transfers the speaker's authority to ordinary participants. After the ordinary participants confirm, the speaker's authority is transferred; in other embodiments, the meeting needs to be interrupted first, and ordinary participants actively apply for the speaker's authority. After the current speaker confirms, the speaker's authority is transferred.

[0070] It can be seen that the above two speaker switching methods not only require multiple interactions between participants, but also require the conference to be interrupted. After the speaker switching is completed, the conference can be continued. In some scenarios, such as medical imaging collaborative conferences, interrupting the meeting will interrupt the doctor's thinking and affect the analysis of the patient's condition. In summary, the above speaker switching process is relatively cumbersome.

[0071] In view of this, an embodiment of the present application proposes an electronic device and a method for determining a speaker, which responds to an image switching command in a multi-person conference, determines the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; matches the user characteristics of each participant with the user characteristics of the uploading user; if the user characteristics of a participant successfully match the user characteristics of the uploading user, the successfully matched participant is determined as the new speaker.

[0072] In an image collaborative conference, the user who uploaded the image is usually required to introduce the image first. Therefore, when switching images, the user characteristics of the uploading user corresponding to the switched image and the user characteristics of the current participants of the meeting are determined, and feature matching is performed to determine whether the user characteristics of a participant successfully match the user characteristics of the uploading user. If so, it means that the participant is the person who uploaded the image. The participant can be determined as the new speaker so that he or she can introduce the image, thereby completing the speaker switching efficiently and intelligently without interrupting the meeting.

[0073] See also Figure 1 FIG. 2 is an application scenario provided by the present embodiment, wherein the scenario includes an electronic device 200 and multiple user devices connected to the electronic device 200, and the multiple user devices are related to the same multi-person conference. Figure 1Three user devices: user device 101, user device 102, and user device 103 are used as an example for description. In actual applications, the number of user devices related to the same multi-person conference may be more or less.

[0074] Data can be transmitted between the electronic device and each user device through a variety of communication methods, such as: Local Area Network (LAN), Wireless Local Area Network (WLAN) or other networks.

[0075] The electronic device can respond to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, receive the current user information of each participant sent by a user device related to the conference, and determine the user characteristics of each participant based on the user information of each participant;

[0076] It is also possible to perform feature matching between the user characteristics of each participant and the user characteristics of the uploading user;

[0077] If the user characteristics of a conference participant successfully match the user characteristics of the uploading user, the conference participant who successfully matches can also be determined as a new speaker.

[0078] In an embodiment of the present application, the user device is provided with a camera and / or a microphone, and may be a mobile phone, a tablet computer, a wearable device, a laptop computer, a television, or other device.

[0079] The electronic device mentioned above includes one or more groups of servers, and the servers may be of one type or multiple types.

[0080] The above application scenarios are only examples of application scenarios for implementing the embodiments of the present application, and the embodiments of the present application are not limited to the above application scenarios.

[0081] The following will be combined with the accompanying drawings and specific embodiments to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0082] The present application embodiment provides a first method for determining a speaker, which can be applied to the above electronic device, such as Figure 2 As shown, the following steps are included:

[0083] Step S201: In response to an image switching instruction in a multi-person conference, determining the user characteristics of the uploading user corresponding to the switched image and the user characteristics of each current participant of the conference.

[0084] The participants include the current speaker and ordinary participants, and the user features include facial features and / or voiceprint features.

[0085] Exemplarily, before the image collaboration meeting begins, a meeting task is created and relevant information of the meeting is set, such as participant identification, meeting start time, meeting end time, etc.; after the meeting task is created, the images that need to be displayed in the meeting are uploaded; in the image collaboration meeting, participants need to analyze and discuss the multiple images displayed in turn.

[0086] In an image collaborative conference, the user who uploaded the image is usually required to introduce the image first. Therefore, when switching images, the user who uploaded the image needs to be determined from the current participants and made the user the presenter so that he or she can introduce the image.

[0087] In this embodiment, when switching images, based on the user characteristics of the uploading user corresponding to the switched image and the user characteristics of each current conference participant, the uploading user of the image can be quickly and accurately determined from the current conference participants.

[0088] The user characteristics of the uploading user may be determined by, but not limited to, the following methods:

[0089] Determine the uploading user ID corresponding to uploading the image;

[0090] The user feature corresponding to the uploading user identifier is obtained from the database, and the user feature is determined as the user feature of the uploading user.

[0091] The user characteristics of each current participant may be determined by, but not limited to, the following methods:

[0092] Receive user information of current participants collected by user devices related to the conference;

[0093] Feature extraction is performed based on the user information of each participant to determine the user features of each participant.

[0094] Among them, user information may include facial images and / or voice. If the user information is a facial image, the corresponding user feature is the facial feature; if the user information is voice, the corresponding user feature is the voiceprint feature; if the user information is a facial image and voice, the corresponding user feature is the facial feature and the voiceprint feature.

[0095] The above method of determining the user characteristics of the uploading user and the user characteristics of each participant is only an example, and the present application is not limited thereto.

[0096] This embodiment does not limit the triggering method of the above-mentioned image switching instruction. For example, the current speaker triggers the image switching instruction by clicking a button representing image switching in the user device. Figure 3 As shown, the button representing switching images may be a “show previous image” or a “show next image” button in the user interface.

[0097] Figure 3 This is just an exemplary description of the user interface. The button representing switching images may be other similar buttons, and this application does not make any specific limitation on this.

[0098] Step S202: matching the user characteristics of each participant with the user characteristics of the uploading user.

[0099] In this embodiment, it is necessary to determine the user who uploaded the image from the current participants based on the user characteristics. Based on this, it is necessary to perform feature matching between the user characteristics of each participant and the user characteristics of the uploading user.

[0100] In some optional implementations, the user characteristics of each participant are matched with the user characteristics of the uploading user, which can be achieved by:

[0101] Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user;

[0102] If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

[0103] Since user characteristics are specific and stable, the user characteristics of the same user will basically not change, and the similarity is high; the user characteristics of different users are quite different, and the similarity is low. Based on this, the user who uploaded the image can be determined from the current participants through the similarity of user characteristics.

[0104] In this embodiment, the similarity between the user characteristics of each participant and the user characteristics of the uploading user is determined; if the similarity between the user characteristics of a participant and the user characteristics of the uploading user reaches a preset similarity threshold, it means that the user characteristics of the participant are highly similar to the user characteristics of the uploading user, and the user characteristics are matched successfully.

[0105] Step S203: If the user characteristics of a conference participant successfully match the user characteristics of the uploading user, the successfully matched conference participant is determined as a new speaker.

[0106] As described above, user characteristics are specific and stable. If the user characteristics of a participant successfully match the user characteristics of the uploading user, it means that the participant is likely to be the uploading user. Based on this, the new speaker can be determined more accurately.

[0107] In the above scheme, since in an image collaborative conference, the user who uploaded the image is usually required to introduce the image first, therefore, when switching images, the user characteristics of the uploading user corresponding to the switched image and the user characteristics of the current participants of the meeting are determined, and feature matching is performed to determine whether the user characteristics of the participant successfully match the user characteristics of the uploading user. If so, it means that the participant is the person who uploaded the image, and the participant can be determined as the new speaker to introduce the image, thereby completing the speaker switching efficiently and intelligently without interrupting the meeting.

[0108] In addition, the uploading user may not be in front of the user device. In this case, no user characteristics of the participant successfully match the user characteristics of the uploading user, that is, the uploading user cannot be determined from the current participants, and the speaker switching is no longer performed.

[0109] In an image collaboration meeting, not only does the uploading user need to introduce the image, but after the introduction, other participants are usually required to discuss it, that is, other participants can express their opinions on the image (for example, in a medical image collaboration meeting, doctors express their opinions on the cases involved in the image). Therefore, when the image is not switched, the speaker switching will also be involved.

[0110] Based on this, in some optional implementations, in response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

[0111] In this embodiment, when an ordinary participant has a need to be a speaker, he or she can actively trigger the first switching instruction to switch to being the speaker.

[0112] In some exemplary embodiments, the first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information. For example:

[0113] 1) When an ordinary participant needs to give a presentation, he makes a target gesture, and the user device collects an image containing the target gesture, triggering a first switching instruction;

[0114] This embodiment does not limit the specific implementation method of the target gesture, such as raising hands, crossing hands, etc.;

[0115] 2) When a common participant needs to give a speech, he / she speaks the first key information, and the user device collects the voice containing the first key information. The electronic device converts the voice into text through the automatic speech recognition (ASR) technology, thereby triggering the first switching instruction;

[0116] This embodiment does not limit the specific implementation method of the first key information, for example, it can be "discussion", "suggestion", etc.;

[0117] 3) When an ordinary participant needs to give a presentation, he / she makes a target gesture and speaks the first key information. The user device collects an image containing the target gesture and a voice containing the first key information, triggering a first switching instruction.

[0118] The triggering method of the above-mentioned first switching instruction is only an exemplary description, and the present application is not limited thereto.

[0119] In the above scheme, since in the image collaborative conference, even if the image is not switched, the speaker switching is also involved, when ordinary participants have the need to be the speaker, they can actively trigger the first switching instruction to achieve the speaker switching.

[0120] Since the first switching instruction is actively triggered by an ordinary participant, when the first switching instruction is triggered, the current speaker may still be performing the speaking operation, such as speaking or switching interfaces. If the speaker is switched at this time, the speaking operation will be interrupted.

[0121] Based on this, on the basis of the above embodiments, Figure 4 The flowchart of the second method for determining a speaker provided in the embodiment of the present application includes the following steps:

[0122] Step S401: In response to a first switching instruction triggered by any current ordinary participant, it is determined that the current speaker has not performed a speaking operation within a preset time period after the first switching instruction is triggered.

[0123] In this embodiment, if the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered, it means that the speaking operation will not be interrupted if the speaker is switched at this time.

[0124] The above preset duration can be set according to the actual application scenario, and this application does not make any specific limitations on this.

[0125] Step S402: Determine the ordinary participant as a new speaker.

[0126] The specific implementation of step S402 can refer to the above embodiment and will not be described again here.

[0127] In the above scheme, since the above-mentioned first switching instruction is actively triggered by an ordinary participant, the current speaker may still be performing the speaking operation when the first switching instruction is triggered. By determining that the current speaker has not performed the speaking operation within a preset time after the first switching instruction is triggered before performing the speaking switch, the occurrence of interrupting the speaking operation is reduced.

[0128] As described above, when the image is not switched, the speaker switching is also involved. Based on this, in some optional implementations, in response to the second switching instruction triggered by the current speaker, the target ordinary participant corresponding to the second switching instruction is determined as the new speaker.

[0129] In this embodiment, since the current speaker may need the assistance of ordinary participants, for example, in a medical image collaborative meeting, after the uploading user has introduced the image, he needs the assistance of a senior doctor for diagnosis; or after a doctor has expressed his own opinion, he wants to listen to the opinions of other doctors. Based on this, when the current speaker needs the assistance of ordinary participants, the second switching instruction can be triggered to designate the target ordinary participant as the new speaker.

[0130] In some exemplary implementations, the second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier. For example:

[0131] When the current presenter needs assistance from the target ordinary participant, the presenter speaks the second key information and the target ordinary participant identifier, and the user device collects the voice including the second key information and the target ordinary participant identifier, triggering the second switching instruction;

[0132] This embodiment does not limit the specific implementation method of the second key information, which may be "discussion", "suggestion", "assistance", etc. The second key information may be the same as or different from the above-mentioned first key information, and this application does not make specific limitations on this.

[0133] The triggering method of the second switching instruction mentioned above is only an exemplary description, and the present application is not limited thereto.

[0134] In the above scheme, since in the video collaborative conference, even if the video is not switched, the speaker switching is also involved, when the current speaker needs the assistance of ordinary participants, the second switching instruction can be triggered to designate the target ordinary participant as the new speaker.

[0135] Since the second switching instruction is triggered by the current speaker, after the second switching instruction is triggered, it is necessary to determine the target ordinary participant from the current ordinary participants.

[0136] Based on this, on the basis of the above embodiments, Figure 5The flowchart of the third method for determining a speaker provided in the embodiment of the present application includes the following steps:

[0137] Step S501: In response to the second switching instruction triggered by the current speaker, determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier; if the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, then determine the ordinary participant as the target ordinary participant.

[0138] As mentioned above, user characteristics are specific and stable. The user characteristics of the same user will basically not change, and the similarity is high; the user characteristics of different users are quite different, and the similarity is low. Based on this, the target ordinary participants can be determined from the current ordinary participants through the similarity of user characteristics.

[0139] The method for determining the user characteristics of each current ordinary participant can refer to the method for determining the user characteristics of each current conference participant mentioned above, which will not be repeated here.

[0140] In this embodiment, the user characteristics corresponding to the target ordinary participant identification may be obtained from the database.

[0141] Step S502: Determine the target ordinary participant as a new speaker.

[0142] The specific implementation of step S502 can refer to the above embodiment and will not be described again here.

[0143] In the above scheme, since the second switching instruction is triggered by the current speaker, after the second switching instruction is triggered, it is necessary to determine the target ordinary participant from the current ordinary participants, and accurately determine the target ordinary participant from the current ordinary participants through the similarity of user characteristics.

[0144] In addition, the target ordinary participant may not be in front of the user device. In this case, no ordinary participant's user characteristics will successfully match the user characteristics corresponding to the target ordinary participant's identifier, that is, the target ordinary participant cannot be determined from the current ordinary participants, and the speaker switching will no longer be performed.

[0145] like Figure 6 As shown, based on the same inventive concept, an embodiment of the present application provides a main speaker determination device 600 , including: a feature processing module 601 and a main speaker switching module 602 .

[0146] The feature processing module 601 is used to respond to the image switching instruction in the multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participant includes the current speaker and ordinary participants, and the user characteristics include facial features and / or voiceprint features;

[0147] The feature processing module 601 is also used to perform feature matching between the user features of each participant and the user features of the uploading user;

[0148] The speaker switching module 602 is used to determine the successfully matched participant as the new speaker if the user characteristics of the participant successfully match the user characteristics of the uploading user.

[0149] In some exemplary embodiments, the feature processing module 601 is specifically configured to:

[0150] Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user;

[0151] If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

[0152] In some exemplary implementations, the speaker switching module 602 is further configured to:

[0153] In response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

[0154] In some exemplary embodiments, the first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information.

[0155] In some exemplary implementations, before determining the ordinary participant as a new speaker, the speaker switching module 602 is further configured to:

[0156] It is determined that the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered.

[0157] In some exemplary implementations, the speaker switching module 602 is further configured to:

[0158] In response to a second switching instruction triggered by the current speaker, a target ordinary participant corresponding to the second switching instruction is determined as a new speaker.

[0159] In some exemplary embodiments, the second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier.

[0160] In some exemplary implementations, before the speaker switching module 602 determines the target ordinary participant corresponding to the second switching instruction as the new speaker, the feature processing module 601 is further configured to:

[0161] Determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier;

[0162] If the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, the ordinary participant is determined as the target ordinary participant.

[0163] Since the device is the device in the method in the embodiment of the present application, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0164] like Figure 7 As shown, based on the same inventive concept, an embodiment of the present application provides an electronic device 700 including: a processor 701 and a memory 702 .

[0165] The electronic device mentioned above also includes a communication unit for performing data transmission with a connected user device.

[0166] The memory 702 may be a volatile memory, such as a random-access memory (RAM); the memory 702 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 702 may be any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 702 may be a combination of the above memories.

[0167] The processor 701 may include one or more central processing units (CPU), graphics processing units (GPU) or digital processing units, etc.

[0168] The specific connection medium between the memory 702 and the processor 701 is not limited in the embodiment of the present application. Figure 7In the embodiment, the memory 702 and the processor 701 are connected via a bus 703. The bus 703 is connected to the processor 701 via a bus 703. Figure 7 In the figure, the bus 703 is shown by a bold line, and can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0169] The memory 702 stores program codes. When the program codes are executed by the processor 701, the processor 701 performs the following process:

[0170] In response to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participant includes the current presenter and ordinary participants, and the user characteristics include facial characteristics and / or voiceprint characteristics;

[0171] Matching the user characteristics of each participant with the user characteristics of the uploading user;

[0172] If the user characteristics of a participant successfully match the user characteristics of the uploading user, the participant who successfully matches will be determined as the new speaker.

[0173] In some exemplary embodiments, the processor is specifically configured to:

[0174] Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user;

[0175] If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

[0176] In some exemplary embodiments, the processor is further configured to:

[0177] In response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

[0178] In some exemplary embodiments, the first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information.

[0179] In some exemplary implementations, before determining the ordinary participant as a new presenter, the processor is further configured to:

[0180] It is determined that the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered.

[0181] In some exemplary embodiments, the processor is further configured to:

[0182] In response to a second switching instruction triggered by the current speaker, a target ordinary participant corresponding to the second switching instruction is determined as a new speaker.

[0183] In some exemplary embodiments, the second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier.

[0184] In some exemplary implementations, before determining the target ordinary participant corresponding to the second switching instruction as the new presenter, the processor is further configured to:

[0185] Determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier;

[0186] If the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, the ordinary participant is determined as the target ordinary participant.

[0187] Since the electronic device is the electronic device in the method in the embodiment of the present application, and the principle of solving the problem by the electronic device is similar to that of the method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0188] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above-mentioned main speaker determination method are implemented. The readable storage medium may be a non-volatile readable storage medium.

[0189] The present application is described above with reference to the block diagrams and / or flow charts showing the methods, devices (systems) and / or computer program products according to the embodiments of the present application. It should be understood that a block of the block diagram and / or flow chart diagram and a combination of blocks of the block diagram and / or flow chart diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer and / or other programmable data processing device to produce a machine, so that the instructions executed by the computer processor and / or other programmable data processing device create a method for implementing the functions / actions specified in the block diagram and / or flow chart block.

[0190] Accordingly, the present application may also be implemented with hardware and / or software (including firmware, resident software, microcode, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium, which has a computer-usable or computer-readable program code implemented in the medium, for use by an instruction execution system or in conjunction with an instruction execution system. In the context of the present application, a computer-usable or computer-readable medium may be any medium that may contain, store, communicate, transmit, or convey a program for use by an instruction execution system, device, or apparatus, or in conjunction with an instruction execution system, device, or apparatus.

[0191] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An electronic device, characterized in that: include: a communication unit and a processor; The communication unit is used to perform data transmission with a connected user equipment; The processor is used to respond to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participants include the current speaker and ordinary participants, and the user characteristics include facial features and / or voiceprint features; feature match the user characteristics of each participant with the user characteristics of the uploading user; if the user characteristics of a participant successfully match the user characteristics of the uploading user, the successfully matched participant is determined as the new speaker.

2. The electronic device according to claim 1, characterized in that: The processor is specifically used for: Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user; If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

3. The electronic device according to claim 1, characterized in that: The processor is further configured to: In response to a first switching instruction triggered by any current ordinary participant, the ordinary participant is determined as a new speaker.

4. The electronic device according to claim 3, characterized in that: The first switching instruction is triggered by an image containing a target gesture and / or a voice containing the first key information.

5. The electronic device according to claim 3, characterized in that: Before determining the ordinary participant as a new presenter, the processor is further configured to: It is determined that the current speaker does not perform a speaking operation within a preset time period after the first switching instruction is triggered.

6. The electronic device according to claim 1, characterized in that: The processor is further configured to: In response to a second switching instruction triggered by the current speaker, a target ordinary participant corresponding to the second switching instruction is determined as a new speaker.

7. The electronic device according to claim 6, characterized in that: The second switching instruction is triggered by a voice message containing the second key information and the target ordinary participant identifier.

8. The electronic device according to claim 7, characterized in that: Before determining the target ordinary participant corresponding to the second switching instruction as the new presenter, the processor is further configured to: Determine the similarity between the user characteristics of each current ordinary participant and the user characteristics corresponding to the target ordinary participant identifier; If the similarity between the user characteristics of an ordinary participant and the user characteristics corresponding to the target ordinary participant identifier reaches a preset similarity threshold, the ordinary participant is determined as the target ordinary participant.

9. A method for determining a speaker, characterized in that: The method comprises: In response to an image switching instruction in a multi-person conference, determine the user characteristics of the uploading user corresponding to the switched image, and the user characteristics of each current participant of the conference; the participant includes the current presenter and ordinary participants, and the user characteristics include facial characteristics and / or voiceprint characteristics; Matching the user characteristics of each participant with the user characteristics of the uploading user; If the user characteristics of a participant successfully match the user characteristics of the uploading user, the participant who successfully matches will be determined as the new speaker.

10. The method according to claim 9, characterized in that Matching the user characteristics of each participant with the user characteristics of the uploading user includes: Determine the similarity between the user characteristics of each participant and the user characteristics of the uploading user; If the similarity between the user characteristics of a conference participant and the user characteristics of the uploading user reaches a preset similarity threshold, it is determined that the user characteristics of the conference participant and the user characteristics of the uploading user are successfully matched.

Images